{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.807017543859649, "eval_steps": 500, "global_step": 800, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.3508771929824561, "grad_norm": 1.360336184501648, "learning_rate": 9.817945383615085e-06, "loss": 1.1184, "step": 100 }, { "epoch": 0.7017543859649122, "grad_norm": 1.3165068626403809, "learning_rate": 8.517555266579974e-06, "loss": 0.9505, "step": 200 }, { "epoch": 1.0526315789473684, "grad_norm": 1.405255913734436, "learning_rate": 7.217165149544864e-06, "loss": 0.8506, "step": 300 }, { "epoch": 1.4035087719298245, "grad_norm": 1.478185772895813, "learning_rate": 5.916775032509754e-06, "loss": 0.8532, "step": 400 }, { "epoch": 1.7543859649122808, "grad_norm": 1.4331449270248413, "learning_rate": 4.6163849154746425e-06, "loss": 0.8386, "step": 500 }, { "epoch": 2.1052631578947367, "grad_norm": 1.5071395635604858, "learning_rate": 3.315994798439532e-06, "loss": 0.837, "step": 600 }, { "epoch": 2.456140350877193, "grad_norm": 1.5284526348114014, "learning_rate": 2.0156046814044216e-06, "loss": 0.8124, "step": 700 }, { "epoch": 2.807017543859649, "grad_norm": 1.4423238039016724, "learning_rate": 7.15214564369311e-07, "loss": 0.7947, "step": 800 } ], "logging_steps": 100, "max_steps": 855, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 5.13850968947841e+17, "train_batch_size": 16, "trial_name": null, "trial_params": null }