{ "best_metric": 0.3330279588699341, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.06415911460421846, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0012831822920843692, "grad_norm": 9.69926643371582, "learning_rate": 5e-05, "loss": 3.4686, "step": 1 }, { "epoch": 0.0012831822920843692, "eval_loss": 4.248011589050293, "eval_runtime": 0.4792, "eval_samples_per_second": 104.347, "eval_steps_per_second": 27.13, "step": 1 }, { "epoch": 0.0025663645841687384, "grad_norm": 9.604711532592773, "learning_rate": 0.0001, "loss": 3.5721, "step": 2 }, { "epoch": 0.0038495468762531075, "grad_norm": 9.658062934875488, "learning_rate": 9.990365154573717e-05, "loss": 3.5483, "step": 3 }, { "epoch": 0.005132729168337477, "grad_norm": 8.972732543945312, "learning_rate": 9.961501876182148e-05, "loss": 2.7079, "step": 4 }, { "epoch": 0.006415911460421846, "grad_norm": 7.0797810554504395, "learning_rate": 9.913533761814537e-05, "loss": 1.846, "step": 5 }, { "epoch": 0.007699093752506215, "grad_norm": 5.179475784301758, "learning_rate": 9.846666218300807e-05, "loss": 1.4564, "step": 6 }, { "epoch": 0.008982276044590584, "grad_norm": 4.027368068695068, "learning_rate": 9.761185582727977e-05, "loss": 1.2109, "step": 7 }, { "epoch": 0.010265458336674953, "grad_norm": 3.563283681869507, "learning_rate": 9.657457896300791e-05, "loss": 0.9135, "step": 8 }, { "epoch": 0.011548640628759323, "grad_norm": 2.7347819805145264, "learning_rate": 9.535927336897098e-05, "loss": 0.7636, "step": 9 }, { "epoch": 0.012831822920843693, "grad_norm": 2.4964144229888916, "learning_rate": 9.397114317029975e-05, "loss": 0.6791, "step": 10 }, { "epoch": 0.014115005212928062, "grad_norm": 2.7495129108428955, "learning_rate": 9.241613255361455e-05, "loss": 0.6407, "step": 11 }, { "epoch": 0.01539818750501243, "grad_norm": 2.3513643741607666, "learning_rate": 9.070090031310558e-05, "loss": 0.5507, "step": 12 }, { "epoch": 0.0166813697970968, "grad_norm": 1.8642207384109497, "learning_rate": 8.883279133655399e-05, "loss": 0.5893, "step": 13 }, { "epoch": 0.017964552089181168, "grad_norm": 2.0092697143554688, "learning_rate": 8.681980515339464e-05, "loss": 0.6107, "step": 14 }, { "epoch": 0.01924773438126554, "grad_norm": 1.567659616470337, "learning_rate": 8.467056167950311e-05, "loss": 0.494, "step": 15 }, { "epoch": 0.020530916673349907, "grad_norm": 1.9570163488388062, "learning_rate": 8.239426430539243e-05, "loss": 0.4533, "step": 16 }, { "epoch": 0.021814098965434278, "grad_norm": 1.603574514389038, "learning_rate": 8.000066048588211e-05, "loss": 0.4829, "step": 17 }, { "epoch": 0.023097281257518646, "grad_norm": 1.8064993619918823, "learning_rate": 7.75e-05, "loss": 0.5042, "step": 18 }, { "epoch": 0.024380463549603014, "grad_norm": 1.494826078414917, "learning_rate": 7.490299105985507e-05, "loss": 0.4298, "step": 19 }, { "epoch": 0.025663645841687385, "grad_norm": 1.5904885530471802, "learning_rate": 7.222075445642904e-05, "loss": 0.5216, "step": 20 }, { "epoch": 0.026946828133771753, "grad_norm": 1.4508434534072876, "learning_rate": 6.946477593864228e-05, "loss": 0.4252, "step": 21 }, { "epoch": 0.028230010425856124, "grad_norm": 1.796913981437683, "learning_rate": 6.664685702961344e-05, "loss": 0.4087, "step": 22 }, { "epoch": 0.029513192717940492, "grad_norm": 1.3291597366333008, "learning_rate": 6.377906449072578e-05, "loss": 0.3526, "step": 23 }, { "epoch": 0.03079637501002486, "grad_norm": 1.1371921300888062, "learning_rate": 6.087367864990233e-05, "loss": 0.3505, "step": 24 }, { "epoch": 0.03207955730210923, "grad_norm": 1.614019513130188, "learning_rate": 5.794314081535644e-05, "loss": 0.6021, "step": 25 }, { "epoch": 0.03207955730210923, "eval_loss": 0.36776840686798096, "eval_runtime": 0.4735, "eval_samples_per_second": 105.59, "eval_steps_per_second": 27.453, "step": 25 }, { "epoch": 0.0333627395941936, "grad_norm": 1.6320197582244873, "learning_rate": 5.500000000000001e-05, "loss": 0.4499, "step": 26 }, { "epoch": 0.03464592188627797, "grad_norm": 1.1622369289398193, "learning_rate": 5.205685918464356e-05, "loss": 0.3862, "step": 27 }, { "epoch": 0.035929104178362335, "grad_norm": 1.5270744562149048, "learning_rate": 4.912632135009769e-05, "loss": 0.391, "step": 28 }, { "epoch": 0.03721228647044671, "grad_norm": 1.5034524202346802, "learning_rate": 4.6220935509274235e-05, "loss": 0.3603, "step": 29 }, { "epoch": 0.03849546876253108, "grad_norm": 1.092508316040039, "learning_rate": 4.3353142970386564e-05, "loss": 0.3308, "step": 30 }, { "epoch": 0.03977865105461545, "grad_norm": 1.2671431303024292, "learning_rate": 4.053522406135775e-05, "loss": 0.4037, "step": 31 }, { "epoch": 0.041061833346699814, "grad_norm": 1.2833945751190186, "learning_rate": 3.777924554357096e-05, "loss": 0.3982, "step": 32 }, { "epoch": 0.042345015638784185, "grad_norm": 1.186705231666565, "learning_rate": 3.509700894014496e-05, "loss": 0.362, "step": 33 }, { "epoch": 0.043628197930868556, "grad_norm": 1.2128040790557861, "learning_rate": 3.250000000000001e-05, "loss": 0.401, "step": 34 }, { "epoch": 0.04491138022295292, "grad_norm": 1.496416687965393, "learning_rate": 2.9999339514117912e-05, "loss": 0.4697, "step": 35 }, { "epoch": 0.04619456251503729, "grad_norm": 1.348049521446228, "learning_rate": 2.760573569460757e-05, "loss": 0.3377, "step": 36 }, { "epoch": 0.04747774480712166, "grad_norm": 1.1160104274749756, "learning_rate": 2.53294383204969e-05, "loss": 0.341, "step": 37 }, { "epoch": 0.04876092709920603, "grad_norm": 1.1745514869689941, "learning_rate": 2.3180194846605367e-05, "loss": 0.4423, "step": 38 }, { "epoch": 0.0500441093912904, "grad_norm": 1.4134280681610107, "learning_rate": 2.1167208663446025e-05, "loss": 0.3774, "step": 39 }, { "epoch": 0.05132729168337477, "grad_norm": 1.0615042448043823, "learning_rate": 1.9299099686894423e-05, "loss": 0.2585, "step": 40 }, { "epoch": 0.05261047397545914, "grad_norm": 1.5986738204956055, "learning_rate": 1.758386744638546e-05, "loss": 0.455, "step": 41 }, { "epoch": 0.053893656267543506, "grad_norm": 1.1567108631134033, "learning_rate": 1.602885682970026e-05, "loss": 0.3465, "step": 42 }, { "epoch": 0.05517683855962788, "grad_norm": 1.347766399383545, "learning_rate": 1.464072663102903e-05, "loss": 0.4256, "step": 43 }, { "epoch": 0.05646002085171225, "grad_norm": 1.1334179639816284, "learning_rate": 1.3425421036992098e-05, "loss": 0.2994, "step": 44 }, { "epoch": 0.05774320314379661, "grad_norm": 1.1669671535491943, "learning_rate": 1.2388144172720251e-05, "loss": 0.3003, "step": 45 }, { "epoch": 0.059026385435880985, "grad_norm": 1.4140655994415283, "learning_rate": 1.1533337816991932e-05, "loss": 0.3947, "step": 46 }, { "epoch": 0.060309567727965356, "grad_norm": 1.5222396850585938, "learning_rate": 1.0864662381854632e-05, "loss": 0.3928, "step": 47 }, { "epoch": 0.06159275002004972, "grad_norm": 1.328269600868225, "learning_rate": 1.0384981238178534e-05, "loss": 0.4035, "step": 48 }, { "epoch": 0.06287593231213409, "grad_norm": 1.2904680967330933, "learning_rate": 1.0096348454262845e-05, "loss": 0.37, "step": 49 }, { "epoch": 0.06415911460421846, "grad_norm": 1.46721613407135, "learning_rate": 1e-05, "loss": 0.4614, "step": 50 }, { "epoch": 0.06415911460421846, "eval_loss": 0.3330279588699341, "eval_runtime": 0.4741, "eval_samples_per_second": 105.458, "eval_steps_per_second": 27.419, "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": 2.544851626439475e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }