{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 330, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 1.8226944208145142, "learning_rate": 9.783837236868609e-05, "loss": 2.0354, "step": 33 }, { "epoch": 2.0, "grad_norm": 2.7249906063079834, "learning_rate": 9.100305426420956e-05, "loss": 0.7837, "step": 66 }, { "epoch": 3.0, "grad_norm": 2.467717409133911, "learning_rate": 8.015407152327448e-05, "loss": 0.4574, "step": 99 }, { "epoch": 4.0, "grad_norm": 1.8809279203414917, "learning_rate": 6.635339816587109e-05, "loss": 0.2493, "step": 132 }, { "epoch": 5.0, "grad_norm": 1.9061037302017212, "learning_rate": 5.095194025516733e-05, "loss": 0.1279, "step": 165 }, { "epoch": 6.0, "grad_norm": 1.2163299322128296, "learning_rate": 3.545729979973005e-05, "loss": 0.0864, "step": 198 }, { "epoch": 7.0, "grad_norm": 0.7751290202140808, "learning_rate": 2.1386200164845526e-05, "loss": 0.0468, "step": 231 }, { "epoch": 8.0, "grad_norm": 0.40003788471221924, "learning_rate": 1.0116018621892237e-05, "loss": 0.0374, "step": 264 }, { "epoch": 9.0, "grad_norm": 0.4982641041278839, "learning_rate": 2.7499590642665774e-06, "loss": 0.031, "step": 297 }, { "epoch": 10.0, "grad_norm": 0.4024178087711334, "learning_rate": 9.06272382371065e-09, "loss": 0.0291, "step": 330 } ], "logging_steps": 500, "max_steps": 330, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2301871990210560.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }