| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0033519553072625, | |
| "eval_steps": 14, | |
| "global_step": 56, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017877094972067038, | |
| "grad_norm": 0.008051837794482708, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9287, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017877094972067038, | |
| "eval_loss": 11.928812026977539, | |
| "eval_runtime": 17.7636, | |
| "eval_samples_per_second": 5.348, | |
| "eval_steps_per_second": 2.702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.035754189944134075, | |
| "grad_norm": 0.008926309645175934, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9296, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.053631284916201116, | |
| "grad_norm": 0.00831968616694212, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9287, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07150837988826815, | |
| "grad_norm": 0.007635825779289007, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9297, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0893854748603352, | |
| "grad_norm": 0.006136827636510134, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9308, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10726256983240223, | |
| "grad_norm": 0.008952487260103226, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9298, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12513966480446928, | |
| "grad_norm": 0.008229999803006649, | |
| "learning_rate": 7e-05, | |
| "loss": 11.9316, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1430167597765363, | |
| "grad_norm": 0.008337481878697872, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9323, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16089385474860335, | |
| "grad_norm": 0.0077857039868831635, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9287, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1787709497206704, | |
| "grad_norm": 0.007779798936098814, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9293, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19664804469273742, | |
| "grad_norm": 0.010903590358793736, | |
| "learning_rate": 9.988343845952697e-05, | |
| "loss": 11.9297, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.21452513966480447, | |
| "grad_norm": 0.008899732492864132, | |
| "learning_rate": 9.953429730181653e-05, | |
| "loss": 11.929, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2324022346368715, | |
| "grad_norm": 0.008686481043696404, | |
| "learning_rate": 9.895420438411616e-05, | |
| "loss": 11.9327, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.25027932960893856, | |
| "grad_norm": 0.008174674585461617, | |
| "learning_rate": 9.814586436738998e-05, | |
| "loss": 11.9286, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.25027932960893856, | |
| "eval_loss": 11.928715705871582, | |
| "eval_runtime": 0.3873, | |
| "eval_samples_per_second": 245.313, | |
| "eval_steps_per_second": 123.947, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2681564245810056, | |
| "grad_norm": 0.008636604063212872, | |
| "learning_rate": 9.711304610594104e-05, | |
| "loss": 11.9307, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2860335195530726, | |
| "grad_norm": 0.009689634665846825, | |
| "learning_rate": 9.586056507527266e-05, | |
| "loss": 11.9291, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3039106145251397, | |
| "grad_norm": 0.007181845605373383, | |
| "learning_rate": 9.439426092011875e-05, | |
| "loss": 11.9316, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3217877094972067, | |
| "grad_norm": 0.00760689377784729, | |
| "learning_rate": 9.272097022732443e-05, | |
| "loss": 11.9297, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3396648044692737, | |
| "grad_norm": 0.007029213942587376, | |
| "learning_rate": 9.08484946505221e-05, | |
| "loss": 11.9308, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3575418994413408, | |
| "grad_norm": 0.009038039483129978, | |
| "learning_rate": 8.8785564535221e-05, | |
| "loss": 11.931, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3754189944134078, | |
| "grad_norm": 0.0075072660110890865, | |
| "learning_rate": 8.654179821390621e-05, | |
| "loss": 11.9313, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.39329608938547483, | |
| "grad_norm": 0.00974891148507595, | |
| "learning_rate": 8.412765716093272e-05, | |
| "loss": 11.9313, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4111731843575419, | |
| "grad_norm": 0.0073928870260715485, | |
| "learning_rate": 8.155439721630264e-05, | |
| "loss": 11.9301, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.42905027932960893, | |
| "grad_norm": 0.009019100107252598, | |
| "learning_rate": 7.883401610574336e-05, | |
| "loss": 11.9291, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.44692737430167595, | |
| "grad_norm": 0.007918241433799267, | |
| "learning_rate": 7.597919750177168e-05, | |
| "loss": 11.9313, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.464804469273743, | |
| "grad_norm": 0.009383410215377808, | |
| "learning_rate": 7.300325188655761e-05, | |
| "loss": 11.9298, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.48268156424581005, | |
| "grad_norm": 0.008459771983325481, | |
| "learning_rate": 6.992005449231208e-05, | |
| "loss": 11.9309, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5005586592178771, | |
| "grad_norm": 0.008441867306828499, | |
| "learning_rate": 6.674398060854931e-05, | |
| "loss": 11.9304, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5005586592178771, | |
| "eval_loss": 11.928580284118652, | |
| "eval_runtime": 0.3886, | |
| "eval_samples_per_second": 244.488, | |
| "eval_steps_per_second": 123.531, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5184357541899441, | |
| "grad_norm": 0.010095364414155483, | |
| "learning_rate": 6.348983855785121e-05, | |
| "loss": 11.9277, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5363128491620112, | |
| "grad_norm": 0.007604570593684912, | |
| "learning_rate": 6.01728006526317e-05, | |
| "loss": 11.9298, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5541899441340782, | |
| "grad_norm": 0.0103254783898592, | |
| "learning_rate": 5.680833245481234e-05, | |
| "loss": 11.9283, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5720670391061452, | |
| "grad_norm": 0.00810755044221878, | |
| "learning_rate": 5.341212066823355e-05, | |
| "loss": 11.931, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5899441340782123, | |
| "grad_norm": 0.007562727201730013, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9287, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6078212290502794, | |
| "grad_norm": 0.008853144943714142, | |
| "learning_rate": 4.658787933176646e-05, | |
| "loss": 11.9304, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6256983240223464, | |
| "grad_norm": 0.009539203718304634, | |
| "learning_rate": 4.319166754518768e-05, | |
| "loss": 11.93, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6435754189944134, | |
| "grad_norm": 0.009173383004963398, | |
| "learning_rate": 3.982719934736832e-05, | |
| "loss": 11.9296, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6614525139664804, | |
| "grad_norm": 0.008169720880687237, | |
| "learning_rate": 3.651016144214878e-05, | |
| "loss": 11.9302, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6793296089385474, | |
| "grad_norm": 0.008827430196106434, | |
| "learning_rate": 3.325601939145069e-05, | |
| "loss": 11.9295, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6972067039106146, | |
| "grad_norm": 0.010021938011050224, | |
| "learning_rate": 3.007994550768793e-05, | |
| "loss": 11.9299, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7150837988826816, | |
| "grad_norm": 0.010521038435399532, | |
| "learning_rate": 2.6996748113442394e-05, | |
| "loss": 11.9308, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7329608938547486, | |
| "grad_norm": 0.009070714004337788, | |
| "learning_rate": 2.4020802498228335e-05, | |
| "loss": 11.93, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7508379888268156, | |
| "grad_norm": 0.008820487186312675, | |
| "learning_rate": 2.1165983894256647e-05, | |
| "loss": 11.9279, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7508379888268156, | |
| "eval_loss": 11.928503036499023, | |
| "eval_runtime": 0.3804, | |
| "eval_samples_per_second": 249.752, | |
| "eval_steps_per_second": 126.19, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7687150837988826, | |
| "grad_norm": 0.010876229964196682, | |
| "learning_rate": 1.8445602783697374e-05, | |
| "loss": 11.9305, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7865921787709497, | |
| "grad_norm": 0.008084769360721111, | |
| "learning_rate": 1.5872342839067306e-05, | |
| "loss": 11.9299, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8044692737430168, | |
| "grad_norm": 0.009019813500344753, | |
| "learning_rate": 1.3458201786093794e-05, | |
| "loss": 11.9283, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8223463687150838, | |
| "grad_norm": 0.008098295889794827, | |
| "learning_rate": 1.1214435464779006e-05, | |
| "loss": 11.9292, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8402234636871508, | |
| "grad_norm": 0.008133570663630962, | |
| "learning_rate": 9.151505349477902e-06, | |
| "loss": 11.9289, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8581005586592179, | |
| "grad_norm": 0.012650455348193645, | |
| "learning_rate": 7.2790297726755716e-06, | |
| "loss": 11.9302, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8759776536312849, | |
| "grad_norm": 0.009691119194030762, | |
| "learning_rate": 5.605739079881239e-06, | |
| "loss": 11.9307, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8938547486033519, | |
| "grad_norm": 0.009178046137094498, | |
| "learning_rate": 4.139434924727359e-06, | |
| "loss": 11.9297, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.911731843575419, | |
| "grad_norm": 0.008271483704447746, | |
| "learning_rate": 2.88695389405898e-06, | |
| "loss": 11.9291, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.929608938547486, | |
| "grad_norm": 0.00795311015099287, | |
| "learning_rate": 1.8541356326100433e-06, | |
| "loss": 11.9286, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.9474860335195531, | |
| "grad_norm": 0.008445663377642632, | |
| "learning_rate": 1.0457956158838544e-06, | |
| "loss": 11.932, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.9653631284916201, | |
| "grad_norm": 0.009014743380248547, | |
| "learning_rate": 4.6570269818346224e-07, | |
| "loss": 11.9283, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9832402234636871, | |
| "grad_norm": 0.009628918021917343, | |
| "learning_rate": 1.1656154047303691e-07, | |
| "loss": 11.9317, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.0033519553072625, | |
| "grad_norm": 0.00985956471413374, | |
| "learning_rate": 0.0, | |
| "loss": 13.9592, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.0033519553072625, | |
| "eval_loss": 11.928487777709961, | |
| "eval_runtime": 0.3738, | |
| "eval_samples_per_second": 254.136, | |
| "eval_steps_per_second": 128.405, | |
| "step": 56 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 56, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 14, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 26468155392.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |