| { | |
| "best_metric": 4.124476432800293, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6125574272588055, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01225114854517611, | |
| "grad_norm": 10.745503425598145, | |
| "learning_rate": 5e-05, | |
| "loss": 12.2523, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01225114854517611, | |
| "eval_loss": 16.951570510864258, | |
| "eval_runtime": 3.8233, | |
| "eval_samples_per_second": 13.078, | |
| "eval_steps_per_second": 3.4, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02450229709035222, | |
| "grad_norm": 12.49609088897705, | |
| "learning_rate": 0.0001, | |
| "loss": 13.7723, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.036753445635528334, | |
| "grad_norm": 12.550621032714844, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 14.4854, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04900459418070444, | |
| "grad_norm": 13.30091381072998, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.1096, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06125574272588055, | |
| "grad_norm": 13.427345275878906, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.1827, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07350689127105667, | |
| "grad_norm": 12.972816467285156, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 9.2575, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08575803981623277, | |
| "grad_norm": 12.511991500854492, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 8.0594, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09800918836140889, | |
| "grad_norm": 8.507739067077637, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.6818, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11026033690658499, | |
| "grad_norm": 8.837478637695312, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.0018, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1225114854517611, | |
| "grad_norm": 9.772110939025879, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 5.5416, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13476263399693722, | |
| "grad_norm": 6.976329326629639, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 5.2258, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14701378254211334, | |
| "grad_norm": 6.051170825958252, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.939, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.15926493108728942, | |
| "grad_norm": 5.066971302032471, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 4.4208, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.17151607963246554, | |
| "grad_norm": 5.1877851486206055, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.8692, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.18376722817764166, | |
| "grad_norm": 8.28836727142334, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.835, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19601837672281777, | |
| "grad_norm": 4.1470627784729, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.2258, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2082695252679939, | |
| "grad_norm": 4.518736362457275, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.2854, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.22052067381316998, | |
| "grad_norm": 4.851465225219727, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.2111, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2327718223583461, | |
| "grad_norm": 3.9323296546936035, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.3463, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2450229709035222, | |
| "grad_norm": 4.334700584411621, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.4973, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2572741194486983, | |
| "grad_norm": 3.286520004272461, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.196, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.26952526799387444, | |
| "grad_norm": 2.783909797668457, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.909, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.28177641653905056, | |
| "grad_norm": 3.3954567909240723, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.8515, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.29402756508422667, | |
| "grad_norm": 3.312572956085205, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.1752, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.30627871362940273, | |
| "grad_norm": 4.2869343757629395, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.3867, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.30627871362940273, | |
| "eval_loss": 4.312661170959473, | |
| "eval_runtime": 3.4786, | |
| "eval_samples_per_second": 14.374, | |
| "eval_steps_per_second": 3.737, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31852986217457885, | |
| "grad_norm": 4.193575859069824, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.0713, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.33078101071975496, | |
| "grad_norm": 3.1048731803894043, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 3.5151, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3430321592649311, | |
| "grad_norm": 3.3635315895080566, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.2449, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3552833078101072, | |
| "grad_norm": 3.2069332599639893, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.4741, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3675344563552833, | |
| "grad_norm": 3.8977670669555664, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.6004, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.37978560490045943, | |
| "grad_norm": 3.4939961433410645, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.6746, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.39203675344563554, | |
| "grad_norm": 3.7394635677337646, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.8201, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.40428790199081166, | |
| "grad_norm": 3.1073238849639893, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.4163, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4165390505359878, | |
| "grad_norm": 3.247821092605591, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 3.8034, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.42879019908116384, | |
| "grad_norm": 3.812506914138794, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.7354, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.44104134762633995, | |
| "grad_norm": 3.2945432662963867, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.6901, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.45329249617151607, | |
| "grad_norm": 3.4342174530029297, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.1264, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4655436447166922, | |
| "grad_norm": 3.3274176120758057, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.3346, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4777947932618683, | |
| "grad_norm": 3.2000293731689453, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.3675, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4900459418070444, | |
| "grad_norm": 3.530086040496826, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.6042, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5022970903522205, | |
| "grad_norm": 3.0272111892700195, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.8003, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5145482388973966, | |
| "grad_norm": 3.1638290882110596, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.693, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5267993874425727, | |
| "grad_norm": 3.7188827991485596, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.8951, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5390505359877489, | |
| "grad_norm": 5.151864528656006, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 4.0331, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5513016845329249, | |
| "grad_norm": 3.6321349143981934, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.9466, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5635528330781011, | |
| "grad_norm": 3.5160648822784424, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.8945, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5758039816232772, | |
| "grad_norm": 3.2792294025421143, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 4.1007, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5880551301684533, | |
| "grad_norm": 4.167824745178223, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.7118, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6003062787136294, | |
| "grad_norm": 4.040383338928223, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.0598, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6125574272588055, | |
| "grad_norm": 3.9678735733032227, | |
| "learning_rate": 1e-05, | |
| "loss": 4.2144, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6125574272588055, | |
| "eval_loss": 4.124476432800293, | |
| "eval_runtime": 3.4902, | |
| "eval_samples_per_second": 14.326, | |
| "eval_steps_per_second": 3.725, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |