{"current_steps": 5, "total_steps": 3160, "loss": 3.9131, "lr": 1.2658227848101267e-05, "epoch": 0.03164556962025317, "percentage": 0.16, "elapsed_time": "0:00:01", "remaining_time": "0:15:08", "throughput": 1578.11, "total_tokens": 2272} {"current_steps": 10, "total_steps": 3160, "loss": 3.0431, "lr": 2.8481012658227846e-05, "epoch": 0.06329113924050633, "percentage": 0.32, "elapsed_time": "0:00:02", "remaining_time": "0:12:38", "throughput": 1899.79, "total_tokens": 4576} {"current_steps": 15, "total_steps": 3160, "loss": 2.1245, "lr": 4.430379746835443e-05, "epoch": 0.0949367088607595, "percentage": 0.47, "elapsed_time": "0:00:03", "remaining_time": "0:11:44", "throughput": 2019.21, "total_tokens": 6784} {"current_steps": 20, "total_steps": 3160, "loss": 1.3902, "lr": 6.012658227848101e-05, "epoch": 0.12658227848101267, "percentage": 0.63, "elapsed_time": "0:00:04", "remaining_time": "0:11:17", "throughput": 2098.77, "total_tokens": 9056} {"current_steps": 25, "total_steps": 3160, "loss": 0.9863, "lr": 7.59493670886076e-05, "epoch": 0.15822784810126583, "percentage": 0.79, "elapsed_time": "0:00:05", "remaining_time": "0:11:01", "throughput": 2154.13, "total_tokens": 11360} {"current_steps": 30, "total_steps": 3160, "loss": 1.1008, "lr": 9.177215189873418e-05, "epoch": 0.189873417721519, "percentage": 0.95, "elapsed_time": "0:00:06", "remaining_time": "0:10:49", "throughput": 2170.85, "total_tokens": 13504} {"current_steps": 35, "total_steps": 3160, "loss": 0.8906, "lr": 0.00010759493670886077, "epoch": 0.22151898734177214, "percentage": 1.11, "elapsed_time": "0:00:07", "remaining_time": "0:10:39", "throughput": 2187.73, "total_tokens": 15680} {"current_steps": 40, "total_steps": 3160, "loss": 0.9773, "lr": 0.00012341772151898734, "epoch": 0.25316455696202533, "percentage": 1.27, "elapsed_time": "0:00:08", "remaining_time": "0:10:34", "throughput": 2207.64, "total_tokens": 17952} {"current_steps": 45, "total_steps": 3160, "loss": 1.0213, "lr": 0.00013924050632911392, "epoch": 0.2848101265822785, "percentage": 1.42, "elapsed_time": "0:00:09", "remaining_time": "0:10:29", "throughput": 2225.58, "total_tokens": 20224} {"current_steps": 50, "total_steps": 3160, "loss": 0.8393, "lr": 0.0001550632911392405, "epoch": 0.31645569620253167, "percentage": 1.58, "elapsed_time": "0:00:10", "remaining_time": "0:10:25", "throughput": 2240.34, "total_tokens": 22528} {"current_steps": 55, "total_steps": 3160, "loss": 0.8312, "lr": 0.00017088607594936708, "epoch": 0.34810126582278483, "percentage": 1.74, "elapsed_time": "0:00:11", "remaining_time": "0:10:23", "throughput": 2255.37, "total_tokens": 24896} {"current_steps": 60, "total_steps": 3160, "loss": 0.869, "lr": 0.00018670886075949366, "epoch": 0.379746835443038, "percentage": 1.9, "elapsed_time": "0:00:12", "remaining_time": "0:10:20", "throughput": 2260.97, "total_tokens": 27136} {"current_steps": 65, "total_steps": 3160, "loss": 0.8962, "lr": 0.00020253164556962027, "epoch": 0.41139240506329117, "percentage": 2.06, "elapsed_time": "0:00:12", "remaining_time": "0:10:17", "throughput": 2271.66, "total_tokens": 29472} {"current_steps": 70, "total_steps": 3160, "loss": 0.7859, "lr": 0.00021835443037974685, "epoch": 0.4430379746835443, "percentage": 2.22, "elapsed_time": "0:00:13", "remaining_time": "0:10:15", "throughput": 2277.51, "total_tokens": 31744} {"current_steps": 75, "total_steps": 3160, "loss": 0.604, "lr": 0.00023417721518987343, "epoch": 0.47468354430379744, "percentage": 2.37, "elapsed_time": "0:00:14", "remaining_time": "0:10:13", "throughput": 2287.73, "total_tokens": 34112} {"current_steps": 80, "total_steps": 3160, "loss": 0.9123, "lr": 0.00025, "epoch": 0.5063291139240507, "percentage": 2.53, "elapsed_time": "0:00:15", "remaining_time": "0:10:11", "throughput": 2288.43, "total_tokens": 36320} {"current_steps": 85, "total_steps": 3160, "loss": 1.0078, "lr": 0.0002658227848101266, "epoch": 0.5379746835443038, "percentage": 2.69, "elapsed_time": "0:00:16", "remaining_time": "0:10:08", "throughput": 2296.77, "total_tokens": 38656} {"current_steps": 90, "total_steps": 3160, "loss": 0.5841, "lr": 0.00028164556962025316, "epoch": 0.569620253164557, "percentage": 2.85, "elapsed_time": "0:00:17", "remaining_time": "0:10:06", "throughput": 2301.17, "total_tokens": 40928} {"current_steps": 95, "total_steps": 3160, "loss": 0.5911, "lr": 0.00029746835443037974, "epoch": 0.6012658227848101, "percentage": 3.01, "elapsed_time": "0:00:18", "remaining_time": "0:10:05", "throughput": 2307.95, "total_tokens": 43296} {"current_steps": 100, "total_steps": 3160, "loss": 0.4616, "lr": 0.0003132911392405063, "epoch": 0.6329113924050633, "percentage": 3.16, "elapsed_time": "0:00:19", "remaining_time": "0:10:03", "throughput": 2311.64, "total_tokens": 45600} {"current_steps": 105, "total_steps": 3160, "loss": 0.3682, "lr": 0.0003291139240506329, "epoch": 0.6645569620253164, "percentage": 3.32, "elapsed_time": "0:00:20", "remaining_time": "0:10:02", "throughput": 2316.31, "total_tokens": 47968} {"current_steps": 110, "total_steps": 3160, "loss": 0.2551, "lr": 0.0003449367088607595, "epoch": 0.6962025316455697, "percentage": 3.48, "elapsed_time": "0:00:21", "remaining_time": "0:10:00", "throughput": 2317.77, "total_tokens": 50208} {"current_steps": 115, "total_steps": 3160, "loss": 0.3104, "lr": 0.00036075949367088606, "epoch": 0.7278481012658228, "percentage": 3.64, "elapsed_time": "0:00:22", "remaining_time": "0:09:58", "throughput": 2319.04, "total_tokens": 52448} {"current_steps": 120, "total_steps": 3160, "loss": 0.2939, "lr": 0.0003765822784810127, "epoch": 0.759493670886076, "percentage": 3.8, "elapsed_time": "0:00:23", "remaining_time": "0:09:57", "throughput": 2321.59, "total_tokens": 54752} {"current_steps": 125, "total_steps": 3160, "loss": 0.3141, "lr": 0.0003924050632911392, "epoch": 0.7911392405063291, "percentage": 3.96, "elapsed_time": "0:00:24", "remaining_time": "0:09:55", "throughput": 2322.7, "total_tokens": 56992} {"current_steps": 130, "total_steps": 3160, "loss": 0.4616, "lr": 0.00040822784810126586, "epoch": 0.8227848101265823, "percentage": 4.11, "elapsed_time": "0:00:25", "remaining_time": "0:09:54", "throughput": 2323.73, "total_tokens": 59232} {"current_steps": 135, "total_steps": 3160, "loss": 0.5166, "lr": 0.0004240506329113924, "epoch": 0.8544303797468354, "percentage": 4.27, "elapsed_time": "0:00:26", "remaining_time": "0:09:52", "throughput": 2323.81, "total_tokens": 61472} {"current_steps": 140, "total_steps": 3160, "loss": 0.2912, "lr": 0.000439873417721519, "epoch": 0.8860759493670886, "percentage": 4.43, "elapsed_time": "0:00:27", "remaining_time": "0:09:50", "throughput": 2320.99, "total_tokens": 63584} {"current_steps": 145, "total_steps": 3160, "loss": 0.5313, "lr": 0.00045569620253164554, "epoch": 0.9177215189873418, "percentage": 4.59, "elapsed_time": "0:00:28", "remaining_time": "0:09:49", "throughput": 2321.89, "total_tokens": 65824} {"current_steps": 150, "total_steps": 3160, "loss": 0.6694, "lr": 0.0004715189873417722, "epoch": 0.9493670886075949, "percentage": 4.75, "elapsed_time": "0:00:29", "remaining_time": "0:09:48", "throughput": 2324.67, "total_tokens": 68128} {"current_steps": 155, "total_steps": 3160, "loss": 0.2239, "lr": 0.00048734177215189876, "epoch": 0.9810126582278481, "percentage": 4.91, "elapsed_time": "0:00:30", "remaining_time": "0:09:46", "throughput": 2326.35, "total_tokens": 70400} {"current_steps": 158, "total_steps": 3160, "eval_loss": 0.29432404041290283, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:00:32", "remaining_time": "0:10:16", "throughput": 2206.79, "total_tokens": 71552} {"current_steps": 160, "total_steps": 3160, "loss": 0.276, "lr": 0.0005031645569620254, "epoch": 1.0126582278481013, "percentage": 5.06, "elapsed_time": "0:00:33", "remaining_time": "0:10:31", "throughput": 2152.5, "total_tokens": 72480} {"current_steps": 165, "total_steps": 3160, "loss": 0.2778, "lr": 0.0005189873417721519, "epoch": 1.0443037974683544, "percentage": 5.22, "elapsed_time": "0:00:34", "remaining_time": "0:10:28", "throughput": 2158.72, "total_tokens": 74784} {"current_steps": 170, "total_steps": 3160, "loss": 0.1551, "lr": 0.0005348101265822784, "epoch": 1.0759493670886076, "percentage": 5.38, "elapsed_time": "0:00:35", "remaining_time": "0:10:25", "throughput": 2161.42, "total_tokens": 76928} {"current_steps": 175, "total_steps": 3160, "loss": 0.1562, "lr": 0.0005506329113924051, "epoch": 1.1075949367088607, "percentage": 5.54, "elapsed_time": "0:00:36", "remaining_time": "0:10:23", "throughput": 2168.02, "total_tokens": 79296} {"current_steps": 180, "total_steps": 3160, "loss": 0.1654, "lr": 0.0005664556962025317, "epoch": 1.139240506329114, "percentage": 5.7, "elapsed_time": "0:00:37", "remaining_time": "0:10:21", "throughput": 2174.07, "total_tokens": 81632} {"current_steps": 185, "total_steps": 3160, "loss": 0.128, "lr": 0.0005822784810126582, "epoch": 1.1708860759493671, "percentage": 5.85, "elapsed_time": "0:00:38", "remaining_time": "0:10:19", "throughput": 2178.31, "total_tokens": 83872} {"current_steps": 190, "total_steps": 3160, "loss": 0.1271, "lr": 0.0005981012658227848, "epoch": 1.2025316455696202, "percentage": 6.01, "elapsed_time": "0:00:39", "remaining_time": "0:10:17", "throughput": 2184.64, "total_tokens": 86240} {"current_steps": 195, "total_steps": 3160, "loss": 0.1042, "lr": 0.0006139240506329115, "epoch": 1.2341772151898733, "percentage": 6.17, "elapsed_time": "0:00:40", "remaining_time": "0:10:14", "throughput": 2189.62, "total_tokens": 88544} {"current_steps": 200, "total_steps": 3160, "loss": 0.1528, "lr": 0.000629746835443038, "epoch": 1.2658227848101267, "percentage": 6.33, "elapsed_time": "0:00:41", "remaining_time": "0:10:12", "throughput": 2194.56, "total_tokens": 90880} {"current_steps": 205, "total_steps": 3160, "loss": 0.0549, "lr": 0.0006455696202531646, "epoch": 1.2974683544303798, "percentage": 6.49, "elapsed_time": "0:00:42", "remaining_time": "0:10:10", "throughput": 2196.45, "total_tokens": 93056} {"current_steps": 210, "total_steps": 3160, "loss": 0.1217, "lr": 0.0006613924050632911, "epoch": 1.3291139240506329, "percentage": 6.65, "elapsed_time": "0:00:43", "remaining_time": "0:10:08", "throughput": 2201.46, "total_tokens": 95392} {"current_steps": 215, "total_steps": 3160, "loss": 0.0983, "lr": 0.0006772151898734177, "epoch": 1.360759493670886, "percentage": 6.8, "elapsed_time": "0:00:44", "remaining_time": "0:10:06", "throughput": 2203.44, "total_tokens": 97568} {"current_steps": 220, "total_steps": 3160, "loss": 0.0474, "lr": 0.0006930379746835443, "epoch": 1.3924050632911391, "percentage": 6.96, "elapsed_time": "0:00:45", "remaining_time": "0:10:04", "throughput": 2205.86, "total_tokens": 99776} {"current_steps": 225, "total_steps": 3160, "loss": 0.1094, "lr": 0.0007088607594936709, "epoch": 1.4240506329113924, "percentage": 7.12, "elapsed_time": "0:00:46", "remaining_time": "0:10:02", "throughput": 2211.17, "total_tokens": 102176} {"current_steps": 230, "total_steps": 3160, "loss": 0.1177, "lr": 0.0007246835443037975, "epoch": 1.4556962025316456, "percentage": 7.28, "elapsed_time": "0:00:47", "remaining_time": "0:10:00", "throughput": 2214.88, "total_tokens": 104480} {"current_steps": 235, "total_steps": 3160, "loss": 0.1631, "lr": 0.000740506329113924, "epoch": 1.4873417721518987, "percentage": 7.44, "elapsed_time": "0:00:48", "remaining_time": "0:09:59", "throughput": 2218.93, "total_tokens": 106816} {"current_steps": 240, "total_steps": 3160, "loss": 0.1521, "lr": 0.0007563291139240507, "epoch": 1.518987341772152, "percentage": 7.59, "elapsed_time": "0:00:49", "remaining_time": "0:09:57", "throughput": 2220.84, "total_tokens": 109024} {"current_steps": 245, "total_steps": 3160, "loss": 0.077, "lr": 0.0007721518987341772, "epoch": 1.5506329113924051, "percentage": 7.75, "elapsed_time": "0:00:50", "remaining_time": "0:09:55", "throughput": 2222.16, "total_tokens": 111200} {"current_steps": 250, "total_steps": 3160, "loss": 0.1036, "lr": 0.0007879746835443038, "epoch": 1.5822784810126582, "percentage": 7.91, "elapsed_time": "0:00:50", "remaining_time": "0:09:53", "throughput": 2223.89, "total_tokens": 113408} {"current_steps": 255, "total_steps": 3160, "loss": 0.0699, "lr": 0.0008037974683544303, "epoch": 1.6139240506329116, "percentage": 8.07, "elapsed_time": "0:00:51", "remaining_time": "0:09:51", "throughput": 2225.13, "total_tokens": 115616} {"current_steps": 260, "total_steps": 3160, "loss": 0.0546, "lr": 0.000819620253164557, "epoch": 1.6455696202531644, "percentage": 8.23, "elapsed_time": "0:00:52", "remaining_time": "0:09:50", "throughput": 2225.39, "total_tokens": 117728} {"current_steps": 265, "total_steps": 3160, "loss": 0.0819, "lr": 0.0008354430379746836, "epoch": 1.6772151898734178, "percentage": 8.39, "elapsed_time": "0:00:53", "remaining_time": "0:09:48", "throughput": 2228.22, "total_tokens": 120032} {"current_steps": 270, "total_steps": 3160, "loss": 0.0862, "lr": 0.0008512658227848101, "epoch": 1.7088607594936709, "percentage": 8.54, "elapsed_time": "0:00:54", "remaining_time": "0:09:46", "throughput": 2228.34, "total_tokens": 122144} {"current_steps": 275, "total_steps": 3160, "loss": 0.0851, "lr": 0.0008670886075949367, "epoch": 1.740506329113924, "percentage": 8.7, "elapsed_time": "0:00:55", "remaining_time": "0:09:45", "throughput": 2230.3, "total_tokens": 124384} {"current_steps": 280, "total_steps": 3160, "loss": 0.1814, "lr": 0.0008829113924050633, "epoch": 1.7721518987341773, "percentage": 8.86, "elapsed_time": "0:00:56", "remaining_time": "0:09:43", "throughput": 2231.38, "total_tokens": 126560} {"current_steps": 285, "total_steps": 3160, "loss": 0.1439, "lr": 0.0008987341772151899, "epoch": 1.8037974683544302, "percentage": 9.02, "elapsed_time": "0:00:57", "remaining_time": "0:09:41", "throughput": 2234.74, "total_tokens": 128928} {"current_steps": 290, "total_steps": 3160, "loss": 0.1391, "lr": 0.0009145569620253165, "epoch": 1.8354430379746836, "percentage": 9.18, "elapsed_time": "0:00:58", "remaining_time": "0:09:40", "throughput": 2237.98, "total_tokens": 131264} {"current_steps": 295, "total_steps": 3160, "loss": 0.1173, "lr": 0.000930379746835443, "epoch": 1.8670886075949367, "percentage": 9.34, "elapsed_time": "0:00:59", "remaining_time": "0:09:38", "throughput": 2240.63, "total_tokens": 133568} {"current_steps": 300, "total_steps": 3160, "loss": 0.1156, "lr": 0.0009462025316455697, "epoch": 1.8987341772151898, "percentage": 9.49, "elapsed_time": "0:01:00", "remaining_time": "0:09:37", "throughput": 2243.31, "total_tokens": 135936} {"current_steps": 305, "total_steps": 3160, "loss": 0.0465, "lr": 0.0009620253164556962, "epoch": 1.9303797468354431, "percentage": 9.65, "elapsed_time": "0:01:01", "remaining_time": "0:09:36", "throughput": 2243.66, "total_tokens": 138080} {"current_steps": 310, "total_steps": 3160, "loss": 0.1008, "lr": 0.000977848101265823, "epoch": 1.9620253164556962, "percentage": 9.81, "elapsed_time": "0:01:02", "remaining_time": "0:09:34", "throughput": 2246.19, "total_tokens": 140384} {"current_steps": 315, "total_steps": 3160, "loss": 0.246, "lr": 0.0009936708860759493, "epoch": 1.9936708860759493, "percentage": 9.97, "elapsed_time": "0:01:03", "remaining_time": "0:09:33", "throughput": 2248.42, "total_tokens": 142752} {"current_steps": 316, "total_steps": 3160, "eval_loss": 0.2061605006456375, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:01:05", "remaining_time": "0:09:47", "throughput": 2189.66, "total_tokens": 142960} {"current_steps": 320, "total_steps": 3160, "loss": 0.109, "lr": 0.0009999972544921997, "epoch": 2.0253164556962027, "percentage": 10.13, "elapsed_time": "0:01:06", "remaining_time": "0:09:53", "throughput": 2164.12, "total_tokens": 144816} {"current_steps": 325, "total_steps": 3160, "loss": 0.0737, "lr": 0.000999980476498165, "epoch": 2.0569620253164556, "percentage": 10.28, "elapsed_time": "0:01:07", "remaining_time": "0:09:52", "throughput": 2167.05, "total_tokens": 147120} {"current_steps": 330, "total_steps": 3160, "loss": 0.0364, "lr": 0.0009999484463034094, "epoch": 2.088607594936709, "percentage": 10.44, "elapsed_time": "0:01:08", "remaining_time": "0:09:50", "throughput": 2169.97, "total_tokens": 149392} {"current_steps": 335, "total_steps": 3160, "loss": 0.1014, "lr": 0.0009999011648850328, "epoch": 2.1202531645569622, "percentage": 10.6, "elapsed_time": "0:01:09", "remaining_time": "0:09:48", "throughput": 2172.43, "total_tokens": 151632} {"current_steps": 340, "total_steps": 3160, "loss": 0.0725, "lr": 0.0009998386336853829, "epoch": 2.151898734177215, "percentage": 10.76, "elapsed_time": "0:01:10", "remaining_time": "0:09:46", "throughput": 2174.9, "total_tokens": 153904} {"current_steps": 345, "total_steps": 3160, "loss": 0.05, "lr": 0.0009997608546120109, "epoch": 2.1835443037974684, "percentage": 10.92, "elapsed_time": "0:01:11", "remaining_time": "0:09:45", "throughput": 2177.31, "total_tokens": 156176} {"current_steps": 350, "total_steps": 3160, "loss": 0.079, "lr": 0.0009996678300376138, "epoch": 2.2151898734177213, "percentage": 11.08, "elapsed_time": "0:01:12", "remaining_time": "0:09:43", "throughput": 2180.32, "total_tokens": 158480} {"current_steps": 355, "total_steps": 3160, "loss": 0.0485, "lr": 0.000999559562799961, "epoch": 2.2468354430379747, "percentage": 11.23, "elapsed_time": "0:01:13", "remaining_time": "0:09:41", "throughput": 2182.14, "total_tokens": 160688} {"current_steps": 360, "total_steps": 3160, "loss": 0.0262, "lr": 0.000999436056201809, "epoch": 2.278481012658228, "percentage": 11.39, "elapsed_time": "0:01:14", "remaining_time": "0:09:40", "throughput": 2183.93, "total_tokens": 162896} {"current_steps": 365, "total_steps": 3160, "loss": 0.1019, "lr": 0.0009992973140107997, "epoch": 2.310126582278481, "percentage": 11.55, "elapsed_time": "0:01:15", "remaining_time": "0:09:38", "throughput": 2186.47, "total_tokens": 165200} {"current_steps": 370, "total_steps": 3160, "loss": 0.0668, "lr": 0.000999143340459346, "epoch": 2.3417721518987342, "percentage": 11.71, "elapsed_time": "0:01:16", "remaining_time": "0:09:36", "throughput": 2187.86, "total_tokens": 167376} {"current_steps": 375, "total_steps": 3160, "loss": 0.0472, "lr": 0.0009989741402445021, "epoch": 2.3734177215189876, "percentage": 11.87, "elapsed_time": "0:01:17", "remaining_time": "0:09:35", "throughput": 2188.82, "total_tokens": 169520} {"current_steps": 380, "total_steps": 3160, "loss": 0.1526, "lr": 0.000998789718527821, "epoch": 2.4050632911392404, "percentage": 12.03, "elapsed_time": "0:01:18", "remaining_time": "0:09:33", "throughput": 2191.93, "total_tokens": 171920} {"current_steps": 385, "total_steps": 3160, "loss": 0.0876, "lr": 0.0009985900809351962, "epoch": 2.4367088607594938, "percentage": 12.18, "elapsed_time": "0:01:19", "remaining_time": "0:09:32", "throughput": 2194.87, "total_tokens": 174288} {"current_steps": 390, "total_steps": 3160, "loss": 0.1276, "lr": 0.0009983752335566908, "epoch": 2.4683544303797467, "percentage": 12.34, "elapsed_time": "0:01:20", "remaining_time": "0:09:30", "throughput": 2197.42, "total_tokens": 176592} {"current_steps": 395, "total_steps": 3160, "loss": 0.084, "lr": 0.0009981451829463518, "epoch": 2.5, "percentage": 12.5, "elapsed_time": "0:01:21", "remaining_time": "0:09:29", "throughput": 2199.84, "total_tokens": 178896} {"current_steps": 400, "total_steps": 3160, "loss": 0.0511, "lr": 0.0009978999361220091, "epoch": 2.5316455696202533, "percentage": 12.66, "elapsed_time": "0:01:22", "remaining_time": "0:09:27", "throughput": 2201.61, "total_tokens": 181168} {"current_steps": 405, "total_steps": 3160, "loss": 0.1116, "lr": 0.0009976395005650623, "epoch": 2.5632911392405062, "percentage": 12.82, "elapsed_time": "0:01:23", "remaining_time": "0:09:26", "throughput": 2202.87, "total_tokens": 183376} {"current_steps": 410, "total_steps": 3160, "loss": 0.0561, "lr": 0.0009973638842202526, "epoch": 2.5949367088607596, "percentage": 12.97, "elapsed_time": "0:01:24", "remaining_time": "0:09:24", "throughput": 2205.49, "total_tokens": 185744} {"current_steps": 415, "total_steps": 3160, "loss": 0.0838, "lr": 0.00099707309549542, "epoch": 2.6265822784810124, "percentage": 13.13, "elapsed_time": "0:01:25", "remaining_time": "0:09:23", "throughput": 2206.81, "total_tokens": 187984} {"current_steps": 420, "total_steps": 3160, "loss": 0.0605, "lr": 0.0009967671432612466, "epoch": 2.6582278481012658, "percentage": 13.29, "elapsed_time": "0:01:26", "remaining_time": "0:09:21", "throughput": 2207.45, "total_tokens": 190128} {"current_steps": 425, "total_steps": 3160, "loss": 0.0865, "lr": 0.0009964460368509867, "epoch": 2.689873417721519, "percentage": 13.45, "elapsed_time": "0:01:27", "remaining_time": "0:09:20", "throughput": 2208.71, "total_tokens": 192336} {"current_steps": 430, "total_steps": 3160, "loss": 0.0716, "lr": 0.0009961097860601818, "epoch": 2.721518987341772, "percentage": 13.61, "elapsed_time": "0:01:28", "remaining_time": "0:09:18", "throughput": 2210.63, "total_tokens": 194640} {"current_steps": 435, "total_steps": 3160, "loss": 0.0469, "lr": 0.0009957584011463612, "epoch": 2.7531645569620253, "percentage": 13.77, "elapsed_time": "0:01:28", "remaining_time": "0:09:17", "throughput": 2211.85, "total_tokens": 196848} {"current_steps": 440, "total_steps": 3160, "loss": 0.0958, "lr": 0.0009953918928287304, "epoch": 2.7848101265822782, "percentage": 13.92, "elapsed_time": "0:01:29", "remaining_time": "0:09:16", "throughput": 2213.32, "total_tokens": 199088} {"current_steps": 445, "total_steps": 3160, "loss": 0.0527, "lr": 0.0009950102722878422, "epoch": 2.8164556962025316, "percentage": 14.08, "elapsed_time": "0:01:30", "remaining_time": "0:09:14", "throughput": 2215.12, "total_tokens": 201392} {"current_steps": 450, "total_steps": 3160, "loss": 0.0687, "lr": 0.000994613551165258, "epoch": 2.848101265822785, "percentage": 14.24, "elapsed_time": "0:01:31", "remaining_time": "0:09:13", "throughput": 2216.54, "total_tokens": 203664} {"current_steps": 455, "total_steps": 3160, "loss": 0.0394, "lr": 0.0009942017415631903, "epoch": 2.879746835443038, "percentage": 14.4, "elapsed_time": "0:01:32", "remaining_time": "0:09:12", "throughput": 2218.26, "total_tokens": 205968} {"current_steps": 460, "total_steps": 3160, "loss": 0.0556, "lr": 0.000993774856044135, "epoch": 2.911392405063291, "percentage": 14.56, "elapsed_time": "0:01:33", "remaining_time": "0:09:10", "throughput": 2219.58, "total_tokens": 208208} {"current_steps": 465, "total_steps": 3160, "loss": 0.0872, "lr": 0.0009933329076304885, "epoch": 2.9430379746835444, "percentage": 14.72, "elapsed_time": "0:01:34", "remaining_time": "0:09:09", "throughput": 2221.41, "total_tokens": 210544} {"current_steps": 470, "total_steps": 3160, "loss": 0.0528, "lr": 0.0009928759098041483, "epoch": 2.9746835443037973, "percentage": 14.87, "elapsed_time": "0:01:35", "remaining_time": "0:09:08", "throughput": 2223.01, "total_tokens": 212848} {"current_steps": 474, "total_steps": 3160, "eval_loss": 0.14478395879268646, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "0:01:38", "remaining_time": "0:09:16", "throughput": 2185.13, "total_tokens": 214432} {"current_steps": 475, "total_steps": 3160, "loss": 0.0956, "lr": 0.000992403876506104, "epoch": 3.0063291139240507, "percentage": 15.03, "elapsed_time": "0:01:39", "remaining_time": "0:09:20", "throughput": 2166.36, "total_tokens": 214944} {"current_steps": 480, "total_steps": 3160, "loss": 0.0524, "lr": 0.0009919168221360114, "epoch": 3.037974683544304, "percentage": 15.19, "elapsed_time": "0:01:40", "remaining_time": "0:09:19", "throughput": 2168.36, "total_tokens": 217280} {"current_steps": 485, "total_steps": 3160, "loss": 0.0353, "lr": 0.0009914147615517526, "epoch": 3.069620253164557, "percentage": 15.35, "elapsed_time": "0:01:41", "remaining_time": "0:09:17", "throughput": 2169.53, "total_tokens": 219456} {"current_steps": 490, "total_steps": 3160, "loss": 0.0849, "lr": 0.0009908977100689831, "epoch": 3.1012658227848102, "percentage": 15.51, "elapsed_time": "0:01:42", "remaining_time": "0:09:16", "throughput": 2170.94, "total_tokens": 221664} {"current_steps": 495, "total_steps": 3160, "loss": 0.0367, "lr": 0.000990365683460665, "epoch": 3.132911392405063, "percentage": 15.66, "elapsed_time": "0:01:43", "remaining_time": "0:09:15", "throughput": 2173.5, "total_tokens": 224064} {"current_steps": 500, "total_steps": 3160, "loss": 0.0144, "lr": 0.0009898186979565848, "epoch": 3.1645569620253164, "percentage": 15.82, "elapsed_time": "0:01:44", "remaining_time": "0:09:13", "throughput": 2175.14, "total_tokens": 226336} {"current_steps": 505, "total_steps": 3160, "loss": 0.1235, "lr": 0.00098925677024286, "epoch": 3.1962025316455698, "percentage": 15.98, "elapsed_time": "0:01:45", "remaining_time": "0:09:12", "throughput": 2177.44, "total_tokens": 228672} {"current_steps": 510, "total_steps": 3160, "loss": 0.055, "lr": 0.0009886799174614283, "epoch": 3.2278481012658227, "percentage": 16.14, "elapsed_time": "0:01:45", "remaining_time": "0:09:10", "throughput": 2178.75, "total_tokens": 230880} {"current_steps": 515, "total_steps": 3160, "loss": 0.0383, "lr": 0.0009880881572095256, "epoch": 3.259493670886076, "percentage": 16.3, "elapsed_time": "0:01:46", "remaining_time": "0:09:09", "throughput": 2179.78, "total_tokens": 233056} {"current_steps": 520, "total_steps": 3160, "loss": 0.0485, "lr": 0.0009874815075391489, "epoch": 3.291139240506329, "percentage": 16.46, "elapsed_time": "0:01:47", "remaining_time": "0:09:07", "throughput": 2180.81, "total_tokens": 235232} {"current_steps": 525, "total_steps": 3160, "loss": 0.0545, "lr": 0.000986859986956506, "epoch": 3.3227848101265822, "percentage": 16.61, "elapsed_time": "0:01:48", "remaining_time": "0:09:06", "throughput": 2182.31, "total_tokens": 237472} {"current_steps": 530, "total_steps": 3160, "loss": 0.0374, "lr": 0.0009862236144214508, "epoch": 3.3544303797468356, "percentage": 16.77, "elapsed_time": "0:01:49", "remaining_time": "0:09:04", "throughput": 2183.5, "total_tokens": 239680} {"current_steps": 535, "total_steps": 3160, "loss": 0.0477, "lr": 0.0009855724093469046, "epoch": 3.3860759493670884, "percentage": 16.93, "elapsed_time": "0:01:50", "remaining_time": "0:09:03", "throughput": 2184.67, "total_tokens": 241888} {"current_steps": 540, "total_steps": 3160, "loss": 0.0418, "lr": 0.0009849063915982636, "epoch": 3.4177215189873418, "percentage": 17.09, "elapsed_time": "0:01:51", "remaining_time": "0:09:01", "throughput": 2186.31, "total_tokens": 244160} {"current_steps": 545, "total_steps": 3160, "loss": 0.0598, "lr": 0.0009842255814927945, "epoch": 3.449367088607595, "percentage": 17.25, "elapsed_time": "0:01:52", "remaining_time": "0:09:00", "throughput": 2187.74, "total_tokens": 246432} {"current_steps": 550, "total_steps": 3160, "loss": 0.0719, "lr": 0.0009835299997990124, "epoch": 3.481012658227848, "percentage": 17.41, "elapsed_time": "0:01:53", "remaining_time": "0:08:59", "throughput": 2189.34, "total_tokens": 248704} {"current_steps": 555, "total_steps": 3160, "loss": 0.0765, "lr": 0.0009828196677360496, "epoch": 3.5126582278481013, "percentage": 17.56, "elapsed_time": "0:01:54", "remaining_time": "0:08:57", "throughput": 2190.7, "total_tokens": 250944} {"current_steps": 560, "total_steps": 3160, "loss": 0.0157, "lr": 0.0009820946069730066, "epoch": 3.5443037974683547, "percentage": 17.72, "elapsed_time": "0:01:55", "remaining_time": "0:08:56", "throughput": 2192.29, "total_tokens": 253248} {"current_steps": 565, "total_steps": 3160, "loss": 0.0886, "lr": 0.0009813548396282912, "epoch": 3.5759493670886076, "percentage": 17.88, "elapsed_time": "0:01:56", "remaining_time": "0:08:55", "throughput": 2194.36, "total_tokens": 255648} {"current_steps": 570, "total_steps": 3160, "loss": 0.0192, "lr": 0.000980600388268945, "epoch": 3.607594936708861, "percentage": 18.04, "elapsed_time": "0:01:57", "remaining_time": "0:08:53", "throughput": 2195.87, "total_tokens": 257952} {"current_steps": 575, "total_steps": 3160, "loss": 0.0891, "lr": 0.0009798312759099538, "epoch": 3.6392405063291138, "percentage": 18.2, "elapsed_time": "0:01:58", "remaining_time": "0:08:52", "throughput": 2197.37, "total_tokens": 260256} {"current_steps": 580, "total_steps": 3160, "loss": 0.0465, "lr": 0.0009790475260135457, "epoch": 3.670886075949367, "percentage": 18.35, "elapsed_time": "0:01:59", "remaining_time": "0:08:51", "throughput": 2199.55, "total_tokens": 262688} {"current_steps": 585, "total_steps": 3160, "loss": 0.0317, "lr": 0.0009782491624884758, "epoch": 3.7025316455696204, "percentage": 18.51, "elapsed_time": "0:02:00", "remaining_time": "0:08:49", "throughput": 2200.96, "total_tokens": 264960} {"current_steps": 590, "total_steps": 3160, "loss": 0.0243, "lr": 0.0009774362096892967, "epoch": 3.7341772151898733, "percentage": 18.67, "elapsed_time": "0:02:01", "remaining_time": "0:08:48", "throughput": 2201.69, "total_tokens": 267136} {"current_steps": 595, "total_steps": 3160, "loss": 0.1092, "lr": 0.000976608692415615, "epoch": 3.7658227848101267, "percentage": 18.83, "elapsed_time": "0:02:02", "remaining_time": "0:08:47", "throughput": 2202.86, "total_tokens": 269408} {"current_steps": 600, "total_steps": 3160, "loss": 0.0523, "lr": 0.0009757666359113356, "epoch": 3.7974683544303796, "percentage": 18.99, "elapsed_time": "0:02:03", "remaining_time": "0:08:45", "throughput": 2204.26, "total_tokens": 271712} {"current_steps": 605, "total_steps": 3160, "loss": 0.0791, "lr": 0.0009749100658638914, "epoch": 3.829113924050633, "percentage": 19.15, "elapsed_time": "0:02:04", "remaining_time": "0:08:44", "throughput": 2205.84, "total_tokens": 274016} {"current_steps": 610, "total_steps": 3160, "loss": 0.0362, "lr": 0.0009740390084034589, "epoch": 3.8607594936708862, "percentage": 19.3, "elapsed_time": "0:02:05", "remaining_time": "0:08:43", "throughput": 2207.13, "total_tokens": 276288} {"current_steps": 615, "total_steps": 3160, "loss": 0.0538, "lr": 0.0009731534901021626, "epoch": 3.892405063291139, "percentage": 19.46, "elapsed_time": "0:02:06", "remaining_time": "0:08:41", "throughput": 2208.42, "total_tokens": 278560} {"current_steps": 620, "total_steps": 3160, "loss": 0.0655, "lr": 0.0009722535379732627, "epoch": 3.9240506329113924, "percentage": 19.62, "elapsed_time": "0:02:07", "remaining_time": "0:08:40", "throughput": 2209.93, "total_tokens": 280864} {"current_steps": 625, "total_steps": 3160, "loss": 0.0144, "lr": 0.0009713391794703321, "epoch": 3.9556962025316453, "percentage": 19.78, "elapsed_time": "0:02:08", "remaining_time": "0:08:39", "throughput": 2210.75, "total_tokens": 283072} {"current_steps": 630, "total_steps": 3160, "loss": 0.0997, "lr": 0.000970410442486419, "epoch": 3.9873417721518987, "percentage": 19.94, "elapsed_time": "0:02:09", "remaining_time": "0:08:38", "throughput": 2211.87, "total_tokens": 285376} {"current_steps": 632, "total_steps": 3160, "eval_loss": 0.1533374935388565, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:02:11", "remaining_time": "0:08:44", "throughput": 2183.02, "total_tokens": 286000} {"current_steps": 635, "total_steps": 3160, "loss": 0.0405, "lr": 0.0009694673553531956, "epoch": 4.018987341772152, "percentage": 20.09, "elapsed_time": "0:02:12", "remaining_time": "0:08:46", "throughput": 2168.83, "total_tokens": 287280} {"current_steps": 640, "total_steps": 3160, "loss": 0.0569, "lr": 0.0009685099468400933, "epoch": 4.050632911392405, "percentage": 20.25, "elapsed_time": "0:02:13", "remaining_time": "0:08:45", "throughput": 2170.12, "total_tokens": 289552} {"current_steps": 645, "total_steps": 3160, "loss": 0.0356, "lr": 0.0009675382461534265, "epoch": 4.082278481012658, "percentage": 20.41, "elapsed_time": "0:02:14", "remaining_time": "0:08:44", "throughput": 2171.43, "total_tokens": 291824} {"current_steps": 650, "total_steps": 3160, "loss": 0.0346, "lr": 0.0009665522829355004, "epoch": 4.113924050632911, "percentage": 20.57, "elapsed_time": "0:02:15", "remaining_time": "0:08:42", "throughput": 2173.33, "total_tokens": 294224} {"current_steps": 655, "total_steps": 3160, "loss": 0.0435, "lr": 0.0009655520872637074, "epoch": 4.1455696202531644, "percentage": 20.73, "elapsed_time": "0:02:16", "remaining_time": "0:08:41", "throughput": 2174.76, "total_tokens": 296496} {"current_steps": 660, "total_steps": 3160, "loss": 0.0602, "lr": 0.0009645376896496087, "epoch": 4.177215189873418, "percentage": 20.89, "elapsed_time": "0:02:17", "remaining_time": "0:08:40", "throughput": 2176.62, "total_tokens": 298896} {"current_steps": 665, "total_steps": 3160, "loss": 0.0586, "lr": 0.0009635091210380051, "epoch": 4.208860759493671, "percentage": 21.04, "elapsed_time": "0:02:18", "remaining_time": "0:08:38", "throughput": 2178.21, "total_tokens": 301200} {"current_steps": 670, "total_steps": 3160, "loss": 0.0346, "lr": 0.0009624664128059915, "epoch": 4.2405063291139244, "percentage": 21.2, "elapsed_time": "0:02:19", "remaining_time": "0:08:37", "throughput": 2179.0, "total_tokens": 303376} {"current_steps": 675, "total_steps": 3160, "loss": 0.0285, "lr": 0.0009614095967620004, "epoch": 4.272151898734177, "percentage": 21.36, "elapsed_time": "0:02:20", "remaining_time": "0:08:36", "throughput": 2180.59, "total_tokens": 305744} {"current_steps": 680, "total_steps": 3160, "loss": 0.1045, "lr": 0.0009603387051448313, "epoch": 4.30379746835443, "percentage": 21.52, "elapsed_time": "0:02:21", "remaining_time": "0:08:34", "throughput": 2181.39, "total_tokens": 307920} {"current_steps": 685, "total_steps": 3160, "loss": 0.0623, "lr": 0.000959253770622668, "epoch": 4.3354430379746836, "percentage": 21.68, "elapsed_time": "0:02:22", "remaining_time": "0:08:33", "throughput": 2182.76, "total_tokens": 310224} {"current_steps": 690, "total_steps": 3160, "loss": 0.0271, "lr": 0.0009581548262920805, "epoch": 4.367088607594937, "percentage": 21.84, "elapsed_time": "0:02:23", "remaining_time": "0:08:32", "throughput": 2183.84, "total_tokens": 312464} {"current_steps": 695, "total_steps": 3160, "loss": 0.0453, "lr": 0.0009570419056770173, "epoch": 4.39873417721519, "percentage": 21.99, "elapsed_time": "0:02:24", "remaining_time": "0:08:30", "throughput": 2184.95, "total_tokens": 314704} {"current_steps": 700, "total_steps": 3160, "loss": 0.0549, "lr": 0.0009559150427277812, "epoch": 4.430379746835443, "percentage": 22.15, "elapsed_time": "0:02:24", "remaining_time": "0:08:29", "throughput": 2186.38, "total_tokens": 317008} {"current_steps": 705, "total_steps": 3160, "loss": 0.0257, "lr": 0.0009547742718199938, "epoch": 4.462025316455696, "percentage": 22.31, "elapsed_time": "0:02:25", "remaining_time": "0:08:28", "throughput": 2187.45, "total_tokens": 319248} {"current_steps": 710, "total_steps": 3160, "loss": 0.1067, "lr": 0.0009536196277535483, "epoch": 4.493670886075949, "percentage": 22.47, "elapsed_time": "0:02:26", "remaining_time": "0:08:26", "throughput": 2188.71, "total_tokens": 321552} {"current_steps": 715, "total_steps": 3160, "loss": 0.06, "lr": 0.0009524511457515457, "epoch": 4.525316455696203, "percentage": 22.63, "elapsed_time": "0:02:27", "remaining_time": "0:08:25", "throughput": 2189.4, "total_tokens": 323728} {"current_steps": 720, "total_steps": 3160, "loss": 0.0325, "lr": 0.000951268861459222, "epoch": 4.556962025316456, "percentage": 22.78, "elapsed_time": "0:02:28", "remaining_time": "0:08:24", "throughput": 2190.6, "total_tokens": 326000} {"current_steps": 725, "total_steps": 3160, "loss": 0.0738, "lr": 0.0009500728109428603, "epoch": 4.588607594936709, "percentage": 22.94, "elapsed_time": "0:02:29", "remaining_time": "0:08:23", "throughput": 2192.03, "total_tokens": 328368} {"current_steps": 730, "total_steps": 3160, "loss": 0.0085, "lr": 0.0009488630306886904, "epoch": 4.620253164556962, "percentage": 23.1, "elapsed_time": "0:02:30", "remaining_time": "0:08:21", "throughput": 2192.86, "total_tokens": 330576} {"current_steps": 735, "total_steps": 3160, "loss": 0.024, "lr": 0.0009476395576017756, "epoch": 4.651898734177215, "percentage": 23.26, "elapsed_time": "0:02:31", "remaining_time": "0:08:20", "throughput": 2193.61, "total_tokens": 332784} {"current_steps": 740, "total_steps": 3160, "loss": 0.0318, "lr": 0.0009464024290048879, "epoch": 4.6835443037974684, "percentage": 23.42, "elapsed_time": "0:02:32", "remaining_time": "0:08:19", "throughput": 2195.15, "total_tokens": 335152} {"current_steps": 745, "total_steps": 3160, "loss": 0.0238, "lr": 0.0009451516826373676, "epoch": 4.715189873417722, "percentage": 23.58, "elapsed_time": "0:02:33", "remaining_time": "0:08:18", "throughput": 2196.46, "total_tokens": 337456} {"current_steps": 750, "total_steps": 3160, "loss": 0.072, "lr": 0.0009438873566539743, "epoch": 4.746835443037975, "percentage": 23.73, "elapsed_time": "0:02:34", "remaining_time": "0:08:16", "throughput": 2197.79, "total_tokens": 339792} {"current_steps": 755, "total_steps": 3160, "loss": 0.0215, "lr": 0.0009426094896237213, "epoch": 4.7784810126582276, "percentage": 23.89, "elapsed_time": "0:02:35", "remaining_time": "0:08:15", "throughput": 2198.58, "total_tokens": 342032} {"current_steps": 760, "total_steps": 3160, "loss": 0.0278, "lr": 0.0009413181205286995, "epoch": 4.810126582278481, "percentage": 24.05, "elapsed_time": "0:02:36", "remaining_time": "0:08:14", "throughput": 2199.68, "total_tokens": 344304} {"current_steps": 765, "total_steps": 3160, "loss": 0.0585, "lr": 0.0009400132887628885, "epoch": 4.841772151898734, "percentage": 24.21, "elapsed_time": "0:02:37", "remaining_time": "0:08:13", "throughput": 2200.95, "total_tokens": 346640} {"current_steps": 770, "total_steps": 3160, "loss": 0.0516, "lr": 0.0009386950341309545, "epoch": 4.8734177215189876, "percentage": 24.37, "elapsed_time": "0:02:38", "remaining_time": "0:08:11", "throughput": 2201.86, "total_tokens": 348880} {"current_steps": 775, "total_steps": 3160, "loss": 0.0503, "lr": 0.0009373633968470361, "epoch": 4.905063291139241, "percentage": 24.53, "elapsed_time": "0:02:39", "remaining_time": "0:08:10", "throughput": 2203.27, "total_tokens": 351248} {"current_steps": 780, "total_steps": 3160, "loss": 0.0874, "lr": 0.0009360184175335181, "epoch": 4.936708860759493, "percentage": 24.68, "elapsed_time": "0:02:40", "remaining_time": "0:08:09", "throughput": 2204.46, "total_tokens": 353552} {"current_steps": 785, "total_steps": 3160, "loss": 0.0494, "lr": 0.0009346601372197913, "epoch": 4.968354430379747, "percentage": 24.84, "elapsed_time": "0:02:41", "remaining_time": "0:08:08", "throughput": 2205.66, "total_tokens": 355888} {"current_steps": 790, "total_steps": 3160, "loss": 0.0227, "lr": 0.0009332885973410014, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:02:42", "remaining_time": "0:08:06", "throughput": 2205.41, "total_tokens": 357888} {"current_steps": 790, "total_steps": 3160, "eval_loss": 0.15590490400791168, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:02:43", "remaining_time": "0:08:11", "throughput": 2183.44, "total_tokens": 357888} {"current_steps": 795, "total_steps": 3160, "loss": 0.0124, "lr": 0.0009319038397367856, "epoch": 5.031645569620253, "percentage": 25.16, "elapsed_time": "0:02:45", "remaining_time": "0:08:13", "throughput": 2172.14, "total_tokens": 360096} {"current_steps": 800, "total_steps": 3160, "loss": 0.03, "lr": 0.0009305059066499948, "epoch": 5.063291139240507, "percentage": 25.32, "elapsed_time": "0:02:46", "remaining_time": "0:08:12", "throughput": 2173.07, "total_tokens": 362432} {"current_steps": 805, "total_steps": 3160, "loss": 0.0469, "lr": 0.0009290948407254065, "epoch": 5.094936708860759, "percentage": 25.47, "elapsed_time": "0:02:47", "remaining_time": "0:08:10", "throughput": 2174.43, "total_tokens": 364768} {"current_steps": 810, "total_steps": 3160, "loss": 0.015, "lr": 0.0009276706850084226, "epoch": 5.1265822784810124, "percentage": 25.63, "elapsed_time": "0:02:48", "remaining_time": "0:08:09", "throughput": 2175.27, "total_tokens": 366976} {"current_steps": 815, "total_steps": 3160, "loss": 0.0183, "lr": 0.0009262334829437575, "epoch": 5.158227848101266, "percentage": 25.79, "elapsed_time": "0:02:49", "remaining_time": "0:08:08", "throughput": 2176.09, "total_tokens": 369184} {"current_steps": 820, "total_steps": 3160, "loss": 0.0278, "lr": 0.0009247832783741119, "epoch": 5.189873417721519, "percentage": 25.95, "elapsed_time": "0:02:50", "remaining_time": "0:08:06", "throughput": 2177.06, "total_tokens": 371424} {"current_steps": 825, "total_steps": 3160, "loss": 0.0145, "lr": 0.0009233201155388354, "epoch": 5.2215189873417724, "percentage": 26.11, "elapsed_time": "0:02:51", "remaining_time": "0:08:05", "throughput": 2177.72, "total_tokens": 373600} {"current_steps": 830, "total_steps": 3160, "loss": 0.0197, "lr": 0.0009218440390725772, "epoch": 5.253164556962025, "percentage": 26.27, "elapsed_time": "0:02:52", "remaining_time": "0:08:04", "throughput": 2179.0, "total_tokens": 375904} {"current_steps": 835, "total_steps": 3160, "loss": 0.0325, "lr": 0.000920355094003925, "epoch": 5.284810126582278, "percentage": 26.42, "elapsed_time": "0:02:53", "remaining_time": "0:08:03", "throughput": 2180.48, "total_tokens": 378336} {"current_steps": 840, "total_steps": 3160, "loss": 0.0597, "lr": 0.0009188533257540302, "epoch": 5.3164556962025316, "percentage": 26.58, "elapsed_time": "0:02:54", "remaining_time": "0:08:01", "throughput": 2181.85, "total_tokens": 380672} {"current_steps": 845, "total_steps": 3160, "loss": 0.0407, "lr": 0.0009173387801352231, "epoch": 5.348101265822785, "percentage": 26.74, "elapsed_time": "0:02:55", "remaining_time": "0:08:00", "throughput": 2182.95, "total_tokens": 382976} {"current_steps": 850, "total_steps": 3160, "loss": 0.0627, "lr": 0.0009158115033496156, "epoch": 5.379746835443038, "percentage": 26.9, "elapsed_time": "0:02:56", "remaining_time": "0:07:59", "throughput": 2183.54, "total_tokens": 385152} {"current_steps": 855, "total_steps": 3160, "loss": 0.0325, "lr": 0.0009142715419876909, "epoch": 5.4113924050632916, "percentage": 27.06, "elapsed_time": "0:02:57", "remaining_time": "0:07:58", "throughput": 2184.79, "total_tokens": 387488} {"current_steps": 860, "total_steps": 3160, "loss": 0.0164, "lr": 0.0009127189430268832, "epoch": 5.443037974683544, "percentage": 27.22, "elapsed_time": "0:02:58", "remaining_time": "0:07:56", "throughput": 2185.53, "total_tokens": 389696} {"current_steps": 865, "total_steps": 3160, "loss": 0.0355, "lr": 0.0009111537538301435, "epoch": 5.474683544303797, "percentage": 27.37, "elapsed_time": "0:02:59", "remaining_time": "0:07:55", "throughput": 2186.71, "total_tokens": 392000} {"current_steps": 870, "total_steps": 3160, "loss": 0.0221, "lr": 0.0009095760221444959, "epoch": 5.506329113924051, "percentage": 27.53, "elapsed_time": "0:03:00", "remaining_time": "0:07:54", "throughput": 2187.58, "total_tokens": 394240} {"current_steps": 875, "total_steps": 3160, "loss": 0.0376, "lr": 0.0009079857960995805, "epoch": 5.537974683544304, "percentage": 27.69, "elapsed_time": "0:03:01", "remaining_time": "0:07:53", "throughput": 2188.53, "total_tokens": 396512} {"current_steps": 880, "total_steps": 3160, "loss": 0.0333, "lr": 0.000906383124206185, "epoch": 5.569620253164557, "percentage": 27.85, "elapsed_time": "0:03:02", "remaining_time": "0:07:51", "throughput": 2189.85, "total_tokens": 398880} {"current_steps": 885, "total_steps": 3160, "loss": 0.0306, "lr": 0.0009047680553547656, "epoch": 5.60126582278481, "percentage": 28.01, "elapsed_time": "0:03:03", "remaining_time": "0:07:50", "throughput": 2190.83, "total_tokens": 401184} {"current_steps": 890, "total_steps": 3160, "loss": 0.0125, "lr": 0.0009031406388139543, "epoch": 5.632911392405063, "percentage": 28.16, "elapsed_time": "0:03:04", "remaining_time": "0:07:49", "throughput": 2191.34, "total_tokens": 403360} {"current_steps": 895, "total_steps": 3160, "loss": 0.0636, "lr": 0.0009015009242290573, "epoch": 5.6645569620253164, "percentage": 28.32, "elapsed_time": "0:03:05", "remaining_time": "0:07:48", "throughput": 2192.64, "total_tokens": 405760} {"current_steps": 900, "total_steps": 3160, "loss": 0.0916, "lr": 0.0008998489616205395, "epoch": 5.69620253164557, "percentage": 28.48, "elapsed_time": "0:03:06", "remaining_time": "0:07:47", "throughput": 2193.64, "total_tokens": 408096} {"current_steps": 905, "total_steps": 3160, "loss": 0.0526, "lr": 0.0008981848013824993, "epoch": 5.727848101265823, "percentage": 28.64, "elapsed_time": "0:03:07", "remaining_time": "0:07:45", "throughput": 2194.63, "total_tokens": 410432} {"current_steps": 910, "total_steps": 3160, "loss": 0.0439, "lr": 0.0008965084942811311, "epoch": 5.759493670886076, "percentage": 28.8, "elapsed_time": "0:03:07", "remaining_time": "0:07:44", "throughput": 2195.12, "total_tokens": 412608} {"current_steps": 915, "total_steps": 3160, "loss": 0.0733, "lr": 0.0008948200914531761, "epoch": 5.791139240506329, "percentage": 28.96, "elapsed_time": "0:03:08", "remaining_time": "0:07:43", "throughput": 2195.61, "total_tokens": 414784} {"current_steps": 920, "total_steps": 3160, "loss": 0.0321, "lr": 0.0008931196444043635, "epoch": 5.822784810126582, "percentage": 29.11, "elapsed_time": "0:03:09", "remaining_time": "0:07:42", "throughput": 2196.39, "total_tokens": 417024} {"current_steps": 925, "total_steps": 3160, "loss": 0.0602, "lr": 0.0008914072050078376, "epoch": 5.8544303797468356, "percentage": 29.27, "elapsed_time": "0:03:10", "remaining_time": "0:07:41", "throughput": 2197.19, "total_tokens": 419296} {"current_steps": 930, "total_steps": 3160, "loss": 0.0796, "lr": 0.0008896828255025777, "epoch": 5.886075949367089, "percentage": 29.43, "elapsed_time": "0:03:11", "remaining_time": "0:07:39", "throughput": 2197.81, "total_tokens": 421504} {"current_steps": 935, "total_steps": 3160, "loss": 0.0227, "lr": 0.000887946558491802, "epoch": 5.917721518987342, "percentage": 29.59, "elapsed_time": "0:03:12", "remaining_time": "0:07:38", "throughput": 2198.43, "total_tokens": 423712} {"current_steps": 940, "total_steps": 3160, "loss": 0.014, "lr": 0.0008861984569413646, "epoch": 5.949367088607595, "percentage": 29.75, "elapsed_time": "0:03:13", "remaining_time": "0:07:37", "throughput": 2199.46, "total_tokens": 426016} {"current_steps": 945, "total_steps": 3160, "loss": 0.0387, "lr": 0.0008844385741781394, "epoch": 5.981012658227848, "percentage": 29.91, "elapsed_time": "0:03:14", "remaining_time": "0:07:36", "throughput": 2200.5, "total_tokens": 428352} {"current_steps": 948, "total_steps": 3160, "eval_loss": 0.1550048142671585, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "0:03:16", "remaining_time": "0:07:39", "throughput": 2181.77, "total_tokens": 429456} {"current_steps": 950, "total_steps": 3160, "loss": 0.0337, "lr": 0.0008826669638883927, "epoch": 6.012658227848101, "percentage": 30.06, "elapsed_time": "0:03:18", "remaining_time": "0:07:40", "throughput": 2172.47, "total_tokens": 430416} {"current_steps": 955, "total_steps": 3160, "loss": 0.027, "lr": 0.0008808836801161464, "epoch": 6.044303797468355, "percentage": 30.22, "elapsed_time": "0:03:19", "remaining_time": "0:07:39", "throughput": 2173.19, "total_tokens": 432624} {"current_steps": 960, "total_steps": 3160, "loss": 0.0342, "lr": 0.0008790887772615288, "epoch": 6.075949367088608, "percentage": 30.38, "elapsed_time": "0:03:20", "remaining_time": "0:07:38", "throughput": 2174.27, "total_tokens": 434960} {"current_steps": 965, "total_steps": 3160, "loss": 0.0166, "lr": 0.0008772823100791151, "epoch": 6.1075949367088604, "percentage": 30.54, "elapsed_time": "0:03:21", "remaining_time": "0:07:37", "throughput": 2175.09, "total_tokens": 437200} {"current_steps": 970, "total_steps": 3160, "loss": 0.0098, "lr": 0.0008754643336762571, "epoch": 6.139240506329114, "percentage": 30.7, "elapsed_time": "0:03:21", "remaining_time": "0:07:35", "throughput": 2175.66, "total_tokens": 439376} {"current_steps": 975, "total_steps": 3160, "loss": 0.0428, "lr": 0.0008736349035114024, "epoch": 6.170886075949367, "percentage": 30.85, "elapsed_time": "0:03:22", "remaining_time": "0:07:34", "throughput": 2176.8, "total_tokens": 441744} {"current_steps": 980, "total_steps": 3160, "loss": 0.0274, "lr": 0.0008717940753924023, "epoch": 6.2025316455696204, "percentage": 31.01, "elapsed_time": "0:03:23", "remaining_time": "0:07:33", "throughput": 2177.44, "total_tokens": 443952} {"current_steps": 985, "total_steps": 3160, "loss": 0.0172, "lr": 0.0008699419054748092, "epoch": 6.234177215189874, "percentage": 31.17, "elapsed_time": "0:03:24", "remaining_time": "0:07:32", "throughput": 2178.51, "total_tokens": 446256} {"current_steps": 990, "total_steps": 3160, "loss": 0.0447, "lr": 0.0008680784502601644, "epoch": 6.265822784810126, "percentage": 31.33, "elapsed_time": "0:03:25", "remaining_time": "0:07:31", "throughput": 2179.47, "total_tokens": 448560} {"current_steps": 995, "total_steps": 3160, "loss": 0.0648, "lr": 0.0008662037665942733, "epoch": 6.2974683544303796, "percentage": 31.49, "elapsed_time": "0:03:26", "remaining_time": "0:07:29", "throughput": 2179.58, "total_tokens": 450640} {"current_steps": 1000, "total_steps": 3160, "loss": 0.0392, "lr": 0.0008643179116654719, "epoch": 6.329113924050633, "percentage": 31.65, "elapsed_time": "0:03:27", "remaining_time": "0:07:28", "throughput": 2180.48, "total_tokens": 452912} {"current_steps": 1005, "total_steps": 3160, "loss": 0.0394, "lr": 0.0008624209430028826, "epoch": 6.360759493670886, "percentage": 31.8, "elapsed_time": "0:03:28", "remaining_time": "0:07:27", "throughput": 2181.66, "total_tokens": 455280} {"current_steps": 1010, "total_steps": 3160, "loss": 0.035, "lr": 0.0008605129184746585, "epoch": 6.3924050632911396, "percentage": 31.96, "elapsed_time": "0:03:29", "remaining_time": "0:07:26", "throughput": 2182.68, "total_tokens": 457584} {"current_steps": 1015, "total_steps": 3160, "loss": 0.06, "lr": 0.0008585938962862184, "epoch": 6.424050632911392, "percentage": 32.12, "elapsed_time": "0:03:30", "remaining_time": "0:07:25", "throughput": 2183.31, "total_tokens": 459792} {"current_steps": 1020, "total_steps": 3160, "loss": 0.0287, "lr": 0.0008566639349784715, "epoch": 6.455696202531645, "percentage": 32.28, "elapsed_time": "0:03:31", "remaining_time": "0:07:23", "throughput": 2184.08, "total_tokens": 462064} {"current_steps": 1025, "total_steps": 3160, "loss": 0.0474, "lr": 0.0008547230934260312, "epoch": 6.487341772151899, "percentage": 32.44, "elapsed_time": "0:03:32", "remaining_time": "0:07:22", "throughput": 2184.67, "total_tokens": 464272} {"current_steps": 1030, "total_steps": 3160, "loss": 0.0214, "lr": 0.0008527714308354191, "epoch": 6.518987341772152, "percentage": 32.59, "elapsed_time": "0:03:33", "remaining_time": "0:07:21", "throughput": 2185.79, "total_tokens": 466640} {"current_steps": 1035, "total_steps": 3160, "loss": 0.0205, "lr": 0.0008508090067432591, "epoch": 6.550632911392405, "percentage": 32.75, "elapsed_time": "0:03:34", "remaining_time": "0:07:20", "throughput": 2186.29, "total_tokens": 468848} {"current_steps": 1040, "total_steps": 3160, "loss": 0.0179, "lr": 0.000848835881014461, "epoch": 6.582278481012658, "percentage": 32.91, "elapsed_time": "0:03:35", "remaining_time": "0:07:19", "throughput": 2187.52, "total_tokens": 471216} {"current_steps": 1045, "total_steps": 3160, "loss": 0.0185, "lr": 0.0008468521138403945, "epoch": 6.613924050632911, "percentage": 33.07, "elapsed_time": "0:03:36", "remaining_time": "0:07:17", "throughput": 2188.41, "total_tokens": 473552} {"current_steps": 1050, "total_steps": 3160, "loss": 0.0362, "lr": 0.0008448577657370528, "epoch": 6.6455696202531644, "percentage": 33.23, "elapsed_time": "0:03:37", "remaining_time": "0:07:16", "throughput": 2189.12, "total_tokens": 475792} {"current_steps": 1055, "total_steps": 3160, "loss": 0.0297, "lr": 0.0008428528975432066, "epoch": 6.677215189873418, "percentage": 33.39, "elapsed_time": "0:03:38", "remaining_time": "0:07:15", "throughput": 2190.06, "total_tokens": 478096} {"current_steps": 1060, "total_steps": 3160, "loss": 0.0233, "lr": 0.0008408375704185482, "epoch": 6.708860759493671, "percentage": 33.54, "elapsed_time": "0:03:39", "remaining_time": "0:07:14", "throughput": 2190.99, "total_tokens": 480400} {"current_steps": 1065, "total_steps": 3160, "loss": 0.0372, "lr": 0.0008388118458418259, "epoch": 6.740506329113924, "percentage": 33.7, "elapsed_time": "0:03:40", "remaining_time": "0:07:13", "throughput": 2191.81, "total_tokens": 482704} {"current_steps": 1070, "total_steps": 3160, "loss": 0.0393, "lr": 0.0008367757856089684, "epoch": 6.772151898734177, "percentage": 33.86, "elapsed_time": "0:03:41", "remaining_time": "0:07:12", "throughput": 2192.14, "total_tokens": 484848} {"current_steps": 1075, "total_steps": 3160, "loss": 0.031, "lr": 0.0008347294518311994, "epoch": 6.80379746835443, "percentage": 34.02, "elapsed_time": "0:03:42", "remaining_time": "0:07:10", "throughput": 2192.96, "total_tokens": 487152} {"current_steps": 1080, "total_steps": 3160, "loss": 0.0113, "lr": 0.0008326729069331436, "epoch": 6.8354430379746836, "percentage": 34.18, "elapsed_time": "0:03:43", "remaining_time": "0:07:09", "throughput": 2193.41, "total_tokens": 489360} {"current_steps": 1085, "total_steps": 3160, "loss": 0.0312, "lr": 0.0008306062136509219, "epoch": 6.867088607594937, "percentage": 34.34, "elapsed_time": "0:03:44", "remaining_time": "0:07:08", "throughput": 2194.21, "total_tokens": 491664} {"current_steps": 1090, "total_steps": 3160, "loss": 0.0686, "lr": 0.0008285294350302375, "epoch": 6.89873417721519, "percentage": 34.49, "elapsed_time": "0:03:45", "remaining_time": "0:07:07", "throughput": 2195.0, "total_tokens": 493968} {"current_steps": 1095, "total_steps": 3160, "loss": 0.0443, "lr": 0.0008264426344244527, "epoch": 6.930379746835443, "percentage": 34.65, "elapsed_time": "0:03:46", "remaining_time": "0:07:06", "throughput": 2195.88, "total_tokens": 496272} {"current_steps": 1100, "total_steps": 3160, "loss": 0.0376, "lr": 0.000824345875492657, "epoch": 6.962025316455696, "percentage": 34.81, "elapsed_time": "0:03:46", "remaining_time": "0:07:05", "throughput": 2196.65, "total_tokens": 498576} {"current_steps": 1105, "total_steps": 3160, "loss": 0.0222, "lr": 0.000822239222197724, "epoch": 6.993670886075949, "percentage": 34.97, "elapsed_time": "0:03:47", "remaining_time": "0:07:03", "throughput": 2197.45, "total_tokens": 500912} {"current_steps": 1106, "total_steps": 3160, "eval_loss": 0.15802980959415436, "epoch": 7.0, "percentage": 35.0, "elapsed_time": "0:03:49", "remaining_time": "0:07:06", "throughput": 2181.25, "total_tokens": 501136} {"current_steps": 1110, "total_steps": 3160, "loss": 0.0145, "lr": 0.0008201227388043606, "epoch": 7.025316455696203, "percentage": 35.13, "elapsed_time": "0:03:51", "remaining_time": "0:07:07", "throughput": 2173.36, "total_tokens": 502928} {"current_steps": 1115, "total_steps": 3160, "loss": 0.0199, "lr": 0.0008179964898771472, "epoch": 7.056962025316456, "percentage": 35.28, "elapsed_time": "0:03:52", "remaining_time": "0:07:06", "throughput": 2173.69, "total_tokens": 505232} {"current_steps": 1120, "total_steps": 3160, "loss": 0.0394, "lr": 0.0008158605402785673, "epoch": 7.0886075949367084, "percentage": 35.44, "elapsed_time": "0:03:53", "remaining_time": "0:07:05", "throughput": 2174.18, "total_tokens": 507408} {"current_steps": 1125, "total_steps": 3160, "loss": 0.048, "lr": 0.000813714955167029, "epoch": 7.120253164556962, "percentage": 35.6, "elapsed_time": "0:03:54", "remaining_time": "0:07:03", "throughput": 2175.02, "total_tokens": 509680} {"current_steps": 1130, "total_steps": 3160, "loss": 0.0122, "lr": 0.0008115597999948779, "epoch": 7.151898734177215, "percentage": 35.76, "elapsed_time": "0:03:55", "remaining_time": "0:07:02", "throughput": 2175.72, "total_tokens": 511920} {"current_steps": 1135, "total_steps": 3160, "loss": 0.0181, "lr": 0.000809395140506399, "epoch": 7.1835443037974684, "percentage": 35.92, "elapsed_time": "0:03:56", "remaining_time": "0:07:01", "throughput": 2176.69, "total_tokens": 514256} {"current_steps": 1140, "total_steps": 3160, "loss": 0.0263, "lr": 0.0008072210427358138, "epoch": 7.215189873417722, "percentage": 36.08, "elapsed_time": "0:03:57", "remaining_time": "0:07:00", "throughput": 2177.51, "total_tokens": 516560} {"current_steps": 1145, "total_steps": 3160, "loss": 0.0184, "lr": 0.0008050375730052621, "epoch": 7.246835443037975, "percentage": 36.23, "elapsed_time": "0:03:58", "remaining_time": "0:06:59", "throughput": 2178.32, "total_tokens": 518864} {"current_steps": 1150, "total_steps": 3160, "loss": 0.0106, "lr": 0.0008028447979227828, "epoch": 7.2784810126582276, "percentage": 36.39, "elapsed_time": "0:03:59", "remaining_time": "0:06:58", "throughput": 2179.36, "total_tokens": 521232} {"current_steps": 1155, "total_steps": 3160, "loss": 0.0263, "lr": 0.0008006427843802786, "epoch": 7.310126582278481, "percentage": 36.55, "elapsed_time": "0:04:00", "remaining_time": "0:06:56", "throughput": 2180.24, "total_tokens": 523536} {"current_steps": 1160, "total_steps": 3160, "loss": 0.0157, "lr": 0.0007984315995514777, "epoch": 7.341772151898734, "percentage": 36.71, "elapsed_time": "0:04:01", "remaining_time": "0:06:55", "throughput": 2181.05, "total_tokens": 525840} {"current_steps": 1165, "total_steps": 3160, "loss": 0.0123, "lr": 0.0007962113108898838, "epoch": 7.3734177215189876, "percentage": 36.87, "elapsed_time": "0:04:02", "remaining_time": "0:06:54", "throughput": 2181.84, "total_tokens": 528144} {"current_steps": 1170, "total_steps": 3160, "loss": 0.0146, "lr": 0.0007939819861267182, "epoch": 7.405063291139241, "percentage": 37.03, "elapsed_time": "0:04:03", "remaining_time": "0:06:53", "throughput": 2182.28, "total_tokens": 530320} {"current_steps": 1175, "total_steps": 3160, "loss": 0.0371, "lr": 0.0007917436932688538, "epoch": 7.436708860759493, "percentage": 37.18, "elapsed_time": "0:04:03", "remaining_time": "0:06:52", "throughput": 2183.05, "total_tokens": 532592} {"current_steps": 1180, "total_steps": 3160, "loss": 0.0172, "lr": 0.0007894965005967404, "epoch": 7.468354430379747, "percentage": 37.34, "elapsed_time": "0:04:04", "remaining_time": "0:06:51", "throughput": 2183.95, "total_tokens": 534960} {"current_steps": 1185, "total_steps": 3160, "loss": 0.034, "lr": 0.0007872404766623225, "epoch": 7.5, "percentage": 37.5, "elapsed_time": "0:04:05", "remaining_time": "0:06:49", "throughput": 2184.69, "total_tokens": 537232} {"current_steps": 1190, "total_steps": 3160, "loss": 0.0342, "lr": 0.000784975690286947, "epoch": 7.531645569620253, "percentage": 37.66, "elapsed_time": "0:04:06", "remaining_time": "0:06:48", "throughput": 2185.43, "total_tokens": 539504} {"current_steps": 1195, "total_steps": 3160, "loss": 0.009, "lr": 0.0007827022105592645, "epoch": 7.563291139240507, "percentage": 37.82, "elapsed_time": "0:04:07", "remaining_time": "0:06:47", "throughput": 2185.85, "total_tokens": 541680} {"current_steps": 1200, "total_steps": 3160, "loss": 0.0166, "lr": 0.0007804201068331211, "epoch": 7.594936708860759, "percentage": 37.97, "elapsed_time": "0:04:08", "remaining_time": "0:06:46", "throughput": 2186.63, "total_tokens": 543984} {"current_steps": 1205, "total_steps": 3160, "loss": 0.0368, "lr": 0.0007781294487254435, "epoch": 7.6265822784810124, "percentage": 38.13, "elapsed_time": "0:04:09", "remaining_time": "0:06:45", "throughput": 2187.25, "total_tokens": 546224} {"current_steps": 1210, "total_steps": 3160, "loss": 0.0279, "lr": 0.0007758303061141148, "epoch": 7.658227848101266, "percentage": 38.29, "elapsed_time": "0:04:10", "remaining_time": "0:06:43", "throughput": 2187.97, "total_tokens": 548496} {"current_steps": 1215, "total_steps": 3160, "loss": 0.0188, "lr": 0.0007735227491358426, "epoch": 7.689873417721519, "percentage": 38.45, "elapsed_time": "0:04:11", "remaining_time": "0:06:42", "throughput": 2188.49, "total_tokens": 550704} {"current_steps": 1220, "total_steps": 3160, "loss": 0.0415, "lr": 0.0007712068481840198, "epoch": 7.7215189873417724, "percentage": 38.61, "elapsed_time": "0:04:12", "remaining_time": "0:06:41", "throughput": 2189.13, "total_tokens": 552976} {"current_steps": 1225, "total_steps": 3160, "loss": 0.047, "lr": 0.0007688826739065777, "epoch": 7.753164556962025, "percentage": 38.77, "elapsed_time": "0:04:13", "remaining_time": "0:06:40", "throughput": 2189.98, "total_tokens": 555312} {"current_steps": 1230, "total_steps": 3160, "loss": 0.0235, "lr": 0.00076655029720383, "epoch": 7.784810126582278, "percentage": 38.92, "elapsed_time": "0:04:14", "remaining_time": "0:06:39", "throughput": 2190.83, "total_tokens": 557680} {"current_steps": 1235, "total_steps": 3160, "loss": 0.0196, "lr": 0.0007642097892263098, "epoch": 7.8164556962025316, "percentage": 39.08, "elapsed_time": "0:04:15", "remaining_time": "0:06:38", "throughput": 2191.55, "total_tokens": 559984} {"current_steps": 1240, "total_steps": 3160, "loss": 0.0259, "lr": 0.0007618612213726, "epoch": 7.848101265822785, "percentage": 39.24, "elapsed_time": "0:04:16", "remaining_time": "0:06:37", "throughput": 2192.25, "total_tokens": 562256} {"current_steps": 1245, "total_steps": 3160, "loss": 0.0349, "lr": 0.0007595046652871552, "epoch": 7.879746835443038, "percentage": 39.4, "elapsed_time": "0:04:17", "remaining_time": "0:06:35", "throughput": 2192.96, "total_tokens": 564560} {"current_steps": 1250, "total_steps": 3160, "loss": 0.0289, "lr": 0.0007571401928581145, "epoch": 7.911392405063291, "percentage": 39.56, "elapsed_time": "0:04:18", "remaining_time": "0:06:34", "throughput": 2193.77, "total_tokens": 566896} {"current_steps": 1255, "total_steps": 3160, "loss": 0.0146, "lr": 0.0007547678762151109, "epoch": 7.943037974683544, "percentage": 39.72, "elapsed_time": "0:04:19", "remaining_time": "0:06:33", "throughput": 2194.54, "total_tokens": 569200} {"current_steps": 1260, "total_steps": 3160, "loss": 0.0233, "lr": 0.0007523877877270695, "epoch": 7.974683544303797, "percentage": 39.87, "elapsed_time": "0:04:20", "remaining_time": "0:06:32", "throughput": 2195.34, "total_tokens": 571536} {"current_steps": 1264, "total_steps": 3160, "eval_loss": 0.19430989027023315, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "0:04:22", "remaining_time": "0:06:34", "throughput": 2181.53, "total_tokens": 573104} {"current_steps": 1265, "total_steps": 3160, "loss": 0.0227, "lr": 0.00075, "epoch": 8.00632911392405, "percentage": 40.03, "elapsed_time": "0:04:23", "remaining_time": "0:06:35", "throughput": 2174.01, "total_tokens": 573616} {"current_steps": 1270, "total_steps": 3160, "loss": 0.008, "lr": 0.000747604585874782, "epoch": 8.037974683544304, "percentage": 40.19, "elapsed_time": "0:04:24", "remaining_time": "0:06:34", "throughput": 2173.97, "total_tokens": 575824} {"current_steps": 1275, "total_steps": 3160, "loss": 0.0146, "lr": 0.0007452016184249428, "epoch": 8.069620253164556, "percentage": 40.35, "elapsed_time": "0:04:25", "remaining_time": "0:06:32", "throughput": 2174.51, "total_tokens": 578032} {"current_steps": 1280, "total_steps": 3160, "loss": 0.0107, "lr": 0.0007427911709544287, "epoch": 8.10126582278481, "percentage": 40.51, "elapsed_time": "0:04:26", "remaining_time": "0:06:31", "throughput": 2175.66, "total_tokens": 580464} {"current_steps": 1285, "total_steps": 3160, "loss": 0.0169, "lr": 0.0007403733169953678, "epoch": 8.132911392405063, "percentage": 40.66, "elapsed_time": "0:04:27", "remaining_time": "0:06:30", "throughput": 2176.08, "total_tokens": 582640} {"current_steps": 1290, "total_steps": 3160, "loss": 0.0252, "lr": 0.0007379481303058282, "epoch": 8.164556962025316, "percentage": 40.82, "elapsed_time": "0:04:28", "remaining_time": "0:06:29", "throughput": 2176.92, "total_tokens": 584976} {"current_steps": 1295, "total_steps": 3160, "loss": 0.0095, "lr": 0.000735515684867567, "epoch": 8.19620253164557, "percentage": 40.98, "elapsed_time": "0:04:29", "remaining_time": "0:06:28", "throughput": 2177.23, "total_tokens": 587120} {"current_steps": 1300, "total_steps": 3160, "loss": 0.0242, "lr": 0.0007330760548837738, "epoch": 8.227848101265822, "percentage": 41.14, "elapsed_time": "0:04:30", "remaining_time": "0:06:27", "throughput": 2177.94, "total_tokens": 589392} {"current_steps": 1305, "total_steps": 3160, "loss": 0.0257, "lr": 0.0007306293147768067, "epoch": 8.259493670886076, "percentage": 41.3, "elapsed_time": "0:04:31", "remaining_time": "0:06:26", "throughput": 2178.54, "total_tokens": 591632} {"current_steps": 1310, "total_steps": 3160, "loss": 0.021, "lr": 0.0007281755391859229, "epoch": 8.291139240506329, "percentage": 41.46, "elapsed_time": "0:04:32", "remaining_time": "0:06:24", "throughput": 2179.44, "total_tokens": 594000} {"current_steps": 1315, "total_steps": 3160, "loss": 0.0117, "lr": 0.0007257148029650007, "epoch": 8.322784810126583, "percentage": 41.61, "elapsed_time": "0:04:33", "remaining_time": "0:06:23", "throughput": 2180.34, "total_tokens": 596368} {"current_steps": 1320, "total_steps": 3160, "loss": 0.0103, "lr": 0.0007232471811802568, "epoch": 8.354430379746836, "percentage": 41.77, "elapsed_time": "0:04:34", "remaining_time": "0:06:22", "throughput": 2181.13, "total_tokens": 598672} {"current_steps": 1325, "total_steps": 3160, "loss": 0.0123, "lr": 0.000720772749107956, "epoch": 8.386075949367088, "percentage": 41.93, "elapsed_time": "0:04:35", "remaining_time": "0:06:21", "throughput": 2182.11, "total_tokens": 601040} {"current_steps": 1330, "total_steps": 3160, "loss": 0.0234, "lr": 0.000718291582232115, "epoch": 8.417721518987342, "percentage": 42.09, "elapsed_time": "0:04:36", "remaining_time": "0:06:20", "throughput": 2182.79, "total_tokens": 603344} {"current_steps": 1335, "total_steps": 3160, "loss": 0.0188, "lr": 0.0007158037562421997, "epoch": 8.449367088607595, "percentage": 42.25, "elapsed_time": "0:04:37", "remaining_time": "0:06:19", "throughput": 2183.19, "total_tokens": 605552} {"current_steps": 1340, "total_steps": 3160, "loss": 0.0198, "lr": 0.0007133093470308164, "epoch": 8.481012658227849, "percentage": 42.41, "elapsed_time": "0:04:38", "remaining_time": "0:06:18", "throughput": 2183.66, "total_tokens": 607760} {"current_steps": 1345, "total_steps": 3160, "loss": 0.0119, "lr": 0.0007108084306913959, "epoch": 8.512658227848101, "percentage": 42.56, "elapsed_time": "0:04:39", "remaining_time": "0:06:16", "throughput": 2184.64, "total_tokens": 610192} {"current_steps": 1350, "total_steps": 3160, "loss": 0.0216, "lr": 0.0007083010835158732, "epoch": 8.544303797468354, "percentage": 42.72, "elapsed_time": "0:04:40", "remaining_time": "0:06:15", "throughput": 2185.4, "total_tokens": 612528} {"current_steps": 1355, "total_steps": 3160, "loss": 0.0113, "lr": 0.0007057873819923602, "epoch": 8.575949367088608, "percentage": 42.88, "elapsed_time": "0:04:41", "remaining_time": "0:06:14", "throughput": 2185.96, "total_tokens": 614768} {"current_steps": 1360, "total_steps": 3160, "loss": 0.0331, "lr": 0.0007032674028028109, "epoch": 8.60759493670886, "percentage": 43.04, "elapsed_time": "0:04:42", "remaining_time": "0:06:13", "throughput": 2186.23, "total_tokens": 616912} {"current_steps": 1365, "total_steps": 3160, "loss": 0.0029, "lr": 0.000700741222820684, "epoch": 8.639240506329115, "percentage": 43.2, "elapsed_time": "0:04:43", "remaining_time": "0:06:12", "throughput": 2186.58, "total_tokens": 619088} {"current_steps": 1370, "total_steps": 3160, "loss": 0.0327, "lr": 0.000698208919108597, "epoch": 8.670886075949367, "percentage": 43.35, "elapsed_time": "0:04:44", "remaining_time": "0:06:11", "throughput": 2187.13, "total_tokens": 621328} {"current_steps": 1375, "total_steps": 3160, "loss": 0.0105, "lr": 0.0006956705689159751, "epoch": 8.70253164556962, "percentage": 43.51, "elapsed_time": "0:04:45", "remaining_time": "0:06:10", "throughput": 2187.57, "total_tokens": 623536} {"current_steps": 1380, "total_steps": 3160, "loss": 0.0212, "lr": 0.0006931262496766954, "epoch": 8.734177215189874, "percentage": 43.67, "elapsed_time": "0:04:45", "remaining_time": "0:06:08", "throughput": 2187.93, "total_tokens": 625744} {"current_steps": 1385, "total_steps": 3160, "loss": 0.0174, "lr": 0.0006905760390067235, "epoch": 8.765822784810126, "percentage": 43.83, "elapsed_time": "0:04:46", "remaining_time": "0:06:07", "throughput": 2188.76, "total_tokens": 628144} {"current_steps": 1390, "total_steps": 3160, "loss": 0.0109, "lr": 0.0006880200147017476, "epoch": 8.79746835443038, "percentage": 43.99, "elapsed_time": "0:04:47", "remaining_time": "0:06:06", "throughput": 2189.41, "total_tokens": 630448} {"current_steps": 1395, "total_steps": 3160, "loss": 0.0095, "lr": 0.0006854582547348037, "epoch": 8.829113924050633, "percentage": 44.15, "elapsed_time": "0:04:48", "remaining_time": "0:06:05", "throughput": 2190.04, "total_tokens": 632720} {"current_steps": 1400, "total_steps": 3160, "loss": 0.041, "lr": 0.0006828908372538977, "epoch": 8.860759493670885, "percentage": 44.3, "elapsed_time": "0:04:49", "remaining_time": "0:06:04", "throughput": 2190.55, "total_tokens": 634960} {"current_steps": 1405, "total_steps": 3160, "loss": 0.0247, "lr": 0.0006803178405796214, "epoch": 8.89240506329114, "percentage": 44.46, "elapsed_time": "0:04:50", "remaining_time": "0:06:03", "throughput": 2191.35, "total_tokens": 637328} {"current_steps": 1410, "total_steps": 3160, "loss": 0.011, "lr": 0.0006777393432027626, "epoch": 8.924050632911392, "percentage": 44.62, "elapsed_time": "0:04:51", "remaining_time": "0:06:02", "throughput": 2191.94, "total_tokens": 639600} {"current_steps": 1415, "total_steps": 3160, "loss": 0.0294, "lr": 0.0006751554237819122, "epoch": 8.955696202531646, "percentage": 44.78, "elapsed_time": "0:04:52", "remaining_time": "0:06:01", "throughput": 2192.37, "total_tokens": 641808} {"current_steps": 1420, "total_steps": 3160, "loss": 0.0281, "lr": 0.0006725661611410633, "epoch": 8.987341772151899, "percentage": 44.94, "elapsed_time": "0:04:53", "remaining_time": "0:05:59", "throughput": 2192.97, "total_tokens": 644080} {"current_steps": 1422, "total_steps": 3160, "eval_loss": 0.2004173845052719, "epoch": 9.0, "percentage": 45.0, "elapsed_time": "0:04:55", "remaining_time": "0:06:01", "throughput": 2180.48, "total_tokens": 644752} {"current_steps": 1425, "total_steps": 3160, "loss": 0.0135, "lr": 0.0006699716342672071, "epoch": 9.018987341772151, "percentage": 45.09, "elapsed_time": "0:04:57", "remaining_time": "0:06:01", "throughput": 2174.27, "total_tokens": 646128} {"current_steps": 1430, "total_steps": 3160, "loss": 0.0054, "lr": 0.0006673719223079233, "epoch": 9.050632911392405, "percentage": 45.25, "elapsed_time": "0:04:58", "remaining_time": "0:06:00", "throughput": 2174.61, "total_tokens": 648336} {"current_steps": 1435, "total_steps": 3160, "loss": 0.0229, "lr": 0.000664767104568966, "epoch": 9.082278481012658, "percentage": 45.41, "elapsed_time": "0:04:59", "remaining_time": "0:05:59", "throughput": 2175.27, "total_tokens": 650640} {"current_steps": 1440, "total_steps": 3160, "loss": 0.0075, "lr": 0.0006621572605118438, "epoch": 9.113924050632912, "percentage": 45.57, "elapsed_time": "0:05:00", "remaining_time": "0:05:58", "throughput": 2173.12, "total_tokens": 652880} {"current_steps": 1445, "total_steps": 3160, "loss": 0.0067, "lr": 0.0006595424697513964, "epoch": 9.145569620253164, "percentage": 45.73, "elapsed_time": "0:05:01", "remaining_time": "0:05:57", "throughput": 2173.49, "total_tokens": 655056} {"current_steps": 1450, "total_steps": 3160, "loss": 0.0147, "lr": 0.000656922812053365, "epoch": 9.177215189873417, "percentage": 45.89, "elapsed_time": "0:05:02", "remaining_time": "0:05:56", "throughput": 2174.07, "total_tokens": 657328} {"current_steps": 1455, "total_steps": 3160, "loss": 0.0103, "lr": 0.0006542983673319606, "epoch": 9.208860759493671, "percentage": 46.04, "elapsed_time": "0:05:03", "remaining_time": "0:05:55", "throughput": 2174.73, "total_tokens": 659632} {"current_steps": 1460, "total_steps": 3160, "loss": 0.0056, "lr": 0.0006516692156474243, "epoch": 9.240506329113924, "percentage": 46.2, "elapsed_time": "0:05:04", "remaining_time": "0:05:54", "throughput": 2175.49, "total_tokens": 662000} {"current_steps": 1465, "total_steps": 3160, "loss": 0.0252, "lr": 0.0006490354372035864, "epoch": 9.272151898734178, "percentage": 46.36, "elapsed_time": "0:05:05", "remaining_time": "0:05:53", "throughput": 2175.95, "total_tokens": 664208} {"current_steps": 1470, "total_steps": 3160, "loss": 0.0103, "lr": 0.000646397112345419, "epoch": 9.30379746835443, "percentage": 46.52, "elapsed_time": "0:05:06", "remaining_time": "0:05:52", "throughput": 2176.95, "total_tokens": 666672} {"current_steps": 1475, "total_steps": 3160, "loss": 0.0121, "lr": 0.0006437543215565858, "epoch": 9.335443037974684, "percentage": 46.68, "elapsed_time": "0:05:07", "remaining_time": "0:05:50", "throughput": 2177.58, "total_tokens": 668944} {"current_steps": 1480, "total_steps": 3160, "loss": 0.0235, "lr": 0.0006411071454569854, "epoch": 9.367088607594937, "percentage": 46.84, "elapsed_time": "0:05:08", "remaining_time": "0:05:49", "throughput": 2178.13, "total_tokens": 671216} {"current_steps": 1485, "total_steps": 3160, "loss": 0.0274, "lr": 0.0006384556648002934, "epoch": 9.39873417721519, "percentage": 46.99, "elapsed_time": "0:05:09", "remaining_time": "0:05:48", "throughput": 2178.57, "total_tokens": 673424} {"current_steps": 1490, "total_steps": 3160, "loss": 0.0049, "lr": 0.0006357999604714987, "epoch": 9.430379746835444, "percentage": 47.15, "elapsed_time": "0:05:10", "remaining_time": "0:05:47", "throughput": 2178.92, "total_tokens": 675600} {"current_steps": 1495, "total_steps": 3160, "loss": 0.0133, "lr": 0.0006331401134844356, "epoch": 9.462025316455696, "percentage": 47.31, "elapsed_time": "0:05:11", "remaining_time": "0:05:46", "throughput": 2179.53, "total_tokens": 677872} {"current_steps": 1500, "total_steps": 3160, "loss": 0.025, "lr": 0.0006304762049793126, "epoch": 9.49367088607595, "percentage": 47.47, "elapsed_time": "0:05:11", "remaining_time": "0:05:45", "throughput": 2179.96, "total_tokens": 680080} {"current_steps": 1505, "total_steps": 3160, "loss": 0.0117, "lr": 0.0006278083162202374, "epoch": 9.525316455696203, "percentage": 47.63, "elapsed_time": "0:05:12", "remaining_time": "0:05:44", "throughput": 2180.41, "total_tokens": 682288} {"current_steps": 1510, "total_steps": 3160, "loss": 0.0113, "lr": 0.0006251365285927373, "epoch": 9.556962025316455, "percentage": 47.78, "elapsed_time": "0:05:13", "remaining_time": "0:05:42", "throughput": 2181.19, "total_tokens": 684656} {"current_steps": 1515, "total_steps": 3160, "loss": 0.0107, "lr": 0.0006224609236012774, "epoch": 9.58860759493671, "percentage": 47.94, "elapsed_time": "0:05:14", "remaining_time": "0:05:41", "throughput": 2181.64, "total_tokens": 686896} {"current_steps": 1520, "total_steps": 3160, "loss": 0.0081, "lr": 0.0006197815828667734, "epoch": 9.620253164556962, "percentage": 48.1, "elapsed_time": "0:05:15", "remaining_time": "0:05:40", "throughput": 2182.05, "total_tokens": 689104} {"current_steps": 1525, "total_steps": 3160, "loss": 0.0217, "lr": 0.0006170985881241021, "epoch": 9.651898734177216, "percentage": 48.26, "elapsed_time": "0:05:16", "remaining_time": "0:05:39", "throughput": 2182.57, "total_tokens": 691376} {"current_steps": 1530, "total_steps": 3160, "loss": 0.0131, "lr": 0.0006144120212196084, "epoch": 9.683544303797468, "percentage": 48.42, "elapsed_time": "0:05:17", "remaining_time": "0:05:38", "throughput": 2183.34, "total_tokens": 693744} {"current_steps": 1535, "total_steps": 3160, "loss": 0.0036, "lr": 0.0006117219641086072, "epoch": 9.715189873417721, "percentage": 48.58, "elapsed_time": "0:05:18", "remaining_time": "0:05:37", "throughput": 2183.83, "total_tokens": 695984} {"current_steps": 1540, "total_steps": 3160, "loss": 0.0134, "lr": 0.0006090284988528853, "epoch": 9.746835443037975, "percentage": 48.73, "elapsed_time": "0:05:19", "remaining_time": "0:05:36", "throughput": 2184.16, "total_tokens": 698160} {"current_steps": 1545, "total_steps": 3160, "loss": 0.0128, "lr": 0.0006063317076181961, "epoch": 9.778481012658228, "percentage": 48.89, "elapsed_time": "0:05:20", "remaining_time": "0:05:35", "throughput": 2184.84, "total_tokens": 700496} {"current_steps": 1550, "total_steps": 3160, "loss": 0.0209, "lr": 0.0006036316726717545, "epoch": 9.810126582278482, "percentage": 49.05, "elapsed_time": "0:05:21", "remaining_time": "0:05:34", "throughput": 2185.33, "total_tokens": 702736} {"current_steps": 1555, "total_steps": 3160, "loss": 0.0279, "lr": 0.0006009284763797266, "epoch": 9.841772151898734, "percentage": 49.21, "elapsed_time": "0:05:22", "remaining_time": "0:05:32", "throughput": 2186.06, "total_tokens": 705104} {"current_steps": 1560, "total_steps": 3160, "loss": 0.0292, "lr": 0.0005982222012047172, "epoch": 9.873417721518987, "percentage": 49.37, "elapsed_time": "0:05:23", "remaining_time": "0:05:31", "throughput": 2186.62, "total_tokens": 707376} {"current_steps": 1565, "total_steps": 3160, "loss": 0.0073, "lr": 0.0005955129297032539, "epoch": 9.905063291139241, "percentage": 49.53, "elapsed_time": "0:05:24", "remaining_time": "0:05:30", "throughput": 2187.1, "total_tokens": 709616} {"current_steps": 1570, "total_steps": 3160, "loss": 0.018, "lr": 0.0005928007445232698, "epoch": 9.936708860759493, "percentage": 49.68, "elapsed_time": "0:05:25", "remaining_time": "0:05:29", "throughput": 2187.6, "total_tokens": 711888} {"current_steps": 1575, "total_steps": 3160, "loss": 0.0441, "lr": 0.0005900857284015807, "epoch": 9.968354430379748, "percentage": 49.84, "elapsed_time": "0:05:26", "remaining_time": "0:05:28", "throughput": 2188.2, "total_tokens": 714192} {"current_steps": 1580, "total_steps": 3160, "loss": 0.036, "lr": 0.0005873679641613625, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:05:27", "remaining_time": "0:05:27", "throughput": 2188.13, "total_tokens": 716192} {"current_steps": 1580, "total_steps": 3160, "eval_loss": 0.19241616129875183, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:05:28", "remaining_time": "0:05:28", "throughput": 2177.23, "total_tokens": 716192} {"current_steps": 1585, "total_steps": 3160, "loss": 0.0156, "lr": 0.000584647534709624, "epoch": 10.031645569620252, "percentage": 50.16, "elapsed_time": "0:05:30", "remaining_time": "0:05:28", "throughput": 2171.86, "total_tokens": 718496} {"current_steps": 1590, "total_steps": 3160, "loss": 0.0169, "lr": 0.0005819245230346772, "epoch": 10.063291139240507, "percentage": 50.32, "elapsed_time": "0:05:31", "remaining_time": "0:05:27", "throughput": 2172.53, "total_tokens": 720800} {"current_steps": 1595, "total_steps": 3160, "loss": 0.003, "lr": 0.0005791990122036075, "epoch": 10.094936708860759, "percentage": 50.47, "elapsed_time": "0:05:32", "remaining_time": "0:05:26", "throughput": 2172.79, "total_tokens": 722944} {"current_steps": 1600, "total_steps": 3160, "loss": 0.0033, "lr": 0.0005764710853597376, "epoch": 10.126582278481013, "percentage": 50.63, "elapsed_time": "0:05:33", "remaining_time": "0:05:25", "throughput": 2173.05, "total_tokens": 725088} {"current_steps": 1605, "total_steps": 3160, "loss": 0.0143, "lr": 0.0005737408257200926, "epoch": 10.158227848101266, "percentage": 50.79, "elapsed_time": "0:05:34", "remaining_time": "0:05:24", "throughput": 2173.32, "total_tokens": 727232} {"current_steps": 1610, "total_steps": 3160, "loss": 0.0091, "lr": 0.0005710083165728604, "epoch": 10.189873417721518, "percentage": 50.95, "elapsed_time": "0:05:35", "remaining_time": "0:05:23", "throughput": 2173.5, "total_tokens": 729344} {"current_steps": 1615, "total_steps": 3160, "loss": 0.0096, "lr": 0.000568273641274852, "epoch": 10.221518987341772, "percentage": 51.11, "elapsed_time": "0:05:36", "remaining_time": "0:05:21", "throughput": 2174.09, "total_tokens": 731616} {"current_steps": 1620, "total_steps": 3160, "loss": 0.0078, "lr": 0.0005655368832489584, "epoch": 10.253164556962025, "percentage": 51.27, "elapsed_time": "0:05:37", "remaining_time": "0:05:20", "throughput": 2174.92, "total_tokens": 734016} {"current_steps": 1625, "total_steps": 3160, "loss": 0.0191, "lr": 0.000562798125981604, "epoch": 10.284810126582279, "percentage": 51.42, "elapsed_time": "0:05:38", "remaining_time": "0:05:19", "throughput": 2175.57, "total_tokens": 736320} {"current_steps": 1630, "total_steps": 3160, "loss": 0.0043, "lr": 0.0005600574530202029, "epoch": 10.316455696202532, "percentage": 51.58, "elapsed_time": "0:05:39", "remaining_time": "0:05:18", "throughput": 2175.97, "total_tokens": 738528} {"current_steps": 1635, "total_steps": 3160, "loss": 0.0122, "lr": 0.0005573149479706079, "epoch": 10.348101265822784, "percentage": 51.74, "elapsed_time": "0:05:40", "remaining_time": "0:05:17", "throughput": 2176.46, "total_tokens": 740768} {"current_steps": 1640, "total_steps": 3160, "loss": 0.0218, "lr": 0.0005545706944945606, "epoch": 10.379746835443038, "percentage": 51.9, "elapsed_time": "0:05:41", "remaining_time": "0:05:16", "throughput": 2176.98, "total_tokens": 743072} {"current_steps": 1645, "total_steps": 3160, "loss": 0.0181, "lr": 0.0005518247763071391, "epoch": 10.41139240506329, "percentage": 52.06, "elapsed_time": "0:05:42", "remaining_time": "0:05:15", "throughput": 2177.4, "total_tokens": 745312} {"current_steps": 1650, "total_steps": 3160, "loss": 0.0163, "lr": 0.0005490772771742055, "epoch": 10.443037974683545, "percentage": 52.22, "elapsed_time": "0:05:43", "remaining_time": "0:05:14", "throughput": 2177.72, "total_tokens": 747488} {"current_steps": 1655, "total_steps": 3160, "loss": 0.0114, "lr": 0.0005463282809098489, "epoch": 10.474683544303797, "percentage": 52.37, "elapsed_time": "0:05:44", "remaining_time": "0:05:13", "throughput": 2178.21, "total_tokens": 749760} {"current_steps": 1660, "total_steps": 3160, "loss": 0.0117, "lr": 0.0005435778713738292, "epoch": 10.50632911392405, "percentage": 52.53, "elapsed_time": "0:05:45", "remaining_time": "0:05:11", "throughput": 2178.7, "total_tokens": 752032} {"current_steps": 1665, "total_steps": 3160, "loss": 0.0083, "lr": 0.0005408261324690192, "epoch": 10.537974683544304, "percentage": 52.69, "elapsed_time": "0:05:46", "remaining_time": "0:05:10", "throughput": 2179.27, "total_tokens": 754336} {"current_steps": 1670, "total_steps": 3160, "loss": 0.0063, "lr": 0.0005380731481388447, "epoch": 10.569620253164556, "percentage": 52.85, "elapsed_time": "0:05:47", "remaining_time": "0:05:09", "throughput": 2179.72, "total_tokens": 756576} {"current_steps": 1675, "total_steps": 3160, "loss": 0.0156, "lr": 0.0005353190023647248, "epoch": 10.60126582278481, "percentage": 53.01, "elapsed_time": "0:05:48", "remaining_time": "0:05:08", "throughput": 2180.18, "total_tokens": 758816} {"current_steps": 1680, "total_steps": 3160, "loss": 0.0122, "lr": 0.0005325637791635076, "epoch": 10.632911392405063, "percentage": 53.16, "elapsed_time": "0:05:49", "remaining_time": "0:05:07", "throughput": 2180.59, "total_tokens": 761056} {"current_steps": 1685, "total_steps": 3160, "loss": 0.0037, "lr": 0.00052980756258491, "epoch": 10.664556962025316, "percentage": 53.32, "elapsed_time": "0:05:49", "remaining_time": "0:05:06", "throughput": 2180.83, "total_tokens": 763200} {"current_steps": 1690, "total_steps": 3160, "loss": 0.0178, "lr": 0.0005270504367089519, "epoch": 10.69620253164557, "percentage": 53.48, "elapsed_time": "0:05:50", "remaining_time": "0:05:05", "throughput": 2181.06, "total_tokens": 765344} {"current_steps": 1695, "total_steps": 3160, "loss": 0.0036, "lr": 0.0005242924856433921, "epoch": 10.727848101265822, "percentage": 53.64, "elapsed_time": "0:05:51", "remaining_time": "0:05:04", "throughput": 2181.45, "total_tokens": 767552} {"current_steps": 1700, "total_steps": 3160, "loss": 0.0052, "lr": 0.0005215337935211622, "epoch": 10.759493670886076, "percentage": 53.8, "elapsed_time": "0:05:52", "remaining_time": "0:05:03", "throughput": 2182.09, "total_tokens": 769920} {"current_steps": 1705, "total_steps": 3160, "loss": 0.0033, "lr": 0.0005187744444978001, "epoch": 10.791139240506329, "percentage": 53.96, "elapsed_time": "0:05:53", "remaining_time": "0:05:01", "throughput": 2182.69, "total_tokens": 772224} {"current_steps": 1710, "total_steps": 3160, "loss": 0.0032, "lr": 0.0005160145227488831, "epoch": 10.822784810126583, "percentage": 54.11, "elapsed_time": "0:05:54", "remaining_time": "0:05:00", "throughput": 2183.33, "total_tokens": 774592} {"current_steps": 1715, "total_steps": 3160, "loss": 0.002, "lr": 0.0005132541124674594, "epoch": 10.854430379746836, "percentage": 54.27, "elapsed_time": "0:05:55", "remaining_time": "0:04:59", "throughput": 2183.79, "total_tokens": 776864} {"current_steps": 1720, "total_steps": 3160, "loss": 0.0019, "lr": 0.0005104932978614806, "epoch": 10.886075949367088, "percentage": 54.43, "elapsed_time": "0:05:56", "remaining_time": "0:04:58", "throughput": 2184.37, "total_tokens": 779168} {"current_steps": 1725, "total_steps": 3160, "loss": 0.0076, "lr": 0.0005077321631512322, "epoch": 10.917721518987342, "percentage": 54.59, "elapsed_time": "0:05:57", "remaining_time": "0:04:57", "throughput": 2184.74, "total_tokens": 781376} {"current_steps": 1730, "total_steps": 3160, "loss": 0.0042, "lr": 0.0005049707925667649, "epoch": 10.949367088607595, "percentage": 54.75, "elapsed_time": "0:05:58", "remaining_time": "0:04:56", "throughput": 2185.41, "total_tokens": 783744} {"current_steps": 1735, "total_steps": 3160, "loss": 0.0096, "lr": 0.0005022092703453246, "epoch": 10.981012658227849, "percentage": 54.91, "elapsed_time": "0:05:59", "remaining_time": "0:04:55", "throughput": 2185.88, "total_tokens": 786016} {"current_steps": 1738, "total_steps": 3160, "eval_loss": 0.23822355270385742, "epoch": 11.0, "percentage": 55.0, "elapsed_time": "0:06:01", "remaining_time": "0:04:56", "throughput": 2175.91, "total_tokens": 787200} {"current_steps": 1740, "total_steps": 3160, "loss": 0.0193, "lr": 0.0004994476807287834, "epoch": 11.012658227848101, "percentage": 55.06, "elapsed_time": "0:06:03", "remaining_time": "0:04:56", "throughput": 2170.8, "total_tokens": 788128} {"current_steps": 1745, "total_steps": 3160, "loss": 0.0093, "lr": 0.0004966861079610688, "epoch": 11.044303797468354, "percentage": 55.22, "elapsed_time": "0:06:04", "remaining_time": "0:04:55", "throughput": 2171.28, "total_tokens": 790432} {"current_steps": 1750, "total_steps": 3160, "loss": 0.0018, "lr": 0.0004939246362855944, "epoch": 11.075949367088608, "percentage": 55.38, "elapsed_time": "0:06:04", "remaining_time": "0:04:54", "throughput": 2171.74, "total_tokens": 792672} {"current_steps": 1755, "total_steps": 3160, "loss": 0.0105, "lr": 0.0004911633499426907, "epoch": 11.10759493670886, "percentage": 55.54, "elapsed_time": "0:06:05", "remaining_time": "0:04:52", "throughput": 2172.37, "total_tokens": 795008} {"current_steps": 1760, "total_steps": 3160, "loss": 0.0087, "lr": 0.0004884023331670334, "epoch": 11.139240506329115, "percentage": 55.7, "elapsed_time": "0:06:06", "remaining_time": "0:04:51", "throughput": 2172.93, "total_tokens": 797344} {"current_steps": 1765, "total_steps": 3160, "loss": 0.0048, "lr": 0.00048564167018507544, "epoch": 11.170886075949367, "percentage": 55.85, "elapsed_time": "0:06:07", "remaining_time": "0:04:50", "throughput": 2173.71, "total_tokens": 799776} {"current_steps": 1770, "total_steps": 3160, "loss": 0.0109, "lr": 0.0004828814452124773, "epoch": 11.20253164556962, "percentage": 56.01, "elapsed_time": "0:06:08", "remaining_time": "0:04:49", "throughput": 2174.03, "total_tokens": 801952} {"current_steps": 1775, "total_steps": 3160, "loss": 0.0033, "lr": 0.0004801217424515373, "epoch": 11.234177215189874, "percentage": 56.17, "elapsed_time": "0:06:09", "remaining_time": "0:04:48", "throughput": 2174.56, "total_tokens": 804224} {"current_steps": 1780, "total_steps": 3160, "loss": 0.0183, "lr": 0.0004773626460886234, "epoch": 11.265822784810126, "percentage": 56.33, "elapsed_time": "0:06:10", "remaining_time": "0:04:47", "throughput": 2175.08, "total_tokens": 806496} {"current_steps": 1785, "total_steps": 3160, "loss": 0.0069, "lr": 0.00047460424029160546, "epoch": 11.29746835443038, "percentage": 56.49, "elapsed_time": "0:06:11", "remaining_time": "0:04:46", "throughput": 2175.38, "total_tokens": 808672} {"current_steps": 1790, "total_steps": 3160, "loss": 0.0005, "lr": 0.0004718466092072868, "epoch": 11.329113924050633, "percentage": 56.65, "elapsed_time": "0:06:12", "remaining_time": "0:04:45", "throughput": 2175.98, "total_tokens": 811008} {"current_steps": 1795, "total_steps": 3160, "loss": 0.0203, "lr": 0.0004690898369588377, "epoch": 11.360759493670885, "percentage": 56.8, "elapsed_time": "0:06:13", "remaining_time": "0:04:44", "throughput": 2176.58, "total_tokens": 813344} {"current_steps": 1800, "total_steps": 3160, "loss": 0.0078, "lr": 0.0004663340076432295, "epoch": 11.39240506329114, "percentage": 56.96, "elapsed_time": "0:06:14", "remaining_time": "0:04:43", "throughput": 2177.12, "total_tokens": 815648} {"current_steps": 1805, "total_steps": 3160, "loss": 0.0119, "lr": 0.0004635792053286682, "epoch": 11.424050632911392, "percentage": 57.12, "elapsed_time": "0:06:15", "remaining_time": "0:04:41", "throughput": 2177.56, "total_tokens": 817888} {"current_steps": 1810, "total_steps": 3160, "loss": 0.0004, "lr": 0.00046082551405203135, "epoch": 11.455696202531646, "percentage": 57.28, "elapsed_time": "0:06:16", "remaining_time": "0:04:40", "throughput": 2177.94, "total_tokens": 820128} {"current_steps": 1815, "total_steps": 3160, "loss": 0.002, "lr": 0.0004580730178163028, "epoch": 11.487341772151899, "percentage": 57.44, "elapsed_time": "0:06:17", "remaining_time": "0:04:39", "throughput": 2178.31, "total_tokens": 822368} {"current_steps": 1820, "total_steps": 3160, "loss": 0.0085, "lr": 0.0004553218005880114, "epoch": 11.518987341772151, "percentage": 57.59, "elapsed_time": "0:06:18", "remaining_time": "0:04:38", "throughput": 2178.67, "total_tokens": 824576} {"current_steps": 1825, "total_steps": 3160, "loss": 0.0048, "lr": 0.00045257194629466917, "epoch": 11.550632911392405, "percentage": 57.75, "elapsed_time": "0:06:19", "remaining_time": "0:04:37", "throughput": 2179.18, "total_tokens": 826880} {"current_steps": 1830, "total_steps": 3160, "loss": 0.0126, "lr": 0.00044982353882221083, "epoch": 11.582278481012658, "percentage": 57.91, "elapsed_time": "0:06:20", "remaining_time": "0:04:36", "throughput": 2179.62, "total_tokens": 829120} {"current_steps": 1835, "total_steps": 3160, "loss": 0.0082, "lr": 0.0004470766620124349, "epoch": 11.613924050632912, "percentage": 58.07, "elapsed_time": "0:06:21", "remaining_time": "0:04:35", "throughput": 2180.1, "total_tokens": 831424} {"current_steps": 1840, "total_steps": 3160, "loss": 0.0108, "lr": 0.00044433139966044646, "epoch": 11.645569620253164, "percentage": 58.23, "elapsed_time": "0:06:22", "remaining_time": "0:04:34", "throughput": 2180.67, "total_tokens": 833728} {"current_steps": 1845, "total_steps": 3160, "loss": 0.0018, "lr": 0.0004415878355121002, "epoch": 11.677215189873417, "percentage": 58.39, "elapsed_time": "0:06:23", "remaining_time": "0:04:33", "throughput": 2181.02, "total_tokens": 835936} {"current_steps": 1850, "total_steps": 3160, "loss": 0.0188, "lr": 0.00043884605326144615, "epoch": 11.708860759493671, "percentage": 58.54, "elapsed_time": "0:06:24", "remaining_time": "0:04:32", "throughput": 2181.39, "total_tokens": 838176} {"current_steps": 1855, "total_steps": 3160, "loss": 0.0045, "lr": 0.0004361061365481771, "epoch": 11.740506329113924, "percentage": 58.7, "elapsed_time": "0:06:25", "remaining_time": "0:04:30", "throughput": 2181.94, "total_tokens": 840480} {"current_steps": 1860, "total_steps": 3160, "loss": 0.0153, "lr": 0.0004333681689550756, "epoch": 11.772151898734178, "percentage": 58.86, "elapsed_time": "0:06:26", "remaining_time": "0:04:29", "throughput": 2182.52, "total_tokens": 842848} {"current_steps": 1865, "total_steps": 3160, "loss": 0.0011, "lr": 0.0004306322340054659, "epoch": 11.80379746835443, "percentage": 59.02, "elapsed_time": "0:06:27", "remaining_time": "0:04:28", "throughput": 2182.73, "total_tokens": 844992} {"current_steps": 1870, "total_steps": 3160, "loss": 0.0059, "lr": 0.0004278984151606648, "epoch": 11.835443037974684, "percentage": 59.18, "elapsed_time": "0:06:28", "remaining_time": "0:04:27", "throughput": 2183.29, "total_tokens": 847328} {"current_steps": 1875, "total_steps": 3160, "loss": 0.0037, "lr": 0.0004251667958174361, "epoch": 11.867088607594937, "percentage": 59.34, "elapsed_time": "0:06:29", "remaining_time": "0:04:26", "throughput": 2183.62, "total_tokens": 849536} {"current_steps": 1880, "total_steps": 3160, "loss": 0.0042, "lr": 0.00042243745930544677, "epoch": 11.89873417721519, "percentage": 59.49, "elapsed_time": "0:06:29", "remaining_time": "0:04:25", "throughput": 2183.9, "total_tokens": 851712} {"current_steps": 1885, "total_steps": 3160, "loss": 0.0292, "lr": 0.00041971048888472443, "epoch": 11.930379746835444, "percentage": 59.65, "elapsed_time": "0:06:30", "remaining_time": "0:04:24", "throughput": 2184.36, "total_tokens": 853984} {"current_steps": 1890, "total_steps": 3160, "loss": 0.0107, "lr": 0.00041698596774311755, "epoch": 11.962025316455696, "percentage": 59.81, "elapsed_time": "0:06:31", "remaining_time": "0:04:23", "throughput": 2184.71, "total_tokens": 856224} {"current_steps": 1895, "total_steps": 3160, "loss": 0.0017, "lr": 0.0004142639789937585, "epoch": 11.99367088607595, "percentage": 59.97, "elapsed_time": "0:06:32", "remaining_time": "0:04:22", "throughput": 2185.24, "total_tokens": 858528} {"current_steps": 1896, "total_steps": 3160, "eval_loss": 0.22486339509487152, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "0:06:34", "remaining_time": "0:04:23", "throughput": 2175.8, "total_tokens": 858736} {"current_steps": 1900, "total_steps": 3160, "loss": 0.0024, "lr": 0.00041154460567252696, "epoch": 12.025316455696203, "percentage": 60.13, "elapsed_time": "0:06:36", "remaining_time": "0:04:22", "throughput": 2171.16, "total_tokens": 860592} {"current_steps": 1905, "total_steps": 3160, "loss": 0.0006, "lr": 0.0004088279307355173, "epoch": 12.056962025316455, "percentage": 60.28, "elapsed_time": "0:06:37", "remaining_time": "0:04:21", "throughput": 2171.48, "total_tokens": 862800} {"current_steps": 1910, "total_steps": 3160, "loss": 0.0003, "lr": 0.0004061140370565088, "epoch": 12.08860759493671, "percentage": 60.44, "elapsed_time": "0:06:38", "remaining_time": "0:04:20", "throughput": 2171.99, "total_tokens": 865104} {"current_steps": 1915, "total_steps": 3160, "loss": 0.0012, "lr": 0.0004034030074244361, "epoch": 12.120253164556962, "percentage": 60.6, "elapsed_time": "0:06:39", "remaining_time": "0:04:19", "throughput": 2172.5, "total_tokens": 867408} {"current_steps": 1920, "total_steps": 3160, "loss": 0.016, "lr": 0.00040069492454086465, "epoch": 12.151898734177216, "percentage": 60.76, "elapsed_time": "0:06:40", "remaining_time": "0:04:18", "throughput": 2172.97, "total_tokens": 869680} {"current_steps": 1925, "total_steps": 3160, "loss": 0.015, "lr": 0.00039798987101746775, "epoch": 12.183544303797468, "percentage": 60.92, "elapsed_time": "0:06:41", "remaining_time": "0:04:17", "throughput": 2173.26, "total_tokens": 871856} {"current_steps": 1930, "total_steps": 3160, "loss": 0.0176, "lr": 0.00039528792937350586, "epoch": 12.215189873417721, "percentage": 61.08, "elapsed_time": "0:06:42", "remaining_time": "0:04:16", "throughput": 2173.74, "total_tokens": 874192} {"current_steps": 1935, "total_steps": 3160, "loss": 0.0007, "lr": 0.0003925891820333104, "epoch": 12.246835443037975, "percentage": 61.23, "elapsed_time": "0:06:43", "remaining_time": "0:04:15", "throughput": 2174.1, "total_tokens": 876432} {"current_steps": 1940, "total_steps": 3160, "loss": 0.0058, "lr": 0.00038989371132376805, "epoch": 12.278481012658228, "percentage": 61.39, "elapsed_time": "0:06:44", "remaining_time": "0:04:14", "throughput": 2174.51, "total_tokens": 878672} {"current_steps": 1945, "total_steps": 3160, "loss": 0.0064, "lr": 0.00038720159947180997, "epoch": 12.310126582278482, "percentage": 61.55, "elapsed_time": "0:06:45", "remaining_time": "0:04:13", "throughput": 2174.99, "total_tokens": 880976} {"current_steps": 1950, "total_steps": 3160, "loss": 0.0092, "lr": 0.00038451292860190386, "epoch": 12.341772151898734, "percentage": 61.71, "elapsed_time": "0:06:46", "remaining_time": "0:04:11", "throughput": 2175.49, "total_tokens": 883280} {"current_steps": 1955, "total_steps": 3160, "loss": 0.0129, "lr": 0.00038182778073354764, "epoch": 12.373417721518987, "percentage": 61.87, "elapsed_time": "0:06:46", "remaining_time": "0:04:10", "throughput": 2175.83, "total_tokens": 885488} {"current_steps": 1960, "total_steps": 3160, "loss": 0.0248, "lr": 0.0003791462377787682, "epoch": 12.405063291139241, "percentage": 62.03, "elapsed_time": "0:06:47", "remaining_time": "0:04:09", "throughput": 2176.3, "total_tokens": 887760} {"current_steps": 1965, "total_steps": 3160, "loss": 0.0017, "lr": 0.0003764683815396226, "epoch": 12.436708860759493, "percentage": 62.18, "elapsed_time": "0:06:48", "remaining_time": "0:04:08", "throughput": 2176.64, "total_tokens": 889968} {"current_steps": 1970, "total_steps": 3160, "loss": 0.0068, "lr": 0.00037379429370570233, "epoch": 12.468354430379748, "percentage": 62.34, "elapsed_time": "0:06:49", "remaining_time": "0:04:07", "throughput": 2177.26, "total_tokens": 892336} {"current_steps": 1975, "total_steps": 3160, "loss": 0.0025, "lr": 0.0003711240558516411, "epoch": 12.5, "percentage": 62.5, "elapsed_time": "0:06:50", "remaining_time": "0:04:06", "throughput": 2177.73, "total_tokens": 894608} {"current_steps": 1980, "total_steps": 3160, "loss": 0.0075, "lr": 0.0003684577494346275, "epoch": 12.531645569620252, "percentage": 62.66, "elapsed_time": "0:06:51", "remaining_time": "0:04:05", "throughput": 2178.26, "total_tokens": 896944} {"current_steps": 1985, "total_steps": 3160, "loss": 0.0106, "lr": 0.0003657954557919183, "epoch": 12.563291139240507, "percentage": 62.82, "elapsed_time": "0:06:52", "remaining_time": "0:04:04", "throughput": 2178.52, "total_tokens": 899120} {"current_steps": 1990, "total_steps": 3160, "loss": 0.0007, "lr": 0.00036313725613835914, "epoch": 12.594936708860759, "percentage": 62.97, "elapsed_time": "0:06:53", "remaining_time": "0:04:03", "throughput": 2179.04, "total_tokens": 901456} {"current_steps": 1995, "total_steps": 3160, "loss": 0.0015, "lr": 0.0003604832315639056, "epoch": 12.626582278481013, "percentage": 63.13, "elapsed_time": "0:06:54", "remaining_time": "0:04:02", "throughput": 2179.43, "total_tokens": 903696} {"current_steps": 2000, "total_steps": 3160, "loss": 0.0084, "lr": 0.00035783346303114983, "epoch": 12.658227848101266, "percentage": 63.29, "elapsed_time": "0:06:55", "remaining_time": "0:04:01", "throughput": 2179.91, "total_tokens": 906000} {"current_steps": 2005, "total_steps": 3160, "loss": 0.0042, "lr": 0.0003551880313728515, "epoch": 12.689873417721518, "percentage": 63.45, "elapsed_time": "0:06:56", "remaining_time": "0:03:59", "throughput": 2180.33, "total_tokens": 908304} {"current_steps": 2010, "total_steps": 3160, "loss": 0.0018, "lr": 0.0003525470172894709, "epoch": 12.721518987341772, "percentage": 63.61, "elapsed_time": "0:06:57", "remaining_time": "0:03:58", "throughput": 2180.52, "total_tokens": 910448} {"current_steps": 2015, "total_steps": 3160, "loss": 0.0028, "lr": 0.00034991050134670736, "epoch": 12.753164556962025, "percentage": 63.77, "elapsed_time": "0:06:58", "remaining_time": "0:03:57", "throughput": 2181.12, "total_tokens": 912816} {"current_steps": 2020, "total_steps": 3160, "loss": 0.0022, "lr": 0.0003472785639730428, "epoch": 12.784810126582279, "percentage": 63.92, "elapsed_time": "0:06:59", "remaining_time": "0:03:56", "throughput": 2181.5, "total_tokens": 915056} {"current_steps": 2025, "total_steps": 3160, "loss": 0.0028, "lr": 0.00034465128545728586, "epoch": 12.816455696202532, "percentage": 64.08, "elapsed_time": "0:07:00", "remaining_time": "0:03:55", "throughput": 2181.81, "total_tokens": 917264} {"current_steps": 2030, "total_steps": 3160, "loss": 0.004, "lr": 0.00034202874594612467, "epoch": 12.848101265822784, "percentage": 64.24, "elapsed_time": "0:07:01", "remaining_time": "0:03:54", "throughput": 2182.19, "total_tokens": 919504} {"current_steps": 2035, "total_steps": 3160, "loss": 0.0008, "lr": 0.00033941102544168133, "epoch": 12.879746835443038, "percentage": 64.4, "elapsed_time": "0:07:02", "remaining_time": "0:03:53", "throughput": 2182.51, "total_tokens": 921712} {"current_steps": 2040, "total_steps": 3160, "loss": 0.0035, "lr": 0.000336798203799071, "epoch": 12.91139240506329, "percentage": 64.56, "elapsed_time": "0:07:03", "remaining_time": "0:03:52", "throughput": 2183.15, "total_tokens": 924112} {"current_steps": 2045, "total_steps": 3160, "loss": 0.0015, "lr": 0.00033419036072396616, "epoch": 12.943037974683545, "percentage": 64.72, "elapsed_time": "0:07:04", "remaining_time": "0:03:51", "throughput": 2183.42, "total_tokens": 926320} {"current_steps": 2050, "total_steps": 3160, "loss": 0.001, "lr": 0.0003315875757701653, "epoch": 12.974683544303797, "percentage": 64.87, "elapsed_time": "0:07:05", "remaining_time": "0:03:50", "throughput": 2183.87, "total_tokens": 928624} {"current_steps": 2054, "total_steps": 3160, "eval_loss": 0.22669243812561035, "epoch": 13.0, "percentage": 65.0, "elapsed_time": "0:07:07", "remaining_time": "0:03:50", "throughput": 2175.37, "total_tokens": 930160} {"current_steps": 2055, "total_steps": 3160, "loss": 0.0054, "lr": 0.0003289899283371657, "epoch": 13.00632911392405, "percentage": 65.03, "elapsed_time": "0:07:08", "remaining_time": "0:03:50", "throughput": 2170.8, "total_tokens": 930576} {"current_steps": 2060, "total_steps": 3160, "loss": 0.0034, "lr": 0.00032639749766774173, "epoch": 13.037974683544304, "percentage": 65.19, "elapsed_time": "0:07:09", "remaining_time": "0:03:49", "throughput": 2171.28, "total_tokens": 932944} {"current_steps": 2065, "total_steps": 3160, "loss": 0.0005, "lr": 0.00032381036284552734, "epoch": 13.069620253164556, "percentage": 65.35, "elapsed_time": "0:07:10", "remaining_time": "0:03:48", "throughput": 2171.61, "total_tokens": 935152} {"current_steps": 2070, "total_steps": 3160, "loss": 0.002, "lr": 0.00032122860279260306, "epoch": 13.10126582278481, "percentage": 65.51, "elapsed_time": "0:07:11", "remaining_time": "0:03:47", "throughput": 2172.07, "total_tokens": 937456} {"current_steps": 2075, "total_steps": 3160, "loss": 0.0006, "lr": 0.0003186522962670897, "epoch": 13.132911392405063, "percentage": 65.66, "elapsed_time": "0:07:12", "remaining_time": "0:03:46", "throughput": 2172.58, "total_tokens": 939760} {"current_steps": 2080, "total_steps": 3160, "loss": 0.0002, "lr": 0.00031608152186074425, "epoch": 13.164556962025316, "percentage": 65.82, "elapsed_time": "0:07:13", "remaining_time": "0:03:45", "throughput": 2173.16, "total_tokens": 942128} {"current_steps": 2085, "total_steps": 3160, "loss": 0.002, "lr": 0.0003135163579965633, "epoch": 13.19620253164557, "percentage": 65.98, "elapsed_time": "0:07:14", "remaining_time": "0:03:44", "throughput": 2173.55, "total_tokens": 944368} {"current_steps": 2090, "total_steps": 3160, "loss": 0.0056, "lr": 0.0003109568829263909, "epoch": 13.227848101265822, "percentage": 66.14, "elapsed_time": "0:07:15", "remaining_time": "0:03:42", "throughput": 2174.01, "total_tokens": 946672} {"current_steps": 2095, "total_steps": 3160, "loss": 0.0016, "lr": 0.00030840317472853075, "epoch": 13.259493670886076, "percentage": 66.3, "elapsed_time": "0:07:16", "remaining_time": "0:03:41", "throughput": 2174.48, "total_tokens": 949008} {"current_steps": 2100, "total_steps": 3160, "loss": 0.007, "lr": 0.00030585531130536447, "epoch": 13.291139240506329, "percentage": 66.46, "elapsed_time": "0:07:17", "remaining_time": "0:03:40", "throughput": 2174.89, "total_tokens": 951312} {"current_steps": 2105, "total_steps": 3160, "loss": 0.0008, "lr": 0.00030331337038097593, "epoch": 13.322784810126583, "percentage": 66.61, "elapsed_time": "0:07:18", "remaining_time": "0:03:39", "throughput": 2175.27, "total_tokens": 953552} {"current_steps": 2110, "total_steps": 3160, "loss": 0.0004, "lr": 0.00030077742949877905, "epoch": 13.354430379746836, "percentage": 66.77, "elapsed_time": "0:07:19", "remaining_time": "0:03:38", "throughput": 2175.65, "total_tokens": 955792} {"current_steps": 2115, "total_steps": 3160, "loss": 0.0017, "lr": 0.0002982475660191536, "epoch": 13.386075949367088, "percentage": 66.93, "elapsed_time": "0:07:20", "remaining_time": "0:03:37", "throughput": 2175.96, "total_tokens": 958000} {"current_steps": 2120, "total_steps": 3160, "loss": 0.0019, "lr": 0.0002957238571170841, "epoch": 13.417721518987342, "percentage": 67.09, "elapsed_time": "0:07:21", "remaining_time": "0:03:36", "throughput": 2176.46, "total_tokens": 960304} {"current_steps": 2125, "total_steps": 3160, "loss": 0.0008, "lr": 0.0002932063797798059, "epoch": 13.449367088607595, "percentage": 67.25, "elapsed_time": "0:07:22", "remaining_time": "0:03:35", "throughput": 2176.66, "total_tokens": 962448} {"current_steps": 2130, "total_steps": 3160, "loss": 0.0017, "lr": 0.0002906952108044574, "epoch": 13.481012658227849, "percentage": 67.41, "elapsed_time": "0:07:23", "remaining_time": "0:03:34", "throughput": 2177.04, "total_tokens": 964688} {"current_steps": 2135, "total_steps": 3160, "loss": 0.0053, "lr": 0.00028819042679573614, "epoch": 13.512658227848101, "percentage": 67.56, "elapsed_time": "0:07:24", "remaining_time": "0:03:33", "throughput": 2177.43, "total_tokens": 966960} {"current_steps": 2140, "total_steps": 3160, "loss": 0.0012, "lr": 0.00028569210416356215, "epoch": 13.544303797468354, "percentage": 67.72, "elapsed_time": "0:07:25", "remaining_time": "0:03:32", "throughput": 2177.92, "total_tokens": 969296} {"current_steps": 2145, "total_steps": 3160, "loss": 0.0012, "lr": 0.0002832003191207487, "epoch": 13.575949367088608, "percentage": 67.88, "elapsed_time": "0:07:26", "remaining_time": "0:03:31", "throughput": 2178.41, "total_tokens": 971600} {"current_steps": 2150, "total_steps": 3160, "loss": 0.0055, "lr": 0.00028071514768067445, "epoch": 13.60759493670886, "percentage": 68.04, "elapsed_time": "0:07:26", "remaining_time": "0:03:29", "throughput": 2178.89, "total_tokens": 973904} {"current_steps": 2155, "total_steps": 3160, "loss": 0.0013, "lr": 0.00027823666565496714, "epoch": 13.639240506329115, "percentage": 68.2, "elapsed_time": "0:07:27", "remaining_time": "0:03:28", "throughput": 2179.26, "total_tokens": 976176} {"current_steps": 2160, "total_steps": 3160, "loss": 0.0041, "lr": 0.00027576494865118984, "epoch": 13.670886075949367, "percentage": 68.35, "elapsed_time": "0:07:28", "remaining_time": "0:03:27", "throughput": 2179.68, "total_tokens": 978480} {"current_steps": 2165, "total_steps": 3160, "loss": 0.0053, "lr": 0.0002733000720705341, "epoch": 13.70253164556962, "percentage": 68.51, "elapsed_time": "0:07:29", "remaining_time": "0:03:26", "throughput": 2180.1, "total_tokens": 980752} {"current_steps": 2170, "total_steps": 3160, "loss": 0.0004, "lr": 0.0002708421111055209, "epoch": 13.734177215189874, "percentage": 68.67, "elapsed_time": "0:07:30", "remaining_time": "0:03:25", "throughput": 2180.59, "total_tokens": 983056} {"current_steps": 2175, "total_steps": 3160, "loss": 0.001, "lr": 0.0002683911407377062, "epoch": 13.765822784810126, "percentage": 68.83, "elapsed_time": "0:07:31", "remaining_time": "0:03:24", "throughput": 2180.83, "total_tokens": 985232} {"current_steps": 2180, "total_steps": 3160, "loss": 0.0006, "lr": 0.00026594723573539306, "epoch": 13.79746835443038, "percentage": 68.99, "elapsed_time": "0:07:32", "remaining_time": "0:03:23", "throughput": 2181.24, "total_tokens": 987536} {"current_steps": 2185, "total_steps": 3160, "loss": 0.0022, "lr": 0.00026351047065135237, "epoch": 13.829113924050633, "percentage": 69.15, "elapsed_time": "0:07:33", "remaining_time": "0:03:22", "throughput": 2181.49, "total_tokens": 989744} {"current_steps": 2190, "total_steps": 3160, "loss": 0.0021, "lr": 0.0002610809198205466, "epoch": 13.860759493670885, "percentage": 69.3, "elapsed_time": "0:07:34", "remaining_time": "0:03:21", "throughput": 2181.77, "total_tokens": 991952} {"current_steps": 2195, "total_steps": 3160, "loss": 0.0027, "lr": 0.00025865865735786377, "epoch": 13.89240506329114, "percentage": 69.46, "elapsed_time": "0:07:35", "remaining_time": "0:03:20", "throughput": 2182.13, "total_tokens": 994224} {"current_steps": 2200, "total_steps": 3160, "loss": 0.0022, "lr": 0.0002562437571558558, "epoch": 13.924050632911392, "percentage": 69.62, "elapsed_time": "0:07:36", "remaining_time": "0:03:19", "throughput": 2182.5, "total_tokens": 996528} {"current_steps": 2205, "total_steps": 3160, "loss": 0.0005, "lr": 0.00025383629288248423, "epoch": 13.955696202531646, "percentage": 69.78, "elapsed_time": "0:07:37", "remaining_time": "0:03:18", "throughput": 2182.91, "total_tokens": 998800} {"current_steps": 2210, "total_steps": 3160, "loss": 0.0012, "lr": 0.0002514363379788733, "epoch": 13.987341772151899, "percentage": 69.94, "elapsed_time": "0:07:38", "remaining_time": "0:03:17", "throughput": 2183.33, "total_tokens": 1001104} {"current_steps": 2212, "total_steps": 3160, "eval_loss": 0.24711216986179352, "epoch": 14.0, "percentage": 70.0, "elapsed_time": "0:07:40", "remaining_time": "0:03:17", "throughput": 2175.4, "total_tokens": 1001792} {"current_steps": 2215, "total_steps": 3160, "loss": 0.0008, "lr": 0.00024904396565707, "epoch": 14.018987341772151, "percentage": 70.09, "elapsed_time": "0:07:41", "remaining_time": "0:03:17", "throughput": 2171.46, "total_tokens": 1003168} {"current_steps": 2220, "total_steps": 3160, "loss": 0.0005, "lr": 0.00024665924889780914, "epoch": 14.050632911392405, "percentage": 70.25, "elapsed_time": "0:07:42", "remaining_time": "0:03:16", "throughput": 2171.66, "total_tokens": 1005472} {"current_steps": 2225, "total_steps": 3160, "loss": 0.0045, "lr": 0.00024428226044828893, "epoch": 14.082278481012658, "percentage": 70.41, "elapsed_time": "0:07:43", "remaining_time": "0:03:14", "throughput": 2172.1, "total_tokens": 1007776} {"current_steps": 2230, "total_steps": 3160, "loss": 0.0007, "lr": 0.00024191307281995058, "epoch": 14.113924050632912, "percentage": 70.57, "elapsed_time": "0:07:44", "remaining_time": "0:03:13", "throughput": 2172.51, "total_tokens": 1010048} {"current_steps": 2235, "total_steps": 3160, "loss": 0.0005, "lr": 0.00023955175828626658, "epoch": 14.145569620253164, "percentage": 70.73, "elapsed_time": "0:07:45", "remaining_time": "0:03:12", "throughput": 2172.82, "total_tokens": 1012256} {"current_steps": 2240, "total_steps": 3160, "loss": 0.0003, "lr": 0.00023719838888053635, "epoch": 14.177215189873417, "percentage": 70.89, "elapsed_time": "0:07:46", "remaining_time": "0:03:11", "throughput": 2173.36, "total_tokens": 1014592} {"current_steps": 2245, "total_steps": 3160, "loss": 0.0033, "lr": 0.00023485303639368782, "epoch": 14.208860759493671, "percentage": 71.04, "elapsed_time": "0:07:47", "remaining_time": "0:03:10", "throughput": 2173.78, "total_tokens": 1016928} {"current_steps": 2250, "total_steps": 3160, "loss": 0.0004, "lr": 0.00023251577237208866, "epoch": 14.240506329113924, "percentage": 71.2, "elapsed_time": "0:07:48", "remaining_time": "0:03:09", "throughput": 2174.25, "total_tokens": 1019232} {"current_steps": 2255, "total_steps": 3160, "loss": 0.0009, "lr": 0.00023018666811536304, "epoch": 14.272151898734178, "percentage": 71.36, "elapsed_time": "0:07:49", "remaining_time": "0:03:08", "throughput": 2174.87, "total_tokens": 1021696} {"current_steps": 2260, "total_steps": 3160, "loss": 0.0017, "lr": 0.00022786579467421614, "epoch": 14.30379746835443, "percentage": 71.52, "elapsed_time": "0:07:50", "remaining_time": "0:03:07", "throughput": 2175.0, "total_tokens": 1023808} {"current_steps": 2265, "total_steps": 3160, "loss": 0.0009, "lr": 0.00022555322284826783, "epoch": 14.335443037974684, "percentage": 71.68, "elapsed_time": "0:07:51", "remaining_time": "0:03:06", "throughput": 2175.36, "total_tokens": 1026080} {"current_steps": 2270, "total_steps": 3160, "loss": 0.0008, "lr": 0.0002232490231838923, "epoch": 14.367088607594937, "percentage": 71.84, "elapsed_time": "0:07:52", "remaining_time": "0:03:05", "throughput": 2175.61, "total_tokens": 1028256} {"current_steps": 2275, "total_steps": 3160, "loss": 0.0004, "lr": 0.00022095326597206528, "epoch": 14.39873417721519, "percentage": 71.99, "elapsed_time": "0:07:53", "remaining_time": "0:03:04", "throughput": 2176.03, "total_tokens": 1030560} {"current_steps": 2280, "total_steps": 3160, "loss": 0.0005, "lr": 0.00021866602124622132, "epoch": 14.430379746835444, "percentage": 72.15, "elapsed_time": "0:07:54", "remaining_time": "0:03:03", "throughput": 2176.43, "total_tokens": 1032832} {"current_steps": 2285, "total_steps": 3160, "loss": 0.0004, "lr": 0.000216387358780116, "epoch": 14.462025316455696, "percentage": 72.31, "elapsed_time": "0:07:55", "remaining_time": "0:03:02", "throughput": 2176.83, "total_tokens": 1035104} {"current_steps": 2290, "total_steps": 3160, "loss": 0.0005, "lr": 0.00021411734808569855, "epoch": 14.49367088607595, "percentage": 72.47, "elapsed_time": "0:07:56", "remaining_time": "0:03:01", "throughput": 2177.06, "total_tokens": 1037280} {"current_steps": 2295, "total_steps": 3160, "loss": 0.0005, "lr": 0.00021185605841098987, "epoch": 14.525316455696203, "percentage": 72.63, "elapsed_time": "0:07:57", "remaining_time": "0:02:59", "throughput": 2177.35, "total_tokens": 1039488} {"current_steps": 2300, "total_steps": 3160, "loss": 0.0001, "lr": 0.00020960355873797176, "epoch": 14.556962025316455, "percentage": 72.78, "elapsed_time": "0:07:58", "remaining_time": "0:02:58", "throughput": 2177.79, "total_tokens": 1041792} {"current_steps": 2305, "total_steps": 3160, "loss": 0.0008, "lr": 0.00020735991778048158, "epoch": 14.58860759493671, "percentage": 72.94, "elapsed_time": "0:07:59", "remaining_time": "0:02:57", "throughput": 2178.18, "total_tokens": 1044064} {"current_steps": 2310, "total_steps": 3160, "loss": 0.0005, "lr": 0.00020512520398211647, "epoch": 14.620253164556962, "percentage": 73.1, "elapsed_time": "0:08:00", "remaining_time": "0:02:56", "throughput": 2178.71, "total_tokens": 1046432} {"current_steps": 2315, "total_steps": 3160, "loss": 0.0004, "lr": 0.00020289948551414482, "epoch": 14.651898734177216, "percentage": 73.26, "elapsed_time": "0:08:01", "remaining_time": "0:02:55", "throughput": 2179.11, "total_tokens": 1048736} {"current_steps": 2320, "total_steps": 3160, "loss": 0.0004, "lr": 0.00020068283027342755, "epoch": 14.683544303797468, "percentage": 73.42, "elapsed_time": "0:08:02", "remaining_time": "0:02:54", "throughput": 2179.51, "total_tokens": 1051040} {"current_steps": 2325, "total_steps": 3160, "loss": 0.001, "lr": 0.00019847530588034635, "epoch": 14.715189873417721, "percentage": 73.58, "elapsed_time": "0:08:03", "remaining_time": "0:02:53", "throughput": 2179.96, "total_tokens": 1053376} {"current_steps": 2330, "total_steps": 3160, "loss": 0.0009, "lr": 0.00019627697967674118, "epoch": 14.746835443037975, "percentage": 73.73, "elapsed_time": "0:08:04", "remaining_time": "0:02:52", "throughput": 2180.24, "total_tokens": 1055584} {"current_steps": 2335, "total_steps": 3160, "loss": 0.0011, "lr": 0.00019408791872385528, "epoch": 14.778481012658228, "percentage": 73.89, "elapsed_time": "0:08:05", "remaining_time": "0:02:51", "throughput": 2180.65, "total_tokens": 1057920} {"current_steps": 2340, "total_steps": 3160, "loss": 0.0004, "lr": 0.00019190818980029047, "epoch": 14.810126582278482, "percentage": 74.05, "elapsed_time": "0:08:06", "remaining_time": "0:02:50", "throughput": 2180.93, "total_tokens": 1060128} {"current_steps": 2345, "total_steps": 3160, "loss": 0.0002, "lr": 0.00018973785939996928, "epoch": 14.841772151898734, "percentage": 74.21, "elapsed_time": "0:08:07", "remaining_time": "0:02:49", "throughput": 2181.26, "total_tokens": 1062400} {"current_steps": 2350, "total_steps": 3160, "loss": 0.0007, "lr": 0.00018757699373010646, "epoch": 14.873417721518987, "percentage": 74.37, "elapsed_time": "0:08:08", "remaining_time": "0:02:48", "throughput": 2181.59, "total_tokens": 1064640} {"current_steps": 2355, "total_steps": 3160, "loss": 0.0029, "lr": 0.00018542565870918992, "epoch": 14.905063291139241, "percentage": 74.53, "elapsed_time": "0:08:08", "remaining_time": "0:02:47", "throughput": 2181.75, "total_tokens": 1066784} {"current_steps": 2360, "total_steps": 3160, "loss": 0.0007, "lr": 0.0001832839199649694, "epoch": 14.936708860759493, "percentage": 74.68, "elapsed_time": "0:08:09", "remaining_time": "0:02:46", "throughput": 2182.02, "total_tokens": 1068992} {"current_steps": 2365, "total_steps": 3160, "loss": 0.0019, "lr": 0.00018115184283245438, "epoch": 14.968354430379748, "percentage": 74.84, "elapsed_time": "0:08:10", "remaining_time": "0:02:45", "throughput": 2182.24, "total_tokens": 1071168} {"current_steps": 2370, "total_steps": 3160, "loss": 0.0017, "lr": 0.0001790294923519215, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "0:08:11", "remaining_time": "0:02:43", "throughput": 2182.29, "total_tokens": 1073248} {"current_steps": 2370, "total_steps": 3160, "eval_loss": 0.2629498839378357, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "0:08:13", "remaining_time": "0:02:44", "throughput": 2175.07, "total_tokens": 1073248} {"current_steps": 2375, "total_steps": 3160, "loss": 0.0002, "lr": 0.00017691693326692942, "epoch": 15.031645569620252, "percentage": 75.16, "elapsed_time": "0:08:15", "remaining_time": "0:02:43", "throughput": 2171.16, "total_tokens": 1075392} {"current_steps": 2380, "total_steps": 3160, "loss": 0.0001, "lr": 0.0001748142300223452, "epoch": 15.063291139240507, "percentage": 75.32, "elapsed_time": "0:08:16", "remaining_time": "0:02:42", "throughput": 2171.27, "total_tokens": 1077632} {"current_steps": 2385, "total_steps": 3160, "loss": 0.0013, "lr": 0.0001727214467623775, "epoch": 15.094936708860759, "percentage": 75.47, "elapsed_time": "0:08:17", "remaining_time": "0:02:41", "throughput": 2171.5, "total_tokens": 1079808} {"current_steps": 2390, "total_steps": 3160, "loss": 0.001, "lr": 0.00017063864732861945, "epoch": 15.126582278481013, "percentage": 75.63, "elapsed_time": "0:08:18", "remaining_time": "0:02:40", "throughput": 2171.84, "total_tokens": 1082048} {"current_steps": 2395, "total_steps": 3160, "loss": 0.0003, "lr": 0.0001685658952581023, "epoch": 15.158227848101266, "percentage": 75.79, "elapsed_time": "0:08:19", "remaining_time": "0:02:39", "throughput": 2172.18, "total_tokens": 1084288} {"current_steps": 2400, "total_steps": 3160, "loss": 0.0002, "lr": 0.00016650325378135628, "epoch": 15.189873417721518, "percentage": 75.95, "elapsed_time": "0:08:20", "remaining_time": "0:02:38", "throughput": 2172.63, "total_tokens": 1086624} {"current_steps": 2405, "total_steps": 3160, "loss": 0.0003, "lr": 0.00016445078582048156, "epoch": 15.221518987341772, "percentage": 76.11, "elapsed_time": "0:08:21", "remaining_time": "0:02:37", "throughput": 2173.09, "total_tokens": 1088960} {"current_steps": 2410, "total_steps": 3160, "loss": 0.0012, "lr": 0.0001624085539872302, "epoch": 15.253164556962025, "percentage": 76.27, "elapsed_time": "0:08:22", "remaining_time": "0:02:36", "throughput": 2173.59, "total_tokens": 1091328} {"current_steps": 2415, "total_steps": 3160, "loss": 0.0019, "lr": 0.00016037662058109413, "epoch": 15.284810126582279, "percentage": 76.42, "elapsed_time": "0:08:23", "remaining_time": "0:02:35", "throughput": 2173.92, "total_tokens": 1093568} {"current_steps": 2420, "total_steps": 3160, "loss": 0.0006, "lr": 0.00015835504758740577, "epoch": 15.316455696202532, "percentage": 76.58, "elapsed_time": "0:08:24", "remaining_time": "0:02:34", "throughput": 2174.21, "total_tokens": 1095808} {"current_steps": 2425, "total_steps": 3160, "loss": 0.0006, "lr": 0.00015634389667544784, "epoch": 15.348101265822784, "percentage": 76.74, "elapsed_time": "0:08:24", "remaining_time": "0:02:33", "throughput": 2174.72, "total_tokens": 1098176} {"current_steps": 2430, "total_steps": 3160, "loss": 0.0006, "lr": 0.00015434322919657023, "epoch": 15.379746835443038, "percentage": 76.9, "elapsed_time": "0:08:25", "remaining_time": "0:02:31", "throughput": 2175.18, "total_tokens": 1100544} {"current_steps": 2435, "total_steps": 3160, "loss": 0.0003, "lr": 0.0001523531061823202, "epoch": 15.41139240506329, "percentage": 77.06, "elapsed_time": "0:08:26", "remaining_time": "0:02:30", "throughput": 2175.67, "total_tokens": 1102880} {"current_steps": 2440, "total_steps": 3160, "loss": 0.0002, "lr": 0.00015037358834257963, "epoch": 15.443037974683545, "percentage": 77.22, "elapsed_time": "0:08:27", "remaining_time": "0:02:29", "throughput": 2175.89, "total_tokens": 1105056} {"current_steps": 2445, "total_steps": 3160, "loss": 0.0007, "lr": 0.00014840473606371298, "epoch": 15.474683544303797, "percentage": 77.37, "elapsed_time": "0:08:28", "remaining_time": "0:02:28", "throughput": 2176.17, "total_tokens": 1107296} {"current_steps": 2450, "total_steps": 3160, "loss": 0.0004, "lr": 0.00014644660940672628, "epoch": 15.50632911392405, "percentage": 77.53, "elapsed_time": "0:08:29", "remaining_time": "0:02:27", "throughput": 2176.46, "total_tokens": 1109536} {"current_steps": 2455, "total_steps": 3160, "loss": 0.0004, "lr": 0.00014449926810543328, "epoch": 15.537974683544304, "percentage": 77.69, "elapsed_time": "0:08:30", "remaining_time": "0:02:26", "throughput": 2176.72, "total_tokens": 1111744} {"current_steps": 2460, "total_steps": 3160, "loss": 0.0004, "lr": 0.00014256277156463404, "epoch": 15.569620253164556, "percentage": 77.85, "elapsed_time": "0:08:31", "remaining_time": "0:02:25", "throughput": 2177.33, "total_tokens": 1114208} {"current_steps": 2465, "total_steps": 3160, "loss": 0.0005, "lr": 0.00014063717885830373, "epoch": 15.60126582278481, "percentage": 78.01, "elapsed_time": "0:08:32", "remaining_time": "0:02:24", "throughput": 2177.65, "total_tokens": 1116448} {"current_steps": 2470, "total_steps": 3160, "loss": 0.0001, "lr": 0.00013872254872778845, "epoch": 15.632911392405063, "percentage": 78.16, "elapsed_time": "0:08:33", "remaining_time": "0:02:23", "throughput": 2177.86, "total_tokens": 1118624} {"current_steps": 2475, "total_steps": 3160, "loss": 0.0005, "lr": 0.00013681893958001517, "epoch": 15.664556962025316, "percentage": 78.32, "elapsed_time": "0:08:34", "remaining_time": "0:02:22", "throughput": 2178.17, "total_tokens": 1120896} {"current_steps": 2480, "total_steps": 3160, "loss": 0.0002, "lr": 0.00013492640948570907, "epoch": 15.69620253164557, "percentage": 78.48, "elapsed_time": "0:08:35", "remaining_time": "0:02:21", "throughput": 2178.65, "total_tokens": 1123264} {"current_steps": 2485, "total_steps": 3160, "loss": 0.0005, "lr": 0.00013304501617762178, "epoch": 15.727848101265822, "percentage": 78.64, "elapsed_time": "0:08:36", "remaining_time": "0:02:20", "throughput": 2178.96, "total_tokens": 1125504} {"current_steps": 2490, "total_steps": 3160, "loss": 0.0003, "lr": 0.00013117481704877165, "epoch": 15.759493670886076, "percentage": 78.8, "elapsed_time": "0:08:37", "remaining_time": "0:02:19", "throughput": 2179.24, "total_tokens": 1127744} {"current_steps": 2495, "total_steps": 3160, "loss": 0.0003, "lr": 0.00012931586915069105, "epoch": 15.791139240506329, "percentage": 78.96, "elapsed_time": "0:08:38", "remaining_time": "0:02:18", "throughput": 2179.45, "total_tokens": 1129920} {"current_steps": 2500, "total_steps": 3160, "loss": 0.0013, "lr": 0.00012746822919168694, "epoch": 15.822784810126583, "percentage": 79.11, "elapsed_time": "0:08:39", "remaining_time": "0:02:17", "throughput": 2179.71, "total_tokens": 1132128} {"current_steps": 2505, "total_steps": 3160, "loss": 0.0002, "lr": 0.00012563195353511175, "epoch": 15.854430379746836, "percentage": 79.27, "elapsed_time": "0:08:40", "remaining_time": "0:02:16", "throughput": 2180.03, "total_tokens": 1134400} {"current_steps": 2510, "total_steps": 3160, "loss": 0.0011, "lr": 0.00012380709819764219, "epoch": 15.886075949367088, "percentage": 79.43, "elapsed_time": "0:08:41", "remaining_time": "0:02:15", "throughput": 2180.34, "total_tokens": 1136640} {"current_steps": 2515, "total_steps": 3160, "loss": 0.0007, "lr": 0.00012199371884757171, "epoch": 15.917721518987342, "percentage": 79.59, "elapsed_time": "0:08:42", "remaining_time": "0:02:13", "throughput": 2180.81, "total_tokens": 1139008} {"current_steps": 2520, "total_steps": 3160, "loss": 0.0008, "lr": 0.00012019187080311228, "epoch": 15.949367088607595, "percentage": 79.75, "elapsed_time": "0:08:43", "remaining_time": "0:02:12", "throughput": 2181.17, "total_tokens": 1141280} {"current_steps": 2525, "total_steps": 3160, "loss": 0.0002, "lr": 0.0001184016090307059, "epoch": 15.981012658227849, "percentage": 79.91, "elapsed_time": "0:08:44", "remaining_time": "0:02:11", "throughput": 2181.53, "total_tokens": 1143552} {"current_steps": 2528, "total_steps": 3160, "eval_loss": 0.2718905806541443, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "0:08:46", "remaining_time": "0:02:11", "throughput": 2174.62, "total_tokens": 1144672} {"current_steps": 2530, "total_steps": 3160, "loss": 0.0004, "lr": 0.00011662298814334899, "epoch": 16.0126582278481, "percentage": 80.06, "elapsed_time": "0:08:47", "remaining_time": "0:02:11", "throughput": 2170.5, "total_tokens": 1145536} {"current_steps": 2535, "total_steps": 3160, "loss": 0.001, "lr": 0.00011485606239892587, "epoch": 16.044303797468356, "percentage": 80.22, "elapsed_time": "0:08:48", "remaining_time": "0:02:10", "throughput": 2170.83, "total_tokens": 1147840} {"current_steps": 2540, "total_steps": 3160, "loss": 0.0003, "lr": 0.00011310088569855315, "epoch": 16.075949367088608, "percentage": 80.38, "elapsed_time": "0:08:49", "remaining_time": "0:02:09", "throughput": 2171.0, "total_tokens": 1149984} {"current_steps": 2545, "total_steps": 3160, "loss": 0.0001, "lr": 0.00011135751158493634, "epoch": 16.10759493670886, "percentage": 80.54, "elapsed_time": "0:08:50", "remaining_time": "0:02:08", "throughput": 2171.26, "total_tokens": 1152192} {"current_steps": 2550, "total_steps": 3160, "loss": 0.0005, "lr": 0.00010962599324073586, "epoch": 16.139240506329113, "percentage": 80.7, "elapsed_time": "0:08:51", "remaining_time": "0:02:07", "throughput": 2171.8, "total_tokens": 1154592} {"current_steps": 2555, "total_steps": 3160, "loss": 0.0012, "lr": 0.00010790638348694487, "epoch": 16.170886075949365, "percentage": 80.85, "elapsed_time": "0:08:52", "remaining_time": "0:02:06", "throughput": 2172.07, "total_tokens": 1156800} {"current_steps": 2560, "total_steps": 3160, "loss": 0.0002, "lr": 0.00010619873478127817, "epoch": 16.20253164556962, "percentage": 81.01, "elapsed_time": "0:08:53", "remaining_time": "0:02:05", "throughput": 2172.44, "total_tokens": 1159104} {"current_steps": 2565, "total_steps": 3160, "loss": 0.0005, "lr": 0.00010450309921657114, "epoch": 16.234177215189874, "percentage": 81.17, "elapsed_time": "0:08:54", "remaining_time": "0:02:03", "throughput": 2172.71, "total_tokens": 1161312} {"current_steps": 2570, "total_steps": 3160, "loss": 0.0004, "lr": 0.00010281952851919158, "epoch": 16.265822784810126, "percentage": 81.33, "elapsed_time": "0:08:55", "remaining_time": "0:02:02", "throughput": 2172.97, "total_tokens": 1163520} {"current_steps": 2575, "total_steps": 3160, "loss": 0.0003, "lr": 0.00010114807404746151, "epoch": 16.29746835443038, "percentage": 81.49, "elapsed_time": "0:08:56", "remaining_time": "0:02:01", "throughput": 2173.33, "total_tokens": 1165792} {"current_steps": 2580, "total_steps": 3160, "loss": 0.0016, "lr": 9.948878679008977e-05, "epoch": 16.32911392405063, "percentage": 81.65, "elapsed_time": "0:08:57", "remaining_time": "0:02:00", "throughput": 2173.59, "total_tokens": 1168000} {"current_steps": 2585, "total_steps": 3160, "loss": 0.0002, "lr": 9.78417173646176e-05, "epoch": 16.360759493670887, "percentage": 81.8, "elapsed_time": "0:08:58", "remaining_time": "0:01:59", "throughput": 2173.86, "total_tokens": 1170208} {"current_steps": 2590, "total_steps": 3160, "loss": 0.0003, "lr": 9.620691601587384e-05, "epoch": 16.39240506329114, "percentage": 81.96, "elapsed_time": "0:08:59", "remaining_time": "0:01:58", "throughput": 2174.28, "total_tokens": 1172544} {"current_steps": 2595, "total_steps": 3160, "loss": 0.0002, "lr": 9.458443261444255e-05, "epoch": 16.424050632911392, "percentage": 82.12, "elapsed_time": "0:09:00", "remaining_time": "0:01:57", "throughput": 2174.64, "total_tokens": 1174816} {"current_steps": 2600, "total_steps": 3160, "loss": 0.0005, "lr": 9.297431665514111e-05, "epoch": 16.455696202531644, "percentage": 82.28, "elapsed_time": "0:09:01", "remaining_time": "0:01:56", "throughput": 2174.96, "total_tokens": 1177056} {"current_steps": 2605, "total_steps": 3160, "loss": 0.0003, "lr": 9.137661725551111e-05, "epoch": 16.4873417721519, "percentage": 82.44, "elapsed_time": "0:09:02", "remaining_time": "0:01:55", "throughput": 2175.33, "total_tokens": 1179392} {"current_steps": 2610, "total_steps": 3160, "loss": 0.0002, "lr": 8.97913831543195e-05, "epoch": 16.518987341772153, "percentage": 82.59, "elapsed_time": "0:09:03", "remaining_time": "0:01:54", "throughput": 2175.68, "total_tokens": 1181664} {"current_steps": 2615, "total_steps": 3160, "loss": 0.0005, "lr": 8.821866271007218e-05, "epoch": 16.550632911392405, "percentage": 82.75, "elapsed_time": "0:09:04", "remaining_time": "0:01:53", "throughput": 2175.84, "total_tokens": 1183808} {"current_steps": 2620, "total_steps": 3160, "loss": 0.0004, "lr": 8.665850389953788e-05, "epoch": 16.582278481012658, "percentage": 82.91, "elapsed_time": "0:09:05", "remaining_time": "0:01:52", "throughput": 2176.32, "total_tokens": 1186240} {"current_steps": 2625, "total_steps": 3160, "loss": 0.0004, "lr": 8.511095431628591e-05, "epoch": 16.61392405063291, "percentage": 83.07, "elapsed_time": "0:09:06", "remaining_time": "0:01:51", "throughput": 2176.89, "total_tokens": 1188704} {"current_steps": 2630, "total_steps": 3160, "loss": 0.0004, "lr": 8.357606116923328e-05, "epoch": 16.645569620253166, "percentage": 83.23, "elapsed_time": "0:09:07", "remaining_time": "0:01:50", "throughput": 2177.19, "total_tokens": 1190944} {"current_steps": 2635, "total_steps": 3160, "loss": 0.0007, "lr": 8.205387128120518e-05, "epoch": 16.67721518987342, "percentage": 83.39, "elapsed_time": "0:09:07", "remaining_time": "0:01:49", "throughput": 2177.5, "total_tokens": 1193216} {"current_steps": 2640, "total_steps": 3160, "loss": 0.0004, "lr": 8.054443108750592e-05, "epoch": 16.70886075949367, "percentage": 83.54, "elapsed_time": "0:09:08", "remaining_time": "0:01:48", "throughput": 2177.95, "total_tokens": 1195584} {"current_steps": 2645, "total_steps": 3160, "loss": 0.0007, "lr": 7.904778663450324e-05, "epoch": 16.740506329113924, "percentage": 83.7, "elapsed_time": "0:09:09", "remaining_time": "0:01:47", "throughput": 2178.25, "total_tokens": 1197824} {"current_steps": 2650, "total_steps": 3160, "loss": 0.0, "lr": 7.75639835782232e-05, "epoch": 16.772151898734176, "percentage": 83.86, "elapsed_time": "0:09:10", "remaining_time": "0:01:46", "throughput": 2178.5, "total_tokens": 1200032} {"current_steps": 2655, "total_steps": 3160, "loss": 0.0005, "lr": 7.60930671829571e-05, "epoch": 16.803797468354432, "percentage": 84.02, "elapsed_time": "0:09:11", "remaining_time": "0:01:44", "throughput": 2178.74, "total_tokens": 1202240} {"current_steps": 2660, "total_steps": 3160, "loss": 0.0005, "lr": 7.46350823198813e-05, "epoch": 16.835443037974684, "percentage": 84.18, "elapsed_time": "0:09:12", "remaining_time": "0:01:43", "throughput": 2179.14, "total_tokens": 1204576} {"current_steps": 2665, "total_steps": 3160, "loss": 0.0004, "lr": 7.319007346568817e-05, "epoch": 16.867088607594937, "percentage": 84.34, "elapsed_time": "0:09:13", "remaining_time": "0:01:42", "throughput": 2179.44, "total_tokens": 1206816} {"current_steps": 2670, "total_steps": 3160, "loss": 0.0005, "lr": 7.175808470122897e-05, "epoch": 16.89873417721519, "percentage": 84.49, "elapsed_time": "0:09:14", "remaining_time": "0:01:41", "throughput": 2179.83, "total_tokens": 1209120} {"current_steps": 2675, "total_steps": 3160, "loss": 0.0001, "lr": 7.033915971016952e-05, "epoch": 16.930379746835442, "percentage": 84.65, "elapsed_time": "0:09:15", "remaining_time": "0:01:40", "throughput": 2180.32, "total_tokens": 1211552} {"current_steps": 2680, "total_steps": 3160, "loss": 0.0002, "lr": 6.893334177765759e-05, "epoch": 16.962025316455698, "percentage": 84.81, "elapsed_time": "0:09:16", "remaining_time": "0:01:39", "throughput": 2180.37, "total_tokens": 1213632} {"current_steps": 2685, "total_steps": 3160, "loss": 0.0003, "lr": 6.75406737890023e-05, "epoch": 16.99367088607595, "percentage": 84.97, "elapsed_time": "0:09:17", "remaining_time": "0:01:38", "throughput": 2180.73, "total_tokens": 1215968} {"current_steps": 2686, "total_steps": 3160, "eval_loss": 0.2750537693500519, "epoch": 17.0, "percentage": 85.0, "elapsed_time": "0:09:19", "remaining_time": "0:01:38", "throughput": 2174.07, "total_tokens": 1216160} {"current_steps": 2690, "total_steps": 3160, "loss": 0.0006, "lr": 6.616119822836609e-05, "epoch": 17.025316455696203, "percentage": 85.13, "elapsed_time": "0:09:21", "remaining_time": "0:01:38", "throughput": 2170.74, "total_tokens": 1217888} {"current_steps": 2695, "total_steps": 3160, "loss": 0.001, "lr": 6.479495717746808e-05, "epoch": 17.056962025316455, "percentage": 85.28, "elapsed_time": "0:09:22", "remaining_time": "0:01:36", "throughput": 2171.0, "total_tokens": 1220128} {"current_steps": 2700, "total_steps": 3160, "loss": 0.0003, "lr": 6.344199231430132e-05, "epoch": 17.088607594936708, "percentage": 85.44, "elapsed_time": "0:09:22", "remaining_time": "0:01:35", "throughput": 2171.41, "total_tokens": 1222432} {"current_steps": 2705, "total_steps": 3160, "loss": 0.0005, "lr": 6.210234491186079e-05, "epoch": 17.120253164556964, "percentage": 85.6, "elapsed_time": "0:09:23", "remaining_time": "0:01:34", "throughput": 2171.85, "total_tokens": 1224768} {"current_steps": 2710, "total_steps": 3160, "loss": 0.001, "lr": 6.077605583688417e-05, "epoch": 17.151898734177216, "percentage": 85.76, "elapsed_time": "0:09:24", "remaining_time": "0:01:33", "throughput": 2172.25, "total_tokens": 1227136} {"current_steps": 2715, "total_steps": 3160, "loss": 0.0002, "lr": 5.946316554860581e-05, "epoch": 17.18354430379747, "percentage": 85.92, "elapsed_time": "0:09:25", "remaining_time": "0:01:32", "throughput": 2172.51, "total_tokens": 1229344} {"current_steps": 2720, "total_steps": 3160, "loss": 0.0002, "lr": 5.8163714097522025e-05, "epoch": 17.21518987341772, "percentage": 86.08, "elapsed_time": "0:09:26", "remaining_time": "0:01:31", "throughput": 2172.76, "total_tokens": 1231552} {"current_steps": 2725, "total_steps": 3160, "loss": 0.001, "lr": 5.6877741124169045e-05, "epoch": 17.246835443037973, "percentage": 86.23, "elapsed_time": "0:09:27", "remaining_time": "0:01:30", "throughput": 2173.1, "total_tokens": 1233824} {"current_steps": 2730, "total_steps": 3160, "loss": 0.0002, "lr": 5.560528585791491e-05, "epoch": 17.27848101265823, "percentage": 86.39, "elapsed_time": "0:09:28", "remaining_time": "0:01:29", "throughput": 2173.5, "total_tokens": 1236160} {"current_steps": 2735, "total_steps": 3160, "loss": 0.0004, "lr": 5.434638711576123e-05, "epoch": 17.310126582278482, "percentage": 86.55, "elapsed_time": "0:09:29", "remaining_time": "0:01:28", "throughput": 2173.84, "total_tokens": 1238464} {"current_steps": 2740, "total_steps": 3160, "loss": 0.0008, "lr": 5.310108330116037e-05, "epoch": 17.341772151898734, "percentage": 86.71, "elapsed_time": "0:09:30", "remaining_time": "0:01:27", "throughput": 2174.13, "total_tokens": 1240704} {"current_steps": 2745, "total_steps": 3160, "loss": 0.0002, "lr": 5.18694124028431e-05, "epoch": 17.373417721518987, "percentage": 86.87, "elapsed_time": "0:09:31", "remaining_time": "0:01:26", "throughput": 2174.44, "total_tokens": 1243008} {"current_steps": 2750, "total_steps": 3160, "loss": 0.0002, "lr": 5.065141199365991e-05, "epoch": 17.40506329113924, "percentage": 87.03, "elapsed_time": "0:09:32", "remaining_time": "0:01:25", "throughput": 2174.64, "total_tokens": 1245184} {"current_steps": 2755, "total_steps": 3160, "loss": 0.0002, "lr": 4.944711922943523e-05, "epoch": 17.436708860759495, "percentage": 87.18, "elapsed_time": "0:09:33", "remaining_time": "0:01:24", "throughput": 2174.97, "total_tokens": 1247456} {"current_steps": 2760, "total_steps": 3160, "loss": 0.0002, "lr": 4.825657084783347e-05, "epoch": 17.468354430379748, "percentage": 87.34, "elapsed_time": "0:09:34", "remaining_time": "0:01:23", "throughput": 2175.35, "total_tokens": 1249760} {"current_steps": 2765, "total_steps": 3160, "loss": 0.0005, "lr": 4.7079803167238366e-05, "epoch": 17.5, "percentage": 87.5, "elapsed_time": "0:09:35", "remaining_time": "0:01:22", "throughput": 2175.65, "total_tokens": 1252032} {"current_steps": 2770, "total_steps": 3160, "loss": 0.0002, "lr": 4.591685208564561e-05, "epoch": 17.531645569620252, "percentage": 87.66, "elapsed_time": "0:09:36", "remaining_time": "0:01:21", "throughput": 2175.87, "total_tokens": 1254240} {"current_steps": 2775, "total_steps": 3160, "loss": 0.0006, "lr": 4.476775307956699e-05, "epoch": 17.563291139240505, "percentage": 87.82, "elapsed_time": "0:09:37", "remaining_time": "0:01:20", "throughput": 2176.17, "total_tokens": 1256512} {"current_steps": 2780, "total_steps": 3160, "loss": 0.0, "lr": 4.363254120294846e-05, "epoch": 17.59493670886076, "percentage": 87.97, "elapsed_time": "0:09:38", "remaining_time": "0:01:19", "throughput": 2176.5, "total_tokens": 1258784} {"current_steps": 2785, "total_steps": 3160, "loss": 0.0002, "lr": 4.2511251086101373e-05, "epoch": 17.626582278481013, "percentage": 88.13, "elapsed_time": "0:09:39", "remaining_time": "0:01:18", "throughput": 2176.79, "total_tokens": 1261024} {"current_steps": 2790, "total_steps": 3160, "loss": 0.0004, "lr": 4.14039169346449e-05, "epoch": 17.658227848101266, "percentage": 88.29, "elapsed_time": "0:09:40", "remaining_time": "0:01:16", "throughput": 2177.18, "total_tokens": 1263392} {"current_steps": 2795, "total_steps": 3160, "loss": 0.0005, "lr": 4.031057252846371e-05, "epoch": 17.689873417721518, "percentage": 88.45, "elapsed_time": "0:09:41", "remaining_time": "0:01:15", "throughput": 2177.38, "total_tokens": 1265600} {"current_steps": 2800, "total_steps": 3160, "loss": 0.0001, "lr": 3.923125122067689e-05, "epoch": 17.72151898734177, "percentage": 88.61, "elapsed_time": "0:09:42", "remaining_time": "0:01:14", "throughput": 2177.61, "total_tokens": 1267808} {"current_steps": 2805, "total_steps": 3160, "loss": 0.0004, "lr": 3.816598593662024e-05, "epoch": 17.753164556962027, "percentage": 88.77, "elapsed_time": "0:09:43", "remaining_time": "0:01:13", "throughput": 2177.84, "total_tokens": 1270016} {"current_steps": 2810, "total_steps": 3160, "loss": 0.0004, "lr": 3.711480917284282e-05, "epoch": 17.78481012658228, "percentage": 88.92, "elapsed_time": "0:09:44", "remaining_time": "0:01:12", "throughput": 2178.32, "total_tokens": 1272448} {"current_steps": 2815, "total_steps": 3160, "loss": 0.0004, "lr": 3.607775299611465e-05, "epoch": 17.81645569620253, "percentage": 89.08, "elapsed_time": "0:09:45", "remaining_time": "0:01:11", "throughput": 2178.75, "total_tokens": 1274848} {"current_steps": 2820, "total_steps": 3160, "loss": 0.0003, "lr": 3.505484904244877e-05, "epoch": 17.848101265822784, "percentage": 89.24, "elapsed_time": "0:09:46", "remaining_time": "0:01:10", "throughput": 2179.09, "total_tokens": 1277152} {"current_steps": 2825, "total_steps": 3160, "loss": 0.0002, "lr": 3.404612851613675e-05, "epoch": 17.879746835443036, "percentage": 89.4, "elapsed_time": "0:09:47", "remaining_time": "0:01:09", "throughput": 2179.46, "total_tokens": 1279488} {"current_steps": 2830, "total_steps": 3160, "loss": 0.0006, "lr": 3.305162218879576e-05, "epoch": 17.911392405063292, "percentage": 89.56, "elapsed_time": "0:09:48", "remaining_time": "0:01:08", "throughput": 2179.73, "total_tokens": 1281728} {"current_steps": 2835, "total_steps": 3160, "loss": 0.0001, "lr": 3.207136039843078e-05, "epoch": 17.943037974683545, "percentage": 89.72, "elapsed_time": "0:09:48", "remaining_time": "0:01:07", "throughput": 2180.01, "total_tokens": 1284000} {"current_steps": 2840, "total_steps": 3160, "loss": 0.0003, "lr": 3.110537304850869e-05, "epoch": 17.974683544303797, "percentage": 89.87, "elapsed_time": "0:09:49", "remaining_time": "0:01:06", "throughput": 2180.2, "total_tokens": 1286176} {"current_steps": 2844, "total_steps": 3160, "eval_loss": 0.276852011680603, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "0:09:52", "remaining_time": "0:01:05", "throughput": 2174.05, "total_tokens": 1287728} {"current_steps": 2845, "total_steps": 3160, "loss": 0.0003, "lr": 3.0153689607045842e-05, "epoch": 18.00632911392405, "percentage": 90.03, "elapsed_time": "0:09:53", "remaining_time": "0:01:05", "throughput": 2170.86, "total_tokens": 1288176} {"current_steps": 2850, "total_steps": 3160, "loss": 0.0002, "lr": 2.92163391057097e-05, "epoch": 18.037974683544302, "percentage": 90.19, "elapsed_time": "0:09:54", "remaining_time": "0:01:04", "throughput": 2171.08, "total_tokens": 1290384} {"current_steps": 2855, "total_steps": 3160, "loss": 0.0002, "lr": 2.8293350138932806e-05, "epoch": 18.069620253164558, "percentage": 90.35, "elapsed_time": "0:09:55", "remaining_time": "0:01:03", "throughput": 2171.31, "total_tokens": 1292592} {"current_steps": 2860, "total_steps": 3160, "loss": 0.0001, "lr": 2.738475086304032e-05, "epoch": 18.10126582278481, "percentage": 90.51, "elapsed_time": "0:09:56", "remaining_time": "0:01:02", "throughput": 2171.61, "total_tokens": 1294864} {"current_steps": 2865, "total_steps": 3160, "loss": 0.0004, "lr": 2.6490568995391984e-05, "epoch": 18.132911392405063, "percentage": 90.66, "elapsed_time": "0:09:57", "remaining_time": "0:01:01", "throughput": 2171.98, "total_tokens": 1297168} {"current_steps": 2870, "total_steps": 3160, "loss": 0.0003, "lr": 2.561083181353524e-05, "epoch": 18.164556962025316, "percentage": 90.82, "elapsed_time": "0:09:58", "remaining_time": "0:01:00", "throughput": 2172.46, "total_tokens": 1299600} {"current_steps": 2875, "total_steps": 3160, "loss": 0.0001, "lr": 2.4745566154374234e-05, "epoch": 18.196202531645568, "percentage": 90.98, "elapsed_time": "0:09:59", "remaining_time": "0:00:59", "throughput": 2172.7, "total_tokens": 1301808} {"current_steps": 2880, "total_steps": 3160, "loss": 0.0002, "lr": 2.3894798413350738e-05, "epoch": 18.227848101265824, "percentage": 91.14, "elapsed_time": "0:10:00", "remaining_time": "0:00:58", "throughput": 2173.07, "total_tokens": 1304144} {"current_steps": 2885, "total_steps": 3160, "loss": 0.0004, "lr": 2.30585545436387e-05, "epoch": 18.259493670886076, "percentage": 91.3, "elapsed_time": "0:10:01", "remaining_time": "0:00:57", "throughput": 2173.3, "total_tokens": 1306352} {"current_steps": 2890, "total_steps": 3160, "loss": 0.0005, "lr": 2.223686005535297e-05, "epoch": 18.29113924050633, "percentage": 91.46, "elapsed_time": "0:10:02", "remaining_time": "0:00:56", "throughput": 2173.48, "total_tokens": 1308528} {"current_steps": 2895, "total_steps": 3160, "loss": 0.0007, "lr": 2.1429740014770993e-05, "epoch": 18.32278481012658, "percentage": 91.61, "elapsed_time": "0:10:02", "remaining_time": "0:00:55", "throughput": 2173.66, "total_tokens": 1310704} {"current_steps": 2900, "total_steps": 3160, "loss": 0.0013, "lr": 2.0637219043567636e-05, "epoch": 18.354430379746834, "percentage": 91.77, "elapsed_time": "0:10:03", "remaining_time": "0:00:54", "throughput": 2173.99, "total_tokens": 1313008} {"current_steps": 2905, "total_steps": 3160, "loss": 0.0012, "lr": 1.985932131806495e-05, "epoch": 18.38607594936709, "percentage": 91.93, "elapsed_time": "0:10:04", "remaining_time": "0:00:53", "throughput": 2174.29, "total_tokens": 1315280} {"current_steps": 2910, "total_steps": 3160, "loss": 0.0003, "lr": 1.9096070568493996e-05, "epoch": 18.417721518987342, "percentage": 92.09, "elapsed_time": "0:10:05", "remaining_time": "0:00:52", "throughput": 2174.52, "total_tokens": 1317488} {"current_steps": 2915, "total_steps": 3160, "loss": 0.0002, "lr": 1.8347490078271244e-05, "epoch": 18.449367088607595, "percentage": 92.25, "elapsed_time": "0:10:06", "remaining_time": "0:00:51", "throughput": 2174.75, "total_tokens": 1319696} {"current_steps": 2920, "total_steps": 3160, "loss": 0.0003, "lr": 1.7613602683288044e-05, "epoch": 18.481012658227847, "percentage": 92.41, "elapsed_time": "0:10:07", "remaining_time": "0:00:49", "throughput": 2174.9, "total_tokens": 1321840} {"current_steps": 2925, "total_steps": 3160, "loss": 0.0001, "lr": 1.6894430771214277e-05, "epoch": 18.5126582278481, "percentage": 92.56, "elapsed_time": "0:10:08", "remaining_time": "0:00:48", "throughput": 2175.12, "total_tokens": 1324048} {"current_steps": 2930, "total_steps": 3160, "loss": 0.0007, "lr": 1.6189996280815354e-05, "epoch": 18.544303797468356, "percentage": 92.72, "elapsed_time": "0:10:09", "remaining_time": "0:00:47", "throughput": 2175.53, "total_tokens": 1326416} {"current_steps": 2935, "total_steps": 3160, "loss": 0.0003, "lr": 1.5500320701282934e-05, "epoch": 18.575949367088608, "percentage": 92.88, "elapsed_time": "0:10:10", "remaining_time": "0:00:46", "throughput": 2175.76, "total_tokens": 1328624} {"current_steps": 2940, "total_steps": 3160, "loss": 0.0002, "lr": 1.4825425071579079e-05, "epoch": 18.60759493670886, "percentage": 93.04, "elapsed_time": "0:10:11", "remaining_time": "0:00:45", "throughput": 2176.13, "total_tokens": 1330992} {"current_steps": 2945, "total_steps": 3160, "loss": 0.0002, "lr": 1.4165329979794973e-05, "epoch": 18.639240506329113, "percentage": 93.2, "elapsed_time": "0:10:12", "remaining_time": "0:00:44", "throughput": 2176.54, "total_tokens": 1333360} {"current_steps": 2950, "total_steps": 3160, "loss": 0.0001, "lr": 1.3520055562522671e-05, "epoch": 18.67088607594937, "percentage": 93.35, "elapsed_time": "0:10:13", "remaining_time": "0:00:43", "throughput": 2176.73, "total_tokens": 1335536} {"current_steps": 2955, "total_steps": 3160, "loss": 0.0002, "lr": 1.2889621504240557e-05, "epoch": 18.70253164556962, "percentage": 93.51, "elapsed_time": "0:10:14", "remaining_time": "0:00:42", "throughput": 2177.12, "total_tokens": 1337872} {"current_steps": 2960, "total_steps": 3160, "loss": 0.0003, "lr": 1.2274047036713198e-05, "epoch": 18.734177215189874, "percentage": 93.67, "elapsed_time": "0:10:15", "remaining_time": "0:00:41", "throughput": 2177.48, "total_tokens": 1340208} {"current_steps": 2965, "total_steps": 3160, "loss": 0.0004, "lr": 1.1673350938404493e-05, "epoch": 18.765822784810126, "percentage": 93.83, "elapsed_time": "0:10:16", "remaining_time": "0:00:40", "throughput": 2177.75, "total_tokens": 1342448} {"current_steps": 2970, "total_steps": 3160, "loss": 0.0004, "lr": 1.1087551533904894e-05, "epoch": 18.79746835443038, "percentage": 93.99, "elapsed_time": "0:10:17", "remaining_time": "0:00:39", "throughput": 2178.05, "total_tokens": 1344720} {"current_steps": 2975, "total_steps": 3160, "loss": 0.0002, "lr": 1.0516666693372423e-05, "epoch": 18.82911392405063, "percentage": 94.15, "elapsed_time": "0:10:18", "remaining_time": "0:00:38", "throughput": 2178.42, "total_tokens": 1347088} {"current_steps": 2980, "total_steps": 3160, "loss": 0.0001, "lr": 9.960713831987323e-06, "epoch": 18.860759493670887, "percentage": 94.3, "elapsed_time": "0:10:19", "remaining_time": "0:00:37", "throughput": 2178.69, "total_tokens": 1349360} {"current_steps": 2985, "total_steps": 3160, "loss": 0.0009, "lr": 9.419709909421203e-06, "epoch": 18.89240506329114, "percentage": 94.46, "elapsed_time": "0:10:20", "remaining_time": "0:00:36", "throughput": 2178.94, "total_tokens": 1351600} {"current_steps": 2990, "total_steps": 3160, "loss": 0.0003, "lr": 8.893671429319295e-06, "epoch": 18.924050632911392, "percentage": 94.62, "elapsed_time": "0:10:21", "remaining_time": "0:00:35", "throughput": 2179.12, "total_tokens": 1353776} {"current_steps": 2995, "total_steps": 3160, "loss": 0.0004, "lr": 8.382614438797177e-06, "epoch": 18.955696202531644, "percentage": 94.78, "elapsed_time": "0:10:22", "remaining_time": "0:00:34", "throughput": 2179.43, "total_tokens": 1356080} {"current_steps": 3000, "total_steps": 3160, "loss": 0.0005, "lr": 7.886554527951117e-06, "epoch": 18.9873417721519, "percentage": 94.94, "elapsed_time": "0:10:23", "remaining_time": "0:00:33", "throughput": 2179.82, "total_tokens": 1358448} {"current_steps": 3002, "total_steps": 3160, "eval_loss": 0.28090646862983704, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "0:10:25", "remaining_time": "0:00:32", "throughput": 2173.94, "total_tokens": 1359120} {"current_steps": 3005, "total_steps": 3160, "loss": 0.0005, "lr": 7.405506829382736e-06, "epoch": 19.018987341772153, "percentage": 95.09, "elapsed_time": "0:10:26", "remaining_time": "0:00:32", "throughput": 2170.87, "total_tokens": 1360464} {"current_steps": 3010, "total_steps": 3160, "loss": 0.0007, "lr": 6.9394860177370845e-06, "epoch": 19.050632911392405, "percentage": 95.25, "elapsed_time": "0:10:27", "remaining_time": "0:00:31", "throughput": 2171.23, "total_tokens": 1362832} {"current_steps": 3015, "total_steps": 3160, "loss": 0.0001, "lr": 6.488506309255238e-06, "epoch": 19.082278481012658, "percentage": 95.41, "elapsed_time": "0:10:28", "remaining_time": "0:00:30", "throughput": 2171.5, "total_tokens": 1365072} {"current_steps": 3020, "total_steps": 3160, "loss": 0.0002, "lr": 6.052581461340411e-06, "epoch": 19.11392405063291, "percentage": 95.57, "elapsed_time": "0:10:29", "remaining_time": "0:00:29", "throughput": 2171.89, "total_tokens": 1367440} {"current_steps": 3025, "total_steps": 3160, "loss": 0.0002, "lr": 5.631724772138469e-06, "epoch": 19.145569620253166, "percentage": 95.73, "elapsed_time": "0:10:30", "remaining_time": "0:00:28", "throughput": 2172.21, "total_tokens": 1369744} {"current_steps": 3030, "total_steps": 3160, "loss": 0.0009, "lr": 5.225949080131964e-06, "epoch": 19.17721518987342, "percentage": 95.89, "elapsed_time": "0:10:31", "remaining_time": "0:00:27", "throughput": 2172.45, "total_tokens": 1371984} {"current_steps": 3035, "total_steps": 3160, "loss": 0.0004, "lr": 4.8352667637490684e-06, "epoch": 19.20886075949367, "percentage": 96.04, "elapsed_time": "0:10:32", "remaining_time": "0:00:26", "throughput": 2172.76, "total_tokens": 1374288} {"current_steps": 3040, "total_steps": 3160, "loss": 0.0002, "lr": 4.459689740985206e-06, "epoch": 19.240506329113924, "percentage": 96.2, "elapsed_time": "0:10:33", "remaining_time": "0:00:25", "throughput": 2172.99, "total_tokens": 1376496} {"current_steps": 3045, "total_steps": 3160, "loss": 0.0003, "lr": 4.099229469040011e-06, "epoch": 19.272151898734176, "percentage": 96.36, "elapsed_time": "0:10:34", "remaining_time": "0:00:23", "throughput": 2173.25, "total_tokens": 1378736} {"current_steps": 3050, "total_steps": 3160, "loss": 0.0003, "lr": 3.7538969439678272e-06, "epoch": 19.303797468354432, "percentage": 96.52, "elapsed_time": "0:10:35", "remaining_time": "0:00:22", "throughput": 2173.47, "total_tokens": 1380944} {"current_steps": 3055, "total_steps": 3160, "loss": 0.0001, "lr": 3.423702700341813e-06, "epoch": 19.335443037974684, "percentage": 96.68, "elapsed_time": "0:10:36", "remaining_time": "0:00:21", "throughput": 2173.81, "total_tokens": 1383248} {"current_steps": 3060, "total_steps": 3160, "loss": 0.0003, "lr": 3.1086568109331413e-06, "epoch": 19.367088607594937, "percentage": 96.84, "elapsed_time": "0:10:37", "remaining_time": "0:00:20", "throughput": 2174.08, "total_tokens": 1385488} {"current_steps": 3065, "total_steps": 3160, "loss": 0.0005, "lr": 2.8087688864033013e-06, "epoch": 19.39873417721519, "percentage": 96.99, "elapsed_time": "0:10:38", "remaining_time": "0:00:19", "throughput": 2174.38, "total_tokens": 1387760} {"current_steps": 3070, "total_steps": 3160, "loss": 0.0002, "lr": 2.524048075011165e-06, "epoch": 19.430379746835442, "percentage": 97.15, "elapsed_time": "0:10:39", "remaining_time": "0:00:18", "throughput": 2174.82, "total_tokens": 1390192} {"current_steps": 3075, "total_steps": 3160, "loss": 0.0006, "lr": 2.254503062333824e-06, "epoch": 19.462025316455698, "percentage": 97.31, "elapsed_time": "0:10:40", "remaining_time": "0:00:17", "throughput": 2175.1, "total_tokens": 1392464} {"current_steps": 3080, "total_steps": 3160, "loss": 0.0001, "lr": 2.0001420710016318e-06, "epoch": 19.49367088607595, "percentage": 97.47, "elapsed_time": "0:10:41", "remaining_time": "0:00:16", "throughput": 2175.44, "total_tokens": 1394768} {"current_steps": 3085, "total_steps": 3160, "loss": 0.0005, "lr": 1.7609728604472963e-06, "epoch": 19.525316455696203, "percentage": 97.63, "elapsed_time": "0:10:42", "remaining_time": "0:00:15", "throughput": 2175.79, "total_tokens": 1397072} {"current_steps": 3090, "total_steps": 3160, "loss": 0.0003, "lr": 1.5370027266694008e-06, "epoch": 19.556962025316455, "percentage": 97.78, "elapsed_time": "0:10:43", "remaining_time": "0:00:14", "throughput": 2176.06, "total_tokens": 1399344} {"current_steps": 3095, "total_steps": 3160, "loss": 0.0002, "lr": 1.3282385020095267e-06, "epoch": 19.588607594936708, "percentage": 97.94, "elapsed_time": "0:10:44", "remaining_time": "0:00:13", "throughput": 2176.27, "total_tokens": 1401552} {"current_steps": 3100, "total_steps": 3160, "loss": 0.0003, "lr": 1.1346865549440867e-06, "epoch": 19.620253164556964, "percentage": 98.1, "elapsed_time": "0:10:44", "remaining_time": "0:00:12", "throughput": 2176.46, "total_tokens": 1403760} {"current_steps": 3105, "total_steps": 3160, "loss": 0.0001, "lr": 9.563527898899805e-07, "epoch": 19.651898734177216, "percentage": 98.26, "elapsed_time": "0:10:45", "remaining_time": "0:00:11", "throughput": 2176.71, "total_tokens": 1406000} {"current_steps": 3110, "total_steps": 3160, "loss": 0.0009, "lr": 7.932426470242948e-07, "epoch": 19.68354430379747, "percentage": 98.42, "elapsed_time": "0:10:46", "remaining_time": "0:00:10", "throughput": 2176.92, "total_tokens": 1408208} {"current_steps": 3115, "total_steps": 3160, "loss": 0.0001, "lr": 6.453611021186578e-07, "epoch": 19.71518987341772, "percentage": 98.58, "elapsed_time": "0:10:47", "remaining_time": "0:00:09", "throughput": 2177.13, "total_tokens": 1410416} {"current_steps": 3120, "total_steps": 3160, "loss": 0.0001, "lr": 5.12712666387194e-07, "epoch": 19.746835443037973, "percentage": 98.73, "elapsed_time": "0:10:48", "remaining_time": "0:00:08", "throughput": 2177.3, "total_tokens": 1412592} {"current_steps": 3125, "total_steps": 3160, "loss": 0.0002, "lr": 3.953013863490784e-07, "epoch": 19.77848101265823, "percentage": 98.89, "elapsed_time": "0:10:49", "remaining_time": "0:00:07", "throughput": 2177.66, "total_tokens": 1414960} {"current_steps": 3130, "total_steps": 3160, "loss": 0.0002, "lr": 2.9313084370496955e-07, "epoch": 19.810126582278482, "percentage": 99.05, "elapsed_time": "0:10:50", "remaining_time": "0:00:06", "throughput": 2177.92, "total_tokens": 1417232} {"current_steps": 3135, "total_steps": 3160, "loss": 0.0002, "lr": 2.062041552277627e-07, "epoch": 19.841772151898734, "percentage": 99.21, "elapsed_time": "0:10:51", "remaining_time": "0:00:05", "throughput": 2178.28, "total_tokens": 1419568} {"current_steps": 3140, "total_steps": 3160, "loss": 0.0003, "lr": 1.3452397266772166e-07, "epoch": 19.873417721518987, "percentage": 99.37, "elapsed_time": "0:10:52", "remaining_time": "0:00:04", "throughput": 2178.45, "total_tokens": 1421776} {"current_steps": 3145, "total_steps": 3160, "loss": 0.0008, "lr": 7.809248267121038e-08, "epoch": 19.90506329113924, "percentage": 99.53, "elapsed_time": "0:10:53", "remaining_time": "0:00:03", "throughput": 2178.66, "total_tokens": 1424016} {"current_steps": 3150, "total_steps": 3160, "loss": 0.0003, "lr": 3.6911406714246195e-08, "epoch": 19.936708860759495, "percentage": 99.68, "elapsed_time": "0:10:54", "remaining_time": "0:00:02", "throughput": 2178.94, "total_tokens": 1426288} {"current_steps": 3155, "total_steps": 3160, "loss": 0.001, "lr": 1.0982001050041657e-08, "epoch": 19.968354430379748, "percentage": 99.84, "elapsed_time": "0:10:55", "remaining_time": "0:00:01", "throughput": 2179.24, "total_tokens": 1428592} {"current_steps": 3160, "total_steps": 3160, "loss": 0.0001, "lr": 3.0505667042435294e-10, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:10:56", "remaining_time": "0:00:00", "throughput": 2179.18, "total_tokens": 1430592} {"current_steps": 3160, "total_steps": 3160, "eval_loss": 0.27992814779281616, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:10:58", "remaining_time": "0:00:00", "throughput": 2173.75, "total_tokens": 1430592} {"current_steps": 3160, "total_steps": 3160, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:10:58", "remaining_time": "0:00:00", "throughput": 2171.03, "total_tokens": 1430592}