{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.09324009324009325, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.018648018648018648, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 40.0153, "step": 1 }, { "epoch": 0.018648018648018648, "eval_loss": NaN, "eval_runtime": 228.7108, "eval_samples_per_second": 0.398, "eval_steps_per_second": 0.201, "step": 1 }, { "epoch": 0.037296037296037296, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 47.885, "step": 2 }, { "epoch": 0.037296037296037296, "eval_loss": NaN, "eval_runtime": 15.8454, "eval_samples_per_second": 5.743, "eval_steps_per_second": 2.903, "step": 2 }, { "epoch": 0.055944055944055944, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 84.6354, "step": 3 }, { "epoch": 0.07459207459207459, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 27.124, "step": 4 }, { "epoch": 0.07459207459207459, "eval_loss": NaN, "eval_runtime": 15.9807, "eval_samples_per_second": 5.694, "eval_steps_per_second": 2.878, "step": 4 }, { "epoch": 0.09324009324009325, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 79.9837, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.13445148557312e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }