{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9999153188246253, "eval_steps": 500, "global_step": 2952, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "grad_norm": 0.439453125, "learning_rate": 3.378378378378379e-07, "loss": 2.6105, "step": 1 }, { "epoch": 0.0, "grad_norm": 0.55078125, "learning_rate": 1.6891891891891894e-06, "loss": 2.5818, "step": 5 }, { "epoch": 0.0, "grad_norm": 0.482421875, "learning_rate": 3.3783783783783788e-06, "loss": 2.5823, "step": 10 }, { "epoch": 0.01, "grad_norm": 0.546875, "learning_rate": 5.067567567567568e-06, "loss": 2.5736, "step": 15 }, { "epoch": 0.01, "grad_norm": 0.53125, "learning_rate": 6.7567567567567575e-06, "loss": 2.5517, "step": 20 }, { "epoch": 0.01, "grad_norm": 0.51171875, "learning_rate": 8.445945945945946e-06, "loss": 2.5821, "step": 25 }, { "epoch": 0.01, "grad_norm": 0.6796875, "learning_rate": 1.0135135135135136e-05, "loss": 2.526, "step": 30 }, { "epoch": 0.01, "grad_norm": 0.5625, "learning_rate": 1.1824324324324325e-05, "loss": 2.5476, "step": 35 }, { "epoch": 0.01, "grad_norm": 0.40234375, "learning_rate": 1.3513513513513515e-05, "loss": 2.492, "step": 40 }, { "epoch": 0.02, "grad_norm": 0.345703125, "learning_rate": 1.5202702702702704e-05, "loss": 2.5255, "step": 45 }, { "epoch": 0.02, "grad_norm": 0.283203125, "learning_rate": 1.6891891891891892e-05, "loss": 2.4882, "step": 50 }, { "epoch": 0.02, "grad_norm": 0.2412109375, "learning_rate": 1.8581081081081082e-05, "loss": 2.4763, "step": 55 }, { "epoch": 0.02, "grad_norm": 0.2138671875, "learning_rate": 2.0270270270270273e-05, "loss": 2.4817, "step": 60 }, { "epoch": 0.02, "grad_norm": 0.193359375, "learning_rate": 2.195945945945946e-05, "loss": 2.491, "step": 65 }, { "epoch": 0.02, "grad_norm": 0.1943359375, "learning_rate": 2.364864864864865e-05, "loss": 2.4636, "step": 70 }, { "epoch": 0.03, "grad_norm": 0.216796875, "learning_rate": 2.533783783783784e-05, "loss": 2.4359, "step": 75 }, { "epoch": 0.03, "grad_norm": 0.2099609375, "learning_rate": 2.702702702702703e-05, "loss": 2.4172, "step": 80 }, { "epoch": 0.03, "grad_norm": 0.177734375, "learning_rate": 2.8716216216216217e-05, "loss": 2.395, "step": 85 }, { "epoch": 0.03, "grad_norm": 0.177734375, "learning_rate": 3.0405405405405407e-05, "loss": 2.3687, "step": 90 }, { "epoch": 0.03, "grad_norm": 0.1650390625, "learning_rate": 3.20945945945946e-05, "loss": 2.3712, "step": 95 }, { "epoch": 0.03, "grad_norm": 0.1630859375, "learning_rate": 3.3783783783783784e-05, "loss": 2.3344, "step": 100 }, { "epoch": 0.04, "grad_norm": 0.1630859375, "learning_rate": 3.547297297297297e-05, "loss": 2.3406, "step": 105 }, { "epoch": 0.04, "grad_norm": 0.18359375, "learning_rate": 3.7162162162162165e-05, "loss": 2.286, "step": 110 }, { "epoch": 0.04, "grad_norm": 0.1591796875, "learning_rate": 3.885135135135135e-05, "loss": 2.2872, "step": 115 }, { "epoch": 0.04, "grad_norm": 0.1572265625, "learning_rate": 4.0540540540540545e-05, "loss": 2.3243, "step": 120 }, { "epoch": 0.04, "grad_norm": 0.1357421875, "learning_rate": 4.222972972972973e-05, "loss": 2.2734, "step": 125 }, { "epoch": 0.04, "grad_norm": 0.13671875, "learning_rate": 4.391891891891892e-05, "loss": 2.2828, "step": 130 }, { "epoch": 0.05, "grad_norm": 0.1376953125, "learning_rate": 4.560810810810811e-05, "loss": 2.2821, "step": 135 }, { "epoch": 0.05, "grad_norm": 0.1328125, "learning_rate": 4.72972972972973e-05, "loss": 2.2867, "step": 140 }, { "epoch": 0.05, "grad_norm": 0.1337890625, "learning_rate": 4.8986486486486486e-05, "loss": 2.2866, "step": 145 }, { "epoch": 0.05, "grad_norm": 0.1337890625, "learning_rate": 5.067567567567568e-05, "loss": 2.2754, "step": 150 }, { "epoch": 0.05, "grad_norm": 0.1357421875, "learning_rate": 5.2364864864864873e-05, "loss": 2.2497, "step": 155 }, { "epoch": 0.05, "grad_norm": 0.13671875, "learning_rate": 5.405405405405406e-05, "loss": 2.2668, "step": 160 }, { "epoch": 0.06, "grad_norm": 0.1318359375, "learning_rate": 5.574324324324325e-05, "loss": 2.2712, "step": 165 }, { "epoch": 0.06, "grad_norm": 0.1337890625, "learning_rate": 5.7432432432432434e-05, "loss": 2.2803, "step": 170 }, { "epoch": 0.06, "grad_norm": 0.1337890625, "learning_rate": 5.912162162162163e-05, "loss": 2.275, "step": 175 }, { "epoch": 0.06, "grad_norm": 0.138671875, "learning_rate": 6.0810810810810814e-05, "loss": 2.2391, "step": 180 }, { "epoch": 0.06, "grad_norm": 0.13671875, "learning_rate": 6.25e-05, "loss": 2.2509, "step": 185 }, { "epoch": 0.06, "grad_norm": 0.1416015625, "learning_rate": 6.41891891891892e-05, "loss": 2.2538, "step": 190 }, { "epoch": 0.07, "grad_norm": 0.150390625, "learning_rate": 6.587837837837837e-05, "loss": 2.2511, "step": 195 }, { "epoch": 0.07, "grad_norm": 0.1455078125, "learning_rate": 6.756756756756757e-05, "loss": 2.2711, "step": 200 }, { "epoch": 0.07, "grad_norm": 0.13671875, "learning_rate": 6.925675675675676e-05, "loss": 2.2703, "step": 205 }, { "epoch": 0.07, "grad_norm": 0.1328125, "learning_rate": 7.094594594594594e-05, "loss": 2.2641, "step": 210 }, { "epoch": 0.07, "grad_norm": 0.1484375, "learning_rate": 7.263513513513514e-05, "loss": 2.2312, "step": 215 }, { "epoch": 0.07, "grad_norm": 0.1484375, "learning_rate": 7.432432432432433e-05, "loss": 2.2609, "step": 220 }, { "epoch": 0.08, "grad_norm": 0.1435546875, "learning_rate": 7.601351351351351e-05, "loss": 2.2292, "step": 225 }, { "epoch": 0.08, "grad_norm": 0.1416015625, "learning_rate": 7.77027027027027e-05, "loss": 2.2355, "step": 230 }, { "epoch": 0.08, "grad_norm": 0.15234375, "learning_rate": 7.93918918918919e-05, "loss": 2.2207, "step": 235 }, { "epoch": 0.08, "grad_norm": 0.1474609375, "learning_rate": 8.108108108108109e-05, "loss": 2.2336, "step": 240 }, { "epoch": 0.08, "grad_norm": 0.150390625, "learning_rate": 8.277027027027028e-05, "loss": 2.2604, "step": 245 }, { "epoch": 0.08, "grad_norm": 0.150390625, "learning_rate": 8.445945945945946e-05, "loss": 2.2512, "step": 250 }, { "epoch": 0.09, "grad_norm": 0.1552734375, "learning_rate": 8.614864864864866e-05, "loss": 2.226, "step": 255 }, { "epoch": 0.09, "grad_norm": 0.1728515625, "learning_rate": 8.783783783783784e-05, "loss": 2.2042, "step": 260 }, { "epoch": 0.09, "grad_norm": 0.1669921875, "learning_rate": 8.952702702702703e-05, "loss": 2.224, "step": 265 }, { "epoch": 0.09, "grad_norm": 0.1611328125, "learning_rate": 9.121621621621623e-05, "loss": 2.224, "step": 270 }, { "epoch": 0.09, "grad_norm": 0.1611328125, "learning_rate": 9.29054054054054e-05, "loss": 2.2425, "step": 275 }, { "epoch": 0.09, "grad_norm": 0.1513671875, "learning_rate": 9.45945945945946e-05, "loss": 2.231, "step": 280 }, { "epoch": 0.1, "grad_norm": 0.150390625, "learning_rate": 9.628378378378379e-05, "loss": 2.2299, "step": 285 }, { "epoch": 0.1, "grad_norm": 0.154296875, "learning_rate": 9.797297297297297e-05, "loss": 2.2135, "step": 290 }, { "epoch": 0.1, "grad_norm": 0.1591796875, "learning_rate": 9.966216216216217e-05, "loss": 2.2346, "step": 295 }, { "epoch": 0.1, "grad_norm": 0.1611328125, "learning_rate": 9.999944036768366e-05, "loss": 2.2271, "step": 300 }, { "epoch": 0.1, "grad_norm": 0.1533203125, "learning_rate": 9.999716688286903e-05, "loss": 2.2334, "step": 305 }, { "epoch": 0.11, "grad_norm": 0.150390625, "learning_rate": 9.999314464799477e-05, "loss": 2.2153, "step": 310 }, { "epoch": 0.11, "grad_norm": 0.1650390625, "learning_rate": 9.998737380374656e-05, "loss": 2.2373, "step": 315 }, { "epoch": 0.11, "grad_norm": 0.1669921875, "learning_rate": 9.997985455197114e-05, "loss": 2.2456, "step": 320 }, { "epoch": 0.11, "grad_norm": 0.1640625, "learning_rate": 9.99705871556692e-05, "loss": 2.2055, "step": 325 }, { "epoch": 0.11, "grad_norm": 0.1591796875, "learning_rate": 9.995957193898633e-05, "loss": 2.1951, "step": 330 }, { "epoch": 0.11, "grad_norm": 0.1591796875, "learning_rate": 9.994680928720159e-05, "loss": 2.2664, "step": 335 }, { "epoch": 0.12, "grad_norm": 0.1533203125, "learning_rate": 9.993229964671401e-05, "loss": 2.2517, "step": 340 }, { "epoch": 0.12, "grad_norm": 0.158203125, "learning_rate": 9.991604352502706e-05, "loss": 2.2064, "step": 345 }, { "epoch": 0.12, "grad_norm": 0.1552734375, "learning_rate": 9.989804149073081e-05, "loss": 2.2151, "step": 350 }, { "epoch": 0.12, "grad_norm": 0.1552734375, "learning_rate": 9.987829417348213e-05, "loss": 2.23, "step": 355 }, { "epoch": 0.12, "grad_norm": 0.15234375, "learning_rate": 9.985680226398261e-05, "loss": 2.2422, "step": 360 }, { "epoch": 0.12, "grad_norm": 0.1591796875, "learning_rate": 9.983356651395436e-05, "loss": 2.2123, "step": 365 }, { "epoch": 0.13, "grad_norm": 0.1669921875, "learning_rate": 9.980858773611388e-05, "loss": 2.2226, "step": 370 }, { "epoch": 0.13, "grad_norm": 0.154296875, "learning_rate": 9.97818668041434e-05, "loss": 2.2272, "step": 375 }, { "epoch": 0.13, "grad_norm": 0.1630859375, "learning_rate": 9.975340465266053e-05, "loss": 2.2006, "step": 380 }, { "epoch": 0.13, "grad_norm": 0.158203125, "learning_rate": 9.972320227718546e-05, "loss": 2.2035, "step": 385 }, { "epoch": 0.13, "grad_norm": 0.154296875, "learning_rate": 9.969126073410617e-05, "loss": 2.2141, "step": 390 }, { "epoch": 0.13, "grad_norm": 0.15625, "learning_rate": 9.965758114064147e-05, "loss": 2.204, "step": 395 }, { "epoch": 0.14, "grad_norm": 0.1572265625, "learning_rate": 9.962216467480193e-05, "loss": 2.2051, "step": 400 }, { "epoch": 0.14, "grad_norm": 0.1572265625, "learning_rate": 9.958501257534866e-05, "loss": 2.2387, "step": 405 }, { "epoch": 0.14, "grad_norm": 0.158203125, "learning_rate": 9.954612614175003e-05, "loss": 2.2191, "step": 410 }, { "epoch": 0.14, "grad_norm": 0.158203125, "learning_rate": 9.950550673413617e-05, "loss": 2.2016, "step": 415 }, { "epoch": 0.14, "grad_norm": 0.1611328125, "learning_rate": 9.94631557732514e-05, "loss": 2.2261, "step": 420 }, { "epoch": 0.14, "grad_norm": 0.1611328125, "learning_rate": 9.941907474040458e-05, "loss": 2.1897, "step": 425 }, { "epoch": 0.15, "grad_norm": 0.1611328125, "learning_rate": 9.937326517741724e-05, "loss": 2.2203, "step": 430 }, { "epoch": 0.15, "grad_norm": 0.16015625, "learning_rate": 9.932572868656969e-05, "loss": 2.194, "step": 435 }, { "epoch": 0.15, "grad_norm": 0.1611328125, "learning_rate": 9.927646693054496e-05, "loss": 2.2442, "step": 440 }, { "epoch": 0.15, "grad_norm": 0.1591796875, "learning_rate": 9.922548163237066e-05, "loss": 2.1735, "step": 445 }, { "epoch": 0.15, "grad_norm": 0.1640625, "learning_rate": 9.917277457535872e-05, "loss": 2.1946, "step": 450 }, { "epoch": 0.15, "grad_norm": 0.1533203125, "learning_rate": 9.911834760304294e-05, "loss": 2.2291, "step": 455 }, { "epoch": 0.16, "grad_norm": 0.1630859375, "learning_rate": 9.906220261911465e-05, "loss": 2.1984, "step": 460 }, { "epoch": 0.16, "grad_norm": 0.1591796875, "learning_rate": 9.900434158735598e-05, "loss": 2.2231, "step": 465 }, { "epoch": 0.16, "grad_norm": 0.162109375, "learning_rate": 9.894476653157126e-05, "loss": 2.1912, "step": 470 }, { "epoch": 0.16, "grad_norm": 0.1689453125, "learning_rate": 9.88834795355162e-05, "loss": 2.2118, "step": 475 }, { "epoch": 0.16, "grad_norm": 0.1630859375, "learning_rate": 9.882048274282505e-05, "loss": 2.2189, "step": 480 }, { "epoch": 0.16, "grad_norm": 0.1689453125, "learning_rate": 9.875577835693554e-05, "loss": 2.2098, "step": 485 }, { "epoch": 0.17, "grad_norm": 0.1572265625, "learning_rate": 9.868936864101188e-05, "loss": 2.2567, "step": 490 }, { "epoch": 0.17, "grad_norm": 0.1611328125, "learning_rate": 9.86212559178656e-05, "loss": 2.2096, "step": 495 }, { "epoch": 0.17, "grad_norm": 0.166015625, "learning_rate": 9.855144256987423e-05, "loss": 2.2169, "step": 500 }, { "epoch": 0.17, "grad_norm": 0.1533203125, "learning_rate": 9.84799310388981e-05, "loss": 2.206, "step": 505 }, { "epoch": 0.17, "grad_norm": 0.15625, "learning_rate": 9.840672382619478e-05, "loss": 2.2387, "step": 510 }, { "epoch": 0.17, "grad_norm": 0.16015625, "learning_rate": 9.833182349233174e-05, "loss": 2.1945, "step": 515 }, { "epoch": 0.18, "grad_norm": 0.1572265625, "learning_rate": 9.825523265709666e-05, "loss": 2.2079, "step": 520 }, { "epoch": 0.18, "grad_norm": 0.1630859375, "learning_rate": 9.817695399940592e-05, "loss": 2.2095, "step": 525 }, { "epoch": 0.18, "grad_norm": 0.1572265625, "learning_rate": 9.80969902572108e-05, "loss": 2.2254, "step": 530 }, { "epoch": 0.18, "grad_norm": 0.1630859375, "learning_rate": 9.801534422740173e-05, "loss": 2.2193, "step": 535 }, { "epoch": 0.18, "grad_norm": 0.1640625, "learning_rate": 9.793201876571053e-05, "loss": 2.2287, "step": 540 }, { "epoch": 0.18, "grad_norm": 0.15625, "learning_rate": 9.784701678661045e-05, "loss": 2.2142, "step": 545 }, { "epoch": 0.19, "grad_norm": 0.16015625, "learning_rate": 9.77603412632143e-05, "loss": 2.1981, "step": 550 }, { "epoch": 0.19, "grad_norm": 0.1630859375, "learning_rate": 9.767199522717036e-05, "loss": 2.1763, "step": 555 }, { "epoch": 0.19, "grad_norm": 0.166015625, "learning_rate": 9.758198176855648e-05, "loss": 2.1829, "step": 560 }, { "epoch": 0.19, "grad_norm": 0.1572265625, "learning_rate": 9.749030403577184e-05, "loss": 2.1872, "step": 565 }, { "epoch": 0.19, "grad_norm": 0.1572265625, "learning_rate": 9.739696523542696e-05, "loss": 2.2023, "step": 570 }, { "epoch": 0.19, "grad_norm": 0.1640625, "learning_rate": 9.73019686322315e-05, "loss": 2.1966, "step": 575 }, { "epoch": 0.2, "grad_norm": 0.1650390625, "learning_rate": 9.720531754888e-05, "loss": 2.2187, "step": 580 }, { "epoch": 0.2, "grad_norm": 0.16015625, "learning_rate": 9.710701536593581e-05, "loss": 2.2016, "step": 585 }, { "epoch": 0.2, "grad_norm": 0.1572265625, "learning_rate": 9.700706552171268e-05, "loss": 2.2113, "step": 590 }, { "epoch": 0.2, "grad_norm": 0.162109375, "learning_rate": 9.690547151215463e-05, "loss": 2.1862, "step": 595 }, { "epoch": 0.2, "grad_norm": 0.1630859375, "learning_rate": 9.680223689071364e-05, "loss": 2.1791, "step": 600 }, { "epoch": 0.2, "grad_norm": 0.15625, "learning_rate": 9.669736526822528e-05, "loss": 2.2076, "step": 605 }, { "epoch": 0.21, "grad_norm": 0.162109375, "learning_rate": 9.659086031278254e-05, "loss": 2.2267, "step": 610 }, { "epoch": 0.21, "grad_norm": 0.1630859375, "learning_rate": 9.648272574960744e-05, "loss": 2.1674, "step": 615 }, { "epoch": 0.21, "grad_norm": 0.158203125, "learning_rate": 9.637296536092075e-05, "loss": 2.1736, "step": 620 }, { "epoch": 0.21, "grad_norm": 0.1591796875, "learning_rate": 9.626158298580973e-05, "loss": 2.196, "step": 625 }, { "epoch": 0.21, "grad_norm": 0.1572265625, "learning_rate": 9.614858252009385e-05, "loss": 2.1903, "step": 630 }, { "epoch": 0.22, "grad_norm": 0.1572265625, "learning_rate": 9.603396791618844e-05, "loss": 2.1976, "step": 635 }, { "epoch": 0.22, "grad_norm": 0.1611328125, "learning_rate": 9.591774318296661e-05, "loss": 2.1985, "step": 640 }, { "epoch": 0.22, "grad_norm": 0.154296875, "learning_rate": 9.579991238561887e-05, "loss": 2.1934, "step": 645 }, { "epoch": 0.22, "grad_norm": 0.162109375, "learning_rate": 9.568047964551102e-05, "loss": 2.1879, "step": 650 }, { "epoch": 0.22, "grad_norm": 0.1591796875, "learning_rate": 9.555944914003998e-05, "loss": 2.1918, "step": 655 }, { "epoch": 0.22, "grad_norm": 0.1611328125, "learning_rate": 9.54368251024877e-05, "loss": 2.2127, "step": 660 }, { "epoch": 0.23, "grad_norm": 0.15625, "learning_rate": 9.531261182187308e-05, "loss": 2.1711, "step": 665 }, { "epoch": 0.23, "grad_norm": 0.1591796875, "learning_rate": 9.51868136428019e-05, "loss": 2.2108, "step": 670 }, { "epoch": 0.23, "grad_norm": 0.150390625, "learning_rate": 9.505943496531496e-05, "loss": 2.2295, "step": 675 }, { "epoch": 0.23, "grad_norm": 0.1591796875, "learning_rate": 9.493048024473412e-05, "loss": 2.1847, "step": 680 }, { "epoch": 0.23, "grad_norm": 0.162109375, "learning_rate": 9.479995399150644e-05, "loss": 2.1936, "step": 685 }, { "epoch": 0.23, "grad_norm": 0.1640625, "learning_rate": 9.466786077104646e-05, "loss": 2.1942, "step": 690 }, { "epoch": 0.24, "grad_norm": 0.1591796875, "learning_rate": 9.453420520357652e-05, "loss": 2.1972, "step": 695 }, { "epoch": 0.24, "grad_norm": 0.15234375, "learning_rate": 9.439899196396515e-05, "loss": 2.1822, "step": 700 }, { "epoch": 0.24, "grad_norm": 0.1572265625, "learning_rate": 9.426222578156356e-05, "loss": 2.2155, "step": 705 }, { "epoch": 0.24, "grad_norm": 0.15625, "learning_rate": 9.412391144004017e-05, "loss": 2.1891, "step": 710 }, { "epoch": 0.24, "grad_norm": 0.158203125, "learning_rate": 9.398405377721338e-05, "loss": 2.1806, "step": 715 }, { "epoch": 0.24, "grad_norm": 0.1630859375, "learning_rate": 9.384265768488225e-05, "loss": 2.1999, "step": 720 }, { "epoch": 0.25, "grad_norm": 0.1611328125, "learning_rate": 9.369972810865557e-05, "loss": 2.224, "step": 725 }, { "epoch": 0.25, "grad_norm": 0.16015625, "learning_rate": 9.355527004777868e-05, "loss": 2.2033, "step": 730 }, { "epoch": 0.25, "grad_norm": 0.1611328125, "learning_rate": 9.340928855495872e-05, "loss": 2.1892, "step": 735 }, { "epoch": 0.25, "grad_norm": 0.1630859375, "learning_rate": 9.32617887361879e-05, "loss": 2.2023, "step": 740 }, { "epoch": 0.25, "grad_norm": 0.1650390625, "learning_rate": 9.311277575056489e-05, "loss": 2.2089, "step": 745 }, { "epoch": 0.25, "grad_norm": 0.1611328125, "learning_rate": 9.296225481011436e-05, "loss": 2.1764, "step": 750 }, { "epoch": 0.26, "grad_norm": 0.1611328125, "learning_rate": 9.281023117960468e-05, "loss": 2.2349, "step": 755 }, { "epoch": 0.26, "grad_norm": 0.162109375, "learning_rate": 9.265671017636383e-05, "loss": 2.2008, "step": 760 }, { "epoch": 0.26, "grad_norm": 0.1630859375, "learning_rate": 9.250169717009334e-05, "loss": 2.1711, "step": 765 }, { "epoch": 0.26, "grad_norm": 0.1669921875, "learning_rate": 9.234519758268049e-05, "loss": 2.2002, "step": 770 }, { "epoch": 0.26, "grad_norm": 0.158203125, "learning_rate": 9.218721688800868e-05, "loss": 2.184, "step": 775 }, { "epoch": 0.26, "grad_norm": 0.1611328125, "learning_rate": 9.202776061176605e-05, "loss": 2.1849, "step": 780 }, { "epoch": 0.27, "grad_norm": 0.1689453125, "learning_rate": 9.186683433125203e-05, "loss": 2.1952, "step": 785 }, { "epoch": 0.27, "grad_norm": 0.1611328125, "learning_rate": 9.170444367518241e-05, "loss": 2.2033, "step": 790 }, { "epoch": 0.27, "grad_norm": 0.166015625, "learning_rate": 9.154059432349245e-05, "loss": 2.191, "step": 795 }, { "epoch": 0.27, "grad_norm": 0.158203125, "learning_rate": 9.13752920071381e-05, "loss": 2.1984, "step": 800 }, { "epoch": 0.27, "grad_norm": 0.1591796875, "learning_rate": 9.120854250789573e-05, "loss": 2.2054, "step": 805 }, { "epoch": 0.27, "grad_norm": 0.1669921875, "learning_rate": 9.104035165815971e-05, "loss": 2.2218, "step": 810 }, { "epoch": 0.28, "grad_norm": 0.16015625, "learning_rate": 9.087072534073859e-05, "loss": 2.2102, "step": 815 }, { "epoch": 0.28, "grad_norm": 0.1669921875, "learning_rate": 9.069966948864916e-05, "loss": 2.2294, "step": 820 }, { "epoch": 0.28, "grad_norm": 0.1630859375, "learning_rate": 9.052719008490909e-05, "loss": 2.203, "step": 825 }, { "epoch": 0.28, "grad_norm": 0.1611328125, "learning_rate": 9.035329316232755e-05, "loss": 2.1868, "step": 830 }, { "epoch": 0.28, "grad_norm": 0.1650390625, "learning_rate": 9.017798480329427e-05, "loss": 2.1755, "step": 835 }, { "epoch": 0.28, "grad_norm": 0.1669921875, "learning_rate": 9.000127113956674e-05, "loss": 2.2099, "step": 840 }, { "epoch": 0.29, "grad_norm": 0.1552734375, "learning_rate": 8.982315835205578e-05, "loss": 2.2155, "step": 845 }, { "epoch": 0.29, "grad_norm": 0.16796875, "learning_rate": 8.964365267060935e-05, "loss": 2.2156, "step": 850 }, { "epoch": 0.29, "grad_norm": 0.1640625, "learning_rate": 8.946276037379467e-05, "loss": 2.1751, "step": 855 }, { "epoch": 0.29, "grad_norm": 0.1689453125, "learning_rate": 8.928048778867848e-05, "loss": 2.1603, "step": 860 }, { "epoch": 0.29, "grad_norm": 0.166015625, "learning_rate": 8.909684129060593e-05, "loss": 2.179, "step": 865 }, { "epoch": 0.29, "grad_norm": 0.16015625, "learning_rate": 8.89118273029775e-05, "loss": 2.1944, "step": 870 }, { "epoch": 0.3, "grad_norm": 0.1650390625, "learning_rate": 8.872545229702426e-05, "loss": 2.214, "step": 875 }, { "epoch": 0.3, "grad_norm": 0.1611328125, "learning_rate": 8.853772279158166e-05, "loss": 2.1941, "step": 880 }, { "epoch": 0.3, "grad_norm": 0.16796875, "learning_rate": 8.834864535286143e-05, "loss": 2.168, "step": 885 }, { "epoch": 0.3, "grad_norm": 0.1640625, "learning_rate": 8.815822659422195e-05, "loss": 2.206, "step": 890 }, { "epoch": 0.3, "grad_norm": 0.1611328125, "learning_rate": 8.796647317593691e-05, "loss": 2.2074, "step": 895 }, { "epoch": 0.3, "grad_norm": 0.1669921875, "learning_rate": 8.777339180496238e-05, "loss": 2.19, "step": 900 }, { "epoch": 0.31, "grad_norm": 0.1630859375, "learning_rate": 8.757898923470218e-05, "loss": 2.2011, "step": 905 }, { "epoch": 0.31, "grad_norm": 0.162109375, "learning_rate": 8.738327226477176e-05, "loss": 2.1937, "step": 910 }, { "epoch": 0.31, "grad_norm": 0.158203125, "learning_rate": 8.718624774076023e-05, "loss": 2.1904, "step": 915 }, { "epoch": 0.31, "grad_norm": 0.1630859375, "learning_rate": 8.698792255399104e-05, "loss": 2.1914, "step": 920 }, { "epoch": 0.31, "grad_norm": 0.1630859375, "learning_rate": 8.67883036412809e-05, "loss": 2.1953, "step": 925 }, { "epoch": 0.32, "grad_norm": 0.1630859375, "learning_rate": 8.658739798469712e-05, "loss": 2.1928, "step": 930 }, { "epoch": 0.32, "grad_norm": 0.162109375, "learning_rate": 8.638521261131349e-05, "loss": 2.2242, "step": 935 }, { "epoch": 0.32, "grad_norm": 0.166015625, "learning_rate": 8.618175459296433e-05, "loss": 2.1607, "step": 940 }, { "epoch": 0.32, "grad_norm": 0.1611328125, "learning_rate": 8.597703104599736e-05, "loss": 2.2007, "step": 945 }, { "epoch": 0.32, "grad_norm": 0.1689453125, "learning_rate": 8.577104913102458e-05, "loss": 2.1936, "step": 950 }, { "epoch": 0.32, "grad_norm": 0.1669921875, "learning_rate": 8.556381605267196e-05, "loss": 2.1839, "step": 955 }, { "epoch": 0.33, "grad_norm": 0.1748046875, "learning_rate": 8.535533905932738e-05, "loss": 2.1786, "step": 960 }, { "epoch": 0.33, "grad_norm": 0.1611328125, "learning_rate": 8.51456254428871e-05, "loss": 2.1859, "step": 965 }, { "epoch": 0.33, "grad_norm": 0.162109375, "learning_rate": 8.49346825385007e-05, "loss": 2.2096, "step": 970 }, { "epoch": 0.33, "grad_norm": 0.162109375, "learning_rate": 8.472251772431461e-05, "loss": 2.2057, "step": 975 }, { "epoch": 0.33, "grad_norm": 0.1708984375, "learning_rate": 8.450913842121396e-05, "loss": 2.1645, "step": 980 }, { "epoch": 0.33, "grad_norm": 0.171875, "learning_rate": 8.429455209256297e-05, "loss": 2.1972, "step": 985 }, { "epoch": 0.34, "grad_norm": 0.162109375, "learning_rate": 8.407876624394406e-05, "loss": 2.194, "step": 990 }, { "epoch": 0.34, "grad_norm": 0.162109375, "learning_rate": 8.38617884228952e-05, "loss": 2.1823, "step": 995 }, { "epoch": 0.34, "grad_norm": 0.1591796875, "learning_rate": 8.364362621864595e-05, "loss": 2.2122, "step": 1000 }, { "epoch": 0.34, "grad_norm": 0.1650390625, "learning_rate": 8.342428726185205e-05, "loss": 2.2262, "step": 1005 }, { "epoch": 0.34, "grad_norm": 0.1669921875, "learning_rate": 8.320377922432848e-05, "loss": 2.1803, "step": 1010 }, { "epoch": 0.34, "grad_norm": 0.1650390625, "learning_rate": 8.298210981878112e-05, "loss": 2.182, "step": 1015 }, { "epoch": 0.35, "grad_norm": 0.1630859375, "learning_rate": 8.275928679853703e-05, "loss": 2.1982, "step": 1020 }, { "epoch": 0.35, "grad_norm": 0.169921875, "learning_rate": 8.253531795727319e-05, "loss": 2.1612, "step": 1025 }, { "epoch": 0.35, "grad_norm": 0.1640625, "learning_rate": 8.231021112874402e-05, "loss": 2.1983, "step": 1030 }, { "epoch": 0.35, "grad_norm": 0.1689453125, "learning_rate": 8.20839741865072e-05, "loss": 2.1974, "step": 1035 }, { "epoch": 0.35, "grad_norm": 0.1650390625, "learning_rate": 8.185661504364844e-05, "loss": 2.1986, "step": 1040 }, { "epoch": 0.35, "grad_norm": 0.1591796875, "learning_rate": 8.162814165250464e-05, "loss": 2.1974, "step": 1045 }, { "epoch": 0.36, "grad_norm": 0.166015625, "learning_rate": 8.139856200438575e-05, "loss": 2.1886, "step": 1050 }, { "epoch": 0.36, "grad_norm": 0.1748046875, "learning_rate": 8.11678841292952e-05, "loss": 2.2085, "step": 1055 }, { "epoch": 0.36, "grad_norm": 0.171875, "learning_rate": 8.093611609564913e-05, "loss": 2.2038, "step": 1060 }, { "epoch": 0.36, "grad_norm": 0.16015625, "learning_rate": 8.070326600999416e-05, "loss": 2.2125, "step": 1065 }, { "epoch": 0.36, "grad_norm": 0.1611328125, "learning_rate": 8.046934201672376e-05, "loss": 2.1787, "step": 1070 }, { "epoch": 0.36, "grad_norm": 0.1669921875, "learning_rate": 8.023435229779351e-05, "loss": 2.2398, "step": 1075 }, { "epoch": 0.37, "grad_norm": 0.1591796875, "learning_rate": 7.999830507243478e-05, "loss": 2.1843, "step": 1080 }, { "epoch": 0.37, "grad_norm": 0.1650390625, "learning_rate": 7.976120859686744e-05, "loss": 2.1823, "step": 1085 }, { "epoch": 0.37, "grad_norm": 0.1689453125, "learning_rate": 7.952307116401086e-05, "loss": 2.1992, "step": 1090 }, { "epoch": 0.37, "grad_norm": 0.16796875, "learning_rate": 7.9283901103194e-05, "loss": 2.1805, "step": 1095 }, { "epoch": 0.37, "grad_norm": 0.16796875, "learning_rate": 7.904370677986404e-05, "loss": 2.2111, "step": 1100 }, { "epoch": 0.37, "grad_norm": 0.16015625, "learning_rate": 7.880249659529376e-05, "loss": 2.1732, "step": 1105 }, { "epoch": 0.38, "grad_norm": 0.1630859375, "learning_rate": 7.85602789862877e-05, "loss": 2.1761, "step": 1110 }, { "epoch": 0.38, "grad_norm": 0.1708984375, "learning_rate": 7.831706242488708e-05, "loss": 2.1856, "step": 1115 }, { "epoch": 0.38, "grad_norm": 0.1630859375, "learning_rate": 7.80728554180734e-05, "loss": 2.1798, "step": 1120 }, { "epoch": 0.38, "grad_norm": 0.166015625, "learning_rate": 7.782766650747108e-05, "loss": 2.1974, "step": 1125 }, { "epoch": 0.38, "grad_norm": 0.1630859375, "learning_rate": 7.758150426904845e-05, "loss": 2.1742, "step": 1130 }, { "epoch": 0.38, "grad_norm": 0.162109375, "learning_rate": 7.733437731281797e-05, "loss": 2.1869, "step": 1135 }, { "epoch": 0.39, "grad_norm": 0.162109375, "learning_rate": 7.708629428253497e-05, "loss": 2.1808, "step": 1140 }, { "epoch": 0.39, "grad_norm": 0.1640625, "learning_rate": 7.683726385539544e-05, "loss": 2.2019, "step": 1145 }, { "epoch": 0.39, "grad_norm": 0.1708984375, "learning_rate": 7.658729474173241e-05, "loss": 2.2051, "step": 1150 }, { "epoch": 0.39, "grad_norm": 0.16015625, "learning_rate": 7.63363956847113e-05, "loss": 2.1951, "step": 1155 }, { "epoch": 0.39, "grad_norm": 0.16796875, "learning_rate": 7.608457546002424e-05, "loss": 2.2108, "step": 1160 }, { "epoch": 0.39, "grad_norm": 0.1640625, "learning_rate": 7.58318428755829e-05, "loss": 2.1563, "step": 1165 }, { "epoch": 0.4, "grad_norm": 0.166015625, "learning_rate": 7.557820677121067e-05, "loss": 2.1778, "step": 1170 }, { "epoch": 0.4, "grad_norm": 0.16015625, "learning_rate": 7.532367601833321e-05, "loss": 2.2198, "step": 1175 }, { "epoch": 0.4, "grad_norm": 0.16796875, "learning_rate": 7.506825951966843e-05, "loss": 2.1818, "step": 1180 }, { "epoch": 0.4, "grad_norm": 0.1708984375, "learning_rate": 7.481196620891482e-05, "loss": 2.1774, "step": 1185 }, { "epoch": 0.4, "grad_norm": 0.166015625, "learning_rate": 7.45548050504392e-05, "loss": 2.167, "step": 1190 }, { "epoch": 0.4, "grad_norm": 0.1728515625, "learning_rate": 7.429678503896304e-05, "loss": 2.153, "step": 1195 }, { "epoch": 0.41, "grad_norm": 0.171875, "learning_rate": 7.403791519924794e-05, "loss": 2.1921, "step": 1200 }, { "epoch": 0.41, "grad_norm": 0.1669921875, "learning_rate": 7.377820458577987e-05, "loss": 2.1914, "step": 1205 }, { "epoch": 0.41, "grad_norm": 0.166015625, "learning_rate": 7.351766228245259e-05, "loss": 2.1962, "step": 1210 }, { "epoch": 0.41, "grad_norm": 0.1650390625, "learning_rate": 7.325629740224979e-05, "loss": 2.216, "step": 1215 }, { "epoch": 0.41, "grad_norm": 0.162109375, "learning_rate": 7.299411908692649e-05, "loss": 2.1387, "step": 1220 }, { "epoch": 0.41, "grad_norm": 0.1669921875, "learning_rate": 7.273113650668919e-05, "loss": 2.1843, "step": 1225 }, { "epoch": 0.42, "grad_norm": 0.1669921875, "learning_rate": 7.246735885987515e-05, "loss": 2.1779, "step": 1230 }, { "epoch": 0.42, "grad_norm": 0.1669921875, "learning_rate": 7.220279537263063e-05, "loss": 2.2041, "step": 1235 }, { "epoch": 0.42, "grad_norm": 0.171875, "learning_rate": 7.193745529858826e-05, "loss": 2.1866, "step": 1240 }, { "epoch": 0.42, "grad_norm": 0.169921875, "learning_rate": 7.167134791854333e-05, "loss": 2.1654, "step": 1245 }, { "epoch": 0.42, "grad_norm": 0.1689453125, "learning_rate": 7.140448254012912e-05, "loss": 2.1932, "step": 1250 }, { "epoch": 0.43, "grad_norm": 0.166015625, "learning_rate": 7.113686849749153e-05, "loss": 2.1708, "step": 1255 }, { "epoch": 0.43, "grad_norm": 0.169921875, "learning_rate": 7.086851515096233e-05, "loss": 2.1748, "step": 1260 }, { "epoch": 0.43, "grad_norm": 0.1689453125, "learning_rate": 7.0599431886732e-05, "loss": 2.1981, "step": 1265 }, { "epoch": 0.43, "grad_norm": 0.1650390625, "learning_rate": 7.032962811652133e-05, "loss": 2.1723, "step": 1270 }, { "epoch": 0.43, "grad_norm": 0.16796875, "learning_rate": 7.005911327725222e-05, "loss": 2.1849, "step": 1275 }, { "epoch": 0.43, "grad_norm": 0.1728515625, "learning_rate": 6.97878968307176e-05, "loss": 2.1794, "step": 1280 }, { "epoch": 0.44, "grad_norm": 0.1669921875, "learning_rate": 6.951598826325056e-05, "loss": 2.1861, "step": 1285 }, { "epoch": 0.44, "grad_norm": 0.166015625, "learning_rate": 6.924339708539244e-05, "loss": 2.1937, "step": 1290 }, { "epoch": 0.44, "grad_norm": 0.1591796875, "learning_rate": 6.897013283156026e-05, "loss": 2.1785, "step": 1295 }, { "epoch": 0.44, "grad_norm": 0.1689453125, "learning_rate": 6.869620505971321e-05, "loss": 2.1728, "step": 1300 }, { "epoch": 0.44, "grad_norm": 0.166015625, "learning_rate": 6.842162335101829e-05, "loss": 2.2097, "step": 1305 }, { "epoch": 0.44, "grad_norm": 0.1748046875, "learning_rate": 6.814639730951532e-05, "loss": 2.166, "step": 1310 }, { "epoch": 0.45, "grad_norm": 0.1669921875, "learning_rate": 6.787053656178087e-05, "loss": 2.1783, "step": 1315 }, { "epoch": 0.45, "grad_norm": 0.16796875, "learning_rate": 6.759405075659166e-05, "loss": 2.2017, "step": 1320 }, { "epoch": 0.45, "grad_norm": 0.1650390625, "learning_rate": 6.731694956458701e-05, "loss": 2.1601, "step": 1325 }, { "epoch": 0.45, "grad_norm": 0.173828125, "learning_rate": 6.703924267793061e-05, "loss": 2.1962, "step": 1330 }, { "epoch": 0.45, "grad_norm": 0.162109375, "learning_rate": 6.676093980997155e-05, "loss": 2.1764, "step": 1335 }, { "epoch": 0.45, "grad_norm": 0.1689453125, "learning_rate": 6.648205069490451e-05, "loss": 2.2019, "step": 1340 }, { "epoch": 0.46, "grad_norm": 0.1708984375, "learning_rate": 6.620258508742935e-05, "loss": 2.205, "step": 1345 }, { "epoch": 0.46, "grad_norm": 0.16796875, "learning_rate": 6.592255276240994e-05, "loss": 2.162, "step": 1350 }, { "epoch": 0.46, "grad_norm": 0.16796875, "learning_rate": 6.564196351453209e-05, "loss": 2.1992, "step": 1355 }, { "epoch": 0.46, "grad_norm": 0.1669921875, "learning_rate": 6.536082715796125e-05, "loss": 2.1835, "step": 1360 }, { "epoch": 0.46, "grad_norm": 0.16796875, "learning_rate": 6.507915352599895e-05, "loss": 2.1851, "step": 1365 }, { "epoch": 0.46, "grad_norm": 0.1650390625, "learning_rate": 6.479695247073907e-05, "loss": 2.2148, "step": 1370 }, { "epoch": 0.47, "grad_norm": 0.1630859375, "learning_rate": 6.451423386272312e-05, "loss": 2.1823, "step": 1375 }, { "epoch": 0.47, "grad_norm": 0.1689453125, "learning_rate": 6.423100759059509e-05, "loss": 2.1676, "step": 1380 }, { "epoch": 0.47, "grad_norm": 0.1669921875, "learning_rate": 6.394728356075551e-05, "loss": 2.1841, "step": 1385 }, { "epoch": 0.47, "grad_norm": 0.1728515625, "learning_rate": 6.366307169701496e-05, "loss": 2.1638, "step": 1390 }, { "epoch": 0.47, "grad_norm": 0.162109375, "learning_rate": 6.337838194024697e-05, "loss": 2.1984, "step": 1395 }, { "epoch": 0.47, "grad_norm": 0.1650390625, "learning_rate": 6.309322424804034e-05, "loss": 2.1869, "step": 1400 }, { "epoch": 0.48, "grad_norm": 0.166015625, "learning_rate": 6.280760859435087e-05, "loss": 2.1684, "step": 1405 }, { "epoch": 0.48, "grad_norm": 0.1689453125, "learning_rate": 6.252154496915244e-05, "loss": 2.1879, "step": 1410 }, { "epoch": 0.48, "grad_norm": 0.1708984375, "learning_rate": 6.223504337808761e-05, "loss": 2.1625, "step": 1415 }, { "epoch": 0.48, "grad_norm": 0.1640625, "learning_rate": 6.194811384211768e-05, "loss": 2.1731, "step": 1420 }, { "epoch": 0.48, "grad_norm": 0.1630859375, "learning_rate": 6.166076639717218e-05, "loss": 2.1673, "step": 1425 }, { "epoch": 0.48, "grad_norm": 0.1708984375, "learning_rate": 6.137301109379783e-05, "loss": 2.1944, "step": 1430 }, { "epoch": 0.49, "grad_norm": 0.169921875, "learning_rate": 6.108485799680701e-05, "loss": 2.1989, "step": 1435 }, { "epoch": 0.49, "grad_norm": 0.166015625, "learning_rate": 6.079631718492569e-05, "loss": 2.163, "step": 1440 }, { "epoch": 0.49, "grad_norm": 0.1708984375, "learning_rate": 6.050739875044098e-05, "loss": 2.1824, "step": 1445 }, { "epoch": 0.49, "grad_norm": 0.1650390625, "learning_rate": 6.021811279884807e-05, "loss": 2.193, "step": 1450 }, { "epoch": 0.49, "grad_norm": 0.169921875, "learning_rate": 5.992846944849679e-05, "loss": 2.196, "step": 1455 }, { "epoch": 0.49, "grad_norm": 0.16796875, "learning_rate": 5.96384788302377e-05, "loss": 2.1575, "step": 1460 }, { "epoch": 0.5, "grad_norm": 0.17578125, "learning_rate": 5.934815108706775e-05, "loss": 2.2159, "step": 1465 }, { "epoch": 0.5, "grad_norm": 0.169921875, "learning_rate": 5.905749637377549e-05, "loss": 2.1838, "step": 1470 }, { "epoch": 0.5, "grad_norm": 0.1689453125, "learning_rate": 5.87665248565859e-05, "loss": 2.2138, "step": 1475 }, { "epoch": 0.5, "grad_norm": 0.1708984375, "learning_rate": 5.847524671280484e-05, "loss": 2.1744, "step": 1480 }, { "epoch": 0.5, "grad_norm": 0.1630859375, "learning_rate": 5.818367213046298e-05, "loss": 2.1914, "step": 1485 }, { "epoch": 0.5, "grad_norm": 0.1669921875, "learning_rate": 5.7891811307959574e-05, "loss": 2.1712, "step": 1490 }, { "epoch": 0.51, "grad_norm": 0.16796875, "learning_rate": 5.759967445370564e-05, "loss": 2.161, "step": 1495 }, { "epoch": 0.51, "grad_norm": 0.1689453125, "learning_rate": 5.7307271785767034e-05, "loss": 2.1811, "step": 1500 }, { "epoch": 0.51, "grad_norm": 0.1728515625, "learning_rate": 5.701461353150687e-05, "loss": 2.1932, "step": 1505 }, { "epoch": 0.51, "grad_norm": 0.1650390625, "learning_rate": 5.6721709927227974e-05, "loss": 2.1521, "step": 1510 }, { "epoch": 0.51, "grad_norm": 0.1640625, "learning_rate": 5.642857121781475e-05, "loss": 2.1954, "step": 1515 }, { "epoch": 0.51, "grad_norm": 0.1708984375, "learning_rate": 5.613520765637489e-05, "loss": 2.169, "step": 1520 }, { "epoch": 0.52, "grad_norm": 0.16796875, "learning_rate": 5.58416295038807e-05, "loss": 2.2079, "step": 1525 }, { "epoch": 0.52, "grad_norm": 0.16796875, "learning_rate": 5.554784702881025e-05, "loss": 2.1636, "step": 1530 }, { "epoch": 0.52, "grad_norm": 0.1669921875, "learning_rate": 5.525387050678819e-05, "loss": 2.1689, "step": 1535 }, { "epoch": 0.52, "grad_norm": 0.1728515625, "learning_rate": 5.495971022022638e-05, "loss": 2.179, "step": 1540 }, { "epoch": 0.52, "grad_norm": 0.166015625, "learning_rate": 5.466537645796416e-05, "loss": 2.195, "step": 1545 }, { "epoch": 0.53, "grad_norm": 0.169921875, "learning_rate": 5.437087951490856e-05, "loss": 2.1827, "step": 1550 }, { "epoch": 0.53, "grad_norm": 0.1787109375, "learning_rate": 5.4076229691674164e-05, "loss": 2.1747, "step": 1555 }, { "epoch": 0.53, "grad_norm": 0.1689453125, "learning_rate": 5.3781437294222845e-05, "loss": 2.179, "step": 1560 }, { "epoch": 0.53, "grad_norm": 0.169921875, "learning_rate": 5.3486512633503303e-05, "loss": 2.219, "step": 1565 }, { "epoch": 0.53, "grad_norm": 0.1767578125, "learning_rate": 5.319146602509042e-05, "loss": 2.198, "step": 1570 }, { "epoch": 0.53, "grad_norm": 0.1728515625, "learning_rate": 5.289630778882442e-05, "loss": 2.1706, "step": 1575 }, { "epoch": 0.54, "grad_norm": 0.171875, "learning_rate": 5.260104824844989e-05, "loss": 2.1725, "step": 1580 }, { "epoch": 0.54, "grad_norm": 0.171875, "learning_rate": 5.230569773125484e-05, "loss": 2.1811, "step": 1585 }, { "epoch": 0.54, "grad_norm": 0.1728515625, "learning_rate": 5.201026656770926e-05, "loss": 2.1745, "step": 1590 }, { "epoch": 0.54, "grad_norm": 0.171875, "learning_rate": 5.1714765091104003e-05, "loss": 2.1982, "step": 1595 }, { "epoch": 0.54, "grad_norm": 0.1640625, "learning_rate": 5.141920363718916e-05, "loss": 2.1957, "step": 1600 }, { "epoch": 0.54, "grad_norm": 0.173828125, "learning_rate": 5.1123592543812734e-05, "loss": 2.1758, "step": 1605 }, { "epoch": 0.55, "grad_norm": 0.16796875, "learning_rate": 5.082794215055894e-05, "loss": 2.1576, "step": 1610 }, { "epoch": 0.55, "grad_norm": 0.16796875, "learning_rate": 5.0532262798386544e-05, "loss": 2.1923, "step": 1615 }, { "epoch": 0.55, "grad_norm": 0.173828125, "learning_rate": 5.023656482926727e-05, "loss": 2.1893, "step": 1620 }, { "epoch": 0.55, "grad_norm": 0.166015625, "learning_rate": 4.994085858582397e-05, "loss": 2.163, "step": 1625 }, { "epoch": 0.55, "grad_norm": 0.169921875, "learning_rate": 4.964515441096889e-05, "loss": 2.1753, "step": 1630 }, { "epoch": 0.55, "grad_norm": 0.16796875, "learning_rate": 4.934946264754199e-05, "loss": 2.1831, "step": 1635 }, { "epoch": 0.56, "grad_norm": 0.16796875, "learning_rate": 4.9053793637949067e-05, "loss": 2.1525, "step": 1640 }, { "epoch": 0.56, "grad_norm": 0.1728515625, "learning_rate": 4.875815772380002e-05, "loss": 2.1687, "step": 1645 }, { "epoch": 0.56, "grad_norm": 0.1640625, "learning_rate": 4.846256524554725e-05, "loss": 2.1775, "step": 1650 }, { "epoch": 0.56, "grad_norm": 0.1689453125, "learning_rate": 4.8167026542123874e-05, "loss": 2.1846, "step": 1655 }, { "epoch": 0.56, "grad_norm": 0.16796875, "learning_rate": 4.78715519505821e-05, "loss": 2.1507, "step": 1660 }, { "epoch": 0.56, "grad_norm": 0.173828125, "learning_rate": 4.7576151805731695e-05, "loss": 2.2013, "step": 1665 }, { "epoch": 0.57, "grad_norm": 0.1669921875, "learning_rate": 4.728083643977855e-05, "loss": 2.1392, "step": 1670 }, { "epoch": 0.57, "grad_norm": 0.1708984375, "learning_rate": 4.698561618196323e-05, "loss": 2.184, "step": 1675 }, { "epoch": 0.57, "grad_norm": 0.162109375, "learning_rate": 4.669050135819966e-05, "loss": 2.1987, "step": 1680 }, { "epoch": 0.57, "grad_norm": 0.16796875, "learning_rate": 4.639550229071407e-05, "loss": 2.1599, "step": 1685 }, { "epoch": 0.57, "grad_norm": 0.171875, "learning_rate": 4.610062929768383e-05, "loss": 2.1722, "step": 1690 }, { "epoch": 0.57, "grad_norm": 0.1689453125, "learning_rate": 4.580589269287661e-05, "loss": 2.1756, "step": 1695 }, { "epoch": 0.58, "grad_norm": 0.1689453125, "learning_rate": 4.5511302785289685e-05, "loss": 2.1929, "step": 1700 }, { "epoch": 0.58, "grad_norm": 0.171875, "learning_rate": 4.521686987878925e-05, "loss": 2.1731, "step": 1705 }, { "epoch": 0.58, "grad_norm": 0.16796875, "learning_rate": 4.492260427175007e-05, "loss": 2.182, "step": 1710 }, { "epoch": 0.58, "grad_norm": 0.1728515625, "learning_rate": 4.4628516256695305e-05, "loss": 2.1768, "step": 1715 }, { "epoch": 0.58, "grad_norm": 0.171875, "learning_rate": 4.433461611993651e-05, "loss": 2.162, "step": 1720 }, { "epoch": 0.58, "grad_norm": 0.1728515625, "learning_rate": 4.4040914141213774e-05, "loss": 2.1815, "step": 1725 }, { "epoch": 0.59, "grad_norm": 0.177734375, "learning_rate": 4.374742059333621e-05, "loss": 2.1603, "step": 1730 }, { "epoch": 0.59, "grad_norm": 0.1650390625, "learning_rate": 4.345414574182272e-05, "loss": 2.1844, "step": 1735 }, { "epoch": 0.59, "grad_norm": 0.1708984375, "learning_rate": 4.316109984454278e-05, "loss": 2.1923, "step": 1740 }, { "epoch": 0.59, "grad_norm": 0.1669921875, "learning_rate": 4.2868293151357806e-05, "loss": 2.2025, "step": 1745 }, { "epoch": 0.59, "grad_norm": 0.1767578125, "learning_rate": 4.2575735903762513e-05, "loss": 2.1585, "step": 1750 }, { "epoch": 0.59, "grad_norm": 0.1669921875, "learning_rate": 4.228343833452684e-05, "loss": 2.1745, "step": 1755 }, { "epoch": 0.6, "grad_norm": 0.16796875, "learning_rate": 4.1991410667337896e-05, "loss": 2.2175, "step": 1760 }, { "epoch": 0.6, "grad_norm": 0.169921875, "learning_rate": 4.1699663116442434e-05, "loss": 2.1835, "step": 1765 }, { "epoch": 0.6, "grad_norm": 0.1650390625, "learning_rate": 4.140820588628964e-05, "loss": 2.1859, "step": 1770 }, { "epoch": 0.6, "grad_norm": 0.173828125, "learning_rate": 4.1117049171174104e-05, "loss": 2.1912, "step": 1775 }, { "epoch": 0.6, "grad_norm": 0.173828125, "learning_rate": 4.082620315487931e-05, "loss": 2.1961, "step": 1780 }, { "epoch": 0.6, "grad_norm": 0.1728515625, "learning_rate": 4.053567801032144e-05, "loss": 2.1623, "step": 1785 }, { "epoch": 0.61, "grad_norm": 0.1728515625, "learning_rate": 4.0245483899193595e-05, "loss": 2.1723, "step": 1790 }, { "epoch": 0.61, "grad_norm": 0.16796875, "learning_rate": 3.995563097161026e-05, "loss": 2.1777, "step": 1795 }, { "epoch": 0.61, "grad_norm": 0.169921875, "learning_rate": 3.966612936575235e-05, "loss": 2.1937, "step": 1800 }, { "epoch": 0.61, "grad_norm": 0.171875, "learning_rate": 3.937698920751268e-05, "loss": 2.184, "step": 1805 }, { "epoch": 0.61, "grad_norm": 0.1748046875, "learning_rate": 3.9088220610141655e-05, "loss": 2.181, "step": 1810 }, { "epoch": 0.61, "grad_norm": 0.166015625, "learning_rate": 3.87998336738936e-05, "loss": 2.1893, "step": 1815 }, { "epoch": 0.62, "grad_norm": 0.17578125, "learning_rate": 3.851183848567351e-05, "loss": 2.175, "step": 1820 }, { "epoch": 0.62, "grad_norm": 0.16796875, "learning_rate": 3.822424511868421e-05, "loss": 2.1897, "step": 1825 }, { "epoch": 0.62, "grad_norm": 0.171875, "learning_rate": 3.7937063632074036e-05, "loss": 2.16, "step": 1830 }, { "epoch": 0.62, "grad_norm": 0.169921875, "learning_rate": 3.7650304070584955e-05, "loss": 2.1899, "step": 1835 }, { "epoch": 0.62, "grad_norm": 0.1708984375, "learning_rate": 3.736397646420135e-05, "loss": 2.1879, "step": 1840 }, { "epoch": 0.62, "grad_norm": 0.171875, "learning_rate": 3.7078090827799e-05, "loss": 2.1832, "step": 1845 }, { "epoch": 0.63, "grad_norm": 0.1708984375, "learning_rate": 3.679265716079501e-05, "loss": 2.1894, "step": 1850 }, { "epoch": 0.63, "grad_norm": 0.166015625, "learning_rate": 3.650768544679788e-05, "loss": 2.1831, "step": 1855 }, { "epoch": 0.63, "grad_norm": 0.1708984375, "learning_rate": 3.622318565325847e-05, "loss": 2.1538, "step": 1860 }, { "epoch": 0.63, "grad_norm": 0.173828125, "learning_rate": 3.593916773112122e-05, "loss": 2.1717, "step": 1865 }, { "epoch": 0.63, "grad_norm": 0.1767578125, "learning_rate": 3.565564161447617e-05, "loss": 2.187, "step": 1870 }, { "epoch": 0.64, "grad_norm": 0.173828125, "learning_rate": 3.5372617220211525e-05, "loss": 2.1609, "step": 1875 }, { "epoch": 0.64, "grad_norm": 0.1767578125, "learning_rate": 3.509010444766674e-05, "loss": 2.1721, "step": 1880 }, { "epoch": 0.64, "grad_norm": 0.1650390625, "learning_rate": 3.480811317828625e-05, "loss": 2.162, "step": 1885 }, { "epoch": 0.64, "grad_norm": 0.1708984375, "learning_rate": 3.452665327527391e-05, "loss": 2.202, "step": 1890 }, { "epoch": 0.64, "grad_norm": 0.16796875, "learning_rate": 3.4245734583248e-05, "loss": 2.1657, "step": 1895 }, { "epoch": 0.64, "grad_norm": 0.1669921875, "learning_rate": 3.3965366927896864e-05, "loss": 2.1612, "step": 1900 }, { "epoch": 0.65, "grad_norm": 0.1708984375, "learning_rate": 3.3685560115635195e-05, "loss": 2.1608, "step": 1905 }, { "epoch": 0.65, "grad_norm": 0.1669921875, "learning_rate": 3.340632393326118e-05, "loss": 2.1767, "step": 1910 }, { "epoch": 0.65, "grad_norm": 0.1748046875, "learning_rate": 3.3127668147614e-05, "loss": 2.1851, "step": 1915 }, { "epoch": 0.65, "grad_norm": 0.1728515625, "learning_rate": 3.284960250523237e-05, "loss": 2.1778, "step": 1920 }, { "epoch": 0.65, "grad_norm": 0.1689453125, "learning_rate": 3.2572136732013555e-05, "loss": 2.1723, "step": 1925 }, { "epoch": 0.65, "grad_norm": 0.1728515625, "learning_rate": 3.2295280532873226e-05, "loss": 2.1986, "step": 1930 }, { "epoch": 0.66, "grad_norm": 0.1669921875, "learning_rate": 3.2019043591405936e-05, "loss": 2.1746, "step": 1935 }, { "epoch": 0.66, "grad_norm": 0.1748046875, "learning_rate": 3.174343556954652e-05, "loss": 2.1711, "step": 1940 }, { "epoch": 0.66, "grad_norm": 0.169921875, "learning_rate": 3.146846610723212e-05, "loss": 2.1924, "step": 1945 }, { "epoch": 0.66, "grad_norm": 0.171875, "learning_rate": 3.1194144822064944e-05, "loss": 2.2043, "step": 1950 }, { "epoch": 0.66, "grad_norm": 0.1630859375, "learning_rate": 3.0920481308975926e-05, "loss": 2.1798, "step": 1955 }, { "epoch": 0.66, "grad_norm": 0.173828125, "learning_rate": 3.0647485139889145e-05, "loss": 2.1784, "step": 1960 }, { "epoch": 0.67, "grad_norm": 0.1826171875, "learning_rate": 3.037516586338699e-05, "loss": 2.2003, "step": 1965 }, { "epoch": 0.67, "grad_norm": 0.1689453125, "learning_rate": 3.0103533004376183e-05, "loss": 2.2178, "step": 1970 }, { "epoch": 0.67, "grad_norm": 0.173828125, "learning_rate": 2.9832596063754613e-05, "loss": 2.1773, "step": 1975 }, { "epoch": 0.67, "grad_norm": 0.166015625, "learning_rate": 2.9562364518079105e-05, "loss": 2.2017, "step": 1980 }, { "epoch": 0.67, "grad_norm": 0.1748046875, "learning_rate": 2.929284781923382e-05, "loss": 2.1396, "step": 1985 }, { "epoch": 0.67, "grad_norm": 0.171875, "learning_rate": 2.902405539409978e-05, "loss": 2.1828, "step": 1990 }, { "epoch": 0.68, "grad_norm": 0.1748046875, "learning_rate": 2.8755996644225097e-05, "loss": 2.1618, "step": 1995 }, { "epoch": 0.68, "grad_norm": 0.1728515625, "learning_rate": 2.848868094549615e-05, "loss": 2.1648, "step": 2000 }, { "epoch": 0.68, "grad_norm": 0.1708984375, "learning_rate": 2.8222117647809553e-05, "loss": 2.1717, "step": 2005 }, { "epoch": 0.68, "grad_norm": 0.16796875, "learning_rate": 2.7956316074745293e-05, "loss": 2.1584, "step": 2010 }, { "epoch": 0.68, "grad_norm": 0.16796875, "learning_rate": 2.7691285523240474e-05, "loss": 2.1671, "step": 2015 }, { "epoch": 0.68, "grad_norm": 0.1728515625, "learning_rate": 2.7427035263264222e-05, "loss": 2.1939, "step": 2020 }, { "epoch": 0.69, "grad_norm": 0.171875, "learning_rate": 2.7163574537493407e-05, "loss": 2.158, "step": 2025 }, { "epoch": 0.69, "grad_norm": 0.1748046875, "learning_rate": 2.690091256098936e-05, "loss": 2.1482, "step": 2030 }, { "epoch": 0.69, "grad_norm": 0.1767578125, "learning_rate": 2.6639058520875615e-05, "loss": 2.1577, "step": 2035 }, { "epoch": 0.69, "grad_norm": 0.1689453125, "learning_rate": 2.6378021576016466e-05, "loss": 2.1594, "step": 2040 }, { "epoch": 0.69, "grad_norm": 0.169921875, "learning_rate": 2.6117810856696702e-05, "loss": 2.194, "step": 2045 }, { "epoch": 0.69, "grad_norm": 0.181640625, "learning_rate": 2.5858435464302315e-05, "loss": 2.1481, "step": 2050 }, { "epoch": 0.7, "grad_norm": 0.1748046875, "learning_rate": 2.559990447100195e-05, "loss": 2.1835, "step": 2055 }, { "epoch": 0.7, "grad_norm": 0.169921875, "learning_rate": 2.5342226919429806e-05, "loss": 2.1606, "step": 2060 }, { "epoch": 0.7, "grad_norm": 0.1689453125, "learning_rate": 2.5085411822369244e-05, "loss": 2.1763, "step": 2065 }, { "epoch": 0.7, "grad_norm": 0.1708984375, "learning_rate": 2.4829468162437554e-05, "loss": 2.1724, "step": 2070 }, { "epoch": 0.7, "grad_norm": 0.1689453125, "learning_rate": 2.4574404891771826e-05, "loss": 2.1815, "step": 2075 }, { "epoch": 0.7, "grad_norm": 0.166015625, "learning_rate": 2.43202309317157e-05, "loss": 2.1717, "step": 2080 }, { "epoch": 0.71, "grad_norm": 0.1728515625, "learning_rate": 2.406695517250753e-05, "loss": 2.1995, "step": 2085 }, { "epoch": 0.71, "grad_norm": 0.173828125, "learning_rate": 2.381458647296925e-05, "loss": 2.1933, "step": 2090 }, { "epoch": 0.71, "grad_norm": 0.17578125, "learning_rate": 2.3563133660196556e-05, "loss": 2.1821, "step": 2095 }, { "epoch": 0.71, "grad_norm": 0.1689453125, "learning_rate": 2.3312605529250276e-05, "loss": 2.1763, "step": 2100 }, { "epoch": 0.71, "grad_norm": 0.169921875, "learning_rate": 2.3063010842848564e-05, "loss": 2.1838, "step": 2105 }, { "epoch": 0.71, "grad_norm": 0.16796875, "learning_rate": 2.2814358331060532e-05, "loss": 2.1895, "step": 2110 }, { "epoch": 0.72, "grad_norm": 0.1708984375, "learning_rate": 2.2566656691000932e-05, "loss": 2.1926, "step": 2115 }, { "epoch": 0.72, "grad_norm": 0.171875, "learning_rate": 2.2319914586525777e-05, "loss": 2.19, "step": 2120 }, { "epoch": 0.72, "grad_norm": 0.1669921875, "learning_rate": 2.2074140647929503e-05, "loss": 2.1611, "step": 2125 }, { "epoch": 0.72, "grad_norm": 0.171875, "learning_rate": 2.1829343471642994e-05, "loss": 2.1936, "step": 2130 }, { "epoch": 0.72, "grad_norm": 0.169921875, "learning_rate": 2.158553161993294e-05, "loss": 2.1815, "step": 2135 }, { "epoch": 0.72, "grad_norm": 0.16796875, "learning_rate": 2.134271362060238e-05, "loss": 2.1871, "step": 2140 }, { "epoch": 0.73, "grad_norm": 0.1728515625, "learning_rate": 2.1100897966692297e-05, "loss": 2.1642, "step": 2145 }, { "epoch": 0.73, "grad_norm": 0.1728515625, "learning_rate": 2.0860093116184797e-05, "loss": 2.1861, "step": 2150 }, { "epoch": 0.73, "grad_norm": 0.1689453125, "learning_rate": 2.0620307491707012e-05, "loss": 2.1904, "step": 2155 }, { "epoch": 0.73, "grad_norm": 0.1796875, "learning_rate": 2.0381549480236685e-05, "loss": 2.1855, "step": 2160 }, { "epoch": 0.73, "grad_norm": 0.1650390625, "learning_rate": 2.0143827432808743e-05, "loss": 2.1886, "step": 2165 }, { "epoch": 0.74, "grad_norm": 0.1669921875, "learning_rate": 1.990714966422321e-05, "loss": 2.1681, "step": 2170 }, { "epoch": 0.74, "grad_norm": 0.1767578125, "learning_rate": 1.9671524452754393e-05, "loss": 2.1596, "step": 2175 }, { "epoch": 0.74, "grad_norm": 0.1708984375, "learning_rate": 1.9436960039861324e-05, "loss": 2.1709, "step": 2180 }, { "epoch": 0.74, "grad_norm": 0.17578125, "learning_rate": 1.9203464629899502e-05, "loss": 2.1794, "step": 2185 }, { "epoch": 0.74, "grad_norm": 0.1748046875, "learning_rate": 1.8971046389833952e-05, "loss": 2.1867, "step": 2190 }, { "epoch": 0.74, "grad_norm": 0.173828125, "learning_rate": 1.873971344895347e-05, "loss": 2.1681, "step": 2195 }, { "epoch": 0.75, "grad_norm": 0.173828125, "learning_rate": 1.850947389858643e-05, "loss": 2.1587, "step": 2200 }, { "epoch": 0.75, "grad_norm": 0.1689453125, "learning_rate": 1.8280335791817733e-05, "loss": 2.1862, "step": 2205 }, { "epoch": 0.75, "grad_norm": 0.1767578125, "learning_rate": 1.805230714320701e-05, "loss": 2.1756, "step": 2210 }, { "epoch": 0.75, "grad_norm": 0.169921875, "learning_rate": 1.7825395928508447e-05, "loss": 2.1792, "step": 2215 }, { "epoch": 0.75, "grad_norm": 0.171875, "learning_rate": 1.7599610084391784e-05, "loss": 2.1885, "step": 2220 }, { "epoch": 0.75, "grad_norm": 0.17578125, "learning_rate": 1.737495750816464e-05, "loss": 2.1602, "step": 2225 }, { "epoch": 0.76, "grad_norm": 0.173828125, "learning_rate": 1.7151446057496406e-05, "loss": 2.1823, "step": 2230 }, { "epoch": 0.76, "grad_norm": 0.1748046875, "learning_rate": 1.6929083550143255e-05, "loss": 2.1806, "step": 2235 }, { "epoch": 0.76, "grad_norm": 0.17578125, "learning_rate": 1.670787776367489e-05, "loss": 2.1781, "step": 2240 }, { "epoch": 0.76, "grad_norm": 0.173828125, "learning_rate": 1.6487836435202357e-05, "loss": 2.1545, "step": 2245 }, { "epoch": 0.76, "grad_norm": 0.17578125, "learning_rate": 1.6268967261107426e-05, "loss": 2.1559, "step": 2250 }, { "epoch": 0.76, "grad_norm": 0.1689453125, "learning_rate": 1.6051277896773565e-05, "loss": 2.1705, "step": 2255 }, { "epoch": 0.77, "grad_norm": 0.177734375, "learning_rate": 1.583477595631794e-05, "loss": 2.1662, "step": 2260 }, { "epoch": 0.77, "grad_norm": 0.16796875, "learning_rate": 1.5619469012325255e-05, "loss": 2.171, "step": 2265 }, { "epoch": 0.77, "grad_norm": 0.177734375, "learning_rate": 1.540536459558286e-05, "loss": 2.1957, "step": 2270 }, { "epoch": 0.77, "grad_norm": 0.169921875, "learning_rate": 1.519247019481731e-05, "loss": 2.1696, "step": 2275 }, { "epoch": 0.77, "grad_norm": 0.16796875, "learning_rate": 1.4980793256432474e-05, "loss": 2.1624, "step": 2280 }, { "epoch": 0.77, "grad_norm": 0.173828125, "learning_rate": 1.4770341184248997e-05, "loss": 2.162, "step": 2285 }, { "epoch": 0.78, "grad_norm": 0.169921875, "learning_rate": 1.4561121339245487e-05, "loss": 2.2188, "step": 2290 }, { "epoch": 0.78, "grad_norm": 0.1689453125, "learning_rate": 1.4353141039300921e-05, "loss": 2.1537, "step": 2295 }, { "epoch": 0.78, "grad_norm": 0.1728515625, "learning_rate": 1.4146407558938695e-05, "loss": 2.1682, "step": 2300 }, { "epoch": 0.78, "grad_norm": 0.1708984375, "learning_rate": 1.3940928129072279e-05, "loss": 2.1791, "step": 2305 }, { "epoch": 0.78, "grad_norm": 0.171875, "learning_rate": 1.3736709936752196e-05, "loss": 2.2001, "step": 2310 }, { "epoch": 0.78, "grad_norm": 0.1728515625, "learning_rate": 1.3533760124914713e-05, "loss": 2.1718, "step": 2315 }, { "epoch": 0.79, "grad_norm": 0.1728515625, "learning_rate": 1.3332085792131966e-05, "loss": 2.1829, "step": 2320 }, { "epoch": 0.79, "grad_norm": 0.171875, "learning_rate": 1.3131693992363664e-05, "loss": 2.17, "step": 2325 }, { "epoch": 0.79, "grad_norm": 0.171875, "learning_rate": 1.293259173471041e-05, "loss": 2.1583, "step": 2330 }, { "epoch": 0.79, "grad_norm": 0.1689453125, "learning_rate": 1.2734785983168485e-05, "loss": 2.1606, "step": 2335 }, { "epoch": 0.79, "grad_norm": 0.1748046875, "learning_rate": 1.2538283656386319e-05, "loss": 2.1793, "step": 2340 }, { "epoch": 0.79, "grad_norm": 0.171875, "learning_rate": 1.2343091627422487e-05, "loss": 2.1768, "step": 2345 }, { "epoch": 0.8, "grad_norm": 0.1669921875, "learning_rate": 1.2149216723505246e-05, "loss": 2.1973, "step": 2350 }, { "epoch": 0.8, "grad_norm": 0.1708984375, "learning_rate": 1.1956665725793831e-05, "loss": 2.1827, "step": 2355 }, { "epoch": 0.8, "grad_norm": 0.171875, "learning_rate": 1.1765445369141276e-05, "loss": 2.174, "step": 2360 }, { "epoch": 0.8, "grad_norm": 0.1728515625, "learning_rate": 1.1575562341858709e-05, "loss": 2.1979, "step": 2365 }, { "epoch": 0.8, "grad_norm": 0.18359375, "learning_rate": 1.1387023285481575e-05, "loss": 2.1689, "step": 2370 }, { "epoch": 0.8, "grad_norm": 0.177734375, "learning_rate": 1.1199834794537263e-05, "loss": 2.2038, "step": 2375 }, { "epoch": 0.81, "grad_norm": 0.1689453125, "learning_rate": 1.1014003416314439e-05, "loss": 2.1569, "step": 2380 }, { "epoch": 0.81, "grad_norm": 0.1767578125, "learning_rate": 1.0829535650634104e-05, "loss": 2.1832, "step": 2385 }, { "epoch": 0.81, "grad_norm": 0.1748046875, "learning_rate": 1.0646437949622118e-05, "loss": 2.2037, "step": 2390 }, { "epoch": 0.81, "grad_norm": 0.1748046875, "learning_rate": 1.0464716717483736e-05, "loss": 2.1605, "step": 2395 }, { "epoch": 0.81, "grad_norm": 0.1728515625, "learning_rate": 1.0284378310279369e-05, "loss": 2.1733, "step": 2400 }, { "epoch": 0.81, "grad_norm": 0.171875, "learning_rate": 1.0105429035702441e-05, "loss": 2.1641, "step": 2405 }, { "epoch": 0.82, "grad_norm": 0.1748046875, "learning_rate": 9.927875152858729e-06, "loss": 2.1786, "step": 2410 }, { "epoch": 0.82, "grad_norm": 0.1728515625, "learning_rate": 9.751722872047353e-06, "loss": 2.1697, "step": 2415 }, { "epoch": 0.82, "grad_norm": 0.169921875, "learning_rate": 9.57697835454367e-06, "loss": 2.1725, "step": 2420 }, { "epoch": 0.82, "grad_norm": 0.16796875, "learning_rate": 9.403647712383712e-06, "loss": 2.1869, "step": 2425 }, { "epoch": 0.82, "grad_norm": 0.173828125, "learning_rate": 9.231737008150415e-06, "loss": 2.1992, "step": 2430 }, { "epoch": 0.82, "grad_norm": 0.171875, "learning_rate": 9.061252254761576e-06, "loss": 2.1953, "step": 2435 }, { "epoch": 0.83, "grad_norm": 0.177734375, "learning_rate": 8.8921994152595e-06, "loss": 2.196, "step": 2440 }, { "epoch": 0.83, "grad_norm": 0.1787109375, "learning_rate": 8.724584402602521e-06, "loss": 2.1629, "step": 2445 }, { "epoch": 0.83, "grad_norm": 0.1748046875, "learning_rate": 8.558413079458106e-06, "loss": 2.159, "step": 2450 }, { "epoch": 0.83, "grad_norm": 0.1767578125, "learning_rate": 8.393691257997782e-06, "loss": 2.1791, "step": 2455 }, { "epoch": 0.83, "grad_norm": 0.1728515625, "learning_rate": 8.230424699693923e-06, "loss": 2.1723, "step": 2460 }, { "epoch": 0.83, "grad_norm": 0.171875, "learning_rate": 8.068619115118176e-06, "loss": 2.1735, "step": 2465 }, { "epoch": 0.84, "grad_norm": 0.173828125, "learning_rate": 7.908280163741732e-06, "loss": 2.1856, "step": 2470 }, { "epoch": 0.84, "grad_norm": 0.1728515625, "learning_rate": 7.749413453737375e-06, "loss": 2.1971, "step": 2475 }, { "epoch": 0.84, "grad_norm": 0.169921875, "learning_rate": 7.592024541783343e-06, "loss": 2.1577, "step": 2480 }, { "epoch": 0.84, "grad_norm": 0.173828125, "learning_rate": 7.43611893286893e-06, "loss": 2.1727, "step": 2485 }, { "epoch": 0.84, "grad_norm": 0.1708984375, "learning_rate": 7.281702080102004e-06, "loss": 2.1791, "step": 2490 }, { "epoch": 0.85, "grad_norm": 0.1708984375, "learning_rate": 7.128779384518164e-06, "loss": 2.139, "step": 2495 }, { "epoch": 0.85, "grad_norm": 0.1708984375, "learning_rate": 6.977356194891998e-06, "loss": 2.1698, "step": 2500 }, { "epoch": 0.85, "grad_norm": 0.173828125, "learning_rate": 6.827437807549814e-06, "loss": 2.1472, "step": 2505 }, { "epoch": 0.85, "grad_norm": 0.1767578125, "learning_rate": 6.679029466184506e-06, "loss": 2.198, "step": 2510 }, { "epoch": 0.85, "grad_norm": 0.1728515625, "learning_rate": 6.5321363616721306e-06, "loss": 2.1632, "step": 2515 }, { "epoch": 0.85, "grad_norm": 0.17578125, "learning_rate": 6.386763631890313e-06, "loss": 2.1649, "step": 2520 }, { "epoch": 0.86, "grad_norm": 0.1728515625, "learning_rate": 6.242916361538559e-06, "loss": 2.1872, "step": 2525 }, { "epoch": 0.86, "grad_norm": 0.16796875, "learning_rate": 6.100599581960415e-06, "loss": 2.1755, "step": 2530 }, { "epoch": 0.86, "grad_norm": 0.1708984375, "learning_rate": 5.9598182709674655e-06, "loss": 2.1657, "step": 2535 }, { "epoch": 0.86, "grad_norm": 0.171875, "learning_rate": 5.820577352665252e-06, "loss": 2.1639, "step": 2540 }, { "epoch": 0.86, "grad_norm": 0.1689453125, "learning_rate": 5.682881697280984e-06, "loss": 2.185, "step": 2545 }, { "epoch": 0.86, "grad_norm": 0.1669921875, "learning_rate": 5.546736120993318e-06, "loss": 2.1609, "step": 2550 }, { "epoch": 0.87, "grad_norm": 0.16796875, "learning_rate": 5.412145385763728e-06, "loss": 2.1895, "step": 2555 }, { "epoch": 0.87, "grad_norm": 0.1708984375, "learning_rate": 5.279114199170093e-06, "loss": 2.1446, "step": 2560 }, { "epoch": 0.87, "grad_norm": 0.173828125, "learning_rate": 5.1476472142419965e-06, "loss": 2.156, "step": 2565 }, { "epoch": 0.87, "grad_norm": 0.171875, "learning_rate": 5.017749029297919e-06, "loss": 2.1997, "step": 2570 }, { "epoch": 0.87, "grad_norm": 0.1708984375, "learning_rate": 4.889424187784486e-06, "loss": 2.1674, "step": 2575 }, { "epoch": 0.87, "grad_norm": 0.1748046875, "learning_rate": 4.762677178117503e-06, "loss": 2.1792, "step": 2580 }, { "epoch": 0.88, "grad_norm": 0.17578125, "learning_rate": 4.637512433524987e-06, "loss": 2.1648, "step": 2585 }, { "epoch": 0.88, "grad_norm": 0.1650390625, "learning_rate": 4.5139343318920945e-06, "loss": 2.1833, "step": 2590 }, { "epoch": 0.88, "grad_norm": 0.166015625, "learning_rate": 4.391947195607965e-06, "loss": 2.1809, "step": 2595 }, { "epoch": 0.88, "grad_norm": 0.169921875, "learning_rate": 4.271555291414636e-06, "loss": 2.2085, "step": 2600 }, { "epoch": 0.88, "grad_norm": 0.166015625, "learning_rate": 4.152762830257689e-06, "loss": 2.153, "step": 2605 }, { "epoch": 0.88, "grad_norm": 0.17578125, "learning_rate": 4.035573967139023e-06, "loss": 2.1964, "step": 2610 }, { "epoch": 0.89, "grad_norm": 0.1748046875, "learning_rate": 3.919992800971517e-06, "loss": 2.1967, "step": 2615 }, { "epoch": 0.89, "grad_norm": 0.1767578125, "learning_rate": 3.8060233744356633e-06, "loss": 2.1448, "step": 2620 }, { "epoch": 0.89, "grad_norm": 0.169921875, "learning_rate": 3.6936696738381737e-06, "loss": 2.151, "step": 2625 }, { "epoch": 0.89, "grad_norm": 0.1767578125, "learning_rate": 3.5829356289725223e-06, "loss": 2.1674, "step": 2630 }, { "epoch": 0.89, "grad_norm": 0.171875, "learning_rate": 3.473825112981527e-06, "loss": 2.1734, "step": 2635 }, { "epoch": 0.89, "grad_norm": 0.1748046875, "learning_rate": 3.3663419422218677e-06, "loss": 2.2007, "step": 2640 }, { "epoch": 0.9, "grad_norm": 0.1708984375, "learning_rate": 3.260489876130568e-06, "loss": 2.1475, "step": 2645 }, { "epoch": 0.9, "grad_norm": 0.173828125, "learning_rate": 3.156272617093553e-06, "loss": 2.1635, "step": 2650 }, { "epoch": 0.9, "grad_norm": 0.1748046875, "learning_rate": 3.0536938103161494e-06, "loss": 2.212, "step": 2655 }, { "epoch": 0.9, "grad_norm": 0.1728515625, "learning_rate": 2.9527570436955255e-06, "loss": 2.1406, "step": 2660 }, { "epoch": 0.9, "grad_norm": 0.1669921875, "learning_rate": 2.8534658476952635e-06, "loss": 2.2019, "step": 2665 }, { "epoch": 0.9, "grad_norm": 0.1689453125, "learning_rate": 2.7558236952218485e-06, "loss": 2.2006, "step": 2670 }, { "epoch": 0.91, "grad_norm": 0.171875, "learning_rate": 2.659834001503186e-06, "loss": 2.1873, "step": 2675 }, { "epoch": 0.91, "grad_norm": 0.1708984375, "learning_rate": 2.5655001239691835e-06, "loss": 2.1746, "step": 2680 }, { "epoch": 0.91, "grad_norm": 0.169921875, "learning_rate": 2.4728253621342566e-06, "loss": 2.1732, "step": 2685 }, { "epoch": 0.91, "grad_norm": 0.1748046875, "learning_rate": 2.381812957481999e-06, "loss": 2.1399, "step": 2690 }, { "epoch": 0.91, "grad_norm": 0.1728515625, "learning_rate": 2.292466093351747e-06, "loss": 2.18, "step": 2695 }, { "epoch": 0.91, "grad_norm": 0.1669921875, "learning_rate": 2.2047878948272373e-06, "loss": 2.1758, "step": 2700 }, { "epoch": 0.92, "grad_norm": 0.1796875, "learning_rate": 2.1187814286273646e-06, "loss": 2.1574, "step": 2705 }, { "epoch": 0.92, "grad_norm": 0.17578125, "learning_rate": 2.0344497029988086e-06, "loss": 2.163, "step": 2710 }, { "epoch": 0.92, "grad_norm": 0.1748046875, "learning_rate": 1.951795667610928e-06, "loss": 2.163, "step": 2715 }, { "epoch": 0.92, "grad_norm": 0.171875, "learning_rate": 1.8708222134525167e-06, "loss": 2.2011, "step": 2720 }, { "epoch": 0.92, "grad_norm": 0.173828125, "learning_rate": 1.7915321727307088e-06, "loss": 2.182, "step": 2725 }, { "epoch": 0.92, "grad_norm": 0.171875, "learning_rate": 1.7139283187719124e-06, "loss": 2.1744, "step": 2730 }, { "epoch": 0.93, "grad_norm": 0.1708984375, "learning_rate": 1.6380133659248176e-06, "loss": 2.1674, "step": 2735 }, { "epoch": 0.93, "grad_norm": 0.1689453125, "learning_rate": 1.5637899694654456e-06, "loss": 2.1665, "step": 2740 }, { "epoch": 0.93, "grad_norm": 0.1728515625, "learning_rate": 1.4912607255042787e-06, "loss": 2.1871, "step": 2745 }, { "epoch": 0.93, "grad_norm": 0.1806640625, "learning_rate": 1.4204281708954437e-06, "loss": 2.1737, "step": 2750 }, { "epoch": 0.93, "grad_norm": 0.1767578125, "learning_rate": 1.3512947831480217e-06, "loss": 2.1824, "step": 2755 }, { "epoch": 0.93, "grad_norm": 0.171875, "learning_rate": 1.2838629803393342e-06, "loss": 2.1608, "step": 2760 }, { "epoch": 0.94, "grad_norm": 0.169921875, "learning_rate": 1.218135121030406e-06, "loss": 2.1652, "step": 2765 }, { "epoch": 0.94, "grad_norm": 0.1669921875, "learning_rate": 1.1541135041834628e-06, "loss": 2.1705, "step": 2770 }, { "epoch": 0.94, "grad_norm": 0.1748046875, "learning_rate": 1.0918003690815138e-06, "loss": 2.1644, "step": 2775 }, { "epoch": 0.94, "grad_norm": 0.1796875, "learning_rate": 1.03119789525003e-06, "loss": 2.1674, "step": 2780 }, { "epoch": 0.94, "grad_norm": 0.173828125, "learning_rate": 9.723082023807118e-07, "loss": 2.158, "step": 2785 }, { "epoch": 0.95, "grad_norm": 0.1748046875, "learning_rate": 9.151333502573467e-07, "loss": 2.2049, "step": 2790 }, { "epoch": 0.95, "grad_norm": 0.1689453125, "learning_rate": 8.596753386837797e-07, "loss": 2.1732, "step": 2795 }, { "epoch": 0.95, "grad_norm": 0.171875, "learning_rate": 8.059361074139293e-07, "loss": 2.1608, "step": 2800 }, { "epoch": 0.95, "grad_norm": 0.1845703125, "learning_rate": 7.539175360839812e-07, "loss": 2.1728, "step": 2805 }, { "epoch": 0.95, "grad_norm": 0.1669921875, "learning_rate": 7.036214441466348e-07, "loss": 2.1575, "step": 2810 }, { "epoch": 0.95, "grad_norm": 0.1708984375, "learning_rate": 6.550495908074328e-07, "loss": 2.179, "step": 2815 }, { "epoch": 0.96, "grad_norm": 0.171875, "learning_rate": 6.082036749632703e-07, "loss": 2.1894, "step": 2820 }, { "epoch": 0.96, "grad_norm": 0.177734375, "learning_rate": 5.630853351429599e-07, "loss": 2.1787, "step": 2825 }, { "epoch": 0.96, "grad_norm": 0.17578125, "learning_rate": 5.196961494498997e-07, "loss": 2.1696, "step": 2830 }, { "epoch": 0.96, "grad_norm": 0.1689453125, "learning_rate": 4.780376355069172e-07, "loss": 2.1568, "step": 2835 }, { "epoch": 0.96, "grad_norm": 0.173828125, "learning_rate": 4.381112504031337e-07, "loss": 2.1699, "step": 2840 }, { "epoch": 0.96, "grad_norm": 0.169921875, "learning_rate": 3.9991839064305035e-07, "loss": 2.1795, "step": 2845 }, { "epoch": 0.97, "grad_norm": 0.169921875, "learning_rate": 3.634603920976809e-07, "loss": 2.1702, "step": 2850 }, { "epoch": 0.97, "grad_norm": 0.1787109375, "learning_rate": 3.2873852995781716e-07, "loss": 2.1864, "step": 2855 }, { "epoch": 0.97, "grad_norm": 0.169921875, "learning_rate": 2.957540186894481e-07, "loss": 2.1621, "step": 2860 }, { "epoch": 0.97, "grad_norm": 0.1748046875, "learning_rate": 2.6450801199126573e-07, "loss": 2.2217, "step": 2865 }, { "epoch": 0.97, "grad_norm": 0.1689453125, "learning_rate": 2.3500160275430893e-07, "loss": 2.1848, "step": 2870 }, { "epoch": 0.97, "grad_norm": 0.17578125, "learning_rate": 2.0723582302376588e-07, "loss": 2.187, "step": 2875 }, { "epoch": 0.98, "grad_norm": 0.1689453125, "learning_rate": 1.812116439628364e-07, "loss": 2.1751, "step": 2880 }, { "epoch": 0.98, "grad_norm": 0.171875, "learning_rate": 1.569299758187981e-07, "loss": 2.1874, "step": 2885 }, { "epoch": 0.98, "grad_norm": 0.1748046875, "learning_rate": 1.3439166789113722e-07, "loss": 2.158, "step": 2890 }, { "epoch": 0.98, "grad_norm": 0.1669921875, "learning_rate": 1.1359750850187256e-07, "loss": 2.1644, "step": 2895 }, { "epoch": 0.98, "grad_norm": 0.17578125, "learning_rate": 9.454822496796634e-08, "loss": 2.1859, "step": 2900 }, { "epoch": 0.98, "grad_norm": 0.171875, "learning_rate": 7.724448357588898e-08, "loss": 2.1779, "step": 2905 }, { "epoch": 0.99, "grad_norm": 0.1728515625, "learning_rate": 6.168688955830448e-08, "loss": 2.1375, "step": 2910 }, { "epoch": 0.99, "grad_norm": 0.171875, "learning_rate": 4.7875987072915075e-08, "loss": 2.1857, "step": 2915 }, { "epoch": 0.99, "grad_norm": 0.1708984375, "learning_rate": 3.581225918342646e-08, "loss": 2.1608, "step": 2920 }, { "epoch": 0.99, "grad_norm": 0.169921875, "learning_rate": 2.5496127842644658e-08, "loss": 2.1335, "step": 2925 }, { "epoch": 0.99, "grad_norm": 0.171875, "learning_rate": 1.692795387772117e-08, "loss": 2.1946, "step": 2930 }, { "epoch": 0.99, "grad_norm": 0.1728515625, "learning_rate": 1.0108036977535262e-08, "loss": 2.1851, "step": 2935 }, { "epoch": 1.0, "grad_norm": 0.171875, "learning_rate": 5.03661568219127e-09, "loss": 2.1765, "step": 2940 }, { "epoch": 1.0, "grad_norm": 0.173828125, "learning_rate": 1.7138673747196799e-09, "loss": 2.2174, "step": 2945 }, { "epoch": 1.0, "grad_norm": 0.1728515625, "learning_rate": 1.3990827483212344e-10, "loss": 2.1651, "step": 2950 }, { "epoch": 1.0, "eval_loss": 2.1763968467712402, "eval_runtime": 177.8602, "eval_samples_per_second": 14.939, "eval_steps_per_second": 1.872, "step": 2952 }, { "epoch": 1.0, "step": 2952, "total_flos": 3.038696615046021e+17, "train_loss": 2.200481324176478, "train_runtime": 12060.097, "train_samples_per_second": 3.917, "train_steps_per_second": 0.245 } ], "logging_steps": 5, "max_steps": 2952, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "total_flos": 3.038696615046021e+17, "train_batch_size": 4, "trial_name": null, "trial_params": null }