{ "best_metric": 1.4303250312805176, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.44543429844098, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008908685968819599, "grad_norm": 0.11133307963609695, "learning_rate": 5e-05, "loss": 1.4532, "step": 1 }, { "epoch": 0.008908685968819599, "eval_loss": 2.072521686553955, "eval_runtime": 4.4753, "eval_samples_per_second": 11.173, "eval_steps_per_second": 2.905, "step": 1 }, { "epoch": 0.017817371937639197, "grad_norm": 0.17192766070365906, "learning_rate": 0.0001, "loss": 1.5536, "step": 2 }, { "epoch": 0.026726057906458798, "grad_norm": 0.18040545284748077, "learning_rate": 9.990365154573717e-05, "loss": 1.6079, "step": 3 }, { "epoch": 0.035634743875278395, "grad_norm": 0.18853719532489777, "learning_rate": 9.961501876182148e-05, "loss": 1.7888, "step": 4 }, { "epoch": 0.044543429844097995, "grad_norm": 0.2150399386882782, "learning_rate": 9.913533761814537e-05, "loss": 1.7919, "step": 5 }, { "epoch": 0.053452115812917596, "grad_norm": 0.22480782866477966, "learning_rate": 9.846666218300807e-05, "loss": 1.7963, "step": 6 }, { "epoch": 0.062360801781737196, "grad_norm": 0.26064804196357727, "learning_rate": 9.761185582727977e-05, "loss": 1.8534, "step": 7 }, { "epoch": 0.07126948775055679, "grad_norm": 0.3298412561416626, "learning_rate": 9.657457896300791e-05, "loss": 1.579, "step": 8 }, { "epoch": 0.0801781737193764, "grad_norm": 0.32930654287338257, "learning_rate": 9.535927336897098e-05, "loss": 1.4792, "step": 9 }, { "epoch": 0.08908685968819599, "grad_norm": 0.3741617500782013, "learning_rate": 9.397114317029975e-05, "loss": 1.4727, "step": 10 }, { "epoch": 0.09799554565701558, "grad_norm": 0.7906994819641113, "learning_rate": 9.241613255361455e-05, "loss": 1.4127, "step": 11 }, { "epoch": 0.10690423162583519, "grad_norm": 1.5986047983169556, "learning_rate": 9.070090031310558e-05, "loss": 1.5383, "step": 12 }, { "epoch": 0.11581291759465479, "grad_norm": 0.29541853070259094, "learning_rate": 8.883279133655399e-05, "loss": 1.5756, "step": 13 }, { "epoch": 0.12472160356347439, "grad_norm": 0.3613141179084778, "learning_rate": 8.681980515339464e-05, "loss": 1.5108, "step": 14 }, { "epoch": 0.133630289532294, "grad_norm": 0.39106887578964233, "learning_rate": 8.467056167950311e-05, "loss": 1.6374, "step": 15 }, { "epoch": 0.14253897550111358, "grad_norm": 0.39802828431129456, "learning_rate": 8.239426430539243e-05, "loss": 1.6392, "step": 16 }, { "epoch": 0.1514476614699332, "grad_norm": 0.3249336779117584, "learning_rate": 8.000066048588211e-05, "loss": 1.7826, "step": 17 }, { "epoch": 0.1603563474387528, "grad_norm": 0.26698875427246094, "learning_rate": 7.75e-05, "loss": 1.7011, "step": 18 }, { "epoch": 0.16926503340757237, "grad_norm": 0.24392510950565338, "learning_rate": 7.490299105985507e-05, "loss": 1.7755, "step": 19 }, { "epoch": 0.17817371937639198, "grad_norm": 0.2130114734172821, "learning_rate": 7.222075445642904e-05, "loss": 1.6791, "step": 20 }, { "epoch": 0.1870824053452116, "grad_norm": 0.24721674621105194, "learning_rate": 6.946477593864228e-05, "loss": 1.5497, "step": 21 }, { "epoch": 0.19599109131403117, "grad_norm": 0.2948874235153198, "learning_rate": 6.664685702961344e-05, "loss": 1.3963, "step": 22 }, { "epoch": 0.20489977728285078, "grad_norm": 0.49845367670059204, "learning_rate": 6.377906449072578e-05, "loss": 1.504, "step": 23 }, { "epoch": 0.21380846325167038, "grad_norm": 0.8768094778060913, "learning_rate": 6.087367864990233e-05, "loss": 1.057, "step": 24 }, { "epoch": 0.22271714922049, "grad_norm": 2.5265109539031982, "learning_rate": 5.794314081535644e-05, "loss": 1.6941, "step": 25 }, { "epoch": 0.22271714922049, "eval_loss": 1.4848670959472656, "eval_runtime": 4.552, "eval_samples_per_second": 10.984, "eval_steps_per_second": 2.856, "step": 25 }, { "epoch": 0.23162583518930957, "grad_norm": 0.10521416366100311, "learning_rate": 5.500000000000001e-05, "loss": 1.3997, "step": 26 }, { "epoch": 0.24053452115812918, "grad_norm": 0.16910868883132935, "learning_rate": 5.205685918464356e-05, "loss": 1.4004, "step": 27 }, { "epoch": 0.24944320712694878, "grad_norm": 0.16062675416469574, "learning_rate": 4.912632135009769e-05, "loss": 1.7033, "step": 28 }, { "epoch": 0.2583518930957684, "grad_norm": 0.19629095494747162, "learning_rate": 4.6220935509274235e-05, "loss": 1.5864, "step": 29 }, { "epoch": 0.267260579064588, "grad_norm": 0.15940530598163605, "learning_rate": 4.3353142970386564e-05, "loss": 1.7366, "step": 30 }, { "epoch": 0.27616926503340755, "grad_norm": 0.1648244708776474, "learning_rate": 4.053522406135775e-05, "loss": 1.7691, "step": 31 }, { "epoch": 0.28507795100222716, "grad_norm": 0.1886545866727829, "learning_rate": 3.777924554357096e-05, "loss": 1.7204, "step": 32 }, { "epoch": 0.29398663697104677, "grad_norm": 0.1986749768257141, "learning_rate": 3.509700894014496e-05, "loss": 1.5048, "step": 33 }, { "epoch": 0.3028953229398664, "grad_norm": 0.23183304071426392, "learning_rate": 3.250000000000001e-05, "loss": 1.5488, "step": 34 }, { "epoch": 0.311804008908686, "grad_norm": 0.30229678750038147, "learning_rate": 2.9999339514117912e-05, "loss": 1.4632, "step": 35 }, { "epoch": 0.3207126948775056, "grad_norm": 0.46872618794441223, "learning_rate": 2.760573569460757e-05, "loss": 1.3581, "step": 36 }, { "epoch": 0.32962138084632514, "grad_norm": 0.7139592170715332, "learning_rate": 2.53294383204969e-05, "loss": 1.1433, "step": 37 }, { "epoch": 0.33853006681514475, "grad_norm": 0.15235215425491333, "learning_rate": 2.3180194846605367e-05, "loss": 1.378, "step": 38 }, { "epoch": 0.34743875278396436, "grad_norm": 0.11655563861131668, "learning_rate": 2.1167208663446025e-05, "loss": 1.3093, "step": 39 }, { "epoch": 0.35634743875278396, "grad_norm": 0.1409669816493988, "learning_rate": 1.9299099686894423e-05, "loss": 1.4876, "step": 40 }, { "epoch": 0.36525612472160357, "grad_norm": 0.16531401872634888, "learning_rate": 1.758386744638546e-05, "loss": 1.5464, "step": 41 }, { "epoch": 0.3741648106904232, "grad_norm": 0.15591953694820404, "learning_rate": 1.602885682970026e-05, "loss": 1.7055, "step": 42 }, { "epoch": 0.3830734966592428, "grad_norm": 0.1626148670911789, "learning_rate": 1.464072663102903e-05, "loss": 1.6206, "step": 43 }, { "epoch": 0.39198218262806234, "grad_norm": 0.183099165558815, "learning_rate": 1.3425421036992098e-05, "loss": 1.7019, "step": 44 }, { "epoch": 0.40089086859688194, "grad_norm": 0.19065551459789276, "learning_rate": 1.2388144172720251e-05, "loss": 1.6422, "step": 45 }, { "epoch": 0.40979955456570155, "grad_norm": 0.20751234889030457, "learning_rate": 1.1533337816991932e-05, "loss": 1.5612, "step": 46 }, { "epoch": 0.41870824053452116, "grad_norm": 0.25490185618400574, "learning_rate": 1.0864662381854632e-05, "loss": 1.4741, "step": 47 }, { "epoch": 0.42761692650334077, "grad_norm": 0.33369606733322144, "learning_rate": 1.0384981238178534e-05, "loss": 1.5135, "step": 48 }, { "epoch": 0.4365256124721604, "grad_norm": 0.4805344343185425, "learning_rate": 1.0096348454262845e-05, "loss": 1.2555, "step": 49 }, { "epoch": 0.44543429844098, "grad_norm": 1.1152390241622925, "learning_rate": 1e-05, "loss": 1.4147, "step": 50 }, { "epoch": 0.44543429844098, "eval_loss": 1.4303250312805176, "eval_runtime": 4.4945, "eval_samples_per_second": 11.125, "eval_steps_per_second": 2.892, "step": 50 } ], "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": true }, "attributes": {} } }, "total_flos": 5.6372392263417856e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }