{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.9958002799813346, "global_step": 1605, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.02, "learning_rate": 4.081632653061225e-06, "loss": 3.83, "step": 10 }, { "epoch": 0.04, "learning_rate": 8.16326530612245e-06, "loss": 3.7366, "step": 20 }, { "epoch": 0.06, "learning_rate": 1.2244897959183674e-05, "loss": 3.6074, "step": 30 }, { "epoch": 0.07, "learning_rate": 1.63265306122449e-05, "loss": 3.1722, "step": 40 }, { "epoch": 0.09, "learning_rate": 1.9999979617830125e-05, "loss": 3.1476, "step": 50 }, { "epoch": 0.11, "learning_rate": 1.9997533857978314e-05, "loss": 3.0026, "step": 60 }, { "epoch": 0.13, "learning_rate": 1.999101280651531e-05, "loss": 2.9246, "step": 70 }, { "epoch": 0.15, "learning_rate": 1.99804191216153e-05, "loss": 2.9575, "step": 80 }, { "epoch": 0.17, "learning_rate": 1.996575712157875e-05, "loss": 2.8573, "step": 90 }, { "epoch": 0.19, "learning_rate": 1.9947032783072173e-05, "loss": 2.8785, "step": 100 }, { "epoch": 0.21, "learning_rate": 1.9924253738691836e-05, "loss": 2.551, "step": 110 }, { "epoch": 0.22, "learning_rate": 1.98974292738525e-05, "loss": 2.6737, "step": 120 }, { "epoch": 0.24, "learning_rate": 1.9866570323002413e-05, "loss": 2.7509, "step": 130 }, { "epoch": 0.26, "learning_rate": 1.983168946516609e-05, "loss": 2.5926, "step": 140 }, { "epoch": 0.28, "learning_rate": 1.9792800918816745e-05, "loss": 2.5292, "step": 150 }, { "epoch": 0.3, "learning_rate": 1.9749920536080403e-05, "loss": 2.6191, "step": 160 }, { "epoch": 0.32, "learning_rate": 1.9703065796274124e-05, "loss": 2.6252, "step": 170 }, { "epoch": 0.34, "learning_rate": 1.965225579878089e-05, "loss": 2.4386, "step": 180 }, { "epoch": 0.35, "learning_rate": 1.959751125526415e-05, "loss": 2.5224, "step": 190 }, { "epoch": 0.37, "learning_rate": 1.9538854481225114e-05, "loss": 2.4643, "step": 200 }, { "epoch": 0.39, "learning_rate": 1.9476309386906303e-05, "loss": 2.3863, "step": 210 }, { "epoch": 0.41, "learning_rate": 1.9409901467545038e-05, "loss": 2.331, "step": 220 }, { "epoch": 0.43, "learning_rate": 1.933965779298078e-05, "loss": 2.2992, "step": 230 }, { "epoch": 0.45, "learning_rate": 1.9265606996620708e-05, "loss": 2.4181, "step": 240 }, { "epoch": 0.47, "learning_rate": 1.9187779263767875e-05, "loss": 2.3913, "step": 250 }, { "epoch": 0.49, "learning_rate": 1.9106206319316757e-05, "loss": 2.3832, "step": 260 }, { "epoch": 0.5, "learning_rate": 1.9020921414821294e-05, "loss": 2.4269, "step": 270 }, { "epoch": 0.52, "learning_rate": 1.8931959314940523e-05, "loss": 2.2566, "step": 280 }, { "epoch": 0.54, "learning_rate": 1.88393562832675e-05, "loss": 2.316, "step": 290 }, { "epoch": 0.56, "learning_rate": 1.8743150067547168e-05, "loss": 2.2473, "step": 300 }, { "epoch": 0.58, "learning_rate": 1.8643379884289266e-05, "loss": 2.3063, "step": 310 }, { "epoch": 0.6, "learning_rate": 1.85400864027825e-05, "loss": 2.187, "step": 320 }, { "epoch": 0.62, "learning_rate": 1.8433311728516553e-05, "loss": 2.141, "step": 330 }, { "epoch": 0.63, "learning_rate": 1.832309938601862e-05, "loss": 2.2089, "step": 340 }, { "epoch": 0.65, "learning_rate": 1.8209494301111535e-05, "loss": 2.2493, "step": 350 }, { "epoch": 0.67, "learning_rate": 1.809254278260066e-05, "loss": 2.2365, "step": 360 }, { "epoch": 0.69, "learning_rate": 1.7972292503397036e-05, "loss": 2.2406, "step": 370 }, { "epoch": 0.71, "learning_rate": 1.7848792481084504e-05, "loss": 2.1423, "step": 380 }, { "epoch": 0.73, "learning_rate": 1.772209305793868e-05, "loss": 2.1684, "step": 390 }, { "epoch": 0.75, "learning_rate": 1.7592245880405934e-05, "loss": 2.1613, "step": 400 }, { "epoch": 0.77, "learning_rate": 1.7459303878050788e-05, "loss": 2.1061, "step": 410 }, { "epoch": 0.78, "learning_rate": 1.732332124198023e-05, "loss": 2.1551, "step": 420 }, { "epoch": 0.8, "learning_rate": 1.7184353402753832e-05, "loss": 2.1107, "step": 430 }, { "epoch": 0.82, "learning_rate": 1.7042457007788594e-05, "loss": 2.2264, "step": 440 }, { "epoch": 0.84, "learning_rate": 1.6897689898267774e-05, "loss": 2.0884, "step": 450 }, { "epoch": 0.86, "learning_rate": 1.6750111085563122e-05, "loss": 2.1016, "step": 460 }, { "epoch": 0.88, "learning_rate": 1.659978072718007e-05, "loss": 2.138, "step": 470 }, { "epoch": 0.9, "learning_rate": 1.644676010223576e-05, "loss": 2.0713, "step": 480 }, { "epoch": 0.91, "learning_rate": 1.6291111586479857e-05, "loss": 2.1247, "step": 490 }, { "epoch": 0.93, "learning_rate": 1.6132898626868336e-05, "loss": 2.0748, "step": 500 }, { "epoch": 0.95, "learning_rate": 1.5972185715700623e-05, "loss": 2.0356, "step": 510 }, { "epoch": 0.97, "learning_rate": 1.5809038364330617e-05, "loss": 2.1173, "step": 520 }, { "epoch": 0.99, "learning_rate": 1.5643523076462325e-05, "loss": 2.1065, "step": 530 }, { "epoch": 1.01, "learning_rate": 1.547570732104095e-05, "loss": 2.1073, "step": 540 }, { "epoch": 1.03, "learning_rate": 1.5305659504750595e-05, "loss": 1.9632, "step": 550 }, { "epoch": 1.05, "learning_rate": 1.5133448944129616e-05, "loss": 2.0967, "step": 560 }, { "epoch": 1.06, "learning_rate": 1.4959145837315182e-05, "loss": 1.9325, "step": 570 }, { "epoch": 1.08, "learning_rate": 1.4782821235428406e-05, "loss": 2.0018, "step": 580 }, { "epoch": 1.1, "learning_rate": 1.4604547013611813e-05, "loss": 1.9439, "step": 590 }, { "epoch": 1.12, "learning_rate": 1.4424395841730889e-05, "loss": 1.9066, "step": 600 }, { "epoch": 1.14, "learning_rate": 1.4242441154751691e-05, "loss": 1.8828, "step": 610 }, { "epoch": 1.16, "learning_rate": 1.4058757122806573e-05, "loss": 1.9665, "step": 620 }, { "epoch": 1.18, "learning_rate": 1.3873418620960237e-05, "loss": 1.9528, "step": 630 }, { "epoch": 1.19, "learning_rate": 1.3686501198688435e-05, "loss": 1.9044, "step": 640 }, { "epoch": 1.21, "learning_rate": 1.3498081049081773e-05, "loss": 1.8582, "step": 650 }, { "epoch": 1.23, "learning_rate": 1.330823497778711e-05, "loss": 2.0053, "step": 660 }, { "epoch": 1.25, "learning_rate": 1.3117040371699334e-05, "loss": 1.9191, "step": 670 }, { "epoch": 1.27, "learning_rate": 1.2924575167416147e-05, "loss": 1.9297, "step": 680 }, { "epoch": 1.29, "learning_rate": 1.2730917819468796e-05, "loss": 1.8852, "step": 690 }, { "epoch": 1.31, "learning_rate": 1.2536147268341676e-05, "loss": 1.9083, "step": 700 }, { "epoch": 1.33, "learning_rate": 1.2340342908293856e-05, "loss": 1.8909, "step": 710 }, { "epoch": 1.34, "learning_rate": 1.2143584554995604e-05, "loss": 1.8984, "step": 720 }, { "epoch": 1.36, "learning_rate": 1.1945952412993162e-05, "loss": 1.9207, "step": 730 }, { "epoch": 1.38, "learning_rate": 1.1747527043014997e-05, "loss": 1.8663, "step": 740 }, { "epoch": 1.4, "learning_rate": 1.1548389329132832e-05, "loss": 1.9107, "step": 750 }, { "epoch": 1.42, "learning_rate": 1.1348620445790926e-05, "loss": 1.9066, "step": 760 }, { "epoch": 1.44, "learning_rate": 1.114830182471695e-05, "loss": 1.8737, "step": 770 }, { "epoch": 1.46, "learning_rate": 1.0947515121727987e-05, "loss": 1.935, "step": 780 }, { "epoch": 1.47, "learning_rate": 1.0746342183445209e-05, "loss": 1.8357, "step": 790 }, { "epoch": 1.49, "learning_rate": 1.0544865013930763e-05, "loss": 1.8526, "step": 800 }, { "epoch": 1.51, "learning_rate": 1.0343165741260474e-05, "loss": 1.9319, "step": 810 }, { "epoch": 1.53, "learning_rate": 1.0141326584046012e-05, "loss": 1.9127, "step": 820 }, { "epoch": 1.55, "learning_rate": 9.93942981792013e-06, "loss": 1.906, "step": 830 }, { "epoch": 1.57, "learning_rate": 9.737557741998696e-06, "loss": 1.7907, "step": 840 }, { "epoch": 1.59, "learning_rate": 9.535792645333114e-06, "loss": 1.8328, "step": 850 }, { "epoch": 1.61, "learning_rate": 9.334216773366863e-06, "loss": 1.8959, "step": 860 }, { "epoch": 1.62, "learning_rate": 9.132912294409814e-06, "loss": 1.8743, "step": 870 }, { "epoch": 1.64, "learning_rate": 8.931961266144003e-06, "loss": 1.7924, "step": 880 }, { "epoch": 1.66, "learning_rate": 8.731445602174463e-06, "loss": 1.8917, "step": 890 }, { "epoch": 1.68, "learning_rate": 8.531447038638812e-06, "loss": 1.8711, "step": 900 }, { "epoch": 1.7, "learning_rate": 8.33204710088918e-06, "loss": 1.8876, "step": 910 }, { "epoch": 1.72, "learning_rate": 8.133327070260064e-06, "loss": 1.8171, "step": 920 }, { "epoch": 1.74, "learning_rate": 7.935367950935623e-06, "loss": 1.84, "step": 930 }, { "epoch": 1.75, "learning_rate": 7.738250436929977e-06, "loss": 1.9742, "step": 940 }, { "epoch": 1.77, "learning_rate": 7.5420548791939406e-06, "loss": 1.8994, "step": 950 }, { "epoch": 1.79, "learning_rate": 7.346861252861577e-06, "loss": 1.886, "step": 960 }, { "epoch": 1.81, "learning_rate": 7.152749124649961e-06, "loss": 1.8094, "step": 970 }, { "epoch": 1.83, "learning_rate": 6.959797620425435e-06, "loss": 1.8344, "step": 980 }, { "epoch": 1.85, "learning_rate": 6.768085392949527e-06, "loss": 1.8566, "step": 990 }, { "epoch": 1.87, "learning_rate": 6.5776905898177936e-06, "loss": 1.7879, "step": 1000 }, { "epoch": 1.89, "learning_rate": 6.388690821604505e-06, "loss": 1.8543, "step": 1010 }, { "epoch": 1.9, "learning_rate": 6.20116313022628e-06, "loss": 1.8772, "step": 1020 }, { "epoch": 1.92, "learning_rate": 6.015183957537523e-06, "loss": 1.8362, "step": 1030 }, { "epoch": 1.94, "learning_rate": 5.830829114170442e-06, "loss": 1.8778, "step": 1040 }, { "epoch": 1.96, "learning_rate": 5.6481737486323936e-06, "loss": 1.8676, "step": 1050 }, { "epoch": 1.98, "learning_rate": 5.467292316673114e-06, "loss": 1.8362, "step": 1060 }, { "epoch": 2.0, "learning_rate": 5.288258550934343e-06, "loss": 1.8752, "step": 1070 }, { "epoch": 2.02, "learning_rate": 5.111145430894229e-06, "loss": 1.9466, "step": 1080 }, { "epoch": 2.03, "learning_rate": 4.936025153118697e-06, "loss": 1.7668, "step": 1090 }, { "epoch": 2.05, "learning_rate": 4.762969101832011e-06, "loss": 1.7815, "step": 1100 }, { "epoch": 2.07, "learning_rate": 4.59204781981843e-06, "loss": 1.72, "step": 1110 }, { "epoch": 2.09, "learning_rate": 4.423330979666878e-06, "loss": 1.7548, "step": 1120 }, { "epoch": 2.11, "learning_rate": 4.256887355370333e-06, "loss": 1.6771, "step": 1130 }, { "epoch": 2.13, "learning_rate": 4.092784794291502e-06, "loss": 1.8401, "step": 1140 }, { "epoch": 2.15, "learning_rate": 3.931090189506222e-06, "loss": 1.7071, "step": 1150 }, { "epoch": 2.17, "learning_rate": 3.7718694525358534e-06, "loss": 1.8095, "step": 1160 }, { "epoch": 2.18, "learning_rate": 3.615187486479794e-06, "loss": 1.7441, "step": 1170 }, { "epoch": 2.2, "learning_rate": 3.4611081595590445e-06, "loss": 1.7304, "step": 1180 }, { "epoch": 2.22, "learning_rate": 3.30969427908162e-06, "loss": 1.7527, "step": 1190 }, { "epoch": 2.24, "learning_rate": 3.1610075658404436e-06, "loss": 1.8059, "step": 1200 }, { "epoch": 2.26, "learning_rate": 3.0151086289540997e-06, "loss": 1.6814, "step": 1210 }, { "epoch": 2.28, "learning_rate": 2.872056941160767e-06, "loss": 1.7992, "step": 1220 }, { "epoch": 2.3, "learning_rate": 2.7319108145753625e-06, "loss": 1.6453, "step": 1230 }, { "epoch": 2.31, "learning_rate": 2.594727376919798e-06, "loss": 1.6889, "step": 1240 }, { "epoch": 2.33, "learning_rate": 2.460562548236015e-06, "loss": 1.7476, "step": 1250 }, { "epoch": 2.35, "learning_rate": 2.329471018091323e-06, "loss": 1.7296, "step": 1260 }, { "epoch": 2.37, "learning_rate": 2.201506223285306e-06, "loss": 1.8352, "step": 1270 }, { "epoch": 2.39, "learning_rate": 2.0767203260673952e-06, "loss": 1.718, "step": 1280 }, { "epoch": 2.41, "learning_rate": 1.9551641928739886e-06, "loss": 1.7623, "step": 1290 }, { "epoch": 2.43, "learning_rate": 1.836887373593782e-06, "loss": 1.7442, "step": 1300 }, { "epoch": 2.45, "learning_rate": 1.7219380813697605e-06, "loss": 1.7989, "step": 1310 }, { "epoch": 2.46, "learning_rate": 1.6103631729460978e-06, "loss": 1.7406, "step": 1320 }, { "epoch": 2.48, "learning_rate": 1.5022081295679436e-06, "loss": 1.7743, "step": 1330 }, { "epoch": 2.5, "learning_rate": 1.397517038441929e-06, "loss": 1.7766, "step": 1340 }, { "epoch": 2.52, "learning_rate": 1.296332574764907e-06, "loss": 1.7424, "step": 1350 }, { "epoch": 2.54, "learning_rate": 1.1986959843282753e-06, "loss": 1.7627, "step": 1360 }, { "epoch": 2.56, "learning_rate": 1.104647066704967e-06, "loss": 1.7274, "step": 1370 }, { "epoch": 2.58, "learning_rate": 1.0142241590259715e-06, "loss": 1.713, "step": 1380 }, { "epoch": 2.59, "learning_rate": 9.274641203529655e-07, "loss": 1.8669, "step": 1390 }, { "epoch": 2.61, "learning_rate": 8.444023166534798e-07, "loss": 1.7232, "step": 1400 }, { "epoch": 2.63, "learning_rate": 7.650726063846703e-07, "loss": 1.7222, "step": 1410 }, { "epoch": 2.65, "learning_rate": 6.895073266916164e-07, "loss": 1.7192, "step": 1420 }, { "epoch": 2.67, "learning_rate": 6.177372802257308e-07, "loss": 1.7451, "step": 1430 }, { "epoch": 2.69, "learning_rate": 5.497917225886918e-07, "loss": 1.7798, "step": 1440 }, { "epoch": 2.71, "learning_rate": 4.856983504069857e-07, "loss": 1.7966, "step": 1450 }, { "epoch": 2.73, "learning_rate": 4.254832900419437e-07, "loss": 1.7129, "step": 1460 }, { "epoch": 2.74, "learning_rate": 3.6917108693985684e-07, "loss": 1.6862, "step": 1470 }, { "epoch": 2.76, "learning_rate": 3.1678469562652856e-07, "loss": 1.7033, "step": 1480 }, { "epoch": 2.78, "learning_rate": 2.6834547035032634e-07, "loss": 1.7667, "step": 1490 }, { "epoch": 2.8, "learning_rate": 2.2387315637755535e-07, "loss": 1.7763, "step": 1500 }, { "epoch": 2.82, "learning_rate": 1.8338588194370176e-07, "loss": 1.7684, "step": 1510 }, { "epoch": 2.84, "learning_rate": 1.4690015086382793e-07, "loss": 1.7335, "step": 1520 }, { "epoch": 2.86, "learning_rate": 1.1443083580512382e-07, "loss": 1.7949, "step": 1530 }, { "epoch": 2.87, "learning_rate": 8.599117222436892e-08, "loss": 1.7364, "step": 1540 }, { "epoch": 2.89, "learning_rate": 6.159275297276557e-08, "loss": 1.8143, "step": 1550 }, { "epoch": 2.91, "learning_rate": 4.124552357035239e-08, "loss": 1.68, "step": 1560 }, { "epoch": 2.93, "learning_rate": 2.4957778151909472e-08, "loss": 1.7381, "step": 1570 }, { "epoch": 2.95, "learning_rate": 1.2736156086026186e-08, "loss": 1.7679, "step": 1580 }, { "epoch": 2.97, "learning_rate": 4.58563926869604e-09, "loss": 1.7197, "step": 1590 }, { "epoch": 2.99, "learning_rate": 5.095500925511588e-10, "loss": 1.7629, "step": 1600 }, { "epoch": 3.0, "step": 1605, "total_flos": 1.1751074904303206e+17, "train_loss": 2.0375683680501684, "train_runtime": 2895.4272, "train_samples_per_second": 62.165, "train_steps_per_second": 0.554 } ], "max_steps": 1605, "num_train_epochs": 3, "total_flos": 1.1751074904303206e+17, "trial_name": null, "trial_params": null }