{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.32, "eval_steps": 500, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.032, "grad_norm": 3.0811734199523926, "learning_rate": 9.900000000000001e-05, "loss": 8.391141967773438, "step": 100 }, { "epoch": 0.064, "grad_norm": 0.9263819456100464, "learning_rate": 0.000199, "loss": 3.055461730957031, "step": 200 }, { "epoch": 0.096, "grad_norm": 0.9063050150871277, "learning_rate": 0.000299, "loss": 1.9104501342773437, "step": 300 }, { "epoch": 0.128, "grad_norm": 1.318272352218628, "learning_rate": 0.00039900000000000005, "loss": 1.6620086669921874, "step": 400 }, { "epoch": 0.16, "grad_norm": 0.7002186179161072, "learning_rate": 0.000499, "loss": 1.5271978759765625, "step": 500 }, { "epoch": 0.192, "grad_norm": 0.6296432018280029, "learning_rate": 0.0004999682018599242, "loss": 1.4492141723632812, "step": 600 }, { "epoch": 0.224, "grad_norm": 0.6575325131416321, "learning_rate": 0.0004998715277031906, "loss": 1.3877157592773437, "step": 700 }, { "epoch": 0.256, "grad_norm": 0.4923152029514313, "learning_rate": 0.0004997099993771365, "loss": 1.3457301330566407, "step": 800 }, { "epoch": 0.288, "grad_norm": 0.5497189164161682, "learning_rate": 0.000499483658806448, "loss": 1.305233154296875, "step": 900 }, { "epoch": 0.32, "grad_norm": 0.5527522563934326, "learning_rate": 0.0004991925647378331, "loss": 1.2742790222167968, "step": 1000 } ], "logging_steps": 100, "max_steps": 20000, "num_input_tokens_seen": 0, "num_train_epochs": 7, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1046696951808000.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }