{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.15503875968992248, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.006201550387596899, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.006201550387596899, "eval_loss": NaN, "eval_runtime": 15.8627, "eval_samples_per_second": 3.152, "eval_steps_per_second": 3.152, "step": 1 }, { "epoch": 0.012403100775193798, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 2 }, { "epoch": 0.018604651162790697, "grad_norm": NaN, "learning_rate": 9.990365154573717e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.024806201550387597, "grad_norm": NaN, "learning_rate": 9.961501876182148e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.031007751937984496, "grad_norm": NaN, "learning_rate": 9.913533761814537e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.037209302325581395, "grad_norm": NaN, "learning_rate": 9.846666218300807e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.043410852713178294, "grad_norm": NaN, "learning_rate": 9.761185582727977e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.04961240310077519, "grad_norm": NaN, "learning_rate": 9.657457896300791e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.05581395348837209, "grad_norm": NaN, "learning_rate": 9.535927336897098e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.06201550387596899, "grad_norm": NaN, "learning_rate": 9.397114317029975e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.06821705426356589, "grad_norm": NaN, "learning_rate": 9.241613255361455e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.07441860465116279, "grad_norm": NaN, "learning_rate": 9.070090031310558e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.08062015503875969, "grad_norm": NaN, "learning_rate": 8.883279133655399e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.08682170542635659, "grad_norm": NaN, "learning_rate": 8.681980515339464e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.09302325581395349, "grad_norm": NaN, "learning_rate": 8.467056167950311e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.09922480620155039, "grad_norm": NaN, "learning_rate": 8.239426430539243e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.10542635658914729, "grad_norm": NaN, "learning_rate": 8.000066048588211e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.11162790697674418, "grad_norm": NaN, "learning_rate": 7.75e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.11782945736434108, "grad_norm": NaN, "learning_rate": 7.490299105985507e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.12403100775193798, "grad_norm": NaN, "learning_rate": 7.222075445642904e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.13023255813953488, "grad_norm": NaN, "learning_rate": 6.946477593864228e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.13643410852713178, "grad_norm": NaN, "learning_rate": 6.664685702961344e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.14263565891472868, "grad_norm": NaN, "learning_rate": 6.377906449072578e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.14883720930232558, "grad_norm": NaN, "learning_rate": 6.087367864990233e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.15503875968992248, "grad_norm": NaN, "learning_rate": 5.794314081535644e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.15503875968992248, "eval_loss": NaN, "eval_runtime": 15.8876, "eval_samples_per_second": 3.147, "eval_steps_per_second": 3.147, "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": 7.07253069938688e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }