{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.022308979364194088, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002230897936419409, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.002230897936419409, "eval_loss": NaN, "eval_runtime": 39.3357, "eval_samples_per_second": 4.805, "eval_steps_per_second": 2.415, "step": 1 }, { "epoch": 0.004461795872838818, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.006692693809258227, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.006692693809258227, "eval_loss": NaN, "eval_runtime": 38.331, "eval_samples_per_second": 4.931, "eval_steps_per_second": 2.478, "step": 3 }, { "epoch": 0.008923591745677636, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.011154489682097044, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.013385387618516454, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.013385387618516454, "eval_loss": NaN, "eval_runtime": 38.6323, "eval_samples_per_second": 4.892, "eval_steps_per_second": 2.459, "step": 6 }, { "epoch": 0.015616285554935862, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.01784718349135527, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.020078081427774678, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.020078081427774678, "eval_loss": NaN, "eval_runtime": 38.7546, "eval_samples_per_second": 4.877, "eval_steps_per_second": 2.451, "step": 9 }, { "epoch": 0.022308979364194088, "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": 5, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 6822575367782400.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }