{ "best_metric": 3.035244941711426, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.129680661371373, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00259361322742746, "grad_norm": 9.774222373962402, "learning_rate": 5e-05, "loss": 55.6682, "step": 1 }, { "epoch": 0.00259361322742746, "eval_loss": 4.410276889801025, "eval_runtime": 3.5615, "eval_samples_per_second": 14.039, "eval_steps_per_second": 3.65, "step": 1 }, { "epoch": 0.00518722645485492, "grad_norm": 10.740211486816406, "learning_rate": 0.0001, "loss": 62.9127, "step": 2 }, { "epoch": 0.007780839682282379, "grad_norm": 11.119783401489258, "learning_rate": 9.990365154573717e-05, "loss": 63.4008, "step": 3 }, { "epoch": 0.01037445290970984, "grad_norm": 16.81085205078125, "learning_rate": 9.961501876182148e-05, "loss": 67.1818, "step": 4 }, { "epoch": 0.0129680661371373, "grad_norm": 20.532699584960938, "learning_rate": 9.913533761814537e-05, "loss": 60.4013, "step": 5 }, { "epoch": 0.015561679364564759, "grad_norm": 21.564678192138672, "learning_rate": 9.846666218300807e-05, "loss": 57.04, "step": 6 }, { "epoch": 0.01815529259199222, "grad_norm": 25.73963165283203, "learning_rate": 9.761185582727977e-05, "loss": 58.4346, "step": 7 }, { "epoch": 0.02074890581941968, "grad_norm": 38.592533111572266, "learning_rate": 9.657457896300791e-05, "loss": 57.8262, "step": 8 }, { "epoch": 0.02334251904684714, "grad_norm": 37.927181243896484, "learning_rate": 9.535927336897098e-05, "loss": 59.3605, "step": 9 }, { "epoch": 0.0259361322742746, "grad_norm": 34.01181411743164, "learning_rate": 9.397114317029975e-05, "loss": 58.7351, "step": 10 }, { "epoch": 0.028529745501702057, "grad_norm": 26.01426124572754, "learning_rate": 9.241613255361455e-05, "loss": 58.2036, "step": 11 }, { "epoch": 0.031123358729129517, "grad_norm": 28.933124542236328, "learning_rate": 9.070090031310558e-05, "loss": 63.9228, "step": 12 }, { "epoch": 0.03371697195655698, "grad_norm": 71.12003326416016, "learning_rate": 8.883279133655399e-05, "loss": 63.5532, "step": 13 }, { "epoch": 0.03631058518398444, "grad_norm": 99.1273422241211, "learning_rate": 8.681980515339464e-05, "loss": 58.6965, "step": 14 }, { "epoch": 0.0389041984114119, "grad_norm": 65.39445495605469, "learning_rate": 8.467056167950311e-05, "loss": 56.3657, "step": 15 }, { "epoch": 0.04149781163883936, "grad_norm": 42.379669189453125, "learning_rate": 8.239426430539243e-05, "loss": 53.4462, "step": 16 }, { "epoch": 0.04409142486626682, "grad_norm": 33.607730865478516, "learning_rate": 8.000066048588211e-05, "loss": 55.2677, "step": 17 }, { "epoch": 0.04668503809369428, "grad_norm": 25.97624969482422, "learning_rate": 7.75e-05, "loss": 50.8529, "step": 18 }, { "epoch": 0.04927865132112174, "grad_norm": 23.127927780151367, "learning_rate": 7.490299105985507e-05, "loss": 52.4718, "step": 19 }, { "epoch": 0.0518722645485492, "grad_norm": 21.260852813720703, "learning_rate": 7.222075445642904e-05, "loss": 53.0907, "step": 20 }, { "epoch": 0.05446587777597666, "grad_norm": 20.860265731811523, "learning_rate": 6.946477593864228e-05, "loss": 53.1623, "step": 21 }, { "epoch": 0.057059491003404114, "grad_norm": 24.28789520263672, "learning_rate": 6.664685702961344e-05, "loss": 55.4951, "step": 22 }, { "epoch": 0.059653104230831575, "grad_norm": 25.533348083496094, "learning_rate": 6.377906449072578e-05, "loss": 55.888, "step": 23 }, { "epoch": 0.062246717458259035, "grad_norm": 31.314680099487305, "learning_rate": 6.087367864990233e-05, "loss": 61.3585, "step": 24 }, { "epoch": 0.0648403306856865, "grad_norm": 47.937957763671875, "learning_rate": 5.794314081535644e-05, "loss": 68.387, "step": 25 }, { "epoch": 0.0648403306856865, "eval_loss": 3.1194334030151367, "eval_runtime": 3.1172, "eval_samples_per_second": 16.04, "eval_steps_per_second": 4.17, "step": 25 }, { "epoch": 0.06743394391311396, "grad_norm": 21.67609977722168, "learning_rate": 5.500000000000001e-05, "loss": 44.0538, "step": 26 }, { "epoch": 0.07002755714054142, "grad_norm": 24.147232055664062, "learning_rate": 5.205685918464356e-05, "loss": 48.1777, "step": 27 }, { "epoch": 0.07262117036796888, "grad_norm": 25.220670700073242, "learning_rate": 4.912632135009769e-05, "loss": 49.6091, "step": 28 }, { "epoch": 0.07521478359539634, "grad_norm": 21.60172462463379, "learning_rate": 4.6220935509274235e-05, "loss": 49.3253, "step": 29 }, { "epoch": 0.0778083968228238, "grad_norm": 19.519107818603516, "learning_rate": 4.3353142970386564e-05, "loss": 51.2563, "step": 30 }, { "epoch": 0.08040201005025126, "grad_norm": 16.33799171447754, "learning_rate": 4.053522406135775e-05, "loss": 50.3858, "step": 31 }, { "epoch": 0.08299562327767872, "grad_norm": 14.904318809509277, "learning_rate": 3.777924554357096e-05, "loss": 50.18, "step": 32 }, { "epoch": 0.08558923650510618, "grad_norm": 14.375073432922363, "learning_rate": 3.509700894014496e-05, "loss": 51.0253, "step": 33 }, { "epoch": 0.08818284973253364, "grad_norm": 15.682596206665039, "learning_rate": 3.250000000000001e-05, "loss": 52.4275, "step": 34 }, { "epoch": 0.0907764629599611, "grad_norm": 17.654769897460938, "learning_rate": 2.9999339514117912e-05, "loss": 52.5927, "step": 35 }, { "epoch": 0.09337007618738856, "grad_norm": 22.502099990844727, "learning_rate": 2.760573569460757e-05, "loss": 57.4791, "step": 36 }, { "epoch": 0.09596368941481602, "grad_norm": 31.115272521972656, "learning_rate": 2.53294383204969e-05, "loss": 61.1302, "step": 37 }, { "epoch": 0.09855730264224348, "grad_norm": 24.96523666381836, "learning_rate": 2.3180194846605367e-05, "loss": 58.228, "step": 38 }, { "epoch": 0.10115091586967094, "grad_norm": 15.320883750915527, "learning_rate": 2.1167208663446025e-05, "loss": 44.4613, "step": 39 }, { "epoch": 0.1037445290970984, "grad_norm": 16.11422348022461, "learning_rate": 1.9299099686894423e-05, "loss": 47.0968, "step": 40 }, { "epoch": 0.10633814232452586, "grad_norm": 15.900169372558594, "learning_rate": 1.758386744638546e-05, "loss": 46.3016, "step": 41 }, { "epoch": 0.10893175555195332, "grad_norm": 15.33053970336914, "learning_rate": 1.602885682970026e-05, "loss": 46.9842, "step": 42 }, { "epoch": 0.11152536877938077, "grad_norm": 13.822281837463379, "learning_rate": 1.464072663102903e-05, "loss": 46.4142, "step": 43 }, { "epoch": 0.11411898200680823, "grad_norm": 13.50814151763916, "learning_rate": 1.3425421036992098e-05, "loss": 48.2081, "step": 44 }, { "epoch": 0.11671259523423569, "grad_norm": 12.32927131652832, "learning_rate": 1.2388144172720251e-05, "loss": 49.4131, "step": 45 }, { "epoch": 0.11930620846166315, "grad_norm": 13.220865249633789, "learning_rate": 1.1533337816991932e-05, "loss": 49.9703, "step": 46 }, { "epoch": 0.12189982168909061, "grad_norm": 16.602933883666992, "learning_rate": 1.0864662381854632e-05, "loss": 53.779, "step": 47 }, { "epoch": 0.12449343491651807, "grad_norm": 19.967239379882812, "learning_rate": 1.0384981238178534e-05, "loss": 54.368, "step": 48 }, { "epoch": 0.12708704814394553, "grad_norm": 24.27589988708496, "learning_rate": 1.0096348454262845e-05, "loss": 56.5035, "step": 49 }, { "epoch": 0.129680661371373, "grad_norm": 43.7401123046875, "learning_rate": 1e-05, "loss": 65.2046, "step": 50 }, { "epoch": 0.129680661371373, "eval_loss": 3.035244941711426, "eval_runtime": 3.1129, "eval_samples_per_second": 16.062, "eval_steps_per_second": 4.176, "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": 5.262429617389568e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }