| { | |
| "best_metric": 11.910688400268555, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.4916512059369202, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029684601113172542, | |
| "grad_norm": 0.0819375291466713, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9231, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029684601113172542, | |
| "eval_loss": 11.920661926269531, | |
| "eval_runtime": 0.1259, | |
| "eval_samples_per_second": 397.08, | |
| "eval_steps_per_second": 103.241, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.059369202226345084, | |
| "grad_norm": 0.07202845066785812, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9261, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08905380333951762, | |
| "grad_norm": 0.07669679075479507, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.9269, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11873840445269017, | |
| "grad_norm": 0.09482110291719437, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9222, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14842300556586271, | |
| "grad_norm": 0.09856817871332169, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.9286, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17810760667903525, | |
| "grad_norm": 0.08858457952737808, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9341, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": 0.10745372623205185, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9302, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.23747680890538034, | |
| "grad_norm": 0.1133977472782135, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9299, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.26716141001855287, | |
| "grad_norm": 0.074555404484272, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9248, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.29684601113172543, | |
| "grad_norm": 0.04240390285849571, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9319, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.06600447744131088, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9298, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3562152133580705, | |
| "grad_norm": 0.0718693882226944, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9277, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.38589981447124305, | |
| "grad_norm": 0.08081339299678802, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9238, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4155844155844156, | |
| "grad_norm": 0.09722533822059631, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9264, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4452690166975881, | |
| "grad_norm": 0.10125495493412018, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.9317, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4749536178107607, | |
| "grad_norm": 0.11832242459058762, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9273, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5046382189239332, | |
| "grad_norm": 0.07648923993110657, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9267, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5343228200371057, | |
| "grad_norm": 0.06109366565942764, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.925, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5640074211502782, | |
| "grad_norm": 0.08881764113903046, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9222, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5936920222634509, | |
| "grad_norm": 0.07279272377490997, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9214, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6233766233766234, | |
| "grad_norm": 0.11327576637268066, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9297, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 0.09995870292186737, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9282, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6827458256029685, | |
| "grad_norm": 0.12067265808582306, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9259, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.712430426716141, | |
| "grad_norm": 0.13204942643642426, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9329, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7421150278293135, | |
| "grad_norm": 0.11414287984371185, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9336, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7421150278293135, | |
| "eval_loss": 11.914447784423828, | |
| "eval_runtime": 0.1457, | |
| "eval_samples_per_second": 343.26, | |
| "eval_steps_per_second": 89.248, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7717996289424861, | |
| "grad_norm": 0.07111849635839462, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9242, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8014842300556586, | |
| "grad_norm": 0.07921064645051956, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.923, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8311688311688312, | |
| "grad_norm": 0.10227816551923752, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9234, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8608534322820037, | |
| "grad_norm": 0.11948052048683167, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.9263, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8905380333951762, | |
| "grad_norm": 0.15240927040576935, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.929, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9202226345083488, | |
| "grad_norm": 0.1400817185640335, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9298, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9499072356215214, | |
| "grad_norm": 0.17380662262439728, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9234, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 0.181602343916893, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9239, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0166975881261595, | |
| "grad_norm": 0.1615762561559677, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 17.6084, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0463821892393321, | |
| "grad_norm": 0.09680893272161484, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 13.2432, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0760667903525047, | |
| "grad_norm": 0.10842955857515335, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.7133, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1057513914656771, | |
| "grad_norm": 0.11968661844730377, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 12.1176, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1354359925788498, | |
| "grad_norm": 0.15758144855499268, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.5781, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1651205936920221, | |
| "grad_norm": 0.16318297386169434, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.8551, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.1948051948051948, | |
| "grad_norm": 0.1592426300048828, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.8129, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2244897959183674, | |
| "grad_norm": 0.18521009385585785, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9893, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.25417439703154, | |
| "grad_norm": 0.1403988003730774, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.9091, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.2838589981447124, | |
| "grad_norm": 0.10750801116228104, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 13.3784, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.313543599257885, | |
| "grad_norm": 0.10899406671524048, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.5317, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.3432282003710574, | |
| "grad_norm": 0.13023824989795685, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.4102, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.37291280148423, | |
| "grad_norm": 0.1307949274778366, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 13.2577, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4025974025974026, | |
| "grad_norm": 0.1620696485042572, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.2825, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.4322820037105752, | |
| "grad_norm": 0.15053598582744598, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 12.119, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.4619666048237476, | |
| "grad_norm": 0.19470062851905823, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 12.0202, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.4916512059369202, | |
| "grad_norm": 0.15723778307437897, | |
| "learning_rate": 1e-05, | |
| "loss": 10.541, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4916512059369202, | |
| "eval_loss": 11.910688400268555, | |
| "eval_runtime": 0.1299, | |
| "eval_samples_per_second": 385.038, | |
| "eval_steps_per_second": 100.11, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1042494259200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |