{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.15979513444302176, "eval_steps": 10, "global_step": 39, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00409731113956466, "eval_loss": NaN, "eval_runtime": 84.8032, "eval_samples_per_second": 19.398, "eval_steps_per_second": 2.429, "step": 1 }, { "epoch": 0.040973111395646605, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.040973111395646605, "eval_loss": NaN, "eval_runtime": 83.8835, "eval_samples_per_second": 19.611, "eval_steps_per_second": 2.456, "step": 10 }, { "epoch": 0.08194622279129321, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.08194622279129321, "eval_loss": NaN, "eval_runtime": 83.8847, "eval_samples_per_second": 19.61, "eval_steps_per_second": 2.456, "step": 20 }, { "epoch": 0.12291933418693982, "grad_norm": NaN, "learning_rate": 3.705904774487396e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.12291933418693982, "eval_loss": NaN, "eval_runtime": 83.7939, "eval_samples_per_second": 19.631, "eval_steps_per_second": 2.458, "step": 30 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.0874048927603098e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }