{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.03259319617029945, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.001303727846811978, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 944.116, "step": 1 }, { "epoch": 0.001303727846811978, "eval_loss": NaN, "eval_runtime": 2.7999, "eval_samples_per_second": 17.858, "eval_steps_per_second": 17.858, "step": 1 }, { "epoch": 0.002607455693623956, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 2 }, { "epoch": 0.003911183540435934, "grad_norm": NaN, "learning_rate": 9.958086757163489e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.005214911387247912, "grad_norm": NaN, "learning_rate": 9.833127793065098e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.00651863923405989, "grad_norm": NaN, "learning_rate": 9.627450856774539e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.007822367080871868, "grad_norm": NaN, "learning_rate": 9.3448873204592e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.009126094927683846, "grad_norm": NaN, "learning_rate": 8.990700808169889e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.010429822774495823, "grad_norm": NaN, "learning_rate": 8.571489144483944e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.011733550621307803, "grad_norm": NaN, "learning_rate": 8.095061449516903e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.01303727846811978, "grad_norm": NaN, "learning_rate": 7.570292669790186e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.014341006314931758, "grad_norm": NaN, "learning_rate": 7.006958254769438e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.015644734161743737, "grad_norm": NaN, "learning_rate": 6.415552058736854e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.016948462008555713, "grad_norm": NaN, "learning_rate": 5.80709086014102e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.018252189855367692, "grad_norm": NaN, "learning_rate": 5.192909139858981e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.01955591770217967, "grad_norm": NaN, "learning_rate": 4.584447941263149e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.020859645548991647, "grad_norm": NaN, "learning_rate": 3.9930417452305626e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.022163373395803626, "grad_norm": NaN, "learning_rate": 3.4297073302098156e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.023467101242615605, "grad_norm": NaN, "learning_rate": 2.9049385504830985e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.02477082908942758, "grad_norm": NaN, "learning_rate": 2.4285108555160577e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.02607455693623956, "grad_norm": NaN, "learning_rate": 2.0092991918301108e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.02737828478305154, "grad_norm": NaN, "learning_rate": 1.6551126795408016e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.028682012629863515, "grad_norm": NaN, "learning_rate": 1.3725491432254624e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.029985740476675495, "grad_norm": NaN, "learning_rate": 1.1668722069349041e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.031289468323487474, "grad_norm": NaN, "learning_rate": 1.0419132428365116e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.03259319617029945, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.03259319617029945, "eval_loss": NaN, "eval_runtime": 2.7853, "eval_samples_per_second": 17.951, "eval_steps_per_second": 17.951, "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": 3755858482692096.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }