{ "best_metric": 10.90999984741211, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 1.2195121951219512, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.024390243902439025, "grad_norm": 18.24968147277832, "learning_rate": 5e-05, "loss": 177.2625, "step": 1 }, { "epoch": 0.024390243902439025, "eval_loss": 11.061498641967773, "eval_runtime": 0.4129, "eval_samples_per_second": 121.089, "eval_steps_per_second": 31.483, "step": 1 }, { "epoch": 0.04878048780487805, "grad_norm": 20.453662872314453, "learning_rate": 0.0001, "loss": 177.4078, "step": 2 }, { "epoch": 0.07317073170731707, "grad_norm": 18.037961959838867, "learning_rate": 9.990365154573717e-05, "loss": 177.2141, "step": 3 }, { "epoch": 0.0975609756097561, "grad_norm": 17.03003692626953, "learning_rate": 9.961501876182148e-05, "loss": 177.1187, "step": 4 }, { "epoch": 0.12195121951219512, "grad_norm": 15.108064651489258, "learning_rate": 9.913533761814537e-05, "loss": 176.9312, "step": 5 }, { "epoch": 0.14634146341463414, "grad_norm": 18.05943489074707, "learning_rate": 9.846666218300807e-05, "loss": 176.8859, "step": 6 }, { "epoch": 0.17073170731707318, "grad_norm": 18.244176864624023, "learning_rate": 9.761185582727977e-05, "loss": 176.7844, "step": 7 }, { "epoch": 0.1951219512195122, "grad_norm": 18.626970291137695, "learning_rate": 9.657457896300791e-05, "loss": 176.5094, "step": 8 }, { "epoch": 0.21951219512195122, "grad_norm": 18.218881607055664, "learning_rate": 9.535927336897098e-05, "loss": 176.4375, "step": 9 }, { "epoch": 0.24390243902439024, "grad_norm": 17.09756851196289, "learning_rate": 9.397114317029975e-05, "loss": 176.3172, "step": 10 }, { "epoch": 0.2682926829268293, "grad_norm": 14.669232368469238, "learning_rate": 9.241613255361455e-05, "loss": 176.3687, "step": 11 }, { "epoch": 0.2926829268292683, "grad_norm": 17.35498809814453, "learning_rate": 9.070090031310558e-05, "loss": 176.1641, "step": 12 }, { "epoch": 0.3170731707317073, "grad_norm": 15.785934448242188, "learning_rate": 8.883279133655399e-05, "loss": 176.1156, "step": 13 }, { "epoch": 0.34146341463414637, "grad_norm": 14.377754211425781, "learning_rate": 8.681980515339464e-05, "loss": 176.1578, "step": 14 }, { "epoch": 0.36585365853658536, "grad_norm": 15.93284797668457, "learning_rate": 8.467056167950311e-05, "loss": 175.6719, "step": 15 }, { "epoch": 0.3902439024390244, "grad_norm": 14.400132179260254, "learning_rate": 8.239426430539243e-05, "loss": 175.8609, "step": 16 }, { "epoch": 0.4146341463414634, "grad_norm": 14.658820152282715, "learning_rate": 8.000066048588211e-05, "loss": 175.5422, "step": 17 }, { "epoch": 0.43902439024390244, "grad_norm": 13.47697925567627, "learning_rate": 7.75e-05, "loss": 175.6453, "step": 18 }, { "epoch": 0.4634146341463415, "grad_norm": 14.613056182861328, "learning_rate": 7.490299105985507e-05, "loss": 175.3156, "step": 19 }, { "epoch": 0.4878048780487805, "grad_norm": 14.092459678649902, "learning_rate": 7.222075445642904e-05, "loss": 175.4109, "step": 20 }, { "epoch": 0.5121951219512195, "grad_norm": 13.947164535522461, "learning_rate": 6.946477593864228e-05, "loss": 175.4219, "step": 21 }, { "epoch": 0.5365853658536586, "grad_norm": 13.621604919433594, "learning_rate": 6.664685702961344e-05, "loss": 175.2969, "step": 22 }, { "epoch": 0.5609756097560976, "grad_norm": 14.145289421081543, "learning_rate": 6.377906449072578e-05, "loss": 175.0688, "step": 23 }, { "epoch": 0.5853658536585366, "grad_norm": 12.0012845993042, "learning_rate": 6.087367864990233e-05, "loss": 175.3359, "step": 24 }, { "epoch": 0.6097560975609756, "grad_norm": 13.05239200592041, "learning_rate": 5.794314081535644e-05, "loss": 175.1875, "step": 25 }, { "epoch": 0.6097560975609756, "eval_loss": 10.949499130249023, "eval_runtime": 0.079, "eval_samples_per_second": 632.81, "eval_steps_per_second": 164.531, "step": 25 }, { "epoch": 0.6341463414634146, "grad_norm": 13.815815925598145, "learning_rate": 5.500000000000001e-05, "loss": 174.8391, "step": 26 }, { "epoch": 0.6585365853658537, "grad_norm": 13.100130081176758, "learning_rate": 5.205685918464356e-05, "loss": 174.8297, "step": 27 }, { "epoch": 0.6829268292682927, "grad_norm": 13.180046081542969, "learning_rate": 4.912632135009769e-05, "loss": 174.8187, "step": 28 }, { "epoch": 0.7073170731707317, "grad_norm": 12.005698204040527, "learning_rate": 4.6220935509274235e-05, "loss": 175.1813, "step": 29 }, { "epoch": 0.7317073170731707, "grad_norm": 12.096576690673828, "learning_rate": 4.3353142970386564e-05, "loss": 175.0422, "step": 30 }, { "epoch": 0.7560975609756098, "grad_norm": 11.68134880065918, "learning_rate": 4.053522406135775e-05, "loss": 175.1812, "step": 31 }, { "epoch": 0.7804878048780488, "grad_norm": 12.187183380126953, "learning_rate": 3.777924554357096e-05, "loss": 174.8641, "step": 32 }, { "epoch": 0.8048780487804879, "grad_norm": 12.428651809692383, "learning_rate": 3.509700894014496e-05, "loss": 174.5688, "step": 33 }, { "epoch": 0.8292682926829268, "grad_norm": 12.642929077148438, "learning_rate": 3.250000000000001e-05, "loss": 174.5922, "step": 34 }, { "epoch": 0.8536585365853658, "grad_norm": 12.03905963897705, "learning_rate": 2.9999339514117912e-05, "loss": 174.6, "step": 35 }, { "epoch": 0.8780487804878049, "grad_norm": 12.165921211242676, "learning_rate": 2.760573569460757e-05, "loss": 174.6328, "step": 36 }, { "epoch": 0.9024390243902439, "grad_norm": 12.175124168395996, "learning_rate": 2.53294383204969e-05, "loss": 174.6594, "step": 37 }, { "epoch": 0.926829268292683, "grad_norm": 12.341449737548828, "learning_rate": 2.3180194846605367e-05, "loss": 174.3922, "step": 38 }, { "epoch": 0.9512195121951219, "grad_norm": 12.094307899475098, "learning_rate": 2.1167208663446025e-05, "loss": 174.4875, "step": 39 }, { "epoch": 0.975609756097561, "grad_norm": 12.679279327392578, "learning_rate": 1.9299099686894423e-05, "loss": 174.3047, "step": 40 }, { "epoch": 1.0, "grad_norm": 12.593793869018555, "learning_rate": 1.758386744638546e-05, "loss": 174.2922, "step": 41 }, { "epoch": 1.024390243902439, "grad_norm": 11.996077537536621, "learning_rate": 1.602885682970026e-05, "loss": 174.5672, "step": 42 }, { "epoch": 1.048780487804878, "grad_norm": 12.248947143554688, "learning_rate": 1.464072663102903e-05, "loss": 174.4156, "step": 43 }, { "epoch": 1.0731707317073171, "grad_norm": 12.989773750305176, "learning_rate": 1.3425421036992098e-05, "loss": 174.1469, "step": 44 }, { "epoch": 1.0975609756097562, "grad_norm": 11.868778228759766, "learning_rate": 1.2388144172720251e-05, "loss": 174.5203, "step": 45 }, { "epoch": 1.1219512195121952, "grad_norm": 11.858358383178711, "learning_rate": 1.1533337816991932e-05, "loss": 174.4172, "step": 46 }, { "epoch": 1.146341463414634, "grad_norm": 11.711751937866211, "learning_rate": 1.0864662381854632e-05, "loss": 174.4203, "step": 47 }, { "epoch": 1.170731707317073, "grad_norm": 12.023517608642578, "learning_rate": 1.0384981238178534e-05, "loss": 174.2734, "step": 48 }, { "epoch": 1.1951219512195121, "grad_norm": 12.9298677444458, "learning_rate": 1.0096348454262845e-05, "loss": 173.8922, "step": 49 }, { "epoch": 1.2195121951219512, "grad_norm": 11.806296348571777, "learning_rate": 1e-05, "loss": 174.325, "step": 50 }, { "epoch": 1.2195121951219512, "eval_loss": 10.90999984741211, "eval_runtime": 0.0961, "eval_samples_per_second": 520.291, "eval_steps_per_second": 135.276, "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": 4202692608000.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }