{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.872727272727273, "eval_steps": 500, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.14545454545454545, "grad_norm": 28.76009972966515, "learning_rate": 4.986304738420684e-06, "loss": 1.0746, "step": 1 }, { "epoch": 0.7272727272727273, "grad_norm": 2.312067763587003, "learning_rate": 4.665063509461098e-06, "loss": 0.4098, "step": 5 }, { "epoch": 1.5818181818181818, "grad_norm": 0.7495197094469845, "learning_rate": 3.7500000000000005e-06, "loss": 0.2514, "step": 10 }, { "epoch": 2.4363636363636365, "grad_norm": 0.6992409074674005, "learning_rate": 2.5e-06, "loss": 0.1896, "step": 15 }, { "epoch": 3.290909090909091, "grad_norm": 0.6343885639630856, "learning_rate": 1.2500000000000007e-06, "loss": 0.1381, "step": 20 }, { "epoch": 4.1454545454545455, "grad_norm": 0.6823715156903619, "learning_rate": 3.3493649053890325e-07, "loss": 0.1051, "step": 25 }, { "epoch": 4.872727272727273, "grad_norm": 0.5676296835301833, "learning_rate": 0.0, "loss": 0.0777, "step": 30 }, { "epoch": 4.872727272727273, "step": 30, "total_flos": 2.111947399978025e+17, "train_loss": 0.21743224561214447, "train_runtime": 3011.3933, "train_samples_per_second": 1.456, "train_steps_per_second": 0.01 } ], "logging_steps": 5, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.111947399978025e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }