| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007407407407407408, | |
| "grad_norm": 1.5567783117294312, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 1.5566, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.037037037037037035, | |
| "grad_norm": 1.6362663507461548, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 1.5121, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.9970850944519043, | |
| "learning_rate": 0.00014814814814814815, | |
| "loss": 1.2449, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.688450813293457, | |
| "learning_rate": 0.0002222222222222222, | |
| "loss": 0.8674, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.4350931942462921, | |
| "learning_rate": 0.0002962962962962963, | |
| "loss": 0.7491, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "grad_norm": 0.377754271030426, | |
| "learning_rate": 0.00037037037037037035, | |
| "loss": 0.6649, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.19140222668647766, | |
| "learning_rate": 0.0004444444444444444, | |
| "loss": 0.6335, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25925925925925924, | |
| "grad_norm": 0.16032004356384277, | |
| "learning_rate": 0.0005185185185185185, | |
| "loss": 0.6068, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.15596596896648407, | |
| "learning_rate": 0.0005925925925925926, | |
| "loss": 0.5878, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.12440178543329239, | |
| "learning_rate": 0.0006666666666666666, | |
| "loss": 0.564, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 0.13573868572711945, | |
| "learning_rate": 0.0007407407407407407, | |
| "loss": 0.56, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4074074074074074, | |
| "grad_norm": 0.10565729439258575, | |
| "learning_rate": 0.0008148148148148148, | |
| "loss": 0.5418, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.11647824943065643, | |
| "learning_rate": 0.0008888888888888888, | |
| "loss": 0.5356, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.48148148148148145, | |
| "grad_norm": 0.10235206037759781, | |
| "learning_rate": 0.0009629629629629629, | |
| "loss": 0.5294, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5185185185185185, | |
| "grad_norm": 0.17172235250473022, | |
| "learning_rate": 0.001037037037037037, | |
| "loss": 0.5216, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.12478260695934296, | |
| "learning_rate": 0.0011111111111111111, | |
| "loss": 0.5218, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.11295782774686813, | |
| "learning_rate": 0.0011851851851851852, | |
| "loss": 0.5144, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6296296296296297, | |
| "grad_norm": 0.1066703274846077, | |
| "learning_rate": 0.0012592592592592592, | |
| "loss": 0.5154, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.0921861082315445, | |
| "learning_rate": 0.0013333333333333333, | |
| "loss": 0.5003, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7037037037037037, | |
| "grad_norm": 0.09984983503818512, | |
| "learning_rate": 0.0014074074074074076, | |
| "loss": 0.5042, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 0.13562288880348206, | |
| "learning_rate": 0.0014814814814814814, | |
| "loss": 0.5003, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.09528646618127823, | |
| "learning_rate": 0.0015555555555555557, | |
| "loss": 0.4996, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8148148148148148, | |
| "grad_norm": 0.14511393010616302, | |
| "learning_rate": 0.0016296296296296295, | |
| "loss": 0.4929, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8518518518518519, | |
| "grad_norm": 0.0997464582324028, | |
| "learning_rate": 0.0017037037037037038, | |
| "loss": 0.4906, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.14288371801376343, | |
| "learning_rate": 0.0017777777777777776, | |
| "loss": 0.4924, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9259259259259259, | |
| "grad_norm": 0.12957949936389923, | |
| "learning_rate": 0.001851851851851852, | |
| "loss": 0.4879, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9629629629629629, | |
| "grad_norm": 0.10427533835172653, | |
| "learning_rate": 0.0019259259259259258, | |
| "loss": 0.4856, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.11492197960615158, | |
| "learning_rate": 0.002, | |
| "loss": 0.4861, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.2494666576385498, | |
| "eval_runtime": 1.452, | |
| "eval_samples_per_second": 2.755, | |
| "eval_steps_per_second": 0.689, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.037037037037037, | |
| "grad_norm": 0.20287227630615234, | |
| "learning_rate": 0.0019999164298554373, | |
| "loss": 0.4759, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.074074074074074, | |
| "grad_norm": 0.10903054475784302, | |
| "learning_rate": 0.0019996657333896874, | |
| "loss": 0.4752, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.09817971289157867, | |
| "learning_rate": 0.00199924795250423, | |
| "loss": 0.4771, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1481481481481481, | |
| "grad_norm": 0.10313747823238373, | |
| "learning_rate": 0.001998663157027083, | |
| "loss": 0.471, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.10586988180875778, | |
| "learning_rate": 0.001997911444701132, | |
| "loss": 0.4675, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 0.10676765441894531, | |
| "learning_rate": 0.001996992941167792, | |
| "loss": 0.4743, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.2592592592592593, | |
| "grad_norm": 0.09956058114767075, | |
| "learning_rate": 0.0019959077999460095, | |
| "loss": 0.4682, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.2962962962962963, | |
| "grad_norm": 0.08940426260232925, | |
| "learning_rate": 0.0019946562024066015, | |
| "loss": 0.4667, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.09569676965475082, | |
| "learning_rate": 0.001993238357741943, | |
| "loss": 0.4742, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3703703703703702, | |
| "grad_norm": 0.1325625479221344, | |
| "learning_rate": 0.0019916545029310014, | |
| "loss": 0.4735, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.4074074074074074, | |
| "grad_norm": 0.09514327347278595, | |
| "learning_rate": 0.0019899049026997273, | |
| "loss": 0.473, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.4444444444444444, | |
| "grad_norm": 0.10093410313129425, | |
| "learning_rate": 0.001987989849476809, | |
| "loss": 0.4693, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 0.10901673138141632, | |
| "learning_rate": 0.0019859096633447963, | |
| "loss": 0.4666, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5185185185185186, | |
| "grad_norm": 0.10339543968439102, | |
| "learning_rate": 0.001983664691986601, | |
| "loss": 0.4712, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": 0.0933491587638855, | |
| "learning_rate": 0.001981255310627385, | |
| "loss": 0.4692, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.5925925925925926, | |
| "grad_norm": 0.09102772176265717, | |
| "learning_rate": 0.0019786819219718443, | |
| "loss": 0.4666, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.6296296296296298, | |
| "grad_norm": 0.08935283869504929, | |
| "learning_rate": 0.0019759449561369035, | |
| "loss": 0.4605, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 0.10174907743930817, | |
| "learning_rate": 0.0019730448705798237, | |
| "loss": 0.465, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.7037037037037037, | |
| "grad_norm": 0.09616223722696304, | |
| "learning_rate": 0.0019699821500217436, | |
| "loss": 0.4684, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.7407407407407407, | |
| "grad_norm": 0.09224896878004074, | |
| "learning_rate": 0.001966757306366662, | |
| "loss": 0.468, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.09403350204229355, | |
| "learning_rate": 0.0019633708786158804, | |
| "loss": 0.4658, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.8148148148148149, | |
| "grad_norm": 0.09764115512371063, | |
| "learning_rate": 0.001959823432777912, | |
| "loss": 0.4682, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.8518518518518519, | |
| "grad_norm": 0.08690910041332245, | |
| "learning_rate": 0.0019561155617738796, | |
| "loss": 0.4679, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 0.10882115364074707, | |
| "learning_rate": 0.0019522478853384153, | |
| "loss": 0.46, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.925925925925926, | |
| "grad_norm": 0.10638313740491867, | |
| "learning_rate": 0.0019482210499160765, | |
| "loss": 0.4601, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.9629629629629628, | |
| "grad_norm": 0.1394616961479187, | |
| "learning_rate": 0.0019440357285533, | |
| "loss": 0.4649, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.11232441663742065, | |
| "learning_rate": 0.0019396926207859084, | |
| "loss": 0.458, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.2390342950820923, | |
| "eval_runtime": 1.4571, | |
| "eval_samples_per_second": 2.745, | |
| "eval_steps_per_second": 0.686, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.037037037037037, | |
| "grad_norm": 0.11058547347784042, | |
| "learning_rate": 0.0019351924525221897, | |
| "loss": 0.4336, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.074074074074074, | |
| "grad_norm": 0.10051153600215912, | |
| "learning_rate": 0.0019305359759215685, | |
| "loss": 0.4345, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.111111111111111, | |
| "grad_norm": 0.09568148106336594, | |
| "learning_rate": 0.0019257239692688907, | |
| "loss": 0.4356, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.148148148148148, | |
| "grad_norm": 0.09497468173503876, | |
| "learning_rate": 0.0019207572368443383, | |
| "loss": 0.44, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.185185185185185, | |
| "grad_norm": 0.10157410800457001, | |
| "learning_rate": 0.001915636608789006, | |
| "loss": 0.439, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.1098947674036026, | |
| "learning_rate": 0.0019103629409661467, | |
| "loss": 0.44, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.259259259259259, | |
| "grad_norm": 0.09858433902263641, | |
| "learning_rate": 0.0019049371148181253, | |
| "loss": 0.4466, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.2962962962962963, | |
| "grad_norm": 0.09663781523704529, | |
| "learning_rate": 0.0018993600372190932, | |
| "loss": 0.4408, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.3333333333333335, | |
| "grad_norm": 0.100925512611866, | |
| "learning_rate": 0.0018936326403234123, | |
| "loss": 0.4393, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.10806870460510254, | |
| "learning_rate": 0.0018877558814098562, | |
| "loss": 0.4393, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.4074074074074074, | |
| "grad_norm": 0.10387130826711655, | |
| "learning_rate": 0.001881730742721608, | |
| "loss": 0.4445, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.4444444444444446, | |
| "grad_norm": 0.09329431504011154, | |
| "learning_rate": 0.0018755582313020908, | |
| "loss": 0.439, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.4814814814814814, | |
| "grad_norm": 0.09396202117204666, | |
| "learning_rate": 0.0018692393788266478, | |
| "loss": 0.4379, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.5185185185185186, | |
| "grad_norm": 0.10305757075548172, | |
| "learning_rate": 0.0018627752414301084, | |
| "loss": 0.4412, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.5555555555555554, | |
| "grad_norm": 0.1034080982208252, | |
| "learning_rate": 0.0018561668995302665, | |
| "loss": 0.4445, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.5925925925925926, | |
| "grad_norm": 0.09808813035488129, | |
| "learning_rate": 0.0018494154576472975, | |
| "loss": 0.4454, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.6296296296296298, | |
| "grad_norm": 0.0979294404387474, | |
| "learning_rate": 0.0018425220442191495, | |
| "loss": 0.4498, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.09154608845710754, | |
| "learning_rate": 0.0018354878114129364, | |
| "loss": 0.4416, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.7037037037037037, | |
| "grad_norm": 0.0931951180100441, | |
| "learning_rate": 0.0018283139349323631, | |
| "loss": 0.4439, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.7407407407407405, | |
| "grad_norm": 0.09334207326173782, | |
| "learning_rate": 0.0018210016138212187, | |
| "loss": 0.4443, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.7777777777777777, | |
| "grad_norm": 0.092356376349926, | |
| "learning_rate": 0.0018135520702629675, | |
| "loss": 0.4429, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.814814814814815, | |
| "grad_norm": 0.09269876778125763, | |
| "learning_rate": 0.0018059665493764742, | |
| "loss": 0.4443, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.851851851851852, | |
| "grad_norm": 0.10383119434118271, | |
| "learning_rate": 0.0017982463190078929, | |
| "loss": 0.4436, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.888888888888889, | |
| "grad_norm": 0.0941496342420578, | |
| "learning_rate": 0.0017903926695187593, | |
| "loss": 0.4456, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.925925925925926, | |
| "grad_norm": 0.09286876022815704, | |
| "learning_rate": 0.0017824069135703197, | |
| "loss": 0.445, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.09152144938707352, | |
| "learning_rate": 0.0017742903859041324, | |
| "loss": 0.4499, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.09554123133420944, | |
| "learning_rate": 0.001766044443118978, | |
| "loss": 0.4423, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.2548832893371582, | |
| "eval_runtime": 1.4432, | |
| "eval_samples_per_second": 2.772, | |
| "eval_steps_per_second": 0.693, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 3.037037037037037, | |
| "grad_norm": 0.0980718806385994, | |
| "learning_rate": 0.001757670463444118, | |
| "loss": 0.4156, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.074074074074074, | |
| "grad_norm": 0.09404606372117996, | |
| "learning_rate": 0.0017491698465089362, | |
| "loss": 0.4121, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 3.111111111111111, | |
| "grad_norm": 0.11583345383405685, | |
| "learning_rate": 0.0017405440131090047, | |
| "loss": 0.4172, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.148148148148148, | |
| "grad_norm": 0.09314367175102234, | |
| "learning_rate": 0.0017317944049686123, | |
| "loss": 0.4166, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 3.185185185185185, | |
| "grad_norm": 0.1007940024137497, | |
| "learning_rate": 0.001722922484499793, | |
| "loss": 0.4123, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.2222222222222223, | |
| "grad_norm": 0.0978422611951828, | |
| "learning_rate": 0.0017139297345578992, | |
| "loss": 0.4199, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 3.259259259259259, | |
| "grad_norm": 0.09395431727170944, | |
| "learning_rate": 0.0017048176581937562, | |
| "loss": 0.4133, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.2962962962962963, | |
| "grad_norm": 0.09783247113227844, | |
| "learning_rate": 0.0016955877784024418, | |
| "loss": 0.4253, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.0955362394452095, | |
| "learning_rate": 0.0016862416378687337, | |
| "loss": 0.4204, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.3703703703703702, | |
| "grad_norm": 0.09792539477348328, | |
| "learning_rate": 0.001676780798709262, | |
| "loss": 0.4232, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 3.4074074074074074, | |
| "grad_norm": 0.09116431325674057, | |
| "learning_rate": 0.0016672068422114196, | |
| "loss": 0.4211, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.4444444444444446, | |
| "grad_norm": 0.1013198271393776, | |
| "learning_rate": 0.0016575213685690638, | |
| "loss": 0.4202, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 3.4814814814814814, | |
| "grad_norm": 0.09579209238290787, | |
| "learning_rate": 0.0016477259966150588, | |
| "loss": 0.4268, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.5185185185185186, | |
| "grad_norm": 0.09915994852781296, | |
| "learning_rate": 0.001637822363550706, | |
| "loss": 0.4274, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.09255506843328476, | |
| "learning_rate": 0.0016278121246720988, | |
| "loss": 0.4237, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.5925925925925926, | |
| "grad_norm": 0.09609281271696091, | |
| "learning_rate": 0.001617696953093457, | |
| "loss": 0.4287, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 3.6296296296296298, | |
| "grad_norm": 0.10273302346467972, | |
| "learning_rate": 0.0016074785394674836, | |
| "loss": 0.4301, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.6666666666666665, | |
| "grad_norm": 0.09646812826395035, | |
| "learning_rate": 0.0015971585917027862, | |
| "loss": 0.4282, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 3.7037037037037037, | |
| "grad_norm": 0.09089499711990356, | |
| "learning_rate": 0.001586738834678418, | |
| "loss": 0.425, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.7407407407407405, | |
| "grad_norm": 0.08903223276138306, | |
| "learning_rate": 0.0015762210099555802, | |
| "loss": 0.4222, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 3.7777777777777777, | |
| "grad_norm": 0.09616349637508392, | |
| "learning_rate": 0.0015656068754865387, | |
| "loss": 0.4243, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.814814814814815, | |
| "grad_norm": 0.0883878841996193, | |
| "learning_rate": 0.001554898205320797, | |
| "loss": 0.4278, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 3.851851851851852, | |
| "grad_norm": 0.0974721610546112, | |
| "learning_rate": 0.0015440967893085827, | |
| "loss": 0.4239, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.888888888888889, | |
| "grad_norm": 0.09724871814250946, | |
| "learning_rate": 0.0015332044328016914, | |
| "loss": 0.4269, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.925925925925926, | |
| "grad_norm": 0.09783729910850525, | |
| "learning_rate": 0.0015222229563517384, | |
| "loss": 0.4289, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.962962962962963, | |
| "grad_norm": 0.09811478108167648, | |
| "learning_rate": 0.0015111541954058731, | |
| "loss": 0.4265, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.09431273490190506, | |
| "learning_rate": 0.0015, | |
| "loss": 0.4244, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.266510009765625, | |
| "eval_runtime": 1.4433, | |
| "eval_samples_per_second": 2.771, | |
| "eval_steps_per_second": 0.693, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.037037037037037, | |
| "grad_norm": 0.09484298527240753, | |
| "learning_rate": 0.0014887622344495642, | |
| "loss": 0.3886, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 4.074074074074074, | |
| "grad_norm": 0.09763394296169281, | |
| "learning_rate": 0.001477442777037949, | |
| "loss": 0.3867, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.111111111111111, | |
| "grad_norm": 0.09587694704532623, | |
| "learning_rate": 0.001466043519702539, | |
| "loss": 0.3934, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.09805364161729813, | |
| "learning_rate": 0.0014545663677185006, | |
| "loss": 0.3913, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.185185185185185, | |
| "grad_norm": 0.09342525154352188, | |
| "learning_rate": 0.0014430132393803352, | |
| "loss": 0.3962, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 4.222222222222222, | |
| "grad_norm": 0.09320686757564545, | |
| "learning_rate": 0.0014313860656812536, | |
| "loss": 0.393, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.2592592592592595, | |
| "grad_norm": 0.09312278032302856, | |
| "learning_rate": 0.001419686789990429, | |
| "loss": 0.3956, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 4.296296296296296, | |
| "grad_norm": 0.09693987667560577, | |
| "learning_rate": 0.0014079173677281835, | |
| "loss": 0.4003, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.333333333333333, | |
| "grad_norm": 0.09647519141435623, | |
| "learning_rate": 0.001396079766039157, | |
| "loss": 0.4026, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 4.37037037037037, | |
| "grad_norm": 0.09753508865833282, | |
| "learning_rate": 0.0013841759634635176, | |
| "loss": 0.4047, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.407407407407407, | |
| "grad_norm": 0.09481139481067657, | |
| "learning_rate": 0.00137220794960627, | |
| "loss": 0.4028, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 0.0947929173707962, | |
| "learning_rate": 0.0013601777248047106, | |
| "loss": 0.4018, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.481481481481482, | |
| "grad_norm": 0.10154122114181519, | |
| "learning_rate": 0.0013480872997940906, | |
| "loss": 0.4019, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 4.518518518518518, | |
| "grad_norm": 0.09206040948629379, | |
| "learning_rate": 0.0013359386953715423, | |
| "loss": 0.401, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.555555555555555, | |
| "grad_norm": 0.0979878157377243, | |
| "learning_rate": 0.0013237339420583212, | |
| "loss": 0.4046, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 4.592592592592593, | |
| "grad_norm": 0.09499992430210114, | |
| "learning_rate": 0.0013114750797604247, | |
| "loss": 0.4092, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.62962962962963, | |
| "grad_norm": 0.096099354326725, | |
| "learning_rate": 0.0012991641574276419, | |
| "loss": 0.4066, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 4.666666666666667, | |
| "grad_norm": 0.09620559960603714, | |
| "learning_rate": 0.0012868032327110904, | |
| "loss": 0.4075, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.703703703703704, | |
| "grad_norm": 0.09676729887723923, | |
| "learning_rate": 0.0012743943716193016, | |
| "loss": 0.4026, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.09284202009439468, | |
| "learning_rate": 0.0012619396481729059, | |
| "loss": 0.4055, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.777777777777778, | |
| "grad_norm": 0.09661979228258133, | |
| "learning_rate": 0.0012494411440579815, | |
| "loss": 0.4068, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 4.814814814814815, | |
| "grad_norm": 0.09566741436719894, | |
| "learning_rate": 0.001236900948278119, | |
| "loss": 0.4021, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.851851851851852, | |
| "grad_norm": 0.09348838031291962, | |
| "learning_rate": 0.0012243211568052678, | |
| "loss": 0.4024, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 4.888888888888889, | |
| "grad_norm": 0.09663164615631104, | |
| "learning_rate": 0.0012117038722294108, | |
| "loss": 0.4062, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.925925925925926, | |
| "grad_norm": 0.09402230381965637, | |
| "learning_rate": 0.0011990512034071405, | |
| "loss": 0.4028, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 4.962962962962963, | |
| "grad_norm": 0.10056190937757492, | |
| "learning_rate": 0.0011863652651091822, | |
| "loss": 0.4074, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.09207284450531006, | |
| "learning_rate": 0.0011736481776669307, | |
| "loss": 0.4051, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.271437644958496, | |
| "eval_runtime": 1.4527, | |
| "eval_samples_per_second": 2.753, | |
| "eval_steps_per_second": 0.688, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 5.037037037037037, | |
| "grad_norm": 0.10166580975055695, | |
| "learning_rate": 0.0011609020666180573, | |
| "loss": 0.369, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.074074074074074, | |
| "grad_norm": 0.10062967240810394, | |
| "learning_rate": 0.001148129062351249, | |
| "loss": 0.3679, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 5.111111111111111, | |
| "grad_norm": 0.09751473367214203, | |
| "learning_rate": 0.0011353312997501312, | |
| "loss": 0.3679, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.148148148148148, | |
| "grad_norm": 0.0990433469414711, | |
| "learning_rate": 0.0011225109178364455, | |
| "loss": 0.3685, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 5.185185185185185, | |
| "grad_norm": 0.099190853536129, | |
| "learning_rate": 0.0011096700594125316, | |
| "loss": 0.3736, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.222222222222222, | |
| "grad_norm": 0.1061362773180008, | |
| "learning_rate": 0.0010968108707031792, | |
| "loss": 0.3751, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 5.2592592592592595, | |
| "grad_norm": 0.11798923462629318, | |
| "learning_rate": 0.0010839355009969068, | |
| "loss": 0.3757, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.296296296296296, | |
| "grad_norm": 0.09905427694320679, | |
| "learning_rate": 0.00107104610228673, | |
| "loss": 0.375, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.1025015115737915, | |
| "learning_rate": 0.0010581448289104759, | |
| "loss": 0.3763, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.37037037037037, | |
| "grad_norm": 0.1149529442191124, | |
| "learning_rate": 0.0010452338371907063, | |
| "loss": 0.3882, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 5.407407407407407, | |
| "grad_norm": 0.12777069211006165, | |
| "learning_rate": 0.0010323152850743107, | |
| "loss": 0.3812, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.444444444444445, | |
| "grad_norm": 0.10847526788711548, | |
| "learning_rate": 0.0010193913317718243, | |
| "loss": 0.3832, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 5.481481481481482, | |
| "grad_norm": 0.11118727922439575, | |
| "learning_rate": 0.0010064641373965393, | |
| "loss": 0.384, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.518518518518518, | |
| "grad_norm": 0.12322206795215607, | |
| "learning_rate": 0.0009935358626034607, | |
| "loss": 0.3826, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 0.1018897145986557, | |
| "learning_rate": 0.0009806086682281757, | |
| "loss": 0.3828, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.592592592592593, | |
| "grad_norm": 0.10415022075176239, | |
| "learning_rate": 0.0009676847149256894, | |
| "loss": 0.3834, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 5.62962962962963, | |
| "grad_norm": 0.10056640207767487, | |
| "learning_rate": 0.0009547661628092937, | |
| "loss": 0.379, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.666666666666667, | |
| "grad_norm": 0.13305579125881195, | |
| "learning_rate": 0.0009418551710895242, | |
| "loss": 0.3836, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 5.703703703703704, | |
| "grad_norm": 0.1132049411535263, | |
| "learning_rate": 0.0009289538977132702, | |
| "loss": 0.3815, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.7407407407407405, | |
| "grad_norm": 0.12073713541030884, | |
| "learning_rate": 0.000916064499003093, | |
| "loss": 0.384, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 5.777777777777778, | |
| "grad_norm": 0.0997130498290062, | |
| "learning_rate": 0.000903189129296821, | |
| "loss": 0.3836, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.814814814814815, | |
| "grad_norm": 0.1098228394985199, | |
| "learning_rate": 0.0008903299405874684, | |
| "loss": 0.3901, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 5.851851851851852, | |
| "grad_norm": 0.10409754514694214, | |
| "learning_rate": 0.0008774890821635547, | |
| "loss": 0.3806, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.888888888888889, | |
| "grad_norm": 0.09349874407052994, | |
| "learning_rate": 0.0008646687002498692, | |
| "loss": 0.3821, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 5.925925925925926, | |
| "grad_norm": 0.0936858206987381, | |
| "learning_rate": 0.0008518709376487514, | |
| "loss": 0.3842, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.962962962962963, | |
| "grad_norm": 0.09671808034181595, | |
| "learning_rate": 0.0008390979333819426, | |
| "loss": 0.3813, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.10419617593288422, | |
| "learning_rate": 0.0008263518223330697, | |
| "loss": 0.3815, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.2959271669387817, | |
| "eval_runtime": 1.4543, | |
| "eval_samples_per_second": 2.75, | |
| "eval_steps_per_second": 0.688, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.037037037037037, | |
| "grad_norm": 0.10344818234443665, | |
| "learning_rate": 0.0008136347348908179, | |
| "loss": 0.3456, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 6.074074074074074, | |
| "grad_norm": 0.11311297118663788, | |
| "learning_rate": 0.0008009487965928596, | |
| "loss": 0.3457, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.111111111111111, | |
| "grad_norm": 0.1126752719283104, | |
| "learning_rate": 0.0007882961277705895, | |
| "loss": 0.3446, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 6.148148148148148, | |
| "grad_norm": 0.10734600573778152, | |
| "learning_rate": 0.0007756788431947326, | |
| "loss": 0.3441, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 6.185185185185185, | |
| "grad_norm": 0.10664735734462738, | |
| "learning_rate": 0.0007630990517218807, | |
| "loss": 0.3464, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 6.222222222222222, | |
| "grad_norm": 0.10784178227186203, | |
| "learning_rate": 0.0007505588559420188, | |
| "loss": 0.3484, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.2592592592592595, | |
| "grad_norm": 0.09735342860221863, | |
| "learning_rate": 0.0007380603518270941, | |
| "loss": 0.3473, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 6.296296296296296, | |
| "grad_norm": 0.10385815799236298, | |
| "learning_rate": 0.0007256056283806986, | |
| "loss": 0.3493, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.333333333333333, | |
| "grad_norm": 0.10252544283866882, | |
| "learning_rate": 0.0007131967672889101, | |
| "loss": 0.3531, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 6.37037037037037, | |
| "grad_norm": 0.10720902681350708, | |
| "learning_rate": 0.0007008358425723586, | |
| "loss": 0.3543, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.407407407407407, | |
| "grad_norm": 0.1041482537984848, | |
| "learning_rate": 0.0006885249202395753, | |
| "loss": 0.3508, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 6.444444444444445, | |
| "grad_norm": 0.10373668372631073, | |
| "learning_rate": 0.000676266057941679, | |
| "loss": 0.3534, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.481481481481482, | |
| "grad_norm": 0.10245037823915482, | |
| "learning_rate": 0.0006640613046284581, | |
| "loss": 0.3521, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 6.518518518518518, | |
| "grad_norm": 0.10254081338644028, | |
| "learning_rate": 0.0006519127002059096, | |
| "loss": 0.3538, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.555555555555555, | |
| "grad_norm": 0.10260630398988724, | |
| "learning_rate": 0.0006398222751952898, | |
| "loss": 0.3537, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 6.592592592592593, | |
| "grad_norm": 0.10130611807107925, | |
| "learning_rate": 0.0006277920503937303, | |
| "loss": 0.3515, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.62962962962963, | |
| "grad_norm": 0.10895968973636627, | |
| "learning_rate": 0.0006158240365364823, | |
| "loss": 0.3578, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.09870075434446335, | |
| "learning_rate": 0.0006039202339608432, | |
| "loss": 0.3512, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.703703703703704, | |
| "grad_norm": 0.10364022850990295, | |
| "learning_rate": 0.0005920826322718165, | |
| "loss": 0.3537, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 6.7407407407407405, | |
| "grad_norm": 0.10551033914089203, | |
| "learning_rate": 0.000580313210009571, | |
| "loss": 0.3566, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.777777777777778, | |
| "grad_norm": 0.10657215118408203, | |
| "learning_rate": 0.0005686139343187468, | |
| "loss": 0.3552, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 6.814814814814815, | |
| "grad_norm": 0.10223071277141571, | |
| "learning_rate": 0.0005569867606196651, | |
| "loss": 0.3584, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.851851851851852, | |
| "grad_norm": 0.10146836936473846, | |
| "learning_rate": 0.0005454336322814994, | |
| "loss": 0.3535, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 6.888888888888889, | |
| "grad_norm": 0.1027546152472496, | |
| "learning_rate": 0.0005339564802974615, | |
| "loss": 0.3501, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.925925925925926, | |
| "grad_norm": 0.10245343297719955, | |
| "learning_rate": 0.0005225572229620509, | |
| "loss": 0.3512, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 6.962962962962963, | |
| "grad_norm": 0.10256995260715485, | |
| "learning_rate": 0.0005112377655504359, | |
| "loss": 0.3543, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.10365499556064606, | |
| "learning_rate": 0.0005000000000000002, | |
| "loss": 0.3546, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.3559757471084595, | |
| "eval_runtime": 1.4533, | |
| "eval_samples_per_second": 2.752, | |
| "eval_steps_per_second": 0.688, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 7.037037037037037, | |
| "grad_norm": 0.11704354733228683, | |
| "learning_rate": 0.0004888458045941269, | |
| "loss": 0.32, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 7.074074074074074, | |
| "grad_norm": 0.11646736413240433, | |
| "learning_rate": 0.0004777770436482617, | |
| "loss": 0.3177, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 7.111111111111111, | |
| "grad_norm": 0.11117232590913773, | |
| "learning_rate": 0.000466795567198309, | |
| "loss": 0.3144, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 7.148148148148148, | |
| "grad_norm": 0.10937786102294922, | |
| "learning_rate": 0.0004559032106914173, | |
| "loss": 0.3212, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 7.185185185185185, | |
| "grad_norm": 0.11477228999137878, | |
| "learning_rate": 0.0004451017946792032, | |
| "loss": 0.3219, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 7.222222222222222, | |
| "grad_norm": 0.10524013638496399, | |
| "learning_rate": 0.0004343931245134616, | |
| "loss": 0.3167, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 7.2592592592592595, | |
| "grad_norm": 0.10898813605308533, | |
| "learning_rate": 0.0004237789900444197, | |
| "loss": 0.3204, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 7.296296296296296, | |
| "grad_norm": 0.11245737224817276, | |
| "learning_rate": 0.0004132611653215822, | |
| "loss": 0.3216, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 7.333333333333333, | |
| "grad_norm": 0.1109575405716896, | |
| "learning_rate": 0.00040284140829721405, | |
| "loss": 0.3211, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 7.37037037037037, | |
| "grad_norm": 0.10827223211526871, | |
| "learning_rate": 0.00039252146053251637, | |
| "loss": 0.3224, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 7.407407407407407, | |
| "grad_norm": 0.11438044160604477, | |
| "learning_rate": 0.00038230304690654306, | |
| "loss": 0.3243, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.444444444444445, | |
| "grad_norm": 0.1066223755478859, | |
| "learning_rate": 0.00037218787532790164, | |
| "loss": 0.3253, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 7.481481481481482, | |
| "grad_norm": 0.11840826272964478, | |
| "learning_rate": 0.0003621776364492939, | |
| "loss": 0.327, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.518518518518518, | |
| "grad_norm": 0.1115390807390213, | |
| "learning_rate": 0.0003522740033849411, | |
| "loss": 0.3261, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 7.555555555555555, | |
| "grad_norm": 0.1104753240942955, | |
| "learning_rate": 0.0003424786314309365, | |
| "loss": 0.3225, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.592592592592593, | |
| "grad_norm": 0.10727293789386749, | |
| "learning_rate": 0.00033279315778858033, | |
| "loss": 0.3237, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 7.62962962962963, | |
| "grad_norm": 0.11141736060380936, | |
| "learning_rate": 0.0003232192012907381, | |
| "loss": 0.3237, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.666666666666667, | |
| "grad_norm": 0.10661887377500534, | |
| "learning_rate": 0.0003137583621312665, | |
| "loss": 0.3257, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 7.703703703703704, | |
| "grad_norm": 0.11351703852415085, | |
| "learning_rate": 0.000304412221597558, | |
| "loss": 0.3236, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.7407407407407405, | |
| "grad_norm": 0.10875287652015686, | |
| "learning_rate": 0.0002951823418062439, | |
| "loss": 0.3268, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 7.777777777777778, | |
| "grad_norm": 0.1116643026471138, | |
| "learning_rate": 0.0002860702654421011, | |
| "loss": 0.3239, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.814814814814815, | |
| "grad_norm": 0.10941953957080841, | |
| "learning_rate": 0.0002770775155002071, | |
| "loss": 0.3257, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 7.851851851851852, | |
| "grad_norm": 0.10806366801261902, | |
| "learning_rate": 0.00026820559503138797, | |
| "loss": 0.3235, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.888888888888889, | |
| "grad_norm": 0.1069023609161377, | |
| "learning_rate": 0.0002594559868909956, | |
| "loss": 0.3293, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 7.925925925925926, | |
| "grad_norm": 0.10821282863616943, | |
| "learning_rate": 0.000250830153491064, | |
| "loss": 0.3267, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.962962962962963, | |
| "grad_norm": 0.1114460751414299, | |
| "learning_rate": 0.00024232953655588209, | |
| "loss": 0.3225, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.1069159284234047, | |
| "learning_rate": 0.0002339555568810221, | |
| "loss": 0.3233, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.4125341176986694, | |
| "eval_runtime": 1.4532, | |
| "eval_samples_per_second": 2.753, | |
| "eval_steps_per_second": 0.688, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 8.037037037037036, | |
| "grad_norm": 0.13299891352653503, | |
| "learning_rate": 0.00022570961409586754, | |
| "loss": 0.2956, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 8.074074074074074, | |
| "grad_norm": 0.11145825684070587, | |
| "learning_rate": 0.00021759308642968023, | |
| "loss": 0.2952, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 8.11111111111111, | |
| "grad_norm": 0.11993227154016495, | |
| "learning_rate": 0.00020960733048124082, | |
| "loss": 0.2951, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 8.148148148148149, | |
| "grad_norm": 0.11672375351190567, | |
| "learning_rate": 0.00020175368099210702, | |
| "loss": 0.2961, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.185185185185185, | |
| "grad_norm": 0.11903874576091766, | |
| "learning_rate": 0.00019403345062352572, | |
| "loss": 0.2981, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 8.222222222222221, | |
| "grad_norm": 0.11281085014343262, | |
| "learning_rate": 0.00018644792973703252, | |
| "loss": 0.2983, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 8.25925925925926, | |
| "grad_norm": 0.11996857821941376, | |
| "learning_rate": 0.00017899838617878162, | |
| "loss": 0.2993, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 8.296296296296296, | |
| "grad_norm": 0.11176000535488129, | |
| "learning_rate": 0.00017168606506763696, | |
| "loss": 0.2972, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 8.333333333333334, | |
| "grad_norm": 0.11802016943693161, | |
| "learning_rate": 0.00016451218858706373, | |
| "loss": 0.2977, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 8.37037037037037, | |
| "grad_norm": 0.11810103803873062, | |
| "learning_rate": 0.00015747795578085046, | |
| "loss": 0.3002, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 8.407407407407407, | |
| "grad_norm": 0.12034923583269119, | |
| "learning_rate": 0.0001505845423527027, | |
| "loss": 0.2961, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 8.444444444444445, | |
| "grad_norm": 0.11696241796016693, | |
| "learning_rate": 0.00014383310046973364, | |
| "loss": 0.2977, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 8.481481481481481, | |
| "grad_norm": 0.11664384603500366, | |
| "learning_rate": 0.00013722475856989158, | |
| "loss": 0.2952, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 8.518518518518519, | |
| "grad_norm": 0.117145836353302, | |
| "learning_rate": 0.00013076062117335218, | |
| "loss": 0.3016, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.555555555555555, | |
| "grad_norm": 0.11361709982156754, | |
| "learning_rate": 0.00012444176869790924, | |
| "loss": 0.2988, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 8.592592592592592, | |
| "grad_norm": 0.1155712679028511, | |
| "learning_rate": 0.00011826925727839199, | |
| "loss": 0.2977, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.62962962962963, | |
| "grad_norm": 0.1212184950709343, | |
| "learning_rate": 0.00011224411859014417, | |
| "loss": 0.298, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 8.666666666666666, | |
| "grad_norm": 0.11797547340393066, | |
| "learning_rate": 0.00010636735967658784, | |
| "loss": 0.3007, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.703703703703704, | |
| "grad_norm": 0.11559978872537613, | |
| "learning_rate": 0.00010063996278090704, | |
| "loss": 0.2958, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 8.74074074074074, | |
| "grad_norm": 0.11640750616788864, | |
| "learning_rate": 9.506288518187466e-05, | |
| "loss": 0.2966, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.777777777777779, | |
| "grad_norm": 0.11927841603755951, | |
| "learning_rate": 8.963705903385344e-05, | |
| "loss": 0.2953, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 8.814814814814815, | |
| "grad_norm": 0.11425163596868515, | |
| "learning_rate": 8.436339121099412e-05, | |
| "loss": 0.2989, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.851851851851851, | |
| "grad_norm": 0.11373434215784073, | |
| "learning_rate": 7.92427631556617e-05, | |
| "loss": 0.2984, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 0.11790241301059723, | |
| "learning_rate": 7.427603073110967e-05, | |
| "loss": 0.2972, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.925925925925926, | |
| "grad_norm": 0.11773653328418732, | |
| "learning_rate": 6.946402407843155e-05, | |
| "loss": 0.3012, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 8.962962962962964, | |
| "grad_norm": 0.12333875894546509, | |
| "learning_rate": 6.480754747781037e-05, | |
| "loss": 0.2959, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.11808749288320541, | |
| "learning_rate": 6.0307379214091684e-05, | |
| "loss": 0.2969, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.4809459447860718, | |
| "eval_runtime": 1.4606, | |
| "eval_samples_per_second": 2.739, | |
| "eval_steps_per_second": 0.685, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 9.037037037037036, | |
| "grad_norm": 0.1122315376996994, | |
| "learning_rate": 5.596427144670002e-05, | |
| "loss": 0.2797, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 9.074074074074074, | |
| "grad_norm": 0.12401442974805832, | |
| "learning_rate": 5.1778950083923526e-05, | |
| "loss": 0.2823, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 9.11111111111111, | |
| "grad_norm": 0.11285774409770966, | |
| "learning_rate": 4.775211466158469e-05, | |
| "loss": 0.2825, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 9.148148148148149, | |
| "grad_norm": 0.11427191644906998, | |
| "learning_rate": 4.3884438226120426e-05, | |
| "loss": 0.2815, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 9.185185185185185, | |
| "grad_norm": 0.11915598809719086, | |
| "learning_rate": 4.017656722208807e-05, | |
| "loss": 0.2806, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 9.222222222222221, | |
| "grad_norm": 0.11690084636211395, | |
| "learning_rate": 3.6629121384119666e-05, | |
| "loss": 0.2811, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 9.25925925925926, | |
| "grad_norm": 0.11301770061254501, | |
| "learning_rate": 3.324269363333799e-05, | |
| "loss": 0.2811, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 9.296296296296296, | |
| "grad_norm": 0.1201760470867157, | |
| "learning_rate": 3.0017849978256518e-05, | |
| "loss": 0.2826, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 9.333333333333334, | |
| "grad_norm": 0.11819873005151749, | |
| "learning_rate": 2.6955129420176194e-05, | |
| "loss": 0.2787, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 9.37037037037037, | |
| "grad_norm": 0.11501555889844894, | |
| "learning_rate": 2.4055043863096426e-05, | |
| "loss": 0.2803, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 9.407407407407407, | |
| "grad_norm": 0.11644010990858078, | |
| "learning_rate": 2.1318078028155885e-05, | |
| "loss": 0.2823, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 9.444444444444445, | |
| "grad_norm": 0.11667327582836151, | |
| "learning_rate": 1.874468937261531e-05, | |
| "loss": 0.2836, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 9.481481481481481, | |
| "grad_norm": 0.11722666025161743, | |
| "learning_rate": 1.6335308013398887e-05, | |
| "loss": 0.2837, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 9.518518518518519, | |
| "grad_norm": 0.11853759735822678, | |
| "learning_rate": 1.4090336655203539e-05, | |
| "loss": 0.2816, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 9.555555555555555, | |
| "grad_norm": 0.11931838095188141, | |
| "learning_rate": 1.2010150523190988e-05, | |
| "loss": 0.2831, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 9.592592592592592, | |
| "grad_norm": 0.11536389589309692, | |
| "learning_rate": 1.0095097300273027e-05, | |
| "loss": 0.2824, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 9.62962962962963, | |
| "grad_norm": 0.11747179180383682, | |
| "learning_rate": 8.345497068998897e-06, | |
| "loss": 0.2849, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.666666666666666, | |
| "grad_norm": 0.12529109418392181, | |
| "learning_rate": 6.761642258056977e-06, | |
| "loss": 0.2841, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 9.703703703703704, | |
| "grad_norm": 0.11867683380842209, | |
| "learning_rate": 5.343797593398536e-06, | |
| "loss": 0.2822, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.74074074074074, | |
| "grad_norm": 0.11928539723157883, | |
| "learning_rate": 4.092200053990691e-06, | |
| "loss": 0.2809, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 9.777777777777779, | |
| "grad_norm": 0.11743851751089096, | |
| "learning_rate": 3.007058832207976e-06, | |
| "loss": 0.2819, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.814814814814815, | |
| "grad_norm": 0.11580769717693329, | |
| "learning_rate": 2.088555298867978e-06, | |
| "loss": 0.2819, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 9.851851851851851, | |
| "grad_norm": 0.11537632346153259, | |
| "learning_rate": 1.3368429729168074e-06, | |
| "loss": 0.2814, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.88888888888889, | |
| "grad_norm": 0.1173846423625946, | |
| "learning_rate": 7.520474957699585e-07, | |
| "loss": 0.2832, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 9.925925925925926, | |
| "grad_norm": 0.11481310427188873, | |
| "learning_rate": 3.3426661031255026e-07, | |
| "loss": 0.285, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.962962962962964, | |
| "grad_norm": 0.11797128617763519, | |
| "learning_rate": 8.357014456272793e-08, | |
| "loss": 0.2824, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.11149542033672333, | |
| "learning_rate": 0.0, | |
| "loss": 0.2818, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.517443060874939, | |
| "eval_runtime": 1.4076, | |
| "eval_samples_per_second": 2.842, | |
| "eval_steps_per_second": 0.71, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1350, | |
| "total_flos": 7.982333171800736e+18, | |
| "train_loss": 0.3983345487382677, | |
| "train_runtime": 11606.8402, | |
| "train_samples_per_second": 14.865, | |
| "train_steps_per_second": 0.116 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1350, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 7.982333171800736e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |