{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.24390243902439024, "eval_steps": 500, "global_step": 200, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.024390243902439025, "grad_norm": 0.21254414319992065, "learning_rate": 0.00019631901840490797, "loss": 2.6924, "step": 20 }, { "epoch": 0.04878048780487805, "grad_norm": 0.15234693884849548, "learning_rate": 0.0001914110429447853, "loss": 2.395, "step": 40 }, { "epoch": 0.07317073170731707, "grad_norm": 0.14660173654556274, "learning_rate": 0.00018650306748466258, "loss": 2.3598, "step": 60 }, { "epoch": 0.0975609756097561, "grad_norm": 0.1487397700548172, "learning_rate": 0.00018159509202453987, "loss": 2.3004, "step": 80 }, { "epoch": 0.12195121951219512, "grad_norm": 0.1340309977531433, "learning_rate": 0.0001766871165644172, "loss": 2.2839, "step": 100 }, { "epoch": 0.14634146341463414, "grad_norm": 0.16995489597320557, "learning_rate": 0.0001717791411042945, "loss": 2.2511, "step": 120 }, { "epoch": 0.17073170731707318, "grad_norm": 0.19542120397090912, "learning_rate": 0.00016687116564417177, "loss": 2.3543, "step": 140 }, { "epoch": 0.1951219512195122, "grad_norm": 0.1439371407032013, "learning_rate": 0.00016196319018404909, "loss": 2.2475, "step": 160 }, { "epoch": 0.21951219512195122, "grad_norm": 0.20567895472049713, "learning_rate": 0.0001570552147239264, "loss": 2.2536, "step": 180 }, { "epoch": 0.24390243902439024, "grad_norm": 0.16278642416000366, "learning_rate": 0.0001521472392638037, "loss": 2.3064, "step": 200 } ], "logging_steps": 20, "max_steps": 820, "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": false }, "attributes": {} } }, "total_flos": 4.827473903616e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }