{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0016649323621227888, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00016649323621227888, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.00016649323621227888, "eval_loss": NaN, "eval_runtime": 541.5183, "eval_samples_per_second": 4.67, "eval_steps_per_second": 2.336, "step": 1 }, { "epoch": 0.00033298647242455777, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0004994797086368366, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0004994797086368366, "eval_loss": NaN, "eval_runtime": 540.5845, "eval_samples_per_second": 4.678, "eval_steps_per_second": 2.34, "step": 3 }, { "epoch": 0.0006659729448491155, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0008324661810613944, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0009989594172736733, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0009989594172736733, "eval_loss": NaN, "eval_runtime": 540.514, "eval_samples_per_second": 4.679, "eval_steps_per_second": 2.34, "step": 6 }, { "epoch": 0.0011654526534859522, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.001331945889698231, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.00149843912591051, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.00149843912591051, "eval_loss": NaN, "eval_runtime": 540.6919, "eval_samples_per_second": 4.677, "eval_steps_per_second": 2.34, "step": 9 }, { "epoch": 0.0016649323621227888, "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": 2612537673646080.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }