| { | |
| "best_metric": 0.6442148685455322, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.9002375296912115, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03800475059382423, | |
| "grad_norm": 0.29411759972572327, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03800475059382423, | |
| "eval_loss": 1.0114444494247437, | |
| "eval_runtime": 3.593, | |
| "eval_samples_per_second": 13.916, | |
| "eval_steps_per_second": 3.618, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07600950118764846, | |
| "grad_norm": 0.43555742502212524, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7299, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11401425178147269, | |
| "grad_norm": 0.530921995639801, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.7875, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15201900237529692, | |
| "grad_norm": 0.44882693886756897, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.6892, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19002375296912113, | |
| "grad_norm": 0.5552424192428589, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.8262, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22802850356294538, | |
| "grad_norm": 0.6508234739303589, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.8837, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2660332541567696, | |
| "grad_norm": 0.21037250757217407, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.693, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.30403800475059384, | |
| "grad_norm": 0.2537347078323364, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.4355, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.342042755344418, | |
| "grad_norm": 0.3227172791957855, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.4278, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.38004750593824227, | |
| "grad_norm": 0.3554595410823822, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5003, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4180522565320665, | |
| "grad_norm": 0.3022133409976959, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.5099, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.45605700712589076, | |
| "grad_norm": 0.31370723247528076, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.5727, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.49406175771971494, | |
| "grad_norm": 0.4634961187839508, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.78, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5320665083135392, | |
| "grad_norm": 0.21107812225818634, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5925, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5700712589073634, | |
| "grad_norm": 0.20424596965312958, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5511, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6080760095011877, | |
| "grad_norm": 0.20124682784080505, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.4627, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6460807600950119, | |
| "grad_norm": 0.19492486119270325, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.475, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.684085510688836, | |
| "grad_norm": 0.22841496765613556, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.5942, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7220902612826603, | |
| "grad_norm": 0.27940472960472107, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5875, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7600950118764845, | |
| "grad_norm": 0.19323502480983734, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7253, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7980997624703088, | |
| "grad_norm": 0.14682111144065857, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4848, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.836104513064133, | |
| "grad_norm": 0.18906645476818085, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6015, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8741092636579573, | |
| "grad_norm": 0.18058668076992035, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4769, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9121140142517815, | |
| "grad_norm": 0.1932019293308258, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4867, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9501187648456056, | |
| "grad_norm": 0.24099431931972504, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.6925, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9501187648456056, | |
| "eval_loss": 0.6592954993247986, | |
| "eval_runtime": 3.2051, | |
| "eval_samples_per_second": 15.6, | |
| "eval_steps_per_second": 4.056, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9881235154394299, | |
| "grad_norm": 0.38394269347190857, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7256, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0261282660332542, | |
| "grad_norm": 0.27747994661331177, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.9868, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0641330166270784, | |
| "grad_norm": 0.12342102080583572, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.4239, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1021377672209025, | |
| "grad_norm": 0.15006037056446075, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.5403, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1401425178147269, | |
| "grad_norm": 0.16108109056949615, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.4129, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.178147268408551, | |
| "grad_norm": 0.21113452315330505, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4638, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2161520190023754, | |
| "grad_norm": 0.2221778929233551, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.5473, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2541567695961995, | |
| "grad_norm": 0.16844679415225983, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.5633, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2921615201900236, | |
| "grad_norm": 0.1440643072128296, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.5656, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.330166270783848, | |
| "grad_norm": 0.133246511220932, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.4032, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3681710213776723, | |
| "grad_norm": 0.15566648542881012, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.411, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4061757719714965, | |
| "grad_norm": 0.17614296078681946, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.3639, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4441805225653206, | |
| "grad_norm": 0.2360568791627884, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.6141, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.482185273159145, | |
| "grad_norm": 0.27539122104644775, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.698, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.520190023752969, | |
| "grad_norm": 0.18563823401927948, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4828, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5581947743467932, | |
| "grad_norm": 0.1377231478691101, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.3974, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5961995249406176, | |
| "grad_norm": 0.1511758714914322, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4339, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.634204275534442, | |
| "grad_norm": 0.16694828867912292, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.407, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.672209026128266, | |
| "grad_norm": 0.22149711847305298, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.5053, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7102137767220902, | |
| "grad_norm": 0.2526493966579437, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.5899, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7482185273159145, | |
| "grad_norm": 0.17709076404571533, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.41, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7862232779097387, | |
| "grad_norm": 0.1758945733308792, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.6798, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8242280285035628, | |
| "grad_norm": 0.14024008810520172, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.4317, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8622327790973872, | |
| "grad_norm": 0.15684950351715088, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.4303, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9002375296912115, | |
| "grad_norm": 0.16915641725063324, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3758, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9002375296912115, | |
| "eval_loss": 0.6442148685455322, | |
| "eval_runtime": 3.237, | |
| "eval_samples_per_second": 15.446, | |
| "eval_steps_per_second": 4.016, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |