{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1, "grad_norm": 0.21553142368793488, "learning_rate": 1.6000000000000003e-05, "loss": 4.6997, "step": 5 }, { "epoch": 0.2, "grad_norm": 0.19729050993919373, "learning_rate": 3.6e-05, "loss": 4.6594, "step": 10 }, { "epoch": 0.3, "grad_norm": 0.2265276163816452, "learning_rate": 5.6000000000000006e-05, "loss": 4.6575, "step": 15 }, { "epoch": 0.4, "grad_norm": 0.24024614691734314, "learning_rate": 7.6e-05, "loss": 4.6701, "step": 20 }, { "epoch": 0.5, "grad_norm": 0.25752702355384827, "learning_rate": 9.6e-05, "loss": 4.637, "step": 25 }, { "epoch": 0.6, "grad_norm": 0.3138992488384247, "learning_rate": 0.000116, "loss": 4.6469, "step": 30 }, { "epoch": 0.7, "grad_norm": 0.3859875202178955, "learning_rate": 0.00013600000000000003, "loss": 4.5877, "step": 35 }, { "epoch": 0.8, "grad_norm": 0.5465034246444702, "learning_rate": 0.00015600000000000002, "loss": 4.5079, "step": 40 }, { "epoch": 0.9, "grad_norm": 0.5064318776130676, "learning_rate": 0.00017600000000000002, "loss": 4.473, "step": 45 }, { "epoch": 1.0, "grad_norm": 0.6789440512657166, "learning_rate": 0.000196, "loss": 4.3371, "step": 50 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 8095363301376.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }