| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.989494747373687, | |
| "eval_steps": 500, | |
| "global_step": 747, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02001000500250125, | |
| "grad_norm": 1.2456663846969604, | |
| "learning_rate": 4.999447296060165e-05, | |
| "loss": 1.3318, | |
| "num_input_tokens_seen": 15648, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0400200100050025, | |
| "grad_norm": 0.8590693473815918, | |
| "learning_rate": 4.997789428625975e-05, | |
| "loss": 1.2773, | |
| "num_input_tokens_seen": 28720, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.060030015007503754, | |
| "grad_norm": 0.8516742587089539, | |
| "learning_rate": 4.995027130745321e-05, | |
| "loss": 1.1401, | |
| "num_input_tokens_seen": 43808, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.080040020010005, | |
| "grad_norm": 1.0357950925827026, | |
| "learning_rate": 4.99116162380454e-05, | |
| "loss": 1.089, | |
| "num_input_tokens_seen": 57472, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10005002501250625, | |
| "grad_norm": 0.744416356086731, | |
| "learning_rate": 4.986194616988364e-05, | |
| "loss": 1.1176, | |
| "num_input_tokens_seen": 71968, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12006003001500751, | |
| "grad_norm": 0.7087241411209106, | |
| "learning_rate": 4.980128306524183e-05, | |
| "loss": 0.9949, | |
| "num_input_tokens_seen": 85552, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14007003501750875, | |
| "grad_norm": 0.708070695400238, | |
| "learning_rate": 4.972965374710952e-05, | |
| "loss": 1.0264, | |
| "num_input_tokens_seen": 100512, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16008004002001, | |
| "grad_norm": 0.7232606410980225, | |
| "learning_rate": 4.964708988733178e-05, | |
| "loss": 1.0004, | |
| "num_input_tokens_seen": 113376, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18009004502251125, | |
| "grad_norm": 1.207189679145813, | |
| "learning_rate": 4.9553627992605066e-05, | |
| "loss": 1.1137, | |
| "num_input_tokens_seen": 127680, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2001000500250125, | |
| "grad_norm": 0.6889365315437317, | |
| "learning_rate": 4.944930938833535e-05, | |
| "loss": 0.9646, | |
| "num_input_tokens_seen": 143136, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22011005502751377, | |
| "grad_norm": 1.3263787031173706, | |
| "learning_rate": 4.9334180200365486e-05, | |
| "loss": 0.9757, | |
| "num_input_tokens_seen": 155488, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24012006003001501, | |
| "grad_norm": 1.0919948816299438, | |
| "learning_rate": 4.9208291334580104e-05, | |
| "loss": 0.9126, | |
| "num_input_tokens_seen": 171008, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.26013006503251623, | |
| "grad_norm": 0.853539764881134, | |
| "learning_rate": 4.907169845439688e-05, | |
| "loss": 1.0119, | |
| "num_input_tokens_seen": 185536, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2801400700350175, | |
| "grad_norm": 0.9023884534835815, | |
| "learning_rate": 4.892446195615423e-05, | |
| "loss": 1.1192, | |
| "num_input_tokens_seen": 201728, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3001500750375188, | |
| "grad_norm": 1.3300387859344482, | |
| "learning_rate": 4.87666469424063e-05, | |
| "loss": 1.0167, | |
| "num_input_tokens_seen": 217584, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.32016008004002, | |
| "grad_norm": 1.1315807104110718, | |
| "learning_rate": 4.859832319313697e-05, | |
| "loss": 0.8291, | |
| "num_input_tokens_seen": 230864, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3401700850425213, | |
| "grad_norm": 1.2459896802902222, | |
| "learning_rate": 4.841956513490577e-05, | |
| "loss": 0.9591, | |
| "num_input_tokens_seen": 245584, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3601800900450225, | |
| "grad_norm": 1.114758849143982, | |
| "learning_rate": 4.8230451807939135e-05, | |
| "loss": 0.9869, | |
| "num_input_tokens_seen": 259760, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.38019009504752377, | |
| "grad_norm": 0.8792176842689514, | |
| "learning_rate": 4.803106683118177e-05, | |
| "loss": 1.0423, | |
| "num_input_tokens_seen": 274432, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.400200100050025, | |
| "grad_norm": 1.6365342140197754, | |
| "learning_rate": 4.782149836532345e-05, | |
| "loss": 1.0122, | |
| "num_input_tokens_seen": 288256, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.42021010505252626, | |
| "grad_norm": 1.2875956296920776, | |
| "learning_rate": 4.760183907381757e-05, | |
| "loss": 0.9849, | |
| "num_input_tokens_seen": 301136, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.44022011005502754, | |
| "grad_norm": 0.8925891518592834, | |
| "learning_rate": 4.737218608190878e-05, | |
| "loss": 0.7958, | |
| "num_input_tokens_seen": 313712, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.46023011505752875, | |
| "grad_norm": 0.9326754808425903, | |
| "learning_rate": 4.713264093368783e-05, | |
| "loss": 0.9773, | |
| "num_input_tokens_seen": 328496, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.48024012006003003, | |
| "grad_norm": 0.9033737182617188, | |
| "learning_rate": 4.6883309547192476e-05, | |
| "loss": 0.9953, | |
| "num_input_tokens_seen": 342288, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5002501250625313, | |
| "grad_norm": 1.606924057006836, | |
| "learning_rate": 4.6624302167574436e-05, | |
| "loss": 0.9726, | |
| "num_input_tokens_seen": 356128, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5202601300650325, | |
| "grad_norm": 1.0410974025726318, | |
| "learning_rate": 4.635573331835302e-05, | |
| "loss": 0.9987, | |
| "num_input_tokens_seen": 368000, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5402701350675337, | |
| "grad_norm": 1.3536303043365479, | |
| "learning_rate": 4.607772175077711e-05, | |
| "loss": 1.012, | |
| "num_input_tokens_seen": 381216, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.560280140070035, | |
| "grad_norm": 0.8227062225341797, | |
| "learning_rate": 4.5790390391317675e-05, | |
| "loss": 0.9104, | |
| "num_input_tokens_seen": 395296, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5802901450725363, | |
| "grad_norm": 1.2021853923797607, | |
| "learning_rate": 4.549386628731425e-05, | |
| "loss": 0.9087, | |
| "num_input_tokens_seen": 409312, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6003001500750376, | |
| "grad_norm": 0.7881823778152466, | |
| "learning_rate": 4.518828055079925e-05, | |
| "loss": 1.0859, | |
| "num_input_tokens_seen": 424064, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6203101550775387, | |
| "grad_norm": 0.6765316724777222, | |
| "learning_rate": 4.487376830052511e-05, | |
| "loss": 0.9696, | |
| "num_input_tokens_seen": 437264, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.64032016008004, | |
| "grad_norm": 1.2535051107406616, | |
| "learning_rate": 4.4550468602219716e-05, | |
| "loss": 1.0014, | |
| "num_input_tokens_seen": 450624, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6603301650825413, | |
| "grad_norm": 0.7798222303390503, | |
| "learning_rate": 4.421852440709666e-05, | |
| "loss": 0.8877, | |
| "num_input_tokens_seen": 465968, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6803401700850426, | |
| "grad_norm": 0.9760732054710388, | |
| "learning_rate": 4.387808248864751e-05, | |
| "loss": 0.9694, | |
| "num_input_tokens_seen": 480720, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7003501750875438, | |
| "grad_norm": 0.7668250799179077, | |
| "learning_rate": 4.352929337774395e-05, | |
| "loss": 0.8613, | |
| "num_input_tokens_seen": 495008, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.720360180090045, | |
| "grad_norm": 0.7338403463363647, | |
| "learning_rate": 4.3172311296078595e-05, | |
| "loss": 0.907, | |
| "num_input_tokens_seen": 509024, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7403701850925463, | |
| "grad_norm": 1.0990034341812134, | |
| "learning_rate": 4.2807294087973834e-05, | |
| "loss": 1.0501, | |
| "num_input_tokens_seen": 524752, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7603801900950475, | |
| "grad_norm": 1.2968486547470093, | |
| "learning_rate": 4.2434403150588895e-05, | |
| "loss": 0.9158, | |
| "num_input_tokens_seen": 537872, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7803901950975488, | |
| "grad_norm": 1.0896228551864624, | |
| "learning_rate": 4.205380336255594e-05, | |
| "loss": 0.9756, | |
| "num_input_tokens_seen": 552832, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.80040020010005, | |
| "grad_norm": 1.2773741483688354, | |
| "learning_rate": 4.166566301107687e-05, | |
| "loss": 1.0702, | |
| "num_input_tokens_seen": 566224, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8204102051025512, | |
| "grad_norm": 1.0507806539535522, | |
| "learning_rate": 4.127015371751284e-05, | |
| "loss": 0.8236, | |
| "num_input_tokens_seen": 582560, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.8404202101050525, | |
| "grad_norm": 0.7220691442489624, | |
| "learning_rate": 4.08674503614997e-05, | |
| "loss": 0.8779, | |
| "num_input_tokens_seen": 595568, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8604302151075538, | |
| "grad_norm": 1.8035520315170288, | |
| "learning_rate": 4.0457731003622606e-05, | |
| "loss": 0.9544, | |
| "num_input_tokens_seen": 609040, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.8804402201100551, | |
| "grad_norm": 1.3739808797836304, | |
| "learning_rate": 4.004117680668422e-05, | |
| "loss": 0.8529, | |
| "num_input_tokens_seen": 623168, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9004502251125562, | |
| "grad_norm": 0.7650644779205322, | |
| "learning_rate": 3.961797195560118e-05, | |
| "loss": 0.916, | |
| "num_input_tokens_seen": 639680, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9204602301150575, | |
| "grad_norm": 0.9346507787704468, | |
| "learning_rate": 3.918830357596434e-05, | |
| "loss": 1.0282, | |
| "num_input_tokens_seen": 654512, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9404702351175588, | |
| "grad_norm": 0.9470961689949036, | |
| "learning_rate": 3.8752361651298675e-05, | |
| "loss": 1.0636, | |
| "num_input_tokens_seen": 668992, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.9604802401200601, | |
| "grad_norm": 0.9078488349914551, | |
| "learning_rate": 3.8310338939059644e-05, | |
| "loss": 0.855, | |
| "num_input_tokens_seen": 683360, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9804902451225613, | |
| "grad_norm": 0.8685442209243774, | |
| "learning_rate": 3.7862430885402876e-05, | |
| "loss": 0.9286, | |
| "num_input_tokens_seen": 697456, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.0005002501250626, | |
| "grad_norm": 1.0271894931793213, | |
| "learning_rate": 3.740883553876515e-05, | |
| "loss": 0.9295, | |
| "num_input_tokens_seen": 713088, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0205102551275638, | |
| "grad_norm": 0.80521160364151, | |
| "learning_rate": 3.694975346229458e-05, | |
| "loss": 0.9945, | |
| "num_input_tokens_seen": 726176, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.040520260130065, | |
| "grad_norm": 0.9811381101608276, | |
| "learning_rate": 3.6485387645169064e-05, | |
| "loss": 0.8799, | |
| "num_input_tokens_seen": 741664, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0605302651325663, | |
| "grad_norm": 0.8328830599784851, | |
| "learning_rate": 3.601594341284195e-05, | |
| "loss": 0.8551, | |
| "num_input_tokens_seen": 754720, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.0805402701350675, | |
| "grad_norm": 0.9785313606262207, | |
| "learning_rate": 3.55416283362546e-05, | |
| "loss": 0.8381, | |
| "num_input_tokens_seen": 767568, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.1005502751375689, | |
| "grad_norm": 1.0604971647262573, | |
| "learning_rate": 3.5062652140056275e-05, | |
| "loss": 0.8036, | |
| "num_input_tokens_seen": 784192, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.12056028014007, | |
| "grad_norm": 0.9006226062774658, | |
| "learning_rate": 3.457922660987155e-05, | |
| "loss": 0.7851, | |
| "num_input_tokens_seen": 797328, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.1405702851425712, | |
| "grad_norm": 0.6364954710006714, | |
| "learning_rate": 3.409156549865654e-05, | |
| "loss": 0.8262, | |
| "num_input_tokens_seen": 812416, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.1605802901450726, | |
| "grad_norm": 1.1533681154251099, | |
| "learning_rate": 3.3599884432185225e-05, | |
| "loss": 0.9297, | |
| "num_input_tokens_seen": 825744, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.1805902951475737, | |
| "grad_norm": 0.8428523540496826, | |
| "learning_rate": 3.310440081370767e-05, | |
| "loss": 1.0422, | |
| "num_input_tokens_seen": 840256, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.2006003001500751, | |
| "grad_norm": 0.9648393392562866, | |
| "learning_rate": 3.260533372782234e-05, | |
| "loss": 0.8906, | |
| "num_input_tokens_seen": 854016, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2206103051525763, | |
| "grad_norm": 1.0610816478729248, | |
| "learning_rate": 3.2102903843604885e-05, | |
| "loss": 0.7934, | |
| "num_input_tokens_seen": 868592, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.2406203101550775, | |
| "grad_norm": 1.2185319662094116, | |
| "learning_rate": 3.1597333317036545e-05, | |
| "loss": 0.7439, | |
| "num_input_tokens_seen": 881280, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.2606303151575788, | |
| "grad_norm": 1.1018725633621216, | |
| "learning_rate": 3.10888456927748e-05, | |
| "loss": 0.841, | |
| "num_input_tokens_seen": 895168, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.28064032016008, | |
| "grad_norm": 1.42940354347229, | |
| "learning_rate": 3.057766580531031e-05, | |
| "loss": 0.9016, | |
| "num_input_tokens_seen": 910624, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.3006503251625814, | |
| "grad_norm": 1.1689488887786865, | |
| "learning_rate": 3.0064019679553274e-05, | |
| "loss": 0.8938, | |
| "num_input_tokens_seen": 923648, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.3206603301650826, | |
| "grad_norm": 1.2434953451156616, | |
| "learning_rate": 2.9548134430893604e-05, | |
| "loss": 0.8739, | |
| "num_input_tokens_seen": 938256, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.3406703351675837, | |
| "grad_norm": 0.6362343430519104, | |
| "learning_rate": 2.903023816477885e-05, | |
| "loss": 0.9641, | |
| "num_input_tokens_seen": 954000, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.360680340170085, | |
| "grad_norm": 1.7914173603057861, | |
| "learning_rate": 2.8510559875854377e-05, | |
| "loss": 0.8616, | |
| "num_input_tokens_seen": 965744, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.3806903451725863, | |
| "grad_norm": 1.1798431873321533, | |
| "learning_rate": 2.7989329346710375e-05, | |
| "loss": 0.7673, | |
| "num_input_tokens_seen": 980512, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.4007003501750876, | |
| "grad_norm": 1.0572681427001953, | |
| "learning_rate": 2.7466777046280457e-05, | |
| "loss": 0.9637, | |
| "num_input_tokens_seen": 996224, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.4207103551775888, | |
| "grad_norm": 1.3495503664016724, | |
| "learning_rate": 2.69431340279368e-05, | |
| "loss": 0.7466, | |
| "num_input_tokens_seen": 1008816, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.44072036018009, | |
| "grad_norm": 0.7960165143013, | |
| "learning_rate": 2.6418631827326857e-05, | |
| "loss": 0.8695, | |
| "num_input_tokens_seen": 1024032, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.4607303651825914, | |
| "grad_norm": 1.0253639221191406, | |
| "learning_rate": 2.5893502359996786e-05, | |
| "loss": 0.8742, | |
| "num_input_tokens_seen": 1035536, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.4807403701850925, | |
| "grad_norm": 1.3461010456085205, | |
| "learning_rate": 2.5367977818847034e-05, | |
| "loss": 0.8879, | |
| "num_input_tokens_seen": 1048784, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.500750375187594, | |
| "grad_norm": 0.9898460507392883, | |
| "learning_rate": 2.484229057146507e-05, | |
| "loss": 0.8188, | |
| "num_input_tokens_seen": 1063920, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.520760380190095, | |
| "grad_norm": 1.0175529718399048, | |
| "learning_rate": 2.431667305738112e-05, | |
| "loss": 0.8898, | |
| "num_input_tokens_seen": 1080048, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.5407703851925962, | |
| "grad_norm": 1.3844118118286133, | |
| "learning_rate": 2.3791357685291863e-05, | |
| "loss": 0.8779, | |
| "num_input_tokens_seen": 1093584, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.5607803901950974, | |
| "grad_norm": 1.3372527360916138, | |
| "learning_rate": 2.3266576730297956e-05, | |
| "loss": 0.9372, | |
| "num_input_tokens_seen": 1108192, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.5807903951975988, | |
| "grad_norm": 0.8785428404808044, | |
| "learning_rate": 2.274256223120051e-05, | |
| "loss": 0.7406, | |
| "num_input_tokens_seen": 1122368, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.6008004002001002, | |
| "grad_norm": 1.2185471057891846, | |
| "learning_rate": 2.221954588790206e-05, | |
| "loss": 0.8414, | |
| "num_input_tokens_seen": 1135040, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.6208104052026013, | |
| "grad_norm": 0.9093597531318665, | |
| "learning_rate": 2.1697758958957448e-05, | |
| "loss": 0.8781, | |
| "num_input_tokens_seen": 1150096, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.6408204102051025, | |
| "grad_norm": 1.1658143997192383, | |
| "learning_rate": 2.1177432159319754e-05, | |
| "loss": 0.8304, | |
| "num_input_tokens_seen": 1163840, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.6608304152076037, | |
| "grad_norm": 1.4369289875030518, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 0.9539, | |
| "num_input_tokens_seen": 1179024, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.680840420210105, | |
| "grad_norm": 1.2581747770309448, | |
| "learning_rate": 2.014207847797256e-05, | |
| "loss": 0.7972, | |
| "num_input_tokens_seen": 1192800, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.7008504252126064, | |
| "grad_norm": 1.6154969930648804, | |
| "learning_rate": 1.9627509391510086e-05, | |
| "loss": 0.9455, | |
| "num_input_tokens_seen": 1206160, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.7208604302151076, | |
| "grad_norm": 0.9386204481124878, | |
| "learning_rate": 1.9115315822428437e-05, | |
| "loss": 0.742, | |
| "num_input_tokens_seen": 1219456, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.7408704352176088, | |
| "grad_norm": 1.32277512550354, | |
| "learning_rate": 1.8605724243850502e-05, | |
| "loss": 0.9298, | |
| "num_input_tokens_seen": 1232848, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.76088044022011, | |
| "grad_norm": 1.7241052389144897, | |
| "learning_rate": 1.809895997839482e-05, | |
| "loss": 0.8751, | |
| "num_input_tokens_seen": 1244944, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.7808904452226113, | |
| "grad_norm": 1.2125686407089233, | |
| "learning_rate": 1.759524709854626e-05, | |
| "loss": 0.8162, | |
| "num_input_tokens_seen": 1259584, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.8009004502251127, | |
| "grad_norm": 1.6025140285491943, | |
| "learning_rate": 1.70948083275794e-05, | |
| "loss": 0.9372, | |
| "num_input_tokens_seen": 1274640, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.8209104552276139, | |
| "grad_norm": 0.9881381392478943, | |
| "learning_rate": 1.6597864941078552e-05, | |
| "loss": 0.9076, | |
| "num_input_tokens_seen": 1289936, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.840920460230115, | |
| "grad_norm": 1.4844774007797241, | |
| "learning_rate": 1.6104636669097776e-05, | |
| "loss": 0.8189, | |
| "num_input_tokens_seen": 1303184, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.8609304652326162, | |
| "grad_norm": 0.8360545635223389, | |
| "learning_rate": 1.561534159900441e-05, | |
| "loss": 0.8545, | |
| "num_input_tokens_seen": 1317920, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.8809404702351176, | |
| "grad_norm": 1.1437807083129883, | |
| "learning_rate": 1.513019607904882e-05, | |
| "loss": 0.8544, | |
| "num_input_tokens_seen": 1332192, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.900950475237619, | |
| "grad_norm": 1.3824429512023926, | |
| "learning_rate": 1.464941462270325e-05, | |
| "loss": 0.9191, | |
| "num_input_tokens_seen": 1348000, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.9209604802401201, | |
| "grad_norm": 0.9468676447868347, | |
| "learning_rate": 1.4173209813811788e-05, | |
| "loss": 0.8605, | |
| "num_input_tokens_seen": 1362096, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.9409704852426213, | |
| "grad_norm": 1.2974201440811157, | |
| "learning_rate": 1.3701792212593662e-05, | |
| "loss": 0.937, | |
| "num_input_tokens_seen": 1378656, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.9609804902451224, | |
| "grad_norm": 1.684973955154419, | |
| "learning_rate": 1.3235370262541272e-05, | |
| "loss": 0.9073, | |
| "num_input_tokens_seen": 1393344, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.9809904952476238, | |
| "grad_norm": 0.7046062350273132, | |
| "learning_rate": 1.277415019825417e-05, | |
| "loss": 0.8941, | |
| "num_input_tokens_seen": 1409280, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 2.001000500250125, | |
| "grad_norm": 1.5292088985443115, | |
| "learning_rate": 1.2318335954249669e-05, | |
| "loss": 0.8051, | |
| "num_input_tokens_seen": 1423536, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0210105052526264, | |
| "grad_norm": 1.1964282989501953, | |
| "learning_rate": 1.1868129074790577e-05, | |
| "loss": 0.751, | |
| "num_input_tokens_seen": 1436048, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 2.0410205102551275, | |
| "grad_norm": 1.2196362018585205, | |
| "learning_rate": 1.1423728624769695e-05, | |
| "loss": 0.762, | |
| "num_input_tokens_seen": 1450272, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.0610305152576287, | |
| "grad_norm": 1.8068214654922485, | |
| "learning_rate": 1.098533110169071e-05, | |
| "loss": 0.8222, | |
| "num_input_tokens_seen": 1464656, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 2.08104052026013, | |
| "grad_norm": 1.1758692264556885, | |
| "learning_rate": 1.0553130348784182e-05, | |
| "loss": 0.7271, | |
| "num_input_tokens_seen": 1478016, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.1010505252626315, | |
| "grad_norm": 1.0688625574111938, | |
| "learning_rate": 1.0127317469297277e-05, | |
| "loss": 0.7618, | |
| "num_input_tokens_seen": 1492080, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.1210605302651326, | |
| "grad_norm": 0.9757594466209412, | |
| "learning_rate": 9.708080741994868e-06, | |
| "loss": 0.7738, | |
| "num_input_tokens_seen": 1507504, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.141070535267634, | |
| "grad_norm": 1.5281833410263062, | |
| "learning_rate": 9.295605537909708e-06, | |
| "loss": 0.7976, | |
| "num_input_tokens_seen": 1520080, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 2.161080540270135, | |
| "grad_norm": 1.202627182006836, | |
| "learning_rate": 8.890074238378074e-06, | |
| "loss": 0.7181, | |
| "num_input_tokens_seen": 1531920, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.181090545272636, | |
| "grad_norm": 1.7492619752883911, | |
| "learning_rate": 8.491666154397573e-06, | |
| "loss": 0.7375, | |
| "num_input_tokens_seen": 1545856, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 2.2011005502751377, | |
| "grad_norm": 1.4915295839309692, | |
| "learning_rate": 8.100557447342327e-06, | |
| "loss": 0.7557, | |
| "num_input_tokens_seen": 1558256, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.221110555277639, | |
| "grad_norm": 1.4687122106552124, | |
| "learning_rate": 7.71692105107098e-06, | |
| "loss": 0.7973, | |
| "num_input_tokens_seen": 1573776, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 2.24112056028014, | |
| "grad_norm": 1.2812813520431519, | |
| "learning_rate": 7.340926595461687e-06, | |
| "loss": 0.881, | |
| "num_input_tokens_seen": 1589968, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.2611305652826412, | |
| "grad_norm": 1.453517198562622, | |
| "learning_rate": 6.972740331408015e-06, | |
| "loss": 0.7725, | |
| "num_input_tokens_seen": 1603488, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 2.2811405702851424, | |
| "grad_norm": 1.4879059791564941, | |
| "learning_rate": 6.612525057308949e-06, | |
| "loss": 0.8143, | |
| "num_input_tokens_seen": 1619136, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.301150575287644, | |
| "grad_norm": 1.426224708557129, | |
| "learning_rate": 6.260440047085439e-06, | |
| "loss": 0.7383, | |
| "num_input_tokens_seen": 1635088, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.321160580290145, | |
| "grad_norm": 1.5303268432617188, | |
| "learning_rate": 5.9166409797553415e-06, | |
| "loss": 0.9513, | |
| "num_input_tokens_seen": 1652560, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.3411705852926463, | |
| "grad_norm": 1.0902361869812012, | |
| "learning_rate": 5.581279870597867e-06, | |
| "loss": 0.6249, | |
| "num_input_tokens_seen": 1665168, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 2.3611805902951475, | |
| "grad_norm": 1.3195565938949585, | |
| "learning_rate": 5.254505003938043e-06, | |
| "loss": 0.7327, | |
| "num_input_tokens_seen": 1677312, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.3811905952976486, | |
| "grad_norm": 1.9101403951644897, | |
| "learning_rate": 4.936460867580889e-06, | |
| "loss": 0.8425, | |
| "num_input_tokens_seen": 1690400, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 2.4012006003001503, | |
| "grad_norm": 1.4452427625656128, | |
| "learning_rate": 4.627288088924156e-06, | |
| "loss": 0.8224, | |
| "num_input_tokens_seen": 1704640, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.4212106053026514, | |
| "grad_norm": 1.2759140729904175, | |
| "learning_rate": 4.327123372778122e-06, | |
| "loss": 0.7743, | |
| "num_input_tokens_seen": 1717808, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 2.4412206103051526, | |
| "grad_norm": 1.3661129474639893, | |
| "learning_rate": 4.036099440919763e-06, | |
| "loss": 0.6191, | |
| "num_input_tokens_seen": 1730688, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.4612306153076537, | |
| "grad_norm": 1.3944261074066162, | |
| "learning_rate": 3.754344973408064e-06, | |
| "loss": 0.8898, | |
| "num_input_tokens_seen": 1745472, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 2.481240620310155, | |
| "grad_norm": 1.5250520706176758, | |
| "learning_rate": 3.481984551686429e-06, | |
| "loss": 0.9432, | |
| "num_input_tokens_seen": 1761008, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.5012506253126565, | |
| "grad_norm": 1.3213047981262207, | |
| "learning_rate": 3.2191386034973627e-06, | |
| "loss": 0.8175, | |
| "num_input_tokens_seen": 1774704, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.5212606303151577, | |
| "grad_norm": 1.5623505115509033, | |
| "learning_rate": 2.9659233496337786e-06, | |
| "loss": 0.793, | |
| "num_input_tokens_seen": 1788768, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.541270635317659, | |
| "grad_norm": 1.8235459327697754, | |
| "learning_rate": 2.722450752550429e-06, | |
| "loss": 0.8368, | |
| "num_input_tokens_seen": 1799968, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 2.56128064032016, | |
| "grad_norm": 1.178887128829956, | |
| "learning_rate": 2.4888284668582285e-06, | |
| "loss": 0.8236, | |
| "num_input_tokens_seen": 1815008, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.581290645322661, | |
| "grad_norm": 1.4837779998779297, | |
| "learning_rate": 2.265159791723373e-06, | |
| "loss": 0.7644, | |
| "num_input_tokens_seen": 1830400, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 2.6013006503251628, | |
| "grad_norm": 1.1914581060409546, | |
| "learning_rate": 2.051543625192226e-06, | |
| "loss": 0.7604, | |
| "num_input_tokens_seen": 1844256, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.621310655327664, | |
| "grad_norm": 1.1886558532714844, | |
| "learning_rate": 1.8480744204622757e-06, | |
| "loss": 0.8209, | |
| "num_input_tokens_seen": 1859024, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 2.641320660330165, | |
| "grad_norm": 1.4688860177993774, | |
| "learning_rate": 1.6548421441183875e-06, | |
| "loss": 0.8396, | |
| "num_input_tokens_seen": 1874624, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.6613306653326663, | |
| "grad_norm": 1.299116849899292, | |
| "learning_rate": 1.4719322363529242e-06, | |
| "loss": 0.7678, | |
| "num_input_tokens_seen": 1888064, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 2.6813406703351674, | |
| "grad_norm": 1.663547396659851, | |
| "learning_rate": 1.2994255731871963e-06, | |
| "loss": 0.8765, | |
| "num_input_tokens_seen": 1902976, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.701350675337669, | |
| "grad_norm": 1.2219780683517456, | |
| "learning_rate": 1.137398430711123e-06, | |
| "loss": 0.8124, | |
| "num_input_tokens_seen": 1916416, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.72136068034017, | |
| "grad_norm": 1.8948079347610474, | |
| "learning_rate": 9.85922451356694e-07, | |
| "loss": 0.8009, | |
| "num_input_tokens_seen": 1931536, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.7413706853426714, | |
| "grad_norm": 1.3554043769836426, | |
| "learning_rate": 8.450646122203865e-07, | |
| "loss": 0.8841, | |
| "num_input_tokens_seen": 1947072, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 2.7613806903451725, | |
| "grad_norm": 1.5139766931533813, | |
| "learning_rate": 7.148871954483105e-07, | |
| "loss": 0.7737, | |
| "num_input_tokens_seen": 1960624, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.7813906953476737, | |
| "grad_norm": 1.410873293876648, | |
| "learning_rate": 5.954477606973679e-07, | |
| "loss": 0.7897, | |
| "num_input_tokens_seen": 1975232, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 2.8014007003501753, | |
| "grad_norm": 1.1572494506835938, | |
| "learning_rate": 4.867991196844918e-07, | |
| "loss": 0.7096, | |
| "num_input_tokens_seen": 1989760, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.8214107053526765, | |
| "grad_norm": 1.0913457870483398, | |
| "learning_rate": 3.8898931283523344e-07, | |
| "loss": 0.8227, | |
| "num_input_tokens_seen": 2006720, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 2.8414207103551776, | |
| "grad_norm": 1.4725265502929688, | |
| "learning_rate": 3.020615880420713e-07, | |
| "loss": 0.7987, | |
| "num_input_tokens_seen": 2021664, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.861430715357679, | |
| "grad_norm": 1.424524188041687, | |
| "learning_rate": 2.2605438154179038e-07, | |
| "loss": 0.7853, | |
| "num_input_tokens_seen": 2037536, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 2.88144072036018, | |
| "grad_norm": 1.1289780139923096, | |
| "learning_rate": 1.6100130092037703e-07, | |
| "loss": 0.7808, | |
| "num_input_tokens_seen": 2050432, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.9014507253626816, | |
| "grad_norm": 1.3387763500213623, | |
| "learning_rate": 1.0693111025300017e-07, | |
| "loss": 0.7777, | |
| "num_input_tokens_seen": 2064080, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 2.9214607303651827, | |
| "grad_norm": 1.7347784042358398, | |
| "learning_rate": 6.386771738558506e-08, | |
| "loss": 0.8181, | |
| "num_input_tokens_seen": 2079760, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.941470735367684, | |
| "grad_norm": 1.5915528535842896, | |
| "learning_rate": 3.1830163363655296e-08, | |
| "loss": 0.7858, | |
| "num_input_tokens_seen": 2094000, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 2.961480740370185, | |
| "grad_norm": 1.8485968112945557, | |
| "learning_rate": 1.0832614013073228e-08, | |
| "loss": 0.9016, | |
| "num_input_tokens_seen": 2108592, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.981490745372686, | |
| "grad_norm": 1.8265576362609863, | |
| "learning_rate": 8.843536764419069e-10, | |
| "loss": 0.7275, | |
| "num_input_tokens_seen": 2121680, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 2.989494747373687, | |
| "num_input_tokens_seen": 2127792, | |
| "step": 747, | |
| "total_flos": 9.608125026100838e+16, | |
| "train_loss": 0.8833092752709446, | |
| "train_runtime": 3405.3466, | |
| "train_samples_per_second": 3.521, | |
| "train_steps_per_second": 0.219 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 747, | |
| "num_input_tokens_seen": 2127792, | |
| "num_train_epochs": 3, | |
| "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": 9.608125026100838e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |