{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.025559105431309903, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0010223642172523962, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0010223642172523962, "eval_loss": NaN, "eval_runtime": 4.2647, "eval_samples_per_second": 11.724, "eval_steps_per_second": 3.048, "step": 1 }, { "epoch": 0.0020447284345047924, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 2 }, { "epoch": 0.0030670926517571886, "grad_norm": NaN, "learning_rate": 9.990365154573717e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.004089456869009585, "grad_norm": NaN, "learning_rate": 9.961501876182148e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.005111821086261981, "grad_norm": NaN, "learning_rate": 9.913533761814537e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.006134185303514377, "grad_norm": NaN, "learning_rate": 9.846666218300807e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.007156549520766773, "grad_norm": NaN, "learning_rate": 9.761185582727977e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.00817891373801917, "grad_norm": NaN, "learning_rate": 9.657457896300791e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.009201277955271566, "grad_norm": NaN, "learning_rate": 9.535927336897098e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.010223642172523962, "grad_norm": NaN, "learning_rate": 9.397114317029975e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.011246006389776358, "grad_norm": NaN, "learning_rate": 9.241613255361455e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.012268370607028754, "grad_norm": NaN, "learning_rate": 9.070090031310558e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.01329073482428115, "grad_norm": NaN, "learning_rate": 8.883279133655399e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.014313099041533547, "grad_norm": NaN, "learning_rate": 8.681980515339464e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.015335463258785943, "grad_norm": NaN, "learning_rate": 8.467056167950311e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.01635782747603834, "grad_norm": NaN, "learning_rate": 8.239426430539243e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.017380191693290734, "grad_norm": NaN, "learning_rate": 8.000066048588211e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.01840255591054313, "grad_norm": NaN, "learning_rate": 7.75e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.019424920127795526, "grad_norm": NaN, "learning_rate": 7.490299105985507e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.020447284345047924, "grad_norm": NaN, "learning_rate": 7.222075445642904e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.02146964856230032, "grad_norm": NaN, "learning_rate": 6.946477593864228e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.022492012779552716, "grad_norm": NaN, "learning_rate": 6.664685702961344e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.02351437699680511, "grad_norm": NaN, "learning_rate": 6.377906449072578e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.02453674121405751, "grad_norm": NaN, "learning_rate": 6.087367864990233e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.025559105431309903, "grad_norm": NaN, "learning_rate": 5.794314081535644e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.025559105431309903, "eval_loss": NaN, "eval_runtime": 4.197, "eval_samples_per_second": 11.913, "eval_steps_per_second": 3.097, "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": 2.829012279754752e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }