| { | |
| "best_metric": 0.2970764636993408, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2757669769045157, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005515339538090314, | |
| "grad_norm": 92.01229095458984, | |
| "learning_rate": 5e-05, | |
| "loss": 14.1252, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005515339538090314, | |
| "eval_loss": 18.986474990844727, | |
| "eval_runtime": 2.0408, | |
| "eval_samples_per_second": 24.5, | |
| "eval_steps_per_second": 6.37, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011030679076180628, | |
| "grad_norm": 91.98246002197266, | |
| "learning_rate": 0.0001, | |
| "loss": 14.1252, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016546018614270942, | |
| "grad_norm": 24.650840759277344, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 7.4289, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022061358152361255, | |
| "grad_norm": 12.607400894165039, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.8179, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027576697690451568, | |
| "grad_norm": 8.091282844543457, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.7571, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.033092037228541885, | |
| "grad_norm": 10.43465805053711, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.7366, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.038607376766632194, | |
| "grad_norm": 11.686391830444336, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.6835, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04412271630472251, | |
| "grad_norm": 12.634721755981445, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.0338, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04963805584281282, | |
| "grad_norm": 13.847232818603516, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 5.1388, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.055153395380903136, | |
| "grad_norm": 15.594215393066406, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.0859, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06066873491899345, | |
| "grad_norm": 18.724210739135742, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.7877, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06618407445708377, | |
| "grad_norm": 20.702985763549805, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.1483, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07169941399517407, | |
| "grad_norm": 13.285849571228027, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.0768, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07721475353326439, | |
| "grad_norm": 15.825389862060547, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.3195, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0827300930713547, | |
| "grad_norm": 15.911724090576172, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.5583, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08824543260944502, | |
| "grad_norm": 16.08411979675293, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.4508, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09376077214753534, | |
| "grad_norm": 16.01078224182129, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.096, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09927611168562564, | |
| "grad_norm": 15.624433517456055, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.5246, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10479145122371596, | |
| "grad_norm": 0.6873359084129333, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0159, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11030679076180627, | |
| "grad_norm": 2.893470525741577, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0446, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11582213029989659, | |
| "grad_norm": 4.74436616897583, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0707, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1213374698379869, | |
| "grad_norm": 3.86313533782959, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0572, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1268528093760772, | |
| "grad_norm": 1.5989004373550415, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0243, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13236814891416754, | |
| "grad_norm": 0.4345037341117859, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0081, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13788348845225784, | |
| "grad_norm": 0.12408547103404999, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0034, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13788348845225784, | |
| "eval_loss": 0.5987976789474487, | |
| "eval_runtime": 2.069, | |
| "eval_samples_per_second": 24.167, | |
| "eval_steps_per_second": 6.283, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14339882799034814, | |
| "grad_norm": 14.616813659667969, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.3624, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.14891416752843847, | |
| "grad_norm": 14.416601181030273, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.4517, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.15442950706652878, | |
| "grad_norm": 14.185774803161621, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.4198, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1599448466046191, | |
| "grad_norm": 14.199448585510254, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.2981, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1654601861427094, | |
| "grad_norm": 14.281562805175781, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.1186, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1709755256807997, | |
| "grad_norm": 9.70438289642334, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.6196, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.17649086521889004, | |
| "grad_norm": 1.0650125741958618, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0159, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.18200620475698034, | |
| "grad_norm": 2.1456191539764404, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0318, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.18752154429507067, | |
| "grad_norm": 2.722893714904785, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0416, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.19303688383316098, | |
| "grad_norm": 2.7244069576263428, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0413, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.19855222337125128, | |
| "grad_norm": 2.097538948059082, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0319, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2040675629093416, | |
| "grad_norm": 1.3665951490402222, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0206, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2095829024474319, | |
| "grad_norm": 8.16921329498291, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.4333, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.21509824198552224, | |
| "grad_norm": 13.686884880065918, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.74, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.22061358152361255, | |
| "grad_norm": 13.585527420043945, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.7545, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22612892106170285, | |
| "grad_norm": 13.636950492858887, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.7381, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.23164426059979318, | |
| "grad_norm": 13.520855903625488, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.6922, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.23715960013788348, | |
| "grad_norm": 12.375536918640137, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.5961, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2426749396759738, | |
| "grad_norm": 1.4398314952850342, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0221, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2481902792140641, | |
| "grad_norm": 1.7233232259750366, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0263, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2537056187521544, | |
| "grad_norm": 1.8829046487808228, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0288, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2592209582902447, | |
| "grad_norm": 1.798218011856079, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0273, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2647362978283351, | |
| "grad_norm": 1.6327126026153564, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.025, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2702516373664254, | |
| "grad_norm": 1.388482689857483, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0213, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2757669769045157, | |
| "grad_norm": 1.101733922958374, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0169, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2757669769045157, | |
| "eval_loss": 0.2970764636993408, | |
| "eval_runtime": 2.0581, | |
| "eval_samples_per_second": 24.294, | |
| "eval_steps_per_second": 6.317, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |