{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.005689900426742532, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005689900426742532, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0005689900426742532, "eval_loss": NaN, "eval_runtime": 19.2767, "eval_samples_per_second": 38.388, "eval_steps_per_second": 19.194, "step": 1 }, { "epoch": 0.0011379800853485065, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0017069701280227596, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0017069701280227596, "eval_loss": NaN, "eval_runtime": 18.3616, "eval_samples_per_second": 40.302, "eval_steps_per_second": 20.151, "step": 3 }, { "epoch": 0.002275960170697013, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.002844950213371266, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0034139402560455193, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0034139402560455193, "eval_loss": NaN, "eval_runtime": 18.4768, "eval_samples_per_second": 40.05, "eval_steps_per_second": 20.025, "step": 6 }, { "epoch": 0.003982930298719772, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.004551920341394026, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.005120910384068279, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.005120910384068279, "eval_loss": NaN, "eval_runtime": 18.356, "eval_samples_per_second": 40.314, "eval_steps_per_second": 20.157, "step": 9 }, { "epoch": 0.005689900426742532, "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": 156783555379200.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }