| { | |
| "best_metric": 1.2635948657989502, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.011259993244004054, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00022519986488008108, | |
| "grad_norm": 2.1278951168060303, | |
| "learning_rate": 5e-05, | |
| "loss": 3.074, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022519986488008108, | |
| "eval_loss": 4.716169834136963, | |
| "eval_runtime": 4.3621, | |
| "eval_samples_per_second": 11.462, | |
| "eval_steps_per_second": 2.98, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00045039972976016217, | |
| "grad_norm": 2.8499019145965576, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7294, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006755995946402432, | |
| "grad_norm": 3.092931032180786, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.7785, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009007994595203243, | |
| "grad_norm": 3.2609915733337402, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.1929, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011259993244004053, | |
| "grad_norm": 4.475097179412842, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.7112, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013511991892804864, | |
| "grad_norm": 2.9876198768615723, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2643, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015763990541605676, | |
| "grad_norm": 2.384199380874634, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.0521, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0018015989190406487, | |
| "grad_norm": 3.000969648361206, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.8703, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0020267987839207298, | |
| "grad_norm": 2.2856993675231934, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.8155, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0022519986488008107, | |
| "grad_norm": 3.448403835296631, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.7403, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002477198513680892, | |
| "grad_norm": 2.4281277656555176, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.6285, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002702398378560973, | |
| "grad_norm": 1.6444188356399536, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.7825, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0029275982434410538, | |
| "grad_norm": 3.361898899078369, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.7924, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003152798108321135, | |
| "grad_norm": 2.4469213485717773, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6112, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003377997973201216, | |
| "grad_norm": 1.2440874576568604, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.5038, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0036031978380812973, | |
| "grad_norm": 1.0188878774642944, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.422, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0038283977029613782, | |
| "grad_norm": 1.1848514080047607, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.4293, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0040535975678414595, | |
| "grad_norm": 1.1049160957336426, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.3361, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00427879743272154, | |
| "grad_norm": 1.1141437292099, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.5148, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004503997297601621, | |
| "grad_norm": 0.9767174124717712, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.455, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004729197162481703, | |
| "grad_norm": 1.102776288986206, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.4185, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004954397027361784, | |
| "grad_norm": 1.1417127847671509, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.4333, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0051795968922418644, | |
| "grad_norm": 1.070078730583191, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.4496, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005404796757121946, | |
| "grad_norm": 0.9801068305969238, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.4157, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005629996622002027, | |
| "grad_norm": 1.6465044021606445, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.6247, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005629996622002027, | |
| "eval_loss": 1.382283329963684, | |
| "eval_runtime": 4.3747, | |
| "eval_samples_per_second": 11.429, | |
| "eval_steps_per_second": 2.972, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0058551964868821076, | |
| "grad_norm": 1.4691429138183594, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.4322, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006080396351762189, | |
| "grad_norm": 1.2287325859069824, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.3127, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00630559621664227, | |
| "grad_norm": 1.1598153114318848, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.34, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006530796081522351, | |
| "grad_norm": 0.9561071991920471, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.3157, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006755995946402432, | |
| "grad_norm": 1.0402426719665527, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2949, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006981195811282513, | |
| "grad_norm": 0.8111638426780701, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.1885, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.007206395676162595, | |
| "grad_norm": 0.9830905795097351, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.2732, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.007431595541042675, | |
| "grad_norm": 0.9290409088134766, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.3023, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0076567954059227564, | |
| "grad_norm": 1.0560059547424316, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.3375, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007881995270802838, | |
| "grad_norm": 1.053708791732788, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.3542, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008107195135682919, | |
| "grad_norm": 1.1545864343643188, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.415, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.008332395000563, | |
| "grad_norm": 1.4278931617736816, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.4864, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.00855759486544308, | |
| "grad_norm": 0.9526941180229187, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.203, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.008782794730323161, | |
| "grad_norm": 1.0327879190444946, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.2277, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009007994595203243, | |
| "grad_norm": 1.0579802989959717, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.2959, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009233194460083324, | |
| "grad_norm": 0.8935350179672241, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.3103, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.009458394324963405, | |
| "grad_norm": 0.7780750393867493, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3531, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.009683594189843487, | |
| "grad_norm": 0.745571494102478, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.3248, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009908794054723568, | |
| "grad_norm": 0.7142487168312073, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2679, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.010133993919603648, | |
| "grad_norm": 0.7780869007110596, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.3402, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.010359193784483729, | |
| "grad_norm": 0.7028299570083618, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.2582, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01058439364936381, | |
| "grad_norm": 0.9651392102241516, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.3955, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.010809593514243892, | |
| "grad_norm": 0.9906733632087708, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.4157, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.011034793379123973, | |
| "grad_norm": 1.2405346632003784, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.4454, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.011259993244004054, | |
| "grad_norm": 1.7434841394424438, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4865, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011259993244004054, | |
| "eval_loss": 1.2635948657989502, | |
| "eval_runtime": 4.3362, | |
| "eval_samples_per_second": 11.531, | |
| "eval_steps_per_second": 2.998, | |
| "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": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |