|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.3557498318762609, |
|
"eval_steps": 50, |
|
"global_step": 63, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02151983860121049, |
|
"grad_norm": 82.97300720214844, |
|
"learning_rate": 7.499999999999999e-06, |
|
"loss": 84.1949, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.02151983860121049, |
|
"eval_loss": 2.7060768604278564, |
|
"eval_runtime": 26.5108, |
|
"eval_samples_per_second": 5.922, |
|
"eval_steps_per_second": 2.98, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.04303967720242098, |
|
"grad_norm": 78.80287170410156, |
|
"learning_rate": 1.4999999999999999e-05, |
|
"loss": 86.2387, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.06455951580363148, |
|
"grad_norm": 89.162841796875, |
|
"learning_rate": 2.2499999999999998e-05, |
|
"loss": 90.0082, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.08607935440484196, |
|
"grad_norm": 86.92474365234375, |
|
"learning_rate": 2.9999999999999997e-05, |
|
"loss": 84.1448, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.10759919300605246, |
|
"grad_norm": 91.07469940185547, |
|
"learning_rate": 3.75e-05, |
|
"loss": 83.3763, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.12911903160726296, |
|
"grad_norm": 104.43302917480469, |
|
"learning_rate": 4.4999999999999996e-05, |
|
"loss": 81.3885, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.15063887020847344, |
|
"grad_norm": 87.57577514648438, |
|
"learning_rate": 5.2499999999999995e-05, |
|
"loss": 74.0475, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.17215870880968392, |
|
"grad_norm": 62.191646575927734, |
|
"learning_rate": 5.9999999999999995e-05, |
|
"loss": 73.151, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.1936785474108944, |
|
"grad_norm": 46.43473815917969, |
|
"learning_rate": 6.75e-05, |
|
"loss": 65.2091, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.21519838601210492, |
|
"grad_norm": 54.11827850341797, |
|
"learning_rate": 7.5e-05, |
|
"loss": 54.5141, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.2367182246133154, |
|
"grad_norm": 40.347389221191406, |
|
"learning_rate": 8.25e-05, |
|
"loss": 55.1426, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.2582380632145259, |
|
"grad_norm": 90.2418212890625, |
|
"learning_rate": 8.999999999999999e-05, |
|
"loss": 47.8972, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.2797579018157364, |
|
"grad_norm": 38.726844787597656, |
|
"learning_rate": 9.75e-05, |
|
"loss": 39.0781, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.3012777404169469, |
|
"grad_norm": 39.34111022949219, |
|
"learning_rate": 0.00010499999999999999, |
|
"loss": 47.5949, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.32279757901815737, |
|
"grad_norm": 30.686641693115234, |
|
"learning_rate": 0.0001125, |
|
"loss": 36.2625, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.34431741761936785, |
|
"grad_norm": 83.62683868408203, |
|
"learning_rate": 0.00011999999999999999, |
|
"loss": 36.2262, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.36583725622057833, |
|
"grad_norm": 70.50878143310547, |
|
"learning_rate": 0.00012749999999999998, |
|
"loss": 41.3695, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.3873570948217888, |
|
"grad_norm": 61.20938491821289, |
|
"learning_rate": 0.000135, |
|
"loss": 40.6851, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.4088769334229993, |
|
"grad_norm": 54.74737548828125, |
|
"learning_rate": 0.0001425, |
|
"loss": 40.0946, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.43039677202420984, |
|
"grad_norm": 113.8772201538086, |
|
"learning_rate": 0.00015, |
|
"loss": 39.7055, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.4519166106254203, |
|
"grad_norm": 77.01616668701172, |
|
"learning_rate": 0.00014994217771805422, |
|
"loss": 36.2917, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.4734364492266308, |
|
"grad_norm": 24.734567642211914, |
|
"learning_rate": 0.00014976880002998458, |
|
"loss": 38.7726, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.4949562878278413, |
|
"grad_norm": 33.39565658569336, |
|
"learning_rate": 0.00014948013427161947, |
|
"loss": 34.3707, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.5164761264290518, |
|
"grad_norm": 19.322717666625977, |
|
"learning_rate": 0.00014907662554463532, |
|
"loss": 35.1135, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.5379959650302623, |
|
"grad_norm": 25.940776824951172, |
|
"learning_rate": 0.00014855889603024227, |
|
"loss": 35.1159, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.5595158036314728, |
|
"grad_norm": 19.108659744262695, |
|
"learning_rate": 0.00014792774402982574, |
|
"loss": 34.2692, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.5810356422326832, |
|
"grad_norm": 18.458415985107422, |
|
"learning_rate": 0.0001471841427340235, |
|
"loss": 34.6374, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.6025554808338938, |
|
"grad_norm": 27.296424865722656, |
|
"learning_rate": 0.00014632923872213652, |
|
"loss": 31.7279, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.6240753194351042, |
|
"grad_norm": 28.622535705566406, |
|
"learning_rate": 0.0001453643501941863, |
|
"loss": 30.2909, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.6455951580363147, |
|
"grad_norm": 20.236257553100586, |
|
"learning_rate": 0.0001442909649383465, |
|
"loss": 35.5433, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.6671149966375253, |
|
"grad_norm": 20.270566940307617, |
|
"learning_rate": 0.0001431107380368811, |
|
"loss": 30.5242, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.6886348352387357, |
|
"grad_norm": 16.822734832763672, |
|
"learning_rate": 0.00014182548931412757, |
|
"loss": 28.2796, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.7101546738399462, |
|
"grad_norm": 16.062442779541016, |
|
"learning_rate": 0.0001404372005304598, |
|
"loss": 28.5974, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.7316745124411567, |
|
"grad_norm": 20.767465591430664, |
|
"learning_rate": 0.0001389480123265569, |
|
"loss": 25.7476, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.7531943510423672, |
|
"grad_norm": 16.310169219970703, |
|
"learning_rate": 0.0001373602209226909, |
|
"loss": 27.5945, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.7747141896435776, |
|
"grad_norm": 16.240127563476562, |
|
"learning_rate": 0.00013567627457812106, |
|
"loss": 33.9283, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.7962340282447882, |
|
"grad_norm": 21.745182037353516, |
|
"learning_rate": 0.00013389876981605584, |
|
"loss": 32.0565, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.8177538668459986, |
|
"grad_norm": 19.725814819335938, |
|
"learning_rate": 0.00013203044742000233, |
|
"loss": 30.1047, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.8392737054472091, |
|
"grad_norm": 20.058591842651367, |
|
"learning_rate": 0.0001300741882076764, |
|
"loss": 32.32, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.8607935440484197, |
|
"grad_norm": 19.011951446533203, |
|
"learning_rate": 0.00012803300858899104, |
|
"loss": 31.0014, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.8823133826496301, |
|
"grad_norm": 14.620553970336914, |
|
"learning_rate": 0.00012591005591497064, |
|
"loss": 23.4541, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.9038332212508406, |
|
"grad_norm": 18.439016342163086, |
|
"learning_rate": 0.00012370860362476374, |
|
"loss": 21.9652, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.9253530598520511, |
|
"grad_norm": 27.745996475219727, |
|
"learning_rate": 0.00012143204619823755, |
|
"loss": 30.1824, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.9468728984532616, |
|
"grad_norm": 27.515642166137695, |
|
"learning_rate": 0.00011908389392193547, |
|
"loss": 30.4211, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.968392737054472, |
|
"grad_norm": 23.003459930419922, |
|
"learning_rate": 0.00011666776747647015, |
|
"loss": 32.9791, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.9899125756556826, |
|
"grad_norm": 22.867385864257812, |
|
"learning_rate": 0.00011418739235369615, |
|
"loss": 23.7823, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 1.0114324142568931, |
|
"grad_norm": 18.280826568603516, |
|
"learning_rate": 0.00011164659311227163, |
|
"loss": 32.527, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 1.0329522528581037, |
|
"grad_norm": 19.427658081054688, |
|
"learning_rate": 0.00010904928748046599, |
|
"loss": 27.8595, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.054472091459314, |
|
"grad_norm": 19.467891693115234, |
|
"learning_rate": 0.0001063994803153071, |
|
"loss": 26.26, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 1.0759919300605245, |
|
"grad_norm": 16.39354705810547, |
|
"learning_rate": 0.00010370125742738173, |
|
"loss": 24.7449, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.0759919300605245, |
|
"eval_loss": 0.8254633545875549, |
|
"eval_runtime": 26.532, |
|
"eval_samples_per_second": 5.917, |
|
"eval_steps_per_second": 2.978, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.097511768661735, |
|
"grad_norm": 27.119155883789062, |
|
"learning_rate": 0.00010095877928081196, |
|
"loss": 25.2238, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 1.1190316072629456, |
|
"grad_norm": 21.737436294555664, |
|
"learning_rate": 9.817627457812105e-05, |
|
"loss": 24.4688, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 1.1405514458641561, |
|
"grad_norm": 18.230609893798828, |
|
"learning_rate": 9.535803373988056e-05, |
|
"loss": 19.7777, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 1.1620712844653664, |
|
"grad_norm": 17.096773147583008, |
|
"learning_rate": 9.25084022891929e-05, |
|
"loss": 26.5253, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 1.183591123066577, |
|
"grad_norm": 25.87575912475586, |
|
"learning_rate": 8.963177415120962e-05, |
|
"loss": 22.2069, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 1.2051109616677875, |
|
"grad_norm": 21.698827743530273, |
|
"learning_rate": 8.673258487801731e-05, |
|
"loss": 25.7023, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 1.226630800268998, |
|
"grad_norm": 22.29081916809082, |
|
"learning_rate": 8.381530480933783e-05, |
|
"loss": 23.0083, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 1.2481506388702084, |
|
"grad_norm": 19.079532623291016, |
|
"learning_rate": 8.088443217958837e-05, |
|
"loss": 25.0357, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 1.269670477471419, |
|
"grad_norm": 19.22806167602539, |
|
"learning_rate": 7.794448618193015e-05, |
|
"loss": 27.0424, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 1.2911903160726295, |
|
"grad_norm": 20.588699340820312, |
|
"learning_rate": 7.5e-05, |
|
"loss": 23.868, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.31271015467384, |
|
"grad_norm": 21.745031356811523, |
|
"learning_rate": 7.205551381806987e-05, |
|
"loss": 23.2284, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 1.3342299932750503, |
|
"grad_norm": 19.947467803955078, |
|
"learning_rate": 6.911556782041163e-05, |
|
"loss": 26.8844, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 1.3557498318762609, |
|
"grad_norm": 23.738483428955078, |
|
"learning_rate": 6.618469519066217e-05, |
|
"loss": 25.726, |
|
"step": 63 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 100, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 9, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 3.3132684787266355e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|