{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00033711179469891704, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 3.37111794698917e-05, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 3.37111794698917e-05, "eval_loss": NaN, "eval_runtime": 1759.5726, "eval_samples_per_second": 7.098, "eval_steps_per_second": 3.549, "step": 1 }, { "epoch": 6.74223589397834e-05, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0001011335384096751, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0001011335384096751, "eval_loss": NaN, "eval_runtime": 1761.5047, "eval_samples_per_second": 7.091, "eval_steps_per_second": 3.545, "step": 3 }, { "epoch": 0.0001348447178795668, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.00016855589734945852, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0002022670768193502, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0002022670768193502, "eval_loss": NaN, "eval_runtime": 1778.6534, "eval_samples_per_second": 7.022, "eval_steps_per_second": 3.511, "step": 6 }, { "epoch": 0.00023597825628924191, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0002696894357591336, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.00030340061522902533, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.00030340061522902533, "eval_loss": NaN, "eval_runtime": 1779.8658, "eval_samples_per_second": 7.017, "eval_steps_per_second": 3.509, "step": 9 }, { "epoch": 0.00033711179469891704, "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": 2820585478422528.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }