| { | |
| "best_metric": 0.1434822976589203, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0355769016965735, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00071153803393147, | |
| "grad_norm": 4.15134859085083, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1572, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00071153803393147, | |
| "eval_loss": 4.378438949584961, | |
| "eval_runtime": 3.4295, | |
| "eval_samples_per_second": 14.579, | |
| "eval_steps_per_second": 3.791, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00142307606786294, | |
| "grad_norm": 4.170166969299316, | |
| "learning_rate": 0.0001, | |
| "loss": 3.5344, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00213461410179441, | |
| "grad_norm": 3.9985992908477783, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.525, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00284615213572588, | |
| "grad_norm": 3.6105992794036865, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.8142, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00355769016965735, | |
| "grad_norm": 5.007969379425049, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.1902, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00426922820358882, | |
| "grad_norm": 3.7518584728240967, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.5608, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00498076623752029, | |
| "grad_norm": 3.1341824531555176, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.1253, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00569230427145176, | |
| "grad_norm": 2.485367774963379, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.8497, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00640384230538323, | |
| "grad_norm": 2.4227840900421143, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.6076, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0071153803393147, | |
| "grad_norm": 2.9558370113372803, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.4456, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00782691837324617, | |
| "grad_norm": 2.320117950439453, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4223, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00853845640717764, | |
| "grad_norm": 2.1507346630096436, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.3642, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00924999444110911, | |
| "grad_norm": 3.829542875289917, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.9195, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00996153247504058, | |
| "grad_norm": 2.7810795307159424, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.6957, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01067307050897205, | |
| "grad_norm": 3.1059398651123047, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.543, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01138460854290352, | |
| "grad_norm": 2.7258763313293457, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.4601, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01209614657683499, | |
| "grad_norm": 1.5909277200698853, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.3518, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01280768461076646, | |
| "grad_norm": 0.9435157179832458, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.2869, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01351922264469793, | |
| "grad_norm": 1.1259710788726807, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.2478, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0142307606786294, | |
| "grad_norm": 0.6966629028320312, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.1902, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01494229871256087, | |
| "grad_norm": 1.0074700117111206, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.1921, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01565383674649234, | |
| "grad_norm": 0.9900541305541992, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.1861, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01636537478042381, | |
| "grad_norm": 0.6567324995994568, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1719, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01707691281435528, | |
| "grad_norm": 0.8026172518730164, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1451, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01778845084828675, | |
| "grad_norm": 0.9177777767181396, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1415, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01778845084828675, | |
| "eval_loss": 0.33393481373786926, | |
| "eval_runtime": 3.4972, | |
| "eval_samples_per_second": 14.297, | |
| "eval_steps_per_second": 3.717, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01849998888221822, | |
| "grad_norm": 2.969831943511963, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.5724, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01921152691614969, | |
| "grad_norm": 2.821878433227539, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.4745, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01992306495008116, | |
| "grad_norm": 2.2078421115875244, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.2994, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02063460298401263, | |
| "grad_norm": 1.3875349760055542, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.2495, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0213461410179441, | |
| "grad_norm": 0.6588164567947388, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.1957, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02205767905187557, | |
| "grad_norm": 0.9994838237762451, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.1777, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02276921708580704, | |
| "grad_norm": 1.3160651922225952, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.1387, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02348075511973851, | |
| "grad_norm": 1.2686349153518677, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.1326, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02419229315366998, | |
| "grad_norm": 1.0544302463531494, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.1315, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02490383118760145, | |
| "grad_norm": 0.8117554187774658, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.1057, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02561536922153292, | |
| "grad_norm": 0.8301512002944946, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.1408, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02632690725546439, | |
| "grad_norm": 0.698844313621521, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.108, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02703844528939586, | |
| "grad_norm": 1.0740541219711304, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.336, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02774998332332733, | |
| "grad_norm": 1.0991758108139038, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.2901, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0284615213572588, | |
| "grad_norm": 0.9590191841125488, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.2117, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02917305939119027, | |
| "grad_norm": 0.9291145205497742, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.1994, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02988459742512174, | |
| "grad_norm": 0.9364894032478333, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.1825, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03059613545905321, | |
| "grad_norm": 0.8379543423652649, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.1323, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03130767349298468, | |
| "grad_norm": 0.8360366821289062, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.1075, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03201921152691615, | |
| "grad_norm": 0.6033630967140198, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.1072, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03273074956084762, | |
| "grad_norm": 0.4806281328201294, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0838, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03344228759477909, | |
| "grad_norm": 0.53305584192276, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0922, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03415382562871056, | |
| "grad_norm": 0.4884934723377228, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.115, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03486536366264203, | |
| "grad_norm": 0.723628044128418, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.1015, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0355769016965735, | |
| "grad_norm": 1.2043287754058838, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1129, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0355769016965735, | |
| "eval_loss": 0.1434822976589203, | |
| "eval_runtime": 3.4781, | |
| "eval_samples_per_second": 14.375, | |
| "eval_steps_per_second": 3.738, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |