{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.41472265422498705, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01658890616899948, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.01658890616899948, "eval_loss": NaN, "eval_runtime": 0.7352, "eval_samples_per_second": 68.013, "eval_steps_per_second": 17.683, "step": 1 }, { "epoch": 0.03317781233799896, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 2 }, { "epoch": 0.049766718506998445, "grad_norm": NaN, "learning_rate": 9.958086757163489e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.06635562467599793, "grad_norm": NaN, "learning_rate": 9.833127793065098e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.08294453084499741, "grad_norm": NaN, "learning_rate": 9.627450856774539e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.09953343701399689, "grad_norm": NaN, "learning_rate": 9.3448873204592e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.11612234318299637, "grad_norm": NaN, "learning_rate": 8.990700808169889e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.13271124935199585, "grad_norm": NaN, "learning_rate": 8.571489144483944e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.14930015552099535, "grad_norm": NaN, "learning_rate": 8.095061449516903e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.16588906168999482, "grad_norm": NaN, "learning_rate": 7.570292669790186e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.1824779678589943, "grad_norm": NaN, "learning_rate": 7.006958254769438e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.19906687402799378, "grad_norm": NaN, "learning_rate": 6.415552058736854e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.21565578019699327, "grad_norm": NaN, "learning_rate": 5.80709086014102e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.23224468636599274, "grad_norm": NaN, "learning_rate": 5.192909139858981e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.24883359253499224, "grad_norm": NaN, "learning_rate": 4.584447941263149e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.2654224987039917, "grad_norm": NaN, "learning_rate": 3.9930417452305626e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.2820114048729912, "grad_norm": NaN, "learning_rate": 3.4297073302098156e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.2986003110419907, "grad_norm": NaN, "learning_rate": 2.9049385504830985e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.31518921721099014, "grad_norm": NaN, "learning_rate": 2.4285108555160577e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.33177812337998963, "grad_norm": NaN, "learning_rate": 2.0092991918301108e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.3483670295489891, "grad_norm": NaN, "learning_rate": 1.6551126795408016e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.3649559357179886, "grad_norm": NaN, "learning_rate": 1.3725491432254624e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.38154484188698806, "grad_norm": NaN, "learning_rate": 1.1668722069349041e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.39813374805598756, "grad_norm": NaN, "learning_rate": 1.0419132428365116e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.41472265422498705, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.41472265422498705, "eval_loss": NaN, "eval_runtime": 0.7441, "eval_samples_per_second": 67.195, "eval_steps_per_second": 17.471, "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": 1.47650456322048e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }