{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.1278772378516624, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005115089514066497, "grad_norm": NaN, "learning_rate": 5e-06, "loss": 0.0, "step": 1 }, { "epoch": 0.005115089514066497, "eval_loss": NaN, "eval_runtime": 24.3768, "eval_samples_per_second": 13.537, "eval_steps_per_second": 1.723, "step": 1 }, { "epoch": 0.010230179028132993, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.015345268542199489, "grad_norm": NaN, "learning_rate": 1.5e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.020460358056265986, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.02557544757033248, "grad_norm": NaN, "learning_rate": 2.5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.030690537084398978, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.03580562659846547, "grad_norm": NaN, "learning_rate": 3.5e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.04092071611253197, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.04603580562659847, "grad_norm": NaN, "learning_rate": 4.5e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.05115089514066496, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.056265984654731455, "grad_norm": NaN, "learning_rate": 5.500000000000001e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.061381074168797956, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.06649616368286446, "grad_norm": NaN, "learning_rate": 6.500000000000001e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.07161125319693094, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.07672634271099744, "grad_norm": NaN, "learning_rate": 7.500000000000001e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.08184143222506395, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.08695652173913043, "grad_norm": NaN, "learning_rate": 8.5e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.09207161125319693, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.09718670076726342, "grad_norm": NaN, "learning_rate": 9.5e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.10230179028132992, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 20 }, { "epoch": 0.10741687979539642, "grad_norm": NaN, "learning_rate": 9.972609476841367e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.11253196930946291, "grad_norm": NaN, "learning_rate": 9.890738003669029e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.11764705882352941, "grad_norm": NaN, "learning_rate": 9.755282581475769e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.12276214833759591, "grad_norm": NaN, "learning_rate": 9.567727288213005e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.1278772378516624, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.1278772378516624, "eval_loss": NaN, "eval_runtime": 24.2316, "eval_samples_per_second": 13.619, "eval_steps_per_second": 1.733, "step": 25 } ], "logging_steps": 1, "max_steps": 50, "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": false }, "attributes": {} } }, "total_flos": 3.77128394686464e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }