| { | |
| "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": 240.46628016222775, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.7929, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01141552511415525, | |
| "grad_norm": 245.40050686537415, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 2.5951, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0228310502283105, | |
| "grad_norm": 108.5355771736147, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 2.3381, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03424657534246575, | |
| "grad_norm": 92.10609311564825, | |
| "learning_rate": 6.818181818181818e-05, | |
| "loss": 1.9168, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.045662100456621, | |
| "grad_norm": 1166.1055385039233, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 13.6037, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05707762557077625, | |
| "grad_norm": 695.5402369585504, | |
| "learning_rate": 0.00011363636363636365, | |
| "loss": 13.6584, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0684931506849315, | |
| "grad_norm": 761.1239739280335, | |
| "learning_rate": 0.00013636363636363637, | |
| "loss": 8.4136, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07990867579908675, | |
| "grad_norm": 1578.3027737091188, | |
| "learning_rate": 0.0001590909090909091, | |
| "loss": 8.6665, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.091324200913242, | |
| "grad_norm": 65.2902593433997, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 9.9526, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10273972602739725, | |
| "grad_norm": 92.74211625664995, | |
| "learning_rate": 0.00019999682111362368, | |
| "loss": 7.7814, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1141552511415525, | |
| "grad_norm": 388.8492851786365, | |
| "learning_rate": 0.00019988558131018186, | |
| "loss": 7.643, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12557077625570776, | |
| "grad_norm": 52.42068791324127, | |
| "learning_rate": 0.0001996155992365444, | |
| "loss": 10.8328, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 67.22123396518563, | |
| "learning_rate": 0.00019918730395931649, | |
| "loss": 12.2142, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14840182648401826, | |
| "grad_norm": 108.11322168523512, | |
| "learning_rate": 0.00019860137614295168, | |
| "loss": 10.6018, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1598173515981735, | |
| "grad_norm": 840.8723407449802, | |
| "learning_rate": 0.00019785874696801202, | |
| "loss": 11.7075, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17123287671232876, | |
| "grad_norm": 920.9036553566684, | |
| "learning_rate": 0.0001969605966512975, | |
| "loss": 10.8955, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.182648401826484, | |
| "grad_norm": 877.4272582883378, | |
| "learning_rate": 0.00019590835257019714, | |
| "loss": 12.7904, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19406392694063926, | |
| "grad_norm": 912.8271704562273, | |
| "learning_rate": 0.00019470368699424218, | |
| "loss": 10.7954, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2054794520547945, | |
| "grad_norm": 1008.5135637969497, | |
| "learning_rate": 0.00019334851442746664, | |
| "loss": 11.2705, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.21689497716894976, | |
| "grad_norm": 38.472345652966226, | |
| "learning_rate": 0.00019184498856579868, | |
| "loss": 8.4385, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.228310502283105, | |
| "grad_norm": 57.1422911131311, | |
| "learning_rate": 0.00019019549887431877, | |
| "loss": 9.6665, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23972602739726026, | |
| "grad_norm": 88.32108375036853, | |
| "learning_rate": 0.00018840266678982342, | |
| "loss": 7.5442, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2511415525114155, | |
| "grad_norm": 347.05998093496095, | |
| "learning_rate": 0.00018646934155473022, | |
| "loss": 7.2958, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2625570776255708, | |
| "grad_norm": 20.572286439019486, | |
| "learning_rate": 0.00018439859568894463, | |
| "loss": 7.3386, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 38.351388562103665, | |
| "learning_rate": 0.00018219372010688515, | |
| "loss": 8.012, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2853881278538813, | |
| "grad_norm": 37.37105945079517, | |
| "learning_rate": 0.00017985821888742685, | |
| "loss": 7.1013, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2968036529680365, | |
| "grad_norm": 26.7507850568603, | |
| "learning_rate": 0.00017739580370507532, | |
| "loss": 6.882, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3082191780821918, | |
| "grad_norm": 88.7335799340544, | |
| "learning_rate": 0.00017481038793122088, | |
| "loss": 6.7721, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.319634703196347, | |
| "grad_norm": 22.97956758710175, | |
| "learning_rate": 0.0001721060804148482, | |
| "loss": 6.9621, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3310502283105023, | |
| "grad_norm": 20.8606176285665, | |
| "learning_rate": 0.00016928717895258437, | |
| "loss": 6.7809, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3424657534246575, | |
| "grad_norm": 26.219570138783702, | |
| "learning_rate": 0.0001663581634584641, | |
| "loss": 6.9626, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3538812785388128, | |
| "grad_norm": 167.86360436359567, | |
| "learning_rate": 0.00016332368884426626, | |
| "loss": 7.6471, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 430.63515082965046, | |
| "learning_rate": 0.0001601885776217367, | |
| "loss": 7.1777, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3767123287671233, | |
| "grad_norm": 25.678714469291474, | |
| "learning_rate": 0.00015695781223845441, | |
| "loss": 6.9389, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.3881278538812785, | |
| "grad_norm": 180.18708109632934, | |
| "learning_rate": 0.0001536365271595212, | |
| "loss": 7.4995, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3995433789954338, | |
| "grad_norm": 50.63109221066056, | |
| "learning_rate": 0.00015023000070765884, | |
| "loss": 6.6471, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 138.11974530731086, | |
| "learning_rate": 0.0001467436466746814, | |
| "loss": 6.4638, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4223744292237443, | |
| "grad_norm": 24.557862163981767, | |
| "learning_rate": 0.00014318300571767513, | |
| "loss": 6.4258, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.4337899543378995, | |
| "grad_norm": 23.71602743273707, | |
| "learning_rate": 0.0001395537365535585, | |
| "loss": 6.2647, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4452054794520548, | |
| "grad_norm": 40.86377604494575, | |
| "learning_rate": 0.00013586160696601665, | |
| "loss": 6.2592, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "grad_norm": 40.35100848104416, | |
| "learning_rate": 0.00013211248463910262, | |
| "loss": 6.1296, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4680365296803653, | |
| "grad_norm": 8.53161320251149, | |
| "learning_rate": 0.00012831232783207277, | |
| "loss": 5.9919, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.4794520547945205, | |
| "grad_norm": 53.85169619244609, | |
| "learning_rate": 0.00012446717591027624, | |
| "loss": 6.1196, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4908675799086758, | |
| "grad_norm": 18.702516339707657, | |
| "learning_rate": 0.00012058313974714746, | |
| "loss": 6.217, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.502283105022831, | |
| "grad_norm": 23.340868803327382, | |
| "learning_rate": 0.00011666639201255506, | |
| "loss": 5.9684, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5136986301369864, | |
| "grad_norm": 27.848028057442086, | |
| "learning_rate": 0.00011272315736294108, | |
| "loss": 5.885, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5251141552511416, | |
| "grad_norm": 11.302150338648437, | |
| "learning_rate": 0.0001087597025488413, | |
| "loss": 5.8254, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5365296803652968, | |
| "grad_norm": 7.856659467347087, | |
| "learning_rate": 0.00010478232645550782, | |
| "loss": 5.797, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 17.570218309451846, | |
| "learning_rate": 0.00010079735009246167, | |
| "loss": 5.6966, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5593607305936074, | |
| "grad_norm": 12.285913129547184, | |
| "learning_rate": 9.681110654788482e-05, | |
| "loss": 5.5947, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.5707762557077626, | |
| "grad_norm": 12.189890918080446, | |
| "learning_rate": 9.282993092381625e-05, | |
| "loss": 5.456, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5821917808219178, | |
| "grad_norm": 13.447394220420884, | |
| "learning_rate": 8.886015026814736e-05, | |
| "loss": 5.3872, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.593607305936073, | |
| "grad_norm": 8.087645921511065, | |
| "learning_rate": 8.490807351941753e-05, | |
| "loss": 5.3234, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6050228310502284, | |
| "grad_norm": 6.294622158332865, | |
| "learning_rate": 8.097998148038985e-05, | |
| "loss": 5.2182, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.6164383561643836, | |
| "grad_norm": 6.8880132676177155, | |
| "learning_rate": 7.708211683634112e-05, | |
| "loss": 5.1346, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6278538812785388, | |
| "grad_norm": 4.3063046925628665, | |
| "learning_rate": 7.322067423393002e-05, | |
| "loss": 5.0977, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.639269406392694, | |
| "grad_norm": 6.202488868271211, | |
| "learning_rate": 6.940179043641005e-05, | |
| "loss": 4.9949, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6506849315068494, | |
| "grad_norm": 9.748600106096807, | |
| "learning_rate": 6.563153457083315e-05, | |
| "loss": 5.0211, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.6621004566210046, | |
| "grad_norm": 4.021422440954996, | |
| "learning_rate": 6.191589848274368e-05, | |
| "loss": 4.9403, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6735159817351598, | |
| "grad_norm": 5.203478173074032, | |
| "learning_rate": 5.82607872136913e-05, | |
| "loss": 4.8661, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 7.795245351250236, | |
| "learning_rate": 5.467200961669619e-05, | |
| "loss": 4.8218, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6963470319634704, | |
| "grad_norm": 6.507211128414033, | |
| "learning_rate": 5.115526912458113e-05, | |
| "loss": 4.7079, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.7077625570776256, | |
| "grad_norm": 3.415005954143531, | |
| "learning_rate": 4.7716154685841944e-05, | |
| "loss": 4.7262, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7191780821917808, | |
| "grad_norm": 4.701959725615529, | |
| "learning_rate": 4.4360131882460555e-05, | |
| "loss": 4.6772, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.730593607305936, | |
| "grad_norm": 7.243992416761161, | |
| "learning_rate": 4.109253424377772e-05, | |
| "loss": 4.6001, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7420091324200914, | |
| "grad_norm": 5.597934572299491, | |
| "learning_rate": 3.791855477022903e-05, | |
| "loss": 4.5783, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7534246575342466, | |
| "grad_norm": 7.0945462547518545, | |
| "learning_rate": 3.4843237680415156e-05, | |
| "loss": 4.5086, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7648401826484018, | |
| "grad_norm": 5.40993943834967, | |
| "learning_rate": 3.1871470394622404e-05, | |
| "loss": 4.396, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.776255707762557, | |
| "grad_norm": 4.514795217834535, | |
| "learning_rate": 2.9007975767533714e-05, | |
| "loss": 4.4116, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7876712328767124, | |
| "grad_norm": 6.619199704533781, | |
| "learning_rate": 2.625730458247362e-05, | |
| "loss": 4.3946, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.7990867579908676, | |
| "grad_norm": 6.797118824330897, | |
| "learning_rate": 2.3623828319116748e-05, | |
| "loss": 4.3655, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8105022831050228, | |
| "grad_norm": 6.319532987233403, | |
| "learning_rate": 2.1111732206152424e-05, | |
| "loss": 4.3162, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 3.6539166546644366, | |
| "learning_rate": 1.8725008569947365e-05, | |
| "loss": 4.2938, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 4.300626146767242, | |
| "learning_rate": 1.6467450489776582e-05, | |
| "loss": 4.1979, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.8447488584474886, | |
| "grad_norm": 4.330204640440713, | |
| "learning_rate": 1.4342645769705977e-05, | |
| "loss": 4.1682, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8561643835616438, | |
| "grad_norm": 3.3916542716906064, | |
| "learning_rate": 1.2353971236706564e-05, | |
| "loss": 4.1933, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.867579908675799, | |
| "grad_norm": 3.4156576312872726, | |
| "learning_rate": 1.0504587374062391e-05, | |
| "loss": 4.0807, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8789954337899544, | |
| "grad_norm": 3.740969173497314, | |
| "learning_rate": 8.797433298600622e-06, | |
| "loss": 4.0922, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.8904109589041096, | |
| "grad_norm": 3.4358795428140096, | |
| "learning_rate": 7.235222089726279e-06, | |
| "loss": 4.129, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9018264840182648, | |
| "grad_norm": 4.4709463768242, | |
| "learning_rate": 5.82043647768502e-06, | |
| "loss": 4.0451, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.91324200913242, | |
| "grad_norm": 3.239079694881163, | |
| "learning_rate": 4.555324897906132e-06, | |
| "loss": 4.0609, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9246575342465754, | |
| "grad_norm": 4.365463466537055, | |
| "learning_rate": 3.441897917696679e-06, | |
| "loss": 4.0053, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.9360730593607306, | |
| "grad_norm": 3.4103467721542082, | |
| "learning_rate": 2.4819250409651607e-06, | |
| "loss": 4.0147, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9474885844748858, | |
| "grad_norm": 2.424364857956352, | |
| "learning_rate": 1.6769318960533464e-06, | |
| "loss": 3.9732, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.958904109589041, | |
| "grad_norm": 2.681966720958818, | |
| "learning_rate": 1.0281978111449375e-06, | |
| "loss": 4.0434, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9703196347031964, | |
| "grad_norm": 2.756086031182227, | |
| "learning_rate": 5.367537811046485e-07, | |
| "loss": 4.028, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9817351598173516, | |
| "grad_norm": 2.613500426580146, | |
| "learning_rate": 2.0338082897886079e-07, | |
| "loss": 3.9626, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9931506849315068, | |
| "grad_norm": 2.209338347291564, | |
| "learning_rate": 2.8608764761639538e-08, | |
| "loss": 3.9549, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 7.139484405517578, | |
| "eval_runtime": 2.4665, | |
| "eval_samples_per_second": 4.865, | |
| "eval_steps_per_second": 0.405, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 438, | |
| "total_flos": 22900899840000.0, | |
| "train_loss": 6.294099572042352, | |
| "train_runtime": 7431.9326, | |
| "train_samples_per_second": 1.884, | |
| "train_steps_per_second": 0.059 | |
| } | |
| ], | |
| "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": 22900899840000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |