| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 438, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00228310502283105, | |
| "grad_norm": 7.218806743621826, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.798, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01141552511415525, | |
| "grad_norm": 7.102625846862793, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 1.7228, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0228310502283105, | |
| "grad_norm": 4.343904495239258, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 1.571, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03424657534246575, | |
| "grad_norm": 2.9180715084075928, | |
| "learning_rate": 6.818181818181818e-05, | |
| "loss": 1.34, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.045662100456621, | |
| "grad_norm": 1.1530470848083496, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 1.1862, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05707762557077625, | |
| "grad_norm": 1.0645655393600464, | |
| "learning_rate": 0.00011363636363636365, | |
| "loss": 1.0852, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0684931506849315, | |
| "grad_norm": 1.113412618637085, | |
| "learning_rate": 0.00013636363636363637, | |
| "loss": 1.0102, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07990867579908675, | |
| "grad_norm": 0.9628555178642273, | |
| "learning_rate": 0.0001590909090909091, | |
| "loss": 0.9345, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.091324200913242, | |
| "grad_norm": 0.5371753573417664, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 0.8871, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10273972602739725, | |
| "grad_norm": 0.7333775162696838, | |
| "learning_rate": 0.00019999682111362368, | |
| "loss": 0.8563, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1141552511415525, | |
| "grad_norm": 0.5362383127212524, | |
| "learning_rate": 0.00019988558131018186, | |
| "loss": 0.8434, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12557077625570776, | |
| "grad_norm": 0.42146092653274536, | |
| "learning_rate": 0.0001996155992365444, | |
| "loss": 0.8227, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 0.42583712935447693, | |
| "learning_rate": 0.00019918730395931649, | |
| "loss": 0.8087, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14840182648401826, | |
| "grad_norm": 0.4173405170440674, | |
| "learning_rate": 0.00019860137614295168, | |
| "loss": 0.8127, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1598173515981735, | |
| "grad_norm": 0.5237720608711243, | |
| "learning_rate": 0.00019785874696801202, | |
| "loss": 0.7888, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17123287671232876, | |
| "grad_norm": 0.4207506477832794, | |
| "learning_rate": 0.0001969605966512975, | |
| "loss": 0.7991, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.182648401826484, | |
| "grad_norm": 0.5145552158355713, | |
| "learning_rate": 0.00019590835257019714, | |
| "loss": 0.8001, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19406392694063926, | |
| "grad_norm": 0.4617029130458832, | |
| "learning_rate": 0.00019470368699424218, | |
| "loss": 0.7777, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2054794520547945, | |
| "grad_norm": 0.48738017678260803, | |
| "learning_rate": 0.00019334851442746664, | |
| "loss": 0.7803, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.21689497716894976, | |
| "grad_norm": 0.4272419512271881, | |
| "learning_rate": 0.00019184498856579868, | |
| "loss": 0.7721, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.228310502283105, | |
| "grad_norm": 0.8292232155799866, | |
| "learning_rate": 0.00019019549887431877, | |
| "loss": 0.774, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23972602739726026, | |
| "grad_norm": 0.48018935322761536, | |
| "learning_rate": 0.00018840266678982342, | |
| "loss": 0.7785, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2511415525114155, | |
| "grad_norm": 0.5646579265594482, | |
| "learning_rate": 0.00018646934155473022, | |
| "loss": 0.7567, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2625570776255708, | |
| "grad_norm": 0.5426482558250427, | |
| "learning_rate": 0.00018439859568894463, | |
| "loss": 0.76, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 0.4849863350391388, | |
| "learning_rate": 0.00018219372010688515, | |
| "loss": 0.7513, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2853881278538813, | |
| "grad_norm": 0.4911242425441742, | |
| "learning_rate": 0.00017985821888742685, | |
| "loss": 0.7547, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2968036529680365, | |
| "grad_norm": 0.4471426010131836, | |
| "learning_rate": 0.00017739580370507532, | |
| "loss": 0.7517, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3082191780821918, | |
| "grad_norm": 0.5667721629142761, | |
| "learning_rate": 0.00017481038793122088, | |
| "loss": 0.7578, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.319634703196347, | |
| "grad_norm": 0.5815710425376892, | |
| "learning_rate": 0.0001721060804148482, | |
| "loss": 0.7629, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3310502283105023, | |
| "grad_norm": 0.4607318043708801, | |
| "learning_rate": 0.00016928717895258437, | |
| "loss": 0.7602, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3424657534246575, | |
| "grad_norm": 0.5995905995368958, | |
| "learning_rate": 0.0001663581634584641, | |
| "loss": 0.75, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3538812785388128, | |
| "grad_norm": 0.5096511244773865, | |
| "learning_rate": 0.00016332368884426626, | |
| "loss": 0.7439, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 0.8967055678367615, | |
| "learning_rate": 0.0001601885776217367, | |
| "loss": 0.7527, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3767123287671233, | |
| "grad_norm": 0.5147667527198792, | |
| "learning_rate": 0.00015695781223845441, | |
| "loss": 0.7527, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.3881278538812785, | |
| "grad_norm": 0.4564310312271118, | |
| "learning_rate": 0.0001536365271595212, | |
| "loss": 0.7487, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3995433789954338, | |
| "grad_norm": 0.7292072176933289, | |
| "learning_rate": 0.00015023000070765884, | |
| "loss": 0.7482, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 0.8427252769470215, | |
| "learning_rate": 0.0001467436466746814, | |
| "loss": 0.7409, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4223744292237443, | |
| "grad_norm": 0.631044328212738, | |
| "learning_rate": 0.00014318300571767513, | |
| "loss": 0.7451, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.4337899543378995, | |
| "grad_norm": 0.4628809690475464, | |
| "learning_rate": 0.0001395537365535585, | |
| "loss": 0.7409, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4452054794520548, | |
| "grad_norm": 0.4346175193786621, | |
| "learning_rate": 0.00013586160696601665, | |
| "loss": 0.747, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "grad_norm": 0.4906691312789917, | |
| "learning_rate": 0.00013211248463910262, | |
| "loss": 0.7389, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4680365296803653, | |
| "grad_norm": 0.4580436050891876, | |
| "learning_rate": 0.00012831232783207277, | |
| "loss": 0.7277, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.4794520547945205, | |
| "grad_norm": 0.4663284122943878, | |
| "learning_rate": 0.00012446717591027624, | |
| "loss": 0.7325, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4908675799086758, | |
| "grad_norm": 0.5113467574119568, | |
| "learning_rate": 0.00012058313974714746, | |
| "loss": 0.7364, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.502283105022831, | |
| "grad_norm": 0.4941682517528534, | |
| "learning_rate": 0.00011666639201255506, | |
| "loss": 0.7251, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5136986301369864, | |
| "grad_norm": 0.47159168124198914, | |
| "learning_rate": 0.00011272315736294108, | |
| "loss": 0.7278, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5251141552511416, | |
| "grad_norm": 0.44525182247161865, | |
| "learning_rate": 0.0001087597025488413, | |
| "loss": 0.7368, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5365296803652968, | |
| "grad_norm": 0.5244260430335999, | |
| "learning_rate": 0.00010478232645550782, | |
| "loss": 0.7374, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 0.4565676152706146, | |
| "learning_rate": 0.00010079735009246167, | |
| "loss": 0.7308, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5593607305936074, | |
| "grad_norm": 0.5089186429977417, | |
| "learning_rate": 9.681110654788482e-05, | |
| "loss": 0.7312, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.5707762557077626, | |
| "grad_norm": 0.502402663230896, | |
| "learning_rate": 9.282993092381625e-05, | |
| "loss": 0.7128, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5821917808219178, | |
| "grad_norm": 0.4394870102405548, | |
| "learning_rate": 8.886015026814736e-05, | |
| "loss": 0.7235, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.593607305936073, | |
| "grad_norm": 0.4642430245876312, | |
| "learning_rate": 8.490807351941753e-05, | |
| "loss": 0.7238, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6050228310502284, | |
| "grad_norm": 0.5627766847610474, | |
| "learning_rate": 8.097998148038985e-05, | |
| "loss": 0.7244, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.6164383561643836, | |
| "grad_norm": 0.5340884327888489, | |
| "learning_rate": 7.708211683634112e-05, | |
| "loss": 0.7196, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6278538812785388, | |
| "grad_norm": 0.48936447501182556, | |
| "learning_rate": 7.322067423393002e-05, | |
| "loss": 0.7142, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.639269406392694, | |
| "grad_norm": 0.6838403940200806, | |
| "learning_rate": 6.940179043641005e-05, | |
| "loss": 0.7134, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6506849315068494, | |
| "grad_norm": 0.46401193737983704, | |
| "learning_rate": 6.563153457083315e-05, | |
| "loss": 0.7232, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.6621004566210046, | |
| "grad_norm": 0.4747474789619446, | |
| "learning_rate": 6.191589848274368e-05, | |
| "loss": 0.7198, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6735159817351598, | |
| "grad_norm": 0.4562244713306427, | |
| "learning_rate": 5.82607872136913e-05, | |
| "loss": 0.7236, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 0.469294011592865, | |
| "learning_rate": 5.467200961669619e-05, | |
| "loss": 0.716, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6963470319634704, | |
| "grad_norm": 0.46684587001800537, | |
| "learning_rate": 5.115526912458113e-05, | |
| "loss": 0.7129, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.7077625570776256, | |
| "grad_norm": 0.5353609323501587, | |
| "learning_rate": 4.7716154685841944e-05, | |
| "loss": 0.7276, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7191780821917808, | |
| "grad_norm": 0.4474339783191681, | |
| "learning_rate": 4.4360131882460555e-05, | |
| "loss": 0.7328, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.730593607305936, | |
| "grad_norm": 0.504355251789093, | |
| "learning_rate": 4.109253424377772e-05, | |
| "loss": 0.7221, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7420091324200914, | |
| "grad_norm": 0.524207592010498, | |
| "learning_rate": 3.791855477022903e-05, | |
| "loss": 0.7156, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7534246575342466, | |
| "grad_norm": 0.5037496089935303, | |
| "learning_rate": 3.4843237680415156e-05, | |
| "loss": 0.7157, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7648401826484018, | |
| "grad_norm": 0.4428478479385376, | |
| "learning_rate": 3.1871470394622404e-05, | |
| "loss": 0.7022, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.776255707762557, | |
| "grad_norm": 0.5166884660720825, | |
| "learning_rate": 2.9007975767533714e-05, | |
| "loss": 0.7137, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7876712328767124, | |
| "grad_norm": 0.4624291956424713, | |
| "learning_rate": 2.625730458247362e-05, | |
| "loss": 0.7221, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.7990867579908676, | |
| "grad_norm": 0.4491420090198517, | |
| "learning_rate": 2.3623828319116748e-05, | |
| "loss": 0.7237, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8105022831050228, | |
| "grad_norm": 0.46221333742141724, | |
| "learning_rate": 2.1111732206152424e-05, | |
| "loss": 0.7258, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 0.4614256024360657, | |
| "learning_rate": 1.8725008569947365e-05, | |
| "loss": 0.7266, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.4534947872161865, | |
| "learning_rate": 1.6467450489776582e-05, | |
| "loss": 0.7149, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.8447488584474886, | |
| "grad_norm": 0.43620970845222473, | |
| "learning_rate": 1.4342645769705977e-05, | |
| "loss": 0.7093, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8561643835616438, | |
| "grad_norm": 0.44368976354599, | |
| "learning_rate": 1.2353971236706564e-05, | |
| "loss": 0.7237, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.867579908675799, | |
| "grad_norm": 0.4331362247467041, | |
| "learning_rate": 1.0504587374062391e-05, | |
| "loss": 0.7055, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8789954337899544, | |
| "grad_norm": 0.5180200934410095, | |
| "learning_rate": 8.797433298600622e-06, | |
| "loss": 0.7083, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.8904109589041096, | |
| "grad_norm": 0.4550034999847412, | |
| "learning_rate": 7.235222089726279e-06, | |
| "loss": 0.7156, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9018264840182648, | |
| "grad_norm": 0.4615817964076996, | |
| "learning_rate": 5.82043647768502e-06, | |
| "loss": 0.7232, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.91324200913242, | |
| "grad_norm": 0.4302138388156891, | |
| "learning_rate": 4.555324897906132e-06, | |
| "loss": 0.7115, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9246575342465754, | |
| "grad_norm": 0.442900687456131, | |
| "learning_rate": 3.441897917696679e-06, | |
| "loss": 0.7153, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.9360730593607306, | |
| "grad_norm": 0.45728132128715515, | |
| "learning_rate": 2.4819250409651607e-06, | |
| "loss": 0.715, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9474885844748858, | |
| "grad_norm": 0.4729623794555664, | |
| "learning_rate": 1.6769318960533464e-06, | |
| "loss": 0.7167, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.958904109589041, | |
| "grad_norm": 0.43312644958496094, | |
| "learning_rate": 1.0281978111449375e-06, | |
| "loss": 0.7266, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9703196347031964, | |
| "grad_norm": 0.4580814838409424, | |
| "learning_rate": 5.367537811046485e-07, | |
| "loss": 0.7222, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9817351598173516, | |
| "grad_norm": 0.4317879378795624, | |
| "learning_rate": 2.0338082897886079e-07, | |
| "loss": 0.7099, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9931506849315068, | |
| "grad_norm": 0.4474068880081177, | |
| "learning_rate": 2.8608764761639538e-08, | |
| "loss": 0.7129, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8165334463119507, | |
| "eval_runtime": 0.9134, | |
| "eval_samples_per_second": 13.137, | |
| "eval_steps_per_second": 1.095, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 438, | |
| "total_flos": 6.128945862132367e+17, | |
| "train_loss": 0.7845394540595138, | |
| "train_runtime": 3064.8006, | |
| "train_samples_per_second": 4.569, | |
| "train_steps_per_second": 0.143 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 438, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.128945862132367e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |