{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 4.393795490264893, "learning_rate": 9.934501067202117e-05, "loss": 2.0761, "step": 100 }, { "epoch": 2.0, "grad_norm": 3.135955333709717, "learning_rate": 9.405214343720707e-05, "loss": 1.3014, "step": 200 }, { "epoch": 3.0, "grad_norm": 3.1582624912261963, "learning_rate": 8.398554292153866e-05, "loss": 0.602, "step": 300 }, { "epoch": 4.0, "grad_norm": 3.5642945766448975, "learning_rate": 7.038717044938519e-05, "loss": 0.3151, "step": 400 }, { "epoch": 5.0, "grad_norm": 2.8030972480773926, "learning_rate": 5.445843903969854e-05, "loss": 0.2062, "step": 500 }, { "epoch": 6.0, "grad_norm": 3.6679484844207764, "learning_rate": 3.8046566580251e-05, "loss": 0.1353, "step": 600 }, { "epoch": 7.0, "grad_norm": 1.5564948320388794, "learning_rate": 2.29300341084631e-05, "loss": 0.1009, "step": 700 }, { "epoch": 8.0, "grad_norm": 0.24029085040092468, "learning_rate": 1.0746952474821614e-05, "loss": 0.0801, "step": 800 }, { "epoch": 9.0, "grad_norm": 0.27839767932891846, "learning_rate": 2.817547614320615e-06, "loss": 0.0696, "step": 900 }, { "epoch": 10.0, "grad_norm": 0.6297050714492798, "learning_rate": 1.0935809887702154e-09, "loss": 0.065, "step": 1000 } ], "logging_steps": 500, "max_steps": 1000, "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": 3508131774627840.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }