| { | |
| "best_metric": 0.7226464152336121, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-600", | |
| "epoch": 0.11953977187826867, | |
| "eval_steps": 50, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019923295313044778, | |
| "eval_loss": 1.1138875484466553, | |
| "eval_runtime": 600.9987, | |
| "eval_samples_per_second": 14.067, | |
| "eval_steps_per_second": 3.517, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019923295313044776, | |
| "grad_norm": 0.4403154253959656, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9082, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003984659062608955, | |
| "grad_norm": 0.4901919364929199, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 0.822, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005976988593913433, | |
| "grad_norm": 0.3764132857322693, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 0.8049, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00796931812521791, | |
| "grad_norm": 0.45194122195243835, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 0.8085, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009961647656522389, | |
| "grad_norm": 0.3927149176597595, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 0.8338, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009961647656522389, | |
| "eval_loss": 0.7959496974945068, | |
| "eval_runtime": 604.4502, | |
| "eval_samples_per_second": 13.986, | |
| "eval_steps_per_second": 3.497, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011953977187826866, | |
| "grad_norm": 0.3628771901130676, | |
| "learning_rate": 0.0001964767868814516, | |
| "loss": 0.6936, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.013946306719131345, | |
| "grad_norm": 0.2550435960292816, | |
| "learning_rate": 0.00019493976084683813, | |
| "loss": 0.7383, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01593863625043582, | |
| "grad_norm": 0.36278122663497925, | |
| "learning_rate": 0.00019313361774523385, | |
| "loss": 0.764, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0179309657817403, | |
| "grad_norm": 0.30000317096710205, | |
| "learning_rate": 0.00019106347728549135, | |
| "loss": 0.8089, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.019923295313044778, | |
| "grad_norm": 0.34697186946868896, | |
| "learning_rate": 0.00018873520750565718, | |
| "loss": 0.8007, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.019923295313044778, | |
| "eval_loss": 0.7775644063949585, | |
| "eval_runtime": 605.6715, | |
| "eval_samples_per_second": 13.958, | |
| "eval_steps_per_second": 3.49, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.021915624844349255, | |
| "grad_norm": 0.2640015780925751, | |
| "learning_rate": 0.0001861554081393806, | |
| "loss": 0.7055, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.023907954375653732, | |
| "grad_norm": 0.28417935967445374, | |
| "learning_rate": 0.0001833313919082515, | |
| "loss": 0.7715, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02590028390695821, | |
| "grad_norm": 0.36866042017936707, | |
| "learning_rate": 0.00018027116379309638, | |
| "loss": 0.7669, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02789261343826269, | |
| "grad_norm": 0.3625430464744568, | |
| "learning_rate": 0.00017698339834299061, | |
| "loss": 0.7763, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.029884942969567167, | |
| "grad_norm": 0.34403666853904724, | |
| "learning_rate": 0.00017347741508630672, | |
| "loss": 0.8049, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.029884942969567167, | |
| "eval_loss": 0.7656979560852051, | |
| "eval_runtime": 604.7609, | |
| "eval_samples_per_second": 13.979, | |
| "eval_steps_per_second": 3.496, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03187727250087164, | |
| "grad_norm": 0.2931734621524811, | |
| "learning_rate": 0.0001697631521134985, | |
| "loss": 0.7082, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03386960203217612, | |
| "grad_norm": 0.283248633146286, | |
| "learning_rate": 0.00016585113790650388, | |
| "loss": 0.7325, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0358619315634806, | |
| "grad_norm": 0.2728399336338043, | |
| "learning_rate": 0.0001617524614946192, | |
| "loss": 0.729, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.037854261094785076, | |
| "grad_norm": 0.8360651731491089, | |
| "learning_rate": 0.0001574787410214407, | |
| "loss": 0.7719, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.039846590626089556, | |
| "grad_norm": 0.3889768123626709, | |
| "learning_rate": 0.00015304209081197425, | |
| "loss": 0.7982, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.039846590626089556, | |
| "eval_loss": 0.7610375881195068, | |
| "eval_runtime": 604.5446, | |
| "eval_samples_per_second": 13.984, | |
| "eval_steps_per_second": 3.497, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04183892015739403, | |
| "grad_norm": 0.27866795659065247, | |
| "learning_rate": 0.00014845508703326504, | |
| "loss": 0.6983, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.04383124968869851, | |
| "grad_norm": 0.2734178602695465, | |
| "learning_rate": 0.00014373073204588556, | |
| "loss": 0.7061, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04582357922000299, | |
| "grad_norm": 0.31276145577430725, | |
| "learning_rate": 0.00013888241754733208, | |
| "loss": 0.7253, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.047815908751307465, | |
| "grad_norm": 0.3338753283023834, | |
| "learning_rate": 0.00013392388661180303, | |
| "loss": 0.7424, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.049808238282611945, | |
| "grad_norm": 0.3599971830844879, | |
| "learning_rate": 0.0001288691947339621, | |
| "loss": 0.771, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.049808238282611945, | |
| "eval_loss": 0.7497034668922424, | |
| "eval_runtime": 604.7251, | |
| "eval_samples_per_second": 13.98, | |
| "eval_steps_per_second": 3.496, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.05180056781391642, | |
| "grad_norm": 0.2486254721879959, | |
| "learning_rate": 0.0001237326699871115, | |
| "loss": 0.6559, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.0537928973452209, | |
| "grad_norm": 0.2816349267959595, | |
| "learning_rate": 0.00011852887240871145, | |
| "loss": 0.7098, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.05578522687652538, | |
| "grad_norm": 0.26698997616767883, | |
| "learning_rate": 0.00011327255272837221, | |
| "loss": 0.7363, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.057777556407829854, | |
| "grad_norm": 0.38490164279937744, | |
| "learning_rate": 0.00010797861055530831, | |
| "loss": 0.7449, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.059769885939134335, | |
| "grad_norm": 0.34599632024765015, | |
| "learning_rate": 0.00010266205214377748, | |
| "loss": 0.7604, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.059769885939134335, | |
| "eval_loss": 0.7407906651496887, | |
| "eval_runtime": 605.4292, | |
| "eval_samples_per_second": 13.964, | |
| "eval_steps_per_second": 3.492, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06176221547043881, | |
| "grad_norm": 0.30134573578834534, | |
| "learning_rate": 9.733794785622253e-05, | |
| "loss": 0.6773, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.06375454500174328, | |
| "grad_norm": 0.28048670291900635, | |
| "learning_rate": 9.202138944469168e-05, | |
| "loss": 0.6969, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.06574687453304777, | |
| "grad_norm": 0.32149261236190796, | |
| "learning_rate": 8.672744727162781e-05, | |
| "loss": 0.7026, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.06773920406435224, | |
| "grad_norm": 0.3494367301464081, | |
| "learning_rate": 8.147112759128859e-05, | |
| "loss": 0.7413, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.06973153359565672, | |
| "grad_norm": 0.4458478093147278, | |
| "learning_rate": 7.626733001288851e-05, | |
| "loss": 0.7612, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06973153359565672, | |
| "eval_loss": 0.735527515411377, | |
| "eval_runtime": 604.4756, | |
| "eval_samples_per_second": 13.986, | |
| "eval_steps_per_second": 3.497, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.0717238631269612, | |
| "grad_norm": 0.2828379273414612, | |
| "learning_rate": 7.113080526603792e-05, | |
| "loss": 0.6987, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.07371619265826568, | |
| "grad_norm": 0.3044438362121582, | |
| "learning_rate": 6.607611338819697e-05, | |
| "loss": 0.7014, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.07570852218957015, | |
| "grad_norm": 0.35144269466400146, | |
| "learning_rate": 6.111758245266794e-05, | |
| "loss": 0.7053, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.07770085172087464, | |
| "grad_norm": 0.37965935468673706, | |
| "learning_rate": 5.626926795411447e-05, | |
| "loss": 0.7327, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.07969318125217911, | |
| "grad_norm": 0.4066285192966461, | |
| "learning_rate": 5.1544912966734994e-05, | |
| "loss": 0.7586, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07969318125217911, | |
| "eval_loss": 0.7312402129173279, | |
| "eval_runtime": 604.9779, | |
| "eval_samples_per_second": 13.974, | |
| "eval_steps_per_second": 3.494, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.08168551078348359, | |
| "grad_norm": 0.28389105200767517, | |
| "learning_rate": 4.695790918802576e-05, | |
| "loss": 0.6942, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.08367784031478806, | |
| "grad_norm": 0.24920526146888733, | |
| "learning_rate": 4.252125897855932e-05, | |
| "loss": 0.7292, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.08567016984609255, | |
| "grad_norm": 0.32768023014068604, | |
| "learning_rate": 3.824753850538082e-05, | |
| "loss": 0.6935, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.08766249937739702, | |
| "grad_norm": 0.2882814407348633, | |
| "learning_rate": 3.414886209349615e-05, | |
| "loss": 0.6909, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.0896548289087015, | |
| "grad_norm": 0.35527971386909485, | |
| "learning_rate": 3.0236847886501542e-05, | |
| "loss": 0.7639, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.0896548289087015, | |
| "eval_loss": 0.725193440914154, | |
| "eval_runtime": 604.3416, | |
| "eval_samples_per_second": 13.989, | |
| "eval_steps_per_second": 3.498, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.09164715844000598, | |
| "grad_norm": 0.3175693452358246, | |
| "learning_rate": 2.6522584913693294e-05, | |
| "loss": 0.6855, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.09363948797131046, | |
| "grad_norm": 0.28028416633605957, | |
| "learning_rate": 2.301660165700936e-05, | |
| "loss": 0.6913, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.09563181750261493, | |
| "grad_norm": 0.26005247235298157, | |
| "learning_rate": 1.9728836206903656e-05, | |
| "loss": 0.6725, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.0976241470339194, | |
| "grad_norm": 0.2885555624961853, | |
| "learning_rate": 1.6668608091748495e-05, | |
| "loss": 0.7315, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.09961647656522389, | |
| "grad_norm": 0.3878602385520935, | |
| "learning_rate": 1.3844591860619383e-05, | |
| "loss": 0.7605, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09961647656522389, | |
| "eval_loss": 0.7219599485397339, | |
| "eval_runtime": 605.6943, | |
| "eval_samples_per_second": 13.958, | |
| "eval_steps_per_second": 3.49, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.10160880609652836, | |
| "grad_norm": 0.3010750710964203, | |
| "learning_rate": 1.1264792494342857e-05, | |
| "loss": 0.6475, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.10360113562783284, | |
| "grad_norm": 0.2743396461009979, | |
| "learning_rate": 8.936522714508678e-06, | |
| "loss": 0.6809, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.10559346515913733, | |
| "grad_norm": 0.3698458969593048, | |
| "learning_rate": 6.866382254766157e-06, | |
| "loss": 0.7357, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.1075857946904418, | |
| "grad_norm": 0.2824854552745819, | |
| "learning_rate": 5.060239153161872e-06, | |
| "loss": 0.7327, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.10957812422174627, | |
| "grad_norm": 0.3766637444496155, | |
| "learning_rate": 3.5232131185484076e-06, | |
| "loss": 0.7644, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.10957812422174627, | |
| "eval_loss": 0.7227113246917725, | |
| "eval_runtime": 606.1455, | |
| "eval_samples_per_second": 13.947, | |
| "eval_steps_per_second": 3.488, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.11157045375305076, | |
| "grad_norm": 0.2523180842399597, | |
| "learning_rate": 2.259661018213333e-06, | |
| "loss": 0.6927, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.11356278328435523, | |
| "grad_norm": 0.3261297643184662, | |
| "learning_rate": 1.2731645278655445e-06, | |
| "loss": 0.7312, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.11555511281565971, | |
| "grad_norm": 0.3216928541660309, | |
| "learning_rate": 5.665199789862907e-07, | |
| "loss": 0.7011, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.11754744234696418, | |
| "grad_norm": 0.33191266655921936, | |
| "learning_rate": 1.4173043232380557e-07, | |
| "loss": 0.7112, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.11953977187826867, | |
| "grad_norm": 0.3486833870410919, | |
| "learning_rate": 0.0, | |
| "loss": 0.7377, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11953977187826867, | |
| "eval_loss": 0.7226464152336121, | |
| "eval_runtime": 604.8428, | |
| "eval_samples_per_second": 13.977, | |
| "eval_steps_per_second": 3.495, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 7.928178145524449e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |