{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.3996003996003996, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.015984015984015984, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.015984015984015984, "eval_loss": NaN, "eval_runtime": 1.1129, "eval_samples_per_second": 44.927, "eval_steps_per_second": 11.681, "step": 1 }, { "epoch": 0.03196803196803197, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 2 }, { "epoch": 0.04795204795204795, "grad_norm": NaN, "learning_rate": 9.958086757163489e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.06393606393606394, "grad_norm": NaN, "learning_rate": 9.833127793065098e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.07992007992007992, "grad_norm": NaN, "learning_rate": 9.627450856774539e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.0959040959040959, "grad_norm": NaN, "learning_rate": 9.3448873204592e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.11188811188811189, "grad_norm": NaN, "learning_rate": 8.990700808169889e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.12787212787212787, "grad_norm": NaN, "learning_rate": 8.571489144483944e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.14385614385614387, "grad_norm": NaN, "learning_rate": 8.095061449516903e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.15984015984015984, "grad_norm": NaN, "learning_rate": 7.570292669790186e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.17582417582417584, "grad_norm": NaN, "learning_rate": 7.006958254769438e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.1918081918081918, "grad_norm": NaN, "learning_rate": 6.415552058736854e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.2077922077922078, "grad_norm": NaN, "learning_rate": 5.80709086014102e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.22377622377622378, "grad_norm": NaN, "learning_rate": 5.192909139858981e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.23976023976023977, "grad_norm": NaN, "learning_rate": 4.584447941263149e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.25574425574425574, "grad_norm": NaN, "learning_rate": 3.9930417452305626e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.27172827172827174, "grad_norm": NaN, "learning_rate": 3.4297073302098156e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.28771228771228774, "grad_norm": NaN, "learning_rate": 2.9049385504830985e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.3036963036963037, "grad_norm": NaN, "learning_rate": 2.4285108555160577e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.3196803196803197, "grad_norm": NaN, "learning_rate": 2.0092991918301108e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.3356643356643357, "grad_norm": NaN, "learning_rate": 1.6551126795408016e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.3516483516483517, "grad_norm": NaN, "learning_rate": 1.3725491432254624e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.3676323676323676, "grad_norm": NaN, "learning_rate": 1.1668722069349041e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.3836163836163836, "grad_norm": NaN, "learning_rate": 1.0419132428365116e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.3996003996003996, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.3996003996003996, "eval_loss": NaN, "eval_runtime": 1.1166, "eval_samples_per_second": 44.781, "eval_steps_per_second": 11.643, "step": 25 } ], "logging_steps": 1, "max_steps": 25, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5.29768176943104e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }