Invalid JSON: Unexpected token 'N', ..."al_loss": NaN,
"... is not valid JSON
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 406, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024630541871921183, | |
| "grad_norm": 0.12471067905426025, | |
| "learning_rate": 4.8780487804878055e-06, | |
| "loss": 0.7732, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012315270935960592, | |
| "grad_norm": 0.13646408915519714, | |
| "learning_rate": 2.4390243902439026e-05, | |
| "loss": 0.7946, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024630541871921183, | |
| "grad_norm": 0.11706612259149551, | |
| "learning_rate": 4.878048780487805e-05, | |
| "loss": 0.7754, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03694581280788178, | |
| "grad_norm": 0.12706132233142853, | |
| "learning_rate": 7.317073170731707e-05, | |
| "loss": 0.7598, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04926108374384237, | |
| "grad_norm": 0.10962966084480286, | |
| "learning_rate": 9.75609756097561e-05, | |
| "loss": 0.7736, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06157635467980296, | |
| "grad_norm": 0.10052120685577393, | |
| "learning_rate": 0.00012195121951219512, | |
| "loss": 0.7773, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07389162561576355, | |
| "grad_norm": 0.0974399521946907, | |
| "learning_rate": 0.00014634146341463414, | |
| "loss": 0.7592, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08620689655172414, | |
| "grad_norm": 0.10327592492103577, | |
| "learning_rate": 0.0001707317073170732, | |
| "loss": 0.766, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09852216748768473, | |
| "grad_norm": 0.10549774765968323, | |
| "learning_rate": 0.0001951219512195122, | |
| "loss": 0.7656, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11083743842364532, | |
| "grad_norm": 0.13311924040317535, | |
| "learning_rate": 0.0001999407400739705, | |
| "loss": 0.7578, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12315270935960591, | |
| "grad_norm": 0.10272041708230972, | |
| "learning_rate": 0.00019970011699250152, | |
| "loss": 0.7683, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1354679802955665, | |
| "grad_norm": 0.1121869683265686, | |
| "learning_rate": 0.00019927487224577402, | |
| "loss": 0.7397, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1477832512315271, | |
| "grad_norm": 0.10058727860450745, | |
| "learning_rate": 0.0001986657932891657, | |
| "loss": 0.7605, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16009852216748768, | |
| "grad_norm": 0.09491652250289917, | |
| "learning_rate": 0.00019787400799669154, | |
| "loss": 0.7506, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 0.09636498987674713, | |
| "learning_rate": 0.00019690098257244064, | |
| "loss": 0.7414, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18472906403940886, | |
| "grad_norm": 0.09627745300531387, | |
| "learning_rate": 0.00019574851883550395, | |
| "loss": 0.7639, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19704433497536947, | |
| "grad_norm": 0.09506456553936005, | |
| "learning_rate": 0.00019441875088341997, | |
| "loss": 0.7442, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20935960591133004, | |
| "grad_norm": 0.09437121450901031, | |
| "learning_rate": 0.00019291414114031743, | |
| "loss": 0.7653, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22167487684729065, | |
| "grad_norm": 0.09612101316452026, | |
| "learning_rate": 0.00019123747579707275, | |
| "loss": 0.7493, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23399014778325122, | |
| "grad_norm": 0.09520900249481201, | |
| "learning_rate": 0.0001893918596519257, | |
| "loss": 0.7494, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.24630541871921183, | |
| "grad_norm": 0.09202856570482254, | |
| "learning_rate": 0.00018738071036110808, | |
| "loss": 0.7437, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25862068965517243, | |
| "grad_norm": 0.09562040865421295, | |
| "learning_rate": 0.00018520775211013093, | |
| "loss": 0.7356, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.270935960591133, | |
| "grad_norm": 0.09436768293380737, | |
| "learning_rate": 0.00018287700871745036, | |
| "loss": 0.7413, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2832512315270936, | |
| "grad_norm": 0.09223506599664688, | |
| "learning_rate": 0.00018039279618328212, | |
| "loss": 0.7642, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2955665024630542, | |
| "grad_norm": 0.09327235072851181, | |
| "learning_rate": 0.0001777597146973627, | |
| "loss": 0.7551, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3078817733990148, | |
| "grad_norm": 0.08710304647684097, | |
| "learning_rate": 0.00017498264012045687, | |
| "loss": 0.7452, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.32019704433497537, | |
| "grad_norm": 0.09283468127250671, | |
| "learning_rate": 0.00017206671495538612, | |
| "loss": 0.7525, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33251231527093594, | |
| "grad_norm": 0.0989128053188324, | |
| "learning_rate": 0.0001690173388242972, | |
| "loss": 0.7557, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 0.09394516050815582, | |
| "learning_rate": 0.0001658401584698049, | |
| "loss": 0.7489, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 0.09611286222934723, | |
| "learning_rate": 0.00016254105729852464, | |
| "loss": 0.7458, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3694581280788177, | |
| "grad_norm": 0.09375113993883133, | |
| "learning_rate": 0.00015912614448635782, | |
| "loss": 0.748, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3817733990147783, | |
| "grad_norm": 0.09553772956132889, | |
| "learning_rate": 0.00015560174366570446, | |
| "loss": 0.7329, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.39408866995073893, | |
| "grad_norm": 0.09203081578016281, | |
| "learning_rate": 0.0001519743812155516, | |
| "loss": 0.7247, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4064039408866995, | |
| "grad_norm": 0.09693845361471176, | |
| "learning_rate": 0.00014825077417612186, | |
| "loss": 0.7598, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4187192118226601, | |
| "grad_norm": 0.09536159783601761, | |
| "learning_rate": 0.00014443781781046136, | |
| "loss": 0.7396, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.43103448275862066, | |
| "grad_norm": 0.0956893116235733, | |
| "learning_rate": 0.00014054257283599973, | |
| "loss": 0.7777, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4433497536945813, | |
| "grad_norm": 0.09435797482728958, | |
| "learning_rate": 0.00013657225234972695, | |
| "loss": 0.7404, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.45566502463054187, | |
| "grad_norm": 0.10020274668931961, | |
| "learning_rate": 0.00013253420847119803, | |
| "loss": 0.7603, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.46798029556650245, | |
| "grad_norm": 0.09175912290811539, | |
| "learning_rate": 0.0001284359187281004, | |
| "loss": 0.7335, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4802955665024631, | |
| "grad_norm": 0.09388455748558044, | |
| "learning_rate": 0.0001242849722095936, | |
| "loss": 0.7459, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.49261083743842365, | |
| "grad_norm": 0.090743288397789, | |
| "learning_rate": 0.00012008905551306356, | |
| "loss": 0.7351, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5049261083743842, | |
| "grad_norm": 0.08773265033960342, | |
| "learning_rate": 0.00011585593851031347, | |
| "loss": 0.7409, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.5172413793103449, | |
| "grad_norm": 0.09125316888093948, | |
| "learning_rate": 0.00011159345995955006, | |
| "loss": 0.7527, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5295566502463054, | |
| "grad_norm": 0.09029875695705414, | |
| "learning_rate": 0.00010730951298980776, | |
| "loss": 0.7414, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.541871921182266, | |
| "grad_norm": 0.09226856380701065, | |
| "learning_rate": 0.00010301203048469083, | |
| "loss": 0.7458, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5541871921182266, | |
| "grad_norm": 0.0976998433470726, | |
| "learning_rate": 9.870897039249911e-05, | |
| "loss": 0.7328, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5665024630541872, | |
| "grad_norm": 0.09883327782154083, | |
| "learning_rate": 9.440830098993969e-05, | |
| "loss": 0.754, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5788177339901478, | |
| "grad_norm": 0.09602724015712738, | |
| "learning_rate": 9.011798612671286e-05, | |
| "loss": 0.7551, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.5911330049261084, | |
| "grad_norm": 0.09901835024356842, | |
| "learning_rate": 8.58459704782957e-05, | |
| "loss": 0.735, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.603448275862069, | |
| "grad_norm": 0.09128189831972122, | |
| "learning_rate": 8.160016483423199e-05, | |
| "loss": 0.733, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.6157635467980296, | |
| "grad_norm": 0.09079871326684952, | |
| "learning_rate": 7.738843144917119e-05, | |
| "loss": 0.7292, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6280788177339901, | |
| "grad_norm": 0.09508458524942398, | |
| "learning_rate": 7.321856948378259e-05, | |
| "loss": 0.743, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.6403940886699507, | |
| "grad_norm": 0.09585162997245789, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.7549, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6527093596059114, | |
| "grad_norm": 0.09590860456228256, | |
| "learning_rate": 6.503525447487715e-05, | |
| "loss": 0.7487, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.6650246305418719, | |
| "grad_norm": 0.09186700731515884, | |
| "learning_rate": 6.103695504692122e-05, | |
| "loss": 0.7296, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6773399014778325, | |
| "grad_norm": 0.09529369324445724, | |
| "learning_rate": 5.7110806208751655e-05, | |
| "loss": 0.7599, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 0.08949359506368637, | |
| "learning_rate": 5.326407828419979e-05, | |
| "loss": 0.7307, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7019704433497537, | |
| "grad_norm": 0.0917147845029831, | |
| "learning_rate": 4.9503894527847964e-05, | |
| "loss": 0.7331, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.09406977891921997, | |
| "learning_rate": 4.583721793440188e-05, | |
| "loss": 0.7529, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7266009852216748, | |
| "grad_norm": 0.09506186842918396, | |
| "learning_rate": 4.227083834482728e-05, | |
| "loss": 0.7456, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.7389162561576355, | |
| "grad_norm": 0.09259527176618576, | |
| "learning_rate": 3.881135987312757e-05, | |
| "loss": 0.7226, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7512315270935961, | |
| "grad_norm": 0.0908261388540268, | |
| "learning_rate": 3.546518867704499e-05, | |
| "loss": 0.7369, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.7635467980295566, | |
| "grad_norm": 0.0925694927573204, | |
| "learning_rate": 3.223852109533112e-05, | |
| "loss": 0.7481, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7758620689655172, | |
| "grad_norm": 0.09128490090370178, | |
| "learning_rate": 2.9137332173554043e-05, | |
| "loss": 0.7443, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.7881773399014779, | |
| "grad_norm": 0.09191950410604477, | |
| "learning_rate": 2.616736459968936e-05, | |
| "loss": 0.748, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8004926108374384, | |
| "grad_norm": 0.09404216706752777, | |
| "learning_rate": 2.33341180699841e-05, | |
| "loss": 0.7425, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.812807881773399, | |
| "grad_norm": 0.09144895523786545, | |
| "learning_rate": 2.0642839104785272e-05, | |
| "loss": 0.7444, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8251231527093597, | |
| "grad_norm": 0.09528341144323349, | |
| "learning_rate": 1.8098511333192024e-05, | |
| "loss": 0.7407, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.8374384236453202, | |
| "grad_norm": 0.09274046123027802, | |
| "learning_rate": 1.570584626452173e-05, | |
| "loss": 0.7525, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8497536945812808, | |
| "grad_norm": 0.0897468701004982, | |
| "learning_rate": 1.3469274563679402e-05, | |
| "loss": 0.7386, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 0.0911116823554039, | |
| "learning_rate": 1.1392937846586215e-05, | |
| "loss": 0.7354, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.874384236453202, | |
| "grad_norm": 0.0972171276807785, | |
| "learning_rate": 9.48068101086026e-06, | |
| "loss": 0.7422, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.8866995073891626, | |
| "grad_norm": 0.09464489668607712, | |
| "learning_rate": 7.736045115951251e-06, | |
| "loss": 0.7373, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8990147783251231, | |
| "grad_norm": 0.09477795660495758, | |
| "learning_rate": 6.16226082591359e-06, | |
| "loss": 0.7528, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.9113300492610837, | |
| "grad_norm": 0.09124425053596497, | |
| "learning_rate": 4.762242426960262e-06, | |
| "loss": 0.7255, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9236453201970444, | |
| "grad_norm": 0.10281544923782349, | |
| "learning_rate": 3.5385824308756587e-06, | |
| "loss": 0.7298, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9359605911330049, | |
| "grad_norm": 0.09235721826553345, | |
| "learning_rate": 2.493546774280531e-06, | |
| "loss": 0.7406, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9482758620689655, | |
| "grad_norm": 0.0930071771144867, | |
| "learning_rate": 1.6290706226390285e-06, | |
| "loss": 0.732, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.9605911330049262, | |
| "grad_norm": 0.09213443100452423, | |
| "learning_rate": 9.46754786777726e-07, | |
| "loss": 0.7212, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9729064039408867, | |
| "grad_norm": 0.09438111633062363, | |
| "learning_rate": 4.4786275855247527e-07, | |
| "loss": 0.7417, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.9852216748768473, | |
| "grad_norm": 0.09238170087337494, | |
| "learning_rate": 1.333183711524133e-07, | |
| "loss": 0.7359, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9975369458128078, | |
| "grad_norm": 0.09528394788503647, | |
| "learning_rate": 3.7040883734462683e-09, | |
| "loss": 0.7378, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": NaN, | |
| "eval_runtime": 19743.7667, | |
| "eval_samples_per_second": 1.17, | |
| "eval_steps_per_second": 0.293, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 406, | |
| "total_flos": 2.1526655915408753e+18, | |
| "train_loss": 0.7470833365553118, | |
| "train_runtime": 86558.0412, | |
| "train_samples_per_second": 1.201, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 406, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1526655915408753e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |