{"current_steps": 1, "total_steps": 480, "loss": 0.5261, "lr": 4.999946454160324e-05, "epoch": 0.06040268456375839, "percentage": 0.21, "elapsed_time": "0:01:17", "remaining_time": "10:16:28", "throughput": 1621.45, "total_tokens": 125208} {"current_steps": 2, "total_steps": 480, "loss": 0.5323, "lr": 4.999785818935018e-05, "epoch": 0.12080536912751678, "percentage": 0.42, "elapsed_time": "0:02:18", "remaining_time": "9:11:12", "throughput": 1688.86, "total_tokens": 233704} {"current_steps": 3, "total_steps": 480, "loss": 0.5076, "lr": 4.9995181012051625e-05, "epoch": 0.18120805369127516, "percentage": 0.62, "elapsed_time": "0:03:17", "remaining_time": "8:43:35", "throughput": 1717.95, "total_tokens": 339432} {"current_steps": 4, "total_steps": 480, "loss": 0.5426, "lr": 4.999143312438893e-05, "epoch": 0.24161073825503357, "percentage": 0.83, "elapsed_time": "0:04:28", "remaining_time": "8:53:06", "throughput": 1683.68, "total_tokens": 452568} {"current_steps": 1, "total_steps": 1110, "loss": 0.5189, "lr": 4.9999899870162604e-05, "epoch": 0.026845637583892617, "percentage": 0.09, "elapsed_time": "0:00:36", "remaining_time": "11:10:13", "throughput": 1611.65, "total_tokens": 58440} {"current_steps": 2, "total_steps": 1110, "loss": 0.5061, "lr": 4.999959948145249e-05, "epoch": 0.053691275167785234, "percentage": 0.18, "elapsed_time": "0:01:10", "remaining_time": "10:51:39", "throughput": 1598.25, "total_tokens": 112800} {"current_steps": 3, "total_steps": 1110, "loss": 0.5956, "lr": 4.999909883627587e-05, "epoch": 0.08053691275167785, "percentage": 0.27, "elapsed_time": "0:01:35", "remaining_time": "9:46:52", "throughput": 1642.12, "total_tokens": 156704} {"current_steps": 4, "total_steps": 1110, "loss": 0.5222, "lr": 4.999839793864313e-05, "epoch": 0.10738255033557047, "percentage": 0.36, "elapsed_time": "0:02:08", "remaining_time": "9:52:42", "throughput": 1663.5, "total_tokens": 213952} {"current_steps": 5, "total_steps": 1110, "loss": 0.4761, "lr": 4.9997496794168726e-05, "epoch": 0.1342281879194631, "percentage": 0.45, "elapsed_time": "0:02:39", "remaining_time": "9:45:59", "throughput": 1677.76, "total_tokens": 266920} {"current_steps": 6, "total_steps": 1110, "loss": 0.5221, "lr": 4.999639541007116e-05, "epoch": 0.1610738255033557, "percentage": 0.54, "elapsed_time": "0:03:03", "remaining_time": "9:23:56", "throughput": 1705.11, "total_tokens": 313560} {"current_steps": 7, "total_steps": 1110, "loss": 0.4738, "lr": 4.999509379517297e-05, "epoch": 0.18791946308724833, "percentage": 0.63, "elapsed_time": "0:03:24", "remaining_time": "8:56:24", "throughput": 1711.34, "total_tokens": 349544} {"current_steps": 8, "total_steps": 1110, "loss": 0.5576, "lr": 4.9993591959900566e-05, "epoch": 0.21476510067114093, "percentage": 0.72, "elapsed_time": "0:03:52", "remaining_time": "8:53:15", "throughput": 1713.3, "total_tokens": 397952} {"current_steps": 9, "total_steps": 1110, "loss": 0.4803, "lr": 4.999188991628425e-05, "epoch": 0.24161073825503357, "percentage": 0.81, "elapsed_time": "0:04:29", "remaining_time": "9:08:45", "throughput": 1681.51, "total_tokens": 452568} {"current_steps": 10, "total_steps": 1110, "loss": 0.4735, "lr": 4.998998767795805e-05, "epoch": 0.2684563758389262, "percentage": 0.9, "elapsed_time": "0:04:50", "remaining_time": "8:53:27", "throughput": 1699.1, "total_tokens": 494400} {"current_steps": 11, "total_steps": 1110, "loss": 0.5054, "lr": 4.998788526015961e-05, "epoch": 0.2953020134228188, "percentage": 0.99, "elapsed_time": "0:05:41", "remaining_time": "9:28:24", "throughput": 1667.92, "total_tokens": 569352} {"current_steps": 12, "total_steps": 1110, "loss": 0.494, "lr": 4.998558267973014e-05, "epoch": 0.3221476510067114, "percentage": 1.08, "elapsed_time": "0:06:14", "remaining_time": "9:30:57", "throughput": 1665.82, "total_tokens": 623680} {"current_steps": 13, "total_steps": 1110, "loss": 0.4411, "lr": 4.998307995511418e-05, "epoch": 0.348993288590604, "percentage": 1.17, "elapsed_time": "0:06:44", "remaining_time": "9:29:15", "throughput": 1669.6, "total_tokens": 675784} {"current_steps": 14, "total_steps": 1110, "loss": 0.5778, "lr": 4.998037710635952e-05, "epoch": 0.37583892617449666, "percentage": 1.26, "elapsed_time": "0:07:14", "remaining_time": "9:27:33", "throughput": 1673.89, "total_tokens": 728120} {"current_steps": 15, "total_steps": 1110, "loss": 0.5217, "lr": 4.9977474155117045e-05, "epoch": 0.40268456375838924, "percentage": 1.35, "elapsed_time": "0:07:44", "remaining_time": "9:25:44", "throughput": 1678.28, "total_tokens": 780392} {"current_steps": 16, "total_steps": 1110, "loss": 0.4175, "lr": 4.997437112464049e-05, "epoch": 0.42953020134228187, "percentage": 1.44, "elapsed_time": "0:08:28", "remaining_time": "9:39:31", "throughput": 1654.11, "total_tokens": 841192} {"current_steps": 17, "total_steps": 1110, "loss": 0.5109, "lr": 4.997106803978636e-05, "epoch": 0.4563758389261745, "percentage": 1.53, "elapsed_time": "0:09:02", "remaining_time": "9:41:02", "throughput": 1658.61, "total_tokens": 899368} {"current_steps": 18, "total_steps": 1110, "loss": 0.4066, "lr": 4.996756492701362e-05, "epoch": 0.48322147651006714, "percentage": 1.62, "elapsed_time": "0:09:29", "remaining_time": "9:36:02", "throughput": 1657.69, "total_tokens": 944400} {"current_steps": 19, "total_steps": 1110, "loss": 0.4501, "lr": 4.996386181438357e-05, "epoch": 0.5100671140939598, "percentage": 1.71, "elapsed_time": "0:09:59", "remaining_time": "9:33:53", "throughput": 1662.63, "total_tokens": 997024} {"current_steps": 20, "total_steps": 1110, "loss": 0.4632, "lr": 4.995995873155958e-05, "epoch": 0.5369127516778524, "percentage": 1.8, "elapsed_time": "0:10:37", "remaining_time": "9:39:09", "throughput": 1658.18, "total_tokens": 1057264} {"current_steps": 21, "total_steps": 1110, "loss": 0.4224, "lr": 4.9955855709806845e-05, "epoch": 0.5637583892617449, "percentage": 1.89, "elapsed_time": "0:10:57", "remaining_time": "9:28:01", "throughput": 1664.82, "total_tokens": 1094144} {"current_steps": 22, "total_steps": 1110, "loss": 0.4084, "lr": 4.9951552781992154e-05, "epoch": 0.5906040268456376, "percentage": 1.98, "elapsed_time": "0:11:25", "remaining_time": "9:24:53", "throughput": 1669.79, "total_tokens": 1144376} {"current_steps": 23, "total_steps": 1110, "loss": 0.3925, "lr": 4.9947049982583625e-05, "epoch": 0.6174496644295302, "percentage": 2.07, "elapsed_time": "0:12:03", "remaining_time": "9:30:11", "throughput": 1666.36, "total_tokens": 1206272} {"current_steps": 24, "total_steps": 1110, "loss": 0.3666, "lr": 4.994234734765043e-05, "epoch": 0.6442953020134228, "percentage": 2.16, "elapsed_time": "0:12:30", "remaining_time": "9:25:48", "throughput": 1669.41, "total_tokens": 1252464} {"current_steps": 25, "total_steps": 1110, "loss": 0.4105, "lr": 4.99374449148625e-05, "epoch": 0.6711409395973155, "percentage": 2.25, "elapsed_time": "0:12:55", "remaining_time": "9:21:09", "throughput": 1669.97, "total_tokens": 1295560} {"current_steps": 26, "total_steps": 1110, "loss": 0.3965, "lr": 4.99323427234902e-05, "epoch": 0.697986577181208, "percentage": 2.34, "elapsed_time": "0:13:32", "remaining_time": "9:24:42", "throughput": 1669.53, "total_tokens": 1356792} {"current_steps": 27, "total_steps": 1110, "loss": 0.3867, "lr": 4.992704081440407e-05, "epoch": 0.7248322147651006, "percentage": 2.43, "elapsed_time": "0:14:01", "remaining_time": "9:22:28", "throughput": 1674.13, "total_tokens": 1408568} {"current_steps": 28, "total_steps": 1110, "loss": 0.4272, "lr": 4.992153923007446e-05, "epoch": 0.7516778523489933, "percentage": 2.52, "elapsed_time": "0:14:32", "remaining_time": "9:22:06", "throughput": 1679.67, "total_tokens": 1465984} {"current_steps": 29, "total_steps": 1110, "loss": 0.3499, "lr": 4.9915838014571174e-05, "epoch": 0.7785234899328859, "percentage": 2.61, "elapsed_time": "0:15:03", "remaining_time": "9:21:16", "throughput": 1685.29, "total_tokens": 1522568} {"current_steps": 30, "total_steps": 1110, "loss": 0.3536, "lr": 4.9909937213563165e-05, "epoch": 0.8053691275167785, "percentage": 2.7, "elapsed_time": "0:15:37", "remaining_time": "9:22:22", "throughput": 1682.07, "total_tokens": 1576592} {"current_steps": 31, "total_steps": 1110, "loss": 0.3416, "lr": 4.9903836874318135e-05, "epoch": 0.8322147651006712, "percentage": 2.79, "elapsed_time": "0:16:05", "remaining_time": "9:19:50", "throughput": 1684.18, "total_tokens": 1625336} {"current_steps": 32, "total_steps": 1110, "loss": 0.3559, "lr": 4.9897537045702146e-05, "epoch": 0.8590604026845637, "percentage": 2.88, "elapsed_time": "0:16:26", "remaining_time": "9:14:08", "throughput": 1690.79, "total_tokens": 1668736} {"current_steps": 33, "total_steps": 1110, "loss": 0.358, "lr": 4.989103777817928e-05, "epoch": 0.8859060402684564, "percentage": 2.97, "elapsed_time": "0:17:00", "remaining_time": "9:15:15", "throughput": 1689.91, "total_tokens": 1725096} {"current_steps": 34, "total_steps": 1110, "loss": 0.354, "lr": 4.988433912381117e-05, "epoch": 0.912751677852349, "percentage": 3.06, "elapsed_time": "0:17:24", "remaining_time": "9:11:04", "throughput": 1692.61, "total_tokens": 1768400} {"current_steps": 35, "total_steps": 1110, "loss": 0.3553, "lr": 4.987744113625665e-05, "epoch": 0.9395973154362416, "percentage": 3.15, "elapsed_time": "0:18:00", "remaining_time": "9:12:55", "throughput": 1693.53, "total_tokens": 1829224} {"current_steps": 36, "total_steps": 1110, "loss": 0.3651, "lr": 4.9870343870771256e-05, "epoch": 0.9664429530201343, "percentage": 3.24, "elapsed_time": "0:18:44", "remaining_time": "9:19:05", "throughput": 1685.71, "total_tokens": 1895440} {"current_steps": 37, "total_steps": 1110, "loss": 0.3117, "lr": 4.9863047384206835e-05, "epoch": 0.9932885906040269, "percentage": 3.33, "elapsed_time": "0:19:14", "remaining_time": "9:18:08", "throughput": 1687.59, "total_tokens": 1948776} {"current_steps": 38, "total_steps": 1110, "loss": 0.3247, "lr": 4.985555173501106e-05, "epoch": 1.0, "percentage": 3.42, "elapsed_time": "0:19:23", "remaining_time": "9:07:10", "throughput": 1685.72, "total_tokens": 1961808} {"current_steps": 39, "total_steps": 1110, "loss": 0.3328, "lr": 4.9847856983226996e-05, "epoch": 1.0268456375838926, "percentage": 3.51, "elapsed_time": "0:19:59", "remaining_time": "9:08:47", "throughput": 1685.17, "total_tokens": 2020584} {"current_steps": 40, "total_steps": 1110, "loss": 0.3809, "lr": 4.9839963190492576e-05, "epoch": 1.0536912751677852, "percentage": 3.6, "elapsed_time": "0:20:37", "remaining_time": "9:11:44", "throughput": 1678.51, "total_tokens": 2077264} {"current_steps": 41, "total_steps": 1110, "loss": 0.296, "lr": 4.9831870420040126e-05, "epoch": 1.0805369127516777, "percentage": 3.69, "elapsed_time": "0:21:00", "remaining_time": "9:07:50", "throughput": 1679.86, "total_tokens": 2117808} {"current_steps": 42, "total_steps": 1110, "loss": 0.3045, "lr": 4.982357873669589e-05, "epoch": 1.1073825503355705, "percentage": 3.78, "elapsed_time": "0:21:21", "remaining_time": "9:03:12", "throughput": 1683.61, "total_tokens": 2157928} {"current_steps": 43, "total_steps": 1110, "loss": 0.3037, "lr": 4.981508820687943e-05, "epoch": 1.1342281879194631, "percentage": 3.87, "elapsed_time": "0:21:53", "remaining_time": "9:03:25", "throughput": 1685.82, "total_tokens": 2215144} {"current_steps": 44, "total_steps": 1110, "loss": 0.308, "lr": 4.9806398898603206e-05, "epoch": 1.1610738255033557, "percentage": 3.96, "elapsed_time": "0:22:23", "remaining_time": "9:02:35", "throughput": 1688.36, "total_tokens": 2268776} {"current_steps": 45, "total_steps": 1110, "loss": 0.3095, "lr": 4.979751088147192e-05, "epoch": 1.1879194630872483, "percentage": 4.05, "elapsed_time": "0:22:50", "remaining_time": "9:00:35", "throughput": 1689.95, "total_tokens": 2316136} {"current_steps": 46, "total_steps": 1110, "loss": 0.3144, "lr": 4.978842422668204e-05, "epoch": 1.2147651006711409, "percentage": 4.14, "elapsed_time": "0:23:20", "remaining_time": "8:59:45", "throughput": 1693.34, "total_tokens": 2370888} {"current_steps": 47, "total_steps": 1110, "loss": 0.3084, "lr": 4.9779139007021184e-05, "epoch": 1.2416107382550337, "percentage": 4.23, "elapsed_time": "0:23:54", "remaining_time": "9:00:49", "throughput": 1691.33, "total_tokens": 2426656} {"current_steps": 48, "total_steps": 1110, "loss": 0.2861, "lr": 4.9769655296867554e-05, "epoch": 1.2684563758389262, "percentage": 4.32, "elapsed_time": "0:24:20", "remaining_time": "8:58:23", "throughput": 1693.04, "total_tokens": 2471944} {"current_steps": 49, "total_steps": 1110, "loss": 0.3136, "lr": 4.9759973172189334e-05, "epoch": 1.2953020134228188, "percentage": 4.41, "elapsed_time": "0:25:04", "remaining_time": "9:02:56", "throughput": 1688.21, "total_tokens": 2539888} {"current_steps": 50, "total_steps": 1110, "loss": 0.26, "lr": 4.975009271054409e-05, "epoch": 1.3221476510067114, "percentage": 4.5, "elapsed_time": "0:25:28", "remaining_time": "9:00:06", "throughput": 1689.09, "total_tokens": 2581936} {"current_steps": 51, "total_steps": 1110, "loss": 0.3178, "lr": 4.974001399107816e-05, "epoch": 1.348993288590604, "percentage": 4.59, "elapsed_time": "0:26:18", "remaining_time": "9:06:19", "throughput": 1676.8, "total_tokens": 2647016} {"current_steps": 52, "total_steps": 1110, "loss": 0.2853, "lr": 4.972973709452597e-05, "epoch": 1.3758389261744965, "percentage": 4.68, "elapsed_time": "0:26:46", "remaining_time": "9:04:51", "throughput": 1676.99, "total_tokens": 2694512} {"current_steps": 53, "total_steps": 1110, "loss": 0.3009, "lr": 4.971926210320944e-05, "epoch": 1.4026845637583891, "percentage": 4.77, "elapsed_time": "0:27:11", "remaining_time": "9:02:13", "throughput": 1676.98, "total_tokens": 2735672} {"current_steps": 54, "total_steps": 1110, "loss": 0.2967, "lr": 4.9708589101037306e-05, "epoch": 1.429530201342282, "percentage": 4.86, "elapsed_time": "0:27:39", "remaining_time": "9:00:58", "throughput": 1680.39, "total_tokens": 2789104} {"current_steps": 55, "total_steps": 1110, "loss": 0.2741, "lr": 4.969771817350445e-05, "epoch": 1.4563758389261745, "percentage": 4.95, "elapsed_time": "0:28:08", "remaining_time": "8:59:46", "throughput": 1680.25, "total_tokens": 2836960} {"current_steps": 56, "total_steps": 1110, "loss": 0.3276, "lr": 4.968664940769121e-05, "epoch": 1.483221476510067, "percentage": 5.05, "elapsed_time": "0:28:43", "remaining_time": "9:00:37", "throughput": 1682.82, "total_tokens": 2900208} {"current_steps": 57, "total_steps": 1110, "loss": 0.2721, "lr": 4.967538289226267e-05, "epoch": 1.5100671140939599, "percentage": 5.14, "elapsed_time": "0:29:24", "remaining_time": "9:03:24", "throughput": 1679.78, "total_tokens": 2964720} {"current_steps": 58, "total_steps": 1110, "loss": 0.3084, "lr": 4.9663918717467996e-05, "epoch": 1.5369127516778525, "percentage": 5.23, "elapsed_time": "0:30:06", "remaining_time": "9:06:00", "throughput": 1677.54, "total_tokens": 3029912} {"current_steps": 59, "total_steps": 1110, "loss": 0.2752, "lr": 4.965225697513965e-05, "epoch": 1.563758389261745, "percentage": 5.32, "elapsed_time": "0:30:35", "remaining_time": "9:04:57", "throughput": 1678.66, "total_tokens": 3081216} {"current_steps": 60, "total_steps": 1110, "loss": 0.2684, "lr": 4.9640397758692715e-05, "epoch": 1.5906040268456376, "percentage": 5.41, "elapsed_time": "0:31:04", "remaining_time": "9:03:48", "throughput": 1679.5, "total_tokens": 3131424} {"current_steps": 61, "total_steps": 1110, "loss": 0.2663, "lr": 4.962834116312409e-05, "epoch": 1.6174496644295302, "percentage": 5.5, "elapsed_time": "0:31:32", "remaining_time": "9:02:23", "throughput": 1682.1, "total_tokens": 3183240} {"current_steps": 62, "total_steps": 1110, "loss": 0.2845, "lr": 4.961608728501178e-05, "epoch": 1.6442953020134228, "percentage": 5.59, "elapsed_time": "0:32:00", "remaining_time": "9:01:00", "throughput": 1682.57, "total_tokens": 3231192} {"current_steps": 63, "total_steps": 1110, "loss": 0.2873, "lr": 4.960363622251409e-05, "epoch": 1.6711409395973154, "percentage": 5.68, "elapsed_time": "0:32:34", "remaining_time": "9:01:16", "throughput": 1683.92, "total_tokens": 3290616} {"current_steps": 64, "total_steps": 1110, "loss": 0.2858, "lr": 4.959098807536885e-05, "epoch": 1.697986577181208, "percentage": 5.77, "elapsed_time": "0:33:04", "remaining_time": "9:00:34", "throughput": 1684.28, "total_tokens": 3342512} {"current_steps": 65, "total_steps": 1110, "loss": 0.2813, "lr": 4.957814294489261e-05, "epoch": 1.7248322147651005, "percentage": 5.86, "elapsed_time": "0:33:46", "remaining_time": "9:03:02", "throughput": 1680.05, "total_tokens": 3404912} {"current_steps": 66, "total_steps": 1110, "loss": 0.2417, "lr": 4.956510093397983e-05, "epoch": 1.7516778523489933, "percentage": 5.95, "elapsed_time": "0:34:07", "remaining_time": "8:59:55", "throughput": 1681.97, "total_tokens": 3444648} {"current_steps": 67, "total_steps": 1110, "loss": 0.303, "lr": 4.955186214710208e-05, "epoch": 1.778523489932886, "percentage": 6.04, "elapsed_time": "0:34:34", "remaining_time": "8:58:21", "throughput": 1683.68, "total_tokens": 3493584} {"current_steps": 68, "total_steps": 1110, "loss": 0.259, "lr": 4.953842669030716e-05, "epoch": 1.8053691275167785, "percentage": 6.13, "elapsed_time": "0:35:02", "remaining_time": "8:57:04", "throughput": 1685.69, "total_tokens": 3544904} {"current_steps": 69, "total_steps": 1110, "loss": 0.2709, "lr": 4.952479467121827e-05, "epoch": 1.8322147651006713, "percentage": 6.22, "elapsed_time": "0:35:29", "remaining_time": "8:55:28", "throughput": 1686.39, "total_tokens": 3591296} {"current_steps": 70, "total_steps": 1110, "loss": 0.2615, "lr": 4.9510966199033174e-05, "epoch": 1.8590604026845639, "percentage": 6.31, "elapsed_time": "0:36:06", "remaining_time": "8:56:29", "throughput": 1687.14, "total_tokens": 3655368} {"current_steps": 71, "total_steps": 1110, "loss": 0.2607, "lr": 4.949694138452327e-05, "epoch": 1.8859060402684564, "percentage": 6.4, "elapsed_time": "0:36:38", "remaining_time": "8:56:14", "throughput": 1686.46, "total_tokens": 3707872} {"current_steps": 72, "total_steps": 1110, "loss": 0.2876, "lr": 4.948272034003275e-05, "epoch": 1.912751677852349, "percentage": 6.49, "elapsed_time": "0:37:05", "remaining_time": "8:54:44", "throughput": 1687.62, "total_tokens": 3755824} {"current_steps": 73, "total_steps": 1110, "loss": 0.2429, "lr": 4.9468303179477706e-05, "epoch": 1.9395973154362416, "percentage": 6.58, "elapsed_time": "0:37:40", "remaining_time": "8:55:05", "throughput": 1686.08, "total_tokens": 3810712} {"current_steps": 74, "total_steps": 1110, "loss": 0.2672, "lr": 4.9453690018345144e-05, "epoch": 1.9664429530201342, "percentage": 6.67, "elapsed_time": "0:38:08", "remaining_time": "8:54:00", "throughput": 1687.45, "total_tokens": 3861920} {"current_steps": 75, "total_steps": 1110, "loss": 0.2764, "lr": 4.943888097369216e-05, "epoch": 1.9932885906040267, "percentage": 6.76, "elapsed_time": "0:38:35", "remaining_time": "8:52:35", "throughput": 1688.41, "total_tokens": 3909768} {"current_steps": 76, "total_steps": 1110, "loss": 0.2707, "lr": 4.942387616414492e-05, "epoch": 2.0, "percentage": 6.85, "elapsed_time": "0:38:45", "remaining_time": "8:47:19", "throughput": 1687.17, "total_tokens": 3923616} {"current_steps": 77, "total_steps": 1110, "loss": 0.2517, "lr": 4.940867570989777e-05, "epoch": 2.0268456375838926, "percentage": 6.94, "elapsed_time": "0:39:16", "remaining_time": "8:46:57", "throughput": 1687.98, "total_tokens": 3978224} {"current_steps": 78, "total_steps": 1110, "loss": 0.2821, "lr": 4.939327973271221e-05, "epoch": 2.053691275167785, "percentage": 7.03, "elapsed_time": "0:39:41", "remaining_time": "8:45:02", "throughput": 1690.08, "total_tokens": 4024096} {"current_steps": 79, "total_steps": 1110, "loss": 0.2396, "lr": 4.9377688355915994e-05, "epoch": 2.0805369127516777, "percentage": 7.12, "elapsed_time": "0:40:12", "remaining_time": "8:44:43", "throughput": 1691.51, "total_tokens": 4080656} {"current_steps": 80, "total_steps": 1110, "loss": 0.2564, "lr": 4.936190170440208e-05, "epoch": 2.1073825503355703, "percentage": 7.21, "elapsed_time": "0:40:34", "remaining_time": "8:42:26", "throughput": 1693.16, "total_tokens": 4122248} {"current_steps": 81, "total_steps": 1110, "loss": 0.2663, "lr": 4.934591990462766e-05, "epoch": 2.134228187919463, "percentage": 7.3, "elapsed_time": "0:41:10", "remaining_time": "8:42:59", "throughput": 1693.73, "total_tokens": 4183624} {"current_steps": 82, "total_steps": 1110, "loss": 0.2373, "lr": 4.932974308461311e-05, "epoch": 2.1610738255033555, "percentage": 7.39, "elapsed_time": "0:41:32", "remaining_time": "8:40:46", "throughput": 1694.64, "total_tokens": 4223696} {"current_steps": 83, "total_steps": 1110, "loss": 0.2743, "lr": 4.931337137394105e-05, "epoch": 2.1879194630872485, "percentage": 7.48, "elapsed_time": "0:42:09", "remaining_time": "8:41:38", "throughput": 1693.05, "total_tokens": 4282504} {"current_steps": 84, "total_steps": 1110, "loss": 0.2516, "lr": 4.92968049037552e-05, "epoch": 2.214765100671141, "percentage": 7.57, "elapsed_time": "0:42:45", "remaining_time": "8:42:21", "throughput": 1690.81, "total_tokens": 4338600} {"current_steps": 85, "total_steps": 1110, "loss": 0.2463, "lr": 4.928004380675941e-05, "epoch": 2.2416107382550337, "percentage": 7.66, "elapsed_time": "0:43:11", "remaining_time": "8:40:56", "throughput": 1692.08, "total_tokens": 4385840} {"current_steps": 86, "total_steps": 1110, "loss": 0.2578, "lr": 4.9263088217216544e-05, "epoch": 2.2684563758389262, "percentage": 7.75, "elapsed_time": "0:43:42", "remaining_time": "8:40:23", "throughput": 1693.32, "total_tokens": 4440368} {"current_steps": 87, "total_steps": 1110, "loss": 0.2369, "lr": 4.9245938270947435e-05, "epoch": 2.295302013422819, "percentage": 7.84, "elapsed_time": "0:44:21", "remaining_time": "8:41:37", "throughput": 1691.46, "total_tokens": 4502040} {"current_steps": 88, "total_steps": 1110, "loss": 0.3009, "lr": 4.922859410532978e-05, "epoch": 2.3221476510067114, "percentage": 7.93, "elapsed_time": "0:45:03", "remaining_time": "8:43:11", "throughput": 1688.22, "total_tokens": 4563296} {"current_steps": 89, "total_steps": 1110, "loss": 0.211, "lr": 4.921105585929709e-05, "epoch": 2.348993288590604, "percentage": 8.02, "elapsed_time": "0:45:34", "remaining_time": "8:42:52", "throughput": 1689.48, "total_tokens": 4620344} {"current_steps": 90, "total_steps": 1110, "loss": 0.2463, "lr": 4.9193323673337476e-05, "epoch": 2.3758389261744965, "percentage": 8.11, "elapsed_time": "0:46:06", "remaining_time": "8:42:36", "throughput": 1689.85, "total_tokens": 4675400} {"current_steps": 91, "total_steps": 1110, "loss": 0.2536, "lr": 4.9175397689492614e-05, "epoch": 2.402684563758389, "percentage": 8.2, "elapsed_time": "0:46:46", "remaining_time": "8:43:41", "throughput": 1687.3, "total_tokens": 4734696} {"current_steps": 92, "total_steps": 1110, "loss": 0.2538, "lr": 4.915727805135657e-05, "epoch": 2.4295302013422817, "percentage": 8.29, "elapsed_time": "0:47:11", "remaining_time": "8:42:07", "throughput": 1689.2, "total_tokens": 4782448} {"current_steps": 93, "total_steps": 1110, "loss": 0.2243, "lr": 4.9138964904074667e-05, "epoch": 2.4563758389261743, "percentage": 8.38, "elapsed_time": "0:47:35", "remaining_time": "8:40:31", "throughput": 1691.38, "total_tokens": 4830504} {"current_steps": 94, "total_steps": 1110, "loss": 0.2701, "lr": 4.91204583943423e-05, "epoch": 2.4832214765100673, "percentage": 8.47, "elapsed_time": "0:48:10", "remaining_time": "8:40:40", "throughput": 1690.48, "total_tokens": 4886040} {"current_steps": 95, "total_steps": 1110, "loss": 0.2292, "lr": 4.910175867040377e-05, "epoch": 2.51006711409396, "percentage": 8.56, "elapsed_time": "0:48:36", "remaining_time": "8:39:18", "throughput": 1692.0, "total_tokens": 4934448} {"current_steps": 96, "total_steps": 1110, "loss": 0.2398, "lr": 4.90828658820511e-05, "epoch": 2.5369127516778525, "percentage": 8.65, "elapsed_time": "0:49:06", "remaining_time": "8:38:42", "throughput": 1692.51, "total_tokens": 4987040} {"current_steps": 97, "total_steps": 1110, "loss": 0.2355, "lr": 4.9063780180622845e-05, "epoch": 2.563758389261745, "percentage": 8.74, "elapsed_time": "0:49:37", "remaining_time": "8:38:14", "throughput": 1691.86, "total_tokens": 5037360} {"current_steps": 98, "total_steps": 1110, "loss": 0.2554, "lr": 4.9044501719002844e-05, "epoch": 2.5906040268456376, "percentage": 8.83, "elapsed_time": "0:50:07", "remaining_time": "8:37:33", "throughput": 1693.15, "total_tokens": 5091640} {"current_steps": 99, "total_steps": 1110, "loss": 0.2176, "lr": 4.9025030651619046e-05, "epoch": 2.61744966442953, "percentage": 8.92, "elapsed_time": "0:50:42", "remaining_time": "8:37:55", "throughput": 1692.18, "total_tokens": 5149232} {"current_steps": 100, "total_steps": 1110, "loss": 0.2191, "lr": 4.9005367134442235e-05, "epoch": 2.6442953020134228, "percentage": 9.01, "elapsed_time": "0:51:09", "remaining_time": "8:36:43", "throughput": 1692.9, "total_tokens": 5196648} {"current_steps": 101, "total_steps": 1110, "loss": 0.2283, "lr": 4.89855113249848e-05, "epoch": 2.6711409395973154, "percentage": 9.1, "elapsed_time": "0:51:54", "remaining_time": "8:38:32", "throughput": 1689.49, "total_tokens": 5261568} {"current_steps": 102, "total_steps": 1110, "loss": 0.234, "lr": 4.896546338229945e-05, "epoch": 2.697986577181208, "percentage": 9.19, "elapsed_time": "0:52:25", "remaining_time": "8:38:06", "throughput": 1688.73, "total_tokens": 5312104} {"current_steps": 103, "total_steps": 1110, "loss": 0.2373, "lr": 4.894522346697796e-05, "epoch": 2.7248322147651005, "percentage": 9.28, "elapsed_time": "0:52:52", "remaining_time": "8:36:55", "throughput": 1689.59, "total_tokens": 5360104} {"current_steps": 104, "total_steps": 1110, "loss": 0.2291, "lr": 4.892479174114989e-05, "epoch": 2.751677852348993, "percentage": 9.37, "elapsed_time": "0:53:17", "remaining_time": "8:35:26", "throughput": 1689.9, "total_tokens": 5402856} {"current_steps": 105, "total_steps": 1110, "loss": 0.2297, "lr": 4.890416836848127e-05, "epoch": 2.778523489932886, "percentage": 9.46, "elapsed_time": "0:53:39", "remaining_time": "8:33:37", "throughput": 1691.13, "total_tokens": 5445040} {"current_steps": 106, "total_steps": 1110, "loss": 0.2271, "lr": 4.888335351417331e-05, "epoch": 2.8053691275167782, "percentage": 9.55, "elapsed_time": "0:54:07", "remaining_time": "8:32:39", "throughput": 1692.8, "total_tokens": 5497368} {"current_steps": 107, "total_steps": 1110, "loss": 0.261, "lr": 4.886234734496102e-05, "epoch": 2.8322147651006713, "percentage": 9.64, "elapsed_time": "0:54:50", "remaining_time": "8:34:01", "throughput": 1690.08, "total_tokens": 5560720} {"current_steps": 108, "total_steps": 1110, "loss": 0.2532, "lr": 4.884115002911197e-05, "epoch": 2.859060402684564, "percentage": 9.73, "elapsed_time": "0:55:28", "remaining_time": "8:34:42", "throughput": 1687.36, "total_tokens": 5616592} {"current_steps": 109, "total_steps": 1110, "loss": 0.2265, "lr": 4.8819761736424854e-05, "epoch": 2.8859060402684564, "percentage": 9.82, "elapsed_time": "0:56:00", "remaining_time": "8:34:24", "throughput": 1688.38, "total_tokens": 5674352} {"current_steps": 110, "total_steps": 1110, "loss": 0.2356, "lr": 4.8798182638228166e-05, "epoch": 2.912751677852349, "percentage": 9.91, "elapsed_time": "0:56:21", "remaining_time": "8:32:18", "throughput": 1688.99, "total_tokens": 5710912} {"current_steps": 111, "total_steps": 1110, "loss": 0.2381, "lr": 4.877641290737884e-05, "epoch": 2.9395973154362416, "percentage": 10.0, "elapsed_time": "0:56:47", "remaining_time": "8:31:08", "throughput": 1689.7, "total_tokens": 5757920} {"current_steps": 112, "total_steps": 1110, "loss": 0.2288, "lr": 4.875445271826084e-05, "epoch": 2.966442953020134, "percentage": 10.09, "elapsed_time": "0:57:15", "remaining_time": "8:30:09", "throughput": 1689.06, "total_tokens": 5802192} {"current_steps": 113, "total_steps": 1110, "loss": 0.2264, "lr": 4.87323022467838e-05, "epoch": 2.9932885906040267, "percentage": 10.18, "elapsed_time": "0:57:58", "remaining_time": "8:31:28", "throughput": 1686.85, "total_tokens": 5867304} {"current_steps": 114, "total_steps": 1110, "loss": 0.2352, "lr": 4.870996167038154e-05, "epoch": 3.0, "percentage": 10.27, "elapsed_time": "0:58:11", "remaining_time": "8:28:20", "throughput": 1685.88, "total_tokens": 5885424} {"current_steps": 115, "total_steps": 1110, "loss": 0.2164, "lr": 4.868743116801074e-05, "epoch": 3.0268456375838926, "percentage": 10.36, "elapsed_time": "0:58:42", "remaining_time": "8:27:53", "throughput": 1687.77, "total_tokens": 5944528} {"current_steps": 116, "total_steps": 1110, "loss": 0.2329, "lr": 4.866471092014945e-05, "epoch": 3.053691275167785, "percentage": 10.45, "elapsed_time": "0:59:20", "remaining_time": "8:28:27", "throughput": 1686.27, "total_tokens": 6003480} {"current_steps": 117, "total_steps": 1110, "loss": 0.2318, "lr": 4.864180110879562e-05, "epoch": 3.0805369127516777, "percentage": 10.54, "elapsed_time": "0:59:56", "remaining_time": "8:28:43", "throughput": 1684.8, "total_tokens": 6059304} {"current_steps": 118, "total_steps": 1110, "loss": 0.2054, "lr": 4.861870191746573e-05, "epoch": 3.1073825503355703, "percentage": 10.63, "elapsed_time": "1:00:32", "remaining_time": "8:28:55", "throughput": 1684.15, "total_tokens": 6117288} {"current_steps": 119, "total_steps": 1110, "loss": 0.2086, "lr": 4.859541353119322e-05, "epoch": 3.134228187919463, "percentage": 10.72, "elapsed_time": "1:00:57", "remaining_time": "8:27:41", "throughput": 1685.17, "total_tokens": 6164008} {"current_steps": 120, "total_steps": 1110, "loss": 0.2353, "lr": 4.857193613652711e-05, "epoch": 3.1610738255033555, "percentage": 10.81, "elapsed_time": "1:01:36", "remaining_time": "8:28:15", "throughput": 1683.92, "total_tokens": 6224560} {"current_steps": 121, "total_steps": 1110, "loss": 0.2295, "lr": 4.854826992153038e-05, "epoch": 3.1879194630872485, "percentage": 10.9, "elapsed_time": "1:02:05", "remaining_time": "8:27:29", "throughput": 1683.94, "total_tokens": 6273248} {"current_steps": 122, "total_steps": 1110, "loss": 0.1945, "lr": 4.8524415075778597e-05, "epoch": 3.214765100671141, "percentage": 10.99, "elapsed_time": "1:02:38", "remaining_time": "8:27:16", "throughput": 1683.59, "total_tokens": 6327592} {"current_steps": 123, "total_steps": 1110, "loss": 0.2389, "lr": 4.850037179035829e-05, "epoch": 3.2416107382550337, "percentage": 11.08, "elapsed_time": "1:03:13", "remaining_time": "8:27:20", "throughput": 1684.4, "total_tokens": 6389680} {"current_steps": 124, "total_steps": 1110, "loss": 0.2083, "lr": 4.847614025786549e-05, "epoch": 3.2684563758389262, "percentage": 11.17, "elapsed_time": "1:03:45", "remaining_time": "8:26:58", "throughput": 1683.82, "total_tokens": 6441392} {"current_steps": 125, "total_steps": 1110, "loss": 0.2497, "lr": 4.845172067240415e-05, "epoch": 3.295302013422819, "percentage": 11.26, "elapsed_time": "1:04:10", "remaining_time": "8:25:38", "throughput": 1684.0, "total_tokens": 6483464} {"current_steps": 126, "total_steps": 1110, "loss": 0.188, "lr": 4.842711322958459e-05, "epoch": 3.3221476510067114, "percentage": 11.35, "elapsed_time": "1:04:42", "remaining_time": "8:25:23", "throughput": 1683.28, "total_tokens": 6536056} {"current_steps": 127, "total_steps": 1110, "loss": 0.1913, "lr": 4.840231812652196e-05, "epoch": 3.348993288590604, "percentage": 11.44, "elapsed_time": "1:05:10", "remaining_time": "8:24:30", "throughput": 1683.47, "total_tokens": 6583768} {"current_steps": 128, "total_steps": 1110, "loss": 0.1926, "lr": 4.837733556183463e-05, "epoch": 3.3758389261744965, "percentage": 11.53, "elapsed_time": "1:05:45", "remaining_time": "8:24:27", "throughput": 1682.81, "total_tokens": 6639048} {"current_steps": 129, "total_steps": 1110, "loss": 0.2234, "lr": 4.8352165735642604e-05, "epoch": 3.402684563758389, "percentage": 11.62, "elapsed_time": "1:06:14", "remaining_time": "8:23:41", "throughput": 1683.75, "total_tokens": 6691360} {"current_steps": 130, "total_steps": 1110, "loss": 0.2332, "lr": 4.8326808849565936e-05, "epoch": 3.4295302013422817, "percentage": 11.71, "elapsed_time": "1:06:49", "remaining_time": "8:23:47", "throughput": 1681.75, "total_tokens": 6743408} {"current_steps": 131, "total_steps": 1110, "loss": 0.18, "lr": 4.830126510672309e-05, "epoch": 3.4563758389261743, "percentage": 11.8, "elapsed_time": "1:07:18", "remaining_time": "8:23:04", "throughput": 1681.3, "total_tokens": 6790704} {"current_steps": 132, "total_steps": 1110, "loss": 0.1964, "lr": 4.827553471172935e-05, "epoch": 3.4832214765100673, "percentage": 11.89, "elapsed_time": "1:07:44", "remaining_time": "8:21:56", "throughput": 1682.54, "total_tokens": 6839200} {"current_steps": 133, "total_steps": 1110, "loss": 0.2116, "lr": 4.824961787069511e-05, "epoch": 3.51006711409396, "percentage": 11.98, "elapsed_time": "1:08:16", "remaining_time": "8:21:29", "throughput": 1682.75, "total_tokens": 6892832} {"current_steps": 134, "total_steps": 1110, "loss": 0.2071, "lr": 4.822351479122432e-05, "epoch": 3.5369127516778525, "percentage": 12.07, "elapsed_time": "1:08:51", "remaining_time": "8:21:35", "throughput": 1681.9, "total_tokens": 6949464} {"current_steps": 135, "total_steps": 1110, "loss": 0.175, "lr": 4.819722568241274e-05, "epoch": 3.563758389261745, "percentage": 12.16, "elapsed_time": "1:09:17", "remaining_time": "8:20:28", "throughput": 1682.72, "total_tokens": 6996480} {"current_steps": 136, "total_steps": 1110, "loss": 0.237, "lr": 4.817075075484629e-05, "epoch": 3.5906040268456376, "percentage": 12.25, "elapsed_time": "1:09:51", "remaining_time": "8:20:15", "throughput": 1683.02, "total_tokens": 7053720} {"current_steps": 137, "total_steps": 1110, "loss": 0.2176, "lr": 4.8144090220599416e-05, "epoch": 3.61744966442953, "percentage": 12.34, "elapsed_time": "1:10:28", "remaining_time": "8:20:32", "throughput": 1681.74, "total_tokens": 7111480} {"current_steps": 138, "total_steps": 1110, "loss": 0.2164, "lr": 4.811724429323329e-05, "epoch": 3.6442953020134228, "percentage": 12.43, "elapsed_time": "1:11:01", "remaining_time": "8:20:13", "throughput": 1681.61, "total_tokens": 7165728} {"current_steps": 139, "total_steps": 1110, "loss": 0.1876, "lr": 4.809021318779419e-05, "epoch": 3.6711409395973154, "percentage": 12.52, "elapsed_time": "1:11:21", "remaining_time": "8:18:32", "throughput": 1683.25, "total_tokens": 7207648} {"current_steps": 140, "total_steps": 1110, "loss": 0.2697, "lr": 4.806299712081172e-05, "epoch": 3.697986577181208, "percentage": 12.61, "elapsed_time": "1:11:47", "remaining_time": "8:17:26", "throughput": 1684.0, "total_tokens": 7254280} {"current_steps": 141, "total_steps": 1110, "loss": 0.1955, "lr": 4.8035596310297124e-05, "epoch": 3.7248322147651005, "percentage": 12.7, "elapsed_time": "1:12:14", "remaining_time": "8:16:26", "throughput": 1683.79, "total_tokens": 7297912} {"current_steps": 142, "total_steps": 1110, "loss": 0.2048, "lr": 4.800801097574149e-05, "epoch": 3.751677852348993, "percentage": 12.79, "elapsed_time": "1:12:40", "remaining_time": "8:15:24", "throughput": 1684.09, "total_tokens": 7343304} {"current_steps": 143, "total_steps": 1110, "loss": 0.2062, "lr": 4.798024133811403e-05, "epoch": 3.778523489932886, "percentage": 12.88, "elapsed_time": "1:13:06", "remaining_time": "8:14:25", "throughput": 1684.93, "total_tokens": 7391688} {"current_steps": 144, "total_steps": 1110, "loss": 0.2123, "lr": 4.795228761986028e-05, "epoch": 3.8053691275167782, "percentage": 12.97, "elapsed_time": "1:13:39", "remaining_time": "8:14:10", "throughput": 1685.09, "total_tokens": 7448016} {"current_steps": 145, "total_steps": 1110, "loss": 0.2128, "lr": 4.792415004490034e-05, "epoch": 3.8322147651006713, "percentage": 13.06, "elapsed_time": "1:14:08", "remaining_time": "8:13:27", "throughput": 1684.81, "total_tokens": 7495312} {"current_steps": 146, "total_steps": 1110, "loss": 0.207, "lr": 4.789582883862708e-05, "epoch": 3.859060402684564, "percentage": 13.15, "elapsed_time": "1:14:48", "remaining_time": "8:13:57", "throughput": 1682.58, "total_tokens": 7552600} {"current_steps": 147, "total_steps": 1110, "loss": 0.2227, "lr": 4.786732422790432e-05, "epoch": 3.8859060402684564, "percentage": 13.24, "elapsed_time": "1:15:28", "remaining_time": "8:14:27", "throughput": 1681.49, "total_tokens": 7615064} {"current_steps": 148, "total_steps": 1110, "loss": 0.2296, "lr": 4.783863644106502e-05, "epoch": 3.912751677852349, "percentage": 13.33, "elapsed_time": "1:16:03", "remaining_time": "8:14:20", "throughput": 1681.25, "total_tokens": 7671712} {"current_steps": 149, "total_steps": 1110, "loss": 0.1989, "lr": 4.780976570790947e-05, "epoch": 3.9395973154362416, "percentage": 13.42, "elapsed_time": "1:16:26", "remaining_time": "8:13:02", "throughput": 1681.82, "total_tokens": 7713880} {"current_steps": 150, "total_steps": 1110, "loss": 0.2485, "lr": 4.77807122597034e-05, "epoch": 3.966442953020134, "percentage": 13.51, "elapsed_time": "1:16:57", "remaining_time": "8:12:30", "throughput": 1682.11, "total_tokens": 7766672} {"current_steps": 151, "total_steps": 1110, "loss": 0.1962, "lr": 4.775147632917617e-05, "epoch": 3.9932885906040267, "percentage": 13.6, "elapsed_time": "1:17:37", "remaining_time": "8:13:00", "throughput": 1682.36, "total_tokens": 7835800} {"current_steps": 152, "total_steps": 1110, "loss": 0.2309, "lr": 4.7722058150518914e-05, "epoch": 4.0, "percentage": 13.69, "elapsed_time": "1:17:43", "remaining_time": "8:09:52", "throughput": 1682.65, "total_tokens": 7847232} {"current_steps": 153, "total_steps": 1110, "loss": 0.2234, "lr": 4.769245795938261e-05, "epoch": 4.026845637583893, "percentage": 13.78, "elapsed_time": "1:18:13", "remaining_time": "8:09:15", "throughput": 1682.17, "total_tokens": 7894656} {"current_steps": 154, "total_steps": 1110, "loss": 0.1936, "lr": 4.766267599287625e-05, "epoch": 4.053691275167785, "percentage": 13.87, "elapsed_time": "1:18:52", "remaining_time": "8:09:37", "throughput": 1681.54, "total_tokens": 7957712} {"current_steps": 155, "total_steps": 1110, "loss": 0.1859, "lr": 4.7632712489564926e-05, "epoch": 4.080536912751678, "percentage": 13.96, "elapsed_time": "1:19:19", "remaining_time": "8:08:41", "throughput": 1682.13, "total_tokens": 8005344} {"current_steps": 156, "total_steps": 1110, "loss": 0.1705, "lr": 4.760256768946787e-05, "epoch": 4.10738255033557, "percentage": 14.05, "elapsed_time": "1:19:53", "remaining_time": "8:08:31", "throughput": 1682.66, "total_tokens": 8065064} {"current_steps": 157, "total_steps": 1110, "loss": 0.1845, "lr": 4.7572241834056616e-05, "epoch": 4.134228187919463, "percentage": 14.14, "elapsed_time": "1:20:25", "remaining_time": "8:08:11", "throughput": 1683.19, "total_tokens": 8122464} {"current_steps": 158, "total_steps": 1110, "loss": 0.2019, "lr": 4.7541735166252986e-05, "epoch": 4.1610738255033555, "percentage": 14.23, "elapsed_time": "1:20:51", "remaining_time": "8:07:12", "throughput": 1683.84, "total_tokens": 8169408} {"current_steps": 159, "total_steps": 1110, "loss": 0.2003, "lr": 4.751104793042722e-05, "epoch": 4.1879194630872485, "percentage": 14.32, "elapsed_time": "1:21:30", "remaining_time": "8:07:30", "throughput": 1682.19, "total_tokens": 8226728} {"current_steps": 160, "total_steps": 1110, "loss": 0.1931, "lr": 4.748018037239592e-05, "epoch": 4.214765100671141, "percentage": 14.41, "elapsed_time": "1:22:13", "remaining_time": "8:08:09", "throughput": 1679.55, "total_tokens": 8285288} {"current_steps": 161, "total_steps": 1110, "loss": 0.2145, "lr": 4.74491327394202e-05, "epoch": 4.241610738255034, "percentage": 14.5, "elapsed_time": "1:22:35", "remaining_time": "8:06:50", "throughput": 1680.83, "total_tokens": 8329624} {"current_steps": 162, "total_steps": 1110, "loss": 0.1892, "lr": 4.7417905280203594e-05, "epoch": 4.268456375838926, "percentage": 14.59, "elapsed_time": "1:23:01", "remaining_time": "8:05:53", "throughput": 1681.17, "total_tokens": 8375536} {"current_steps": 163, "total_steps": 1110, "loss": 0.206, "lr": 4.7386498244890146e-05, "epoch": 4.295302013422819, "percentage": 14.68, "elapsed_time": "1:23:37", "remaining_time": "8:05:48", "throughput": 1680.88, "total_tokens": 8433088} {"current_steps": 164, "total_steps": 1110, "loss": 0.1692, "lr": 4.735491188506237e-05, "epoch": 4.322147651006711, "percentage": 14.77, "elapsed_time": "1:24:03", "remaining_time": "8:04:55", "throughput": 1681.41, "total_tokens": 8480984} {"current_steps": 165, "total_steps": 1110, "loss": 0.2201, "lr": 4.732314645373921e-05, "epoch": 4.348993288590604, "percentage": 14.86, "elapsed_time": "1:24:34", "remaining_time": "8:04:22", "throughput": 1681.41, "total_tokens": 8532168} {"current_steps": 166, "total_steps": 1110, "loss": 0.1763, "lr": 4.7291202205374086e-05, "epoch": 4.375838926174497, "percentage": 14.95, "elapsed_time": "1:25:00", "remaining_time": "8:03:26", "throughput": 1682.02, "total_tokens": 8579384} {"current_steps": 167, "total_steps": 1110, "loss": 0.1781, "lr": 4.7259079395852776e-05, "epoch": 4.402684563758389, "percentage": 15.05, "elapsed_time": "1:25:27", "remaining_time": "8:02:35", "throughput": 1682.28, "total_tokens": 8626592} {"current_steps": 168, "total_steps": 1110, "loss": 0.2067, "lr": 4.7226778282491424e-05, "epoch": 4.429530201342282, "percentage": 15.14, "elapsed_time": "1:26:01", "remaining_time": "8:02:22", "throughput": 1681.67, "total_tokens": 8680320} {"current_steps": 169, "total_steps": 1110, "loss": 0.1795, "lr": 4.719429912403445e-05, "epoch": 4.456375838926174, "percentage": 15.23, "elapsed_time": "1:26:40", "remaining_time": "8:02:37", "throughput": 1680.69, "total_tokens": 8740824} {"current_steps": 170, "total_steps": 1110, "loss": 0.2021, "lr": 4.7161642180652464e-05, "epoch": 4.483221476510067, "percentage": 15.32, "elapsed_time": "1:27:08", "remaining_time": "8:01:50", "throughput": 1681.02, "total_tokens": 8789312} {"current_steps": 171, "total_steps": 1110, "loss": 0.1916, "lr": 4.712880771394024e-05, "epoch": 4.510067114093959, "percentage": 15.41, "elapsed_time": "1:27:37", "remaining_time": "8:01:08", "throughput": 1681.22, "total_tokens": 8838400} {"current_steps": 172, "total_steps": 1110, "loss": 0.1852, "lr": 4.709579598691456e-05, "epoch": 4.5369127516778525, "percentage": 15.5, "elapsed_time": "1:28:01", "remaining_time": "8:00:00", "throughput": 1682.06, "total_tokens": 8883320} {"current_steps": 173, "total_steps": 1110, "loss": 0.162, "lr": 4.7062607264012124e-05, "epoch": 4.563758389261745, "percentage": 15.59, "elapsed_time": "1:28:26", "remaining_time": "7:59:03", "throughput": 1682.92, "total_tokens": 8931240} {"current_steps": 174, "total_steps": 1110, "loss": 0.1763, "lr": 4.7029241811087457e-05, "epoch": 4.590604026845638, "percentage": 15.68, "elapsed_time": "1:28:58", "remaining_time": "7:58:38", "throughput": 1682.51, "total_tokens": 8982280} {"current_steps": 175, "total_steps": 1110, "loss": 0.2005, "lr": 4.699569989541074e-05, "epoch": 4.617449664429531, "percentage": 15.77, "elapsed_time": "1:29:24", "remaining_time": "7:57:39", "throughput": 1683.02, "total_tokens": 9027824} {"current_steps": 176, "total_steps": 1110, "loss": 0.1985, "lr": 4.69619817856657e-05, "epoch": 4.644295302013423, "percentage": 15.86, "elapsed_time": "1:29:53", "remaining_time": "7:57:00", "throughput": 1683.91, "total_tokens": 9081584} {"current_steps": 177, "total_steps": 1110, "loss": 0.1963, "lr": 4.692808775194745e-05, "epoch": 4.671140939597316, "percentage": 15.95, "elapsed_time": "1:30:29", "remaining_time": "7:57:02", "throughput": 1683.64, "total_tokens": 9142112} {"current_steps": 178, "total_steps": 1110, "loss": 0.1691, "lr": 4.68940180657603e-05, "epoch": 4.697986577181208, "percentage": 16.04, "elapsed_time": "1:30:56", "remaining_time": "7:56:10", "throughput": 1684.23, "total_tokens": 9190280} {"current_steps": 179, "total_steps": 1110, "loss": 0.1896, "lr": 4.685977300001565e-05, "epoch": 4.724832214765101, "percentage": 16.13, "elapsed_time": "1:31:25", "remaining_time": "7:55:31", "throughput": 1684.52, "total_tokens": 9240592} {"current_steps": 180, "total_steps": 1110, "loss": 0.1724, "lr": 4.6825352829029705e-05, "epoch": 4.751677852348993, "percentage": 16.22, "elapsed_time": "1:31:58", "remaining_time": "7:55:10", "throughput": 1684.35, "total_tokens": 9294464} {"current_steps": 181, "total_steps": 1110, "loss": 0.1698, "lr": 4.679075782852137e-05, "epoch": 4.778523489932886, "percentage": 16.31, "elapsed_time": "1:32:29", "remaining_time": "7:54:45", "throughput": 1684.65, "total_tokens": 9349552} {"current_steps": 182, "total_steps": 1110, "loss": 0.2092, "lr": 4.675598827560998e-05, "epoch": 4.805369127516778, "percentage": 16.4, "elapsed_time": "1:33:10", "remaining_time": "7:55:05", "throughput": 1683.08, "total_tokens": 9409136} {"current_steps": 183, "total_steps": 1110, "loss": 0.1763, "lr": 4.67210444488131e-05, "epoch": 4.832214765100671, "percentage": 16.49, "elapsed_time": "1:33:29", "remaining_time": "7:53:35", "throughput": 1683.57, "total_tokens": 9444096} {"current_steps": 184, "total_steps": 1110, "loss": 0.219, "lr": 4.668592662804432e-05, "epoch": 4.859060402684563, "percentage": 16.58, "elapsed_time": "1:34:14", "remaining_time": "7:54:16", "throughput": 1681.63, "total_tokens": 9508552} {"current_steps": 185, "total_steps": 1110, "loss": 0.1856, "lr": 4.665063509461097e-05, "epoch": 4.885906040268456, "percentage": 16.67, "elapsed_time": "1:34:46", "remaining_time": "7:53:52", "throughput": 1681.92, "total_tokens": 9564224} {"current_steps": 186, "total_steps": 1110, "loss": 0.1747, "lr": 4.661517013121189e-05, "epoch": 4.912751677852349, "percentage": 16.76, "elapsed_time": "1:35:20", "remaining_time": "7:53:37", "throughput": 1681.77, "total_tokens": 9620384} {"current_steps": 187, "total_steps": 1110, "loss": 0.1685, "lr": 4.657953202193516e-05, "epoch": 4.939597315436242, "percentage": 16.85, "elapsed_time": "1:35:53", "remaining_time": "7:53:19", "throughput": 1682.33, "total_tokens": 9679824} {"current_steps": 188, "total_steps": 1110, "loss": 0.1636, "lr": 4.654372105225583e-05, "epoch": 4.966442953020135, "percentage": 16.94, "elapsed_time": "1:36:23", "remaining_time": "7:52:44", "throughput": 1682.74, "total_tokens": 9732328} {"current_steps": 189, "total_steps": 1110, "loss": 0.1429, "lr": 4.650773750903363e-05, "epoch": 4.993288590604027, "percentage": 17.03, "elapsed_time": "1:37:00", "remaining_time": "7:52:45", "throughput": 1682.44, "total_tokens": 9793456} {"current_steps": 190, "total_steps": 1110, "loss": 0.1757, "lr": 4.647158168051066e-05, "epoch": 5.0, "percentage": 17.12, "elapsed_time": "1:37:10", "remaining_time": "7:50:32", "throughput": 1682.31, "total_tokens": 9809040} {"current_steps": 191, "total_steps": 1110, "loss": 0.1711, "lr": 4.6435253856309094e-05, "epoch": 5.026845637583893, "percentage": 17.21, "elapsed_time": "1:37:41", "remaining_time": "7:50:02", "throughput": 1682.81, "total_tokens": 9863696} {"current_steps": 192, "total_steps": 1110, "loss": 0.156, "lr": 4.639875432742886e-05, "epoch": 5.053691275167785, "percentage": 17.3, "elapsed_time": "1:38:07", "remaining_time": "7:49:08", "throughput": 1682.76, "total_tokens": 9906912} {"current_steps": 193, "total_steps": 1110, "loss": 0.17, "lr": 4.636208338624533e-05, "epoch": 5.080536912751678, "percentage": 17.39, "elapsed_time": "1:38:30", "remaining_time": "7:48:02", "throughput": 1683.48, "total_tokens": 9950056} {"current_steps": 194, "total_steps": 1110, "loss": 0.1882, "lr": 4.6325241326506915e-05, "epoch": 5.10738255033557, "percentage": 17.48, "elapsed_time": "1:39:00", "remaining_time": "7:47:29", "throughput": 1683.57, "total_tokens": 10001296} {"current_steps": 195, "total_steps": 1110, "loss": 0.1564, "lr": 4.628822844333278e-05, "epoch": 5.134228187919463, "percentage": 17.57, "elapsed_time": "1:39:30", "remaining_time": "7:46:55", "throughput": 1683.76, "total_tokens": 10052888} {"current_steps": 196, "total_steps": 1110, "loss": 0.1606, "lr": 4.625104503321045e-05, "epoch": 5.1610738255033555, "percentage": 17.66, "elapsed_time": "1:40:01", "remaining_time": "7:46:28", "throughput": 1684.47, "total_tokens": 10109912} {"current_steps": 197, "total_steps": 1110, "loss": 0.1722, "lr": 4.621369139399341e-05, "epoch": 5.1879194630872485, "percentage": 17.75, "elapsed_time": "1:40:24", "remaining_time": "7:45:20", "throughput": 1684.96, "total_tokens": 10151104} {"current_steps": 198, "total_steps": 1110, "loss": 0.1679, "lr": 4.6176167824898773e-05, "epoch": 5.214765100671141, "percentage": 17.84, "elapsed_time": "1:40:51", "remaining_time": "7:44:31", "throughput": 1685.05, "total_tokens": 10196304} {"current_steps": 199, "total_steps": 1110, "loss": 0.1548, "lr": 4.613847462650486e-05, "epoch": 5.241610738255034, "percentage": 17.93, "elapsed_time": "1:41:29", "remaining_time": "7:44:37", "throughput": 1684.06, "total_tokens": 10255152} {"current_steps": 200, "total_steps": 1110, "loss": 0.166, "lr": 4.6100612100748765e-05, "epoch": 5.268456375838926, "percentage": 18.02, "elapsed_time": "1:41:52", "remaining_time": "7:43:30", "throughput": 1684.33, "total_tokens": 10294912} {"current_steps": 201, "total_steps": 1110, "loss": 0.1648, "lr": 4.606258055092397e-05, "epoch": 5.295302013422819, "percentage": 18.11, "elapsed_time": "1:42:30", "remaining_time": "7:43:35", "throughput": 1683.94, "total_tokens": 10357248} {"current_steps": 202, "total_steps": 1110, "loss": 0.1419, "lr": 4.602438028167792e-05, "epoch": 5.322147651006711, "percentage": 18.2, "elapsed_time": "1:43:03", "remaining_time": "7:43:14", "throughput": 1683.79, "total_tokens": 10411456} {"current_steps": 203, "total_steps": 1110, "loss": 0.1935, "lr": 4.5986011599009544e-05, "epoch": 5.348993288590604, "percentage": 18.29, "elapsed_time": "1:43:31", "remaining_time": "7:42:32", "throughput": 1684.33, "total_tokens": 10462080} {"current_steps": 204, "total_steps": 1110, "loss": 0.1449, "lr": 4.594747481026684e-05, "epoch": 5.375838926174497, "percentage": 18.38, "elapsed_time": "1:44:13", "remaining_time": "7:42:52", "throughput": 1683.94, "total_tokens": 10530312} {"current_steps": 205, "total_steps": 1110, "loss": 0.1548, "lr": 4.59087702241444e-05, "epoch": 5.402684563758389, "percentage": 18.47, "elapsed_time": "1:44:53", "remaining_time": "7:43:04", "throughput": 1683.13, "total_tokens": 10593232} {"current_steps": 206, "total_steps": 1110, "loss": 0.2084, "lr": 4.586989815068095e-05, "epoch": 5.429530201342282, "percentage": 18.56, "elapsed_time": "1:45:36", "remaining_time": "7:43:27", "throughput": 1682.51, "total_tokens": 10661464} {"current_steps": 207, "total_steps": 1110, "loss": 0.1527, "lr": 4.5830858901256826e-05, "epoch": 5.456375838926174, "percentage": 18.65, "elapsed_time": "1:46:01", "remaining_time": "7:42:30", "throughput": 1682.76, "total_tokens": 10704912} {"current_steps": 208, "total_steps": 1110, "loss": 0.1515, "lr": 4.579165278859152e-05, "epoch": 5.483221476510067, "percentage": 18.74, "elapsed_time": "1:46:29", "remaining_time": "7:41:46", "throughput": 1682.66, "total_tokens": 10750792} {"current_steps": 209, "total_steps": 1110, "loss": 0.155, "lr": 4.575228012674118e-05, "epoch": 5.510067114093959, "percentage": 18.83, "elapsed_time": "1:47:04", "remaining_time": "7:41:37", "throughput": 1683.84, "total_tokens": 10818288} {"current_steps": 210, "total_steps": 1110, "loss": 0.1514, "lr": 4.571274123109606e-05, "epoch": 5.5369127516778525, "percentage": 18.92, "elapsed_time": "1:47:36", "remaining_time": "7:41:10", "throughput": 1683.81, "total_tokens": 10871488} {"current_steps": 211, "total_steps": 1110, "loss": 0.1645, "lr": 4.5673036418378006e-05, "epoch": 5.563758389261745, "percentage": 19.01, "elapsed_time": "1:48:06", "remaining_time": "7:40:37", "throughput": 1684.25, "total_tokens": 10925024} {"current_steps": 212, "total_steps": 1110, "loss": 0.1532, "lr": 4.563316600663795e-05, "epoch": 5.590604026845638, "percentage": 19.1, "elapsed_time": "1:48:41", "remaining_time": "7:40:22", "throughput": 1684.1, "total_tokens": 10982200} {"current_steps": 213, "total_steps": 1110, "loss": 0.1754, "lr": 4.559313031525331e-05, "epoch": 5.617449664429531, "percentage": 19.19, "elapsed_time": "1:49:08", "remaining_time": "7:39:38", "throughput": 1684.29, "total_tokens": 11029976} {"current_steps": 214, "total_steps": 1110, "loss": 0.1611, "lr": 4.555292966492547e-05, "epoch": 5.644295302013423, "percentage": 19.28, "elapsed_time": "1:49:42", "remaining_time": "7:39:19", "throughput": 1684.11, "total_tokens": 11085192} {"current_steps": 215, "total_steps": 1110, "loss": 0.1856, "lr": 4.551256437767719e-05, "epoch": 5.671140939597316, "percentage": 19.37, "elapsed_time": "1:50:07", "remaining_time": "7:38:25", "throughput": 1684.79, "total_tokens": 11132072} {"current_steps": 216, "total_steps": 1110, "loss": 0.1658, "lr": 4.547203477685005e-05, "epoch": 5.697986577181208, "percentage": 19.46, "elapsed_time": "1:50:52", "remaining_time": "7:38:53", "throughput": 1682.95, "total_tokens": 11195808} {"current_steps": 217, "total_steps": 1110, "loss": 0.1649, "lr": 4.543134118710184e-05, "epoch": 5.724832214765101, "percentage": 19.55, "elapsed_time": "1:51:21", "remaining_time": "7:38:14", "throughput": 1683.04, "total_tokens": 11244688} {"current_steps": 218, "total_steps": 1110, "loss": 0.1582, "lr": 4.539048393440395e-05, "epoch": 5.751677852348993, "percentage": 19.64, "elapsed_time": "1:51:53", "remaining_time": "7:37:48", "throughput": 1683.08, "total_tokens": 11298888} {"current_steps": 219, "total_steps": 1110, "loss": 0.1624, "lr": 4.534946334603879e-05, "epoch": 5.778523489932886, "percentage": 19.73, "elapsed_time": "1:52:20", "remaining_time": "7:37:02", "throughput": 1683.25, "total_tokens": 11345304} {"current_steps": 220, "total_steps": 1110, "loss": 0.1548, "lr": 4.530827975059715e-05, "epoch": 5.805369127516778, "percentage": 19.82, "elapsed_time": "1:52:42", "remaining_time": "7:35:56", "throughput": 1684.01, "total_tokens": 11387752} {"current_steps": 221, "total_steps": 1110, "loss": 0.1478, "lr": 4.526693347797557e-05, "epoch": 5.832214765100671, "percentage": 19.91, "elapsed_time": "1:53:06", "remaining_time": "7:34:58", "throughput": 1684.71, "total_tokens": 11432728} {"current_steps": 222, "total_steps": 1110, "loss": 0.1313, "lr": 4.522542485937369e-05, "epoch": 5.859060402684563, "percentage": 20.0, "elapsed_time": "1:53:44", "remaining_time": "7:34:59", "throughput": 1683.98, "total_tokens": 11493064} {"current_steps": 223, "total_steps": 1110, "loss": 0.1719, "lr": 4.518375422729161e-05, "epoch": 5.885906040268456, "percentage": 20.09, "elapsed_time": "1:54:12", "remaining_time": "7:34:14", "throughput": 1684.5, "total_tokens": 11542392} {"current_steps": 224, "total_steps": 1110, "loss": 0.1587, "lr": 4.5141921915527216e-05, "epoch": 5.912751677852349, "percentage": 20.18, "elapsed_time": "1:54:46", "remaining_time": "7:33:56", "throughput": 1684.04, "total_tokens": 11596408} {"current_steps": 225, "total_steps": 1110, "loss": 0.1751, "lr": 4.5099928259173516e-05, "epoch": 5.939597315436242, "percentage": 20.27, "elapsed_time": "1:55:21", "remaining_time": "7:33:45", "throughput": 1684.15, "total_tokens": 11657288} {"current_steps": 226, "total_steps": 1110, "loss": 0.1532, "lr": 4.505777359461595e-05, "epoch": 5.966442953020135, "percentage": 20.36, "elapsed_time": "1:55:56", "remaining_time": "7:33:29", "throughput": 1684.04, "total_tokens": 11714680} {"current_steps": 227, "total_steps": 1110, "loss": 0.1638, "lr": 4.50154582595297e-05, "epoch": 5.993288590604027, "percentage": 20.45, "elapsed_time": "1:56:15", "remaining_time": "7:32:11", "throughput": 1684.85, "total_tokens": 11751840} {"current_steps": 228, "total_steps": 1110, "loss": 0.118, "lr": 4.497298259287696e-05, "epoch": 6.0, "percentage": 20.54, "elapsed_time": "1:56:25", "remaining_time": "7:30:21", "throughput": 1685.13, "total_tokens": 11770848} {"current_steps": 229, "total_steps": 1110, "loss": 0.1428, "lr": 4.493034693490427e-05, "epoch": 6.026845637583893, "percentage": 20.63, "elapsed_time": "1:56:54", "remaining_time": "7:29:44", "throughput": 1685.45, "total_tokens": 11821848} {"current_steps": 230, "total_steps": 1110, "loss": 0.1504, "lr": 4.488755162713975e-05, "epoch": 6.053691275167785, "percentage": 20.72, "elapsed_time": "1:57:22", "remaining_time": "7:29:05", "throughput": 1685.35, "total_tokens": 11869152} {"current_steps": 231, "total_steps": 1110, "loss": 0.161, "lr": 4.484459701239038e-05, "epoch": 6.080536912751678, "percentage": 20.81, "elapsed_time": "1:57:51", "remaining_time": "7:28:28", "throughput": 1685.25, "total_tokens": 11917464} {"current_steps": 232, "total_steps": 1110, "loss": 0.1354, "lr": 4.480148343473923e-05, "epoch": 6.10738255033557, "percentage": 20.9, "elapsed_time": "1:58:17", "remaining_time": "7:27:39", "throughput": 1685.47, "total_tokens": 11962184} {"current_steps": 233, "total_steps": 1110, "loss": 0.1328, "lr": 4.475821123954275e-05, "epoch": 6.134228187919463, "percentage": 20.99, "elapsed_time": "1:58:41", "remaining_time": "7:26:43", "throughput": 1685.86, "total_tokens": 12005088} {"current_steps": 234, "total_steps": 1110, "loss": 0.1532, "lr": 4.471478077342798e-05, "epoch": 6.1610738255033555, "percentage": 21.08, "elapsed_time": "1:59:14", "remaining_time": "7:26:24", "throughput": 1685.41, "total_tokens": 12058808} {"current_steps": 235, "total_steps": 1110, "loss": 0.1316, "lr": 4.467119238428975e-05, "epoch": 6.1879194630872485, "percentage": 21.17, "elapsed_time": "1:59:53", "remaining_time": "7:26:25", "throughput": 1685.66, "total_tokens": 12126248} {"current_steps": 236, "total_steps": 1110, "loss": 0.1279, "lr": 4.4627446421287935e-05, "epoch": 6.214765100671141, "percentage": 21.26, "elapsed_time": "2:00:29", "remaining_time": "7:26:12", "throughput": 1685.81, "total_tokens": 12186960} {"current_steps": 237, "total_steps": 1110, "loss": 0.1389, "lr": 4.4583543234844616e-05, "epoch": 6.241610738255034, "percentage": 21.35, "elapsed_time": "2:01:01", "remaining_time": "7:25:47", "throughput": 1686.49, "total_tokens": 12246416} {"current_steps": 238, "total_steps": 1110, "loss": 0.1439, "lr": 4.4539483176641304e-05, "epoch": 6.268456375838926, "percentage": 21.44, "elapsed_time": "2:01:35", "remaining_time": "7:25:28", "throughput": 1686.22, "total_tokens": 12301360} {"current_steps": 239, "total_steps": 1110, "loss": 0.1386, "lr": 4.4495266599616136e-05, "epoch": 6.295302013422819, "percentage": 21.53, "elapsed_time": "2:02:01", "remaining_time": "7:24:41", "throughput": 1686.58, "total_tokens": 12347960} {"current_steps": 240, "total_steps": 1110, "loss": 0.1562, "lr": 4.445089385796099e-05, "epoch": 6.322147651006711, "percentage": 21.62, "elapsed_time": "2:02:32", "remaining_time": "7:24:11", "throughput": 1686.52, "total_tokens": 12399640} {"current_steps": 241, "total_steps": 1110, "loss": 0.1364, "lr": 4.4406365307118703e-05, "epoch": 6.348993288590604, "percentage": 21.71, "elapsed_time": "2:03:01", "remaining_time": "7:23:36", "throughput": 1686.82, "total_tokens": 12451256} {"current_steps": 242, "total_steps": 1110, "loss": 0.1404, "lr": 4.4361681303780195e-05, "epoch": 6.375838926174497, "percentage": 21.8, "elapsed_time": "2:03:27", "remaining_time": "7:22:48", "throughput": 1687.14, "total_tokens": 12497184} {"current_steps": 243, "total_steps": 1110, "loss": 0.1622, "lr": 4.431684220588163e-05, "epoch": 6.402684563758389, "percentage": 21.89, "elapsed_time": "2:04:02", "remaining_time": "7:22:32", "throughput": 1686.55, "total_tokens": 12551512} {"current_steps": 244, "total_steps": 1110, "loss": 0.1497, "lr": 4.427184837260153e-05, "epoch": 6.429530201342282, "percentage": 21.98, "elapsed_time": "2:04:25", "remaining_time": "7:21:34", "throughput": 1687.31, "total_tokens": 12595808} {"current_steps": 245, "total_steps": 1110, "loss": 0.1504, "lr": 4.422670016435792e-05, "epoch": 6.456375838926174, "percentage": 22.07, "elapsed_time": "2:04:51", "remaining_time": "7:20:49", "throughput": 1688.52, "total_tokens": 12649504} {"current_steps": 246, "total_steps": 1110, "loss": 0.129, "lr": 4.418139794280541e-05, "epoch": 6.483221476510067, "percentage": 22.16, "elapsed_time": "2:05:17", "remaining_time": "7:20:03", "throughput": 1688.58, "total_tokens": 12694312} {"current_steps": 247, "total_steps": 1110, "loss": 0.1363, "lr": 4.413594207083234e-05, "epoch": 6.510067114093959, "percentage": 22.25, "elapsed_time": "2:05:43", "remaining_time": "7:19:15", "throughput": 1689.16, "total_tokens": 12741872} {"current_steps": 248, "total_steps": 1110, "loss": 0.1325, "lr": 4.409033291255782e-05, "epoch": 6.5369127516778525, "percentage": 22.34, "elapsed_time": "2:06:17", "remaining_time": "7:18:59", "throughput": 1689.0, "total_tokens": 12799032} {"current_steps": 249, "total_steps": 1110, "loss": 0.1501, "lr": 4.404457083332886e-05, "epoch": 6.563758389261745, "percentage": 22.43, "elapsed_time": "2:07:00", "remaining_time": "7:19:08", "throughput": 1687.72, "total_tokens": 12860432} {"current_steps": 250, "total_steps": 1110, "loss": 0.1375, "lr": 4.3998656199717435e-05, "epoch": 6.590604026845638, "percentage": 22.52, "elapsed_time": "2:07:28", "remaining_time": "7:18:29", "throughput": 1687.54, "total_tokens": 12906592} {"current_steps": 251, "total_steps": 1110, "loss": 0.1387, "lr": 4.395258937951753e-05, "epoch": 6.617449664429531, "percentage": 22.61, "elapsed_time": "2:08:03", "remaining_time": "7:18:16", "throughput": 1687.54, "total_tokens": 12966808} {"current_steps": 252, "total_steps": 1110, "loss": 0.1627, "lr": 4.3906370741742186e-05, "epoch": 6.644295302013423, "percentage": 22.7, "elapsed_time": "2:08:48", "remaining_time": "7:18:34", "throughput": 1685.47, "total_tokens": 13026504} {"current_steps": 253, "total_steps": 1110, "loss": 0.1509, "lr": 4.386000065662059e-05, "epoch": 6.671140939597316, "percentage": 22.79, "elapsed_time": "2:09:14", "remaining_time": "7:17:46", "throughput": 1685.57, "total_tokens": 13070176} {"current_steps": 254, "total_steps": 1110, "loss": 0.1298, "lr": 4.381347949559506e-05, "epoch": 6.697986577181208, "percentage": 22.88, "elapsed_time": "2:09:51", "remaining_time": "7:17:36", "throughput": 1684.77, "total_tokens": 13126104} {"current_steps": 255, "total_steps": 1110, "loss": 0.1396, "lr": 4.3766807631318106e-05, "epoch": 6.724832214765101, "percentage": 22.97, "elapsed_time": "2:10:23", "remaining_time": "7:17:12", "throughput": 1684.42, "total_tokens": 13178312} {"current_steps": 256, "total_steps": 1110, "loss": 0.1206, "lr": 4.371998543764943e-05, "epoch": 6.751677852348993, "percentage": 23.06, "elapsed_time": "2:10:56", "remaining_time": "7:16:48", "throughput": 1684.77, "total_tokens": 13236216} {"current_steps": 257, "total_steps": 1110, "loss": 0.1168, "lr": 4.367301328965291e-05, "epoch": 6.778523489932886, "percentage": 23.15, "elapsed_time": "2:11:31", "remaining_time": "7:16:31", "throughput": 1684.37, "total_tokens": 13291752} {"current_steps": 258, "total_steps": 1110, "loss": 0.1435, "lr": 4.3625891563593626e-05, "epoch": 6.805369127516778, "percentage": 23.24, "elapsed_time": "2:12:04", "remaining_time": "7:16:07", "throughput": 1684.73, "total_tokens": 13349872} {"current_steps": 259, "total_steps": 1110, "loss": 0.1216, "lr": 4.357862063693486e-05, "epoch": 6.832214765100671, "percentage": 23.33, "elapsed_time": "2:12:38", "remaining_time": "7:15:48", "throughput": 1684.61, "total_tokens": 13406328} {"current_steps": 260, "total_steps": 1110, "loss": 0.1269, "lr": 4.353120088833501e-05, "epoch": 6.859060402684563, "percentage": 23.42, "elapsed_time": "2:13:12", "remaining_time": "7:15:30", "throughput": 1683.87, "total_tokens": 13459016} {"current_steps": 261, "total_steps": 1110, "loss": 0.1441, "lr": 4.348363269764462e-05, "epoch": 6.885906040268456, "percentage": 23.51, "elapsed_time": "2:13:39", "remaining_time": "7:14:45", "throughput": 1684.09, "total_tokens": 13505008} {"current_steps": 262, "total_steps": 1110, "loss": 0.1136, "lr": 4.3435916445903296e-05, "epoch": 6.912751677852349, "percentage": 23.6, "elapsed_time": "2:14:12", "remaining_time": "7:14:23", "throughput": 1683.95, "total_tokens": 13559976} {"current_steps": 263, "total_steps": 1110, "loss": 0.1511, "lr": 4.3388052515336696e-05, "epoch": 6.939597315436242, "percentage": 23.69, "elapsed_time": "2:14:39", "remaining_time": "7:13:39", "throughput": 1684.31, "total_tokens": 13608168} {"current_steps": 264, "total_steps": 1110, "loss": 0.1307, "lr": 4.3340041289353415e-05, "epoch": 6.966442953020135, "percentage": 23.78, "elapsed_time": "2:15:07", "remaining_time": "7:12:59", "throughput": 1685.03, "total_tokens": 13660808} {"current_steps": 265, "total_steps": 1110, "loss": 0.1342, "lr": 4.329188315254196e-05, "epoch": 6.993288590604027, "percentage": 23.87, "elapsed_time": "2:15:38", "remaining_time": "7:12:31", "throughput": 1685.38, "total_tokens": 13716800} {"current_steps": 266, "total_steps": 1110, "loss": 0.1316, "lr": 4.324357849066764e-05, "epoch": 7.0, "percentage": 23.96, "elapsed_time": "2:15:49", "remaining_time": "7:10:57", "throughput": 1685.12, "total_tokens": 13732656} {"current_steps": 267, "total_steps": 1110, "loss": 0.12, "lr": 4.319512769066949e-05, "epoch": 7.026845637583893, "percentage": 24.05, "elapsed_time": "2:16:10", "remaining_time": "7:09:55", "throughput": 1685.75, "total_tokens": 13772968} {"current_steps": 268, "total_steps": 1110, "loss": 0.1223, "lr": 4.3146531140657176e-05, "epoch": 7.053691275167785, "percentage": 24.14, "elapsed_time": "2:16:40", "remaining_time": "7:09:25", "throughput": 1685.66, "total_tokens": 13823688} {"current_steps": 269, "total_steps": 1110, "loss": 0.1282, "lr": 4.309778922990786e-05, "epoch": 7.080536912751678, "percentage": 24.23, "elapsed_time": "2:17:17", "remaining_time": "7:09:12", "throughput": 1685.81, "total_tokens": 13886264} {"current_steps": 270, "total_steps": 1110, "loss": 0.1336, "lr": 4.3048902348863116e-05, "epoch": 7.10738255033557, "percentage": 24.32, "elapsed_time": "2:17:58", "remaining_time": "7:09:14", "throughput": 1684.53, "total_tokens": 13944672} {"current_steps": 271, "total_steps": 1110, "loss": 0.121, "lr": 4.299987088912577e-05, "epoch": 7.134228187919463, "percentage": 24.41, "elapsed_time": "2:18:31", "remaining_time": "7:08:50", "throughput": 1684.49, "total_tokens": 13999968} {"current_steps": 272, "total_steps": 1110, "loss": 0.1186, "lr": 4.295069524345681e-05, "epoch": 7.1610738255033555, "percentage": 24.5, "elapsed_time": "2:19:03", "remaining_time": "7:08:25", "throughput": 1684.45, "total_tokens": 14054224} {"current_steps": 273, "total_steps": 1110, "loss": 0.1355, "lr": 4.290137580577216e-05, "epoch": 7.1879194630872485, "percentage": 24.59, "elapsed_time": "2:19:33", "remaining_time": "7:07:52", "throughput": 1684.66, "total_tokens": 14106328} {"current_steps": 274, "total_steps": 1110, "loss": 0.1239, "lr": 4.285191297113962e-05, "epoch": 7.214765100671141, "percentage": 24.68, "elapsed_time": "2:20:00", "remaining_time": "7:07:09", "throughput": 1685.07, "total_tokens": 14154608} {"current_steps": 275, "total_steps": 1110, "loss": 0.129, "lr": 4.280230713577564e-05, "epoch": 7.241610738255034, "percentage": 24.77, "elapsed_time": "2:20:29", "remaining_time": "7:06:34", "throughput": 1685.47, "total_tokens": 14207424} {"current_steps": 276, "total_steps": 1110, "loss": 0.117, "lr": 4.275255869704214e-05, "epoch": 7.268456375838926, "percentage": 24.86, "elapsed_time": "2:21:04", "remaining_time": "7:06:18", "throughput": 1685.6, "total_tokens": 14268200} {"current_steps": 277, "total_steps": 1110, "loss": 0.1202, "lr": 4.2702668053443394e-05, "epoch": 7.295302013422819, "percentage": 24.95, "elapsed_time": "2:21:32", "remaining_time": "7:05:38", "throughput": 1686.22, "total_tokens": 14319864} {"current_steps": 278, "total_steps": 1110, "loss": 0.1429, "lr": 4.265263560462275e-05, "epoch": 7.322147651006711, "percentage": 25.05, "elapsed_time": "2:22:02", "remaining_time": "7:05:04", "throughput": 1686.27, "total_tokens": 14370536} {"current_steps": 279, "total_steps": 1110, "loss": 0.1076, "lr": 4.260246175135948e-05, "epoch": 7.348993288590604, "percentage": 25.14, "elapsed_time": "2:22:38", "remaining_time": "7:04:51", "throughput": 1686.24, "total_tokens": 14431608} {"current_steps": 280, "total_steps": 1110, "loss": 0.109, "lr": 4.255214689556557e-05, "epoch": 7.375838926174497, "percentage": 25.23, "elapsed_time": "2:23:12", "remaining_time": "7:04:30", "throughput": 1685.97, "total_tokens": 14486360} {"current_steps": 281, "total_steps": 1110, "loss": 0.121, "lr": 4.2501691440282476e-05, "epoch": 7.402684563758389, "percentage": 25.32, "elapsed_time": "2:23:34", "remaining_time": "7:03:35", "throughput": 1686.5, "total_tokens": 14529160} {"current_steps": 282, "total_steps": 1110, "loss": 0.1183, "lr": 4.2451095789677945e-05, "epoch": 7.429530201342282, "percentage": 25.41, "elapsed_time": "2:24:00", "remaining_time": "7:02:51", "throughput": 1686.56, "total_tokens": 14573320} {"current_steps": 283, "total_steps": 1110, "loss": 0.1345, "lr": 4.24003603490427e-05, "epoch": 7.456375838926174, "percentage": 25.5, "elapsed_time": "2:24:32", "remaining_time": "7:02:24", "throughput": 1686.7, "total_tokens": 14628488} {"current_steps": 284, "total_steps": 1110, "loss": 0.1195, "lr": 4.234948552478726e-05, "epoch": 7.483221476510067, "percentage": 25.59, "elapsed_time": "2:24:55", "remaining_time": "7:01:31", "throughput": 1687.11, "total_tokens": 14670808} {"current_steps": 285, "total_steps": 1110, "loss": 0.1245, "lr": 4.229847172443866e-05, "epoch": 7.510067114093959, "percentage": 25.68, "elapsed_time": "2:25:22", "remaining_time": "7:00:49", "throughput": 1687.13, "total_tokens": 14716336} {"current_steps": 286, "total_steps": 1110, "loss": 0.1456, "lr": 4.2247319356637174e-05, "epoch": 7.5369127516778525, "percentage": 25.77, "elapsed_time": "2:26:15", "remaining_time": "7:01:22", "throughput": 1685.03, "total_tokens": 14786728} {"current_steps": 287, "total_steps": 1110, "loss": 0.1158, "lr": 4.219602883113306e-05, "epoch": 7.563758389261745, "percentage": 25.86, "elapsed_time": "2:26:48", "remaining_time": "7:00:59", "throughput": 1684.69, "total_tokens": 14839744} {"current_steps": 288, "total_steps": 1110, "loss": 0.1049, "lr": 4.214460055878329e-05, "epoch": 7.590604026845638, "percentage": 25.95, "elapsed_time": "2:27:18", "remaining_time": "7:00:27", "throughput": 1684.72, "total_tokens": 14891016} {"current_steps": 289, "total_steps": 1110, "loss": 0.1165, "lr": 4.209303495154822e-05, "epoch": 7.617449664429531, "percentage": 26.04, "elapsed_time": "2:27:51", "remaining_time": "7:00:03", "throughput": 1684.94, "total_tokens": 14948496} {"current_steps": 290, "total_steps": 1110, "loss": 0.12, "lr": 4.204133242248832e-05, "epoch": 7.644295302013423, "percentage": 26.13, "elapsed_time": "2:28:20", "remaining_time": "6:59:28", "throughput": 1685.33, "total_tokens": 15001096} {"current_steps": 291, "total_steps": 1110, "loss": 0.1135, "lr": 4.1989493385760864e-05, "epoch": 7.671140939597316, "percentage": 26.22, "elapsed_time": "2:28:56", "remaining_time": "6:59:09", "throughput": 1685.84, "total_tokens": 15064648} {"current_steps": 292, "total_steps": 1110, "loss": 0.1081, "lr": 4.193751825661658e-05, "epoch": 7.697986577181208, "percentage": 26.31, "elapsed_time": "2:29:20", "remaining_time": "6:58:22", "throughput": 1685.84, "total_tokens": 15106280} {"current_steps": 293, "total_steps": 1110, "loss": 0.1251, "lr": 4.188540745139638e-05, "epoch": 7.724832214765101, "percentage": 26.4, "elapsed_time": "2:29:39", "remaining_time": "6:57:19", "throughput": 1686.21, "total_tokens": 15142096} {"current_steps": 294, "total_steps": 1110, "loss": 0.1018, "lr": 4.1833161387527986e-05, "epoch": 7.751677852348993, "percentage": 26.49, "elapsed_time": "2:30:29", "remaining_time": "6:57:42", "throughput": 1684.78, "total_tokens": 15213520} {"current_steps": 295, "total_steps": 1110, "loss": 0.1049, "lr": 4.1780780483522575e-05, "epoch": 7.778523489932886, "percentage": 26.58, "elapsed_time": "2:30:57", "remaining_time": "6:57:03", "throughput": 1685.82, "total_tokens": 15269304} {"current_steps": 296, "total_steps": 1110, "loss": 0.1171, "lr": 4.172826515897146e-05, "epoch": 7.805369127516778, "percentage": 26.67, "elapsed_time": "2:31:29", "remaining_time": "6:56:37", "throughput": 1685.64, "total_tokens": 15322184} {"current_steps": 297, "total_steps": 1110, "loss": 0.1249, "lr": 4.167561583454272e-05, "epoch": 7.832214765100671, "percentage": 26.76, "elapsed_time": "2:31:55", "remaining_time": "6:55:51", "throughput": 1686.09, "total_tokens": 15369024} {"current_steps": 298, "total_steps": 1110, "loss": 0.0995, "lr": 4.162283293197782e-05, "epoch": 7.859060402684563, "percentage": 26.85, "elapsed_time": "2:32:29", "remaining_time": "6:55:30", "throughput": 1685.8, "total_tokens": 15424072} {"current_steps": 299, "total_steps": 1110, "loss": 0.1308, "lr": 4.156991687408822e-05, "epoch": 7.885906040268456, "percentage": 26.94, "elapsed_time": "2:32:56", "remaining_time": "6:54:50", "throughput": 1685.97, "total_tokens": 15471344} {"current_steps": 300, "total_steps": 1110, "loss": 0.1206, "lr": 4.151686808475204e-05, "epoch": 7.912751677852349, "percentage": 27.03, "elapsed_time": "2:33:32", "remaining_time": "6:54:33", "throughput": 1685.59, "total_tokens": 15528120} {"current_steps": 301, "total_steps": 1110, "loss": 0.111, "lr": 4.14636869889106e-05, "epoch": 7.939597315436242, "percentage": 27.12, "elapsed_time": "2:34:05", "remaining_time": "6:54:07", "throughput": 1685.81, "total_tokens": 15585400} {"current_steps": 302, "total_steps": 1110, "loss": 0.1348, "lr": 4.141037401256508e-05, "epoch": 7.966442953020135, "percentage": 27.21, "elapsed_time": "2:34:31", "remaining_time": "6:53:25", "throughput": 1685.81, "total_tokens": 15629880} {"current_steps": 303, "total_steps": 1110, "loss": 0.107, "lr": 4.135692958277302e-05, "epoch": 7.993288590604027, "percentage": 27.3, "elapsed_time": "2:35:01", "remaining_time": "6:52:54", "throughput": 1685.81, "total_tokens": 15681416} {"current_steps": 304, "total_steps": 1110, "loss": 0.1307, "lr": 4.130335412764501e-05, "epoch": 8.0, "percentage": 27.39, "elapsed_time": "2:35:10", "remaining_time": "6:51:25", "throughput": 1685.63, "total_tokens": 15694464} {"current_steps": 305, "total_steps": 1110, "loss": 0.1133, "lr": 4.1249648076341165e-05, "epoch": 8.026845637583893, "percentage": 27.48, "elapsed_time": "2:35:33", "remaining_time": "6:50:35", "throughput": 1685.97, "total_tokens": 15736640} {"current_steps": 306, "total_steps": 1110, "loss": 0.102, "lr": 4.1195811859067754e-05, "epoch": 8.053691275167786, "percentage": 27.57, "elapsed_time": "2:36:02", "remaining_time": "6:49:59", "throughput": 1686.2, "total_tokens": 15786808} {"current_steps": 307, "total_steps": 1110, "loss": 0.0965, "lr": 4.1141845907073695e-05, "epoch": 8.080536912751677, "percentage": 27.66, "elapsed_time": "2:36:31", "remaining_time": "6:49:24", "throughput": 1686.18, "total_tokens": 15835800} {"current_steps": 308, "total_steps": 1110, "loss": 0.117, "lr": 4.108775065264716e-05, "epoch": 8.10738255033557, "percentage": 27.75, "elapsed_time": "2:36:53", "remaining_time": "6:48:31", "throughput": 1686.24, "total_tokens": 15873008} {"current_steps": 309, "total_steps": 1110, "loss": 0.1014, "lr": 4.1033526529112064e-05, "epoch": 8.134228187919463, "percentage": 27.84, "elapsed_time": "2:37:20", "remaining_time": "6:47:50", "throughput": 1686.63, "total_tokens": 15921856} {"current_steps": 310, "total_steps": 1110, "loss": 0.1139, "lr": 4.0979173970824626e-05, "epoch": 8.161073825503356, "percentage": 27.93, "elapsed_time": "2:37:57", "remaining_time": "6:47:36", "throughput": 1686.03, "total_tokens": 15978552} {"current_steps": 311, "total_steps": 1110, "loss": 0.1167, "lr": 4.092469341316987e-05, "epoch": 8.187919463087248, "percentage": 28.02, "elapsed_time": "2:38:31", "remaining_time": "6:47:17", "throughput": 1686.03, "total_tokens": 16037488} {"current_steps": 312, "total_steps": 1110, "loss": 0.0923, "lr": 4.0870085292558145e-05, "epoch": 8.21476510067114, "percentage": 28.11, "elapsed_time": "2:39:08", "remaining_time": "6:47:01", "throughput": 1686.57, "total_tokens": 16103576} {"current_steps": 313, "total_steps": 1110, "loss": 0.1117, "lr": 4.081535004642163e-05, "epoch": 8.241610738255034, "percentage": 28.2, "elapsed_time": "2:39:30", "remaining_time": "6:46:10", "throughput": 1687.13, "total_tokens": 16147040} {"current_steps": 314, "total_steps": 1110, "loss": 0.1141, "lr": 4.076048811321083e-05, "epoch": 8.268456375838927, "percentage": 28.29, "elapsed_time": "2:39:53", "remaining_time": "6:45:20", "throughput": 1687.61, "total_tokens": 16190784} {"current_steps": 315, "total_steps": 1110, "loss": 0.0817, "lr": 4.070549993239106e-05, "epoch": 8.29530201342282, "percentage": 28.38, "elapsed_time": "2:40:34", "remaining_time": "6:45:16", "throughput": 1686.58, "total_tokens": 16249800} {"current_steps": 316, "total_steps": 1110, "loss": 0.0984, "lr": 4.065038594443893e-05, "epoch": 8.322147651006711, "percentage": 28.47, "elapsed_time": "2:41:01", "remaining_time": "6:44:35", "throughput": 1686.86, "total_tokens": 16297512} {"current_steps": 317, "total_steps": 1110, "loss": 0.1051, "lr": 4.059514659083881e-05, "epoch": 8.348993288590604, "percentage": 28.56, "elapsed_time": "2:41:34", "remaining_time": "6:44:12", "throughput": 1686.89, "total_tokens": 16354200} {"current_steps": 318, "total_steps": 1110, "loss": 0.1052, "lr": 4.053978231407931e-05, "epoch": 8.375838926174497, "percentage": 28.65, "elapsed_time": "2:42:01", "remaining_time": "6:43:30", "throughput": 1687.24, "total_tokens": 16401728} {"current_steps": 319, "total_steps": 1110, "loss": 0.1027, "lr": 4.0484293557649686e-05, "epoch": 8.40268456375839, "percentage": 28.74, "elapsed_time": "2:42:31", "remaining_time": "6:42:59", "throughput": 1687.57, "total_tokens": 16456088} {"current_steps": 320, "total_steps": 1110, "loss": 0.087, "lr": 4.0428680766036384e-05, "epoch": 8.429530201342281, "percentage": 28.83, "elapsed_time": "2:43:08", "remaining_time": "6:42:44", "throughput": 1687.55, "total_tokens": 16518056} {"current_steps": 321, "total_steps": 1110, "loss": 0.0932, "lr": 4.0372944384719364e-05, "epoch": 8.456375838926174, "percentage": 28.92, "elapsed_time": "2:43:40", "remaining_time": "6:42:19", "throughput": 1687.47, "total_tokens": 16572552} {"current_steps": 322, "total_steps": 1110, "loss": 0.1056, "lr": 4.0317084860168616e-05, "epoch": 8.483221476510067, "percentage": 29.01, "elapsed_time": "2:44:08", "remaining_time": "6:41:41", "throughput": 1687.48, "total_tokens": 16619064} {"current_steps": 323, "total_steps": 1110, "loss": 0.0868, "lr": 4.026110263984055e-05, "epoch": 8.51006711409396, "percentage": 29.1, "elapsed_time": "2:44:46", "remaining_time": "6:41:28", "throughput": 1687.81, "total_tokens": 16686344} {"current_steps": 324, "total_steps": 1110, "loss": 0.0956, "lr": 4.0204998172174415e-05, "epoch": 8.536912751677852, "percentage": 29.19, "elapsed_time": "2:45:23", "remaining_time": "6:41:13", "throughput": 1687.36, "total_tokens": 16744376} {"current_steps": 325, "total_steps": 1110, "loss": 0.1014, "lr": 4.0148771906588706e-05, "epoch": 8.563758389261745, "percentage": 29.28, "elapsed_time": "2:46:06", "remaining_time": "6:41:11", "throughput": 1686.09, "total_tokens": 16803672} {"current_steps": 326, "total_steps": 1110, "loss": 0.1091, "lr": 4.009242429347757e-05, "epoch": 8.590604026845638, "percentage": 29.37, "elapsed_time": "2:46:31", "remaining_time": "6:40:29", "throughput": 1686.1, "total_tokens": 16847144} {"current_steps": 327, "total_steps": 1110, "loss": 0.1104, "lr": 4.0035955784207203e-05, "epoch": 8.61744966442953, "percentage": 29.46, "elapsed_time": "2:47:00", "remaining_time": "6:39:54", "throughput": 1686.51, "total_tokens": 16900264} {"current_steps": 328, "total_steps": 1110, "loss": 0.0872, "lr": 3.997936683111221e-05, "epoch": 8.644295302013422, "percentage": 29.55, "elapsed_time": "2:47:32", "remaining_time": "6:39:27", "throughput": 1686.5, "total_tokens": 16954056} {"current_steps": 329, "total_steps": 1110, "loss": 0.0994, "lr": 3.9922657887491997e-05, "epoch": 8.671140939597315, "percentage": 29.64, "elapsed_time": "2:48:04", "remaining_time": "6:39:00", "throughput": 1686.52, "total_tokens": 17008432} {"current_steps": 330, "total_steps": 1110, "loss": 0.0914, "lr": 3.986582940760717e-05, "epoch": 8.697986577181208, "percentage": 29.73, "elapsed_time": "2:48:31", "remaining_time": "6:38:19", "throughput": 1687.17, "total_tokens": 17059568} {"current_steps": 331, "total_steps": 1110, "loss": 0.0943, "lr": 3.980888184667582e-05, "epoch": 8.724832214765101, "percentage": 29.82, "elapsed_time": "2:49:02", "remaining_time": "6:37:50", "throughput": 1687.38, "total_tokens": 17114616} {"current_steps": 332, "total_steps": 1110, "loss": 0.0998, "lr": 3.975181566086996e-05, "epoch": 8.751677852348994, "percentage": 29.91, "elapsed_time": "2:49:26", "remaining_time": "6:37:04", "throughput": 1687.52, "total_tokens": 17156664} {"current_steps": 333, "total_steps": 1110, "loss": 0.1181, "lr": 3.969463130731183e-05, "epoch": 8.778523489932885, "percentage": 30.0, "elapsed_time": "2:50:02", "remaining_time": "6:36:46", "throughput": 1687.01, "total_tokens": 17212024} {"current_steps": 334, "total_steps": 1110, "loss": 0.0887, "lr": 3.963732924407022e-05, "epoch": 8.805369127516778, "percentage": 30.09, "elapsed_time": "2:50:42", "remaining_time": "6:36:35", "throughput": 1686.56, "total_tokens": 17273752} {"current_steps": 335, "total_steps": 1110, "loss": 0.1016, "lr": 3.957990993015683e-05, "epoch": 8.832214765100671, "percentage": 30.18, "elapsed_time": "2:51:08", "remaining_time": "6:35:55", "throughput": 1686.98, "total_tokens": 17322408} {"current_steps": 336, "total_steps": 1110, "loss": 0.1141, "lr": 3.95223738255226e-05, "epoch": 8.859060402684564, "percentage": 30.27, "elapsed_time": "2:51:30", "remaining_time": "6:35:03", "throughput": 1687.09, "total_tokens": 17360304} {"current_steps": 337, "total_steps": 1110, "loss": 0.0935, "lr": 3.946472139105398e-05, "epoch": 8.885906040268456, "percentage": 30.36, "elapsed_time": "2:52:04", "remaining_time": "6:34:40", "throughput": 1686.78, "total_tokens": 17414344} {"current_steps": 338, "total_steps": 1110, "loss": 0.1163, "lr": 3.94069530885693e-05, "epoch": 8.912751677852349, "percentage": 30.45, "elapsed_time": "2:52:32", "remaining_time": "6:34:04", "throughput": 1686.93, "total_tokens": 17463200} {"current_steps": 339, "total_steps": 1110, "loss": 0.1059, "lr": 3.934906938081499e-05, "epoch": 8.939597315436242, "percentage": 30.54, "elapsed_time": "2:53:03", "remaining_time": "6:33:35", "throughput": 1687.14, "total_tokens": 17518608} {"current_steps": 340, "total_steps": 1110, "loss": 0.1212, "lr": 3.929107073146197e-05, "epoch": 8.966442953020135, "percentage": 30.63, "elapsed_time": "2:53:43", "remaining_time": "6:33:25", "throughput": 1686.39, "total_tokens": 17577392} {"current_steps": 341, "total_steps": 1110, "loss": 0.1031, "lr": 3.923295760510186e-05, "epoch": 8.993288590604028, "percentage": 30.72, "elapsed_time": "2:54:33", "remaining_time": "6:33:39", "throughput": 1685.15, "total_tokens": 17649440} {"current_steps": 342, "total_steps": 1110, "loss": 0.1223, "lr": 3.9174730467243294e-05, "epoch": 9.0, "percentage": 30.81, "elapsed_time": "2:54:37", "remaining_time": "6:32:07", "throughput": 1685.21, "total_tokens": 17656272} {"current_steps": 343, "total_steps": 1110, "loss": 0.0748, "lr": 3.911638978430818e-05, "epoch": 9.026845637583893, "percentage": 30.9, "elapsed_time": "2:55:11", "remaining_time": "6:31:46", "throughput": 1685.33, "total_tokens": 17716024} {"current_steps": 344, "total_steps": 1110, "loss": 0.0694, "lr": 3.905793602362796e-05, "epoch": 9.053691275167786, "percentage": 30.99, "elapsed_time": "2:55:44", "remaining_time": "6:31:19", "throughput": 1685.08, "total_tokens": 17767664} {"current_steps": 345, "total_steps": 1110, "loss": 0.0923, "lr": 3.899936965343989e-05, "epoch": 9.080536912751677, "percentage": 31.08, "elapsed_time": "2:56:08", "remaining_time": "6:30:33", "throughput": 1685.35, "total_tokens": 17810840} {"current_steps": 346, "total_steps": 1110, "loss": 0.0835, "lr": 3.8940691142883244e-05, "epoch": 9.10738255033557, "percentage": 31.17, "elapsed_time": "2:56:38", "remaining_time": "6:30:01", "throughput": 1685.49, "total_tokens": 17863000} {"current_steps": 347, "total_steps": 1110, "loss": 0.0992, "lr": 3.888190096199561e-05, "epoch": 9.134228187919463, "percentage": 31.26, "elapsed_time": "2:57:05", "remaining_time": "6:29:24", "throughput": 1685.62, "total_tokens": 17911392} {"current_steps": 348, "total_steps": 1110, "loss": 0.0782, "lr": 3.882299958170909e-05, "epoch": 9.161073825503356, "percentage": 31.35, "elapsed_time": "2:57:45", "remaining_time": "6:29:13", "throughput": 1685.49, "total_tokens": 17976320} {"current_steps": 349, "total_steps": 1110, "loss": 0.0822, "lr": 3.876398747384653e-05, "epoch": 9.187919463087248, "percentage": 31.44, "elapsed_time": "2:58:20", "remaining_time": "6:28:53", "throughput": 1685.47, "total_tokens": 18035832} {"current_steps": 350, "total_steps": 1110, "loss": 0.0985, "lr": 3.8704865111117746e-05, "epoch": 9.21476510067114, "percentage": 31.53, "elapsed_time": "2:59:05", "remaining_time": "6:28:53", "throughput": 1684.39, "total_tokens": 18100080} {"current_steps": 351, "total_steps": 1110, "loss": 0.0873, "lr": 3.8645632967115753e-05, "epoch": 9.241610738255034, "percentage": 31.62, "elapsed_time": "2:59:34", "remaining_time": "6:28:18", "throughput": 1684.44, "total_tokens": 18149144} {"current_steps": 352, "total_steps": 1110, "loss": 0.0846, "lr": 3.858629151631295e-05, "epoch": 9.268456375838927, "percentage": 31.71, "elapsed_time": "2:59:58", "remaining_time": "6:27:34", "throughput": 1684.42, "total_tokens": 18190000} {"current_steps": 353, "total_steps": 1110, "loss": 0.0982, "lr": 3.85268412340573e-05, "epoch": 9.29530201342282, "percentage": 31.8, "elapsed_time": "3:00:22", "remaining_time": "6:26:48", "throughput": 1684.49, "total_tokens": 18230080} {"current_steps": 354, "total_steps": 1110, "loss": 0.084, "lr": 3.84672825965686e-05, "epoch": 9.322147651006711, "percentage": 31.89, "elapsed_time": "3:00:50", "remaining_time": "6:26:11", "throughput": 1684.71, "total_tokens": 18279672} {"current_steps": 355, "total_steps": 1110, "loss": 0.0999, "lr": 3.840761608093456e-05, "epoch": 9.348993288590604, "percentage": 31.98, "elapsed_time": "3:01:12", "remaining_time": "6:25:22", "throughput": 1685.19, "total_tokens": 18321928} {"current_steps": 356, "total_steps": 1110, "loss": 0.0809, "lr": 3.8347842165107085e-05, "epoch": 9.375838926174497, "percentage": 32.07, "elapsed_time": "3:01:41", "remaining_time": "6:24:48", "throughput": 1685.27, "total_tokens": 18371680} {"current_steps": 357, "total_steps": 1110, "loss": 0.0759, "lr": 3.828796132789835e-05, "epoch": 9.40268456375839, "percentage": 32.16, "elapsed_time": "3:02:20", "remaining_time": "6:24:35", "throughput": 1684.84, "total_tokens": 18432296} {"current_steps": 358, "total_steps": 1110, "loss": 0.0871, "lr": 3.822797404897705e-05, "epoch": 9.429530201342281, "percentage": 32.25, "elapsed_time": "3:02:45", "remaining_time": "6:23:52", "throughput": 1685.15, "total_tokens": 18477896} {"current_steps": 359, "total_steps": 1110, "loss": 0.0955, "lr": 3.816788080886449e-05, "epoch": 9.456375838926174, "percentage": 32.34, "elapsed_time": "3:03:07", "remaining_time": "6:23:04", "throughput": 1685.76, "total_tokens": 18522080} {"current_steps": 360, "total_steps": 1110, "loss": 0.0808, "lr": 3.8107682088930794e-05, "epoch": 9.483221476510067, "percentage": 32.43, "elapsed_time": "3:03:47", "remaining_time": "6:22:53", "throughput": 1685.12, "total_tokens": 18582520} {"current_steps": 361, "total_steps": 1110, "loss": 0.0706, "lr": 3.8047378371391e-05, "epoch": 9.51006711409396, "percentage": 32.52, "elapsed_time": "3:04:36", "remaining_time": "6:23:01", "throughput": 1684.62, "total_tokens": 18659480} {"current_steps": 362, "total_steps": 1110, "loss": 0.0713, "lr": 3.7986970139301214e-05, "epoch": 9.536912751677852, "percentage": 32.61, "elapsed_time": "3:05:21", "remaining_time": "6:23:00", "throughput": 1684.11, "total_tokens": 18729616} {"current_steps": 363, "total_steps": 1110, "loss": 0.0905, "lr": 3.792645787655476e-05, "epoch": 9.563758389261745, "percentage": 32.7, "elapsed_time": "3:05:43", "remaining_time": "6:22:11", "throughput": 1684.42, "total_tokens": 18770496} {"current_steps": 364, "total_steps": 1110, "loss": 0.1042, "lr": 3.786584206787828e-05, "epoch": 9.590604026845638, "percentage": 32.79, "elapsed_time": "3:06:08", "remaining_time": "6:21:29", "throughput": 1684.95, "total_tokens": 18818488} {"current_steps": 365, "total_steps": 1110, "loss": 0.0984, "lr": 3.7805123198827857e-05, "epoch": 9.61744966442953, "percentage": 32.88, "elapsed_time": "3:06:46", "remaining_time": "6:21:13", "throughput": 1684.55, "total_tokens": 18877640} {"current_steps": 366, "total_steps": 1110, "loss": 0.0934, "lr": 3.774430175578514e-05, "epoch": 9.644295302013422, "percentage": 32.97, "elapsed_time": "3:07:24", "remaining_time": "6:20:58", "throughput": 1683.7, "total_tokens": 18932992} {"current_steps": 367, "total_steps": 1110, "loss": 0.0912, "lr": 3.768337822595341e-05, "epoch": 9.671140939597315, "percentage": 33.06, "elapsed_time": "3:07:50", "remaining_time": "6:20:17", "throughput": 1684.2, "total_tokens": 18981672} {"current_steps": 368, "total_steps": 1110, "loss": 0.0786, "lr": 3.7622353097353724e-05, "epoch": 9.697986577181208, "percentage": 33.15, "elapsed_time": "3:08:30", "remaining_time": "6:20:04", "throughput": 1683.74, "total_tokens": 19043504} {"current_steps": 369, "total_steps": 1110, "loss": 0.0837, "lr": 3.756122685882098e-05, "epoch": 9.724832214765101, "percentage": 33.24, "elapsed_time": "3:08:58", "remaining_time": "6:19:28", "throughput": 1684.26, "total_tokens": 19096376} {"current_steps": 370, "total_steps": 1110, "loss": 0.088, "lr": 3.7500000000000003e-05, "epoch": 9.751677852348994, "percentage": 33.33, "elapsed_time": "3:09:27", "remaining_time": "6:18:55", "throughput": 1684.21, "total_tokens": 19145816} {"current_steps": 371, "total_steps": 1110, "loss": 0.0835, "lr": 3.7438673011341626e-05, "epoch": 9.778523489932885, "percentage": 33.42, "elapsed_time": "3:09:57", "remaining_time": "6:18:22", "throughput": 1684.45, "total_tokens": 19198616} {"current_steps": 372, "total_steps": 1110, "loss": 0.0939, "lr": 3.737724638409876e-05, "epoch": 9.805369127516778, "percentage": 33.51, "elapsed_time": "3:10:27", "remaining_time": "6:17:50", "throughput": 1684.61, "total_tokens": 19250832} {"current_steps": 373, "total_steps": 1110, "loss": 0.0894, "lr": 3.731572061032247e-05, "epoch": 9.832214765100671, "percentage": 33.6, "elapsed_time": "3:10:55", "remaining_time": "6:17:14", "throughput": 1684.72, "total_tokens": 19299240} {"current_steps": 374, "total_steps": 1110, "loss": 0.0751, "lr": 3.7254096182858e-05, "epoch": 9.859060402684564, "percentage": 33.69, "elapsed_time": "3:11:33", "remaining_time": "6:16:58", "throughput": 1683.91, "total_tokens": 19354544} {"current_steps": 375, "total_steps": 1110, "loss": 0.0879, "lr": 3.719237359534087e-05, "epoch": 9.885906040268456, "percentage": 33.78, "elapsed_time": "3:12:02", "remaining_time": "6:16:23", "throughput": 1683.99, "total_tokens": 19403272} {"current_steps": 376, "total_steps": 1110, "loss": 0.0772, "lr": 3.7130553342192886e-05, "epoch": 9.912751677852349, "percentage": 33.87, "elapsed_time": "3:12:34", "remaining_time": "6:15:55", "throughput": 1683.9, "total_tokens": 19456648} {"current_steps": 377, "total_steps": 1110, "loss": 0.0933, "lr": 3.706863591861821e-05, "epoch": 9.939597315436242, "percentage": 33.96, "elapsed_time": "3:12:58", "remaining_time": "6:15:11", "throughput": 1684.03, "total_tokens": 19498288} {"current_steps": 378, "total_steps": 1110, "loss": 0.0989, "lr": 3.7006621820599356e-05, "epoch": 9.966442953020135, "percentage": 34.05, "elapsed_time": "3:13:35", "remaining_time": "6:14:52", "throughput": 1683.96, "total_tokens": 19559480} {"current_steps": 379, "total_steps": 1110, "loss": 0.0974, "lr": 3.6944511544893254e-05, "epoch": 9.993288590604028, "percentage": 34.14, "elapsed_time": "3:14:04", "remaining_time": "6:14:19", "throughput": 1684.15, "total_tokens": 19610848} {"current_steps": 380, "total_steps": 1110, "loss": 0.1093, "lr": 3.688230558902725e-05, "epoch": 10.0, "percentage": 34.23, "elapsed_time": "3:14:08", "remaining_time": "6:12:56", "throughput": 1684.21, "total_tokens": 19618080} {"current_steps": 381, "total_steps": 1110, "loss": 0.0527, "lr": 3.682000445129512e-05, "epoch": 10.026845637583893, "percentage": 34.32, "elapsed_time": "3:14:44", "remaining_time": "6:12:37", "throughput": 1683.96, "total_tokens": 19677008} {"current_steps": 382, "total_steps": 1110, "loss": 0.0715, "lr": 3.675760863075309e-05, "epoch": 10.053691275167786, "percentage": 34.41, "elapsed_time": "3:15:18", "remaining_time": "6:12:13", "throughput": 1683.94, "total_tokens": 19733680} {"current_steps": 383, "total_steps": 1110, "loss": 0.0663, "lr": 3.669511862721583e-05, "epoch": 10.080536912751677, "percentage": 34.5, "elapsed_time": "3:15:48", "remaining_time": "6:11:41", "throughput": 1684.05, "total_tokens": 19785448} {"current_steps": 384, "total_steps": 1110, "loss": 0.0798, "lr": 3.663253494125244e-05, "epoch": 10.10738255033557, "percentage": 34.59, "elapsed_time": "3:16:10", "remaining_time": "6:10:53", "throughput": 1684.41, "total_tokens": 19826104} {"current_steps": 385, "total_steps": 1110, "loss": 0.0797, "lr": 3.656985807418248e-05, "epoch": 10.134228187919463, "percentage": 34.68, "elapsed_time": "3:16:41", "remaining_time": "6:10:23", "throughput": 1684.7, "total_tokens": 19881960} {"current_steps": 386, "total_steps": 1110, "loss": 0.0681, "lr": 3.65070885280719e-05, "epoch": 10.161073825503356, "percentage": 34.77, "elapsed_time": "3:17:12", "remaining_time": "6:09:52", "throughput": 1684.83, "total_tokens": 19934936} {"current_steps": 387, "total_steps": 1110, "loss": 0.0788, "lr": 3.6444226805729056e-05, "epoch": 10.187919463087248, "percentage": 34.86, "elapsed_time": "3:17:35", "remaining_time": "6:09:09", "throughput": 1685.27, "total_tokens": 19980488} {"current_steps": 388, "total_steps": 1110, "loss": 0.0694, "lr": 3.6381273410700685e-05, "epoch": 10.21476510067114, "percentage": 34.95, "elapsed_time": "3:18:05", "remaining_time": "6:08:36", "throughput": 1685.15, "total_tokens": 20028736} {"current_steps": 389, "total_steps": 1110, "loss": 0.0615, "lr": 3.631822884726783e-05, "epoch": 10.241610738255034, "percentage": 35.05, "elapsed_time": "3:18:34", "remaining_time": "6:08:03", "throughput": 1685.08, "total_tokens": 20077448} {"current_steps": 390, "total_steps": 1110, "loss": 0.0918, "lr": 3.6255093620441834e-05, "epoch": 10.268456375838927, "percentage": 35.14, "elapsed_time": "3:19:03", "remaining_time": "6:07:29", "throughput": 1684.83, "total_tokens": 20122424} {"current_steps": 391, "total_steps": 1110, "loss": 0.0779, "lr": 3.619186823596031e-05, "epoch": 10.29530201342282, "percentage": 35.23, "elapsed_time": "3:19:51", "remaining_time": "6:07:30", "throughput": 1684.06, "total_tokens": 20193720} {"current_steps": 392, "total_steps": 1110, "loss": 0.0723, "lr": 3.6128553200283064e-05, "epoch": 10.322147651006711, "percentage": 35.32, "elapsed_time": "3:20:21", "remaining_time": "6:06:58", "throughput": 1683.89, "total_tokens": 20242264} {"current_steps": 393, "total_steps": 1110, "loss": 0.0727, "lr": 3.606514902058802e-05, "epoch": 10.348993288590604, "percentage": 35.41, "elapsed_time": "3:20:48", "remaining_time": "6:06:21", "throughput": 1683.98, "total_tokens": 20289480} {"current_steps": 394, "total_steps": 1110, "loss": 0.083, "lr": 3.600165620476719e-05, "epoch": 10.375838926174497, "percentage": 35.5, "elapsed_time": "3:21:18", "remaining_time": "6:05:49", "throughput": 1684.31, "total_tokens": 20343288} {"current_steps": 395, "total_steps": 1110, "loss": 0.0875, "lr": 3.593807526142261e-05, "epoch": 10.40268456375839, "percentage": 35.59, "elapsed_time": "3:21:44", "remaining_time": "6:05:10", "throughput": 1684.53, "total_tokens": 20390120} {"current_steps": 396, "total_steps": 1110, "loss": 0.064, "lr": 3.587440669986224e-05, "epoch": 10.429530201342281, "percentage": 35.68, "elapsed_time": "3:22:24", "remaining_time": "6:04:56", "throughput": 1683.9, "total_tokens": 20450088} {"current_steps": 397, "total_steps": 1110, "loss": 0.069, "lr": 3.58106510300959e-05, "epoch": 10.456375838926174, "percentage": 35.77, "elapsed_time": "3:22:54", "remaining_time": "6:04:25", "throughput": 1684.09, "total_tokens": 20503232} {"current_steps": 398, "total_steps": 1110, "loss": 0.0668, "lr": 3.574680876283116e-05, "epoch": 10.483221476510067, "percentage": 35.86, "elapsed_time": "3:23:30", "remaining_time": "6:04:03", "throughput": 1684.09, "total_tokens": 20562832} {"current_steps": 399, "total_steps": 1110, "loss": 0.0738, "lr": 3.5682880409469315e-05, "epoch": 10.51006711409396, "percentage": 35.95, "elapsed_time": "3:23:55", "remaining_time": "6:03:22", "throughput": 1684.54, "total_tokens": 20610704} {"current_steps": 400, "total_steps": 1110, "loss": 0.0688, "lr": 3.56188664821012e-05, "epoch": 10.536912751677852, "percentage": 36.04, "elapsed_time": "3:24:21", "remaining_time": "6:02:44", "throughput": 1684.85, "total_tokens": 20659448} {"current_steps": 401, "total_steps": 1110, "loss": 0.0808, "lr": 3.5554767493503144e-05, "epoch": 10.563758389261745, "percentage": 36.13, "elapsed_time": "3:24:48", "remaining_time": "6:02:07", "throughput": 1684.99, "total_tokens": 20706680} {"current_steps": 402, "total_steps": 1110, "loss": 0.0727, "lr": 3.549058395713285e-05, "epoch": 10.590604026845638, "percentage": 36.22, "elapsed_time": "3:25:24", "remaining_time": "6:01:46", "throughput": 1684.96, "total_tokens": 20766576} {"current_steps": 403, "total_steps": 1110, "loss": 0.0578, "lr": 3.542631638712529e-05, "epoch": 10.61744966442953, "percentage": 36.31, "elapsed_time": "3:26:09", "remaining_time": "6:01:39", "throughput": 1684.92, "total_tokens": 20841280} {"current_steps": 404, "total_steps": 1110, "loss": 0.0806, "lr": 3.536196529828858e-05, "epoch": 10.644295302013422, "percentage": 36.4, "elapsed_time": "3:26:39", "remaining_time": "6:01:07", "throughput": 1684.88, "total_tokens": 20891264} {"current_steps": 405, "total_steps": 1110, "loss": 0.0733, "lr": 3.529753120609982e-05, "epoch": 10.671140939597315, "percentage": 36.49, "elapsed_time": "3:27:03", "remaining_time": "6:00:25", "throughput": 1684.99, "total_tokens": 20932840} {"current_steps": 406, "total_steps": 1110, "loss": 0.0715, "lr": 3.523301462670104e-05, "epoch": 10.697986577181208, "percentage": 36.58, "elapsed_time": "3:27:31", "remaining_time": "5:59:51", "throughput": 1685.04, "total_tokens": 20981472} {"current_steps": 407, "total_steps": 1110, "loss": 0.0638, "lr": 3.516841607689501e-05, "epoch": 10.724832214765101, "percentage": 36.67, "elapsed_time": "3:28:00", "remaining_time": "5:59:17", "throughput": 1685.05, "total_tokens": 21030624} {"current_steps": 408, "total_steps": 1110, "loss": 0.0672, "lr": 3.5103736074141105e-05, "epoch": 10.751677852348994, "percentage": 36.76, "elapsed_time": "3:28:32", "remaining_time": "5:58:49", "throughput": 1684.83, "total_tokens": 21082264} {"current_steps": 409, "total_steps": 1110, "loss": 0.0638, "lr": 3.503897513655118e-05, "epoch": 10.778523489932885, "percentage": 36.85, "elapsed_time": "3:29:06", "remaining_time": "5:58:23", "throughput": 1684.68, "total_tokens": 21136432} {"current_steps": 410, "total_steps": 1110, "loss": 0.0715, "lr": 3.497413378288541e-05, "epoch": 10.805369127516778, "percentage": 36.94, "elapsed_time": "3:29:35", "remaining_time": "5:57:49", "throughput": 1684.62, "total_tokens": 21184304} {"current_steps": 411, "total_steps": 1110, "loss": 0.0839, "lr": 3.490921253254813e-05, "epoch": 10.832214765100671, "percentage": 37.03, "elapsed_time": "3:29:57", "remaining_time": "5:57:05", "throughput": 1684.89, "total_tokens": 21225504} {"current_steps": 412, "total_steps": 1110, "loss": 0.0632, "lr": 3.484421190558368e-05, "epoch": 10.859060402684564, "percentage": 37.12, "elapsed_time": "3:30:33", "remaining_time": "5:56:43", "throughput": 1684.73, "total_tokens": 21284488} {"current_steps": 413, "total_steps": 1110, "loss": 0.073, "lr": 3.4779132422672234e-05, "epoch": 10.885906040268456, "percentage": 37.21, "elapsed_time": "3:31:02", "remaining_time": "5:56:09", "throughput": 1684.96, "total_tokens": 21335424} {"current_steps": 414, "total_steps": 1110, "loss": 0.1019, "lr": 3.471397460512563e-05, "epoch": 10.912751677852349, "percentage": 37.3, "elapsed_time": "3:31:38", "remaining_time": "5:55:48", "throughput": 1684.46, "total_tokens": 21390376} {"current_steps": 415, "total_steps": 1110, "loss": 0.0799, "lr": 3.464873897488322e-05, "epoch": 10.939597315436242, "percentage": 37.39, "elapsed_time": "3:32:16", "remaining_time": "5:55:29", "throughput": 1684.45, "total_tokens": 21453256} {"current_steps": 416, "total_steps": 1110, "loss": 0.0728, "lr": 3.458342605450764e-05, "epoch": 10.966442953020135, "percentage": 37.48, "elapsed_time": "3:32:47", "remaining_time": "5:55:00", "throughput": 1684.28, "total_tokens": 21504544} {"current_steps": 417, "total_steps": 1110, "loss": 0.0652, "lr": 3.451803636718064e-05, "epoch": 10.993288590604028, "percentage": 37.57, "elapsed_time": "3:33:23", "remaining_time": "5:54:37", "throughput": 1683.99, "total_tokens": 21560296} {"current_steps": 418, "total_steps": 1110, "loss": 0.1109, "lr": 3.445257043669894e-05, "epoch": 11.0, "percentage": 37.66, "elapsed_time": "3:33:41", "remaining_time": "5:53:46", "throughput": 1683.09, "total_tokens": 21579888} {"current_steps": 419, "total_steps": 1110, "loss": 0.0475, "lr": 3.4387028787469974e-05, "epoch": 11.026845637583893, "percentage": 37.75, "elapsed_time": "3:34:13", "remaining_time": "5:53:17", "throughput": 1682.98, "total_tokens": 21632376} {"current_steps": 420, "total_steps": 1110, "loss": 0.0604, "lr": 3.432141194450772e-05, "epoch": 11.053691275167786, "percentage": 37.84, "elapsed_time": "3:34:48", "remaining_time": "5:52:54", "throughput": 1682.72, "total_tokens": 21688456} {"current_steps": 421, "total_steps": 1110, "loss": 0.0752, "lr": 3.425572043342847e-05, "epoch": 11.080536912751677, "percentage": 37.93, "elapsed_time": "3:35:14", "remaining_time": "5:52:15", "throughput": 1682.89, "total_tokens": 21733728} {"current_steps": 422, "total_steps": 1110, "loss": 0.0695, "lr": 3.418995478044667e-05, "epoch": 11.10738255033557, "percentage": 38.02, "elapsed_time": "3:35:47", "remaining_time": "5:51:48", "throughput": 1682.67, "total_tokens": 21786488} {"current_steps": 423, "total_steps": 1110, "loss": 0.0626, "lr": 3.412411551237064e-05, "epoch": 11.134228187919463, "percentage": 38.11, "elapsed_time": "3:36:12", "remaining_time": "5:51:08", "throughput": 1682.98, "total_tokens": 21832088} {"current_steps": 424, "total_steps": 1110, "loss": 0.0615, "lr": 3.405820315659838e-05, "epoch": 11.161073825503356, "percentage": 38.2, "elapsed_time": "3:36:45", "remaining_time": "5:50:42", "throughput": 1682.81, "total_tokens": 21886128} {"current_steps": 425, "total_steps": 1110, "loss": 0.0618, "lr": 3.39922182411134e-05, "epoch": 11.187919463087248, "percentage": 38.29, "elapsed_time": "3:37:12", "remaining_time": "5:50:05", "throughput": 1683.11, "total_tokens": 21935272} {"current_steps": 426, "total_steps": 1110, "loss": 0.0519, "lr": 3.392616129448038e-05, "epoch": 11.21476510067114, "percentage": 38.38, "elapsed_time": "3:37:40", "remaining_time": "5:49:30", "throughput": 1683.28, "total_tokens": 21984328} {"current_steps": 427, "total_steps": 1110, "loss": 0.0527, "lr": 3.386003284584105e-05, "epoch": 11.241610738255034, "percentage": 38.47, "elapsed_time": "3:38:09", "remaining_time": "5:48:56", "throughput": 1683.19, "total_tokens": 22031864} {"current_steps": 428, "total_steps": 1110, "loss": 0.0733, "lr": 3.379383342490986e-05, "epoch": 11.268456375838927, "percentage": 38.56, "elapsed_time": "3:38:52", "remaining_time": "5:48:45", "throughput": 1682.58, "total_tokens": 22095736} {"current_steps": 429, "total_steps": 1110, "loss": 0.0496, "lr": 3.3727563561969787e-05, "epoch": 11.29530201342282, "percentage": 38.65, "elapsed_time": "3:39:19", "remaining_time": "5:48:09", "throughput": 1682.75, "total_tokens": 22144384} {"current_steps": 430, "total_steps": 1110, "loss": 0.0637, "lr": 3.3661223787868094e-05, "epoch": 11.322147651006711, "percentage": 38.74, "elapsed_time": "3:39:49", "remaining_time": "5:47:37", "throughput": 1683.0, "total_tokens": 22197480} {"current_steps": 431, "total_steps": 1110, "loss": 0.0466, "lr": 3.359481463401203e-05, "epoch": 11.348993288590604, "percentage": 38.83, "elapsed_time": "3:40:34", "remaining_time": "5:47:29", "throughput": 1682.3, "total_tokens": 22264744} {"current_steps": 432, "total_steps": 1110, "loss": 0.0578, "lr": 3.3528336632364624e-05, "epoch": 11.375838926174497, "percentage": 38.92, "elapsed_time": "3:41:04", "remaining_time": "5:46:57", "throughput": 1682.37, "total_tokens": 22315488} {"current_steps": 433, "total_steps": 1110, "loss": 0.0654, "lr": 3.34617903154404e-05, "epoch": 11.40268456375839, "percentage": 39.01, "elapsed_time": "3:41:33", "remaining_time": "5:46:24", "throughput": 1682.47, "total_tokens": 22366144} {"current_steps": 434, "total_steps": 1110, "loss": 0.0614, "lr": 3.33951762163011e-05, "epoch": 11.429530201342281, "percentage": 39.1, "elapsed_time": "3:41:57", "remaining_time": "5:45:43", "throughput": 1682.72, "total_tokens": 22410272} {"current_steps": 435, "total_steps": 1110, "loss": 0.0569, "lr": 3.332849486855144e-05, "epoch": 11.456375838926174, "percentage": 39.19, "elapsed_time": "3:42:29", "remaining_time": "5:45:15", "throughput": 1682.91, "total_tokens": 22466400} {"current_steps": 436, "total_steps": 1110, "loss": 0.0562, "lr": 3.326174680633483e-05, "epoch": 11.483221476510067, "percentage": 39.28, "elapsed_time": "3:42:58", "remaining_time": "5:44:40", "throughput": 1683.07, "total_tokens": 22516440} {"current_steps": 437, "total_steps": 1110, "loss": 0.0708, "lr": 3.3194932564329064e-05, "epoch": 11.51006711409396, "percentage": 39.37, "elapsed_time": "3:43:26", "remaining_time": "5:44:05", "throughput": 1682.88, "total_tokens": 22560848} {"current_steps": 438, "total_steps": 1110, "loss": 0.0519, "lr": 3.312805267774209e-05, "epoch": 11.536912751677852, "percentage": 39.46, "elapsed_time": "3:44:01", "remaining_time": "5:43:42", "throughput": 1682.94, "total_tokens": 22621752} {"current_steps": 439, "total_steps": 1110, "loss": 0.0587, "lr": 3.3061107682307665e-05, "epoch": 11.563758389261745, "percentage": 39.55, "elapsed_time": "3:44:27", "remaining_time": "5:43:05", "throughput": 1683.07, "total_tokens": 22667384} {"current_steps": 440, "total_steps": 1110, "loss": 0.0536, "lr": 3.2994098114281134e-05, "epoch": 11.590604026845638, "percentage": 39.64, "elapsed_time": "3:45:05", "remaining_time": "5:42:45", "throughput": 1682.8, "total_tokens": 22726904} {"current_steps": 441, "total_steps": 1110, "loss": 0.0527, "lr": 3.2927024510435055e-05, "epoch": 11.61744966442953, "percentage": 39.73, "elapsed_time": "3:45:34", "remaining_time": "5:42:12", "throughput": 1682.96, "total_tokens": 22778192} {"current_steps": 442, "total_steps": 1110, "loss": 0.0628, "lr": 3.285988740805495e-05, "epoch": 11.644295302013422, "percentage": 39.82, "elapsed_time": "3:46:08", "remaining_time": "5:41:45", "throughput": 1683.08, "total_tokens": 22836184} {"current_steps": 443, "total_steps": 1110, "loss": 0.0532, "lr": 3.279268734493499e-05, "epoch": 11.671140939597315, "percentage": 39.91, "elapsed_time": "3:46:42", "remaining_time": "5:41:19", "throughput": 1683.34, "total_tokens": 22896992} {"current_steps": 444, "total_steps": 1110, "loss": 0.0627, "lr": 3.272542485937369e-05, "epoch": 11.697986577181208, "percentage": 40.0, "elapsed_time": "3:47:07", "remaining_time": "5:40:41", "throughput": 1683.44, "total_tokens": 22941096} {"current_steps": 445, "total_steps": 1110, "loss": 0.0645, "lr": 3.265810049016959e-05, "epoch": 11.724832214765101, "percentage": 40.09, "elapsed_time": "3:47:33", "remaining_time": "5:40:03", "throughput": 1683.52, "total_tokens": 22986064} {"current_steps": 446, "total_steps": 1110, "loss": 0.0542, "lr": 3.259071477661694e-05, "epoch": 11.751677852348994, "percentage": 40.18, "elapsed_time": "3:48:06", "remaining_time": "5:39:35", "throughput": 1683.53, "total_tokens": 23041088} {"current_steps": 447, "total_steps": 1110, "loss": 0.0556, "lr": 3.252326825850139e-05, "epoch": 11.778523489932885, "percentage": 40.27, "elapsed_time": "3:48:38", "remaining_time": "5:39:07", "throughput": 1683.57, "total_tokens": 23095464} {"current_steps": 448, "total_steps": 1110, "loss": 0.0644, "lr": 3.245576147609564e-05, "epoch": 11.805369127516778, "percentage": 40.36, "elapsed_time": "3:49:07", "remaining_time": "5:38:34", "throughput": 1683.67, "total_tokens": 23146904} {"current_steps": 449, "total_steps": 1110, "loss": 0.0725, "lr": 3.238819497015514e-05, "epoch": 11.832214765100671, "percentage": 40.45, "elapsed_time": "3:49:34", "remaining_time": "5:37:57", "throughput": 1683.69, "total_tokens": 23191600} {"current_steps": 450, "total_steps": 1110, "loss": 0.0812, "lr": 3.232056928191376e-05, "epoch": 11.859060402684564, "percentage": 40.54, "elapsed_time": "3:50:15", "remaining_time": "5:37:43", "throughput": 1683.08, "total_tokens": 23253392} {"current_steps": 451, "total_steps": 1110, "loss": 0.0735, "lr": 3.225288495307944e-05, "epoch": 11.885906040268456, "percentage": 40.63, "elapsed_time": "3:50:39", "remaining_time": "5:37:01", "throughput": 1683.41, "total_tokens": 23296704} {"current_steps": 452, "total_steps": 1110, "loss": 0.0491, "lr": 3.218514252582983e-05, "epoch": 11.912751677852349, "percentage": 40.72, "elapsed_time": "3:51:20", "remaining_time": "5:36:45", "throughput": 1683.44, "total_tokens": 23366096} {"current_steps": 453, "total_steps": 1110, "loss": 0.0546, "lr": 3.211734254280799e-05, "epoch": 11.939597315436242, "percentage": 40.81, "elapsed_time": "3:51:51", "remaining_time": "5:36:16", "throughput": 1683.43, "total_tokens": 23418984} {"current_steps": 454, "total_steps": 1110, "loss": 0.068, "lr": 3.204948554711803e-05, "epoch": 11.966442953020135, "percentage": 40.9, "elapsed_time": "3:52:20", "remaining_time": "5:35:42", "throughput": 1683.46, "total_tokens": 23467672} {"current_steps": 455, "total_steps": 1110, "loss": 0.0711, "lr": 3.1981572082320756e-05, "epoch": 11.993288590604028, "percentage": 40.99, "elapsed_time": "3:53:03", "remaining_time": "5:35:30", "throughput": 1682.81, "total_tokens": 23532368} {"current_steps": 456, "total_steps": 1110, "loss": 0.0876, "lr": 3.191360269242928e-05, "epoch": 12.0, "percentage": 41.08, "elapsed_time": "3:53:09", "remaining_time": "5:34:23", "throughput": 1682.83, "total_tokens": 23541696} {"current_steps": 457, "total_steps": 1110, "loss": 0.0422, "lr": 3.184557792190473e-05, "epoch": 12.026845637583893, "percentage": 41.17, "elapsed_time": "3:53:42", "remaining_time": "5:33:56", "throughput": 1682.66, "total_tokens": 23595560} {"current_steps": 458, "total_steps": 1110, "loss": 0.0486, "lr": 3.177749831565184e-05, "epoch": 12.053691275167786, "percentage": 41.26, "elapsed_time": "3:54:20", "remaining_time": "5:33:35", "throughput": 1682.4, "total_tokens": 23654632} {"current_steps": 459, "total_steps": 1110, "loss": 0.0515, "lr": 3.1709364419014615e-05, "epoch": 12.080536912751677, "percentage": 41.35, "elapsed_time": "3:54:50", "remaining_time": "5:33:04", "throughput": 1682.56, "total_tokens": 23708304} {"current_steps": 460, "total_steps": 1110, "loss": 0.0433, "lr": 3.164117677777191e-05, "epoch": 12.10738255033557, "percentage": 41.44, "elapsed_time": "3:55:30", "remaining_time": "5:32:46", "throughput": 1682.46, "total_tokens": 23773424} {"current_steps": 461, "total_steps": 1110, "loss": 0.0457, "lr": 3.157293593813314e-05, "epoch": 12.134228187919463, "percentage": 41.53, "elapsed_time": "3:56:03", "remaining_time": "5:32:19", "throughput": 1682.25, "total_tokens": 23825952} {"current_steps": 462, "total_steps": 1110, "loss": 0.0437, "lr": 3.150464244673383e-05, "epoch": 12.161073825503356, "percentage": 41.62, "elapsed_time": "3:56:35", "remaining_time": "5:31:50", "throughput": 1682.54, "total_tokens": 23884456} {"current_steps": 463, "total_steps": 1110, "loss": 0.0468, "lr": 3.143629685063128e-05, "epoch": 12.187919463087248, "percentage": 41.71, "elapsed_time": "3:57:06", "remaining_time": "5:31:19", "throughput": 1682.43, "total_tokens": 23934728} {"current_steps": 464, "total_steps": 1110, "loss": 0.0521, "lr": 3.1367899697300154e-05, "epoch": 12.21476510067114, "percentage": 41.8, "elapsed_time": "3:57:33", "remaining_time": "5:30:44", "throughput": 1682.75, "total_tokens": 23985904} {"current_steps": 465, "total_steps": 1110, "loss": 0.0571, "lr": 3.1299451534628135e-05, "epoch": 12.241610738255034, "percentage": 41.89, "elapsed_time": "3:57:59", "remaining_time": "5:30:07", "throughput": 1682.68, "total_tokens": 24028464} {"current_steps": 466, "total_steps": 1110, "loss": 0.0514, "lr": 3.1230952910911485e-05, "epoch": 12.268456375838927, "percentage": 41.98, "elapsed_time": "3:58:22", "remaining_time": "5:29:26", "throughput": 1682.91, "total_tokens": 24070200} {"current_steps": 467, "total_steps": 1110, "loss": 0.0434, "lr": 3.1162404374850686e-05, "epoch": 12.29530201342282, "percentage": 42.07, "elapsed_time": "3:58:52", "remaining_time": "5:28:53", "throughput": 1682.96, "total_tokens": 24120608} {"current_steps": 468, "total_steps": 1110, "loss": 0.0481, "lr": 3.109380647554604e-05, "epoch": 12.322147651006711, "percentage": 42.16, "elapsed_time": "3:59:20", "remaining_time": "5:28:20", "throughput": 1683.11, "total_tokens": 24170744} {"current_steps": 469, "total_steps": 1110, "loss": 0.0525, "lr": 3.1025159762493276e-05, "epoch": 12.348993288590604, "percentage": 42.25, "elapsed_time": "3:59:47", "remaining_time": "5:27:43", "throughput": 1683.31, "total_tokens": 24218168} {"current_steps": 470, "total_steps": 1110, "loss": 0.0468, "lr": 3.0956464785579124e-05, "epoch": 12.375838926174497, "percentage": 42.34, "elapsed_time": "4:00:19", "remaining_time": "5:27:15", "throughput": 1683.24, "total_tokens": 24272256} {"current_steps": 471, "total_steps": 1110, "loss": 0.0427, "lr": 3.088772209507694e-05, "epoch": 12.40268456375839, "percentage": 42.43, "elapsed_time": "4:00:52", "remaining_time": "5:26:47", "throughput": 1683.56, "total_tokens": 24331456} {"current_steps": 472, "total_steps": 1110, "loss": 0.0473, "lr": 3.0818932241642276e-05, "epoch": 12.429530201342281, "percentage": 42.52, "elapsed_time": "4:01:14", "remaining_time": "5:26:05", "throughput": 1683.87, "total_tokens": 24373712} {"current_steps": 473, "total_steps": 1110, "loss": 0.0584, "lr": 3.075009577630847e-05, "epoch": 12.456375838926174, "percentage": 42.61, "elapsed_time": "4:01:49", "remaining_time": "5:25:40", "throughput": 1683.68, "total_tokens": 24429440} {"current_steps": 474, "total_steps": 1110, "loss": 0.0629, "lr": 3.0681213250482255e-05, "epoch": 12.483221476510067, "percentage": 42.7, "elapsed_time": "4:02:34", "remaining_time": "5:25:28", "throughput": 1682.91, "total_tokens": 24493976} {"current_steps": 475, "total_steps": 1110, "loss": 0.0521, "lr": 3.061228521593931e-05, "epoch": 12.51006711409396, "percentage": 42.79, "elapsed_time": "4:03:04", "remaining_time": "5:24:57", "throughput": 1683.23, "total_tokens": 24549648} {"current_steps": 476, "total_steps": 1110, "loss": 0.0392, "lr": 3.0543312224819894e-05, "epoch": 12.536912751677852, "percentage": 42.88, "elapsed_time": "4:03:36", "remaining_time": "5:24:28", "throughput": 1682.98, "total_tokens": 24599264} {"current_steps": 477, "total_steps": 1110, "loss": 0.0825, "lr": 3.0474294829624327e-05, "epoch": 12.563758389261745, "percentage": 42.97, "elapsed_time": "4:04:23", "remaining_time": "5:24:18", "throughput": 1681.96, "total_tokens": 24662888} {"current_steps": 478, "total_steps": 1110, "loss": 0.0451, "lr": 3.0405233583208674e-05, "epoch": 12.590604026845638, "percentage": 43.06, "elapsed_time": "4:04:53", "remaining_time": "5:23:47", "throughput": 1682.07, "total_tokens": 24715728} {"current_steps": 479, "total_steps": 1110, "loss": 0.0457, "lr": 3.0336129038780236e-05, "epoch": 12.61744966442953, "percentage": 43.15, "elapsed_time": "4:05:21", "remaining_time": "5:23:13", "throughput": 1682.22, "total_tokens": 24765544} {"current_steps": 480, "total_steps": 1110, "loss": 0.0529, "lr": 3.0266981749893157e-05, "epoch": 12.644295302013422, "percentage": 43.24, "elapsed_time": "4:05:52", "remaining_time": "5:22:42", "throughput": 1682.36, "total_tokens": 24819168} {"current_steps": 481, "total_steps": 1110, "loss": 0.0539, "lr": 3.0197792270443982e-05, "epoch": 12.671140939597315, "percentage": 43.33, "elapsed_time": "4:06:21", "remaining_time": "5:22:09", "throughput": 1682.33, "total_tokens": 24867464} {"current_steps": 482, "total_steps": 1110, "loss": 0.0577, "lr": 3.0128561154667218e-05, "epoch": 12.697986577181208, "percentage": 43.42, "elapsed_time": "4:06:54", "remaining_time": "5:21:41", "throughput": 1682.08, "total_tokens": 24918432} {"current_steps": 483, "total_steps": 1110, "loss": 0.0581, "lr": 3.0059288957130892e-05, "epoch": 12.724832214765101, "percentage": 43.51, "elapsed_time": "4:07:18", "remaining_time": "5:21:02", "throughput": 1682.36, "total_tokens": 24963248} {"current_steps": 484, "total_steps": 1110, "loss": 0.0575, "lr": 2.998997623273212e-05, "epoch": 12.751677852348994, "percentage": 43.6, "elapsed_time": "4:07:40", "remaining_time": "5:20:19", "throughput": 1682.57, "total_tokens": 25003240} {"current_steps": 485, "total_steps": 1110, "loss": 0.0552, "lr": 2.9920623536692638e-05, "epoch": 12.778523489932885, "percentage": 43.69, "elapsed_time": "4:08:08", "remaining_time": "5:19:45", "throughput": 1682.8, "total_tokens": 25053816} {"current_steps": 486, "total_steps": 1110, "loss": 0.0574, "lr": 2.985123142455438e-05, "epoch": 12.805369127516778, "percentage": 43.78, "elapsed_time": "4:08:37", "remaining_time": "5:19:13", "throughput": 1683.06, "total_tokens": 25107392} {"current_steps": 487, "total_steps": 1110, "loss": 0.0557, "lr": 2.9781800452175034e-05, "epoch": 12.832214765100671, "percentage": 43.87, "elapsed_time": "4:09:16", "remaining_time": "5:18:52", "throughput": 1682.44, "total_tokens": 25162616} {"current_steps": 488, "total_steps": 1110, "loss": 0.0424, "lr": 2.971233117572354e-05, "epoch": 12.859060402684564, "percentage": 43.96, "elapsed_time": "4:10:04", "remaining_time": "5:18:44", "throughput": 1681.56, "total_tokens": 25231176} {"current_steps": 489, "total_steps": 1110, "loss": 0.0497, "lr": 2.9642824151675702e-05, "epoch": 12.885906040268456, "percentage": 44.05, "elapsed_time": "4:10:39", "remaining_time": "5:18:18", "throughput": 1681.54, "total_tokens": 25289112} {"current_steps": 490, "total_steps": 1110, "loss": 0.0549, "lr": 2.9573279936809667e-05, "epoch": 12.912751677852349, "percentage": 44.14, "elapsed_time": "4:11:03", "remaining_time": "5:17:40", "throughput": 1681.74, "total_tokens": 25332992} {"current_steps": 491, "total_steps": 1110, "loss": 0.05, "lr": 2.950369908820152e-05, "epoch": 12.939597315436242, "percentage": 44.23, "elapsed_time": "4:11:35", "remaining_time": "5:17:10", "throughput": 1681.7, "total_tokens": 25385360} {"current_steps": 492, "total_steps": 1110, "loss": 0.0503, "lr": 2.9434082163220773e-05, "epoch": 12.966442953020135, "percentage": 44.32, "elapsed_time": "4:12:09", "remaining_time": "5:16:44", "throughput": 1681.55, "total_tokens": 25441344} {"current_steps": 493, "total_steps": 1110, "loss": 0.0448, "lr": 2.9364429719525953e-05, "epoch": 12.993288590604028, "percentage": 44.41, "elapsed_time": "4:12:39", "remaining_time": "5:16:12", "throughput": 1681.58, "total_tokens": 25491584} {"current_steps": 494, "total_steps": 1110, "loss": 0.0613, "lr": 2.9294742315060075e-05, "epoch": 13.0, "percentage": 44.5, "elapsed_time": "4:12:46", "remaining_time": "5:15:11", "throughput": 1681.59, "total_tokens": 25503504} {"current_steps": 495, "total_steps": 1110, "loss": 0.0345, "lr": 2.9225020508046232e-05, "epoch": 13.026845637583893, "percentage": 44.59, "elapsed_time": "4:13:19", "remaining_time": "5:14:44", "throughput": 1681.48, "total_tokens": 25557552} {"current_steps": 496, "total_steps": 1110, "loss": 0.0347, "lr": 2.915526485698306e-05, "epoch": 13.053691275167786, "percentage": 44.68, "elapsed_time": "4:13:47", "remaining_time": "5:14:10", "throughput": 1681.68, "total_tokens": 25607800} {"current_steps": 497, "total_steps": 1110, "loss": 0.0447, "lr": 2.9085475920640337e-05, "epoch": 13.080536912751677, "percentage": 44.77, "elapsed_time": "4:14:17", "remaining_time": "5:13:38", "throughput": 1681.71, "total_tokens": 25658640} {"current_steps": 498, "total_steps": 1110, "loss": 0.0436, "lr": 2.901565425805443e-05, "epoch": 13.10738255033557, "percentage": 44.86, "elapsed_time": "4:14:44", "remaining_time": "5:13:02", "throughput": 1681.75, "total_tokens": 25703856} {"current_steps": 499, "total_steps": 1110, "loss": 0.0394, "lr": 2.8945800428523902e-05, "epoch": 13.134228187919463, "percentage": 44.95, "elapsed_time": "4:15:15", "remaining_time": "5:12:32", "throughput": 1681.74, "total_tokens": 25756584} {"current_steps": 500, "total_steps": 1110, "loss": 0.0479, "lr": 2.8875914991604948e-05, "epoch": 13.161073825503356, "percentage": 45.05, "elapsed_time": "4:15:39", "remaining_time": "5:11:54", "throughput": 1681.91, "total_tokens": 25799784} {"current_steps": 501, "total_steps": 1110, "loss": 0.0528, "lr": 2.8805998507106956e-05, "epoch": 13.187919463087248, "percentage": 45.14, "elapsed_time": "4:16:02", "remaining_time": "5:11:14", "throughput": 1682.17, "total_tokens": 25842528} {"current_steps": 502, "total_steps": 1110, "loss": 0.0348, "lr": 2.8736051535088043e-05, "epoch": 13.21476510067114, "percentage": 45.23, "elapsed_time": "4:16:33", "remaining_time": "5:10:43", "throughput": 1682.23, "total_tokens": 25895520} {"current_steps": 503, "total_steps": 1110, "loss": 0.0386, "lr": 2.8666074635850505e-05, "epoch": 13.241610738255034, "percentage": 45.32, "elapsed_time": "4:17:00", "remaining_time": "5:10:09", "throughput": 1682.37, "total_tokens": 25943552} {"current_steps": 504, "total_steps": 1110, "loss": 0.0367, "lr": 2.8596068369936386e-05, "epoch": 13.268456375838927, "percentage": 45.41, "elapsed_time": "4:17:32", "remaining_time": "5:09:40", "throughput": 1682.34, "total_tokens": 25997160} {"current_steps": 505, "total_steps": 1110, "loss": 0.0331, "lr": 2.8526033298122985e-05, "epoch": 13.29530201342282, "percentage": 45.5, "elapsed_time": "4:18:10", "remaining_time": "5:09:17", "throughput": 1681.99, "total_tokens": 26054912} {"current_steps": 506, "total_steps": 1110, "loss": 0.0358, "lr": 2.845596998141831e-05, "epoch": 13.322147651006711, "percentage": 45.59, "elapsed_time": "4:18:45", "remaining_time": "5:08:52", "throughput": 1681.96, "total_tokens": 26113840} {"current_steps": 507, "total_steps": 1110, "loss": 0.0428, "lr": 2.8385878981056662e-05, "epoch": 13.348993288590604, "percentage": 45.68, "elapsed_time": "4:19:15", "remaining_time": "5:08:20", "throughput": 1682.09, "total_tokens": 26165736} {"current_steps": 508, "total_steps": 1110, "loss": 0.0387, "lr": 2.831576085849406e-05, "epoch": 13.375838926174497, "percentage": 45.77, "elapsed_time": "4:19:43", "remaining_time": "5:07:46", "throughput": 1682.19, "total_tokens": 26214168} {"current_steps": 509, "total_steps": 1110, "loss": 0.0447, "lr": 2.824561617540381e-05, "epoch": 13.40268456375839, "percentage": 45.86, "elapsed_time": "4:20:04", "remaining_time": "5:07:05", "throughput": 1682.56, "total_tokens": 26256160} {"current_steps": 510, "total_steps": 1110, "loss": 0.0361, "lr": 2.8175445493671972e-05, "epoch": 13.429530201342281, "percentage": 45.95, "elapsed_time": "4:20:32", "remaining_time": "5:06:31", "throughput": 1682.87, "total_tokens": 26308112} {"current_steps": 511, "total_steps": 1110, "loss": 0.069, "lr": 2.810524937539285e-05, "epoch": 13.456375838926174, "percentage": 46.04, "elapsed_time": "4:21:06", "remaining_time": "5:06:04", "throughput": 1682.54, "total_tokens": 26360064} {"current_steps": 512, "total_steps": 1110, "loss": 0.039, "lr": 2.8035028382864532e-05, "epoch": 13.483221476510067, "percentage": 46.13, "elapsed_time": "4:21:38", "remaining_time": "5:05:35", "throughput": 1682.78, "total_tokens": 26417392} {"current_steps": 513, "total_steps": 1110, "loss": 0.0377, "lr": 2.7964783078584333e-05, "epoch": 13.51006711409396, "percentage": 46.22, "elapsed_time": "4:22:08", "remaining_time": "5:05:03", "throughput": 1682.85, "total_tokens": 26468696} {"current_steps": 514, "total_steps": 1110, "loss": 0.0678, "lr": 2.789451402524433e-05, "epoch": 13.536912751677852, "percentage": 46.31, "elapsed_time": "4:22:45", "remaining_time": "5:04:40", "throughput": 1682.5, "total_tokens": 26524752} {"current_steps": 515, "total_steps": 1110, "loss": 0.0399, "lr": 2.782422178572682e-05, "epoch": 13.563758389261745, "percentage": 46.4, "elapsed_time": "4:23:13", "remaining_time": "5:04:06", "throughput": 1682.88, "total_tokens": 26577968} {"current_steps": 516, "total_steps": 1110, "loss": 0.0403, "lr": 2.7753906923099865e-05, "epoch": 13.590604026845638, "percentage": 46.49, "elapsed_time": "4:23:45", "remaining_time": "5:03:38", "throughput": 1682.78, "total_tokens": 26631360} {"current_steps": 517, "total_steps": 1110, "loss": 0.0572, "lr": 2.768357000061271e-05, "epoch": 13.61744966442953, "percentage": 46.58, "elapsed_time": "4:24:29", "remaining_time": "5:03:22", "throughput": 1682.08, "total_tokens": 26693888} {"current_steps": 518, "total_steps": 1110, "loss": 0.0455, "lr": 2.761321158169134e-05, "epoch": 13.644295302013422, "percentage": 46.67, "elapsed_time": "4:24:53", "remaining_time": "5:02:43", "throughput": 1682.26, "total_tokens": 26736344} {"current_steps": 519, "total_steps": 1110, "loss": 0.0513, "lr": 2.75428322299339e-05, "epoch": 13.671140939597315, "percentage": 46.76, "elapsed_time": "4:25:44", "remaining_time": "5:02:36", "throughput": 1681.44, "total_tokens": 26809512} {"current_steps": 520, "total_steps": 1110, "loss": 0.0387, "lr": 2.7472432509106248e-05, "epoch": 13.697986577181208, "percentage": 46.85, "elapsed_time": "4:26:15", "remaining_time": "5:02:06", "throughput": 1681.38, "total_tokens": 26861680} {"current_steps": 521, "total_steps": 1110, "loss": 0.052, "lr": 2.7402012983137382e-05, "epoch": 13.724832214765101, "percentage": 46.94, "elapsed_time": "4:26:36", "remaining_time": "5:01:24", "throughput": 1681.68, "total_tokens": 26901712} {"current_steps": 522, "total_steps": 1110, "loss": 0.0359, "lr": 2.7331574216114964e-05, "epoch": 13.751677852348994, "percentage": 47.03, "elapsed_time": "4:27:18", "remaining_time": "5:01:06", "throughput": 1681.41, "total_tokens": 26966944} {"current_steps": 523, "total_steps": 1110, "loss": 0.0334, "lr": 2.726111677228077e-05, "epoch": 13.778523489932885, "percentage": 47.12, "elapsed_time": "4:27:45", "remaining_time": "5:00:31", "throughput": 1681.66, "total_tokens": 27016728} {"current_steps": 524, "total_steps": 1110, "loss": 0.0362, "lr": 2.71906412160262e-05, "epoch": 13.805369127516778, "percentage": 47.21, "elapsed_time": "4:28:29", "remaining_time": "5:00:15", "throughput": 1681.25, "total_tokens": 27083216} {"current_steps": 525, "total_steps": 1110, "loss": 0.0406, "lr": 2.7120148111887732e-05, "epoch": 13.832214765100671, "percentage": 47.3, "elapsed_time": "4:28:54", "remaining_time": "4:59:37", "throughput": 1681.35, "total_tokens": 27127072} {"current_steps": 526, "total_steps": 1110, "loss": 0.0412, "lr": 2.7049638024542407e-05, "epoch": 13.859060402684564, "percentage": 47.39, "elapsed_time": "4:29:30", "remaining_time": "4:59:13", "throughput": 1681.11, "total_tokens": 27184224} {"current_steps": 527, "total_steps": 1110, "loss": 0.0518, "lr": 2.6979111518803307e-05, "epoch": 13.885906040268456, "percentage": 47.48, "elapsed_time": "4:29:57", "remaining_time": "4:58:38", "throughput": 1681.1, "total_tokens": 27229088} {"current_steps": 528, "total_steps": 1110, "loss": 0.0417, "lr": 2.6908569159615038e-05, "epoch": 13.912751677852349, "percentage": 47.57, "elapsed_time": "4:30:29", "remaining_time": "4:58:09", "throughput": 1680.88, "total_tokens": 27280016} {"current_steps": 529, "total_steps": 1110, "loss": 0.0429, "lr": 2.6838011512049204e-05, "epoch": 13.939597315436242, "percentage": 47.66, "elapsed_time": "4:31:09", "remaining_time": "4:57:48", "throughput": 1680.7, "total_tokens": 27343896} {"current_steps": 530, "total_steps": 1110, "loss": 0.0425, "lr": 2.6767439141299865e-05, "epoch": 13.966442953020135, "percentage": 47.75, "elapsed_time": "4:31:44", "remaining_time": "4:57:22", "throughput": 1680.65, "total_tokens": 27402624} {"current_steps": 531, "total_steps": 1110, "loss": 0.0397, "lr": 2.6696852612679023e-05, "epoch": 13.993288590604028, "percentage": 47.84, "elapsed_time": "4:32:11", "remaining_time": "4:56:48", "throughput": 1680.82, "total_tokens": 27450632} {"current_steps": 532, "total_steps": 1110, "loss": 0.0339, "lr": 2.662625249161208e-05, "epoch": 14.0, "percentage": 47.93, "elapsed_time": "4:32:19", "remaining_time": "4:55:52", "throughput": 1680.89, "total_tokens": 27465312} {"current_steps": 533, "total_steps": 1110, "loss": 0.0277, "lr": 2.6555639343633332e-05, "epoch": 14.026845637583893, "percentage": 48.02, "elapsed_time": "4:32:48", "remaining_time": "4:55:20", "throughput": 1680.93, "total_tokens": 27514912} {"current_steps": 534, "total_steps": 1110, "loss": 0.0357, "lr": 2.648501373438142e-05, "epoch": 14.053691275167786, "percentage": 48.11, "elapsed_time": "4:33:15", "remaining_time": "4:54:45", "throughput": 1680.93, "total_tokens": 27560544} {"current_steps": 535, "total_steps": 1110, "loss": 0.0317, "lr": 2.6414376229594813e-05, "epoch": 14.080536912751677, "percentage": 48.2, "elapsed_time": "4:33:48", "remaining_time": "4:54:17", "throughput": 1680.91, "total_tokens": 27615240} {"current_steps": 536, "total_steps": 1110, "loss": 0.0325, "lr": 2.634372739510725e-05, "epoch": 14.10738255033557, "percentage": 48.29, "elapsed_time": "4:34:16", "remaining_time": "4:53:42", "throughput": 1681.16, "total_tokens": 27665200} {"current_steps": 537, "total_steps": 1110, "loss": 0.0342, "lr": 2.6273067796843244e-05, "epoch": 14.134228187919463, "percentage": 48.38, "elapsed_time": "4:34:38", "remaining_time": "4:53:02", "throughput": 1681.38, "total_tokens": 27705992} {"current_steps": 538, "total_steps": 1110, "loss": 0.0542, "lr": 2.6202398000813517e-05, "epoch": 14.161073825503356, "percentage": 48.47, "elapsed_time": "4:35:13", "remaining_time": "4:52:37", "throughput": 1681.1, "total_tokens": 27760800} {"current_steps": 539, "total_steps": 1110, "loss": 0.0334, "lr": 2.613171857311048e-05, "epoch": 14.187919463087248, "percentage": 48.56, "elapsed_time": "4:35:41", "remaining_time": "4:52:03", "throughput": 1681.33, "total_tokens": 27811840} {"current_steps": 540, "total_steps": 1110, "loss": 0.0343, "lr": 2.606103007990371e-05, "epoch": 14.21476510067114, "percentage": 48.65, "elapsed_time": "4:36:13", "remaining_time": "4:51:33", "throughput": 1681.51, "total_tokens": 27867816} {"current_steps": 541, "total_steps": 1110, "loss": 0.0328, "lr": 2.5990333087435387e-05, "epoch": 14.241610738255034, "percentage": 48.74, "elapsed_time": "4:36:40", "remaining_time": "4:50:59", "throughput": 1681.52, "total_tokens": 27913448} {"current_steps": 542, "total_steps": 1110, "loss": 0.0334, "lr": 2.5919628162015785e-05, "epoch": 14.268456375838927, "percentage": 48.83, "elapsed_time": "4:37:06", "remaining_time": "4:50:24", "throughput": 1681.27, "total_tokens": 27953896} {"current_steps": 543, "total_steps": 1110, "loss": 0.0279, "lr": 2.5848915870018718e-05, "epoch": 14.29530201342282, "percentage": 48.92, "elapsed_time": "4:37:48", "remaining_time": "4:50:04", "throughput": 1680.98, "total_tokens": 28018624} {"current_steps": 544, "total_steps": 1110, "loss": 0.032, "lr": 2.5778196777877012e-05, "epoch": 14.322147651006711, "percentage": 49.01, "elapsed_time": "4:38:14", "remaining_time": "4:49:29", "throughput": 1681.25, "total_tokens": 28067112} {"current_steps": 545, "total_steps": 1110, "loss": 0.035, "lr": 2.570747145207796e-05, "epoch": 14.348993288590604, "percentage": 49.1, "elapsed_time": "4:38:39", "remaining_time": "4:48:52", "throughput": 1681.49, "total_tokens": 28113440} {"current_steps": 546, "total_steps": 1110, "loss": 0.0459, "lr": 2.5636740459158777e-05, "epoch": 14.375838926174497, "percentage": 49.19, "elapsed_time": "4:39:33", "remaining_time": "4:48:46", "throughput": 1680.42, "total_tokens": 28187168} {"current_steps": 547, "total_steps": 1110, "loss": 0.0353, "lr": 2.556600436570211e-05, "epoch": 14.40268456375839, "percentage": 49.28, "elapsed_time": "4:40:02", "remaining_time": "4:48:13", "throughput": 1680.6, "total_tokens": 28237744} {"current_steps": 548, "total_steps": 1110, "loss": 0.0323, "lr": 2.5495263738331442e-05, "epoch": 14.429530201342281, "percentage": 49.37, "elapsed_time": "4:40:26", "remaining_time": "4:47:35", "throughput": 1680.74, "total_tokens": 28280408} {"current_steps": 549, "total_steps": 1110, "loss": 0.0484, "lr": 2.542451914370656e-05, "epoch": 14.456375838926174, "percentage": 49.46, "elapsed_time": "4:41:01", "remaining_time": "4:47:10", "throughput": 1680.52, "total_tokens": 28336328} {"current_steps": 550, "total_steps": 1110, "loss": 0.027, "lr": 2.5353771148519057e-05, "epoch": 14.483221476510067, "percentage": 49.55, "elapsed_time": "4:41:36", "remaining_time": "4:46:43", "throughput": 1680.6, "total_tokens": 28396168} {"current_steps": 551, "total_steps": 1110, "loss": 0.0319, "lr": 2.5283020319487742e-05, "epoch": 14.51006711409396, "percentage": 49.64, "elapsed_time": "4:42:00", "remaining_time": "4:46:05", "throughput": 1680.82, "total_tokens": 28439520} {"current_steps": 552, "total_steps": 1110, "loss": 0.0269, "lr": 2.521226722335414e-05, "epoch": 14.536912751677852, "percentage": 49.73, "elapsed_time": "4:42:31", "remaining_time": "4:45:35", "throughput": 1680.85, "total_tokens": 28493080} {"current_steps": 553, "total_steps": 1110, "loss": 0.0327, "lr": 2.514151242687794e-05, "epoch": 14.563758389261745, "percentage": 49.82, "elapsed_time": "4:43:04", "remaining_time": "4:45:07", "throughput": 1680.82, "total_tokens": 28548368} {"current_steps": 554, "total_steps": 1110, "loss": 0.0334, "lr": 2.507075649683243e-05, "epoch": 14.590604026845638, "percentage": 49.91, "elapsed_time": "4:43:36", "remaining_time": "4:44:37", "throughput": 1680.72, "total_tokens": 28600024} {"current_steps": 555, "total_steps": 1110, "loss": 0.0263, "lr": 2.5e-05, "epoch": 14.61744966442953, "percentage": 50.0, "elapsed_time": "4:44:14", "remaining_time": "4:44:14", "throughput": 1680.8, "total_tokens": 28665256} {"current_steps": 556, "total_steps": 1110, "loss": 0.0409, "lr": 2.4929243503167572e-05, "epoch": 14.644295302013422, "percentage": 50.09, "elapsed_time": "4:44:42", "remaining_time": "4:43:40", "throughput": 1680.65, "total_tokens": 28709472} {"current_steps": 557, "total_steps": 1110, "loss": 0.0374, "lr": 2.485848757312207e-05, "epoch": 14.671140939597315, "percentage": 50.18, "elapsed_time": "4:45:10", "remaining_time": "4:43:07", "throughput": 1680.71, "total_tokens": 28757456} {"current_steps": 558, "total_steps": 1110, "loss": 0.0261, "lr": 2.4787732776645865e-05, "epoch": 14.697986577181208, "percentage": 50.27, "elapsed_time": "4:45:42", "remaining_time": "4:42:38", "throughput": 1680.91, "total_tokens": 28814952} {"current_steps": 559, "total_steps": 1110, "loss": 0.0364, "lr": 2.4716979680512267e-05, "epoch": 14.724832214765101, "percentage": 50.36, "elapsed_time": "4:46:29", "remaining_time": "4:42:23", "throughput": 1680.45, "total_tokens": 28885968} {"current_steps": 560, "total_steps": 1110, "loss": 0.0274, "lr": 2.4646228851480956e-05, "epoch": 14.751677852348994, "percentage": 50.45, "elapsed_time": "4:47:08", "remaining_time": "4:42:00", "throughput": 1680.32, "total_tokens": 28948576} {"current_steps": 561, "total_steps": 1110, "loss": 0.0375, "lr": 2.4575480856293447e-05, "epoch": 14.778523489932885, "percentage": 50.54, "elapsed_time": "4:47:33", "remaining_time": "4:41:24", "throughput": 1680.58, "total_tokens": 28995904} {"current_steps": 562, "total_steps": 1110, "loss": 0.0336, "lr": 2.450473626166856e-05, "epoch": 14.805369127516778, "percentage": 50.63, "elapsed_time": "4:47:59", "remaining_time": "4:40:49", "throughput": 1680.99, "total_tokens": 29046600} {"current_steps": 563, "total_steps": 1110, "loss": 0.0327, "lr": 2.4433995634297885e-05, "epoch": 14.832214765100671, "percentage": 50.72, "elapsed_time": "4:48:36", "remaining_time": "4:40:24", "throughput": 1680.63, "total_tokens": 29102280} {"current_steps": 564, "total_steps": 1110, "loss": 0.041, "lr": 2.4363259540841222e-05, "epoch": 14.859060402684564, "percentage": 50.81, "elapsed_time": "4:48:58", "remaining_time": "4:39:45", "throughput": 1680.97, "total_tokens": 29145872} {"current_steps": 565, "total_steps": 1110, "loss": 0.0374, "lr": 2.429252854792205e-05, "epoch": 14.885906040268456, "percentage": 50.9, "elapsed_time": "4:49:25", "remaining_time": "4:39:10", "throughput": 1680.83, "total_tokens": 29188232} {"current_steps": 566, "total_steps": 1110, "loss": 0.0351, "lr": 2.4221803222122993e-05, "epoch": 14.912751677852349, "percentage": 50.99, "elapsed_time": "4:50:03", "remaining_time": "4:38:47", "throughput": 1680.88, "total_tokens": 29253440} {"current_steps": 567, "total_steps": 1110, "loss": 0.0329, "lr": 2.4151084129981285e-05, "epoch": 14.939597315436242, "percentage": 51.08, "elapsed_time": "4:50:36", "remaining_time": "4:38:18", "throughput": 1680.68, "total_tokens": 29304552} {"current_steps": 568, "total_steps": 1110, "loss": 0.0327, "lr": 2.4080371837984218e-05, "epoch": 14.966442953020135, "percentage": 51.17, "elapsed_time": "4:51:06", "remaining_time": "4:37:46", "throughput": 1680.73, "total_tokens": 29355840} {"current_steps": 569, "total_steps": 1110, "loss": 0.0292, "lr": 2.4009666912564615e-05, "epoch": 14.993288590604028, "percentage": 51.26, "elapsed_time": "4:51:38", "remaining_time": "4:37:17", "throughput": 1681.07, "total_tokens": 29416032} {"current_steps": 570, "total_steps": 1110, "loss": 0.0353, "lr": 2.39389699200963e-05, "epoch": 15.0, "percentage": 51.35, "elapsed_time": "4:51:43", "remaining_time": "4:36:22", "throughput": 1681.17, "total_tokens": 29427120} {"current_steps": 571, "total_steps": 1110, "loss": 0.0264, "lr": 2.386828142688953e-05, "epoch": 15.026845637583893, "percentage": 51.44, "elapsed_time": "4:52:13", "remaining_time": "4:35:51", "throughput": 1681.21, "total_tokens": 29477816} {"current_steps": 572, "total_steps": 1110, "loss": 0.0224, "lr": 2.37976019991865e-05, "epoch": 15.053691275167786, "percentage": 51.53, "elapsed_time": "4:52:53", "remaining_time": "4:35:28", "throughput": 1680.81, "total_tokens": 29537560} {"current_steps": 573, "total_steps": 1110, "loss": 0.0285, "lr": 2.3726932203156772e-05, "epoch": 15.080536912751677, "percentage": 51.62, "elapsed_time": "4:53:26", "remaining_time": "4:35:00", "throughput": 1680.72, "total_tokens": 29591184} {"current_steps": 574, "total_steps": 1110, "loss": 0.0223, "lr": 2.3656272604892753e-05, "epoch": 15.10738255033557, "percentage": 51.71, "elapsed_time": "4:53:56", "remaining_time": "4:34:28", "throughput": 1680.67, "total_tokens": 29641248} {"current_steps": 575, "total_steps": 1110, "loss": 0.0397, "lr": 2.358562377040519e-05, "epoch": 15.134228187919463, "percentage": 51.8, "elapsed_time": "4:54:37", "remaining_time": "4:34:07", "throughput": 1680.19, "total_tokens": 29701672} {"current_steps": 576, "total_steps": 1110, "loss": 0.0335, "lr": 2.351498626561858e-05, "epoch": 15.161073825503356, "percentage": 51.89, "elapsed_time": "4:55:08", "remaining_time": "4:33:36", "throughput": 1680.13, "total_tokens": 29751776} {"current_steps": 577, "total_steps": 1110, "loss": 0.0279, "lr": 2.344436065636667e-05, "epoch": 15.187919463087248, "percentage": 51.98, "elapsed_time": "4:55:33", "remaining_time": "4:33:01", "throughput": 1680.27, "total_tokens": 29797896} {"current_steps": 578, "total_steps": 1110, "loss": 0.0249, "lr": 2.3373747508387926e-05, "epoch": 15.21476510067114, "percentage": 52.07, "elapsed_time": "4:55:58", "remaining_time": "4:32:25", "throughput": 1680.41, "total_tokens": 29841760} {"current_steps": 579, "total_steps": 1110, "loss": 0.0326, "lr": 2.3303147387320983e-05, "epoch": 15.241610738255034, "percentage": 52.16, "elapsed_time": "4:56:20", "remaining_time": "4:31:46", "throughput": 1680.6, "total_tokens": 29881824} {"current_steps": 580, "total_steps": 1110, "loss": 0.023, "lr": 2.3232560858700137e-05, "epoch": 15.268456375838927, "percentage": 52.25, "elapsed_time": "4:56:58", "remaining_time": "4:31:22", "throughput": 1680.59, "total_tokens": 29945264} {"current_steps": 581, "total_steps": 1110, "loss": 0.0246, "lr": 2.31619884879508e-05, "epoch": 15.29530201342282, "percentage": 52.34, "elapsed_time": "4:57:27", "remaining_time": "4:30:50", "throughput": 1680.66, "total_tokens": 29996304} {"current_steps": 582, "total_steps": 1110, "loss": 0.0436, "lr": 2.3091430840384964e-05, "epoch": 15.322147651006711, "percentage": 52.43, "elapsed_time": "4:58:12", "remaining_time": "4:30:32", "throughput": 1680.01, "total_tokens": 30059216} {"current_steps": 583, "total_steps": 1110, "loss": 0.027, "lr": 2.3020888481196702e-05, "epoch": 15.348993288590604, "percentage": 52.52, "elapsed_time": "4:58:40", "remaining_time": "4:29:58", "throughput": 1680.1, "total_tokens": 30107712} {"current_steps": 584, "total_steps": 1110, "loss": 0.0261, "lr": 2.2950361975457606e-05, "epoch": 15.375838926174497, "percentage": 52.61, "elapsed_time": "4:59:15", "remaining_time": "4:29:32", "throughput": 1680.01, "total_tokens": 30164952} {"current_steps": 585, "total_steps": 1110, "loss": 0.0261, "lr": 2.287985188811228e-05, "epoch": 15.40268456375839, "percentage": 52.7, "elapsed_time": "4:59:46", "remaining_time": "4:29:01", "throughput": 1680.05, "total_tokens": 30217624} {"current_steps": 586, "total_steps": 1110, "loss": 0.0319, "lr": 2.2809358783973798e-05, "epoch": 15.429530201342281, "percentage": 52.79, "elapsed_time": "5:00:15", "remaining_time": "4:28:29", "throughput": 1680.01, "total_tokens": 30265584} {"current_steps": 587, "total_steps": 1110, "loss": 0.0219, "lr": 2.2738883227719228e-05, "epoch": 15.456375838926174, "percentage": 52.88, "elapsed_time": "5:00:44", "remaining_time": "4:27:56", "throughput": 1680.33, "total_tokens": 30320120} {"current_steps": 588, "total_steps": 1110, "loss": 0.0273, "lr": 2.2668425783885038e-05, "epoch": 15.483221476510067, "percentage": 52.97, "elapsed_time": "5:01:13", "remaining_time": "4:27:24", "throughput": 1680.28, "total_tokens": 30368304} {"current_steps": 589, "total_steps": 1110, "loss": 0.0296, "lr": 2.259798701686262e-05, "epoch": 15.51006711409396, "percentage": 53.06, "elapsed_time": "5:01:40", "remaining_time": "4:26:50", "throughput": 1680.4, "total_tokens": 30415520} {"current_steps": 590, "total_steps": 1110, "loss": 0.024, "lr": 2.2527567490893758e-05, "epoch": 15.536912751677852, "percentage": 53.15, "elapsed_time": "5:02:12", "remaining_time": "4:26:20", "throughput": 1680.32, "total_tokens": 30467712} {"current_steps": 591, "total_steps": 1110, "loss": 0.0245, "lr": 2.2457167770066105e-05, "epoch": 15.563758389261745, "percentage": 53.24, "elapsed_time": "5:02:42", "remaining_time": "4:25:50", "throughput": 1680.55, "total_tokens": 30523456} {"current_steps": 592, "total_steps": 1110, "loss": 0.0256, "lr": 2.238678841830867e-05, "epoch": 15.590604026845638, "percentage": 53.33, "elapsed_time": "5:03:11", "remaining_time": "4:25:17", "throughput": 1680.81, "total_tokens": 30576392} {"current_steps": 593, "total_steps": 1110, "loss": 0.021, "lr": 2.231642999938729e-05, "epoch": 15.61744966442953, "percentage": 53.42, "elapsed_time": "5:03:42", "remaining_time": "4:24:47", "throughput": 1680.85, "total_tokens": 30629520} {"current_steps": 594, "total_steps": 1110, "loss": 0.0237, "lr": 2.2246093076900144e-05, "epoch": 15.644295302013422, "percentage": 53.51, "elapsed_time": "5:04:16", "remaining_time": "4:24:19", "throughput": 1680.92, "total_tokens": 30688112} {"current_steps": 595, "total_steps": 1110, "loss": 0.0247, "lr": 2.2175778214273185e-05, "epoch": 15.671140939597315, "percentage": 53.6, "elapsed_time": "5:04:47", "remaining_time": "4:23:48", "throughput": 1680.92, "total_tokens": 30739848} {"current_steps": 596, "total_steps": 1110, "loss": 0.0303, "lr": 2.2105485974755686e-05, "epoch": 15.697986577181208, "percentage": 53.69, "elapsed_time": "5:05:17", "remaining_time": "4:23:17", "throughput": 1681.24, "total_tokens": 30795912} {"current_steps": 597, "total_steps": 1110, "loss": 0.0252, "lr": 2.203521692141568e-05, "epoch": 15.724832214765101, "percentage": 53.78, "elapsed_time": "5:05:52", "remaining_time": "4:22:50", "throughput": 1681.07, "total_tokens": 30851976} {"current_steps": 598, "total_steps": 1110, "loss": 0.0205, "lr": 2.1964971617135467e-05, "epoch": 15.751677852348994, "percentage": 53.87, "elapsed_time": "5:06:29", "remaining_time": "4:22:24", "throughput": 1681.11, "total_tokens": 30914536} {"current_steps": 599, "total_steps": 1110, "loss": 0.0262, "lr": 2.189475062460715e-05, "epoch": 15.778523489932885, "percentage": 53.96, "elapsed_time": "5:06:53", "remaining_time": "4:21:48", "throughput": 1681.31, "total_tokens": 30958912} {"current_steps": 600, "total_steps": 1110, "loss": 0.0268, "lr": 2.182455450632803e-05, "epoch": 15.805369127516778, "percentage": 54.05, "elapsed_time": "5:07:20", "remaining_time": "4:21:14", "throughput": 1681.4, "total_tokens": 31005760} {"current_steps": 601, "total_steps": 1110, "loss": 0.0253, "lr": 2.1754383824596193e-05, "epoch": 15.832214765100671, "percentage": 54.14, "elapsed_time": "5:07:49", "remaining_time": "4:20:42", "throughput": 1681.56, "total_tokens": 31058184} {"current_steps": 602, "total_steps": 1110, "loss": 0.0306, "lr": 2.1684239141505942e-05, "epoch": 15.859060402684564, "percentage": 54.23, "elapsed_time": "5:08:25", "remaining_time": "4:20:15", "throughput": 1681.37, "total_tokens": 31114000} {"current_steps": 603, "total_steps": 1110, "loss": 0.0271, "lr": 2.1614121018943344e-05, "epoch": 15.885906040268456, "percentage": 54.32, "elapsed_time": "5:08:47", "remaining_time": "4:19:37", "throughput": 1681.69, "total_tokens": 31157072} {"current_steps": 604, "total_steps": 1110, "loss": 0.0325, "lr": 2.154403001858169e-05, "epoch": 15.912751677852349, "percentage": 54.41, "elapsed_time": "5:09:10", "remaining_time": "4:19:00", "throughput": 1681.92, "total_tokens": 31199576} {"current_steps": 605, "total_steps": 1110, "loss": 0.0439, "lr": 2.1473966701877025e-05, "epoch": 15.939597315436242, "percentage": 54.5, "elapsed_time": "5:09:55", "remaining_time": "4:18:41", "throughput": 1681.38, "total_tokens": 31265624} {"current_steps": 606, "total_steps": 1110, "loss": 0.0292, "lr": 2.1403931630063616e-05, "epoch": 15.966442953020135, "percentage": 54.59, "elapsed_time": "5:10:22", "remaining_time": "4:18:07", "throughput": 1681.59, "total_tokens": 31315160} {"current_steps": 607, "total_steps": 1110, "loss": 0.0269, "lr": 2.1333925364149507e-05, "epoch": 15.993288590604028, "percentage": 54.68, "elapsed_time": "5:11:04", "remaining_time": "4:17:47", "throughput": 1681.18, "total_tokens": 31379144} {"current_steps": 608, "total_steps": 1110, "loss": 0.0298, "lr": 2.126394846491197e-05, "epoch": 16.0, "percentage": 54.77, "elapsed_time": "5:11:10", "remaining_time": "4:16:55", "throughput": 1681.21, "total_tokens": 31388928} {"current_steps": 609, "total_steps": 1110, "loss": 0.016, "lr": 2.119400149289305e-05, "epoch": 16.026845637583893, "percentage": 54.86, "elapsed_time": "5:11:41", "remaining_time": "4:16:24", "throughput": 1681.26, "total_tokens": 31441392} {"current_steps": 610, "total_steps": 1110, "loss": 0.0201, "lr": 2.1124085008395054e-05, "epoch": 16.053691275167786, "percentage": 54.95, "elapsed_time": "5:12:06", "remaining_time": "4:15:49", "throughput": 1681.39, "total_tokens": 31487280} {"current_steps": 611, "total_steps": 1110, "loss": 0.0284, "lr": 2.1054199571476097e-05, "epoch": 16.08053691275168, "percentage": 55.05, "elapsed_time": "5:12:32", "remaining_time": "4:15:15", "throughput": 1681.52, "total_tokens": 31532856} {"current_steps": 612, "total_steps": 1110, "loss": 0.0216, "lr": 2.098434574194557e-05, "epoch": 16.107382550335572, "percentage": 55.14, "elapsed_time": "5:12:56", "remaining_time": "4:14:39", "throughput": 1681.7, "total_tokens": 31577168} {"current_steps": 613, "total_steps": 1110, "loss": 0.0232, "lr": 2.0914524079359672e-05, "epoch": 16.13422818791946, "percentage": 55.23, "elapsed_time": "5:13:23", "remaining_time": "4:14:05", "throughput": 1681.92, "total_tokens": 31625816} {"current_steps": 614, "total_steps": 1110, "loss": 0.0223, "lr": 2.0844735143016946e-05, "epoch": 16.161073825503355, "percentage": 55.32, "elapsed_time": "5:13:54", "remaining_time": "4:13:34", "throughput": 1682.08, "total_tokens": 31680680} {"current_steps": 615, "total_steps": 1110, "loss": 0.0211, "lr": 2.0774979491953777e-05, "epoch": 16.187919463087248, "percentage": 55.41, "elapsed_time": "5:14:33", "remaining_time": "4:13:10", "throughput": 1682.03, "total_tokens": 31745016} {"current_steps": 616, "total_steps": 1110, "loss": 0.0365, "lr": 2.0705257684939927e-05, "epoch": 16.21476510067114, "percentage": 55.5, "elapsed_time": "5:15:13", "remaining_time": "4:12:47", "throughput": 1681.58, "total_tokens": 31804856} {"current_steps": 617, "total_steps": 1110, "loss": 0.0343, "lr": 2.0635570280474053e-05, "epoch": 16.241610738255034, "percentage": 55.59, "elapsed_time": "5:15:46", "remaining_time": "4:12:19", "throughput": 1681.73, "total_tokens": 31863512} {"current_steps": 618, "total_steps": 1110, "loss": 0.0248, "lr": 2.056591783677923e-05, "epoch": 16.268456375838927, "percentage": 55.68, "elapsed_time": "5:16:10", "remaining_time": "4:11:43", "throughput": 1681.81, "total_tokens": 31905328} {"current_steps": 619, "total_steps": 1110, "loss": 0.0203, "lr": 2.049630091179849e-05, "epoch": 16.29530201342282, "percentage": 55.77, "elapsed_time": "5:16:41", "remaining_time": "4:11:11", "throughput": 1681.89, "total_tokens": 31957768} {"current_steps": 620, "total_steps": 1110, "loss": 0.0383, "lr": 2.0426720063190335e-05, "epoch": 16.322147651006713, "percentage": 55.86, "elapsed_time": "5:17:29", "remaining_time": "4:10:55", "throughput": 1681.23, "total_tokens": 32026448} {"current_steps": 621, "total_steps": 1110, "loss": 0.0198, "lr": 2.0357175848324307e-05, "epoch": 16.348993288590606, "percentage": 55.95, "elapsed_time": "5:18:12", "remaining_time": "4:10:34", "throughput": 1680.98, "total_tokens": 32094848} {"current_steps": 622, "total_steps": 1110, "loss": 0.0182, "lr": 2.0287668824276456e-05, "epoch": 16.375838926174495, "percentage": 56.04, "elapsed_time": "5:18:40", "remaining_time": "4:10:01", "throughput": 1681.16, "total_tokens": 32144536} {"current_steps": 623, "total_steps": 1110, "loss": 0.0218, "lr": 2.021819954782497e-05, "epoch": 16.40268456375839, "percentage": 56.13, "elapsed_time": "5:19:13", "remaining_time": "4:09:32", "throughput": 1680.97, "total_tokens": 32196720} {"current_steps": 624, "total_steps": 1110, "loss": 0.0181, "lr": 2.0148768575445617e-05, "epoch": 16.42953020134228, "percentage": 56.22, "elapsed_time": "5:19:56", "remaining_time": "4:09:11", "throughput": 1680.69, "total_tokens": 32263512} {"current_steps": 625, "total_steps": 1110, "loss": 0.0195, "lr": 2.0079376463307368e-05, "epoch": 16.456375838926174, "percentage": 56.31, "elapsed_time": "5:20:26", "remaining_time": "4:08:39", "throughput": 1680.65, "total_tokens": 32312992} {"current_steps": 626, "total_steps": 1110, "loss": 0.0205, "lr": 2.0010023767267888e-05, "epoch": 16.483221476510067, "percentage": 56.4, "elapsed_time": "5:20:55", "remaining_time": "4:08:07", "throughput": 1680.73, "total_tokens": 32363744} {"current_steps": 627, "total_steps": 1110, "loss": 0.0238, "lr": 1.994071104286911e-05, "epoch": 16.51006711409396, "percentage": 56.49, "elapsed_time": "5:21:33", "remaining_time": "4:07:42", "throughput": 1680.21, "total_tokens": 32417112} {"current_steps": 628, "total_steps": 1110, "loss": 0.0402, "lr": 1.9871438845332788e-05, "epoch": 16.536912751677853, "percentage": 56.58, "elapsed_time": "5:22:11", "remaining_time": "4:07:17", "throughput": 1679.97, "total_tokens": 32476672} {"current_steps": 629, "total_steps": 1110, "loss": 0.0185, "lr": 1.980220772955602e-05, "epoch": 16.563758389261746, "percentage": 56.67, "elapsed_time": "5:22:45", "remaining_time": "4:06:48", "throughput": 1679.81, "total_tokens": 32530536} {"current_steps": 630, "total_steps": 1110, "loss": 0.0174, "lr": 1.973301825010685e-05, "epoch": 16.59060402684564, "percentage": 56.76, "elapsed_time": "5:23:16", "remaining_time": "4:06:18", "throughput": 1679.68, "total_tokens": 32580328} {"current_steps": 631, "total_steps": 1110, "loss": 0.0184, "lr": 1.9663870961219766e-05, "epoch": 16.61744966442953, "percentage": 56.85, "elapsed_time": "5:23:51", "remaining_time": "4:05:50", "throughput": 1679.72, "total_tokens": 32638936} {"current_steps": 632, "total_steps": 1110, "loss": 0.0254, "lr": 1.959476641679133e-05, "epoch": 16.644295302013422, "percentage": 56.94, "elapsed_time": "5:24:14", "remaining_time": "4:05:14", "throughput": 1679.96, "total_tokens": 32683272} {"current_steps": 633, "total_steps": 1110, "loss": 0.0219, "lr": 1.9525705170375675e-05, "epoch": 16.671140939597315, "percentage": 57.03, "elapsed_time": "5:24:48", "remaining_time": "4:04:45", "throughput": 1680.15, "total_tokens": 32743112} {"current_steps": 634, "total_steps": 1110, "loss": 0.0193, "lr": 1.945668777518011e-05, "epoch": 16.697986577181208, "percentage": 57.12, "elapsed_time": "5:25:16", "remaining_time": "4:04:12", "throughput": 1680.28, "total_tokens": 32793168} {"current_steps": 635, "total_steps": 1110, "loss": 0.0184, "lr": 1.9387714784060685e-05, "epoch": 16.7248322147651, "percentage": 57.21, "elapsed_time": "5:25:53", "remaining_time": "4:03:46", "throughput": 1680.17, "total_tokens": 32853064} {"current_steps": 636, "total_steps": 1110, "loss": 0.0193, "lr": 1.9318786749517755e-05, "epoch": 16.751677852348994, "percentage": 57.3, "elapsed_time": "5:26:25", "remaining_time": "4:03:16", "throughput": 1680.13, "total_tokens": 32905624} {"current_steps": 637, "total_steps": 1110, "loss": 0.0219, "lr": 1.924990422369154e-05, "epoch": 16.778523489932887, "percentage": 57.39, "elapsed_time": "5:26:55", "remaining_time": "4:02:45", "throughput": 1680.12, "total_tokens": 32957176} {"current_steps": 638, "total_steps": 1110, "loss": 0.0232, "lr": 1.9181067758357734e-05, "epoch": 16.80536912751678, "percentage": 57.48, "elapsed_time": "5:27:22", "remaining_time": "4:02:11", "throughput": 1680.14, "total_tokens": 33002136} {"current_steps": 639, "total_steps": 1110, "loss": 0.0258, "lr": 1.9112277904923065e-05, "epoch": 16.83221476510067, "percentage": 57.57, "elapsed_time": "5:27:45", "remaining_time": "4:01:35", "throughput": 1680.35, "total_tokens": 33044720} {"current_steps": 640, "total_steps": 1110, "loss": 0.0194, "lr": 1.904353521442088e-05, "epoch": 16.859060402684563, "percentage": 57.66, "elapsed_time": "5:28:17", "remaining_time": "4:01:05", "throughput": 1680.24, "total_tokens": 33096992} {"current_steps": 641, "total_steps": 1110, "loss": 0.0215, "lr": 1.8974840237506723e-05, "epoch": 16.885906040268456, "percentage": 57.75, "elapsed_time": "5:28:42", "remaining_time": "4:00:30", "throughput": 1680.5, "total_tokens": 33142904} {"current_steps": 642, "total_steps": 1110, "loss": 0.0234, "lr": 1.8906193524453964e-05, "epoch": 16.91275167785235, "percentage": 57.84, "elapsed_time": "5:29:14", "remaining_time": "4:00:00", "throughput": 1680.51, "total_tokens": 33198224} {"current_steps": 643, "total_steps": 1110, "loss": 0.0245, "lr": 1.8837595625149323e-05, "epoch": 16.93959731543624, "percentage": 57.93, "elapsed_time": "5:29:41", "remaining_time": "3:59:26", "throughput": 1680.65, "total_tokens": 33245576} {"current_steps": 644, "total_steps": 1110, "loss": 0.0228, "lr": 1.8769047089088525e-05, "epoch": 16.966442953020135, "percentage": 58.02, "elapsed_time": "5:30:04", "remaining_time": "3:58:50", "throughput": 1680.94, "total_tokens": 33289928} {"current_steps": 645, "total_steps": 1110, "loss": 0.0204, "lr": 1.8700548465371874e-05, "epoch": 16.993288590604028, "percentage": 58.11, "elapsed_time": "5:30:34", "remaining_time": "3:58:19", "throughput": 1680.93, "total_tokens": 33340464} {"current_steps": 646, "total_steps": 1110, "loss": 0.018, "lr": 1.863210030269985e-05, "epoch": 17.0, "percentage": 58.2, "elapsed_time": "5:30:39", "remaining_time": "3:57:30", "throughput": 1681.02, "total_tokens": 33350736} {"current_steps": 647, "total_steps": 1110, "loss": 0.0166, "lr": 1.856370314936873e-05, "epoch": 17.026845637583893, "percentage": 58.29, "elapsed_time": "5:31:09", "remaining_time": "3:56:58", "throughput": 1681.13, "total_tokens": 33402432} {"current_steps": 648, "total_steps": 1110, "loss": 0.0149, "lr": 1.8495357553266178e-05, "epoch": 17.053691275167786, "percentage": 58.38, "elapsed_time": "5:31:35", "remaining_time": "3:56:25", "throughput": 1681.23, "total_tokens": 33449760} {"current_steps": 649, "total_steps": 1110, "loss": 0.0156, "lr": 1.8427064061866866e-05, "epoch": 17.08053691275168, "percentage": 58.47, "elapsed_time": "5:32:03", "remaining_time": "3:55:52", "throughput": 1681.38, "total_tokens": 33499184} {"current_steps": 650, "total_steps": 1110, "loss": 0.015, "lr": 1.8358823222228097e-05, "epoch": 17.107382550335572, "percentage": 58.56, "elapsed_time": "5:32:32", "remaining_time": "3:55:20", "throughput": 1681.52, "total_tokens": 33550568} {"current_steps": 651, "total_steps": 1110, "loss": 0.0195, "lr": 1.8290635580985394e-05, "epoch": 17.13422818791946, "percentage": 58.65, "elapsed_time": "5:32:58", "remaining_time": "3:54:46", "throughput": 1681.56, "total_tokens": 33595688} {"current_steps": 652, "total_steps": 1110, "loss": 0.0181, "lr": 1.822250168434816e-05, "epoch": 17.161073825503355, "percentage": 58.74, "elapsed_time": "5:33:21", "remaining_time": "3:54:10", "throughput": 1681.82, "total_tokens": 33639496} {"current_steps": 653, "total_steps": 1110, "loss": 0.0352, "lr": 1.8154422078095273e-05, "epoch": 17.187919463087248, "percentage": 58.83, "elapsed_time": "5:34:01", "remaining_time": "3:53:46", "throughput": 1681.28, "total_tokens": 33696096} {"current_steps": 654, "total_steps": 1110, "loss": 0.022, "lr": 1.8086397307570723e-05, "epoch": 17.21476510067114, "percentage": 58.92, "elapsed_time": "5:34:30", "remaining_time": "3:53:13", "throughput": 1681.14, "total_tokens": 33740816} {"current_steps": 655, "total_steps": 1110, "loss": 0.0154, "lr": 1.801842791767925e-05, "epoch": 17.241610738255034, "percentage": 59.01, "elapsed_time": "5:34:57", "remaining_time": "3:52:40", "throughput": 1681.18, "total_tokens": 33787792} {"current_steps": 656, "total_steps": 1110, "loss": 0.0179, "lr": 1.795051445288197e-05, "epoch": 17.268456375838927, "percentage": 59.1, "elapsed_time": "5:35:25", "remaining_time": "3:52:08", "throughput": 1681.26, "total_tokens": 33836440} {"current_steps": 657, "total_steps": 1110, "loss": 0.0132, "lr": 1.7882657457192013e-05, "epoch": 17.29530201342282, "percentage": 59.19, "elapsed_time": "5:35:57", "remaining_time": "3:51:38", "throughput": 1681.22, "total_tokens": 33889824} {"current_steps": 658, "total_steps": 1110, "loss": 0.0204, "lr": 1.7814857474170176e-05, "epoch": 17.322147651006713, "percentage": 59.28, "elapsed_time": "5:36:31", "remaining_time": "3:51:10", "throughput": 1681.04, "total_tokens": 33943352} {"current_steps": 659, "total_steps": 1110, "loss": 0.0183, "lr": 1.774711504692057e-05, "epoch": 17.348993288590606, "percentage": 59.37, "elapsed_time": "5:36:59", "remaining_time": "3:50:37", "throughput": 1681.23, "total_tokens": 33993824} {"current_steps": 660, "total_steps": 1110, "loss": 0.016, "lr": 1.7679430718086243e-05, "epoch": 17.375838926174495, "percentage": 59.46, "elapsed_time": "5:37:26", "remaining_time": "3:50:04", "throughput": 1681.49, "total_tokens": 34044000} {"current_steps": 661, "total_steps": 1110, "loss": 0.019, "lr": 1.7611805029844867e-05, "epoch": 17.40268456375839, "percentage": 59.55, "elapsed_time": "5:37:55", "remaining_time": "3:49:32", "throughput": 1681.4, "total_tokens": 34090728} {"current_steps": 662, "total_steps": 1110, "loss": 0.0156, "lr": 1.754423852390437e-05, "epoch": 17.42953020134228, "percentage": 59.64, "elapsed_time": "5:38:28", "remaining_time": "3:49:03", "throughput": 1681.22, "total_tokens": 34142440} {"current_steps": 663, "total_steps": 1110, "loss": 0.0175, "lr": 1.747673174149862e-05, "epoch": 17.456375838926174, "percentage": 59.73, "elapsed_time": "5:39:02", "remaining_time": "3:48:35", "throughput": 1681.37, "total_tokens": 34203200} {"current_steps": 664, "total_steps": 1110, "loss": 0.0159, "lr": 1.7409285223383064e-05, "epoch": 17.483221476510067, "percentage": 59.82, "elapsed_time": "5:39:32", "remaining_time": "3:48:03", "throughput": 1681.55, "total_tokens": 34257216} {"current_steps": 665, "total_steps": 1110, "loss": 0.0137, "lr": 1.7341899509830416e-05, "epoch": 17.51006711409396, "percentage": 59.91, "elapsed_time": "5:40:00", "remaining_time": "3:47:31", "throughput": 1681.75, "total_tokens": 34307928} {"current_steps": 666, "total_steps": 1110, "loss": 0.0193, "lr": 1.7274575140626318e-05, "epoch": 17.536912751677853, "percentage": 60.0, "elapsed_time": "5:40:30", "remaining_time": "3:47:00", "throughput": 1681.65, "total_tokens": 34357184} {"current_steps": 667, "total_steps": 1110, "loss": 0.0155, "lr": 1.720731265506502e-05, "epoch": 17.563758389261746, "percentage": 60.09, "elapsed_time": "5:41:04", "remaining_time": "3:46:31", "throughput": 1681.52, "total_tokens": 34411872} {"current_steps": 668, "total_steps": 1110, "loss": 0.016, "lr": 1.7140112591945064e-05, "epoch": 17.59060402684564, "percentage": 60.18, "elapsed_time": "5:41:42", "remaining_time": "3:46:06", "throughput": 1681.64, "total_tokens": 34478280} {"current_steps": 669, "total_steps": 1110, "loss": 0.0185, "lr": 1.7072975489564958e-05, "epoch": 17.61744966442953, "percentage": 60.27, "elapsed_time": "5:42:23", "remaining_time": "3:45:42", "throughput": 1681.38, "total_tokens": 34541712} {"current_steps": 670, "total_steps": 1110, "loss": 0.0188, "lr": 1.700590188571887e-05, "epoch": 17.644295302013422, "percentage": 60.36, "elapsed_time": "5:42:47", "remaining_time": "3:45:07", "throughput": 1681.54, "total_tokens": 34585616} {"current_steps": 671, "total_steps": 1110, "loss": 0.0217, "lr": 1.6938892317692334e-05, "epoch": 17.671140939597315, "percentage": 60.45, "elapsed_time": "5:43:24", "remaining_time": "3:44:40", "throughput": 1681.45, "total_tokens": 34645072} {"current_steps": 672, "total_steps": 1110, "loss": 0.0172, "lr": 1.6871947322257915e-05, "epoch": 17.697986577181208, "percentage": 60.54, "elapsed_time": "5:43:56", "remaining_time": "3:44:10", "throughput": 1681.37, "total_tokens": 34697320} {"current_steps": 673, "total_steps": 1110, "loss": 0.0215, "lr": 1.6805067435670938e-05, "epoch": 17.7248322147651, "percentage": 60.63, "elapsed_time": "5:44:26", "remaining_time": "3:43:39", "throughput": 1681.34, "total_tokens": 34748056} {"current_steps": 674, "total_steps": 1110, "loss": 0.0215, "lr": 1.6738253193665176e-05, "epoch": 17.751677852348994, "percentage": 60.72, "elapsed_time": "5:44:55", "remaining_time": "3:43:07", "throughput": 1681.41, "total_tokens": 34797680} {"current_steps": 675, "total_steps": 1110, "loss": 0.0163, "lr": 1.667150513144856e-05, "epoch": 17.778523489932887, "percentage": 60.81, "elapsed_time": "5:45:26", "remaining_time": "3:42:37", "throughput": 1681.4, "total_tokens": 34849552} {"current_steps": 676, "total_steps": 1110, "loss": 0.0158, "lr": 1.66048237836989e-05, "epoch": 17.80536912751678, "percentage": 60.9, "elapsed_time": "5:45:51", "remaining_time": "3:42:02", "throughput": 1681.51, "total_tokens": 34894312} {"current_steps": 677, "total_steps": 1110, "loss": 0.0154, "lr": 1.653820968455961e-05, "epoch": 17.83221476510067, "percentage": 60.99, "elapsed_time": "5:46:25", "remaining_time": "3:41:34", "throughput": 1681.51, "total_tokens": 34951208} {"current_steps": 678, "total_steps": 1110, "loss": 0.0155, "lr": 1.647166336763538e-05, "epoch": 17.859060402684563, "percentage": 61.08, "elapsed_time": "5:47:02", "remaining_time": "3:41:07", "throughput": 1681.51, "total_tokens": 35013896} {"current_steps": 679, "total_steps": 1110, "loss": 0.0165, "lr": 1.6405185365987977e-05, "epoch": 17.885906040268456, "percentage": 61.17, "elapsed_time": "5:47:35", "remaining_time": "3:40:38", "throughput": 1681.52, "total_tokens": 35069312} {"current_steps": 680, "total_steps": 1110, "loss": 0.0178, "lr": 1.633877621213192e-05, "epoch": 17.91275167785235, "percentage": 61.26, "elapsed_time": "5:48:06", "remaining_time": "3:40:07", "throughput": 1681.76, "total_tokens": 35125944} {"current_steps": 681, "total_steps": 1110, "loss": 0.0198, "lr": 1.627243643803022e-05, "epoch": 17.93959731543624, "percentage": 61.35, "elapsed_time": "5:48:34", "remaining_time": "3:39:34", "throughput": 1681.87, "total_tokens": 35174816} {"current_steps": 682, "total_steps": 1110, "loss": 0.0326, "lr": 1.6206166575090148e-05, "epoch": 17.966442953020135, "percentage": 61.44, "elapsed_time": "5:49:19", "remaining_time": "3:39:13", "throughput": 1681.28, "total_tokens": 35238088} {"current_steps": 683, "total_steps": 1110, "loss": 0.0388, "lr": 1.6139967154158954e-05, "epoch": 17.993288590604028, "percentage": 61.53, "elapsed_time": "5:49:58", "remaining_time": "3:38:47", "throughput": 1680.71, "total_tokens": 35292648} {"current_steps": 684, "total_steps": 1110, "loss": 0.0142, "lr": 1.6073838705519616e-05, "epoch": 18.0, "percentage": 61.62, "elapsed_time": "5:50:11", "remaining_time": "3:38:06", "throughput": 1680.63, "total_tokens": 35312544} {"current_steps": 685, "total_steps": 1110, "loss": 0.0116, "lr": 1.6007781758886607e-05, "epoch": 18.026845637583893, "percentage": 61.71, "elapsed_time": "5:50:39", "remaining_time": "3:37:33", "throughput": 1680.9, "total_tokens": 35365952} {"current_steps": 686, "total_steps": 1110, "loss": 0.0135, "lr": 1.594179684340162e-05, "epoch": 18.053691275167786, "percentage": 61.8, "elapsed_time": "5:51:10", "remaining_time": "3:37:03", "throughput": 1681.08, "total_tokens": 35421040} {"current_steps": 687, "total_steps": 1110, "loss": 0.0133, "lr": 1.587588448762937e-05, "epoch": 18.08053691275168, "percentage": 61.89, "elapsed_time": "5:51:37", "remaining_time": "3:36:30", "throughput": 1681.2, "total_tokens": 35469784} {"current_steps": 688, "total_steps": 1110, "loss": 0.0156, "lr": 1.5810045219553338e-05, "epoch": 18.107382550335572, "percentage": 61.98, "elapsed_time": "5:51:59", "remaining_time": "3:35:54", "throughput": 1681.51, "total_tokens": 35512936} {"current_steps": 689, "total_steps": 1110, "loss": 0.0124, "lr": 1.5744279566571533e-05, "epoch": 18.13422818791946, "percentage": 62.07, "elapsed_time": "5:52:27", "remaining_time": "3:35:21", "throughput": 1681.56, "total_tokens": 35561048} {"current_steps": 690, "total_steps": 1110, "loss": 0.0159, "lr": 1.567858805549229e-05, "epoch": 18.161073825503355, "percentage": 62.16, "elapsed_time": "5:53:01", "remaining_time": "3:34:52", "throughput": 1681.24, "total_tokens": 35610952} {"current_steps": 691, "total_steps": 1110, "loss": 0.011, "lr": 1.561297121253003e-05, "epoch": 18.187919463087248, "percentage": 62.25, "elapsed_time": "5:53:35", "remaining_time": "3:34:24", "throughput": 1681.3, "total_tokens": 35669936} {"current_steps": 692, "total_steps": 1110, "loss": 0.0127, "lr": 1.5547429563301066e-05, "epoch": 18.21476510067114, "percentage": 62.34, "elapsed_time": "5:54:10", "remaining_time": "3:33:56", "throughput": 1681.23, "total_tokens": 35726760} {"current_steps": 693, "total_steps": 1110, "loss": 0.0119, "lr": 1.548196363281937e-05, "epoch": 18.241610738255034, "percentage": 62.43, "elapsed_time": "5:54:53", "remaining_time": "3:33:32", "throughput": 1680.73, "total_tokens": 35788008} {"current_steps": 694, "total_steps": 1110, "loss": 0.0141, "lr": 1.5416573945492366e-05, "epoch": 18.268456375838927, "percentage": 62.52, "elapsed_time": "5:55:27", "remaining_time": "3:33:04", "throughput": 1680.74, "total_tokens": 35846704} {"current_steps": 695, "total_steps": 1110, "loss": 0.0116, "lr": 1.535126102511678e-05, "epoch": 18.29530201342282, "percentage": 62.61, "elapsed_time": "5:56:01", "remaining_time": "3:32:35", "throughput": 1680.73, "total_tokens": 35903256} {"current_steps": 696, "total_steps": 1110, "loss": 0.0128, "lr": 1.5286025394874364e-05, "epoch": 18.322147651006713, "percentage": 62.7, "elapsed_time": "5:56:28", "remaining_time": "3:32:02", "throughput": 1680.9, "total_tokens": 35952552} {"current_steps": 697, "total_steps": 1110, "loss": 0.0319, "lr": 1.5220867577327769e-05, "epoch": 18.348993288590606, "percentage": 62.79, "elapsed_time": "5:57:11", "remaining_time": "3:31:39", "throughput": 1680.46, "total_tokens": 36015248} {"current_steps": 698, "total_steps": 1110, "loss": 0.0144, "lr": 1.5155788094416323e-05, "epoch": 18.375838926174495, "percentage": 62.88, "elapsed_time": "5:57:34", "remaining_time": "3:31:03", "throughput": 1680.54, "total_tokens": 36055480} {"current_steps": 699, "total_steps": 1110, "loss": 0.0132, "lr": 1.5090787467451872e-05, "epoch": 18.40268456375839, "percentage": 62.97, "elapsed_time": "5:58:03", "remaining_time": "3:30:31", "throughput": 1680.71, "total_tokens": 36107072} {"current_steps": 700, "total_steps": 1110, "loss": 0.0156, "lr": 1.5025866217114592e-05, "epoch": 18.42953020134228, "percentage": 63.06, "elapsed_time": "5:58:35", "remaining_time": "3:30:01", "throughput": 1680.67, "total_tokens": 36159608} {"current_steps": 701, "total_steps": 1110, "loss": 0.0189, "lr": 1.4961024863448825e-05, "epoch": 18.456375838926174, "percentage": 63.15, "elapsed_time": "5:59:05", "remaining_time": "3:29:30", "throughput": 1681.02, "total_tokens": 36218672} {"current_steps": 702, "total_steps": 1110, "loss": 0.0134, "lr": 1.4896263925858903e-05, "epoch": 18.483221476510067, "percentage": 63.24, "elapsed_time": "5:59:42", "remaining_time": "3:29:03", "throughput": 1680.76, "total_tokens": 36274504} {"current_steps": 703, "total_steps": 1110, "loss": 0.0178, "lr": 1.4831583923104999e-05, "epoch": 18.51006711409396, "percentage": 63.33, "elapsed_time": "6:00:07", "remaining_time": "3:28:29", "throughput": 1680.93, "total_tokens": 36320136} {"current_steps": 704, "total_steps": 1110, "loss": 0.0133, "lr": 1.4766985373298967e-05, "epoch": 18.536912751677853, "percentage": 63.42, "elapsed_time": "6:00:36", "remaining_time": "3:27:58", "throughput": 1681.01, "total_tokens": 36371712} {"current_steps": 705, "total_steps": 1110, "loss": 0.0118, "lr": 1.4702468793900188e-05, "epoch": 18.563758389261746, "percentage": 63.51, "elapsed_time": "6:01:12", "remaining_time": "3:27:30", "throughput": 1681.09, "total_tokens": 36432984} {"current_steps": 706, "total_steps": 1110, "loss": 0.0131, "lr": 1.4638034701711422e-05, "epoch": 18.59060402684564, "percentage": 63.6, "elapsed_time": "6:01:37", "remaining_time": "3:26:56", "throughput": 1681.32, "total_tokens": 36480192} {"current_steps": 707, "total_steps": 1110, "loss": 0.0122, "lr": 1.4573683612874712e-05, "epoch": 18.61744966442953, "percentage": 63.69, "elapsed_time": "6:02:15", "remaining_time": "3:26:29", "throughput": 1681.04, "total_tokens": 36538712} {"current_steps": 708, "total_steps": 1110, "loss": 0.0124, "lr": 1.4509416042867149e-05, "epoch": 18.644295302013422, "percentage": 63.78, "elapsed_time": "6:02:48", "remaining_time": "3:26:00", "throughput": 1680.97, "total_tokens": 36592536} {"current_steps": 709, "total_steps": 1110, "loss": 0.015, "lr": 1.4445232506496864e-05, "epoch": 18.671140939597315, "percentage": 63.87, "elapsed_time": "6:03:18", "remaining_time": "3:25:28", "throughput": 1681.09, "total_tokens": 36645016} {"current_steps": 710, "total_steps": 1110, "loss": 0.0105, "lr": 1.4381133517898804e-05, "epoch": 18.697986577181208, "percentage": 63.96, "elapsed_time": "6:03:50", "remaining_time": "3:24:58", "throughput": 1681.33, "total_tokens": 36704712} {"current_steps": 711, "total_steps": 1110, "loss": 0.0193, "lr": 1.4317119590530692e-05, "epoch": 18.7248322147651, "percentage": 64.05, "elapsed_time": "6:04:11", "remaining_time": "3:24:22", "throughput": 1681.52, "total_tokens": 36743832} {"current_steps": 712, "total_steps": 1110, "loss": 0.0185, "lr": 1.4253191237168839e-05, "epoch": 18.751677852348994, "percentage": 64.14, "elapsed_time": "6:04:42", "remaining_time": "3:23:52", "throughput": 1681.48, "total_tokens": 36795776} {"current_steps": 713, "total_steps": 1110, "loss": 0.0152, "lr": 1.4189348969904115e-05, "epoch": 18.778523489932887, "percentage": 64.23, "elapsed_time": "6:05:06", "remaining_time": "3:23:17", "throughput": 1681.58, "total_tokens": 36836672} {"current_steps": 714, "total_steps": 1110, "loss": 0.0133, "lr": 1.4125593300137766e-05, "epoch": 18.80536912751678, "percentage": 64.32, "elapsed_time": "6:05:37", "remaining_time": "3:22:47", "throughput": 1681.66, "total_tokens": 36891688} {"current_steps": 715, "total_steps": 1110, "loss": 0.0293, "lr": 1.4061924738577403e-05, "epoch": 18.83221476510067, "percentage": 64.41, "elapsed_time": "6:06:15", "remaining_time": "3:22:20", "throughput": 1681.5, "total_tokens": 36951712} {"current_steps": 716, "total_steps": 1110, "loss": 0.0336, "lr": 1.3998343795232819e-05, "epoch": 18.859060402684563, "percentage": 64.5, "elapsed_time": "6:06:55", "remaining_time": "3:21:54", "throughput": 1681.23, "total_tokens": 37012536} {"current_steps": 717, "total_steps": 1110, "loss": 0.0147, "lr": 1.393485097941199e-05, "epoch": 18.885906040268456, "percentage": 64.59, "elapsed_time": "6:07:24", "remaining_time": "3:21:22", "throughput": 1681.4, "total_tokens": 37065648} {"current_steps": 718, "total_steps": 1110, "loss": 0.0159, "lr": 1.3871446799716936e-05, "epoch": 18.91275167785235, "percentage": 64.68, "elapsed_time": "6:07:52", "remaining_time": "3:20:50", "throughput": 1681.35, "total_tokens": 37110792} {"current_steps": 719, "total_steps": 1110, "loss": 0.0153, "lr": 1.3808131764039689e-05, "epoch": 18.93959731543624, "percentage": 64.77, "elapsed_time": "6:08:24", "remaining_time": "3:20:20", "throughput": 1681.24, "total_tokens": 37163224} {"current_steps": 720, "total_steps": 1110, "loss": 0.0152, "lr": 1.3744906379558165e-05, "epoch": 18.966442953020135, "percentage": 64.86, "elapsed_time": "6:08:59", "remaining_time": "3:19:52", "throughput": 1681.08, "total_tokens": 37218576} {"current_steps": 721, "total_steps": 1110, "loss": 0.0156, "lr": 1.3681771152732184e-05, "epoch": 18.993288590604028, "percentage": 64.95, "elapsed_time": "6:09:26", "remaining_time": "3:19:19", "throughput": 1681.21, "total_tokens": 37267032} {"current_steps": 722, "total_steps": 1110, "loss": 0.0259, "lr": 1.3618726589299322e-05, "epoch": 19.0, "percentage": 65.05, "elapsed_time": "6:09:30", "remaining_time": "3:18:34", "throughput": 1681.26, "total_tokens": 37274352} {"current_steps": 723, "total_steps": 1110, "loss": 0.013, "lr": 1.3555773194270948e-05, "epoch": 19.026845637583893, "percentage": 65.14, "elapsed_time": "6:09:48", "remaining_time": "3:17:56", "throughput": 1681.42, "total_tokens": 37308704} {"current_steps": 724, "total_steps": 1110, "loss": 0.0115, "lr": 1.3492911471928104e-05, "epoch": 19.053691275167786, "percentage": 65.23, "elapsed_time": "6:10:20", "remaining_time": "3:17:27", "throughput": 1681.41, "total_tokens": 37362312} {"current_steps": 725, "total_steps": 1110, "loss": 0.0556, "lr": 1.3430141925817532e-05, "epoch": 19.08053691275168, "percentage": 65.32, "elapsed_time": "6:11:12", "remaining_time": "3:17:07", "throughput": 1680.64, "total_tokens": 37431528} {"current_steps": 726, "total_steps": 1110, "loss": 0.0117, "lr": 1.3367465058747567e-05, "epoch": 19.107382550335572, "percentage": 65.41, "elapsed_time": "6:11:47", "remaining_time": "3:16:38", "throughput": 1680.48, "total_tokens": 37486688} {"current_steps": 727, "total_steps": 1110, "loss": 0.0126, "lr": 1.3304881372784179e-05, "epoch": 19.13422818791946, "percentage": 65.5, "elapsed_time": "6:12:14", "remaining_time": "3:16:06", "throughput": 1680.67, "total_tokens": 37536744} {"current_steps": 728, "total_steps": 1110, "loss": 0.0113, "lr": 1.3242391369246921e-05, "epoch": 19.161073825503355, "percentage": 65.59, "elapsed_time": "6:12:40", "remaining_time": "3:15:32", "throughput": 1680.9, "total_tokens": 37584984} {"current_steps": 729, "total_steps": 1110, "loss": 0.0095, "lr": 1.3179995548704883e-05, "epoch": 19.187919463087248, "percentage": 65.68, "elapsed_time": "6:13:17", "remaining_time": "3:15:05", "throughput": 1680.93, "total_tokens": 37648576} {"current_steps": 730, "total_steps": 1110, "loss": 0.0098, "lr": 1.3117694410972748e-05, "epoch": 19.21476510067114, "percentage": 65.77, "elapsed_time": "6:13:54", "remaining_time": "3:14:38", "throughput": 1681.01, "total_tokens": 37712680} {"current_steps": 731, "total_steps": 1110, "loss": 0.0139, "lr": 1.3055488455106748e-05, "epoch": 19.241610738255034, "percentage": 65.86, "elapsed_time": "6:14:32", "remaining_time": "3:14:11", "throughput": 1680.6, "total_tokens": 37766624} {"current_steps": 732, "total_steps": 1110, "loss": 0.013, "lr": 1.2993378179400645e-05, "epoch": 19.268456375838927, "percentage": 65.95, "elapsed_time": "6:14:56", "remaining_time": "3:13:36", "throughput": 1680.91, "total_tokens": 37813976} {"current_steps": 733, "total_steps": 1110, "loss": 0.0111, "lr": 1.2931364081381797e-05, "epoch": 19.29530201342282, "percentage": 66.04, "elapsed_time": "6:15:22", "remaining_time": "3:13:03", "throughput": 1680.96, "total_tokens": 37859040} {"current_steps": 734, "total_steps": 1110, "loss": 0.0124, "lr": 1.2869446657807117e-05, "epoch": 19.322147651006713, "percentage": 66.13, "elapsed_time": "6:15:59", "remaining_time": "3:12:36", "throughput": 1680.93, "total_tokens": 37921040} {"current_steps": 735, "total_steps": 1110, "loss": 0.017, "lr": 1.2807626404659142e-05, "epoch": 19.348993288590606, "percentage": 66.22, "elapsed_time": "6:16:26", "remaining_time": "3:12:03", "throughput": 1680.85, "total_tokens": 37964688} {"current_steps": 736, "total_steps": 1110, "loss": 0.0311, "lr": 1.2745903817142008e-05, "epoch": 19.375838926174495, "percentage": 66.31, "elapsed_time": "6:17:18", "remaining_time": "3:11:43", "throughput": 1680.11, "total_tokens": 38034632} {"current_steps": 737, "total_steps": 1110, "loss": 0.0107, "lr": 1.2684279389677534e-05, "epoch": 19.40268456375839, "percentage": 66.4, "elapsed_time": "6:17:50", "remaining_time": "3:11:13", "throughput": 1679.93, "total_tokens": 38084000} {"current_steps": 738, "total_steps": 1110, "loss": 0.0186, "lr": 1.2622753615901244e-05, "epoch": 19.42953020134228, "percentage": 66.49, "elapsed_time": "6:18:15", "remaining_time": "3:10:40", "throughput": 1680.11, "total_tokens": 38131152} {"current_steps": 739, "total_steps": 1110, "loss": 0.0171, "lr": 1.2561326988658378e-05, "epoch": 19.456375838926174, "percentage": 66.58, "elapsed_time": "6:18:35", "remaining_time": "3:10:04", "throughput": 1680.36, "total_tokens": 38171048} {"current_steps": 740, "total_steps": 1110, "loss": 0.0109, "lr": 1.2500000000000006e-05, "epoch": 19.483221476510067, "percentage": 66.67, "elapsed_time": "6:19:06", "remaining_time": "3:09:33", "throughput": 1680.48, "total_tokens": 38224384} {"current_steps": 741, "total_steps": 1110, "loss": 0.0095, "lr": 1.2438773141179025e-05, "epoch": 19.51006711409396, "percentage": 66.76, "elapsed_time": "6:19:39", "remaining_time": "3:09:03", "throughput": 1680.5, "total_tokens": 38281144} {"current_steps": 742, "total_steps": 1110, "loss": 0.0168, "lr": 1.2377646902646287e-05, "epoch": 19.536912751677853, "percentage": 66.85, "elapsed_time": "6:20:13", "remaining_time": "3:08:34", "throughput": 1680.6, "total_tokens": 38339760} {"current_steps": 743, "total_steps": 1110, "loss": 0.0108, "lr": 1.2316621774046597e-05, "epoch": 19.563758389261746, "percentage": 66.94, "elapsed_time": "6:20:38", "remaining_time": "3:08:01", "throughput": 1680.69, "total_tokens": 38385312} {"current_steps": 744, "total_steps": 1110, "loss": 0.0124, "lr": 1.2255698244214864e-05, "epoch": 19.59060402684564, "percentage": 67.03, "elapsed_time": "6:21:13", "remaining_time": "3:07:32", "throughput": 1680.7, "total_tokens": 38442800} {"current_steps": 745, "total_steps": 1110, "loss": 0.0128, "lr": 1.2194876801172148e-05, "epoch": 19.61744966442953, "percentage": 67.12, "elapsed_time": "6:21:37", "remaining_time": "3:06:58", "throughput": 1680.85, "total_tokens": 38486712} {"current_steps": 746, "total_steps": 1110, "loss": 0.0093, "lr": 1.2134157932121724e-05, "epoch": 19.644295302013422, "percentage": 67.21, "elapsed_time": "6:22:06", "remaining_time": "3:06:26", "throughput": 1680.99, "total_tokens": 38539040} {"current_steps": 747, "total_steps": 1110, "loss": 0.0109, "lr": 1.2073542123445239e-05, "epoch": 19.671140939597315, "percentage": 67.3, "elapsed_time": "6:22:36", "remaining_time": "3:05:55", "throughput": 1681.19, "total_tokens": 38594128} {"current_steps": 748, "total_steps": 1110, "loss": 0.0152, "lr": 1.2013029860698793e-05, "epoch": 19.697986577181208, "percentage": 67.39, "elapsed_time": "6:23:03", "remaining_time": "3:05:22", "throughput": 1681.24, "total_tokens": 38639944} {"current_steps": 749, "total_steps": 1110, "loss": 0.0097, "lr": 1.1952621628609004e-05, "epoch": 19.7248322147651, "percentage": 67.48, "elapsed_time": "6:23:31", "remaining_time": "3:04:50", "throughput": 1681.27, "total_tokens": 38688368} {"current_steps": 750, "total_steps": 1110, "loss": 0.0122, "lr": 1.1892317911069212e-05, "epoch": 19.751677852348994, "percentage": 67.57, "elapsed_time": "6:24:00", "remaining_time": "3:04:19", "throughput": 1681.26, "total_tokens": 38737552} {"current_steps": 751, "total_steps": 1110, "loss": 0.0106, "lr": 1.183211919113551e-05, "epoch": 19.778523489932887, "percentage": 67.66, "elapsed_time": "6:24:29", "remaining_time": "3:03:47", "throughput": 1681.37, "total_tokens": 38788216} {"current_steps": 752, "total_steps": 1110, "loss": 0.0117, "lr": 1.177202595102296e-05, "epoch": 19.80536912751678, "percentage": 67.75, "elapsed_time": "6:25:01", "remaining_time": "3:03:17", "throughput": 1681.47, "total_tokens": 38844408} {"current_steps": 753, "total_steps": 1110, "loss": 0.0101, "lr": 1.1712038672101654e-05, "epoch": 19.83221476510067, "percentage": 67.84, "elapsed_time": "6:25:36", "remaining_time": "3:02:49", "throughput": 1681.65, "total_tokens": 38908040} {"current_steps": 754, "total_steps": 1110, "loss": 0.0125, "lr": 1.1652157834892926e-05, "epoch": 19.859060402684563, "percentage": 67.93, "elapsed_time": "6:26:11", "remaining_time": "3:02:20", "throughput": 1681.45, "total_tokens": 38961992} {"current_steps": 755, "total_steps": 1110, "loss": 0.0132, "lr": 1.1592383919065442e-05, "epoch": 19.885906040268456, "percentage": 68.02, "elapsed_time": "6:26:37", "remaining_time": "3:01:47", "throughput": 1681.68, "total_tokens": 39011472} {"current_steps": 756, "total_steps": 1110, "loss": 0.0105, "lr": 1.1532717403431403e-05, "epoch": 19.91275167785235, "percentage": 68.11, "elapsed_time": "6:27:12", "remaining_time": "3:01:18", "throughput": 1681.55, "total_tokens": 39066216} {"current_steps": 757, "total_steps": 1110, "loss": 0.0108, "lr": 1.1473158765942704e-05, "epoch": 19.93959731543624, "percentage": 68.2, "elapsed_time": "6:27:40", "remaining_time": "3:00:46", "throughput": 1681.72, "total_tokens": 39117960} {"current_steps": 758, "total_steps": 1110, "loss": 0.0122, "lr": 1.1413708483687057e-05, "epoch": 19.966442953020135, "percentage": 68.29, "elapsed_time": "6:28:08", "remaining_time": "3:00:14", "throughput": 1681.72, "total_tokens": 39164024} {"current_steps": 759, "total_steps": 1110, "loss": 0.0113, "lr": 1.1354367032884244e-05, "epoch": 19.993288590604028, "percentage": 68.38, "elapsed_time": "6:28:41", "remaining_time": "2:59:45", "throughput": 1681.72, "total_tokens": 39220664} {"current_steps": 760, "total_steps": 1110, "loss": 0.0097, "lr": 1.1295134888882258e-05, "epoch": 20.0, "percentage": 68.47, "elapsed_time": "6:28:51", "remaining_time": "2:59:04", "throughput": 1681.7, "total_tokens": 39236160} {"current_steps": 761, "total_steps": 1110, "loss": 0.01, "lr": 1.1236012526153475e-05, "epoch": 20.026845637583893, "percentage": 68.56, "elapsed_time": "6:29:18", "remaining_time": "2:58:32", "throughput": 1681.82, "total_tokens": 39285160} {"current_steps": 762, "total_steps": 1110, "loss": 0.032, "lr": 1.1177000418290917e-05, "epoch": 20.053691275167786, "percentage": 68.65, "elapsed_time": "6:30:02", "remaining_time": "2:58:07", "throughput": 1681.3, "total_tokens": 39346408} {"current_steps": 763, "total_steps": 1110, "loss": 0.0089, "lr": 1.111809903800439e-05, "epoch": 20.08053691275168, "percentage": 68.74, "elapsed_time": "6:30:30", "remaining_time": "2:57:35", "throughput": 1681.35, "total_tokens": 39394880} {"current_steps": 764, "total_steps": 1110, "loss": 0.0097, "lr": 1.1059308857116762e-05, "epoch": 20.107382550335572, "percentage": 68.83, "elapsed_time": "6:31:13", "remaining_time": "2:57:10", "throughput": 1681.19, "total_tokens": 39462992} {"current_steps": 765, "total_steps": 1110, "loss": 0.0132, "lr": 1.1000630346560117e-05, "epoch": 20.13422818791946, "percentage": 68.92, "elapsed_time": "6:31:40", "remaining_time": "2:56:38", "throughput": 1681.2, "total_tokens": 39509336} {"current_steps": 766, "total_steps": 1110, "loss": 0.0116, "lr": 1.0942063976372046e-05, "epoch": 20.161073825503355, "percentage": 69.01, "elapsed_time": "6:32:01", "remaining_time": "2:56:03", "throughput": 1681.31, "total_tokens": 39546352} {"current_steps": 767, "total_steps": 1110, "loss": 0.0094, "lr": 1.0883610215691825e-05, "epoch": 20.187919463087248, "percentage": 69.1, "elapsed_time": "6:32:33", "remaining_time": "2:55:33", "throughput": 1681.17, "total_tokens": 39598320} {"current_steps": 768, "total_steps": 1110, "loss": 0.0103, "lr": 1.0825269532756707e-05, "epoch": 20.21476510067114, "percentage": 69.19, "elapsed_time": "6:33:08", "remaining_time": "2:55:04", "throughput": 1681.16, "total_tokens": 39656824} {"current_steps": 769, "total_steps": 1110, "loss": 0.0092, "lr": 1.076704239489814e-05, "epoch": 20.241610738255034, "percentage": 69.28, "elapsed_time": "6:33:49", "remaining_time": "2:54:38", "throughput": 1680.79, "total_tokens": 39715824} {"current_steps": 770, "total_steps": 1110, "loss": 0.0111, "lr": 1.0708929268538034e-05, "epoch": 20.268456375838927, "percentage": 69.37, "elapsed_time": "6:34:14", "remaining_time": "2:54:04", "throughput": 1680.88, "total_tokens": 39760968} {"current_steps": 771, "total_steps": 1110, "loss": 0.0115, "lr": 1.065093061918501e-05, "epoch": 20.29530201342282, "percentage": 69.46, "elapsed_time": "6:34:40", "remaining_time": "2:53:32", "throughput": 1680.95, "total_tokens": 39805816} {"current_steps": 772, "total_steps": 1110, "loss": 0.0116, "lr": 1.059304691143071e-05, "epoch": 20.322147651006713, "percentage": 69.55, "elapsed_time": "6:35:12", "remaining_time": "2:53:01", "throughput": 1680.81, "total_tokens": 39856568} {"current_steps": 773, "total_steps": 1110, "loss": 0.0141, "lr": 1.0535278608946015e-05, "epoch": 20.348993288590606, "percentage": 69.64, "elapsed_time": "6:35:38", "remaining_time": "2:52:28", "throughput": 1680.85, "total_tokens": 39900272} {"current_steps": 774, "total_steps": 1110, "loss": 0.0106, "lr": 1.0477626174477404e-05, "epoch": 20.375838926174495, "percentage": 69.73, "elapsed_time": "6:36:10", "remaining_time": "2:51:58", "throughput": 1681.02, "total_tokens": 39958704} {"current_steps": 775, "total_steps": 1110, "loss": 0.0104, "lr": 1.0420090069843167e-05, "epoch": 20.40268456375839, "percentage": 69.82, "elapsed_time": "6:36:37", "remaining_time": "2:51:26", "throughput": 1681.11, "total_tokens": 40006016} {"current_steps": 776, "total_steps": 1110, "loss": 0.0084, "lr": 1.0362670755929788e-05, "epoch": 20.42953020134228, "percentage": 69.91, "elapsed_time": "6:37:12", "remaining_time": "2:50:57", "throughput": 1680.93, "total_tokens": 40060840} {"current_steps": 777, "total_steps": 1110, "loss": 0.0104, "lr": 1.0305368692688174e-05, "epoch": 20.456375838926174, "percentage": 70.0, "elapsed_time": "6:37:47", "remaining_time": "2:50:28", "throughput": 1680.84, "total_tokens": 40117280} {"current_steps": 778, "total_steps": 1110, "loss": 0.0108, "lr": 1.0248184339130046e-05, "epoch": 20.483221476510067, "percentage": 70.09, "elapsed_time": "6:38:17", "remaining_time": "2:49:57", "throughput": 1680.7, "total_tokens": 40164480} {"current_steps": 779, "total_steps": 1110, "loss": 0.0111, "lr": 1.0191118153324175e-05, "epoch": 20.51006711409396, "percentage": 70.18, "elapsed_time": "6:38:49", "remaining_time": "2:49:27", "throughput": 1680.79, "total_tokens": 40221176} {"current_steps": 780, "total_steps": 1110, "loss": 0.0134, "lr": 1.0134170592392836e-05, "epoch": 20.536912751677853, "percentage": 70.27, "elapsed_time": "6:39:16", "remaining_time": "2:48:55", "throughput": 1680.82, "total_tokens": 40265776} {"current_steps": 781, "total_steps": 1110, "loss": 0.009, "lr": 1.0077342112507996e-05, "epoch": 20.563758389261746, "percentage": 70.36, "elapsed_time": "6:39:41", "remaining_time": "2:48:22", "throughput": 1680.96, "total_tokens": 40311456} {"current_steps": 782, "total_steps": 1110, "loss": 0.0084, "lr": 1.0020633168887794e-05, "epoch": 20.59060402684564, "percentage": 70.45, "elapsed_time": "6:40:11", "remaining_time": "2:47:51", "throughput": 1681.05, "total_tokens": 40363768} {"current_steps": 783, "total_steps": 1110, "loss": 0.0067, "lr": 9.964044215792796e-06, "epoch": 20.61744966442953, "percentage": 70.54, "elapsed_time": "6:40:45", "remaining_time": "2:47:22", "throughput": 1681.08, "total_tokens": 40422616} {"current_steps": 784, "total_steps": 1110, "loss": 0.0102, "lr": 9.907575706522433e-06, "epoch": 20.644295302013422, "percentage": 70.63, "elapsed_time": "6:41:12", "remaining_time": "2:46:49", "throughput": 1681.14, "total_tokens": 40468920} {"current_steps": 785, "total_steps": 1110, "loss": 0.0114, "lr": 9.851228093411296e-06, "epoch": 20.671140939597315, "percentage": 70.72, "elapsed_time": "6:41:40", "remaining_time": "2:46:18", "throughput": 1681.44, "total_tokens": 40524008} {"current_steps": 786, "total_steps": 1110, "loss": 0.0097, "lr": 9.795001827825596e-06, "epoch": 20.697986577181208, "percentage": 70.81, "elapsed_time": "6:42:11", "remaining_time": "2:45:47", "throughput": 1681.4, "total_tokens": 40575144} {"current_steps": 787, "total_steps": 1110, "loss": 0.0084, "lr": 9.738897360159455e-06, "epoch": 20.7248322147651, "percentage": 70.9, "elapsed_time": "6:42:40", "remaining_time": "2:45:16", "throughput": 1681.42, "total_tokens": 40624544} {"current_steps": 788, "total_steps": 1110, "loss": 0.0112, "lr": 9.682915139831395e-06, "epoch": 20.751677852348994, "percentage": 70.99, "elapsed_time": "6:43:10", "remaining_time": "2:44:44", "throughput": 1681.44, "total_tokens": 40674080} {"current_steps": 789, "total_steps": 1110, "loss": 0.0316, "lr": 9.627055615280642e-06, "epoch": 20.778523489932887, "percentage": 71.08, "elapsed_time": "6:43:51", "remaining_time": "2:44:18", "throughput": 1681.1, "total_tokens": 40735672} {"current_steps": 790, "total_steps": 1110, "loss": 0.0298, "lr": 9.571319233963627e-06, "epoch": 20.80536912751678, "percentage": 71.17, "elapsed_time": "6:44:35", "remaining_time": "2:43:53", "throughput": 1680.63, "total_tokens": 40797632} {"current_steps": 791, "total_steps": 1110, "loss": 0.0096, "lr": 9.515706442350306e-06, "epoch": 20.83221476510067, "percentage": 71.26, "elapsed_time": "6:45:05", "remaining_time": "2:43:22", "throughput": 1680.79, "total_tokens": 40852408} {"current_steps": 792, "total_steps": 1110, "loss": 0.0084, "lr": 9.460217685920697e-06, "epoch": 20.859060402684563, "percentage": 71.35, "elapsed_time": "6:45:33", "remaining_time": "2:42:50", "throughput": 1680.94, "total_tokens": 40902944} {"current_steps": 793, "total_steps": 1110, "loss": 0.0098, "lr": 9.404853409161188e-06, "epoch": 20.885906040268456, "percentage": 71.44, "elapsed_time": "6:46:04", "remaining_time": "2:42:19", "throughput": 1681.03, "total_tokens": 40958040} {"current_steps": 794, "total_steps": 1110, "loss": 0.0122, "lr": 9.349614055561073e-06, "epoch": 20.91275167785235, "percentage": 71.53, "elapsed_time": "6:46:32", "remaining_time": "2:41:47", "throughput": 1681.09, "total_tokens": 41006048} {"current_steps": 795, "total_steps": 1110, "loss": 0.0082, "lr": 9.29450006760894e-06, "epoch": 20.93959731543624, "percentage": 71.62, "elapsed_time": "6:47:06", "remaining_time": "2:41:18", "throughput": 1681.31, "total_tokens": 41068224} {"current_steps": 796, "total_steps": 1110, "loss": 0.0086, "lr": 9.239511886789176e-06, "epoch": 20.966442953020135, "percentage": 71.71, "elapsed_time": "6:47:40", "remaining_time": "2:40:49", "throughput": 1681.4, "total_tokens": 41128144} {"current_steps": 797, "total_steps": 1110, "loss": 0.0083, "lr": 9.184649953578373e-06, "epoch": 20.993288590604028, "percentage": 71.8, "elapsed_time": "6:48:09", "remaining_time": "2:40:17", "throughput": 1681.51, "total_tokens": 41180168} {"current_steps": 798, "total_steps": 1110, "loss": 0.0079, "lr": 9.129914707441864e-06, "epoch": 21.0, "percentage": 71.89, "elapsed_time": "6:48:21", "remaining_time": "2:39:39", "throughput": 1681.43, "total_tokens": 41197968} {"current_steps": 799, "total_steps": 1110, "loss": 0.0116, "lr": 9.075306586830134e-06, "epoch": 21.026845637583893, "percentage": 71.98, "elapsed_time": "6:48:46", "remaining_time": "2:39:06", "throughput": 1681.57, "total_tokens": 41242720} {"current_steps": 800, "total_steps": 1110, "loss": 0.0103, "lr": 9.020826029175384e-06, "epoch": 21.053691275167786, "percentage": 72.07, "elapsed_time": "6:49:12", "remaining_time": "2:38:34", "throughput": 1681.54, "total_tokens": 41286072} {"current_steps": 801, "total_steps": 1110, "loss": 0.0282, "lr": 8.96647347088794e-06, "epoch": 21.08053691275168, "percentage": 72.16, "elapsed_time": "6:50:01", "remaining_time": "2:38:10", "throughput": 1681.06, "total_tokens": 41356288} {"current_steps": 802, "total_steps": 1110, "loss": 0.0072, "lr": 8.91224934735285e-06, "epoch": 21.107382550335572, "percentage": 72.25, "elapsed_time": "6:50:37", "remaining_time": "2:37:41", "throughput": 1681.1, "total_tokens": 41417496} {"current_steps": 803, "total_steps": 1110, "loss": 0.0307, "lr": 8.858154092926303e-06, "epoch": 21.13422818791946, "percentage": 72.34, "elapsed_time": "6:51:25", "remaining_time": "2:37:17", "throughput": 1680.49, "total_tokens": 41483136} {"current_steps": 804, "total_steps": 1110, "loss": 0.0083, "lr": 8.80418814093225e-06, "epoch": 21.161073825503355, "percentage": 72.43, "elapsed_time": "6:52:04", "remaining_time": "2:36:50", "throughput": 1680.5, "total_tokens": 41549160} {"current_steps": 805, "total_steps": 1110, "loss": 0.0101, "lr": 8.750351923658832e-06, "epoch": 21.187919463087248, "percentage": 72.52, "elapsed_time": "6:52:24", "remaining_time": "2:36:15", "throughput": 1680.53, "total_tokens": 41583920} {"current_steps": 806, "total_steps": 1110, "loss": 0.0126, "lr": 8.696645872354994e-06, "epoch": 21.21476510067114, "percentage": 72.61, "elapsed_time": "6:53:00", "remaining_time": "2:35:46", "throughput": 1680.38, "total_tokens": 41641400} {"current_steps": 807, "total_steps": 1110, "loss": 0.0114, "lr": 8.643070417226978e-06, "epoch": 21.241610738255034, "percentage": 72.7, "elapsed_time": "6:53:23", "remaining_time": "2:35:12", "throughput": 1680.6, "total_tokens": 41684400} {"current_steps": 808, "total_steps": 1110, "loss": 0.0112, "lr": 8.58962598743493e-06, "epoch": 21.268456375838927, "percentage": 72.79, "elapsed_time": "6:53:49", "remaining_time": "2:34:40", "throughput": 1680.79, "total_tokens": 41733920} {"current_steps": 809, "total_steps": 1110, "loss": 0.0094, "lr": 8.536313011089398e-06, "epoch": 21.29530201342282, "percentage": 72.88, "elapsed_time": "6:54:10", "remaining_time": "2:34:06", "throughput": 1681.02, "total_tokens": 41774664} {"current_steps": 810, "total_steps": 1110, "loss": 0.0072, "lr": 8.483131915247968e-06, "epoch": 21.322147651006713, "percentage": 72.97, "elapsed_time": "6:54:38", "remaining_time": "2:33:34", "throughput": 1681.28, "total_tokens": 41828520} {"current_steps": 811, "total_steps": 1110, "loss": 0.0083, "lr": 8.430083125911786e-06, "epoch": 21.348993288590606, "percentage": 73.06, "elapsed_time": "6:55:01", "remaining_time": "2:33:00", "throughput": 1681.45, "total_tokens": 41871280} {"current_steps": 812, "total_steps": 1110, "loss": 0.0081, "lr": 8.377167068022199e-06, "epoch": 21.375838926174495, "percentage": 73.15, "elapsed_time": "6:55:31", "remaining_time": "2:32:29", "throughput": 1681.47, "total_tokens": 41922128} {"current_steps": 813, "total_steps": 1110, "loss": 0.0064, "lr": 8.324384165457289e-06, "epoch": 21.40268456375839, "percentage": 73.24, "elapsed_time": "6:56:04", "remaining_time": "2:31:59", "throughput": 1681.36, "total_tokens": 41973792} {"current_steps": 814, "total_steps": 1110, "loss": 0.0081, "lr": 8.271734841028553e-06, "epoch": 21.42953020134228, "percentage": 73.33, "elapsed_time": "6:56:28", "remaining_time": "2:31:26", "throughput": 1681.48, "total_tokens": 42018336} {"current_steps": 815, "total_steps": 1110, "loss": 0.0102, "lr": 8.219219516477428e-06, "epoch": 21.456375838926174, "percentage": 73.42, "elapsed_time": "6:57:01", "remaining_time": "2:30:56", "throughput": 1681.39, "total_tokens": 42071504} {"current_steps": 816, "total_steps": 1110, "loss": 0.0093, "lr": 8.16683861247202e-06, "epoch": 21.483221476510067, "percentage": 73.51, "elapsed_time": "6:57:34", "remaining_time": "2:30:27", "throughput": 1681.35, "total_tokens": 42126016} {"current_steps": 817, "total_steps": 1110, "loss": 0.008, "lr": 8.114592548603614e-06, "epoch": 21.51006711409396, "percentage": 73.6, "elapsed_time": "6:58:03", "remaining_time": "2:29:55", "throughput": 1681.55, "total_tokens": 42178264} {"current_steps": 818, "total_steps": 1110, "loss": 0.01, "lr": 8.06248174338342e-06, "epoch": 21.536912751677853, "percentage": 73.69, "elapsed_time": "6:58:28", "remaining_time": "2:29:22", "throughput": 1681.73, "total_tokens": 42225848} {"current_steps": 819, "total_steps": 1110, "loss": 0.0086, "lr": 8.010506614239139e-06, "epoch": 21.563758389261746, "percentage": 73.78, "elapsed_time": "6:58:59", "remaining_time": "2:28:52", "throughput": 1681.68, "total_tokens": 42276880} {"current_steps": 820, "total_steps": 1110, "loss": 0.009, "lr": 7.958667577511683e-06, "epoch": 21.59060402684564, "percentage": 73.87, "elapsed_time": "6:59:31", "remaining_time": "2:28:21", "throughput": 1681.6, "total_tokens": 42327800} {"current_steps": 821, "total_steps": 1110, "loss": 0.012, "lr": 7.90696504845178e-06, "epoch": 21.61744966442953, "percentage": 73.96, "elapsed_time": "6:59:54", "remaining_time": "2:27:48", "throughput": 1681.79, "total_tokens": 42372136} {"current_steps": 822, "total_steps": 1110, "loss": 0.0082, "lr": 7.855399441216716e-06, "epoch": 21.644295302013422, "percentage": 74.05, "elapsed_time": "7:00:23", "remaining_time": "2:27:17", "throughput": 1681.78, "total_tokens": 42421224} {"current_steps": 823, "total_steps": 1110, "loss": 0.0093, "lr": 7.803971168866942e-06, "epoch": 21.671140939597315, "percentage": 74.14, "elapsed_time": "7:00:57", "remaining_time": "2:26:47", "throughput": 1681.73, "total_tokens": 42475544} {"current_steps": 824, "total_steps": 1110, "loss": 0.0096, "lr": 7.75268064336284e-06, "epoch": 21.697986577181208, "percentage": 74.23, "elapsed_time": "7:01:26", "remaining_time": "2:26:16", "throughput": 1681.89, "total_tokens": 42528352} {"current_steps": 825, "total_steps": 1110, "loss": 0.0101, "lr": 7.701528275561348e-06, "epoch": 21.7248322147651, "percentage": 74.32, "elapsed_time": "7:01:52", "remaining_time": "2:25:44", "throughput": 1682.14, "total_tokens": 42578296} {"current_steps": 826, "total_steps": 1110, "loss": 0.0266, "lr": 7.650514475212747e-06, "epoch": 21.751677852348994, "percentage": 74.41, "elapsed_time": "7:02:41", "remaining_time": "2:25:20", "throughput": 1681.5, "total_tokens": 42646096} {"current_steps": 827, "total_steps": 1110, "loss": 0.0088, "lr": 7.599639650957297e-06, "epoch": 21.778523489932887, "percentage": 74.5, "elapsed_time": "7:03:20", "remaining_time": "2:24:51", "throughput": 1681.27, "total_tokens": 42704512} {"current_steps": 828, "total_steps": 1110, "loss": 0.0084, "lr": 7.548904210322058e-06, "epoch": 21.80536912751678, "percentage": 74.59, "elapsed_time": "7:03:49", "remaining_time": "2:24:20", "throughput": 1681.26, "total_tokens": 42753920} {"current_steps": 829, "total_steps": 1110, "loss": 0.0095, "lr": 7.498308559717518e-06, "epoch": 21.83221476510067, "percentage": 74.68, "elapsed_time": "7:04:14", "remaining_time": "2:23:48", "throughput": 1681.24, "total_tokens": 42794600} {"current_steps": 830, "total_steps": 1110, "loss": 0.0085, "lr": 7.447853104434438e-06, "epoch": 21.859060402684563, "percentage": 74.77, "elapsed_time": "7:04:52", "remaining_time": "2:23:19", "throughput": 1680.98, "total_tokens": 42852304} {"current_steps": 831, "total_steps": 1110, "loss": 0.0089, "lr": 7.397538248640526e-06, "epoch": 21.885906040268456, "percentage": 74.86, "elapsed_time": "7:05:22", "remaining_time": "2:22:48", "throughput": 1681.04, "total_tokens": 42904112} {"current_steps": 832, "total_steps": 1110, "loss": 0.0093, "lr": 7.347364395377257e-06, "epoch": 21.91275167785235, "percentage": 74.95, "elapsed_time": "7:05:48", "remaining_time": "2:22:16", "throughput": 1681.2, "total_tokens": 42951976} {"current_steps": 833, "total_steps": 1110, "loss": 0.0065, "lr": 7.297331946556604e-06, "epoch": 21.93959731543624, "percentage": 75.05, "elapsed_time": "7:06:24", "remaining_time": "2:21:47", "throughput": 1681.3, "total_tokens": 43015176} {"current_steps": 834, "total_steps": 1110, "loss": 0.0088, "lr": 7.247441302957858e-06, "epoch": 21.966442953020135, "percentage": 75.14, "elapsed_time": "7:07:03", "remaining_time": "2:21:19", "throughput": 1681.3, "total_tokens": 43080592} {"current_steps": 835, "total_steps": 1110, "loss": 0.0062, "lr": 7.197692864224365e-06, "epoch": 21.993288590604028, "percentage": 75.23, "elapsed_time": "7:07:42", "remaining_time": "2:20:51", "throughput": 1681.28, "total_tokens": 43145776} {"current_steps": 836, "total_steps": 1110, "loss": 0.0154, "lr": 7.148087028860387e-06, "epoch": 22.0, "percentage": 75.32, "elapsed_time": "7:07:49", "remaining_time": "2:20:13", "throughput": 1681.37, "total_tokens": 43159776} {"current_steps": 837, "total_steps": 1110, "loss": 0.0066, "lr": 7.0986241942278455e-06, "epoch": 22.026845637583893, "percentage": 75.41, "elapsed_time": "7:08:19", "remaining_time": "2:19:42", "throughput": 1681.69, "total_tokens": 43218280} {"current_steps": 838, "total_steps": 1110, "loss": 0.0077, "lr": 7.049304756543207e-06, "epoch": 22.053691275167786, "percentage": 75.5, "elapsed_time": "7:08:56", "remaining_time": "2:19:13", "throughput": 1681.69, "total_tokens": 43281456} {"current_steps": 839, "total_steps": 1110, "loss": 0.0066, "lr": 7.000129110874226e-06, "epoch": 22.08053691275168, "percentage": 75.59, "elapsed_time": "7:09:34", "remaining_time": "2:18:45", "throughput": 1681.68, "total_tokens": 43345048} {"current_steps": 840, "total_steps": 1110, "loss": 0.0109, "lr": 6.951097651136889e-06, "epoch": 22.107382550335572, "percentage": 75.68, "elapsed_time": "7:10:02", "remaining_time": "2:18:13", "throughput": 1681.92, "total_tokens": 43397896} {"current_steps": 841, "total_steps": 1110, "loss": 0.0087, "lr": 6.902210770092141e-06, "epoch": 22.13422818791946, "percentage": 75.77, "elapsed_time": "7:10:22", "remaining_time": "2:17:39", "throughput": 1682.14, "total_tokens": 43437848} {"current_steps": 842, "total_steps": 1110, "loss": 0.0072, "lr": 6.853468859342827e-06, "epoch": 22.161073825503355, "percentage": 75.86, "elapsed_time": "7:10:48", "remaining_time": "2:17:07", "throughput": 1682.22, "total_tokens": 43483240} {"current_steps": 843, "total_steps": 1110, "loss": 0.0157, "lr": 6.804872309330506e-06, "epoch": 22.187919463087248, "percentage": 75.95, "elapsed_time": "7:11:20", "remaining_time": "2:16:37", "throughput": 1682.27, "total_tokens": 43538208} {"current_steps": 844, "total_steps": 1110, "loss": 0.0093, "lr": 6.756421509332364e-06, "epoch": 22.21476510067114, "percentage": 76.04, "elapsed_time": "7:11:46", "remaining_time": "2:16:04", "throughput": 1682.32, "total_tokens": 43583304} {"current_steps": 845, "total_steps": 1110, "loss": 0.0205, "lr": 6.708116847458043e-06, "epoch": 22.241610738255034, "percentage": 76.13, "elapsed_time": "7:12:39", "remaining_time": "2:15:41", "throughput": 1681.8, "total_tokens": 43659520} {"current_steps": 846, "total_steps": 1110, "loss": 0.0102, "lr": 6.659958710646591e-06, "epoch": 22.268456375838927, "percentage": 76.22, "elapsed_time": "7:13:05", "remaining_time": "2:15:08", "throughput": 1682.08, "total_tokens": 43709632} {"current_steps": 847, "total_steps": 1110, "loss": 0.0091, "lr": 6.6119474846633115e-06, "epoch": 22.29530201342282, "percentage": 76.31, "elapsed_time": "7:13:29", "remaining_time": "2:14:36", "throughput": 1682.13, "total_tokens": 43751944} {"current_steps": 848, "total_steps": 1110, "loss": 0.0085, "lr": 6.564083554096714e-06, "epoch": 22.322147651006713, "percentage": 76.4, "elapsed_time": "7:13:51", "remaining_time": "2:14:02", "throughput": 1682.25, "total_tokens": 43791824} {"current_steps": 849, "total_steps": 1110, "loss": 0.0081, "lr": 6.5163673023553915e-06, "epoch": 22.348993288590606, "percentage": 76.49, "elapsed_time": "7:14:30", "remaining_time": "2:13:34", "throughput": 1682.03, "total_tokens": 43850928} {"current_steps": 850, "total_steps": 1110, "loss": 0.0083, "lr": 6.468799111665003e-06, "epoch": 22.375838926174495, "percentage": 76.58, "elapsed_time": "7:15:02", "remaining_time": "2:13:04", "throughput": 1681.99, "total_tokens": 43904864} {"current_steps": 851, "total_steps": 1110, "loss": 0.0233, "lr": 6.421379363065142e-06, "epoch": 22.40268456375839, "percentage": 76.67, "elapsed_time": "7:15:44", "remaining_time": "2:12:37", "throughput": 1681.73, "total_tokens": 43967944} {"current_steps": 852, "total_steps": 1110, "loss": 0.0076, "lr": 6.374108436406373e-06, "epoch": 22.42953020134228, "percentage": 76.76, "elapsed_time": "7:16:19", "remaining_time": "2:12:07", "throughput": 1681.57, "total_tokens": 44021920} {"current_steps": 853, "total_steps": 1110, "loss": 0.0085, "lr": 6.326986710347091e-06, "epoch": 22.456375838926174, "percentage": 76.85, "elapsed_time": "7:16:45", "remaining_time": "2:11:35", "throughput": 1681.55, "total_tokens": 44065240} {"current_steps": 854, "total_steps": 1110, "loss": 0.0069, "lr": 6.280014562350575e-06, "epoch": 22.483221476510067, "percentage": 76.94, "elapsed_time": "7:17:18", "remaining_time": "2:11:05", "throughput": 1681.6, "total_tokens": 44122200} {"current_steps": 855, "total_steps": 1110, "loss": 0.0074, "lr": 6.23319236868189e-06, "epoch": 22.51006711409396, "percentage": 77.03, "elapsed_time": "7:17:59", "remaining_time": "2:10:37", "throughput": 1681.35, "total_tokens": 44184896} {"current_steps": 856, "total_steps": 1110, "loss": 0.0088, "lr": 6.186520504404944e-06, "epoch": 22.536912751677853, "percentage": 77.12, "elapsed_time": "7:18:23", "remaining_time": "2:10:05", "throughput": 1681.45, "total_tokens": 44228256} {"current_steps": 857, "total_steps": 1110, "loss": 0.0084, "lr": 6.139999343379415e-06, "epoch": 22.563758389261746, "percentage": 77.21, "elapsed_time": "7:18:49", "remaining_time": "2:09:32", "throughput": 1681.55, "total_tokens": 44273696} {"current_steps": 858, "total_steps": 1110, "loss": 0.0089, "lr": 6.093629258257821e-06, "epoch": 22.59060402684564, "percentage": 77.3, "elapsed_time": "7:19:12", "remaining_time": "2:09:00", "throughput": 1681.62, "total_tokens": 44315640} {"current_steps": 859, "total_steps": 1110, "loss": 0.0072, "lr": 6.0474106204824775e-06, "epoch": 22.61744966442953, "percentage": 77.39, "elapsed_time": "7:19:47", "remaining_time": "2:08:30", "throughput": 1681.75, "total_tokens": 44377736} {"current_steps": 860, "total_steps": 1110, "loss": 0.0071, "lr": 6.001343800282569e-06, "epoch": 22.644295302013422, "percentage": 77.48, "elapsed_time": "7:20:25", "remaining_time": "2:08:01", "throughput": 1681.6, "total_tokens": 44436336} {"current_steps": 861, "total_steps": 1110, "loss": 0.0095, "lr": 5.95542916667114e-06, "epoch": 22.671140939597315, "percentage": 77.57, "elapsed_time": "7:20:47", "remaining_time": "2:07:28", "throughput": 1681.68, "total_tokens": 44477000} {"current_steps": 862, "total_steps": 1110, "loss": 0.0057, "lr": 5.9096670874421885e-06, "epoch": 22.697986577181208, "percentage": 77.66, "elapsed_time": "7:21:28", "remaining_time": "2:07:00", "throughput": 1681.49, "total_tokens": 44540224} {"current_steps": 863, "total_steps": 1110, "loss": 0.028, "lr": 5.86405792916766e-06, "epoch": 22.7248322147651, "percentage": 77.75, "elapsed_time": "7:22:06", "remaining_time": "2:06:32", "throughput": 1681.2, "total_tokens": 44595984} {"current_steps": 864, "total_steps": 1110, "loss": 0.0067, "lr": 5.818602057194589e-06, "epoch": 22.751677852348994, "percentage": 77.84, "elapsed_time": "7:22:36", "remaining_time": "2:06:01", "throughput": 1681.22, "total_tokens": 44647816} {"current_steps": 865, "total_steps": 1110, "loss": 0.0074, "lr": 5.7732998356420796e-06, "epoch": 22.778523489932887, "percentage": 77.93, "elapsed_time": "7:23:11", "remaining_time": "2:05:31", "throughput": 1681.03, "total_tokens": 44700952} {"current_steps": 866, "total_steps": 1110, "loss": 0.0086, "lr": 5.72815162739847e-06, "epoch": 22.80536912751678, "percentage": 78.02, "elapsed_time": "7:23:44", "remaining_time": "2:05:01", "throughput": 1680.85, "total_tokens": 44751184} {"current_steps": 867, "total_steps": 1110, "loss": 0.0126, "lr": 5.683157794118371e-06, "epoch": 22.83221476510067, "percentage": 78.11, "elapsed_time": "7:24:04", "remaining_time": "2:04:27", "throughput": 1681.02, "total_tokens": 44790392} {"current_steps": 868, "total_steps": 1110, "loss": 0.0059, "lr": 5.63831869621981e-06, "epoch": 22.859060402684563, "percentage": 78.2, "elapsed_time": "7:24:32", "remaining_time": "2:03:56", "throughput": 1681.16, "total_tokens": 44840368} {"current_steps": 869, "total_steps": 1110, "loss": 0.0096, "lr": 5.593634692881302e-06, "epoch": 22.885906040268456, "percentage": 78.29, "elapsed_time": "7:25:01", "remaining_time": "2:03:25", "throughput": 1681.24, "total_tokens": 44890944} {"current_steps": 870, "total_steps": 1110, "loss": 0.0068, "lr": 5.549106142039018e-06, "epoch": 22.91275167785235, "percentage": 78.38, "elapsed_time": "7:25:31", "remaining_time": "2:02:54", "throughput": 1681.34, "total_tokens": 44945224} {"current_steps": 871, "total_steps": 1110, "loss": 0.0066, "lr": 5.504733400383869e-06, "epoch": 22.93959731543624, "percentage": 78.47, "elapsed_time": "7:26:01", "remaining_time": "2:02:23", "throughput": 1681.46, "total_tokens": 44997696} {"current_steps": 872, "total_steps": 1110, "loss": 0.007, "lr": 5.460516823358699e-06, "epoch": 22.966442953020135, "percentage": 78.56, "elapsed_time": "7:26:38", "remaining_time": "2:01:54", "throughput": 1681.43, "total_tokens": 45060064} {"current_steps": 873, "total_steps": 1110, "loss": 0.0099, "lr": 5.416456765155392e-06, "epoch": 22.993288590604028, "percentage": 78.65, "elapsed_time": "7:27:05", "remaining_time": "2:01:22", "throughput": 1681.45, "total_tokens": 45105880} {"current_steps": 874, "total_steps": 1110, "loss": 0.0141, "lr": 5.372553578712078e-06, "epoch": 23.0, "percentage": 78.74, "elapsed_time": "7:27:16", "remaining_time": "2:00:46", "throughput": 1681.32, "total_tokens": 45121584} {"current_steps": 875, "total_steps": 1110, "loss": 0.0057, "lr": 5.328807615710246e-06, "epoch": 23.026845637583893, "percentage": 78.83, "elapsed_time": "7:27:39", "remaining_time": "2:00:13", "throughput": 1681.48, "total_tokens": 45164000} {"current_steps": 876, "total_steps": 1110, "loss": 0.0087, "lr": 5.2852192265720216e-06, "epoch": 23.053691275167786, "percentage": 78.92, "elapsed_time": "7:28:08", "remaining_time": "1:59:42", "throughput": 1681.49, "total_tokens": 45212640} {"current_steps": 877, "total_steps": 1110, "loss": 0.0075, "lr": 5.241788760457247e-06, "epoch": 23.08053691275168, "percentage": 79.01, "elapsed_time": "7:28:47", "remaining_time": "1:59:14", "throughput": 1681.27, "total_tokens": 45272216} {"current_steps": 878, "total_steps": 1110, "loss": 0.0066, "lr": 5.198516565260778e-06, "epoch": 23.107382550335572, "percentage": 79.1, "elapsed_time": "7:29:20", "remaining_time": "1:58:43", "throughput": 1681.51, "total_tokens": 45334000} {"current_steps": 879, "total_steps": 1110, "loss": 0.0064, "lr": 5.155402987609628e-06, "epoch": 23.13422818791946, "percentage": 79.19, "elapsed_time": "7:29:51", "remaining_time": "1:58:13", "throughput": 1681.39, "total_tokens": 45383056} {"current_steps": 880, "total_steps": 1110, "loss": 0.0159, "lr": 5.112448372860257e-06, "epoch": 23.161073825503355, "percentage": 79.28, "elapsed_time": "7:30:21", "remaining_time": "1:57:42", "throughput": 1681.32, "total_tokens": 45432168} {"current_steps": 881, "total_steps": 1110, "loss": 0.0267, "lr": 5.069653065095731e-06, "epoch": 23.187919463087248, "percentage": 79.37, "elapsed_time": "7:31:00", "remaining_time": "1:57:14", "throughput": 1680.97, "total_tokens": 45488704} {"current_steps": 882, "total_steps": 1110, "loss": 0.0065, "lr": 5.027017407123047e-06, "epoch": 23.21476510067114, "percentage": 79.46, "elapsed_time": "7:31:26", "remaining_time": "1:56:41", "throughput": 1681.2, "total_tokens": 45538112} {"current_steps": 883, "total_steps": 1110, "loss": 0.0084, "lr": 4.984541740470308e-06, "epoch": 23.241610738255034, "percentage": 79.55, "elapsed_time": "7:32:03", "remaining_time": "1:56:12", "throughput": 1681.09, "total_tokens": 45596984} {"current_steps": 884, "total_steps": 1110, "loss": 0.0081, "lr": 4.9422264053840564e-06, "epoch": 23.268456375838927, "percentage": 79.64, "elapsed_time": "7:32:32", "remaining_time": "1:55:41", "throughput": 1681.06, "total_tokens": 45644664} {"current_steps": 885, "total_steps": 1110, "loss": 0.0081, "lr": 4.900071740826489e-06, "epoch": 23.29530201342282, "percentage": 79.73, "elapsed_time": "7:33:00", "remaining_time": "1:55:10", "throughput": 1681.24, "total_tokens": 45697120} {"current_steps": 886, "total_steps": 1110, "loss": 0.0071, "lr": 4.858078084472795e-06, "epoch": 23.322147651006713, "percentage": 79.82, "elapsed_time": "7:33:23", "remaining_time": "1:54:37", "throughput": 1681.42, "total_tokens": 45740032} {"current_steps": 887, "total_steps": 1110, "loss": 0.0072, "lr": 4.816245772708394e-06, "epoch": 23.348993288590606, "percentage": 79.91, "elapsed_time": "7:33:56", "remaining_time": "1:54:07", "throughput": 1681.41, "total_tokens": 45795984} {"current_steps": 888, "total_steps": 1110, "loss": 0.0054, "lr": 4.7745751406263165e-06, "epoch": 23.375838926174495, "percentage": 80.0, "elapsed_time": "7:34:32", "remaining_time": "1:53:38", "throughput": 1681.32, "total_tokens": 45854288} {"current_steps": 889, "total_steps": 1110, "loss": 0.0086, "lr": 4.733066522024432e-06, "epoch": 23.40268456375839, "percentage": 80.09, "elapsed_time": "7:34:54", "remaining_time": "1:53:05", "throughput": 1681.34, "total_tokens": 45891576} {"current_steps": 890, "total_steps": 1110, "loss": 0.0065, "lr": 4.691720249402856e-06, "epoch": 23.42953020134228, "percentage": 80.18, "elapsed_time": "7:35:23", "remaining_time": "1:52:34", "throughput": 1681.51, "total_tokens": 45944160} {"current_steps": 891, "total_steps": 1110, "loss": 0.0069, "lr": 4.650536653961215e-06, "epoch": 23.456375838926174, "percentage": 80.27, "elapsed_time": "7:35:49", "remaining_time": "1:52:02", "throughput": 1681.55, "total_tokens": 45989360} {"current_steps": 892, "total_steps": 1110, "loss": 0.006, "lr": 4.609516065596062e-06, "epoch": 23.483221476510067, "percentage": 80.36, "elapsed_time": "7:36:19", "remaining_time": "1:51:31", "throughput": 1681.52, "total_tokens": 46040024} {"current_steps": 893, "total_steps": 1110, "loss": 0.0075, "lr": 4.568658812898169e-06, "epoch": 23.51006711409396, "percentage": 80.45, "elapsed_time": "7:36:49", "remaining_time": "1:51:00", "throughput": 1681.56, "total_tokens": 46090936} {"current_steps": 894, "total_steps": 1110, "loss": 0.0275, "lr": 4.527965223149957e-06, "epoch": 23.536912751677853, "percentage": 80.54, "elapsed_time": "7:37:29", "remaining_time": "1:50:32", "throughput": 1681.35, "total_tokens": 46152296} {"current_steps": 895, "total_steps": 1110, "loss": 0.0078, "lr": 4.487435622322814e-06, "epoch": 23.563758389261746, "percentage": 80.63, "elapsed_time": "7:37:59", "remaining_time": "1:50:01", "throughput": 1681.37, "total_tokens": 46202488} {"current_steps": 896, "total_steps": 1110, "loss": 0.0077, "lr": 4.44707033507454e-06, "epoch": 23.59060402684564, "percentage": 80.72, "elapsed_time": "7:38:26", "remaining_time": "1:49:29", "throughput": 1681.45, "total_tokens": 46250496} {"current_steps": 897, "total_steps": 1110, "loss": 0.0069, "lr": 4.4068696847466975e-06, "epoch": 23.61744966442953, "percentage": 80.81, "elapsed_time": "7:38:59", "remaining_time": "1:48:59", "throughput": 1681.43, "total_tokens": 46305848}