| {"current_steps": 32, "total_steps": 5000, "loss": 10.1393, "eval_loss": null, "predict_loss": null, "learning_rate": 4.7999999999999994e-05, "epoch": 0.0018213899482042233, "percentage": 0.64} | |
| {"current_steps": 64, "total_steps": 5000, "loss": 9.5073, "eval_loss": null, "predict_loss": null, "learning_rate": 9.599999999999999e-05, "epoch": 0.0036427798964084467, "percentage": 1.28} | |
| {"current_steps": 96, "total_steps": 5000, "loss": 8.6838, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014399999999999998, "epoch": 0.00546416984461267, "percentage": 1.92} | |
| {"current_steps": 128, "total_steps": 5000, "loss": 7.7214, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00019199999999999998, "epoch": 0.007285559792816893, "percentage": 2.56} | |
| {"current_steps": 160, "total_steps": 5000, "loss": 6.9903, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00023999999999999998, "epoch": 0.009106949741021117, "percentage": 3.2} | |
| {"current_steps": 192, "total_steps": 5000, "loss": 6.6401, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00028799999999999995, "epoch": 0.01092833968922534, "percentage": 3.84} | |
| {"current_steps": 224, "total_steps": 5000, "loss": 6.3909, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029998334538502416, "epoch": 0.012749729637429564, "percentage": 4.48} | |
| {"current_steps": 256, "total_steps": 5000, "loss": 6.2519, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029990933316011853, "epoch": 0.014571119585633787, "percentage": 5.12} | |
| {"current_steps": 288, "total_steps": 5000, "loss": 6.0075, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002997761452428938, "epoch": 0.01639250953383801, "percentage": 5.76} | |
| {"current_steps": 320, "total_steps": 5000, "loss": 5.7978, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029958384005397226, "epoch": 0.018213899482042235, "percentage": 6.4} | |
| {"current_steps": 352, "total_steps": 5000, "loss": 5.7382, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029933250194476556, "epoch": 0.020035289430246458, "percentage": 7.04} | |
| {"current_steps": 384, "total_steps": 5000, "loss": 5.5462, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029902224116047513, "epoch": 0.02185667937845068, "percentage": 7.68} | |
| {"current_steps": 416, "total_steps": 5000, "loss": 5.5531, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002986531937917352, "epoch": 0.023678069326654904, "percentage": 8.32} | |
| {"current_steps": 448, "total_steps": 5000, "loss": 5.3855, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029822552171491893, "epoch": 0.025499459274859127, "percentage": 8.96} | |
| {"current_steps": 480, "total_steps": 5000, "loss": 5.2726, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002977394125211339, "epoch": 0.02732084922306335, "percentage": 9.6} | |
| {"current_steps": 512, "total_steps": 5000, "loss": 5.2783, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029719507943393837, "epoch": 0.029142239171267573, "percentage": 10.24} | |
| {"current_steps": 544, "total_steps": 5000, "loss": 5.2148, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002965927612158149, "epoch": 0.030963629119471796, "percentage": 10.88} | |
| {"current_steps": 576, "total_steps": 5000, "loss": 5.1568, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029593272206344083, "epoch": 0.03278501906767602, "percentage": 11.52} | |
| {"current_steps": 608, "total_steps": 5000, "loss": 5.1074, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029521525149180274, "epoch": 0.034606409015880246, "percentage": 12.16} | |
| {"current_steps": 640, "total_steps": 5000, "loss": 5.0522, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029444066420720603, "epoch": 0.03642779896408447, "percentage": 12.8} | |
| {"current_steps": 672, "total_steps": 5000, "loss": 5.0094, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029360929996923415, "epoch": 0.03824918891228869, "percentage": 13.44} | |
| {"current_steps": 704, "total_steps": 5000, "loss": 5.015, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002927215234417186, "epoch": 0.040070578860492916, "percentage": 14.08} | |
| {"current_steps": 736, "total_steps": 5000, "loss": 4.998, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029177772403278567, "epoch": 0.04189196880869714, "percentage": 14.72} | |
| {"current_steps": 768, "total_steps": 5000, "loss": 4.8852, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00029077831572404906, "epoch": 0.04371335875690136, "percentage": 15.36} | |
| {"current_steps": 800, "total_steps": 5000, "loss": 4.9104, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002897237368890237, "epoch": 0.045534748705105585, "percentage": 16.0} | |
| {"current_steps": 832, "total_steps": 5000, "loss": 4.8376, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00028861445010084074, "epoch": 0.04735613865330981, "percentage": 16.64} | |
| {"current_steps": 864, "total_steps": 5000, "loss": 4.8827, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00028745094192934775, "epoch": 0.04917752860151403, "percentage": 17.28} | |
| {"current_steps": 896, "total_steps": 5000, "loss": 4.8356, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002862337227276831, "epoch": 0.050998918549718254, "percentage": 17.92} | |
| {"current_steps": 928, "total_steps": 5000, "loss": 4.7351, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002849633264084181, "epoch": 0.05282030849792248, "percentage": 18.56} | |
| {"current_steps": 960, "total_steps": 5000, "loss": 4.7177, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002836403102093653, "epoch": 0.0546416984461267, "percentage": 19.2} | |
| {"current_steps": 992, "total_steps": 5000, "loss": 4.7996, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00028226525444915583, "epoch": 0.056463088394330924, "percentage": 19.84} | |
| {"current_steps": 1024, "total_steps": 5000, "loss": 4.6191, "eval_loss": null, "predict_loss": null, "learning_rate": 0.000280838762272692, "epoch": 0.05828447834253515, "percentage": 20.48} | |
| {"current_steps": 1056, "total_steps": 5000, "loss": 4.597, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002793614593865885, "epoch": 0.06010586829073937, "percentage": 21.12} | |
| {"current_steps": 1088, "total_steps": 5000, "loss": 4.6013, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002778339937847165, "epoch": 0.06192725823894359, "percentage": 21.76} | |
| {"current_steps": 1120, "total_steps": 5000, "loss": 4.7089, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00027625703546397206, "epoch": 0.06374864818714782, "percentage": 22.4} | |
| {"current_steps": 1152, "total_steps": 5000, "loss": 4.5636, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00027463127613039384, "epoch": 0.06557003813535205, "percentage": 23.04} | |
| {"current_steps": 1184, "total_steps": 5000, "loss": 4.4686, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00027295742889575723, "epoch": 0.06739142808355626, "percentage": 23.68} | |
| {"current_steps": 1216, "total_steps": 5000, "loss": 4.5344, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002712362279647805, "epoch": 0.06921281803176049, "percentage": 24.32} | |
| {"current_steps": 1248, "total_steps": 5000, "loss": 4.5155, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00026946842831307834, "epoch": 0.07103420797996471, "percentage": 24.96} | |
| {"current_steps": 1280, "total_steps": 5000, "loss": 4.4555, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00026765480535600414, "epoch": 0.07285559792816894, "percentage": 25.6} | |
| {"current_steps": 1312, "total_steps": 5000, "loss": 4.531, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002657961546085278, "epoch": 0.07467698787637315, "percentage": 26.24} | |
| {"current_steps": 1344, "total_steps": 5000, "loss": 4.4471, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002638932913362961, "epoch": 0.07649837782457738, "percentage": 26.88} | |
| {"current_steps": 1376, "total_steps": 5000, "loss": 4.4205, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00026194705019803047, "epoch": 0.0783197677727816, "percentage": 27.52} | |
| {"current_steps": 1408, "total_steps": 5000, "loss": 4.4162, "eval_loss": null, "predict_loss": null, "learning_rate": 0.000259958284879418, "epoch": 0.08014115772098583, "percentage": 28.16} | |
| {"current_steps": 1440, "total_steps": 5000, "loss": 4.4846, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002579278677186568, "epoch": 0.08196254766919005, "percentage": 28.8} | |
| {"current_steps": 1472, "total_steps": 5000, "loss": 4.3474, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002558566893238194, "epoch": 0.08378393761739428, "percentage": 29.44} | |
| {"current_steps": 1504, "total_steps": 5000, "loss": 4.2632, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002537456581822029, "epoch": 0.0856053275655985, "percentage": 30.08} | |
| {"current_steps": 1536, "total_steps": 5000, "loss": 4.2303, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002515957002618363, "epoch": 0.08742671751380272, "percentage": 30.72} | |
| {"current_steps": 1568, "total_steps": 5000, "loss": 4.3677, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002494077586053202, "epoch": 0.08924810746200694, "percentage": 31.36} | |
| {"current_steps": 1600, "total_steps": 5000, "loss": 4.166, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00024718279291617725, "epoch": 0.09106949741021117, "percentage": 32.0} | |
| {"current_steps": 1632, "total_steps": 5000, "loss": 4.2925, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002449217791378946, "epoch": 0.09289088735841539, "percentage": 32.64} | |
| {"current_steps": 1664, "total_steps": 5000, "loss": 4.3175, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002426257090258426, "epoch": 0.09471227730661962, "percentage": 33.28} | |
| {"current_steps": 1696, "total_steps": 5000, "loss": 4.2804, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00024029558971225818, "epoch": 0.09653366725482383, "percentage": 33.92} | |
| {"current_steps": 1728, "total_steps": 5000, "loss": 4.278, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002379324432644834, "epoch": 0.09835505720302806, "percentage": 34.56} | |
| {"current_steps": 1760, "total_steps": 5000, "loss": 4.2631, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00023553730623665308, "epoch": 0.10017644715123228, "percentage": 35.2} | |
| {"current_steps": 1792, "total_steps": 5000, "loss": 4.2717, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00023311122921502756, "epoch": 0.10199783709943651, "percentage": 35.84} | |
| {"current_steps": 1824, "total_steps": 5000, "loss": 4.2946, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00023065527635717122, "epoch": 0.10381922704764072, "percentage": 36.48} | |
| {"current_steps": 1856, "total_steps": 5000, "loss": 4.1761, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002281705249251774, "epoch": 0.10564061699584495, "percentage": 37.12} | |
| {"current_steps": 1888, "total_steps": 5000, "loss": 4.125, "eval_loss": null, "predict_loss": null, "learning_rate": 0.000225658064813146, "epoch": 0.10746200694404917, "percentage": 37.76} | |
| {"current_steps": 1920, "total_steps": 5000, "loss": 4.2356, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00022311899806911982, "epoch": 0.1092833968922534, "percentage": 38.4} | |
| {"current_steps": 1952, "total_steps": 5000, "loss": 4.1268, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00022055443841168969, "epoch": 0.11110478684045763, "percentage": 39.04} | |
| {"current_steps": 1984, "total_steps": 5000, "loss": 4.1658, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00021796551074148077, "epoch": 0.11292617678866185, "percentage": 39.68} | |
| {"current_steps": 2016, "total_steps": 5000, "loss": 4.1877, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00021535335064773418, "epoch": 0.11474756673686608, "percentage": 40.32} | |
| {"current_steps": 2048, "total_steps": 5000, "loss": 4.1135, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0002127191039101997, "epoch": 0.1165689566850703, "percentage": 40.96} | |
| {"current_steps": 2080, "total_steps": 5000, "loss": 4.2758, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00021006392599655905, "epoch": 0.11839034663327452, "percentage": 41.6} | |
| {"current_steps": 2112, "total_steps": 5000, "loss": 4.1658, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00020738898155559963, "epoch": 0.12021173658147874, "percentage": 42.24} | |
| {"current_steps": 2144, "total_steps": 5000, "loss": 4.1002, "eval_loss": null, "predict_loss": null, "learning_rate": 0.000204695443906361, "epoch": 0.12203312652968297, "percentage": 42.88} | |
| {"current_steps": 2176, "total_steps": 5000, "loss": 4.1133, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00020198449452347837, "epoch": 0.12385451647788719, "percentage": 43.52} | |
| {"current_steps": 2208, "total_steps": 5000, "loss": 4.18, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00019925732251894874, "epoch": 0.12567590642609142, "percentage": 44.16} | |
| {"current_steps": 2240, "total_steps": 5000, "loss": 4.1474, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00019651512412054723, "epoch": 0.12749729637429563, "percentage": 44.8} | |
| {"current_steps": 2272, "total_steps": 5000, "loss": 4.0877, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00019375910214712184, "epoch": 0.12931868632249985, "percentage": 45.44} | |
| {"current_steps": 2304, "total_steps": 5000, "loss": 4.0205, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00019099046548099748, "epoch": 0.1311400762707041, "percentage": 46.08} | |
| {"current_steps": 2336, "total_steps": 5000, "loss": 4.1051, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00018821042853772024, "epoch": 0.1329614662189083, "percentage": 46.72} | |
| {"current_steps": 2368, "total_steps": 5000, "loss": 4.098, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001854202107333746, "epoch": 0.13478285616711252, "percentage": 47.36} | |
| {"current_steps": 2400, "total_steps": 5000, "loss": 3.901, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00018262103594970697, "epoch": 0.13660424611531674, "percentage": 48.0} | |
| {"current_steps": 2432, "total_steps": 5000, "loss": 4.0379, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001798141319972911, "epoch": 0.13842563606352098, "percentage": 48.64} | |
| {"current_steps": 2464, "total_steps": 5000, "loss": 4.0482, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00017700073007696963, "epoch": 0.1402470260117252, "percentage": 49.28} | |
| {"current_steps": 2496, "total_steps": 5000, "loss": 4.0919, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001741820642398085, "epoch": 0.14206841595992942, "percentage": 49.92} | |
| {"current_steps": 2528, "total_steps": 5000, "loss": 4.0893, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00017135937084580174, "epoch": 0.14388980590813363, "percentage": 50.56} | |
| {"current_steps": 2560, "total_steps": 5000, "loss": 3.9577, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00016853388802156287, "epoch": 0.14571119585633788, "percentage": 51.2} | |
| {"current_steps": 2592, "total_steps": 5000, "loss": 3.943, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001657068551172416, "epoch": 0.1475325858045421, "percentage": 51.84} | |
| {"current_steps": 2624, "total_steps": 5000, "loss": 4.0669, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001628795121629042, "epoch": 0.1493539757527463, "percentage": 52.48} | |
| {"current_steps": 2656, "total_steps": 5000, "loss": 4.0342, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00016005309932461487, "epoch": 0.15117536570095053, "percentage": 53.12} | |
| {"current_steps": 2688, "total_steps": 5000, "loss": 3.9895, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001572288563604584, "epoch": 0.15299675564915477, "percentage": 53.76} | |
| {"current_steps": 2720, "total_steps": 5000, "loss": 3.9198, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015440802207674096, "epoch": 0.15481814559735899, "percentage": 54.4} | |
| {"current_steps": 2752, "total_steps": 5000, "loss": 3.896, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015159183378460873, "epoch": 0.1566395355455632, "percentage": 55.04} | |
| {"current_steps": 2784, "total_steps": 5000, "loss": 3.9168, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001487815267573226, "epoch": 0.15846092549376742, "percentage": 55.68} | |
| {"current_steps": 2816, "total_steps": 5000, "loss": 3.959, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014597833368842634, "epoch": 0.16028231544197166, "percentage": 56.32} | |
| {"current_steps": 2848, "total_steps": 5000, "loss": 3.857, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014318348415104625, "epoch": 0.16210370539017588, "percentage": 56.96} | |
| {"current_steps": 2880, "total_steps": 5000, "loss": 4.0205, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014039820405856008, "epoch": 0.1639250953383801, "percentage": 57.6} | |
| {"current_steps": 2912, "total_steps": 5000, "loss": 4.0671, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013762371512687085, "epoch": 0.1657464852865843, "percentage": 58.24} | |
| {"current_steps": 2944, "total_steps": 5000, "loss": 3.8878, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013486123433852158, "epoch": 0.16756787523478855, "percentage": 58.88} | |
| {"current_steps": 2976, "total_steps": 5000, "loss": 3.9037, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013211197340888697, "epoch": 0.16938926518299277, "percentage": 59.52} | |
| {"current_steps": 3008, "total_steps": 5000, "loss": 3.9373, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012937713825467468, "epoch": 0.171210655131197, "percentage": 60.16} | |
| {"current_steps": 3040, "total_steps": 5000, "loss": 3.9889, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012665792846497045, "epoch": 0.17303204507940123, "percentage": 60.8} | |
| {"current_steps": 3072, "total_steps": 5000, "loss": 3.9549, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012395553677505878, "epoch": 0.17485343502760545, "percentage": 61.44} | |
| {"current_steps": 3104, "total_steps": 5000, "loss": 3.7918, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012127114854324987, "epoch": 0.17667482497580966, "percentage": 62.08} | |
| {"current_steps": 3136, "total_steps": 5000, "loss": 3.9069, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011860594123094184, "epoch": 0.17849621492401388, "percentage": 62.72} | |
| {"current_steps": 3168, "total_steps": 5000, "loss": 4.0053, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011596108388614794, "epoch": 0.18031760487221812, "percentage": 63.36} | |
| {"current_steps": 3200, "total_steps": 5000, "loss": 3.8754, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011333773663071288, "epoch": 0.18213899482042234, "percentage": 64.0} | |
| {"current_steps": 3232, "total_steps": 5000, "loss": 3.9701, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001107370501514454, "epoch": 0.18396038476862656, "percentage": 64.64} | |
| {"current_steps": 3264, "total_steps": 5000, "loss": 3.9604, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010816016519538871, "epoch": 0.18578177471683077, "percentage": 65.28} | |
| {"current_steps": 3296, "total_steps": 5000, "loss": 3.8252, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010560821206945143, "epoch": 0.18760316466503502, "percentage": 65.92} | |
| {"current_steps": 3328, "total_steps": 5000, "loss": 3.8151, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010308231014461753, "epoch": 0.18942455461323923, "percentage": 66.56} | |
| {"current_steps": 3360, "total_steps": 5000, "loss": 3.819, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010058356736495284, "epoch": 0.19124594456144345, "percentage": 67.2} | |
| {"current_steps": 3392, "total_steps": 5000, "loss": 3.8178, "eval_loss": null, "predict_loss": null, "learning_rate": 9.811307976162497e-05, "epoch": 0.19306733450964766, "percentage": 67.84} | |
| {"current_steps": 3424, "total_steps": 5000, "loss": 3.8663, "eval_loss": null, "predict_loss": null, "learning_rate": 9.567193097214706e-05, "epoch": 0.1948887244578519, "percentage": 68.48} | |
| {"current_steps": 3456, "total_steps": 5000, "loss": 3.9651, "eval_loss": null, "predict_loss": null, "learning_rate": 9.326119176505879e-05, "epoch": 0.19671011440605612, "percentage": 69.12} | |
| {"current_steps": 3488, "total_steps": 5000, "loss": 3.8245, "eval_loss": null, "predict_loss": null, "learning_rate": 9.088191957025219e-05, "epoch": 0.19853150435426034, "percentage": 69.76} | |
| {"current_steps": 3520, "total_steps": 5000, "loss": 3.8818, "eval_loss": null, "predict_loss": null, "learning_rate": 8.85351580151476e-05, "epoch": 0.20035289430246456, "percentage": 70.4} | |
| {"current_steps": 3552, "total_steps": 5000, "loss": 3.8965, "eval_loss": null, "predict_loss": null, "learning_rate": 8.622193646692415e-05, "epoch": 0.2021742842506688, "percentage": 71.04} | |
| {"current_steps": 3584, "total_steps": 5000, "loss": 3.8703, "eval_loss": null, "predict_loss": null, "learning_rate": 8.394326958100568e-05, "epoch": 0.20399567419887302, "percentage": 71.68} | |
| {"current_steps": 3616, "total_steps": 5000, "loss": 3.7913, "eval_loss": null, "predict_loss": null, "learning_rate": 8.170015685599894e-05, "epoch": 0.20581706414707723, "percentage": 72.32} | |
| {"current_steps": 3648, "total_steps": 5000, "loss": 3.8577, "eval_loss": null, "predict_loss": null, "learning_rate": 7.949358219528073e-05, "epoch": 0.20763845409528145, "percentage": 72.96} | |
| {"current_steps": 3680, "total_steps": 5000, "loss": 3.8242, "eval_loss": null, "predict_loss": null, "learning_rate": 7.73245134754252e-05, "epoch": 0.2094598440434857, "percentage": 73.6} | |
| {"current_steps": 3712, "total_steps": 5000, "loss": 3.8459, "eval_loss": null, "predict_loss": null, "learning_rate": 7.51939021216613e-05, "epoch": 0.2112812339916899, "percentage": 74.24} | |
| {"current_steps": 3744, "total_steps": 5000, "loss": 3.9595, "eval_loss": null, "predict_loss": null, "learning_rate": 7.31026826905461e-05, "epoch": 0.21310262393989413, "percentage": 74.88} | |
| {"current_steps": 3776, "total_steps": 5000, "loss": 3.7997, "eval_loss": null, "predict_loss": null, "learning_rate": 7.105177246003757e-05, "epoch": 0.21492401388809834, "percentage": 75.52} | |
| {"current_steps": 3808, "total_steps": 5000, "loss": 3.8206, "eval_loss": null, "predict_loss": null, "learning_rate": 6.904207102714602e-05, "epoch": 0.21674540383630259, "percentage": 76.16} | |
| {"current_steps": 3840, "total_steps": 5000, "loss": 3.9024, "eval_loss": null, "predict_loss": null, "learning_rate": 6.707445991334119e-05, "epoch": 0.2185667937845068, "percentage": 76.8} | |
| {"current_steps": 3872, "total_steps": 5000, "loss": 3.8829, "eval_loss": null, "predict_loss": null, "learning_rate": 6.514980217788767e-05, "epoch": 0.22038818373271102, "percentage": 77.44} | |
| {"current_steps": 3904, "total_steps": 5000, "loss": 3.8427, "eval_loss": null, "predict_loss": null, "learning_rate": 6.32689420392789e-05, "epoch": 0.22220957368091526, "percentage": 78.08} | |
| {"current_steps": 3936, "total_steps": 5000, "loss": 3.8553, "eval_loss": null, "predict_loss": null, "learning_rate": 6.143270450493458e-05, "epoch": 0.22403096362911948, "percentage": 78.72} | |
| {"current_steps": 3968, "total_steps": 5000, "loss": 3.7891, "eval_loss": null, "predict_loss": null, "learning_rate": 5.964189500932548e-05, "epoch": 0.2258523535773237, "percentage": 79.36} | |
| {"current_steps": 4000, "total_steps": 5000, "loss": 3.7086, "eval_loss": null, "predict_loss": null, "learning_rate": 5.789729906068326e-05, "epoch": 0.2276737435255279, "percentage": 80.0} | |
| {"current_steps": 4032, "total_steps": 5000, "loss": 3.8187, "eval_loss": null, "predict_loss": null, "learning_rate": 5.6199681896450386e-05, "epoch": 0.22949513347373215, "percentage": 80.64} | |
| {"current_steps": 4064, "total_steps": 5000, "loss": 3.7619, "eval_loss": null, "predict_loss": null, "learning_rate": 5.454978814762181e-05, "epoch": 0.23131652342193637, "percentage": 81.28} | |
| {"current_steps": 4096, "total_steps": 5000, "loss": 3.8338, "eval_loss": null, "predict_loss": null, "learning_rate": 5.29483415121254e-05, "epoch": 0.2331379133701406, "percentage": 81.92} | |
| {"current_steps": 4128, "total_steps": 5000, "loss": 3.7375, "eval_loss": null, "predict_loss": null, "learning_rate": 5.139604443738368e-05, "epoch": 0.2349593033183448, "percentage": 82.56} | |
| {"current_steps": 4160, "total_steps": 5000, "loss": 3.9105, "eval_loss": null, "predict_loss": null, "learning_rate": 4.9893577812197555e-05, "epoch": 0.23678069326654905, "percentage": 83.2} | |
| {"current_steps": 4192, "total_steps": 5000, "loss": 3.8391, "eval_loss": null, "predict_loss": null, "learning_rate": 4.8441600668085826e-05, "epoch": 0.23860208321475326, "percentage": 83.84} | |
| {"current_steps": 4224, "total_steps": 5000, "loss": 3.7692, "eval_loss": null, "predict_loss": null, "learning_rate": 4.704074989021219e-05, "epoch": 0.24042347316295748, "percentage": 84.48} | |
| {"current_steps": 4256, "total_steps": 5000, "loss": 3.8248, "eval_loss": null, "predict_loss": null, "learning_rate": 4.569163993802638e-05, "epoch": 0.2422448631111617, "percentage": 85.12} | |
| {"current_steps": 4288, "total_steps": 5000, "loss": 3.8411, "eval_loss": null, "predict_loss": null, "learning_rate": 4.439486257574193e-05, "epoch": 0.24406625305936594, "percentage": 85.76} | |
| {"current_steps": 4320, "total_steps": 5000, "loss": 3.7753, "eval_loss": null, "predict_loss": null, "learning_rate": 4.315098661276884e-05, "epoch": 0.24588764300757016, "percentage": 86.4} | |
| {"current_steps": 4352, "total_steps": 5000, "loss": 3.7486, "eval_loss": null, "predict_loss": null, "learning_rate": 4.1960557654214884e-05, "epoch": 0.24770903295577437, "percentage": 87.04} | |
| {"current_steps": 4384, "total_steps": 5000, "loss": 3.7969, "eval_loss": null, "predict_loss": null, "learning_rate": 4.082409786156541e-05, "epoch": 0.2495304229039786, "percentage": 87.68} | |
| {"current_steps": 4416, "total_steps": 5000, "loss": 3.6981, "eval_loss": null, "predict_loss": null, "learning_rate": 3.9742105723645814e-05, "epoch": 0.25135181285218283, "percentage": 88.32} | |
| {"current_steps": 4448, "total_steps": 5000, "loss": 3.7178, "eval_loss": null, "predict_loss": null, "learning_rate": 3.871505583796792e-05, "epoch": 0.253173202800387, "percentage": 88.96} | |
| {"current_steps": 4480, "total_steps": 5000, "loss": 3.7591, "eval_loss": null, "predict_loss": null, "learning_rate": 3.774339870255591e-05, "epoch": 0.25499459274859126, "percentage": 89.6} | |
| {"current_steps": 4512, "total_steps": 5000, "loss": 3.7841, "eval_loss": null, "predict_loss": null, "learning_rate": 3.682756051834299e-05, "epoch": 0.2568159826967955, "percentage": 90.24} | |
| {"current_steps": 4544, "total_steps": 5000, "loss": 3.7037, "eval_loss": null, "predict_loss": null, "learning_rate": 3.596794300222543e-05, "epoch": 0.2586373726449997, "percentage": 90.88} | |
| {"current_steps": 4576, "total_steps": 5000, "loss": 3.7163, "eval_loss": null, "predict_loss": null, "learning_rate": 3.516492321085647e-05, "epoch": 0.26045876259320394, "percentage": 91.52} | |
| {"current_steps": 4608, "total_steps": 5000, "loss": 3.6617, "eval_loss": null, "predict_loss": null, "learning_rate": 3.4418853375256644e-05, "epoch": 0.2622801525414082, "percentage": 92.16} | |
| {"current_steps": 4640, "total_steps": 5000, "loss": 3.7857, "eval_loss": null, "predict_loss": null, "learning_rate": 3.3730060746313664e-05, "epoch": 0.2641015424896124, "percentage": 92.8} | |
| {"current_steps": 4672, "total_steps": 5000, "loss": 3.766, "eval_loss": null, "predict_loss": null, "learning_rate": 3.309884745123941e-05, "epoch": 0.2659229324378166, "percentage": 93.44} | |
| {"current_steps": 4704, "total_steps": 5000, "loss": 3.7389, "eval_loss": null, "predict_loss": null, "learning_rate": 3.2525490361046904e-05, "epoch": 0.2677443223860208, "percentage": 94.08} | |
| {"current_steps": 4736, "total_steps": 5000, "loss": 3.7761, "eval_loss": null, "predict_loss": null, "learning_rate": 3.201024096910552e-05, "epoch": 0.26956571233422505, "percentage": 94.72} | |
| {"current_steps": 4768, "total_steps": 5000, "loss": 3.7587, "eval_loss": null, "predict_loss": null, "learning_rate": 3.155332528082772e-05, "epoch": 0.2713871022824293, "percentage": 95.36} | |
| {"current_steps": 4800, "total_steps": 5000, "loss": 3.7763, "eval_loss": null, "predict_loss": null, "learning_rate": 3.11549437145356e-05, "epoch": 0.2732084922306335, "percentage": 96.0} | |
| {"current_steps": 4832, "total_steps": 5000, "loss": 3.7871, "eval_loss": null, "predict_loss": null, "learning_rate": 3.081527101355075e-05, "epoch": 0.2750298821788377, "percentage": 96.64} | |
| {"current_steps": 4864, "total_steps": 5000, "loss": 3.7559, "eval_loss": null, "predict_loss": null, "learning_rate": 3.053445616954611e-05, "epoch": 0.27685127212704197, "percentage": 97.28} | |
| {"current_steps": 4896, "total_steps": 5000, "loss": 3.8204, "eval_loss": null, "predict_loss": null, "learning_rate": 3.0312622357193284e-05, "epoch": 0.27867266207524616, "percentage": 97.92} | |
| {"current_steps": 4928, "total_steps": 5000, "loss": 3.691, "eval_loss": null, "predict_loss": null, "learning_rate": 3.014986688013406e-05, "epoch": 0.2804940520234504, "percentage": 98.56} | |
| {"current_steps": 4960, "total_steps": 5000, "loss": 3.7984, "eval_loss": null, "predict_loss": null, "learning_rate": 3.0046261128299766e-05, "epoch": 0.28231544197165465, "percentage": 99.2} | |
| {"current_steps": 4992, "total_steps": 5000, "loss": 3.8311, "eval_loss": null, "predict_loss": null, "learning_rate": 3.000185054659739e-05, "epoch": 0.28413683191985883, "percentage": 99.84} | |
| {"current_steps": 5000, "total_steps": 5000, "loss": null, "eval_loss": null, "predict_loss": null, "learning_rate": null, "epoch": 0.2845921794069099, "percentage": 100.0} | |