{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.011071132023249377, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0011071132023249377, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0011071132023249377, "eval_loss": NaN, "eval_runtime": 22.9568, "eval_samples_per_second": 16.596, "eval_steps_per_second": 8.32, "step": 1 }, { "epoch": 0.0022142264046498754, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0033213396069748133, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0033213396069748133, "eval_loss": NaN, "eval_runtime": 21.2051, "eval_samples_per_second": 17.967, "eval_steps_per_second": 9.007, "step": 3 }, { "epoch": 0.004428452809299751, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.005535566011624689, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0066426792139496265, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0066426792139496265, "eval_loss": NaN, "eval_runtime": 21.3393, "eval_samples_per_second": 17.854, "eval_steps_per_second": 8.951, "step": 6 }, { "epoch": 0.0077497924162745644, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.008856905618599501, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.00996401882092444, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.00996401882092444, "eval_loss": NaN, "eval_runtime": 21.1574, "eval_samples_per_second": 18.008, "eval_steps_per_second": 9.028, "step": 9 }, { "epoch": 0.011071132023249377, "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": 3319718822805504.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }