{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.03374103753690426, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.001687051876845213, "eval_loss": NaN, "eval_runtime": 14.4599, "eval_samples_per_second": 17.289, "eval_steps_per_second": 8.645, "step": 1 }, { "epoch": 0.005061155630535639, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.010122311261071278, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.013496415014761703, "eval_loss": NaN, "eval_runtime": 13.6716, "eval_samples_per_second": 18.286, "eval_steps_per_second": 9.143, "step": 8 }, { "epoch": 0.015183466891606916, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.020244622522142555, "grad_norm": NaN, "learning_rate": 0.00019510565162951537, "loss": 0.0, "step": 12 }, { "epoch": 0.025305778152678194, "grad_norm": NaN, "learning_rate": 0.00017071067811865476, "loss": 0.0, "step": 15 }, { "epoch": 0.026992830029523407, "eval_loss": NaN, "eval_runtime": 13.8496, "eval_samples_per_second": 18.051, "eval_steps_per_second": 9.026, "step": 16 }, { "epoch": 0.030366933783213833, "grad_norm": NaN, "learning_rate": 0.00013090169943749476, "loss": 0.0, "step": 18 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 6534582019031040.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }