| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 30, |
| "global_step": 1162, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.017219113215669393, |
| "grad_norm": 8.32422161102295, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 2.589, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.034438226431338786, |
| "grad_norm": 0.8107045292854309, |
| "learning_rate": 3.247863247863248e-05, |
| "loss": 0.9674, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.05165733964700818, |
| "grad_norm": 0.7474735379219055, |
| "learning_rate": 4.9572649572649575e-05, |
| "loss": 0.5896, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.05165733964700818, |
| "eval_loss": 0.5013840198516846, |
| "eval_runtime": 53.9761, |
| "eval_samples_per_second": 4.539, |
| "eval_steps_per_second": 4.539, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.06887645286267757, |
| "grad_norm": 0.5421889424324036, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.439, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.08609556607834697, |
| "grad_norm": 0.5523178577423096, |
| "learning_rate": 8.376068376068377e-05, |
| "loss": 0.334, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.10331467929401636, |
| "grad_norm": 0.5268102884292603, |
| "learning_rate": 0.00010085470085470086, |
| "loss": 0.2835, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.10331467929401636, |
| "eval_loss": 0.2452857494354248, |
| "eval_runtime": 53.6208, |
| "eval_samples_per_second": 4.569, |
| "eval_steps_per_second": 4.569, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.12053379250968575, |
| "grad_norm": 0.4393221437931061, |
| "learning_rate": 0.00011794871794871796, |
| "loss": 0.2366, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.13775290572535515, |
| "grad_norm": 0.5775641202926636, |
| "learning_rate": 0.00013504273504273505, |
| "loss": 0.2218, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.15497201894102453, |
| "grad_norm": 0.4302266240119934, |
| "learning_rate": 0.00015213675213675214, |
| "loss": 0.1986, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.15497201894102453, |
| "eval_loss": 0.1793452501296997, |
| "eval_runtime": 53.5304, |
| "eval_samples_per_second": 4.577, |
| "eval_steps_per_second": 4.577, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.17219113215669393, |
| "grad_norm": 0.39770159125328064, |
| "learning_rate": 0.00016923076923076923, |
| "loss": 0.186, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1894102453723633, |
| "grad_norm": 0.4006386399269104, |
| "learning_rate": 0.00018632478632478634, |
| "loss": 0.1708, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.20662935858803272, |
| "grad_norm": 0.4491441547870636, |
| "learning_rate": 0.00019999819242697418, |
| "loss": 0.1712, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.20662935858803272, |
| "eval_loss": 0.15836507081985474, |
| "eval_runtime": 53.6179, |
| "eval_samples_per_second": 4.569, |
| "eval_steps_per_second": 4.569, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.2238484718037021, |
| "grad_norm": 0.33016568422317505, |
| "learning_rate": 0.00019993493423217814, |
| "loss": 0.1638, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.2410675850193715, |
| "grad_norm": 0.22399674355983734, |
| "learning_rate": 0.00019978136272187747, |
| "loss": 0.1533, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.2582866982350409, |
| "grad_norm": 0.2746177911758423, |
| "learning_rate": 0.0001995376166818969, |
| "loss": 0.158, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.2582866982350409, |
| "eval_loss": 0.14334778487682343, |
| "eval_runtime": 53.578, |
| "eval_samples_per_second": 4.573, |
| "eval_steps_per_second": 4.573, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.2755058114507103, |
| "grad_norm": 0.2805308699607849, |
| "learning_rate": 0.00019920391639069242, |
| "loss": 0.1509, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.29272492466637967, |
| "grad_norm": 0.4730603098869324, |
| "learning_rate": 0.00019878056342028102, |
| "loss": 0.1496, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.30994403788204905, |
| "grad_norm": 0.23217393457889557, |
| "learning_rate": 0.00019826794036370362, |
| "loss": 0.1472, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.30994403788204905, |
| "eval_loss": 0.13477234542369843, |
| "eval_runtime": 53.4805, |
| "eval_samples_per_second": 4.581, |
| "eval_steps_per_second": 4.581, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.3271631510977185, |
| "grad_norm": 0.28313347697257996, |
| "learning_rate": 0.0001976665104892678, |
| "loss": 0.147, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.34438226431338786, |
| "grad_norm": 0.15724846720695496, |
| "learning_rate": 0.00019697681732188218, |
| "loss": 0.1426, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.36160137752905724, |
| "grad_norm": 0.24457155168056488, |
| "learning_rate": 0.00019619948415186173, |
| "loss": 0.1397, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.36160137752905724, |
| "eval_loss": 0.13591289520263672, |
| "eval_runtime": 53.3683, |
| "eval_samples_per_second": 4.591, |
| "eval_steps_per_second": 4.591, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.3788204907447266, |
| "grad_norm": 0.25315046310424805, |
| "learning_rate": 0.00019533521347164687, |
| "loss": 0.1454, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.39603960396039606, |
| "grad_norm": 0.20438989996910095, |
| "learning_rate": 0.00019438478634094638, |
| "loss": 0.1404, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.41325871717606544, |
| "grad_norm": 0.3646264672279358, |
| "learning_rate": 0.00019334906168087698, |
| "loss": 0.1371, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.41325871717606544, |
| "eval_loss": 0.12897279858589172, |
| "eval_runtime": 53.3855, |
| "eval_samples_per_second": 4.589, |
| "eval_steps_per_second": 4.589, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.4304778303917348, |
| "grad_norm": 0.24957729876041412, |
| "learning_rate": 0.00019222897549773848, |
| "loss": 0.1489, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.4476969436074042, |
| "grad_norm": 0.17658768594264984, |
| "learning_rate": 0.00019102554003712466, |
| "loss": 0.1221, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.46491605682307363, |
| "grad_norm": 0.26017439365386963, |
| "learning_rate": 0.00018973984286913584, |
| "loss": 0.1364, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.46491605682307363, |
| "eval_loss": 0.12664556503295898, |
| "eval_runtime": 53.4534, |
| "eval_samples_per_second": 4.583, |
| "eval_steps_per_second": 4.583, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.482135170038743, |
| "grad_norm": 0.13661746680736542, |
| "learning_rate": 0.0001883730459055186, |
| "loss": 0.128, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.4993542832544124, |
| "grad_norm": 0.20260806381702423, |
| "learning_rate": 0.00018692638434962143, |
| "loss": 0.1341, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.5165733964700818, |
| "grad_norm": 0.14534738659858704, |
| "learning_rate": 0.0001854011655801157, |
| "loss": 0.1393, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.5165733964700818, |
| "eval_loss": 0.12330517172813416, |
| "eval_runtime": 53.8347, |
| "eval_samples_per_second": 4.551, |
| "eval_steps_per_second": 4.551, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.5337925096857512, |
| "grad_norm": 0.15992437303066254, |
| "learning_rate": 0.0001837987679694894, |
| "loss": 0.1344, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.5510116229014206, |
| "grad_norm": 0.17435793578624725, |
| "learning_rate": 0.0001821206396383831, |
| "loss": 0.1326, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.56823073611709, |
| "grad_norm": 0.12753354012966156, |
| "learning_rate": 0.00018036829714689252, |
| "loss": 0.1265, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.56823073611709, |
| "eval_loss": 0.12111596018075943, |
| "eval_runtime": 53.8413, |
| "eval_samples_per_second": 4.55, |
| "eval_steps_per_second": 4.55, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.5854498493327593, |
| "grad_norm": 0.17733751237392426, |
| "learning_rate": 0.00017854332412402108, |
| "loss": 0.1321, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.6026689625484287, |
| "grad_norm": 0.18490831553936005, |
| "learning_rate": 0.00017664736983652088, |
| "loss": 0.1336, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.6198880757640981, |
| "grad_norm": 0.16691215336322784, |
| "learning_rate": 0.0001746821476984154, |
| "loss": 0.1286, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.6198880757640981, |
| "eval_loss": 0.1179625391960144, |
| "eval_runtime": 53.9361, |
| "eval_samples_per_second": 4.542, |
| "eval_steps_per_second": 4.542, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.6371071889797676, |
| "grad_norm": 0.1389610469341278, |
| "learning_rate": 0.000172649433722551, |
| "loss": 0.123, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.654326302195437, |
| "grad_norm": 0.12287218123674393, |
| "learning_rate": 0.00017055106491557645, |
| "loss": 0.1264, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.6715454154111064, |
| "grad_norm": 0.13567915558815002, |
| "learning_rate": 0.00016838893761780127, |
| "loss": 0.1258, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.6715454154111064, |
| "eval_loss": 0.11948917806148529, |
| "eval_runtime": 53.9271, |
| "eval_samples_per_second": 4.543, |
| "eval_steps_per_second": 4.543, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.6887645286267757, |
| "grad_norm": 0.1640617996454239, |
| "learning_rate": 0.00016616500578943273, |
| "loss": 0.1233, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.7059836418424451, |
| "grad_norm": 0.10329368710517883, |
| "learning_rate": 0.0001638812792447406, |
| "loss": 0.1275, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.7232027550581145, |
| "grad_norm": 0.11142633855342865, |
| "learning_rate": 0.0001615398218357457, |
| "loss": 0.132, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.7232027550581145, |
| "eval_loss": 0.11622682213783264, |
| "eval_runtime": 53.961, |
| "eval_samples_per_second": 4.54, |
| "eval_steps_per_second": 4.54, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.7404218682737839, |
| "grad_norm": 0.12253064662218094, |
| "learning_rate": 0.0001591427495870729, |
| "loss": 0.1272, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.7576409814894532, |
| "grad_norm": 0.14540846645832062, |
| "learning_rate": 0.00015669222878365486, |
| "loss": 0.1317, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.7748600947051227, |
| "grad_norm": 0.10412976145744324, |
| "learning_rate": 0.00015419047401301472, |
| "loss": 0.1317, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.7748600947051227, |
| "eval_loss": 0.11769552528858185, |
| "eval_runtime": 53.9569, |
| "eval_samples_per_second": 4.541, |
| "eval_steps_per_second": 4.541, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.7920792079207921, |
| "grad_norm": 0.12871715426445007, |
| "learning_rate": 0.0001516397461638962, |
| "loss": 0.129, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.8092983211364615, |
| "grad_norm": 0.21784746646881104, |
| "learning_rate": 0.00014904235038305083, |
| "loss": 0.1233, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.8265174343521309, |
| "grad_norm": 0.4632514417171478, |
| "learning_rate": 0.0001464006339920278, |
| "loss": 0.1363, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.8265174343521309, |
| "eval_loss": 0.11895836144685745, |
| "eval_runtime": 54.1763, |
| "eval_samples_per_second": 4.522, |
| "eval_steps_per_second": 4.522, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.8437365475678003, |
| "grad_norm": 0.15127432346343994, |
| "learning_rate": 0.00014371698436585004, |
| "loss": 0.1265, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.8609556607834696, |
| "grad_norm": 0.17194333672523499, |
| "learning_rate": 0.0001409938267754926, |
| "loss": 0.13, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.878174773999139, |
| "grad_norm": 0.15506021678447723, |
| "learning_rate": 0.0001382336221961141, |
| "loss": 0.1274, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.878174773999139, |
| "eval_loss": 0.11823900789022446, |
| "eval_runtime": 53.9107, |
| "eval_samples_per_second": 4.545, |
| "eval_steps_per_second": 4.545, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.8953938872148084, |
| "grad_norm": 0.13229945302009583, |
| "learning_rate": 0.00013543886508302148, |
| "loss": 0.1295, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.9126130004304779, |
| "grad_norm": 0.19207294285297394, |
| "learning_rate": 0.00013261208111737765, |
| "loss": 0.1156, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.9298321136461473, |
| "grad_norm": 0.20044037699699402, |
| "learning_rate": 0.00012975582492369016, |
| "loss": 0.1198, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.9298321136461473, |
| "eval_loss": 0.11498646438121796, |
| "eval_runtime": 53.9988, |
| "eval_samples_per_second": 4.537, |
| "eval_steps_per_second": 4.537, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.9470512268618166, |
| "grad_norm": 0.2503241002559662, |
| "learning_rate": 0.00012687267776114304, |
| "loss": 0.1325, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.964270340077486, |
| "grad_norm": 0.1304081231355667, |
| "learning_rate": 0.0001239652451908579, |
| "loss": 0.1305, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.9814894532931554, |
| "grad_norm": 0.17837955057621002, |
| "learning_rate": 0.0001210361547211936, |
| "loss": 0.1105, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.9814894532931554, |
| "eval_loss": 0.1158880740404129, |
| "eval_runtime": 53.9013, |
| "eval_samples_per_second": 4.545, |
| "eval_steps_per_second": 4.545, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.9987085665088248, |
| "grad_norm": 0.14954382181167603, |
| "learning_rate": 0.000118088053433211, |
| "loss": 0.1275, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.0154972018941024, |
| "grad_norm": 0.16672547161579132, |
| "learning_rate": 0.00011512360558844994, |
| "loss": 0.122, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.0327163151097718, |
| "grad_norm": 0.22516606748104095, |
| "learning_rate": 0.00011214549022117967, |
| "loss": 0.1215, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.0327163151097718, |
| "eval_loss": 0.11643720418214798, |
| "eval_runtime": 54.0392, |
| "eval_samples_per_second": 4.534, |
| "eval_steps_per_second": 4.534, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.0499354283254412, |
| "grad_norm": 0.10763582587242126, |
| "learning_rate": 0.00010915639871729874, |
| "loss": 0.1092, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.0671545415411106, |
| "grad_norm": 0.12457219511270523, |
| "learning_rate": 0.00010615903238207292, |
| "loss": 0.1262, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.08437365475678, |
| "grad_norm": 0.10427327454090118, |
| "learning_rate": 0.00010315609999890798, |
| "loss": 0.1221, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.08437365475678, |
| "eval_loss": 0.11431042104959488, |
| "eval_runtime": 53.9648, |
| "eval_samples_per_second": 4.54, |
| "eval_steps_per_second": 4.54, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.1015927679724493, |
| "grad_norm": 0.10417324304580688, |
| "learning_rate": 0.00010015031538136518, |
| "loss": 0.1243, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.118811881188119, |
| "grad_norm": 0.10996241122484207, |
| "learning_rate": 9.71443949206304e-05, |
| "loss": 0.123, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.1360309944037883, |
| "grad_norm": 0.09512694925069809, |
| "learning_rate": 9.41410551306537e-05, |
| "loss": 0.1161, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.1360309944037883, |
| "eval_loss": 0.11319658905267715, |
| "eval_runtime": 54.1752, |
| "eval_samples_per_second": 4.522, |
| "eval_steps_per_second": 4.522, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.1532501076194577, |
| "grad_norm": 0.08619705587625504, |
| "learning_rate": 9.114301019317854e-05, |
| "loss": 0.1138, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.170469220835127, |
| "grad_norm": 0.099159836769104, |
| "learning_rate": 8.815296950487804e-05, |
| "loss": 0.116, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.1876883340507964, |
| "grad_norm": 0.09249532967805862, |
| "learning_rate": 8.517363522881579e-05, |
| "loss": 0.1209, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.1876883340507964, |
| "eval_loss": 0.11321850121021271, |
| "eval_runtime": 54.1757, |
| "eval_samples_per_second": 4.522, |
| "eval_steps_per_second": 4.522, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.2049074472664658, |
| "grad_norm": 0.10436110198497772, |
| "learning_rate": 8.220769985244425e-05, |
| "loss": 0.1245, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.2221265604821352, |
| "grad_norm": 0.08504263311624527, |
| "learning_rate": 7.925784375434629e-05, |
| "loss": 0.1116, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.2393456736978046, |
| "grad_norm": 0.10974706709384918, |
| "learning_rate": 7.63267327819209e-05, |
| "loss": 0.1213, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.2393456736978046, |
| "eval_loss": 0.11273372918367386, |
| "eval_runtime": 54.1807, |
| "eval_samples_per_second": 4.522, |
| "eval_steps_per_second": 4.522, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.256564786913474, |
| "grad_norm": 0.0872415080666542, |
| "learning_rate": 7.341701584220006e-05, |
| "loss": 0.1164, |
| "step": 730 |
| }, |
| { |
| "epoch": 1.2737839001291433, |
| "grad_norm": 0.09694085270166397, |
| "learning_rate": 7.05313225079756e-05, |
| "loss": 0.1193, |
| "step": 740 |
| }, |
| { |
| "epoch": 1.2910030133448127, |
| "grad_norm": 0.09382116794586182, |
| "learning_rate": 6.767226064139841e-05, |
| "loss": 0.1212, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.2910030133448127, |
| "eval_loss": 0.11223271489143372, |
| "eval_runtime": 53.9413, |
| "eval_samples_per_second": 4.542, |
| "eval_steps_per_second": 4.542, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.308222126560482, |
| "grad_norm": 0.09150267392396927, |
| "learning_rate": 6.484241403719842e-05, |
| "loss": 0.1204, |
| "step": 760 |
| }, |
| { |
| "epoch": 1.3254412397761515, |
| "grad_norm": 0.10270262509584427, |
| "learning_rate": 6.204434008765458e-05, |
| "loss": 0.119, |
| "step": 770 |
| }, |
| { |
| "epoch": 1.3426603529918208, |
| "grad_norm": 0.10682746022939682, |
| "learning_rate": 5.9280567471425077e-05, |
| "loss": 0.1158, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.3426603529918208, |
| "eval_loss": 0.11181723326444626, |
| "eval_runtime": 53.9263, |
| "eval_samples_per_second": 4.543, |
| "eval_steps_per_second": 4.543, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.3598794662074902, |
| "grad_norm": 0.0856538936495781, |
| "learning_rate": 5.655359386832728e-05, |
| "loss": 0.1214, |
| "step": 790 |
| }, |
| { |
| "epoch": 1.3770985794231598, |
| "grad_norm": 0.08333317190408707, |
| "learning_rate": 5.386588370213124e-05, |
| "loss": 0.123, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.394317692638829, |
| "grad_norm": 0.08669654279947281, |
| "learning_rate": 5.121986591340808e-05, |
| "loss": 0.1177, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.394317692638829, |
| "eval_loss": 0.11222003400325775, |
| "eval_runtime": 53.9921, |
| "eval_samples_per_second": 4.538, |
| "eval_steps_per_second": 4.538, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.4115368058544986, |
| "grad_norm": 0.09735915809869766, |
| "learning_rate": 4.861793176444479e-05, |
| "loss": 0.1155, |
| "step": 820 |
| }, |
| { |
| "epoch": 1.428755919070168, |
| "grad_norm": 0.10614746063947678, |
| "learning_rate": 4.6062432678209986e-05, |
| "loss": 0.1126, |
| "step": 830 |
| }, |
| { |
| "epoch": 1.4459750322858373, |
| "grad_norm": 0.09488119930028915, |
| "learning_rate": 4.355567811332311e-05, |
| "loss": 0.1153, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.4459750322858373, |
| "eval_loss": 0.11169660836458206, |
| "eval_runtime": 54.1675, |
| "eval_samples_per_second": 4.523, |
| "eval_steps_per_second": 4.523, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.4631941455015067, |
| "grad_norm": 0.10649088025093079, |
| "learning_rate": 4.109993347694781e-05, |
| "loss": 0.1289, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.480413258717176, |
| "grad_norm": 0.08584726601839066, |
| "learning_rate": 3.8697418077495575e-05, |
| "loss": 0.1193, |
| "step": 860 |
| }, |
| { |
| "epoch": 1.4976323719328455, |
| "grad_norm": 0.08480769395828247, |
| "learning_rate": 3.635030311898975e-05, |
| "loss": 0.1167, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.4976323719328455, |
| "eval_loss": 0.1113625019788742, |
| "eval_runtime": 54.0863, |
| "eval_samples_per_second": 4.53, |
| "eval_steps_per_second": 4.53, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.5148514851485149, |
| "grad_norm": 0.09291431307792664, |
| "learning_rate": 3.4060709738902485e-05, |
| "loss": 0.1223, |
| "step": 880 |
| }, |
| { |
| "epoch": 1.5320705983641842, |
| "grad_norm": 0.06462642550468445, |
| "learning_rate": 3.183070709123781e-05, |
| "loss": 0.1113, |
| "step": 890 |
| }, |
| { |
| "epoch": 1.5492897115798536, |
| "grad_norm": 0.08776138722896576, |
| "learning_rate": 2.9662310476593492e-05, |
| "loss": 0.1159, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.5492897115798536, |
| "eval_loss": 0.11135545372962952, |
| "eval_runtime": 54.2115, |
| "eval_samples_per_second": 4.519, |
| "eval_steps_per_second": 4.519, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.566508824795523, |
| "grad_norm": 0.08839749544858932, |
| "learning_rate": 2.7557479520891104e-05, |
| "loss": 0.1226, |
| "step": 910 |
| }, |
| { |
| "epoch": 1.5837279380111924, |
| "grad_norm": 0.1001950353384018, |
| "learning_rate": 2.551811640442081e-05, |
| "loss": 0.1156, |
| "step": 920 |
| }, |
| { |
| "epoch": 1.6009470512268618, |
| "grad_norm": 0.08094879239797592, |
| "learning_rate": 2.354606414280045e-05, |
| "loss": 0.1178, |
| "step": 930 |
| }, |
| { |
| "epoch": 1.6009470512268618, |
| "eval_loss": 0.11072849482297897, |
| "eval_runtime": 54.2409, |
| "eval_samples_per_second": 4.517, |
| "eval_steps_per_second": 4.517, |
| "step": 930 |
| }, |
| { |
| "epoch": 1.6181661644425311, |
| "grad_norm": 0.0837637260556221, |
| "learning_rate": 2.1643104921403657e-05, |
| "loss": 0.1163, |
| "step": 940 |
| }, |
| { |
| "epoch": 1.6353852776582007, |
| "grad_norm": 0.08061401546001434, |
| "learning_rate": 1.98109584847609e-05, |
| "loss": 0.1215, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.65260439087387, |
| "grad_norm": 0.08909575641155243, |
| "learning_rate": 1.805128058239014e-05, |
| "loss": 0.1214, |
| "step": 960 |
| }, |
| { |
| "epoch": 1.65260439087387, |
| "eval_loss": 0.11049379408359528, |
| "eval_runtime": 54.0663, |
| "eval_samples_per_second": 4.531, |
| "eval_steps_per_second": 4.531, |
| "step": 960 |
| }, |
| { |
| "epoch": 1.6698235040895395, |
| "grad_norm": 0.0853874459862709, |
| "learning_rate": 1.6365661472460946e-05, |
| "loss": 0.1223, |
| "step": 970 |
| }, |
| { |
| "epoch": 1.6870426173052087, |
| "grad_norm": 0.07660456001758575, |
| "learning_rate": 1.475562448464437e-05, |
| "loss": 0.1249, |
| "step": 980 |
| }, |
| { |
| "epoch": 1.7042617305208783, |
| "grad_norm": 0.08277535438537598, |
| "learning_rate": 1.3222624643447879e-05, |
| "loss": 0.1139, |
| "step": 990 |
| }, |
| { |
| "epoch": 1.7042617305208783, |
| "eval_loss": 0.11061510443687439, |
| "eval_runtime": 54.1562, |
| "eval_samples_per_second": 4.524, |
| "eval_steps_per_second": 4.524, |
| "step": 990 |
| }, |
| { |
| "epoch": 1.7214808437365474, |
| "grad_norm": 0.08193802833557129, |
| "learning_rate": 1.1768047353278721e-05, |
| "loss": 0.1163, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.738699956952217, |
| "grad_norm": 0.09207924455404282, |
| "learning_rate": 1.0393207146424766e-05, |
| "loss": 0.1171, |
| "step": 1010 |
| }, |
| { |
| "epoch": 1.7559190701678864, |
| "grad_norm": 0.07924116402864456, |
| "learning_rate": 9.09934649508375e-06, |
| "loss": 0.1215, |
| "step": 1020 |
| }, |
| { |
| "epoch": 1.7559190701678864, |
| "eval_loss": 0.1104968935251236, |
| "eval_runtime": 54.2108, |
| "eval_samples_per_second": 4.519, |
| "eval_steps_per_second": 4.519, |
| "step": 1020 |
| }, |
| { |
| "epoch": 1.7731381833835558, |
| "grad_norm": 0.0777198001742363, |
| "learning_rate": 7.887634688515e-06, |
| "loss": 0.1204, |
| "step": 1030 |
| }, |
| { |
| "epoch": 1.7903572965992252, |
| "grad_norm": 0.09511927515268326, |
| "learning_rate": 6.759166776327786e-06, |
| "loss": 0.1125, |
| "step": 1040 |
| }, |
| { |
| "epoch": 1.8075764098148945, |
| "grad_norm": 0.08975937217473984, |
| "learning_rate": 5.71496257886196e-06, |
| "loss": 0.1143, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.8075764098148945, |
| "eval_loss": 0.11050143837928772, |
| "eval_runtime": 54.1535, |
| "eval_samples_per_second": 4.524, |
| "eval_steps_per_second": 4.524, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.824795523030564, |
| "grad_norm": 0.08812955766916275, |
| "learning_rate": 4.755965765554637e-06, |
| "loss": 0.112, |
| "step": 1060 |
| }, |
| { |
| "epoch": 1.8420146362462333, |
| "grad_norm": 0.08198709785938263, |
| "learning_rate": 3.883043002126219e-06, |
| "loss": 0.1149, |
| "step": 1070 |
| }, |
| { |
| "epoch": 1.8592337494619027, |
| "grad_norm": 0.0873785987496376, |
| "learning_rate": 3.0969831673562042e-06, |
| "loss": 0.1142, |
| "step": 1080 |
| }, |
| { |
| "epoch": 1.8592337494619027, |
| "eval_loss": 0.11041069775819778, |
| "eval_runtime": 54.1647, |
| "eval_samples_per_second": 4.523, |
| "eval_steps_per_second": 4.523, |
| "step": 1080 |
| }, |
| { |
| "epoch": 1.876452862677572, |
| "grad_norm": 0.08640486001968384, |
| "learning_rate": 2.3984966401567e-06, |
| "loss": 0.1154, |
| "step": 1090 |
| }, |
| { |
| "epoch": 1.8936719758932417, |
| "grad_norm": 0.09290562570095062, |
| "learning_rate": 1.7882146575880166e-06, |
| "loss": 0.1163, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.9108910891089108, |
| "grad_norm": 0.0945608988404274, |
| "learning_rate": 1.266688744396327e-06, |
| "loss": 0.1162, |
| "step": 1110 |
| }, |
| { |
| "epoch": 1.9108910891089108, |
| "eval_loss": 0.11023778468370438, |
| "eval_runtime": 54.2854, |
| "eval_samples_per_second": 4.513, |
| "eval_steps_per_second": 4.513, |
| "step": 1110 |
| }, |
| { |
| "epoch": 1.9281102023245804, |
| "grad_norm": 0.09848543256521225, |
| "learning_rate": 8.343902145891646e-07, |
| "loss": 0.1112, |
| "step": 1120 |
| }, |
| { |
| "epoch": 1.9453293155402496, |
| "grad_norm": 0.09019118547439575, |
| "learning_rate": 4.917097454988584e-07, |
| "loss": 0.1156, |
| "step": 1130 |
| }, |
| { |
| "epoch": 1.9625484287559192, |
| "grad_norm": 0.09469816088676453, |
| "learning_rate": 2.389570247192552e-07, |
| "loss": 0.1218, |
| "step": 1140 |
| }, |
| { |
| "epoch": 1.9625484287559192, |
| "eval_loss": 0.11023097485303879, |
| "eval_runtime": 54.1686, |
| "eval_samples_per_second": 4.523, |
| "eval_steps_per_second": 4.523, |
| "step": 1140 |
| }, |
| { |
| "epoch": 1.9797675419715883, |
| "grad_norm": 0.08748683333396912, |
| "learning_rate": 7.636047023441561e-08, |
| "loss": 0.1202, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.996986655187258, |
| "grad_norm": 0.09518461674451828, |
| "learning_rate": 4.0670239925155725e-09, |
| "loss": 0.1136, |
| "step": 1160 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1162, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 1.6568373351982694e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
