{"current_steps": 5, "total_steps": 40000, "loss": 2.6928, "lr": 4.999999876629946e-05, "epoch": 0.08849557522123894, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "10:47:36", "throughput": 619.23, "total_tokens": 3008} {"current_steps": 10, "total_steps": 40000, "loss": 1.1, "lr": 4.999999375439123e-05, "epoch": 0.17699115044247787, "percentage": 0.03, "elapsed_time": "0:00:07", "remaining_time": "7:48:57", "throughput": 870.92, "total_tokens": 6128} {"current_steps": 15, "total_steps": 40000, "loss": 0.5093, "lr": 4.9999984887169785e-05, "epoch": 0.26548672566371684, "percentage": 0.04, "elapsed_time": "0:00:09", "remaining_time": "6:44:01", "throughput": 995.81, "total_tokens": 9056} {"current_steps": 20, "total_steps": 40000, "loss": 0.1975, "lr": 4.9999972164636506e-05, "epoch": 0.35398230088495575, "percentage": 0.05, "elapsed_time": "0:00:11", "remaining_time": "6:11:51", "throughput": 1133.91, "total_tokens": 12656} {"current_steps": 25, "total_steps": 40000, "loss": 0.5269, "lr": 4.999995558679334e-05, "epoch": 0.4424778761061947, "percentage": 0.06, "elapsed_time": "0:00:13", "remaining_time": "5:52:25", "throughput": 1195.36, "total_tokens": 15808} {"current_steps": 30, "total_steps": 40000, "loss": 0.3717, "lr": 4.999993515364287e-05, "epoch": 0.5309734513274337, "percentage": 0.07, "elapsed_time": "0:00:15", "remaining_time": "5:39:48", "throughput": 1196.12, "total_tokens": 18304} {"current_steps": 35, "total_steps": 40000, "loss": 0.1708, "lr": 4.999991086518822e-05, "epoch": 0.6194690265486725, "percentage": 0.09, "elapsed_time": "0:00:17", "remaining_time": "5:30:35", "throughput": 1249.85, "total_tokens": 21712} {"current_steps": 40, "total_steps": 40000, "loss": 0.1173, "lr": 4.999988272143315e-05, "epoch": 0.7079646017699115, "percentage": 0.1, "elapsed_time": "0:00:19", "remaining_time": "5:23:49", "throughput": 1263.65, "total_tokens": 24576} {"current_steps": 45, "total_steps": 40000, "loss": 0.0917, "lr": 4.999985072238199e-05, "epoch": 0.7964601769911505, "percentage": 0.11, "elapsed_time": "0:00:21", "remaining_time": "5:18:32", "throughput": 1258.41, "total_tokens": 27088} {"current_steps": 50, "total_steps": 40000, "loss": 0.2997, "lr": 4.999981486803969e-05, "epoch": 0.8849557522123894, "percentage": 0.12, "elapsed_time": "0:00:23", "remaining_time": "5:14:07", "throughput": 1256.84, "total_tokens": 29648} {"current_steps": 55, "total_steps": 40000, "loss": 0.1974, "lr": 4.999977515841176e-05, "epoch": 0.9734513274336283, "percentage": 0.14, "elapsed_time": "0:00:25", "remaining_time": "5:10:23", "throughput": 1249.17, "total_tokens": 32032} {"current_steps": 60, "total_steps": 40000, "loss": 0.0836, "lr": 4.9999731593504344e-05, "epoch": 1.0530973451327434, "percentage": 0.15, "elapsed_time": "0:00:27", "remaining_time": "5:09:15", "throughput": 1242.11, "total_tokens": 34624} {"current_steps": 65, "total_steps": 40000, "loss": 0.0943, "lr": 4.999968417332415e-05, "epoch": 1.1415929203539823, "percentage": 0.16, "elapsed_time": "0:00:29", "remaining_time": "5:06:42", "throughput": 1255.33, "total_tokens": 37600} {"current_steps": 70, "total_steps": 40000, "loss": 0.2222, "lr": 4.999963289787848e-05, "epoch": 1.2300884955752212, "percentage": 0.18, "elapsed_time": "0:00:32", "remaining_time": "5:04:28", "throughput": 1256.96, "total_tokens": 40256} {"current_steps": 75, "total_steps": 40000, "loss": 0.1158, "lr": 4.999957776717526e-05, "epoch": 1.3185840707964602, "percentage": 0.19, "elapsed_time": "0:00:34", "remaining_time": "5:02:26", "throughput": 1274.34, "total_tokens": 43440} {"current_steps": 80, "total_steps": 40000, "loss": 0.1155, "lr": 4.9999518781222984e-05, "epoch": 1.407079646017699, "percentage": 0.2, "elapsed_time": "0:00:36", "remaining_time": "5:00:38", "throughput": 1277.81, "total_tokens": 46192} {"current_steps": 85, "total_steps": 40000, "loss": 0.1563, "lr": 4.9999455940030746e-05, "epoch": 1.495575221238938, "percentage": 0.21, "elapsed_time": "0:00:38", "remaining_time": "4:59:05", "throughput": 1291.62, "total_tokens": 49360} {"current_steps": 90, "total_steps": 40000, "loss": 0.4079, "lr": 4.999938924360824e-05, "epoch": 1.584070796460177, "percentage": 0.22, "elapsed_time": "0:00:40", "remaining_time": "4:57:44", "throughput": 1286.82, "total_tokens": 51840} {"current_steps": 95, "total_steps": 40000, "loss": 0.0457, "lr": 4.999931869196575e-05, "epoch": 1.672566371681416, "percentage": 0.24, "elapsed_time": "0:00:42", "remaining_time": "4:56:26", "throughput": 1297.98, "total_tokens": 54960} {"current_steps": 100, "total_steps": 40000, "loss": 0.1414, "lr": 4.999924428511416e-05, "epoch": 1.7610619469026547, "percentage": 0.25, "elapsed_time": "0:00:44", "remaining_time": "4:55:16", "throughput": 1301.16, "total_tokens": 57776} {"current_steps": 105, "total_steps": 40000, "loss": 0.1734, "lr": 4.999916602306494e-05, "epoch": 1.8495575221238938, "percentage": 0.26, "elapsed_time": "0:00:46", "remaining_time": "4:54:18", "throughput": 1304.42, "total_tokens": 60624} {"current_steps": 110, "total_steps": 40000, "loss": 0.0351, "lr": 4.999908390583016e-05, "epoch": 1.9380530973451329, "percentage": 0.27, "elapsed_time": "0:00:48", "remaining_time": "4:53:18", "throughput": 1306.95, "total_tokens": 63424} {"current_steps": 115, "total_steps": 40000, "loss": 0.1362, "lr": 4.999899793342247e-05, "epoch": 2.017699115044248, "percentage": 0.29, "elapsed_time": "0:00:50", "remaining_time": "4:53:30", "throughput": 1290.81, "total_tokens": 65544} {"current_steps": 120, "total_steps": 40000, "loss": 0.0021, "lr": 4.999890810585516e-05, "epoch": 2.106194690265487, "percentage": 0.3, "elapsed_time": "0:00:52", "remaining_time": "4:52:42", "throughput": 1297.18, "total_tokens": 68552} {"current_steps": 125, "total_steps": 40000, "loss": 0.1074, "lr": 4.999881442314206e-05, "epoch": 2.1946902654867255, "percentage": 0.31, "elapsed_time": "0:00:54", "remaining_time": "4:51:55", "throughput": 1297.77, "total_tokens": 71256} {"current_steps": 130, "total_steps": 40000, "loss": 0.067, "lr": 4.9998716885297617e-05, "epoch": 2.2831858407079646, "percentage": 0.33, "elapsed_time": "0:00:56", "remaining_time": "4:51:11", "throughput": 1302.49, "total_tokens": 74200} {"current_steps": 135, "total_steps": 40000, "loss": 0.2343, "lr": 4.999861549233688e-05, "epoch": 2.3716814159292037, "percentage": 0.34, "elapsed_time": "0:00:59", "remaining_time": "4:50:31", "throughput": 1299.26, "total_tokens": 76696} {"current_steps": 140, "total_steps": 40000, "loss": 0.0737, "lr": 4.999851024427548e-05, "epoch": 2.4601769911504423, "percentage": 0.35, "elapsed_time": "0:01:01", "remaining_time": "4:49:58", "throughput": 1303.28, "total_tokens": 79640} {"current_steps": 145, "total_steps": 40000, "loss": 0.1341, "lr": 4.999840114112965e-05, "epoch": 2.5486725663716814, "percentage": 0.36, "elapsed_time": "0:01:03", "remaining_time": "4:49:22", "throughput": 1308.15, "total_tokens": 82632} {"current_steps": 150, "total_steps": 40000, "loss": 0.0808, "lr": 4.999828818291621e-05, "epoch": 2.6371681415929205, "percentage": 0.38, "elapsed_time": "0:01:05", "remaining_time": "4:48:49", "throughput": 1310.68, "total_tokens": 85496} {"current_steps": 155, "total_steps": 40000, "loss": 0.0805, "lr": 4.999817136965259e-05, "epoch": 2.725663716814159, "percentage": 0.39, "elapsed_time": "0:01:07", "remaining_time": "4:48:17", "throughput": 1324.54, "total_tokens": 89128} {"current_steps": 160, "total_steps": 40000, "loss": 0.0858, "lr": 4.9998050701356794e-05, "epoch": 2.814159292035398, "percentage": 0.4, "elapsed_time": "0:01:09", "remaining_time": "4:47:46", "throughput": 1328.92, "total_tokens": 92152} {"current_steps": 165, "total_steps": 40000, "loss": 0.1289, "lr": 4.999792617804744e-05, "epoch": 2.9026548672566372, "percentage": 0.41, "elapsed_time": "0:01:11", "remaining_time": "4:47:18", "throughput": 1325.33, "total_tokens": 94632} {"current_steps": 170, "total_steps": 40000, "loss": 0.1869, "lr": 4.9997797799743724e-05, "epoch": 2.991150442477876, "percentage": 0.43, "elapsed_time": "0:01:13", "remaining_time": "4:46:48", "throughput": 1328.06, "total_tokens": 97544} {"current_steps": 175, "total_steps": 40000, "loss": 0.0076, "lr": 4.999766556646545e-05, "epoch": 3.0707964601769913, "percentage": 0.44, "elapsed_time": "0:01:15", "remaining_time": "4:47:13", "throughput": 1320.42, "total_tokens": 99992} {"current_steps": 180, "total_steps": 40000, "loss": 0.0042, "lr": 4.9997529478232996e-05, "epoch": 3.15929203539823, "percentage": 0.45, "elapsed_time": "0:01:17", "remaining_time": "4:46:47", "throughput": 1321.91, "total_tokens": 102824} {"current_steps": 185, "total_steps": 40000, "loss": 0.0253, "lr": 4.9997389535067365e-05, "epoch": 3.247787610619469, "percentage": 0.46, "elapsed_time": "0:01:19", "remaining_time": "4:46:23", "throughput": 1322.71, "total_tokens": 105608} {"current_steps": 190, "total_steps": 40000, "loss": 0.0016, "lr": 4.999724573699012e-05, "epoch": 3.336283185840708, "percentage": 0.47, "elapsed_time": "0:01:21", "remaining_time": "4:45:59", "throughput": 1327.41, "total_tokens": 108712} {"current_steps": 195, "total_steps": 40000, "loss": 0.067, "lr": 4.9997098084023457e-05, "epoch": 3.4247787610619467, "percentage": 0.49, "elapsed_time": "0:01:23", "remaining_time": "4:45:37", "throughput": 1329.42, "total_tokens": 111608} {"current_steps": 200, "total_steps": 40000, "loss": 0.1231, "lr": 4.999694657619013e-05, "epoch": 3.5132743362831858, "percentage": 0.5, "elapsed_time": "0:01:26", "remaining_time": "4:45:15", "throughput": 1331.31, "total_tokens": 114504} {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.29828834533691406, "epoch": 3.5132743362831858, "percentage": 0.5, "elapsed_time": "0:01:27", "remaining_time": "4:48:47", "throughput": 1315.05, "total_tokens": 114504} {"current_steps": 205, "total_steps": 40000, "loss": 0.1848, "lr": 4.999679121351352e-05, "epoch": 3.601769911504425, "percentage": 0.51, "elapsed_time": "0:01:31", "remaining_time": "4:57:33", "throughput": 1278.59, "total_tokens": 117592} {"current_steps": 210, "total_steps": 40000, "loss": 0.0779, "lr": 4.9996631996017565e-05, "epoch": 3.6902654867256635, "percentage": 0.53, "elapsed_time": "0:01:34", "remaining_time": "4:57:01", "throughput": 1278.12, "total_tokens": 120216} {"current_steps": 215, "total_steps": 40000, "loss": 0.0765, "lr": 4.9996468923726835e-05, "epoch": 3.7787610619469025, "percentage": 0.54, "elapsed_time": "0:01:36", "remaining_time": "4:56:29", "throughput": 1278.45, "total_tokens": 122904} {"current_steps": 220, "total_steps": 40000, "loss": 0.1641, "lr": 4.999630199666647e-05, "epoch": 3.8672566371681416, "percentage": 0.55, "elapsed_time": "0:01:38", "remaining_time": "4:55:56", "throughput": 1281.39, "total_tokens": 125832} {"current_steps": 225, "total_steps": 40000, "loss": 0.1494, "lr": 4.999613121486222e-05, "epoch": 3.9557522123893807, "percentage": 0.56, "elapsed_time": "0:01:40", "remaining_time": "4:55:21", "throughput": 1291.93, "total_tokens": 129512} {"current_steps": 230, "total_steps": 40000, "loss": 0.0775, "lr": 4.999595657834041e-05, "epoch": 4.035398230088496, "percentage": 0.57, "elapsed_time": "0:01:42", "remaining_time": "4:55:22", "throughput": 1286.62, "total_tokens": 131872} {"current_steps": 235, "total_steps": 40000, "loss": 0.0035, "lr": 4.999577808712798e-05, "epoch": 4.123893805309734, "percentage": 0.59, "elapsed_time": "0:01:44", "remaining_time": "4:54:51", "throughput": 1287.62, "total_tokens": 134624} {"current_steps": 240, "total_steps": 40000, "loss": 0.0015, "lr": 4.999559574125244e-05, "epoch": 4.212389380530974, "percentage": 0.6, "elapsed_time": "0:01:46", "remaining_time": "4:54:24", "throughput": 1286.41, "total_tokens": 137168} {"current_steps": 245, "total_steps": 40000, "loss": 0.1199, "lr": 4.9995409540741934e-05, "epoch": 4.300884955752212, "percentage": 0.61, "elapsed_time": "0:01:48", "remaining_time": "4:53:55", "throughput": 1287.24, "total_tokens": 139904} {"current_steps": 250, "total_steps": 40000, "loss": 0.0813, "lr": 4.999521948562516e-05, "epoch": 4.389380530973451, "percentage": 0.62, "elapsed_time": "0:01:50", "remaining_time": "4:53:28", "throughput": 1286.69, "total_tokens": 142496} {"current_steps": 255, "total_steps": 40000, "loss": 0.0094, "lr": 4.999502557593143e-05, "epoch": 4.477876106194691, "percentage": 0.64, "elapsed_time": "0:01:52", "remaining_time": "4:53:01", "throughput": 1291.06, "total_tokens": 145632} {"current_steps": 260, "total_steps": 40000, "loss": 0.0058, "lr": 4.999482781169066e-05, "epoch": 4.566371681415929, "percentage": 0.65, "elapsed_time": "0:01:54", "remaining_time": "4:52:35", "throughput": 1290.48, "total_tokens": 148224} {"current_steps": 265, "total_steps": 40000, "loss": 0.0216, "lr": 4.9994626192933324e-05, "epoch": 4.654867256637168, "percentage": 0.66, "elapsed_time": "0:01:56", "remaining_time": "4:52:10", "throughput": 1290.9, "total_tokens": 150928} {"current_steps": 270, "total_steps": 40000, "loss": 0.0179, "lr": 4.999442071969054e-05, "epoch": 4.743362831858407, "percentage": 0.68, "elapsed_time": "0:01:58", "remaining_time": "4:51:48", "throughput": 1292.7, "total_tokens": 153808} {"current_steps": 275, "total_steps": 40000, "loss": 0.081, "lr": 4.999421139199397e-05, "epoch": 4.831858407079646, "percentage": 0.69, "elapsed_time": "0:02:01", "remaining_time": "4:51:27", "throughput": 1298.91, "total_tokens": 157248} {"current_steps": 280, "total_steps": 40000, "loss": 0.0748, "lr": 4.999399820987592e-05, "epoch": 4.920353982300885, "percentage": 0.7, "elapsed_time": "0:02:03", "remaining_time": "4:51:05", "throughput": 1302.39, "total_tokens": 160352} {"current_steps": 285, "total_steps": 40000, "loss": 0.0004, "lr": 4.999378117336924e-05, "epoch": 5.0, "percentage": 0.71, "elapsed_time": "0:02:05", "remaining_time": "4:50:36", "throughput": 1300.53, "total_tokens": 162728} {"current_steps": 290, "total_steps": 40000, "loss": 0.0003, "lr": 4.9993560282507415e-05, "epoch": 5.088495575221239, "percentage": 0.73, "elapsed_time": "0:02:07", "remaining_time": "4:50:49", "throughput": 1297.71, "total_tokens": 165368} {"current_steps": 295, "total_steps": 40000, "loss": 0.0051, "lr": 4.9993335537324495e-05, "epoch": 5.176991150442478, "percentage": 0.74, "elapsed_time": "0:02:09", "remaining_time": "4:50:29", "throughput": 1300.81, "total_tokens": 168456} {"current_steps": 300, "total_steps": 40000, "loss": 0.017, "lr": 4.999310693785516e-05, "epoch": 5.265486725663717, "percentage": 0.75, "elapsed_time": "0:02:11", "remaining_time": "4:50:09", "throughput": 1303.68, "total_tokens": 171512} {"current_steps": 305, "total_steps": 40000, "loss": 0.0004, "lr": 4.9992874484134653e-05, "epoch": 5.353982300884955, "percentage": 0.76, "elapsed_time": "0:02:13", "remaining_time": "4:49:50", "throughput": 1309.09, "total_tokens": 174920} {"current_steps": 310, "total_steps": 40000, "loss": 0.001, "lr": 4.999263817619882e-05, "epoch": 5.442477876106195, "percentage": 0.78, "elapsed_time": "0:02:15", "remaining_time": "4:49:34", "throughput": 1307.94, "total_tokens": 177496} {"current_steps": 315, "total_steps": 40000, "loss": 0.0001, "lr": 4.9992398014084105e-05, "epoch": 5.530973451327434, "percentage": 0.79, "elapsed_time": "0:02:17", "remaining_time": "4:49:16", "throughput": 1308.92, "total_tokens": 180328} {"current_steps": 320, "total_steps": 40000, "loss": 0.1955, "lr": 4.999215399782754e-05, "epoch": 5.619469026548672, "percentage": 0.8, "elapsed_time": "0:02:19", "remaining_time": "4:48:58", "throughput": 1308.79, "total_tokens": 183000} {"current_steps": 325, "total_steps": 40000, "loss": 0.0906, "lr": 4.999190612746675e-05, "epoch": 5.707964601769912, "percentage": 0.81, "elapsed_time": "0:02:21", "remaining_time": "4:48:40", "throughput": 1307.49, "total_tokens": 185512} {"current_steps": 330, "total_steps": 40000, "loss": 0.0029, "lr": 4.999165440303998e-05, "epoch": 5.79646017699115, "percentage": 0.83, "elapsed_time": "0:02:23", "remaining_time": "4:48:23", "throughput": 1311.46, "total_tokens": 188776} {"current_steps": 335, "total_steps": 40000, "loss": 0.0029, "lr": 4.999139882458603e-05, "epoch": 5.88495575221239, "percentage": 0.84, "elapsed_time": "0:02:26", "remaining_time": "4:48:07", "throughput": 1313.78, "total_tokens": 191816} {"current_steps": 340, "total_steps": 40000, "loss": 0.0102, "lr": 4.9991139392144314e-05, "epoch": 5.9734513274336285, "percentage": 0.85, "elapsed_time": "0:02:28", "remaining_time": "4:47:49", "throughput": 1312.68, "total_tokens": 194344} {"current_steps": 345, "total_steps": 40000, "loss": 0.0009, "lr": 4.999087610575485e-05, "epoch": 6.053097345132743, "percentage": 0.86, "elapsed_time": "0:02:30", "remaining_time": "4:47:57", "throughput": 1310.58, "total_tokens": 197000} {"current_steps": 350, "total_steps": 40000, "loss": 0.1099, "lr": 4.999060896545824e-05, "epoch": 6.1415929203539825, "percentage": 0.88, "elapsed_time": "0:02:32", "remaining_time": "4:47:42", "throughput": 1312.48, "total_tokens": 199992} {"current_steps": 355, "total_steps": 40000, "loss": 0.1047, "lr": 4.999033797129568e-05, "epoch": 6.230088495575221, "percentage": 0.89, "elapsed_time": "0:02:34", "remaining_time": "4:47:28", "throughput": 1315.69, "total_tokens": 203208} {"current_steps": 360, "total_steps": 40000, "loss": 0.0148, "lr": 4.999006312330894e-05, "epoch": 6.31858407079646, "percentage": 0.9, "elapsed_time": "0:02:36", "remaining_time": "4:47:13", "throughput": 1316.04, "total_tokens": 205976} {"current_steps": 365, "total_steps": 40000, "loss": 0.0014, "lr": 4.998978442154043e-05, "epoch": 6.407079646017699, "percentage": 0.91, "elapsed_time": "0:02:38", "remaining_time": "4:46:58", "throughput": 1319.14, "total_tokens": 209176} {"current_steps": 370, "total_steps": 40000, "loss": 0.0063, "lr": 4.9989501866033125e-05, "epoch": 6.495575221238938, "percentage": 0.92, "elapsed_time": "0:02:40", "remaining_time": "4:46:45", "throughput": 1319.11, "total_tokens": 211896} {"current_steps": 375, "total_steps": 40000, "loss": 0.0001, "lr": 4.998921545683059e-05, "epoch": 6.584070796460177, "percentage": 0.94, "elapsed_time": "0:02:42", "remaining_time": "4:46:31", "throughput": 1320.42, "total_tokens": 214824} {"current_steps": 380, "total_steps": 40000, "loss": 0.0148, "lr": 4.9988925193976996e-05, "epoch": 6.672566371681416, "percentage": 0.95, "elapsed_time": "0:02:44", "remaining_time": "4:46:18", "throughput": 1318.19, "total_tokens": 217192} {"current_steps": 385, "total_steps": 40000, "loss": 0.0, "lr": 4.998863107751711e-05, "epoch": 6.761061946902655, "percentage": 0.96, "elapsed_time": "0:02:46", "remaining_time": "4:46:06", "throughput": 1317.59, "total_tokens": 219816} {"current_steps": 390, "total_steps": 40000, "loss": 0.0029, "lr": 4.998833310749629e-05, "epoch": 6.849557522123893, "percentage": 0.97, "elapsed_time": "0:02:48", "remaining_time": "4:45:53", "throughput": 1316.59, "total_tokens": 222360} {"current_steps": 395, "total_steps": 40000, "loss": 0.0, "lr": 4.998803128396047e-05, "epoch": 6.938053097345133, "percentage": 0.99, "elapsed_time": "0:02:50", "remaining_time": "4:45:39", "throughput": 1321.28, "total_tokens": 225864} {"current_steps": 400, "total_steps": 40000, "loss": 0.0, "lr": 4.9987725606956215e-05, "epoch": 7.017699115044247, "percentage": 1.0, "elapsed_time": "0:02:53", "remaining_time": "4:45:44", "throughput": 1319.46, "total_tokens": 228504} {"current_steps": 400, "total_steps": 40000, "eval_loss": 0.27719274163246155, "epoch": 7.017699115044247, "percentage": 1.0, "elapsed_time": "0:02:54", "remaining_time": "4:47:29", "throughput": 1311.44, "total_tokens": 228504} {"current_steps": 405, "total_steps": 40000, "loss": 0.0001, "lr": 4.998741607653066e-05, "epoch": 7.106194690265487, "percentage": 1.01, "elapsed_time": "0:02:57", "remaining_time": "4:49:56", "throughput": 1300.53, "total_tokens": 231416} {"current_steps": 410, "total_steps": 40000, "loss": 0.0001, "lr": 4.9987102692731523e-05, "epoch": 7.1946902654867255, "percentage": 1.03, "elapsed_time": "0:03:00", "remaining_time": "4:49:45", "throughput": 1298.73, "total_tokens": 233832} {"current_steps": 415, "total_steps": 40000, "loss": 0.0001, "lr": 4.9986785455607157e-05, "epoch": 7.283185840707965, "percentage": 1.04, "elapsed_time": "0:03:02", "remaining_time": "4:49:32", "throughput": 1300.07, "total_tokens": 236776} {"current_steps": 420, "total_steps": 40000, "loss": 0.0797, "lr": 4.9986464365206456e-05, "epoch": 7.371681415929204, "percentage": 1.05, "elapsed_time": "0:03:04", "remaining_time": "4:49:17", "throughput": 1301.49, "total_tokens": 239720} {"current_steps": 425, "total_steps": 40000, "loss": 0.0013, "lr": 4.9986139421578956e-05, "epoch": 7.460176991150442, "percentage": 1.06, "elapsed_time": "0:03:06", "remaining_time": "4:49:03", "throughput": 1301.17, "total_tokens": 242344} {"current_steps": 430, "total_steps": 40000, "loss": 0.065, "lr": 4.998581062477477e-05, "epoch": 7.548672566371682, "percentage": 1.07, "elapsed_time": "0:03:08", "remaining_time": "4:48:48", "throughput": 1302.16, "total_tokens": 245208} {"current_steps": 435, "total_steps": 40000, "loss": 0.0262, "lr": 4.998547797484458e-05, "epoch": 7.6371681415929205, "percentage": 1.09, "elapsed_time": "0:03:10", "remaining_time": "4:48:35", "throughput": 1303.88, "total_tokens": 248232} {"current_steps": 440, "total_steps": 40000, "loss": 0.0012, "lr": 4.9985141471839706e-05, "epoch": 7.725663716814159, "percentage": 1.1, "elapsed_time": "0:03:12", "remaining_time": "4:48:21", "throughput": 1304.74, "total_tokens": 251080} {"current_steps": 445, "total_steps": 40000, "loss": 0.0297, "lr": 4.998480111581203e-05, "epoch": 7.814159292035399, "percentage": 1.11, "elapsed_time": "0:03:14", "remaining_time": "4:48:08", "throughput": 1303.76, "total_tokens": 253576} {"current_steps": 450, "total_steps": 40000, "loss": 0.0618, "lr": 4.998445690681405e-05, "epoch": 7.902654867256637, "percentage": 1.12, "elapsed_time": "0:03:16", "remaining_time": "4:47:56", "throughput": 1305.47, "total_tokens": 256616} {"current_steps": 455, "total_steps": 40000, "loss": 0.0004, "lr": 4.9984108844898834e-05, "epoch": 7.991150442477876, "percentage": 1.14, "elapsed_time": "0:03:18", "remaining_time": "4:47:41", "throughput": 1306.83, "total_tokens": 259544} {"current_steps": 460, "total_steps": 40000, "loss": 0.0001, "lr": 4.9983756930120076e-05, "epoch": 8.070796460176991, "percentage": 1.15, "elapsed_time": "0:03:20", "remaining_time": "4:47:45", "throughput": 1305.54, "total_tokens": 262232} {"current_steps": 465, "total_steps": 40000, "loss": 0.1894, "lr": 4.9983401162532025e-05, "epoch": 8.15929203539823, "percentage": 1.16, "elapsed_time": "0:03:22", "remaining_time": "4:47:33", "throughput": 1306.14, "total_tokens": 265048} {"current_steps": 470, "total_steps": 40000, "loss": 0.0006, "lr": 4.998304154218955e-05, "epoch": 8.247787610619469, "percentage": 1.18, "elapsed_time": "0:03:24", "remaining_time": "4:47:20", "throughput": 1307.45, "total_tokens": 268008} {"current_steps": 475, "total_steps": 40000, "loss": 0.0042, "lr": 4.998267806914812e-05, "epoch": 8.336283185840708, "percentage": 1.19, "elapsed_time": "0:03:27", "remaining_time": "4:47:08", "throughput": 1306.79, "total_tokens": 270568} {"current_steps": 480, "total_steps": 40000, "loss": 0.0056, "lr": 4.998231074346378e-05, "epoch": 8.424778761061948, "percentage": 1.2, "elapsed_time": "0:03:29", "remaining_time": "4:46:56", "throughput": 1306.62, "total_tokens": 273224} {"current_steps": 485, "total_steps": 40000, "loss": 0.003, "lr": 4.998193956519317e-05, "epoch": 8.513274336283185, "percentage": 1.21, "elapsed_time": "0:03:31", "remaining_time": "4:46:45", "throughput": 1309.19, "total_tokens": 276472} {"current_steps": 490, "total_steps": 40000, "loss": 0.0011, "lr": 4.9981564534393545e-05, "epoch": 8.601769911504425, "percentage": 1.23, "elapsed_time": "0:03:33", "remaining_time": "4:46:33", "throughput": 1310.43, "total_tokens": 279432} {"current_steps": 495, "total_steps": 40000, "loss": 0.0, "lr": 4.998118565112272e-05, "epoch": 8.690265486725664, "percentage": 1.24, "elapsed_time": "0:03:35", "remaining_time": "4:46:22", "throughput": 1310.89, "total_tokens": 282232} {"current_steps": 500, "total_steps": 40000, "loss": 0.0002, "lr": 4.998080291543914e-05, "epoch": 8.778761061946902, "percentage": 1.25, "elapsed_time": "0:03:37", "remaining_time": "4:46:11", "throughput": 1310.17, "total_tokens": 284776} {"current_steps": 505, "total_steps": 40000, "loss": 0.0, "lr": 4.9980416327401826e-05, "epoch": 8.867256637168142, "percentage": 1.26, "elapsed_time": "0:03:39", "remaining_time": "4:46:00", "throughput": 1311.96, "total_tokens": 287864} {"current_steps": 510, "total_steps": 40000, "loss": 0.0, "lr": 4.998002588707038e-05, "epoch": 8.955752212389381, "percentage": 1.27, "elapsed_time": "0:03:41", "remaining_time": "4:45:49", "throughput": 1312.62, "total_tokens": 290712} {"current_steps": 515, "total_steps": 40000, "loss": 0.119, "lr": 4.997963159450503e-05, "epoch": 9.035398230088495, "percentage": 1.29, "elapsed_time": "0:03:43", "remaining_time": "4:45:52", "throughput": 1310.4, "total_tokens": 293160} {"current_steps": 520, "total_steps": 40000, "loss": 0.0, "lr": 4.9979233449766575e-05, "epoch": 9.123893805309734, "percentage": 1.3, "elapsed_time": "0:03:45", "remaining_time": "4:45:42", "throughput": 1313.04, "total_tokens": 296472} {"current_steps": 525, "total_steps": 40000, "loss": 0.0, "lr": 4.997883145291641e-05, "epoch": 9.212389380530974, "percentage": 1.31, "elapsed_time": "0:03:47", "remaining_time": "4:45:32", "throughput": 1312.75, "total_tokens": 299112} {"current_steps": 530, "total_steps": 40000, "loss": 0.0, "lr": 4.9978425604016536e-05, "epoch": 9.300884955752213, "percentage": 1.32, "elapsed_time": "0:03:49", "remaining_time": "4:45:21", "throughput": 1313.65, "total_tokens": 302024} {"current_steps": 535, "total_steps": 40000, "loss": 0.0001, "lr": 4.9978015903129536e-05, "epoch": 9.389380530973451, "percentage": 1.34, "elapsed_time": "0:03:51", "remaining_time": "4:45:11", "throughput": 1314.26, "total_tokens": 304872} {"current_steps": 540, "total_steps": 40000, "loss": 0.0001, "lr": 4.997760235031859e-05, "epoch": 9.47787610619469, "percentage": 1.35, "elapsed_time": "0:03:54", "remaining_time": "4:45:01", "throughput": 1314.17, "total_tokens": 307560} {"current_steps": 545, "total_steps": 40000, "loss": 0.0, "lr": 4.9977184945647473e-05, "epoch": 9.56637168141593, "percentage": 1.36, "elapsed_time": "0:03:56", "remaining_time": "4:44:53", "throughput": 1316.47, "total_tokens": 310840} {"current_steps": 550, "total_steps": 40000, "loss": 0.0115, "lr": 4.997676368918055e-05, "epoch": 9.654867256637168, "percentage": 1.38, "elapsed_time": "0:03:58", "remaining_time": "4:44:44", "throughput": 1317.48, "total_tokens": 313800} {"current_steps": 555, "total_steps": 40000, "loss": 0.0018, "lr": 4.9976338580982794e-05, "epoch": 9.743362831858407, "percentage": 1.39, "elapsed_time": "0:04:00", "remaining_time": "4:44:35", "throughput": 1318.04, "total_tokens": 316664} {"current_steps": 560, "total_steps": 40000, "loss": 0.0063, "lr": 4.9975909621119755e-05, "epoch": 9.831858407079647, "percentage": 1.4, "elapsed_time": "0:04:02", "remaining_time": "4:44:26", "throughput": 1319.15, "total_tokens": 319656} {"current_steps": 565, "total_steps": 40000, "loss": 0.0005, "lr": 4.997547680965758e-05, "epoch": 9.920353982300885, "percentage": 1.41, "elapsed_time": "0:04:04", "remaining_time": "4:44:17", "throughput": 1319.8, "total_tokens": 322536} {"current_steps": 570, "total_steps": 40000, "loss": 0.0, "lr": 4.997504014666302e-05, "epoch": 10.0, "percentage": 1.43, "elapsed_time": "0:04:06", "remaining_time": "4:44:04", "throughput": 1317.53, "total_tokens": 324624} {"current_steps": 575, "total_steps": 40000, "loss": 0.0001, "lr": 4.997459963220342e-05, "epoch": 10.08849557522124, "percentage": 1.44, "elapsed_time": "0:04:08", "remaining_time": "4:44:11", "throughput": 1316.88, "total_tokens": 327488} {"current_steps": 580, "total_steps": 40000, "loss": 0.0068, "lr": 4.997415526634671e-05, "epoch": 10.176991150442477, "percentage": 1.45, "elapsed_time": "0:04:10", "remaining_time": "4:44:02", "throughput": 1317.04, "total_tokens": 330240} {"current_steps": 585, "total_steps": 40000, "loss": 0.0028, "lr": 4.99737070491614e-05, "epoch": 10.265486725663717, "percentage": 1.46, "elapsed_time": "0:04:12", "remaining_time": "4:43:53", "throughput": 1317.12, "total_tokens": 332976} {"current_steps": 590, "total_steps": 40000, "loss": 0.0046, "lr": 4.997325498071663e-05, "epoch": 10.353982300884956, "percentage": 1.47, "elapsed_time": "0:04:14", "remaining_time": "4:43:44", "throughput": 1316.36, "total_tokens": 335504} {"current_steps": 595, "total_steps": 40000, "loss": 0.0027, "lr": 4.997279906108211e-05, "epoch": 10.442477876106194, "percentage": 1.49, "elapsed_time": "0:04:16", "remaining_time": "4:43:36", "throughput": 1317.44, "total_tokens": 338512} {"current_steps": 600, "total_steps": 40000, "loss": 0.0, "lr": 4.9972339290328155e-05, "epoch": 10.530973451327434, "percentage": 1.5, "elapsed_time": "0:04:19", "remaining_time": "4:43:28", "throughput": 1317.08, "total_tokens": 341136} {"current_steps": 600, "total_steps": 40000, "eval_loss": 0.2460305392742157, "epoch": 10.530973451327434, "percentage": 1.5, "elapsed_time": "0:04:20", "remaining_time": "4:44:38", "throughput": 1311.7, "total_tokens": 341136} {"current_steps": 605, "total_steps": 40000, "loss": 0.0, "lr": 4.9971875668525646e-05, "epoch": 10.619469026548673, "percentage": 1.51, "elapsed_time": "0:04:24", "remaining_time": "4:47:10", "throughput": 1298.74, "total_tokens": 343664} {"current_steps": 610, "total_steps": 40000, "loss": 0.0, "lr": 4.997140819574609e-05, "epoch": 10.70796460176991, "percentage": 1.52, "elapsed_time": "0:04:26", "remaining_time": "4:47:01", "throughput": 1299.85, "total_tokens": 346656} {"current_steps": 615, "total_steps": 40000, "loss": 0.0, "lr": 4.997093687206159e-05, "epoch": 10.79646017699115, "percentage": 1.54, "elapsed_time": "0:04:28", "remaining_time": "4:46:50", "throughput": 1301.26, "total_tokens": 349712} {"current_steps": 620, "total_steps": 40000, "loss": 0.0001, "lr": 4.997046169754482e-05, "epoch": 10.88495575221239, "percentage": 1.55, "elapsed_time": "0:04:30", "remaining_time": "4:46:41", "throughput": 1303.07, "total_tokens": 352896} {"current_steps": 625, "total_steps": 40000, "loss": 0.0, "lr": 4.996998267226905e-05, "epoch": 10.973451327433628, "percentage": 1.56, "elapsed_time": "0:04:32", "remaining_time": "4:46:30", "throughput": 1304.75, "total_tokens": 356016} {"current_steps": 630, "total_steps": 40000, "loss": 0.0001, "lr": 4.996949979630817e-05, "epoch": 11.053097345132743, "percentage": 1.57, "elapsed_time": "0:04:35", "remaining_time": "4:46:32", "throughput": 1302.86, "total_tokens": 358432} {"current_steps": 635, "total_steps": 40000, "loss": 0.0, "lr": 4.996901306973663e-05, "epoch": 11.141592920353983, "percentage": 1.59, "elapsed_time": "0:04:37", "remaining_time": "4:46:22", "throughput": 1302.45, "total_tokens": 361008} {"current_steps": 640, "total_steps": 40000, "loss": 0.0, "lr": 4.996852249262949e-05, "epoch": 11.230088495575222, "percentage": 1.6, "elapsed_time": "0:04:39", "remaining_time": "4:46:13", "throughput": 1302.57, "total_tokens": 363728} {"current_steps": 645, "total_steps": 40000, "loss": 0.0, "lr": 4.996802806506241e-05, "epoch": 11.31858407079646, "percentage": 1.61, "elapsed_time": "0:04:41", "remaining_time": "4:46:03", "throughput": 1305.5, "total_tokens": 367232} {"current_steps": 650, "total_steps": 40000, "loss": 0.0, "lr": 4.996752978711164e-05, "epoch": 11.4070796460177, "percentage": 1.62, "elapsed_time": "0:04:43", "remaining_time": "4:45:54", "throughput": 1307.35, "total_tokens": 370448} {"current_steps": 655, "total_steps": 40000, "loss": 0.0, "lr": 4.996702765885401e-05, "epoch": 11.495575221238939, "percentage": 1.64, "elapsed_time": "0:04:45", "remaining_time": "4:45:45", "throughput": 1308.55, "total_tokens": 373504} {"current_steps": 660, "total_steps": 40000, "loss": 0.0015, "lr": 4.9966521680366964e-05, "epoch": 11.584070796460177, "percentage": 1.65, "elapsed_time": "0:04:47", "remaining_time": "4:45:36", "throughput": 1309.47, "total_tokens": 376464} {"current_steps": 665, "total_steps": 40000, "loss": 0.0, "lr": 4.9966011851728524e-05, "epoch": 11.672566371681416, "percentage": 1.66, "elapsed_time": "0:04:49", "remaining_time": "4:45:27", "throughput": 1309.6, "total_tokens": 379216} {"current_steps": 670, "total_steps": 40000, "loss": 0.0381, "lr": 4.996549817301731e-05, "epoch": 11.761061946902656, "percentage": 1.68, "elapsed_time": "0:04:51", "remaining_time": "4:45:19", "throughput": 1308.69, "total_tokens": 381664} {"current_steps": 675, "total_steps": 40000, "loss": 0.0001, "lr": 4.9964980644312544e-05, "epoch": 11.849557522123893, "percentage": 1.69, "elapsed_time": "0:04:53", "remaining_time": "4:45:10", "throughput": 1308.95, "total_tokens": 384432} {"current_steps": 680, "total_steps": 40000, "loss": 0.0, "lr": 4.996445926569403e-05, "epoch": 11.938053097345133, "percentage": 1.7, "elapsed_time": "0:04:55", "remaining_time": "4:45:01", "throughput": 1309.52, "total_tokens": 387296} {"current_steps": 685, "total_steps": 40000, "loss": 0.0, "lr": 4.996393403724218e-05, "epoch": 12.017699115044248, "percentage": 1.71, "elapsed_time": "0:04:57", "remaining_time": "4:45:03", "throughput": 1309.29, "total_tokens": 390160} {"current_steps": 690, "total_steps": 40000, "loss": 0.0, "lr": 4.9963404959037985e-05, "epoch": 12.106194690265486, "percentage": 1.73, "elapsed_time": "0:05:00", "remaining_time": "4:44:55", "throughput": 1309.53, "total_tokens": 392944} {"current_steps": 695, "total_steps": 40000, "loss": 0.0, "lr": 4.996287203116303e-05, "epoch": 12.194690265486726, "percentage": 1.74, "elapsed_time": "0:05:02", "remaining_time": "4:44:46", "throughput": 1310.64, "total_tokens": 395984} {"current_steps": 700, "total_steps": 40000, "loss": 0.0, "lr": 4.996233525369951e-05, "epoch": 12.283185840707965, "percentage": 1.75, "elapsed_time": "0:05:04", "remaining_time": "4:44:38", "throughput": 1311.17, "total_tokens": 398848} {"current_steps": 705, "total_steps": 40000, "loss": 0.0, "lr": 4.99617946267302e-05, "epoch": 12.371681415929203, "percentage": 1.76, "elapsed_time": "0:05:06", "remaining_time": "4:44:29", "throughput": 1311.13, "total_tokens": 401536} {"current_steps": 710, "total_steps": 40000, "loss": 0.0, "lr": 4.996125015033846e-05, "epoch": 12.460176991150442, "percentage": 1.77, "elapsed_time": "0:05:08", "remaining_time": "4:44:21", "throughput": 1313.17, "total_tokens": 404864} {"current_steps": 715, "total_steps": 40000, "loss": 0.0, "lr": 4.996070182460827e-05, "epoch": 12.548672566371682, "percentage": 1.79, "elapsed_time": "0:05:10", "remaining_time": "4:44:13", "throughput": 1313.73, "total_tokens": 407744} {"current_steps": 720, "total_steps": 40000, "loss": 0.0002, "lr": 4.996014964962418e-05, "epoch": 12.63716814159292, "percentage": 1.8, "elapsed_time": "0:05:12", "remaining_time": "4:44:04", "throughput": 1313.61, "total_tokens": 410416} {"current_steps": 725, "total_steps": 40000, "loss": 0.0004, "lr": 4.9959593625471344e-05, "epoch": 12.725663716814159, "percentage": 1.81, "elapsed_time": "0:05:14", "remaining_time": "4:43:56", "throughput": 1314.78, "total_tokens": 413488} {"current_steps": 730, "total_steps": 40000, "loss": 0.0, "lr": 4.995903375223552e-05, "epoch": 12.814159292035399, "percentage": 1.82, "elapsed_time": "0:05:16", "remaining_time": "4:43:49", "throughput": 1314.25, "total_tokens": 416048} {"current_steps": 735, "total_steps": 40000, "loss": 0.0, "lr": 4.995847003000302e-05, "epoch": 12.902654867256636, "percentage": 1.84, "elapsed_time": "0:05:18", "remaining_time": "4:43:41", "throughput": 1314.85, "total_tokens": 418944} {"current_steps": 740, "total_steps": 40000, "loss": 0.0001, "lr": 4.9957902458860804e-05, "epoch": 12.991150442477876, "percentage": 1.85, "elapsed_time": "0:05:20", "remaining_time": "4:43:32", "throughput": 1314.86, "total_tokens": 421632} {"current_steps": 745, "total_steps": 40000, "loss": 0.0, "lr": 4.995733103889639e-05, "epoch": 13.070796460176991, "percentage": 1.86, "elapsed_time": "0:05:22", "remaining_time": "4:43:35", "throughput": 1314.86, "total_tokens": 424608} {"current_steps": 750, "total_steps": 40000, "loss": 0.0, "lr": 4.99567557701979e-05, "epoch": 13.15929203539823, "percentage": 1.88, "elapsed_time": "0:05:25", "remaining_time": "4:43:28", "throughput": 1314.12, "total_tokens": 427088} {"current_steps": 755, "total_steps": 40000, "loss": 0.0, "lr": 4.995617665285403e-05, "epoch": 13.247787610619469, "percentage": 1.89, "elapsed_time": "0:05:27", "remaining_time": "4:43:20", "throughput": 1313.94, "total_tokens": 429744} {"current_steps": 760, "total_steps": 40000, "loss": 0.0, "lr": 4.99555936869541e-05, "epoch": 13.336283185840708, "percentage": 1.9, "elapsed_time": "0:05:29", "remaining_time": "4:43:13", "throughput": 1314.85, "total_tokens": 432752} {"current_steps": 765, "total_steps": 40000, "loss": 0.0, "lr": 4.995500687258803e-05, "epoch": 13.424778761061948, "percentage": 1.91, "elapsed_time": "0:05:31", "remaining_time": "4:43:06", "throughput": 1314.78, "total_tokens": 435456} {"current_steps": 770, "total_steps": 40000, "loss": 0.0, "lr": 4.995441620984628e-05, "epoch": 13.513274336283185, "percentage": 1.93, "elapsed_time": "0:05:33", "remaining_time": "4:42:59", "throughput": 1316.1, "total_tokens": 438608} {"current_steps": 775, "total_steps": 40000, "loss": 0.0, "lr": 4.995382169881996e-05, "epoch": 13.601769911504425, "percentage": 1.94, "elapsed_time": "0:05:35", "remaining_time": "4:42:51", "throughput": 1315.89, "total_tokens": 441248} {"current_steps": 780, "total_steps": 40000, "loss": 0.0, "lr": 4.9953223339600755e-05, "epoch": 13.690265486725664, "percentage": 1.95, "elapsed_time": "0:05:37", "remaining_time": "4:42:44", "throughput": 1316.49, "total_tokens": 444160} {"current_steps": 785, "total_steps": 40000, "loss": 0.0, "lr": 4.995262113228091e-05, "epoch": 13.778761061946902, "percentage": 1.96, "elapsed_time": "0:05:39", "remaining_time": "4:42:36", "throughput": 1317.46, "total_tokens": 447200} {"current_steps": 790, "total_steps": 40000, "loss": 0.0, "lr": 4.995201507695332e-05, "epoch": 13.867256637168142, "percentage": 1.98, "elapsed_time": "0:05:41", "remaining_time": "4:42:29", "throughput": 1318.67, "total_tokens": 450320} {"current_steps": 795, "total_steps": 40000, "loss": 0.0, "lr": 4.995140517371144e-05, "epoch": 13.955752212389381, "percentage": 1.99, "elapsed_time": "0:05:43", "remaining_time": "4:42:21", "throughput": 1319.54, "total_tokens": 453328} {"current_steps": 800, "total_steps": 40000, "loss": 0.0, "lr": 4.995079142264932e-05, "epoch": 14.035398230088495, "percentage": 2.0, "elapsed_time": "0:05:45", "remaining_time": "4:42:25", "throughput": 1317.13, "total_tokens": 455488} {"current_steps": 800, "total_steps": 40000, "eval_loss": 0.32453352212905884, "epoch": 14.035398230088495, "percentage": 2.0, "elapsed_time": "0:05:46", "remaining_time": "4:43:17", "throughput": 1313.1, "total_tokens": 455488} {"current_steps": 805, "total_steps": 40000, "loss": 0.0, "lr": 4.995017382386162e-05, "epoch": 14.123893805309734, "percentage": 2.01, "elapsed_time": "0:05:50", "remaining_time": "4:44:39", "throughput": 1306.76, "total_tokens": 458400} {"current_steps": 810, "total_steps": 40000, "loss": 0.0, "lr": 4.994955237744356e-05, "epoch": 14.212389380530974, "percentage": 2.02, "elapsed_time": "0:05:52", "remaining_time": "4:44:32", "throughput": 1306.91, "total_tokens": 461168} {"current_steps": 815, "total_steps": 40000, "loss": 0.0, "lr": 4.994892708349101e-05, "epoch": 14.300884955752213, "percentage": 2.04, "elapsed_time": "0:05:54", "remaining_time": "4:44:24", "throughput": 1306.87, "total_tokens": 463840} {"current_steps": 820, "total_steps": 40000, "loss": 0.0, "lr": 4.994829794210035e-05, "epoch": 14.389380530973451, "percentage": 2.05, "elapsed_time": "0:05:56", "remaining_time": "4:44:16", "throughput": 1308.2, "total_tokens": 467008} {"current_steps": 825, "total_steps": 40000, "loss": 0.0, "lr": 4.994766495336864e-05, "epoch": 14.47787610619469, "percentage": 2.06, "elapsed_time": "0:05:59", "remaining_time": "4:44:09", "throughput": 1308.57, "total_tokens": 469856} {"current_steps": 830, "total_steps": 40000, "loss": 0.0, "lr": 4.994702811739348e-05, "epoch": 14.56637168141593, "percentage": 2.08, "elapsed_time": "0:06:01", "remaining_time": "4:44:03", "throughput": 1308.84, "total_tokens": 472672} {"current_steps": 835, "total_steps": 40000, "loss": 0.0, "lr": 4.994638743427308e-05, "epoch": 14.654867256637168, "percentage": 2.09, "elapsed_time": "0:06:03", "remaining_time": "4:43:55", "throughput": 1309.59, "total_tokens": 475648} {"current_steps": 840, "total_steps": 40000, "loss": 0.0, "lr": 4.994574290410624e-05, "epoch": 14.743362831858407, "percentage": 2.1, "elapsed_time": "0:06:05", "remaining_time": "4:43:48", "throughput": 1311.96, "total_tokens": 479216} {"current_steps": 845, "total_steps": 40000, "loss": 0.0, "lr": 4.9945094526992364e-05, "epoch": 14.831858407079647, "percentage": 2.11, "elapsed_time": "0:06:07", "remaining_time": "4:43:41", "throughput": 1311.48, "total_tokens": 481744} {"current_steps": 850, "total_steps": 40000, "loss": 0.0, "lr": 4.994444230303142e-05, "epoch": 14.920353982300885, "percentage": 2.12, "elapsed_time": "0:06:09", "remaining_time": "4:43:33", "throughput": 1312.0, "total_tokens": 484640} {"current_steps": 855, "total_steps": 40000, "loss": 0.0, "lr": 4.994378623232402e-05, "epoch": 15.0, "percentage": 2.14, "elapsed_time": "0:06:11", "remaining_time": "4:43:23", "throughput": 1310.39, "total_tokens": 486672} {"current_steps": 860, "total_steps": 40000, "loss": 0.0, "lr": 4.99431263149713e-05, "epoch": 15.08849557522124, "percentage": 2.15, "elapsed_time": "0:06:13", "remaining_time": "4:43:27", "throughput": 1310.38, "total_tokens": 489680} {"current_steps": 865, "total_steps": 40000, "loss": 0.0, "lr": 4.9942462551075056e-05, "epoch": 15.176991150442477, "percentage": 2.16, "elapsed_time": "0:06:15", "remaining_time": "4:43:20", "throughput": 1311.62, "total_tokens": 492864} {"current_steps": 870, "total_steps": 40000, "loss": 0.0, "lr": 4.994179494073764e-05, "epoch": 15.265486725663717, "percentage": 2.17, "elapsed_time": "0:06:17", "remaining_time": "4:43:13", "throughput": 1311.62, "total_tokens": 495568} {"current_steps": 875, "total_steps": 40000, "loss": 0.0, "lr": 4.9941123484062e-05, "epoch": 15.353982300884956, "percentage": 2.19, "elapsed_time": "0:06:19", "remaining_time": "4:43:06", "throughput": 1312.33, "total_tokens": 498544} {"current_steps": 880, "total_steps": 40000, "loss": 0.0, "lr": 4.99404481811517e-05, "epoch": 15.442477876106194, "percentage": 2.2, "elapsed_time": "0:06:21", "remaining_time": "4:42:59", "throughput": 1312.92, "total_tokens": 501472} {"current_steps": 885, "total_steps": 40000, "loss": 0.0, "lr": 4.9939769032110864e-05, "epoch": 15.530973451327434, "percentage": 2.21, "elapsed_time": "0:06:24", "remaining_time": "4:42:52", "throughput": 1312.64, "total_tokens": 504064} {"current_steps": 890, "total_steps": 40000, "loss": 0.0, "lr": 4.993908603704423e-05, "epoch": 15.619469026548673, "percentage": 2.23, "elapsed_time": "0:06:26", "remaining_time": "4:42:45", "throughput": 1312.76, "total_tokens": 506816} {"current_steps": 895, "total_steps": 40000, "loss": 0.0, "lr": 4.9938399196057126e-05, "epoch": 15.70796460176991, "percentage": 2.24, "elapsed_time": "0:06:28", "remaining_time": "4:42:38", "throughput": 1312.82, "total_tokens": 509552} {"current_steps": 900, "total_steps": 40000, "loss": 0.0, "lr": 4.993770850925547e-05, "epoch": 15.79646017699115, "percentage": 2.25, "elapsed_time": "0:06:30", "remaining_time": "4:42:32", "throughput": 1313.56, "total_tokens": 512576} {"current_steps": 905, "total_steps": 40000, "loss": 0.0, "lr": 4.993701397674577e-05, "epoch": 15.88495575221239, "percentage": 2.26, "elapsed_time": "0:06:32", "remaining_time": "4:42:25", "throughput": 1314.54, "total_tokens": 515664} {"current_steps": 910, "total_steps": 40000, "loss": 0.0, "lr": 4.993631559863515e-05, "epoch": 15.973451327433628, "percentage": 2.27, "elapsed_time": "0:06:34", "remaining_time": "4:42:18", "throughput": 1314.84, "total_tokens": 518464} {"current_steps": 915, "total_steps": 40000, "loss": 0.0, "lr": 4.9935613375031283e-05, "epoch": 16.053097345132745, "percentage": 2.29, "elapsed_time": "0:06:36", "remaining_time": "4:42:19", "throughput": 1312.71, "total_tokens": 520584} {"current_steps": 920, "total_steps": 40000, "loss": 0.0, "lr": 4.993490730604248e-05, "epoch": 16.141592920353983, "percentage": 2.3, "elapsed_time": "0:06:38", "remaining_time": "4:42:13", "throughput": 1314.71, "total_tokens": 524104} {"current_steps": 925, "total_steps": 40000, "loss": 0.0, "lr": 4.993419739177761e-05, "epoch": 16.23008849557522, "percentage": 2.31, "elapsed_time": "0:06:40", "remaining_time": "4:42:07", "throughput": 1316.04, "total_tokens": 527352} {"current_steps": 930, "total_steps": 40000, "loss": 0.0, "lr": 4.9933483632346164e-05, "epoch": 16.31858407079646, "percentage": 2.33, "elapsed_time": "0:06:42", "remaining_time": "4:42:00", "throughput": 1316.7, "total_tokens": 530328} {"current_steps": 935, "total_steps": 40000, "loss": 0.0, "lr": 4.993276602785821e-05, "epoch": 16.4070796460177, "percentage": 2.34, "elapsed_time": "0:06:44", "remaining_time": "4:41:54", "throughput": 1316.4, "total_tokens": 532936} {"current_steps": 940, "total_steps": 40000, "loss": 0.0, "lr": 4.993204457842441e-05, "epoch": 16.495575221238937, "percentage": 2.35, "elapsed_time": "0:06:46", "remaining_time": "4:41:48", "throughput": 1317.66, "total_tokens": 536168} {"current_steps": 945, "total_steps": 40000, "loss": 0.0, "lr": 4.993131928415602e-05, "epoch": 16.58407079646018, "percentage": 2.36, "elapsed_time": "0:06:48", "remaining_time": "4:41:41", "throughput": 1317.28, "total_tokens": 538728} {"current_steps": 950, "total_steps": 40000, "loss": 0.0, "lr": 4.993059014516489e-05, "epoch": 16.672566371681416, "percentage": 2.38, "elapsed_time": "0:06:51", "remaining_time": "4:41:35", "throughput": 1318.23, "total_tokens": 541832} {"current_steps": 955, "total_steps": 40000, "loss": 0.0, "lr": 4.9929857161563464e-05, "epoch": 16.761061946902654, "percentage": 2.39, "elapsed_time": "0:06:53", "remaining_time": "4:41:29", "throughput": 1317.97, "total_tokens": 544440} {"current_steps": 960, "total_steps": 40000, "loss": 0.0, "lr": 4.992912033346477e-05, "epoch": 16.849557522123895, "percentage": 2.4, "elapsed_time": "0:06:55", "remaining_time": "4:41:22", "throughput": 1318.21, "total_tokens": 547256} {"current_steps": 965, "total_steps": 40000, "loss": 0.0, "lr": 4.992837966098245e-05, "epoch": 16.938053097345133, "percentage": 2.41, "elapsed_time": "0:06:57", "remaining_time": "4:41:16", "throughput": 1319.17, "total_tokens": 550360} {"current_steps": 970, "total_steps": 40000, "loss": 0.0, "lr": 4.992763514423071e-05, "epoch": 17.01769911504425, "percentage": 2.43, "elapsed_time": "0:06:59", "remaining_time": "4:41:17", "throughput": 1317.13, "total_tokens": 552464} {"current_steps": 975, "total_steps": 40000, "loss": 0.0, "lr": 4.992688678332437e-05, "epoch": 17.106194690265486, "percentage": 2.44, "elapsed_time": "0:07:01", "remaining_time": "4:41:11", "throughput": 1316.74, "total_tokens": 555040} {"current_steps": 980, "total_steps": 40000, "loss": 0.0, "lr": 4.992613457837884e-05, "epoch": 17.194690265486727, "percentage": 2.45, "elapsed_time": "0:07:03", "remaining_time": "4:41:05", "throughput": 1317.25, "total_tokens": 557968} {"current_steps": 985, "total_steps": 40000, "loss": 0.0, "lr": 4.992537852951011e-05, "epoch": 17.283185840707965, "percentage": 2.46, "elapsed_time": "0:07:05", "remaining_time": "4:41:00", "throughput": 1317.41, "total_tokens": 560768} {"current_steps": 990, "total_steps": 40000, "loss": 0.0, "lr": 4.9924618636834785e-05, "epoch": 17.371681415929203, "percentage": 2.48, "elapsed_time": "0:07:07", "remaining_time": "4:40:53", "throughput": 1317.27, "total_tokens": 563424} {"current_steps": 995, "total_steps": 40000, "loss": 0.0, "lr": 4.9923854900470046e-05, "epoch": 17.460176991150444, "percentage": 2.49, "elapsed_time": "0:07:09", "remaining_time": "4:40:47", "throughput": 1317.84, "total_tokens": 566384} {"current_steps": 1000, "total_steps": 40000, "loss": 0.0, "lr": 4.992308732053367e-05, "epoch": 17.548672566371682, "percentage": 2.5, "elapsed_time": "0:07:11", "remaining_time": "4:40:41", "throughput": 1318.79, "total_tokens": 569504} {"current_steps": 1000, "total_steps": 40000, "eval_loss": 0.32255837321281433, "epoch": 17.548672566371682, "percentage": 2.5, "elapsed_time": "0:07:12", "remaining_time": "4:41:23", "throughput": 1315.55, "total_tokens": 569504} {"current_steps": 1005, "total_steps": 40000, "loss": 0.0, "lr": 4.992231589714402e-05, "epoch": 17.63716814159292, "percentage": 2.51, "elapsed_time": "0:07:16", "remaining_time": "4:42:21", "throughput": 1311.44, "total_tokens": 572608} {"current_steps": 1010, "total_steps": 40000, "loss": 0.0, "lr": 4.992154063042007e-05, "epoch": 17.72566371681416, "percentage": 2.53, "elapsed_time": "0:07:18", "remaining_time": "4:42:15", "throughput": 1311.83, "total_tokens": 575504} {"current_steps": 1015, "total_steps": 40000, "loss": 0.0, "lr": 4.992076152048136e-05, "epoch": 17.8141592920354, "percentage": 2.54, "elapsed_time": "0:07:20", "remaining_time": "4:42:09", "throughput": 1311.5, "total_tokens": 578064} {"current_steps": 1020, "total_steps": 40000, "loss": 0.0, "lr": 4.991997856744807e-05, "epoch": 17.902654867256636, "percentage": 2.55, "elapsed_time": "0:07:22", "remaining_time": "4:42:02", "throughput": 1312.73, "total_tokens": 581312} {"current_steps": 1025, "total_steps": 40000, "loss": 0.0, "lr": 4.9919191771440905e-05, "epoch": 17.991150442477878, "percentage": 2.56, "elapsed_time": "0:07:24", "remaining_time": "4:41:55", "throughput": 1313.29, "total_tokens": 584240} {"current_steps": 1030, "total_steps": 40000, "loss": 0.0, "lr": 4.991840113258122e-05, "epoch": 18.07079646017699, "percentage": 2.57, "elapsed_time": "0:07:27", "remaining_time": "4:41:56", "throughput": 1311.26, "total_tokens": 586296} {"current_steps": 1035, "total_steps": 40000, "loss": 0.0, "lr": 4.9917606650990933e-05, "epoch": 18.15929203539823, "percentage": 2.59, "elapsed_time": "0:07:29", "remaining_time": "4:41:50", "throughput": 1311.11, "total_tokens": 588936} {"current_steps": 1040, "total_steps": 40000, "loss": 0.0, "lr": 4.9916808326792566e-05, "epoch": 18.24778761061947, "percentage": 2.6, "elapsed_time": "0:07:31", "remaining_time": "4:41:45", "throughput": 1311.45, "total_tokens": 591816} {"current_steps": 1045, "total_steps": 40000, "loss": 0.0, "lr": 4.9916006160109235e-05, "epoch": 18.336283185840706, "percentage": 2.61, "elapsed_time": "0:07:33", "remaining_time": "4:41:39", "throughput": 1312.48, "total_tokens": 595000} {"current_steps": 1050, "total_steps": 40000, "loss": 0.0, "lr": 4.991520015106464e-05, "epoch": 18.424778761061948, "percentage": 2.62, "elapsed_time": "0:07:35", "remaining_time": "4:41:33", "throughput": 1313.05, "total_tokens": 597960} {"current_steps": 1055, "total_steps": 40000, "loss": 0.0, "lr": 4.991439029978308e-05, "epoch": 18.513274336283185, "percentage": 2.64, "elapsed_time": "0:07:37", "remaining_time": "4:41:26", "throughput": 1313.18, "total_tokens": 600728} {"current_steps": 1060, "total_steps": 40000, "loss": 0.0, "lr": 4.9913576606389434e-05, "epoch": 18.601769911504427, "percentage": 2.65, "elapsed_time": "0:07:39", "remaining_time": "4:41:21", "throughput": 1313.29, "total_tokens": 603496} {"current_steps": 1065, "total_steps": 40000, "loss": 0.0, "lr": 4.991275907100919e-05, "epoch": 18.690265486725664, "percentage": 2.66, "elapsed_time": "0:07:41", "remaining_time": "4:41:15", "throughput": 1313.07, "total_tokens": 606104} {"current_steps": 1070, "total_steps": 40000, "loss": 0.0, "lr": 4.9911937693768434e-05, "epoch": 18.778761061946902, "percentage": 2.67, "elapsed_time": "0:07:43", "remaining_time": "4:41:09", "throughput": 1313.84, "total_tokens": 609160} {"current_steps": 1075, "total_steps": 40000, "loss": 0.0, "lr": 4.991111247479382e-05, "epoch": 18.86725663716814, "percentage": 2.69, "elapsed_time": "0:07:45", "remaining_time": "4:41:03", "throughput": 1314.67, "total_tokens": 612264} {"current_steps": 1080, "total_steps": 40000, "loss": 0.0, "lr": 4.9910283414212605e-05, "epoch": 18.95575221238938, "percentage": 2.7, "elapsed_time": "0:07:47", "remaining_time": "4:40:57", "throughput": 1315.29, "total_tokens": 615256} {"current_steps": 1085, "total_steps": 40000, "loss": 0.0, "lr": 4.990945051215265e-05, "epoch": 19.035398230088497, "percentage": 2.71, "elapsed_time": "0:07:50", "remaining_time": "4:40:57", "throughput": 1314.59, "total_tokens": 617880} {"current_steps": 1090, "total_steps": 40000, "loss": 0.0, "lr": 4.99086137687424e-05, "epoch": 19.123893805309734, "percentage": 2.73, "elapsed_time": "0:07:52", "remaining_time": "4:40:51", "throughput": 1314.1, "total_tokens": 620360} {"current_steps": 1095, "total_steps": 40000, "loss": 0.0, "lr": 4.9907773184110874e-05, "epoch": 19.212389380530972, "percentage": 2.74, "elapsed_time": "0:07:54", "remaining_time": "4:40:45", "throughput": 1314.44, "total_tokens": 623224} {"current_steps": 1100, "total_steps": 40000, "loss": 0.0, "lr": 4.9906928758387715e-05, "epoch": 19.300884955752213, "percentage": 2.75, "elapsed_time": "0:07:56", "remaining_time": "4:40:40", "throughput": 1313.65, "total_tokens": 625560} {"current_steps": 1105, "total_steps": 40000, "loss": 0.0, "lr": 4.9906080491703146e-05, "epoch": 19.38938053097345, "percentage": 2.76, "elapsed_time": "0:07:58", "remaining_time": "4:40:34", "throughput": 1314.11, "total_tokens": 628488} {"current_steps": 1110, "total_steps": 40000, "loss": 0.0, "lr": 4.990522838418797e-05, "epoch": 19.47787610619469, "percentage": 2.77, "elapsed_time": "0:08:00", "remaining_time": "4:40:28", "throughput": 1314.5, "total_tokens": 631400} {"current_steps": 1115, "total_steps": 40000, "loss": 0.0, "lr": 4.9904372435973604e-05, "epoch": 19.56637168141593, "percentage": 2.79, "elapsed_time": "0:08:02", "remaining_time": "4:40:23", "throughput": 1315.13, "total_tokens": 634408} {"current_steps": 1120, "total_steps": 40000, "loss": 0.0, "lr": 4.990351264719203e-05, "epoch": 19.654867256637168, "percentage": 2.8, "elapsed_time": "0:08:04", "remaining_time": "4:40:17", "throughput": 1315.79, "total_tokens": 637448} {"current_steps": 1125, "total_steps": 40000, "loss": 0.0, "lr": 4.990264901797586e-05, "epoch": 19.743362831858406, "percentage": 2.81, "elapsed_time": "0:08:06", "remaining_time": "4:40:11", "throughput": 1316.05, "total_tokens": 640280} {"current_steps": 1130, "total_steps": 40000, "loss": 0.0, "lr": 4.990178154845826e-05, "epoch": 19.831858407079647, "percentage": 2.83, "elapsed_time": "0:08:08", "remaining_time": "4:40:06", "throughput": 1316.04, "total_tokens": 642984} {"current_steps": 1135, "total_steps": 40000, "loss": 0.0, "lr": 4.9900910238773014e-05, "epoch": 19.920353982300885, "percentage": 2.84, "elapsed_time": "0:08:10", "remaining_time": "4:40:00", "throughput": 1316.82, "total_tokens": 646072} {"current_steps": 1140, "total_steps": 40000, "loss": 0.0, "lr": 4.990003508905448e-05, "epoch": 20.0, "percentage": 2.85, "elapsed_time": "0:08:12", "remaining_time": "4:39:52", "throughput": 1316.86, "total_tokens": 648736} {"current_steps": 1145, "total_steps": 40000, "loss": 0.0, "lr": 4.989915609943763e-05, "epoch": 20.088495575221238, "percentage": 2.86, "elapsed_time": "0:08:14", "remaining_time": "4:39:56", "throughput": 1315.79, "total_tokens": 651264} {"current_steps": 1150, "total_steps": 40000, "loss": 0.0, "lr": 4.9898273270058e-05, "epoch": 20.17699115044248, "percentage": 2.88, "elapsed_time": "0:08:17", "remaining_time": "4:39:51", "throughput": 1316.52, "total_tokens": 654352} {"current_steps": 1155, "total_steps": 40000, "loss": 0.0, "lr": 4.989738660105174e-05, "epoch": 20.265486725663717, "percentage": 2.89, "elapsed_time": "0:08:19", "remaining_time": "4:39:45", "throughput": 1316.56, "total_tokens": 657088} {"current_steps": 1160, "total_steps": 40000, "loss": 0.0, "lr": 4.989649609255559e-05, "epoch": 20.353982300884955, "percentage": 2.9, "elapsed_time": "0:08:21", "remaining_time": "4:39:40", "throughput": 1316.88, "total_tokens": 659968} {"current_steps": 1165, "total_steps": 40000, "loss": 0.0, "lr": 4.989560174470687e-05, "epoch": 20.442477876106196, "percentage": 2.91, "elapsed_time": "0:08:23", "remaining_time": "4:39:34", "throughput": 1317.81, "total_tokens": 663152} {"current_steps": 1170, "total_steps": 40000, "loss": 0.0, "lr": 4.989470355764351e-05, "epoch": 20.530973451327434, "percentage": 2.93, "elapsed_time": "0:08:25", "remaining_time": "4:39:29", "throughput": 1318.54, "total_tokens": 666240} {"current_steps": 1175, "total_steps": 40000, "loss": 0.0, "lr": 4.9893801531504e-05, "epoch": 20.61946902654867, "percentage": 2.94, "elapsed_time": "0:08:27", "remaining_time": "4:39:24", "throughput": 1318.38, "total_tokens": 668896} {"current_steps": 1180, "total_steps": 40000, "loss": 0.0, "lr": 4.9892895666427475e-05, "epoch": 20.707964601769913, "percentage": 2.95, "elapsed_time": "0:08:29", "remaining_time": "4:39:19", "throughput": 1317.9, "total_tokens": 671376} {"current_steps": 1185, "total_steps": 40000, "loss": 0.0, "lr": 4.9891985962553606e-05, "epoch": 20.79646017699115, "percentage": 2.96, "elapsed_time": "0:08:31", "remaining_time": "4:39:14", "throughput": 1318.28, "total_tokens": 674304} {"current_steps": 1190, "total_steps": 40000, "loss": 0.0, "lr": 4.989107242002269e-05, "epoch": 20.884955752212388, "percentage": 2.97, "elapsed_time": "0:08:33", "remaining_time": "4:39:09", "throughput": 1318.52, "total_tokens": 677152} {"current_steps": 1195, "total_steps": 40000, "loss": 0.0, "lr": 4.989015503897561e-05, "epoch": 20.97345132743363, "percentage": 2.99, "elapsed_time": "0:08:35", "remaining_time": "4:39:03", "throughput": 1318.51, "total_tokens": 679840} {"current_steps": 1200, "total_steps": 40000, "loss": 0.0, "lr": 4.988923381955383e-05, "epoch": 21.053097345132745, "percentage": 3.0, "elapsed_time": "0:08:37", "remaining_time": "4:39:04", "throughput": 1316.99, "total_tokens": 682024} {"current_steps": 1200, "total_steps": 40000, "eval_loss": 0.3285369575023651, "epoch": 21.053097345132745, "percentage": 3.0, "elapsed_time": "0:08:38", "remaining_time": "4:39:38", "throughput": 1314.3, "total_tokens": 682024} {"current_steps": 1205, "total_steps": 40000, "loss": 0.0, "lr": 4.988830876189942e-05, "epoch": 21.141592920353983, "percentage": 3.01, "elapsed_time": "0:08:42", "remaining_time": "4:40:24", "throughput": 1311.39, "total_tokens": 685320} {"current_steps": 1210, "total_steps": 40000, "loss": 0.0, "lr": 4.988737986615503e-05, "epoch": 21.23008849557522, "percentage": 3.02, "elapsed_time": "0:08:44", "remaining_time": "4:40:19", "throughput": 1311.71, "total_tokens": 688200} {"current_steps": 1215, "total_steps": 40000, "loss": 0.0, "lr": 4.988644713246391e-05, "epoch": 21.31858407079646, "percentage": 3.04, "elapsed_time": "0:08:46", "remaining_time": "4:40:14", "throughput": 1312.69, "total_tokens": 691432} {"current_steps": 1220, "total_steps": 40000, "loss": 0.0, "lr": 4.988551056096991e-05, "epoch": 21.4070796460177, "percentage": 3.05, "elapsed_time": "0:08:48", "remaining_time": "4:40:08", "throughput": 1312.59, "total_tokens": 694088} {"current_steps": 1225, "total_steps": 40000, "loss": 0.0, "lr": 4.988457015181743e-05, "epoch": 21.495575221238937, "percentage": 3.06, "elapsed_time": "0:08:50", "remaining_time": "4:40:03", "throughput": 1312.17, "total_tokens": 696568} {"current_steps": 1230, "total_steps": 40000, "loss": 0.0, "lr": 4.988362590515153e-05, "epoch": 21.58407079646018, "percentage": 3.08, "elapsed_time": "0:08:52", "remaining_time": "4:39:57", "throughput": 1311.91, "total_tokens": 699128} {"current_steps": 1235, "total_steps": 40000, "loss": 0.0, "lr": 4.9882677821117805e-05, "epoch": 21.672566371681416, "percentage": 3.09, "elapsed_time": "0:08:54", "remaining_time": "4:39:51", "throughput": 1313.99, "total_tokens": 702936} {"current_steps": 1240, "total_steps": 40000, "loss": 0.0, "lr": 4.988172589986246e-05, "epoch": 21.761061946902654, "percentage": 3.1, "elapsed_time": "0:08:57", "remaining_time": "4:39:46", "throughput": 1313.84, "total_tokens": 705560} {"current_steps": 1245, "total_steps": 40000, "loss": 0.0, "lr": 4.9880770141532304e-05, "epoch": 21.849557522123895, "percentage": 3.11, "elapsed_time": "0:08:59", "remaining_time": "4:39:40", "throughput": 1313.93, "total_tokens": 708312} {"current_steps": 1250, "total_steps": 40000, "loss": 0.0, "lr": 4.987981054627472e-05, "epoch": 21.938053097345133, "percentage": 3.12, "elapsed_time": "0:09:01", "remaining_time": "4:39:35", "throughput": 1314.3, "total_tokens": 711224} {"current_steps": 1255, "total_steps": 40000, "loss": 0.0, "lr": 4.987884711423769e-05, "epoch": 22.01769911504425, "percentage": 3.14, "elapsed_time": "0:09:03", "remaining_time": "4:39:35", "throughput": 1312.89, "total_tokens": 713400} {"current_steps": 1260, "total_steps": 40000, "loss": 0.0, "lr": 4.9877879845569784e-05, "epoch": 22.106194690265486, "percentage": 3.15, "elapsed_time": "0:09:05", "remaining_time": "4:39:30", "throughput": 1313.5, "total_tokens": 716440} {"current_steps": 1265, "total_steps": 40000, "loss": 0.0, "lr": 4.9876908740420175e-05, "epoch": 22.194690265486727, "percentage": 3.16, "elapsed_time": "0:09:07", "remaining_time": "4:39:24", "throughput": 1313.44, "total_tokens": 719112} {"current_steps": 1270, "total_steps": 40000, "loss": 0.0, "lr": 4.987593379893861e-05, "epoch": 22.283185840707965, "percentage": 3.17, "elapsed_time": "0:09:09", "remaining_time": "4:39:19", "throughput": 1314.71, "total_tokens": 722520} {"current_steps": 1275, "total_steps": 40000, "loss": 0.0, "lr": 4.987495502127545e-05, "epoch": 22.371681415929203, "percentage": 3.19, "elapsed_time": "0:09:11", "remaining_time": "4:39:14", "throughput": 1316.19, "total_tokens": 726040} {"current_steps": 1280, "total_steps": 40000, "loss": 0.0, "lr": 4.987397240758162e-05, "epoch": 22.460176991150444, "percentage": 3.2, "elapsed_time": "0:09:13", "remaining_time": "4:39:09", "throughput": 1316.11, "total_tokens": 728712} {"current_steps": 1285, "total_steps": 40000, "loss": 0.0, "lr": 4.9872985958008664e-05, "epoch": 22.548672566371682, "percentage": 3.21, "elapsed_time": "0:09:15", "remaining_time": "4:39:04", "throughput": 1316.84, "total_tokens": 731848} {"current_steps": 1290, "total_steps": 40000, "loss": 0.0, "lr": 4.987199567270871e-05, "epoch": 22.63716814159292, "percentage": 3.23, "elapsed_time": "0:09:17", "remaining_time": "4:38:59", "throughput": 1316.73, "total_tokens": 734504} {"current_steps": 1295, "total_steps": 40000, "loss": 0.0, "lr": 4.9871001551834444e-05, "epoch": 22.72566371681416, "percentage": 3.24, "elapsed_time": "0:09:19", "remaining_time": "4:38:54", "throughput": 1316.75, "total_tokens": 737240} {"current_steps": 1300, "total_steps": 40000, "loss": 0.0, "lr": 4.98700035955392e-05, "epoch": 22.8141592920354, "percentage": 3.25, "elapsed_time": "0:09:21", "remaining_time": "4:38:49", "throughput": 1316.84, "total_tokens": 740024} {"current_steps": 1305, "total_steps": 40000, "loss": 0.0, "lr": 4.986900180397686e-05, "epoch": 22.902654867256636, "percentage": 3.26, "elapsed_time": "0:09:24", "remaining_time": "4:38:44", "throughput": 1316.53, "total_tokens": 742568} {"current_steps": 1310, "total_steps": 40000, "loss": 0.0, "lr": 4.9867996177301926e-05, "epoch": 22.991150442477878, "percentage": 3.28, "elapsed_time": "0:09:26", "remaining_time": "4:38:38", "throughput": 1316.46, "total_tokens": 745224} {"current_steps": 1315, "total_steps": 40000, "loss": 0.0, "lr": 4.9866986715669464e-05, "epoch": 23.07079646017699, "percentage": 3.29, "elapsed_time": "0:09:28", "remaining_time": "4:38:39", "throughput": 1315.8, "total_tokens": 747824} {"current_steps": 1320, "total_steps": 40000, "loss": 0.0, "lr": 4.9865973419235155e-05, "epoch": 23.15929203539823, "percentage": 3.3, "elapsed_time": "0:09:30", "remaining_time": "4:38:34", "throughput": 1316.14, "total_tokens": 750752} {"current_steps": 1325, "total_steps": 40000, "loss": 0.0, "lr": 4.986495628815526e-05, "epoch": 23.24778761061947, "percentage": 3.31, "elapsed_time": "0:09:32", "remaining_time": "4:38:29", "throughput": 1316.85, "total_tokens": 753872} {"current_steps": 1330, "total_steps": 40000, "loss": 0.0, "lr": 4.986393532258663e-05, "epoch": 23.336283185840706, "percentage": 3.33, "elapsed_time": "0:09:34", "remaining_time": "4:38:24", "throughput": 1317.14, "total_tokens": 756752} {"current_steps": 1335, "total_steps": 40000, "loss": 0.0, "lr": 4.986291052268671e-05, "epoch": 23.424778761061948, "percentage": 3.34, "elapsed_time": "0:09:36", "remaining_time": "4:38:19", "throughput": 1316.9, "total_tokens": 759328} {"current_steps": 1340, "total_steps": 40000, "loss": 0.0, "lr": 4.986188188861355e-05, "epoch": 23.513274336283185, "percentage": 3.35, "elapsed_time": "0:09:38", "remaining_time": "4:38:14", "throughput": 1317.22, "total_tokens": 762224} {"current_steps": 1345, "total_steps": 40000, "loss": 0.0, "lr": 4.9860849420525766e-05, "epoch": 23.601769911504427, "percentage": 3.36, "elapsed_time": "0:09:40", "remaining_time": "4:38:09", "throughput": 1317.92, "total_tokens": 765344} {"current_steps": 1350, "total_steps": 40000, "loss": 0.0, "lr": 4.9859813118582575e-05, "epoch": 23.690265486725664, "percentage": 3.38, "elapsed_time": "0:09:42", "remaining_time": "4:38:04", "throughput": 1318.26, "total_tokens": 768256} {"current_steps": 1355, "total_steps": 40000, "loss": 0.0, "lr": 4.98587729829438e-05, "epoch": 23.778761061946902, "percentage": 3.39, "elapsed_time": "0:09:44", "remaining_time": "4:38:00", "throughput": 1318.22, "total_tokens": 770960} {"current_steps": 1360, "total_steps": 40000, "loss": 0.0, "lr": 4.985772901376983e-05, "epoch": 23.86725663716814, "percentage": 3.4, "elapsed_time": "0:09:46", "remaining_time": "4:37:55", "throughput": 1318.05, "total_tokens": 773584} {"current_steps": 1365, "total_steps": 40000, "loss": 0.0, "lr": 4.9856681211221666e-05, "epoch": 23.95575221238938, "percentage": 3.41, "elapsed_time": "0:09:48", "remaining_time": "4:37:50", "throughput": 1319.0, "total_tokens": 776848} {"current_steps": 1370, "total_steps": 40000, "loss": 0.0, "lr": 4.985562957546089e-05, "epoch": 24.035398230088497, "percentage": 3.43, "elapsed_time": "0:09:51", "remaining_time": "4:37:50", "throughput": 1318.14, "total_tokens": 779304} {"current_steps": 1375, "total_steps": 40000, "loss": 0.0, "lr": 4.9854574106649686e-05, "epoch": 24.123893805309734, "percentage": 3.44, "elapsed_time": "0:09:53", "remaining_time": "4:37:45", "throughput": 1318.25, "total_tokens": 782088} {"current_steps": 1380, "total_steps": 40000, "loss": 0.0, "lr": 4.985351480495081e-05, "epoch": 24.212389380530972, "percentage": 3.45, "elapsed_time": "0:09:55", "remaining_time": "4:37:41", "throughput": 1318.69, "total_tokens": 785080} {"current_steps": 1385, "total_steps": 40000, "loss": 0.0, "lr": 4.985245167052762e-05, "epoch": 24.300884955752213, "percentage": 3.46, "elapsed_time": "0:09:57", "remaining_time": "4:37:36", "throughput": 1318.7, "total_tokens": 787800} {"current_steps": 1390, "total_steps": 40000, "loss": 0.0, "lr": 4.9851384703544066e-05, "epoch": 24.38938053097345, "percentage": 3.48, "elapsed_time": "0:09:59", "remaining_time": "4:37:31", "throughput": 1318.54, "total_tokens": 790424} {"current_steps": 1395, "total_steps": 40000, "loss": 0.0, "lr": 4.985031390416469e-05, "epoch": 24.47787610619469, "percentage": 3.49, "elapsed_time": "0:10:01", "remaining_time": "4:37:26", "throughput": 1318.33, "total_tokens": 793032} {"current_steps": 1400, "total_steps": 40000, "loss": 0.0, "lr": 4.984923927255461e-05, "epoch": 24.56637168141593, "percentage": 3.5, "elapsed_time": "0:10:03", "remaining_time": "4:37:22", "throughput": 1319.29, "total_tokens": 796328} {"current_steps": 1400, "total_steps": 40000, "eval_loss": 0.33615559339523315, "epoch": 24.56637168141593, "percentage": 3.5, "elapsed_time": "0:10:04", "remaining_time": "4:37:51", "throughput": 1316.97, "total_tokens": 796328} {"current_steps": 1405, "total_steps": 40000, "loss": 0.0, "lr": 4.984816080887958e-05, "epoch": 24.654867256637168, "percentage": 3.51, "elapsed_time": "0:10:08", "remaining_time": "4:38:35", "throughput": 1313.35, "total_tokens": 799176} {"current_steps": 1410, "total_steps": 40000, "loss": 0.0, "lr": 4.9847078513305875e-05, "epoch": 24.743362831858406, "percentage": 3.52, "elapsed_time": "0:10:10", "remaining_time": "4:38:30", "throughput": 1313.66, "total_tokens": 802072} {"current_steps": 1415, "total_steps": 40000, "loss": 0.0, "lr": 4.984599238600043e-05, "epoch": 24.831858407079647, "percentage": 3.54, "elapsed_time": "0:10:12", "remaining_time": "4:38:32", "throughput": 1312.88, "total_tokens": 804648} {"current_steps": 1420, "total_steps": 40000, "loss": 0.0, "lr": 4.9844902427130716e-05, "epoch": 24.920353982300885, "percentage": 3.55, "elapsed_time": "0:10:14", "remaining_time": "4:38:28", "throughput": 1312.85, "total_tokens": 807368} {"current_steps": 1425, "total_steps": 40000, "loss": 0.0, "lr": 4.984380863686482e-05, "epoch": 25.0, "percentage": 3.56, "elapsed_time": "0:10:16", "remaining_time": "4:38:22", "throughput": 1313.12, "total_tokens": 810192} {"current_steps": 1430, "total_steps": 40000, "loss": 0.0, "lr": 4.984271101537143e-05, "epoch": 25.088495575221238, "percentage": 3.57, "elapsed_time": "0:10:19", "remaining_time": "4:38:23", "throughput": 1312.73, "total_tokens": 812960} {"current_steps": 1435, "total_steps": 40000, "loss": 0.0, "lr": 4.9841609562819816e-05, "epoch": 25.17699115044248, "percentage": 3.59, "elapsed_time": "0:10:21", "remaining_time": "4:38:18", "throughput": 1313.69, "total_tokens": 816256} {"current_steps": 1440, "total_steps": 40000, "loss": 0.0, "lr": 4.984050427937983e-05, "epoch": 25.265486725663717, "percentage": 3.6, "elapsed_time": "0:10:23", "remaining_time": "4:38:13", "throughput": 1314.13, "total_tokens": 819232} {"current_steps": 1445, "total_steps": 40000, "loss": 0.0, "lr": 4.983939516522191e-05, "epoch": 25.353982300884955, "percentage": 3.61, "elapsed_time": "0:10:25", "remaining_time": "4:38:08", "throughput": 1314.36, "total_tokens": 822080} {"current_steps": 1450, "total_steps": 40000, "loss": 0.0, "lr": 4.983828222051711e-05, "epoch": 25.442477876106196, "percentage": 3.62, "elapsed_time": "0:10:27", "remaining_time": "4:38:03", "throughput": 1314.21, "total_tokens": 824688} {"current_steps": 1455, "total_steps": 40000, "loss": 0.0, "lr": 4.983716544543705e-05, "epoch": 25.530973451327434, "percentage": 3.64, "elapsed_time": "0:10:29", "remaining_time": "4:37:58", "throughput": 1314.11, "total_tokens": 827360} {"current_steps": 1460, "total_steps": 40000, "loss": 0.0, "lr": 4.983604484015395e-05, "epoch": 25.61946902654867, "percentage": 3.65, "elapsed_time": "0:10:31", "remaining_time": "4:37:54", "throughput": 1315.35, "total_tokens": 830848} {"current_steps": 1465, "total_steps": 40000, "loss": 0.0, "lr": 4.983492040484064e-05, "epoch": 25.707964601769913, "percentage": 3.66, "elapsed_time": "0:10:33", "remaining_time": "4:37:49", "throughput": 1314.89, "total_tokens": 833264} {"current_steps": 1470, "total_steps": 40000, "loss": 0.0, "lr": 4.98337921396705e-05, "epoch": 25.79646017699115, "percentage": 3.67, "elapsed_time": "0:10:35", "remaining_time": "4:37:44", "throughput": 1315.7, "total_tokens": 836480} {"current_steps": 1475, "total_steps": 40000, "loss": 0.0, "lr": 4.983266004481753e-05, "epoch": 25.884955752212388, "percentage": 3.69, "elapsed_time": "0:10:37", "remaining_time": "4:37:39", "throughput": 1315.68, "total_tokens": 839168} {"current_steps": 1480, "total_steps": 40000, "loss": 0.0, "lr": 4.9831524120456316e-05, "epoch": 25.97345132743363, "percentage": 3.7, "elapsed_time": "0:10:39", "remaining_time": "4:37:33", "throughput": 1316.15, "total_tokens": 842160} {"current_steps": 1485, "total_steps": 40000, "loss": 0.0, "lr": 4.9830384366762026e-05, "epoch": 26.053097345132745, "percentage": 3.71, "elapsed_time": "0:10:42", "remaining_time": "4:37:34", "throughput": 1315.0, "total_tokens": 844392} {"current_steps": 1490, "total_steps": 40000, "loss": 0.0, "lr": 4.9829240783910436e-05, "epoch": 26.141592920353983, "percentage": 3.72, "elapsed_time": "0:10:44", "remaining_time": "4:37:29", "throughput": 1315.56, "total_tokens": 847464} {"current_steps": 1495, "total_steps": 40000, "loss": 0.0, "lr": 4.982809337207789e-05, "epoch": 26.23008849557522, "percentage": 3.74, "elapsed_time": "0:10:46", "remaining_time": "4:37:25", "throughput": 1314.87, "total_tokens": 849752} {"current_steps": 1500, "total_steps": 40000, "loss": 0.0, "lr": 4.9826942131441337e-05, "epoch": 26.31858407079646, "percentage": 3.75, "elapsed_time": "0:10:48", "remaining_time": "4:37:20", "throughput": 1315.15, "total_tokens": 852632} {"current_steps": 1505, "total_steps": 40000, "loss": 0.0, "lr": 4.9825787062178315e-05, "epoch": 26.4070796460177, "percentage": 3.76, "elapsed_time": "0:10:50", "remaining_time": "4:37:15", "throughput": 1315.62, "total_tokens": 855640} {"current_steps": 1510, "total_steps": 40000, "loss": 0.0, "lr": 4.9824628164466945e-05, "epoch": 26.495575221238937, "percentage": 3.77, "elapsed_time": "0:10:52", "remaining_time": "4:37:10", "throughput": 1316.2, "total_tokens": 858728} {"current_steps": 1515, "total_steps": 40000, "loss": 0.0, "lr": 4.982346543848595e-05, "epoch": 26.58407079646018, "percentage": 3.79, "elapsed_time": "0:10:54", "remaining_time": "4:37:05", "throughput": 1316.67, "total_tokens": 861736} {"current_steps": 1520, "total_steps": 40000, "loss": 0.0, "lr": 4.9822298884414626e-05, "epoch": 26.672566371681416, "percentage": 3.8, "elapsed_time": "0:10:56", "remaining_time": "4:37:00", "throughput": 1316.36, "total_tokens": 864248} {"current_steps": 1525, "total_steps": 40000, "loss": 0.0, "lr": 4.982112850243288e-05, "epoch": 26.761061946902654, "percentage": 3.81, "elapsed_time": "0:10:58", "remaining_time": "4:36:56", "throughput": 1316.87, "total_tokens": 867288} {"current_steps": 1530, "total_steps": 40000, "loss": 0.0, "lr": 4.98199542927212e-05, "epoch": 26.849557522123895, "percentage": 3.82, "elapsed_time": "0:11:00", "remaining_time": "4:36:51", "throughput": 1317.66, "total_tokens": 870536} {"current_steps": 1535, "total_steps": 40000, "loss": 0.0, "lr": 4.981877625546066e-05, "epoch": 26.938053097345133, "percentage": 3.84, "elapsed_time": "0:11:02", "remaining_time": "4:36:47", "throughput": 1317.35, "total_tokens": 873048} {"current_steps": 1540, "total_steps": 40000, "loss": 0.0, "lr": 4.981759439083293e-05, "epoch": 27.01769911504425, "percentage": 3.85, "elapsed_time": "0:11:04", "remaining_time": "4:36:46", "throughput": 1316.31, "total_tokens": 875304} {"current_steps": 1545, "total_steps": 40000, "loss": 0.0, "lr": 4.981640869902027e-05, "epoch": 27.106194690265486, "percentage": 3.86, "elapsed_time": "0:11:07", "remaining_time": "4:36:42", "throughput": 1316.74, "total_tokens": 878312} {"current_steps": 1550, "total_steps": 40000, "loss": 0.0, "lr": 4.9815219180205517e-05, "epoch": 27.194690265486727, "percentage": 3.88, "elapsed_time": "0:11:09", "remaining_time": "4:36:38", "throughput": 1316.97, "total_tokens": 881192} {"current_steps": 1555, "total_steps": 40000, "loss": 0.0, "lr": 4.9814025834572126e-05, "epoch": 27.283185840707965, "percentage": 3.89, "elapsed_time": "0:11:11", "remaining_time": "4:36:33", "throughput": 1316.93, "total_tokens": 883896} {"current_steps": 1560, "total_steps": 40000, "loss": 0.0, "lr": 4.981282866230411e-05, "epoch": 27.371681415929203, "percentage": 3.9, "elapsed_time": "0:11:13", "remaining_time": "4:36:29", "throughput": 1316.58, "total_tokens": 886376} {"current_steps": 1565, "total_steps": 40000, "loss": 0.0, "lr": 4.981162766358611e-05, "epoch": 27.460176991150444, "percentage": 3.91, "elapsed_time": "0:11:15", "remaining_time": "4:36:25", "throughput": 1316.99, "total_tokens": 889384} {"current_steps": 1570, "total_steps": 40000, "loss": 0.0, "lr": 4.9810422838603316e-05, "epoch": 27.548672566371682, "percentage": 3.92, "elapsed_time": "0:11:17", "remaining_time": "4:36:20", "throughput": 1317.36, "total_tokens": 892344} {"current_steps": 1575, "total_steps": 40000, "loss": 0.0, "lr": 4.9809214187541533e-05, "epoch": 27.63716814159292, "percentage": 3.94, "elapsed_time": "0:11:19", "remaining_time": "4:36:16", "throughput": 1317.34, "total_tokens": 895048} {"current_steps": 1580, "total_steps": 40000, "loss": 0.0, "lr": 4.980800171058715e-05, "epoch": 27.72566371681416, "percentage": 3.95, "elapsed_time": "0:11:21", "remaining_time": "4:36:11", "throughput": 1317.68, "total_tokens": 897992} {"current_steps": 1585, "total_steps": 40000, "loss": 0.0, "lr": 4.980678540792715e-05, "epoch": 27.8141592920354, "percentage": 3.96, "elapsed_time": "0:11:23", "remaining_time": "4:36:06", "throughput": 1317.95, "total_tokens": 900888} {"current_steps": 1590, "total_steps": 40000, "loss": 0.0, "lr": 4.980556527974909e-05, "epoch": 27.902654867256636, "percentage": 3.98, "elapsed_time": "0:11:25", "remaining_time": "4:36:02", "throughput": 1318.65, "total_tokens": 904072} {"current_steps": 1595, "total_steps": 40000, "loss": 0.0, "lr": 4.980434132624114e-05, "epoch": 27.991150442477878, "percentage": 3.99, "elapsed_time": "0:11:27", "remaining_time": "4:35:57", "throughput": 1319.02, "total_tokens": 907016} {"current_steps": 1600, "total_steps": 40000, "loss": 0.0, "lr": 4.980311354759205e-05, "epoch": 28.07079646017699, "percentage": 4.0, "elapsed_time": "0:11:29", "remaining_time": "4:35:57", "throughput": 1318.04, "total_tokens": 909320} {"current_steps": 1600, "total_steps": 40000, "eval_loss": 0.34196165204048157, "epoch": 28.07079646017699, "percentage": 4.0, "elapsed_time": "0:11:30", "remaining_time": "4:36:23", "throughput": 1316.0, "total_tokens": 909320} {"current_steps": 1605, "total_steps": 40000, "loss": 0.0, "lr": 4.980188194399116e-05, "epoch": 28.15929203539823, "percentage": 4.01, "elapsed_time": "0:11:34", "remaining_time": "4:36:57", "throughput": 1313.63, "total_tokens": 912536} {"current_steps": 1610, "total_steps": 40000, "loss": 0.0, "lr": 4.9800646515628384e-05, "epoch": 28.24778761061947, "percentage": 4.03, "elapsed_time": "0:11:36", "remaining_time": "4:36:53", "throughput": 1313.95, "total_tokens": 915480} {"current_steps": 1615, "total_steps": 40000, "loss": 0.0, "lr": 4.979940726269426e-05, "epoch": 28.336283185840706, "percentage": 4.04, "elapsed_time": "0:11:38", "remaining_time": "4:36:48", "throughput": 1314.18, "total_tokens": 918344} {"current_steps": 1620, "total_steps": 40000, "loss": 0.0, "lr": 4.979816418537988e-05, "epoch": 28.424778761061948, "percentage": 4.05, "elapsed_time": "0:11:40", "remaining_time": "4:36:44", "throughput": 1313.84, "total_tokens": 920808} {"current_steps": 1625, "total_steps": 40000, "loss": 0.0, "lr": 4.979691728387696e-05, "epoch": 28.513274336283185, "percentage": 4.06, "elapsed_time": "0:11:42", "remaining_time": "4:36:39", "throughput": 1314.5, "total_tokens": 923976} {"current_steps": 1630, "total_steps": 40000, "loss": 0.0, "lr": 4.979566655837776e-05, "epoch": 28.601769911504427, "percentage": 4.08, "elapsed_time": "0:11:44", "remaining_time": "4:36:35", "throughput": 1314.31, "total_tokens": 926568} {"current_steps": 1635, "total_steps": 40000, "loss": 0.0, "lr": 4.9794412009075184e-05, "epoch": 28.690265486725664, "percentage": 4.09, "elapsed_time": "0:11:47", "remaining_time": "4:36:30", "throughput": 1314.64, "total_tokens": 929512} {"current_steps": 1640, "total_steps": 40000, "loss": 0.0, "lr": 4.979315363616269e-05, "epoch": 28.778761061946902, "percentage": 4.1, "elapsed_time": "0:11:49", "remaining_time": "4:36:26", "throughput": 1314.93, "total_tokens": 932424} {"current_steps": 1645, "total_steps": 40000, "loss": 0.0, "lr": 4.979189143983434e-05, "epoch": 28.86725663716814, "percentage": 4.11, "elapsed_time": "0:11:51", "remaining_time": "4:36:21", "throughput": 1315.45, "total_tokens": 935496} {"current_steps": 1650, "total_steps": 40000, "loss": 0.0, "lr": 4.979062542028478e-05, "epoch": 28.95575221238938, "percentage": 4.12, "elapsed_time": "0:11:53", "remaining_time": "4:36:16", "throughput": 1316.11, "total_tokens": 938664} {"current_steps": 1655, "total_steps": 40000, "loss": 0.0, "lr": 4.978935557770923e-05, "epoch": 29.035398230088497, "percentage": 4.14, "elapsed_time": "0:11:55", "remaining_time": "4:36:16", "throughput": 1314.93, "total_tokens": 940776} {"current_steps": 1660, "total_steps": 40000, "loss": 0.0, "lr": 4.978808191230353e-05, "epoch": 29.123893805309734, "percentage": 4.15, "elapsed_time": "0:11:57", "remaining_time": "4:36:12", "throughput": 1315.13, "total_tokens": 943624} {"current_steps": 1665, "total_steps": 40000, "loss": 0.0, "lr": 4.9786804424264085e-05, "epoch": 29.212389380530972, "percentage": 4.16, "elapsed_time": "0:11:59", "remaining_time": "4:36:07", "throughput": 1315.66, "total_tokens": 946728} {"current_steps": 1670, "total_steps": 40000, "loss": 0.0, "lr": 4.978552311378792e-05, "epoch": 29.300884955752213, "percentage": 4.17, "elapsed_time": "0:12:01", "remaining_time": "4:36:03", "throughput": 1316.26, "total_tokens": 949880} {"current_steps": 1675, "total_steps": 40000, "loss": 0.0, "lr": 4.978423798107261e-05, "epoch": 29.38938053097345, "percentage": 4.19, "elapsed_time": "0:12:03", "remaining_time": "4:35:59", "throughput": 1315.93, "total_tokens": 952376} {"current_steps": 1680, "total_steps": 40000, "loss": 0.0, "lr": 4.978294902631635e-05, "epoch": 29.47787610619469, "percentage": 4.2, "elapsed_time": "0:12:05", "remaining_time": "4:35:54", "throughput": 1316.19, "total_tokens": 955272} {"current_steps": 1685, "total_steps": 40000, "loss": 0.0, "lr": 4.9781656249717914e-05, "epoch": 29.56637168141593, "percentage": 4.21, "elapsed_time": "0:12:07", "remaining_time": "4:35:50", "throughput": 1316.72, "total_tokens": 958376} {"current_steps": 1690, "total_steps": 40000, "loss": 0.0, "lr": 4.9780359651476645e-05, "epoch": 29.654867256637168, "percentage": 4.23, "elapsed_time": "0:12:09", "remaining_time": "4:35:46", "throughput": 1316.53, "total_tokens": 960952} {"current_steps": 1695, "total_steps": 40000, "loss": 0.0, "lr": 4.977905923179251e-05, "epoch": 29.743362831858406, "percentage": 4.24, "elapsed_time": "0:12:11", "remaining_time": "4:35:41", "throughput": 1316.63, "total_tokens": 963752} {"current_steps": 1700, "total_steps": 40000, "loss": 0.0, "lr": 4.977775499086606e-05, "epoch": 29.831858407079647, "percentage": 4.25, "elapsed_time": "0:12:14", "remaining_time": "4:35:37", "throughput": 1317.41, "total_tokens": 967032} {"current_steps": 1705, "total_steps": 40000, "loss": 0.0, "lr": 4.97764469288984e-05, "epoch": 29.920353982300885, "percentage": 4.26, "elapsed_time": "0:12:16", "remaining_time": "4:35:33", "throughput": 1317.29, "total_tokens": 969672} {"current_steps": 1710, "total_steps": 40000, "loss": 0.0, "lr": 4.977513504609127e-05, "epoch": 30.0, "percentage": 4.28, "elapsed_time": "0:12:18", "remaining_time": "4:35:27", "throughput": 1317.12, "total_tokens": 972184} {"current_steps": 1715, "total_steps": 40000, "loss": 0.0, "lr": 4.9773819342646965e-05, "epoch": 30.088495575221238, "percentage": 4.29, "elapsed_time": "0:12:20", "remaining_time": "4:35:28", "throughput": 1316.69, "total_tokens": 974888} {"current_steps": 1720, "total_steps": 40000, "loss": 0.0, "lr": 4.97724998187684e-05, "epoch": 30.17699115044248, "percentage": 4.3, "elapsed_time": "0:12:22", "remaining_time": "4:35:24", "throughput": 1316.37, "total_tokens": 977368} {"current_steps": 1725, "total_steps": 40000, "loss": 0.0, "lr": 4.9771176474659045e-05, "epoch": 30.265486725663717, "percentage": 4.31, "elapsed_time": "0:12:24", "remaining_time": "4:35:19", "throughput": 1317.2, "total_tokens": 980696} {"current_steps": 1730, "total_steps": 40000, "loss": 0.0, "lr": 4.976984931052299e-05, "epoch": 30.353982300884955, "percentage": 4.32, "elapsed_time": "0:12:26", "remaining_time": "4:35:15", "throughput": 1317.04, "total_tokens": 983288} {"current_steps": 1735, "total_steps": 40000, "loss": 0.0, "lr": 4.976851832656489e-05, "epoch": 30.442477876106196, "percentage": 4.34, "elapsed_time": "0:12:28", "remaining_time": "4:35:11", "throughput": 1317.74, "total_tokens": 986520} {"current_steps": 1740, "total_steps": 40000, "loss": 0.0, "lr": 4.9767183522990004e-05, "epoch": 30.530973451327434, "percentage": 4.35, "elapsed_time": "0:12:30", "remaining_time": "4:35:07", "throughput": 1318.07, "total_tokens": 989496} {"current_steps": 1745, "total_steps": 40000, "loss": 0.0, "lr": 4.9765844900004176e-05, "epoch": 30.61946902654867, "percentage": 4.36, "elapsed_time": "0:12:32", "remaining_time": "4:35:02", "throughput": 1318.52, "total_tokens": 992552} {"current_steps": 1750, "total_steps": 40000, "loss": 0.0, "lr": 4.9764502457813834e-05, "epoch": 30.707964601769913, "percentage": 4.38, "elapsed_time": "0:12:34", "remaining_time": "4:34:58", "throughput": 1318.76, "total_tokens": 995448} {"current_steps": 1755, "total_steps": 40000, "loss": 0.0, "lr": 4.9763156196626005e-05, "epoch": 30.79646017699115, "percentage": 4.39, "elapsed_time": "0:12:36", "remaining_time": "4:34:54", "throughput": 1319.21, "total_tokens": 998504} {"current_steps": 1760, "total_steps": 40000, "loss": 0.0, "lr": 4.97618061166483e-05, "epoch": 30.884955752212388, "percentage": 4.4, "elapsed_time": "0:12:38", "remaining_time": "4:34:50", "throughput": 1319.38, "total_tokens": 1001352} {"current_steps": 1765, "total_steps": 40000, "loss": 0.0, "lr": 4.9760452218088915e-05, "epoch": 30.97345132743363, "percentage": 4.41, "elapsed_time": "0:12:41", "remaining_time": "4:34:45", "throughput": 1319.17, "total_tokens": 1003896} {"current_steps": 1770, "total_steps": 40000, "loss": 0.0, "lr": 4.975909450115663e-05, "epoch": 31.053097345132745, "percentage": 4.42, "elapsed_time": "0:12:43", "remaining_time": "4:34:45", "throughput": 1318.52, "total_tokens": 1006384} {"current_steps": 1775, "total_steps": 40000, "loss": 0.0, "lr": 4.975773296606084e-05, "epoch": 31.141592920353983, "percentage": 4.44, "elapsed_time": "0:12:45", "remaining_time": "4:34:41", "throughput": 1319.15, "total_tokens": 1009600} {"current_steps": 1780, "total_steps": 40000, "loss": 0.0, "lr": 4.97563676130115e-05, "epoch": 31.23008849557522, "percentage": 4.45, "elapsed_time": "0:12:47", "remaining_time": "4:34:37", "throughput": 1319.7, "total_tokens": 1012736} {"current_steps": 1785, "total_steps": 40000, "loss": 0.0, "lr": 4.9754998442219166e-05, "epoch": 31.31858407079646, "percentage": 4.46, "elapsed_time": "0:12:49", "remaining_time": "4:34:33", "throughput": 1319.93, "total_tokens": 1015632} {"current_steps": 1790, "total_steps": 40000, "loss": 0.0, "lr": 4.9753625453894984e-05, "epoch": 31.4070796460177, "percentage": 4.47, "elapsed_time": "0:12:51", "remaining_time": "4:34:29", "throughput": 1320.28, "total_tokens": 1018624} {"current_steps": 1795, "total_steps": 40000, "loss": 0.0, "lr": 4.975224864825068e-05, "epoch": 31.495575221238937, "percentage": 4.49, "elapsed_time": "0:12:53", "remaining_time": "4:34:24", "throughput": 1320.04, "total_tokens": 1021152} {"current_steps": 1800, "total_steps": 40000, "loss": 0.0, "lr": 4.9750868025498576e-05, "epoch": 31.58407079646018, "percentage": 4.5, "elapsed_time": "0:12:55", "remaining_time": "4:34:20", "throughput": 1319.81, "total_tokens": 1023696} {"current_steps": 1800, "total_steps": 40000, "eval_loss": 0.34817826747894287, "epoch": 31.58407079646018, "percentage": 4.5, "elapsed_time": "0:12:56", "remaining_time": "4:34:43", "throughput": 1318.01, "total_tokens": 1023696} {"current_steps": 1805, "total_steps": 40000, "loss": 0.0, "lr": 4.974948358585158e-05, "epoch": 31.672566371681416, "percentage": 4.51, "elapsed_time": "0:13:00", "remaining_time": "4:35:15", "throughput": 1315.06, "total_tokens": 1026400} {"current_steps": 1810, "total_steps": 40000, "loss": 0.0, "lr": 4.9748095329523205e-05, "epoch": 31.761061946902654, "percentage": 4.52, "elapsed_time": "0:13:02", "remaining_time": "4:35:11", "throughput": 1314.94, "total_tokens": 1029040} {"current_steps": 1815, "total_steps": 40000, "loss": 0.0, "lr": 4.974670325672752e-05, "epoch": 31.849557522123895, "percentage": 4.54, "elapsed_time": "0:13:04", "remaining_time": "4:35:07", "throughput": 1315.31, "total_tokens": 1032032} {"current_steps": 1820, "total_steps": 40000, "loss": 0.0, "lr": 4.974530736767921e-05, "epoch": 31.938053097345133, "percentage": 4.55, "elapsed_time": "0:13:06", "remaining_time": "4:35:03", "throughput": 1315.52, "total_tokens": 1034912} {"current_steps": 1825, "total_steps": 40000, "loss": 0.0, "lr": 4.9743907662593524e-05, "epoch": 32.017699115044245, "percentage": 4.56, "elapsed_time": "0:13:08", "remaining_time": "4:35:02", "throughput": 1314.97, "total_tokens": 1037416} {"current_steps": 1830, "total_steps": 40000, "loss": 0.0, "lr": 4.974250414168633e-05, "epoch": 32.10619469026549, "percentage": 4.58, "elapsed_time": "0:13:10", "remaining_time": "4:34:58", "throughput": 1314.85, "total_tokens": 1040040} {"current_steps": 1835, "total_steps": 40000, "loss": 0.0, "lr": 4.974109680517407e-05, "epoch": 32.19469026548673, "percentage": 4.59, "elapsed_time": "0:13:13", "remaining_time": "4:34:54", "throughput": 1315.54, "total_tokens": 1043288} {"current_steps": 1840, "total_steps": 40000, "loss": 0.0, "lr": 4.973968565327376e-05, "epoch": 32.283185840707965, "percentage": 4.6, "elapsed_time": "0:13:15", "remaining_time": "4:34:50", "throughput": 1315.39, "total_tokens": 1045896} {"current_steps": 1845, "total_steps": 40000, "loss": 0.0, "lr": 4.973827068620303e-05, "epoch": 32.3716814159292, "percentage": 4.61, "elapsed_time": "0:13:17", "remaining_time": "4:34:46", "throughput": 1315.62, "total_tokens": 1048792} {"current_steps": 1850, "total_steps": 40000, "loss": 0.0, "lr": 4.973685190418008e-05, "epoch": 32.46017699115044, "percentage": 4.62, "elapsed_time": "0:13:19", "remaining_time": "4:34:41", "throughput": 1315.42, "total_tokens": 1051352} {"current_steps": 1855, "total_steps": 40000, "loss": 0.0, "lr": 4.97354293074237e-05, "epoch": 32.54867256637168, "percentage": 4.64, "elapsed_time": "0:13:21", "remaining_time": "4:34:37", "throughput": 1315.99, "total_tokens": 1054520} {"current_steps": 1860, "total_steps": 40000, "loss": 0.0, "lr": 4.9734002896153276e-05, "epoch": 32.63716814159292, "percentage": 4.65, "elapsed_time": "0:13:23", "remaining_time": "4:34:33", "throughput": 1316.66, "total_tokens": 1057768} {"current_steps": 1865, "total_steps": 40000, "loss": 0.0, "lr": 4.973257267058877e-05, "epoch": 32.72566371681416, "percentage": 4.66, "elapsed_time": "0:13:25", "remaining_time": "4:34:29", "throughput": 1317.23, "total_tokens": 1060936} {"current_steps": 1870, "total_steps": 40000, "loss": 0.0, "lr": 4.973113863095076e-05, "epoch": 32.8141592920354, "percentage": 4.67, "elapsed_time": "0:13:27", "remaining_time": "4:34:25", "throughput": 1317.52, "total_tokens": 1063880} {"current_steps": 1875, "total_steps": 40000, "loss": 0.0, "lr": 4.9729700777460384e-05, "epoch": 32.902654867256636, "percentage": 4.69, "elapsed_time": "0:13:29", "remaining_time": "4:34:20", "throughput": 1317.55, "total_tokens": 1066616} {"current_steps": 1880, "total_steps": 40000, "loss": 0.0, "lr": 4.972825911033937e-05, "epoch": 32.991150442477874, "percentage": 4.7, "elapsed_time": "0:13:31", "remaining_time": "4:34:16", "throughput": 1317.25, "total_tokens": 1069080} {"current_steps": 1885, "total_steps": 40000, "loss": 0.0, "lr": 4.9726813629810056e-05, "epoch": 33.07079646017699, "percentage": 4.71, "elapsed_time": "0:13:33", "remaining_time": "4:34:16", "throughput": 1316.83, "total_tokens": 1071712} {"current_steps": 1890, "total_steps": 40000, "loss": 0.0, "lr": 4.9725364336095326e-05, "epoch": 33.15929203539823, "percentage": 4.72, "elapsed_time": "0:13:35", "remaining_time": "4:34:12", "throughput": 1317.06, "total_tokens": 1074608} {"current_steps": 1895, "total_steps": 40000, "loss": 0.0, "lr": 4.972391122941871e-05, "epoch": 33.24778761061947, "percentage": 4.74, "elapsed_time": "0:13:37", "remaining_time": "4:34:07", "throughput": 1316.87, "total_tokens": 1077168} {"current_steps": 1900, "total_steps": 40000, "loss": 0.0, "lr": 4.972245431000428e-05, "epoch": 33.336283185840706, "percentage": 4.75, "elapsed_time": "0:13:40", "remaining_time": "4:34:03", "throughput": 1316.92, "total_tokens": 1079920} {"current_steps": 1905, "total_steps": 40000, "loss": 0.0, "lr": 4.972099357807671e-05, "epoch": 33.424778761061944, "percentage": 4.76, "elapsed_time": "0:13:42", "remaining_time": "4:33:59", "throughput": 1317.14, "total_tokens": 1082816} {"current_steps": 1910, "total_steps": 40000, "loss": 0.0, "lr": 4.971952903386127e-05, "epoch": 33.51327433628319, "percentage": 4.78, "elapsed_time": "0:13:44", "remaining_time": "4:33:55", "throughput": 1317.22, "total_tokens": 1085600} {"current_steps": 1915, "total_steps": 40000, "loss": 0.0, "lr": 4.971806067758381e-05, "epoch": 33.60176991150443, "percentage": 4.79, "elapsed_time": "0:13:46", "remaining_time": "4:33:51", "throughput": 1317.38, "total_tokens": 1088464} {"current_steps": 1920, "total_steps": 40000, "loss": 0.0, "lr": 4.971658850947076e-05, "epoch": 33.690265486725664, "percentage": 4.8, "elapsed_time": "0:13:48", "remaining_time": "4:33:47", "throughput": 1317.96, "total_tokens": 1091648} {"current_steps": 1925, "total_steps": 40000, "loss": 0.0, "lr": 4.9715112529749165e-05, "epoch": 33.7787610619469, "percentage": 4.81, "elapsed_time": "0:13:50", "remaining_time": "4:33:43", "throughput": 1317.6, "total_tokens": 1094080} {"current_steps": 1930, "total_steps": 40000, "loss": 0.0, "lr": 4.9713632738646624e-05, "epoch": 33.86725663716814, "percentage": 4.83, "elapsed_time": "0:13:52", "remaining_time": "4:33:40", "throughput": 1318.24, "total_tokens": 1097344} {"current_steps": 1935, "total_steps": 40000, "loss": 0.0, "lr": 4.971214913639134e-05, "epoch": 33.95575221238938, "percentage": 4.84, "elapsed_time": "0:13:54", "remaining_time": "4:33:35", "throughput": 1318.22, "total_tokens": 1100032} {"current_steps": 1940, "total_steps": 40000, "loss": 0.0, "lr": 4.9710661723212104e-05, "epoch": 34.0353982300885, "percentage": 4.85, "elapsed_time": "0:13:56", "remaining_time": "4:33:35", "throughput": 1317.67, "total_tokens": 1102528} {"current_steps": 1945, "total_steps": 40000, "loss": 0.0, "lr": 4.9709170499338295e-05, "epoch": 34.123893805309734, "percentage": 4.86, "elapsed_time": "0:13:58", "remaining_time": "4:33:31", "throughput": 1318.15, "total_tokens": 1105648} {"current_steps": 1950, "total_steps": 40000, "loss": 0.0, "lr": 4.9707675464999895e-05, "epoch": 34.21238938053097, "percentage": 4.88, "elapsed_time": "0:14:00", "remaining_time": "4:33:27", "throughput": 1318.47, "total_tokens": 1108656} {"current_steps": 1955, "total_steps": 40000, "loss": 0.0, "lr": 4.970617662042743e-05, "epoch": 34.30088495575221, "percentage": 4.89, "elapsed_time": "0:14:02", "remaining_time": "4:33:23", "throughput": 1318.63, "total_tokens": 1111504} {"current_steps": 1960, "total_steps": 40000, "loss": 0.0, "lr": 4.970467396585206e-05, "epoch": 34.389380530973455, "percentage": 4.9, "elapsed_time": "0:14:04", "remaining_time": "4:33:19", "throughput": 1318.9, "total_tokens": 1114448} {"current_steps": 1965, "total_steps": 40000, "loss": 0.0, "lr": 4.97031675015055e-05, "epoch": 34.47787610619469, "percentage": 4.91, "elapsed_time": "0:14:07", "remaining_time": "4:33:15", "throughput": 1320.05, "total_tokens": 1118144} {"current_steps": 1970, "total_steps": 40000, "loss": 0.0, "lr": 4.9701657227620075e-05, "epoch": 34.56637168141593, "percentage": 4.92, "elapsed_time": "0:14:09", "remaining_time": "4:33:11", "throughput": 1319.74, "total_tokens": 1120592} {"current_steps": 1975, "total_steps": 40000, "loss": 0.0, "lr": 4.9700143144428685e-05, "epoch": 34.65486725663717, "percentage": 4.94, "elapsed_time": "0:14:11", "remaining_time": "4:33:07", "throughput": 1319.4, "total_tokens": 1123024} {"current_steps": 1980, "total_steps": 40000, "loss": 0.0, "lr": 4.969862525216482e-05, "epoch": 34.743362831858406, "percentage": 4.95, "elapsed_time": "0:14:13", "remaining_time": "4:33:03", "throughput": 1319.72, "total_tokens": 1126016} {"current_steps": 1985, "total_steps": 40000, "loss": 0.0, "lr": 4.9697103551062556e-05, "epoch": 34.83185840707964, "percentage": 4.96, "elapsed_time": "0:14:15", "remaining_time": "4:32:59", "throughput": 1320.08, "total_tokens": 1129056} {"current_steps": 1990, "total_steps": 40000, "loss": 0.0, "lr": 4.9695578041356565e-05, "epoch": 34.92035398230089, "percentage": 4.98, "elapsed_time": "0:14:17", "remaining_time": "4:32:55", "throughput": 1319.88, "total_tokens": 1131600} {"current_steps": 1995, "total_steps": 40000, "loss": 0.0, "lr": 4.969404872328209e-05, "epoch": 35.0, "percentage": 4.99, "elapsed_time": "0:14:19", "remaining_time": "4:32:50", "throughput": 1319.64, "total_tokens": 1134032} {"current_steps": 2000, "total_steps": 40000, "loss": 0.0, "lr": 4.969251559707498e-05, "epoch": 35.08849557522124, "percentage": 5.0, "elapsed_time": "0:14:21", "remaining_time": "4:32:51", "throughput": 1319.9, "total_tokens": 1137280} {"current_steps": 2000, "total_steps": 40000, "eval_loss": 0.33682557940483093, "epoch": 35.08849557522124, "percentage": 5.0, "elapsed_time": "0:14:22", "remaining_time": "4:33:11", "throughput": 1318.27, "total_tokens": 1137280} {"current_steps": 2005, "total_steps": 40000, "loss": 0.0, "lr": 4.9690978662971674e-05, "epoch": 35.176991150442475, "percentage": 5.01, "elapsed_time": "0:14:26", "remaining_time": "4:33:45", "throughput": 1315.05, "total_tokens": 1139856} {"current_steps": 2010, "total_steps": 40000, "loss": 0.0, "lr": 4.968943792120916e-05, "epoch": 35.26548672566372, "percentage": 5.03, "elapsed_time": "0:14:28", "remaining_time": "4:33:41", "throughput": 1315.31, "total_tokens": 1142800} {"current_steps": 2015, "total_steps": 40000, "loss": 0.0, "lr": 4.9687893372025046e-05, "epoch": 35.35398230088496, "percentage": 5.04, "elapsed_time": "0:14:30", "remaining_time": "4:33:37", "throughput": 1315.65, "total_tokens": 1145824} {"current_steps": 2020, "total_steps": 40000, "loss": 0.0, "lr": 4.9686345015657535e-05, "epoch": 35.442477876106196, "percentage": 5.05, "elapsed_time": "0:14:32", "remaining_time": "4:33:33", "throughput": 1315.88, "total_tokens": 1148736} {"current_steps": 2025, "total_steps": 40000, "loss": 0.0, "lr": 4.968479285234538e-05, "epoch": 35.530973451327434, "percentage": 5.06, "elapsed_time": "0:14:35", "remaining_time": "4:33:29", "throughput": 1316.24, "total_tokens": 1151760} {"current_steps": 2030, "total_steps": 40000, "loss": 0.0, "lr": 4.9683236882327974e-05, "epoch": 35.61946902654867, "percentage": 5.08, "elapsed_time": "0:14:37", "remaining_time": "4:33:25", "throughput": 1316.27, "total_tokens": 1154496} {"current_steps": 2035, "total_steps": 40000, "loss": 0.0, "lr": 4.968167710584526e-05, "epoch": 35.70796460176991, "percentage": 5.09, "elapsed_time": "0:14:39", "remaining_time": "4:33:21", "throughput": 1316.13, "total_tokens": 1157088} {"current_steps": 2040, "total_steps": 40000, "loss": 0.0, "lr": 4.968011352313775e-05, "epoch": 35.796460176991154, "percentage": 5.1, "elapsed_time": "0:14:41", "remaining_time": "4:33:17", "throughput": 1316.16, "total_tokens": 1159824} {"current_steps": 2045, "total_steps": 40000, "loss": 0.0, "lr": 4.967854613444659e-05, "epoch": 35.88495575221239, "percentage": 5.11, "elapsed_time": "0:14:43", "remaining_time": "4:33:13", "throughput": 1316.03, "total_tokens": 1162432} {"current_steps": 2050, "total_steps": 40000, "loss": 0.0, "lr": 4.967697494001349e-05, "epoch": 35.97345132743363, "percentage": 5.12, "elapsed_time": "0:14:45", "remaining_time": "4:33:09", "throughput": 1316.63, "total_tokens": 1165680} {"current_steps": 2055, "total_steps": 40000, "loss": 0.0, "lr": 4.9675399940080736e-05, "epoch": 36.05309734513274, "percentage": 5.14, "elapsed_time": "0:14:47", "remaining_time": "4:33:09", "throughput": 1316.04, "total_tokens": 1168136} {"current_steps": 2060, "total_steps": 40000, "loss": 0.0, "lr": 4.9673821134891226e-05, "epoch": 36.14159292035398, "percentage": 5.15, "elapsed_time": "0:14:49", "remaining_time": "4:33:05", "throughput": 1316.85, "total_tokens": 1171576} {"current_steps": 2065, "total_steps": 40000, "loss": 0.0, "lr": 4.967223852468842e-05, "epoch": 36.230088495575224, "percentage": 5.16, "elapsed_time": "0:14:51", "remaining_time": "4:33:01", "throughput": 1316.93, "total_tokens": 1174360} {"current_steps": 2070, "total_steps": 40000, "loss": 0.0, "lr": 4.967065210971639e-05, "epoch": 36.31858407079646, "percentage": 5.17, "elapsed_time": "0:14:53", "remaining_time": "4:32:57", "throughput": 1317.11, "total_tokens": 1177240} {"current_steps": 2075, "total_steps": 40000, "loss": 0.0, "lr": 4.966906189021977e-05, "epoch": 36.4070796460177, "percentage": 5.19, "elapsed_time": "0:14:55", "remaining_time": "4:32:53", "throughput": 1317.04, "total_tokens": 1179896} {"current_steps": 2080, "total_steps": 40000, "loss": 0.0, "lr": 4.966746786644379e-05, "epoch": 36.49557522123894, "percentage": 5.2, "elapsed_time": "0:14:57", "remaining_time": "4:32:49", "throughput": 1317.1, "total_tokens": 1182664} {"current_steps": 2085, "total_steps": 40000, "loss": 0.0, "lr": 4.966587003863429e-05, "epoch": 36.584070796460175, "percentage": 5.21, "elapsed_time": "0:15:00", "remaining_time": "4:32:46", "throughput": 1316.98, "total_tokens": 1185304} {"current_steps": 2090, "total_steps": 40000, "loss": 0.0, "lr": 4.966426840703765e-05, "epoch": 36.67256637168141, "percentage": 5.22, "elapsed_time": "0:15:02", "remaining_time": "4:32:42", "throughput": 1317.56, "total_tokens": 1188536} {"current_steps": 2095, "total_steps": 40000, "loss": 0.0, "lr": 4.9662662971900875e-05, "epoch": 36.76106194690266, "percentage": 5.24, "elapsed_time": "0:15:04", "remaining_time": "4:32:38", "throughput": 1317.62, "total_tokens": 1191304} {"current_steps": 2100, "total_steps": 40000, "loss": 0.0, "lr": 4.9661053733471534e-05, "epoch": 36.849557522123895, "percentage": 5.25, "elapsed_time": "0:15:06", "remaining_time": "4:32:34", "throughput": 1317.45, "total_tokens": 1193864} {"current_steps": 2105, "total_steps": 40000, "loss": 0.0, "lr": 4.965944069199781e-05, "epoch": 36.93805309734513, "percentage": 5.26, "elapsed_time": "0:15:08", "remaining_time": "4:32:30", "throughput": 1318.02, "total_tokens": 1197096} {"current_steps": 2110, "total_steps": 40000, "loss": 0.0, "lr": 4.965782384772842e-05, "epoch": 37.017699115044245, "percentage": 5.27, "elapsed_time": "0:15:10", "remaining_time": "4:32:30", "throughput": 1317.64, "total_tokens": 1199704} {"current_steps": 2115, "total_steps": 40000, "loss": 0.0, "lr": 4.9656203200912734e-05, "epoch": 37.10619469026549, "percentage": 5.29, "elapsed_time": "0:15:12", "remaining_time": "4:32:26", "throughput": 1318.35, "total_tokens": 1203080} {"current_steps": 2120, "total_steps": 40000, "loss": 0.0, "lr": 4.965457875180067e-05, "epoch": 37.19469026548673, "percentage": 5.3, "elapsed_time": "0:15:14", "remaining_time": "4:32:22", "throughput": 1318.46, "total_tokens": 1205912} {"current_steps": 2125, "total_steps": 40000, "loss": 0.0, "lr": 4.9652950500642724e-05, "epoch": 37.283185840707965, "percentage": 5.31, "elapsed_time": "0:15:16", "remaining_time": "4:32:18", "throughput": 1318.64, "total_tokens": 1208792} {"current_steps": 2130, "total_steps": 40000, "loss": 0.0, "lr": 4.965131844769001e-05, "epoch": 37.3716814159292, "percentage": 5.33, "elapsed_time": "0:15:18", "remaining_time": "4:32:14", "throughput": 1318.91, "total_tokens": 1211752} {"current_steps": 2135, "total_steps": 40000, "loss": 0.0, "lr": 4.96496825931942e-05, "epoch": 37.46017699115044, "percentage": 5.34, "elapsed_time": "0:15:20", "remaining_time": "4:32:10", "throughput": 1318.74, "total_tokens": 1214312} {"current_steps": 2140, "total_steps": 40000, "loss": 0.0, "lr": 4.9648042937407566e-05, "epoch": 37.54867256637168, "percentage": 5.35, "elapsed_time": "0:15:22", "remaining_time": "4:32:07", "throughput": 1318.67, "total_tokens": 1216968} {"current_steps": 2145, "total_steps": 40000, "loss": 0.0, "lr": 4.964639948058297e-05, "epoch": 37.63716814159292, "percentage": 5.36, "elapsed_time": "0:15:24", "remaining_time": "4:32:03", "throughput": 1319.82, "total_tokens": 1220744} {"current_steps": 2150, "total_steps": 40000, "loss": 0.0, "lr": 4.9644752222973846e-05, "epoch": 37.72566371681416, "percentage": 5.38, "elapsed_time": "0:15:26", "remaining_time": "4:31:59", "throughput": 1319.7, "total_tokens": 1223352} {"current_steps": 2155, "total_steps": 40000, "loss": 0.0, "lr": 4.964310116483422e-05, "epoch": 37.8141592920354, "percentage": 5.39, "elapsed_time": "0:15:29", "remaining_time": "4:31:55", "throughput": 1320.09, "total_tokens": 1226424} {"current_steps": 2160, "total_steps": 40000, "loss": 0.0, "lr": 4.964144630641872e-05, "epoch": 37.902654867256636, "percentage": 5.4, "elapsed_time": "0:15:31", "remaining_time": "4:31:51", "throughput": 1319.82, "total_tokens": 1228920} {"current_steps": 2165, "total_steps": 40000, "loss": 0.0, "lr": 4.9639787647982525e-05, "epoch": 37.991150442477874, "percentage": 5.41, "elapsed_time": "0:15:33", "remaining_time": "4:31:47", "throughput": 1319.87, "total_tokens": 1231672} {"current_steps": 2170, "total_steps": 40000, "loss": 0.0, "lr": 4.963812518978143e-05, "epoch": 38.07079646017699, "percentage": 5.42, "elapsed_time": "0:15:35", "remaining_time": "4:31:47", "throughput": 1319.28, "total_tokens": 1234104} {"current_steps": 2175, "total_steps": 40000, "loss": 0.0, "lr": 4.963645893207182e-05, "epoch": 38.15929203539823, "percentage": 5.44, "elapsed_time": "0:15:37", "remaining_time": "4:31:44", "throughput": 1319.54, "total_tokens": 1237080} {"current_steps": 2180, "total_steps": 40000, "loss": 0.0, "lr": 4.963478887511063e-05, "epoch": 38.24778761061947, "percentage": 5.45, "elapsed_time": "0:15:39", "remaining_time": "4:31:40", "throughput": 1320.0, "total_tokens": 1240248} {"current_steps": 2185, "total_steps": 40000, "loss": 0.0, "lr": 4.963311501915542e-05, "epoch": 38.336283185840706, "percentage": 5.46, "elapsed_time": "0:15:41", "remaining_time": "4:31:37", "throughput": 1319.93, "total_tokens": 1242936} {"current_steps": 2190, "total_steps": 40000, "loss": 0.0, "lr": 4.963143736446432e-05, "epoch": 38.424778761061944, "percentage": 5.47, "elapsed_time": "0:15:43", "remaining_time": "4:31:33", "throughput": 1320.03, "total_tokens": 1245752} {"current_steps": 2195, "total_steps": 40000, "loss": 0.0, "lr": 4.962975591129603e-05, "epoch": 38.51327433628319, "percentage": 5.49, "elapsed_time": "0:15:45", "remaining_time": "4:31:29", "throughput": 1319.66, "total_tokens": 1248152} {"current_steps": 2200, "total_steps": 40000, "loss": 0.0, "lr": 4.962807065990986e-05, "epoch": 38.60176991150443, "percentage": 5.5, "elapsed_time": "0:15:47", "remaining_time": "4:31:26", "throughput": 1320.42, "total_tokens": 1251592} {"current_steps": 2200, "total_steps": 40000, "eval_loss": 0.34983158111572266, "epoch": 38.60176991150443, "percentage": 5.5, "elapsed_time": "0:15:48", "remaining_time": "4:31:44", "throughput": 1318.95, "total_tokens": 1251592} {"current_steps": 2205, "total_steps": 40000, "loss": 0.0, "lr": 4.9626381610565714e-05, "epoch": 38.690265486725664, "percentage": 5.51, "elapsed_time": "0:15:52", "remaining_time": "4:32:08", "throughput": 1316.67, "total_tokens": 1254312} {"current_steps": 2210, "total_steps": 40000, "loss": 0.0, "lr": 4.9624688763524043e-05, "epoch": 38.7787610619469, "percentage": 5.53, "elapsed_time": "0:15:54", "remaining_time": "4:32:05", "throughput": 1316.74, "total_tokens": 1257096} {"current_steps": 2215, "total_steps": 40000, "loss": 0.0, "lr": 4.962299211904591e-05, "epoch": 38.86725663716814, "percentage": 5.54, "elapsed_time": "0:15:56", "remaining_time": "4:32:01", "throughput": 1317.13, "total_tokens": 1260184} {"current_steps": 2220, "total_steps": 40000, "loss": 0.0, "lr": 4.962129167739296e-05, "epoch": 38.95575221238938, "percentage": 5.55, "elapsed_time": "0:15:58", "remaining_time": "4:31:57", "throughput": 1317.13, "total_tokens": 1262888} {"current_steps": 2225, "total_steps": 40000, "loss": 0.0, "lr": 4.961958743882742e-05, "epoch": 39.0353982300885, "percentage": 5.56, "elapsed_time": "0:16:01", "remaining_time": "4:31:56", "throughput": 1316.7, "total_tokens": 1265464} {"current_steps": 2230, "total_steps": 40000, "loss": 0.0, "lr": 4.961787940361211e-05, "epoch": 39.123893805309734, "percentage": 5.58, "elapsed_time": "0:16:03", "remaining_time": "4:31:53", "throughput": 1316.6, "total_tokens": 1268088} {"current_steps": 2235, "total_steps": 40000, "loss": 0.0, "lr": 4.961616757201043e-05, "epoch": 39.21238938053097, "percentage": 5.59, "elapsed_time": "0:16:05", "remaining_time": "4:31:49", "throughput": 1317.17, "total_tokens": 1271352} {"current_steps": 2240, "total_steps": 40000, "loss": 0.0, "lr": 4.961445194428637e-05, "epoch": 39.30088495575221, "percentage": 5.6, "elapsed_time": "0:16:07", "remaining_time": "4:31:45", "throughput": 1316.8, "total_tokens": 1273736} {"current_steps": 2245, "total_steps": 40000, "loss": 0.0, "lr": 4.9612732520704486e-05, "epoch": 39.389380530973455, "percentage": 5.61, "elapsed_time": "0:16:09", "remaining_time": "4:31:41", "throughput": 1316.96, "total_tokens": 1276600} {"current_steps": 2250, "total_steps": 40000, "loss": 0.0, "lr": 4.961100930152994e-05, "epoch": 39.47787610619469, "percentage": 5.62, "elapsed_time": "0:16:11", "remaining_time": "4:31:38", "throughput": 1317.46, "total_tokens": 1279800} {"current_steps": 2255, "total_steps": 40000, "loss": 0.0, "lr": 4.960928228702849e-05, "epoch": 39.56637168141593, "percentage": 5.64, "elapsed_time": "0:16:13", "remaining_time": "4:31:34", "throughput": 1318.11, "total_tokens": 1283144} {"current_steps": 2260, "total_steps": 40000, "loss": 0.0, "lr": 4.960755147746645e-05, "epoch": 39.65486725663717, "percentage": 5.65, "elapsed_time": "0:16:15", "remaining_time": "4:31:30", "throughput": 1318.04, "total_tokens": 1285816} {"current_steps": 2265, "total_steps": 40000, "loss": 0.0, "lr": 4.9605816873110736e-05, "epoch": 39.743362831858406, "percentage": 5.66, "elapsed_time": "0:16:17", "remaining_time": "4:31:27", "throughput": 1318.37, "total_tokens": 1288856} {"current_steps": 2270, "total_steps": 40000, "loss": 0.0, "lr": 4.960407847422883e-05, "epoch": 39.83185840707964, "percentage": 5.67, "elapsed_time": "0:16:19", "remaining_time": "4:31:23", "throughput": 1318.34, "total_tokens": 1291544} {"current_steps": 2275, "total_steps": 40000, "loss": 0.0, "lr": 4.960233628108885e-05, "epoch": 39.92035398230089, "percentage": 5.69, "elapsed_time": "0:16:21", "remaining_time": "4:31:19", "throughput": 1318.38, "total_tokens": 1294296} {"current_steps": 2280, "total_steps": 40000, "loss": 0.0, "lr": 4.960059029395942e-05, "epoch": 40.0, "percentage": 5.7, "elapsed_time": "0:16:23", "remaining_time": "4:31:14", "throughput": 1318.14, "total_tokens": 1296696} {"current_steps": 2285, "total_steps": 40000, "loss": 0.0, "lr": 4.959884051310983e-05, "epoch": 40.08849557522124, "percentage": 5.71, "elapsed_time": "0:16:26", "remaining_time": "4:31:15", "throughput": 1318.04, "total_tokens": 1299640} {"current_steps": 2290, "total_steps": 40000, "loss": 0.0, "lr": 4.959708693880991e-05, "epoch": 40.176991150442475, "percentage": 5.73, "elapsed_time": "0:16:28", "remaining_time": "4:31:11", "throughput": 1318.21, "total_tokens": 1302520} {"current_steps": 2295, "total_steps": 40000, "loss": 0.0, "lr": 4.9595329571330074e-05, "epoch": 40.26548672566372, "percentage": 5.74, "elapsed_time": "0:16:30", "remaining_time": "4:31:07", "throughput": 1318.74, "total_tokens": 1305784} {"current_steps": 2300, "total_steps": 40000, "loss": 0.0, "lr": 4.9593568410941326e-05, "epoch": 40.35398230088496, "percentage": 5.75, "elapsed_time": "0:16:32", "remaining_time": "4:31:04", "throughput": 1319.36, "total_tokens": 1309128} {"current_steps": 2305, "total_steps": 40000, "loss": 0.0, "lr": 4.959180345791528e-05, "epoch": 40.442477876106196, "percentage": 5.76, "elapsed_time": "0:16:34", "remaining_time": "4:31:00", "throughput": 1319.09, "total_tokens": 1311592} {"current_steps": 2310, "total_steps": 40000, "loss": 0.0, "lr": 4.9590034712524086e-05, "epoch": 40.530973451327434, "percentage": 5.78, "elapsed_time": "0:16:36", "remaining_time": "4:30:57", "throughput": 1318.87, "total_tokens": 1314104} {"current_steps": 2315, "total_steps": 40000, "loss": 0.0, "lr": 4.958826217504053e-05, "epoch": 40.61946902654867, "percentage": 5.79, "elapsed_time": "0:16:38", "remaining_time": "4:30:53", "throughput": 1318.82, "total_tokens": 1316776} {"current_steps": 2320, "total_steps": 40000, "loss": 0.0, "lr": 4.958648584573795e-05, "epoch": 40.70796460176991, "percentage": 5.8, "elapsed_time": "0:16:40", "remaining_time": "4:30:49", "throughput": 1318.72, "total_tokens": 1319400} {"current_steps": 2325, "total_steps": 40000, "loss": 0.0, "lr": 4.958470572489028e-05, "epoch": 40.796460176991154, "percentage": 5.81, "elapsed_time": "0:16:42", "remaining_time": "4:30:46", "throughput": 1319.0, "total_tokens": 1322408} {"current_steps": 2330, "total_steps": 40000, "loss": 0.0, "lr": 4.958292181277203e-05, "epoch": 40.88495575221239, "percentage": 5.83, "elapsed_time": "0:16:44", "remaining_time": "4:30:42", "throughput": 1319.12, "total_tokens": 1325256} {"current_steps": 2335, "total_steps": 40000, "loss": 0.0, "lr": 4.958113410965832e-05, "epoch": 40.97345132743363, "percentage": 5.84, "elapsed_time": "0:16:46", "remaining_time": "4:30:38", "throughput": 1319.13, "total_tokens": 1327976} {"current_steps": 2340, "total_steps": 40000, "loss": 0.0, "lr": 4.957934261582481e-05, "epoch": 41.05309734513274, "percentage": 5.85, "elapsed_time": "0:16:48", "remaining_time": "4:30:38", "throughput": 1318.84, "total_tokens": 1330648} {"current_steps": 2345, "total_steps": 40000, "loss": 0.0, "lr": 4.95775473315478e-05, "epoch": 41.14159292035398, "percentage": 5.86, "elapsed_time": "0:16:51", "remaining_time": "4:30:34", "throughput": 1319.55, "total_tokens": 1334088} {"current_steps": 2350, "total_steps": 40000, "loss": 0.0, "lr": 4.9575748257104124e-05, "epoch": 41.230088495575224, "percentage": 5.88, "elapsed_time": "0:16:53", "remaining_time": "4:30:30", "throughput": 1319.74, "total_tokens": 1337000} {"current_steps": 2355, "total_steps": 40000, "loss": 0.0, "lr": 4.9573945392771224e-05, "epoch": 41.31858407079646, "percentage": 5.89, "elapsed_time": "0:16:55", "remaining_time": "4:30:27", "throughput": 1319.99, "total_tokens": 1339976} {"current_steps": 2360, "total_steps": 40000, "loss": 0.0, "lr": 4.9572138738827134e-05, "epoch": 41.4070796460177, "percentage": 5.9, "elapsed_time": "0:16:57", "remaining_time": "4:30:23", "throughput": 1320.08, "total_tokens": 1342792} {"current_steps": 2365, "total_steps": 40000, "loss": 0.0, "lr": 4.957032829555046e-05, "epoch": 41.49557522123894, "percentage": 5.91, "elapsed_time": "0:16:59", "remaining_time": "4:30:19", "throughput": 1320.05, "total_tokens": 1345480} {"current_steps": 2370, "total_steps": 40000, "loss": 0.0, "lr": 4.956851406322039e-05, "epoch": 41.584070796460175, "percentage": 5.92, "elapsed_time": "0:17:01", "remaining_time": "4:30:16", "throughput": 1320.29, "total_tokens": 1348472} {"current_steps": 2375, "total_steps": 40000, "loss": 0.0, "lr": 4.9566696042116704e-05, "epoch": 41.67256637168141, "percentage": 5.94, "elapsed_time": "0:17:03", "remaining_time": "4:30:12", "throughput": 1320.53, "total_tokens": 1351432} {"current_steps": 2380, "total_steps": 40000, "loss": 0.0, "lr": 4.9564874232519766e-05, "epoch": 41.76106194690266, "percentage": 5.95, "elapsed_time": "0:17:05", "remaining_time": "4:30:09", "throughput": 1320.54, "total_tokens": 1354168} {"current_steps": 2385, "total_steps": 40000, "loss": 0.0, "lr": 4.9563048634710516e-05, "epoch": 41.849557522123895, "percentage": 5.96, "elapsed_time": "0:17:07", "remaining_time": "4:30:05", "throughput": 1320.6, "total_tokens": 1356952} {"current_steps": 2390, "total_steps": 40000, "loss": 0.0, "lr": 4.956121924897049e-05, "epoch": 41.93805309734513, "percentage": 5.97, "elapsed_time": "0:17:09", "remaining_time": "4:30:01", "throughput": 1320.25, "total_tokens": 1359304} {"current_steps": 2395, "total_steps": 40000, "loss": 0.0, "lr": 4.955938607558181e-05, "epoch": 42.017699115044245, "percentage": 5.99, "elapsed_time": "0:17:11", "remaining_time": "4:30:01", "throughput": 1319.75, "total_tokens": 1361752} {"current_steps": 2400, "total_steps": 40000, "loss": 0.0, "lr": 4.955754911482715e-05, "epoch": 42.10619469026549, "percentage": 6.0, "elapsed_time": "0:17:13", "remaining_time": "4:29:57", "throughput": 1319.58, "total_tokens": 1364312} {"current_steps": 2400, "total_steps": 40000, "eval_loss": 0.34935858845710754, "epoch": 42.10619469026549, "percentage": 6.0, "elapsed_time": "0:17:14", "remaining_time": "4:30:14", "throughput": 1318.21, "total_tokens": 1364312} {"current_steps": 2405, "total_steps": 40000, "loss": 0.0, "lr": 4.9555708366989804e-05, "epoch": 42.19469026548673, "percentage": 6.01, "elapsed_time": "0:17:18", "remaining_time": "4:30:36", "throughput": 1316.24, "total_tokens": 1367144} {"current_steps": 2410, "total_steps": 40000, "loss": 0.0, "lr": 4.9553863832353655e-05, "epoch": 42.283185840707965, "percentage": 6.02, "elapsed_time": "0:17:20", "remaining_time": "4:30:32", "throughput": 1316.24, "total_tokens": 1369864} {"current_steps": 2415, "total_steps": 40000, "loss": 0.0, "lr": 4.955201551120313e-05, "epoch": 42.3716814159292, "percentage": 6.04, "elapsed_time": "0:17:22", "remaining_time": "4:30:29", "throughput": 1316.94, "total_tokens": 1373304} {"current_steps": 2420, "total_steps": 40000, "loss": 0.0, "lr": 4.955016340382328e-05, "epoch": 42.46017699115044, "percentage": 6.05, "elapsed_time": "0:17:24", "remaining_time": "4:30:25", "throughput": 1317.08, "total_tokens": 1376168} {"current_steps": 2425, "total_steps": 40000, "loss": 0.0, "lr": 4.954830751049972e-05, "epoch": 42.54867256637168, "percentage": 6.06, "elapsed_time": "0:17:26", "remaining_time": "4:30:22", "throughput": 1317.26, "total_tokens": 1379080} {"current_steps": 2430, "total_steps": 40000, "loss": 0.0, "lr": 4.954644783151864e-05, "epoch": 42.63716814159292, "percentage": 6.08, "elapsed_time": "0:17:29", "remaining_time": "4:30:18", "throughput": 1317.52, "total_tokens": 1382088} {"current_steps": 2435, "total_steps": 40000, "loss": 0.0, "lr": 4.954458436716684e-05, "epoch": 42.72566371681416, "percentage": 6.09, "elapsed_time": "0:17:31", "remaining_time": "4:30:15", "throughput": 1317.3, "total_tokens": 1384600} {"current_steps": 2440, "total_steps": 40000, "loss": 0.0, "lr": 4.954271711773168e-05, "epoch": 42.8141592920354, "percentage": 6.1, "elapsed_time": "0:17:33", "remaining_time": "4:30:11", "throughput": 1317.12, "total_tokens": 1387128} {"current_steps": 2445, "total_steps": 40000, "loss": 0.0, "lr": 4.9540846083501115e-05, "epoch": 42.902654867256636, "percentage": 6.11, "elapsed_time": "0:17:35", "remaining_time": "4:30:08", "throughput": 1317.17, "total_tokens": 1389896} {"current_steps": 2450, "total_steps": 40000, "loss": 0.0, "lr": 4.953897126476369e-05, "epoch": 42.991150442477874, "percentage": 6.12, "elapsed_time": "0:17:37", "remaining_time": "4:30:04", "throughput": 1317.75, "total_tokens": 1393192} {"current_steps": 2455, "total_steps": 40000, "loss": 0.0, "lr": 4.9537092661808514e-05, "epoch": 43.07079646017699, "percentage": 6.14, "elapsed_time": "0:17:39", "remaining_time": "4:30:03", "throughput": 1317.2, "total_tokens": 1395600} {"current_steps": 2460, "total_steps": 40000, "loss": 0.0, "lr": 4.9535210274925306e-05, "epoch": 43.15929203539823, "percentage": 6.15, "elapsed_time": "0:17:41", "remaining_time": "4:29:59", "throughput": 1317.79, "total_tokens": 1398944} {"current_steps": 2465, "total_steps": 40000, "loss": 0.0, "lr": 4.953332410440435e-05, "epoch": 43.24778761061947, "percentage": 6.16, "elapsed_time": "0:17:43", "remaining_time": "4:29:56", "throughput": 1318.26, "total_tokens": 1402160} {"current_steps": 2470, "total_steps": 40000, "loss": 0.0, "lr": 4.9531434150536496e-05, "epoch": 43.336283185840706, "percentage": 6.17, "elapsed_time": "0:17:45", "remaining_time": "4:29:52", "throughput": 1318.16, "total_tokens": 1404784} {"current_steps": 2475, "total_steps": 40000, "loss": 0.0, "lr": 4.952954041361322e-05, "epoch": 43.424778761061944, "percentage": 6.19, "elapsed_time": "0:17:47", "remaining_time": "4:29:49", "throughput": 1318.01, "total_tokens": 1407344} {"current_steps": 2480, "total_steps": 40000, "loss": 0.0, "lr": 4.952764289392655e-05, "epoch": 43.51327433628319, "percentage": 6.2, "elapsed_time": "0:17:49", "remaining_time": "4:29:45", "throughput": 1318.55, "total_tokens": 1410656} {"current_steps": 2485, "total_steps": 40000, "loss": 0.0, "lr": 4.952574159176912e-05, "epoch": 43.60176991150443, "percentage": 6.21, "elapsed_time": "0:17:51", "remaining_time": "4:29:42", "throughput": 1318.53, "total_tokens": 1413344} {"current_steps": 2490, "total_steps": 40000, "loss": 0.0, "lr": 4.952383650743413e-05, "epoch": 43.690265486725664, "percentage": 6.22, "elapsed_time": "0:17:53", "remaining_time": "4:29:38", "throughput": 1318.38, "total_tokens": 1415904} {"current_steps": 2495, "total_steps": 40000, "loss": 0.0, "lr": 4.952192764121536e-05, "epoch": 43.7787610619469, "percentage": 6.24, "elapsed_time": "0:17:56", "remaining_time": "4:29:34", "throughput": 1318.16, "total_tokens": 1418384} {"current_steps": 2500, "total_steps": 40000, "loss": 0.0, "lr": 4.9520014993407185e-05, "epoch": 43.86725663716814, "percentage": 6.25, "elapsed_time": "0:17:58", "remaining_time": "4:29:31", "throughput": 1318.37, "total_tokens": 1421328} {"current_steps": 2505, "total_steps": 40000, "loss": 0.0, "lr": 4.951809856430456e-05, "epoch": 43.95575221238938, "percentage": 6.26, "elapsed_time": "0:18:00", "remaining_time": "4:29:27", "throughput": 1318.61, "total_tokens": 1424304} {"current_steps": 2510, "total_steps": 40000, "loss": 0.0, "lr": 4.951617835420303e-05, "epoch": 44.0353982300885, "percentage": 6.28, "elapsed_time": "0:18:02", "remaining_time": "4:29:26", "throughput": 1318.0, "total_tokens": 1426608} {"current_steps": 2515, "total_steps": 40000, "loss": 0.0, "lr": 4.951425436339869e-05, "epoch": 44.123893805309734, "percentage": 6.29, "elapsed_time": "0:18:04", "remaining_time": "4:29:23", "throughput": 1318.07, "total_tokens": 1429392} {"current_steps": 2520, "total_steps": 40000, "loss": 0.0, "lr": 4.9512326592188274e-05, "epoch": 44.21238938053097, "percentage": 6.3, "elapsed_time": "0:18:06", "remaining_time": "4:29:19", "throughput": 1318.4, "total_tokens": 1432464} {"current_steps": 2525, "total_steps": 40000, "loss": 0.0, "lr": 4.9510395040869054e-05, "epoch": 44.30088495575221, "percentage": 6.31, "elapsed_time": "0:18:08", "remaining_time": "4:29:16", "throughput": 1318.41, "total_tokens": 1435200} {"current_steps": 2530, "total_steps": 40000, "loss": 0.0, "lr": 4.9508459709738905e-05, "epoch": 44.389380530973455, "percentage": 6.33, "elapsed_time": "0:18:10", "remaining_time": "4:29:12", "throughput": 1318.89, "total_tokens": 1438448} {"current_steps": 2535, "total_steps": 40000, "loss": 0.0, "lr": 4.950652059909627e-05, "epoch": 44.47787610619469, "percentage": 6.34, "elapsed_time": "0:18:12", "remaining_time": "4:29:09", "throughput": 1318.72, "total_tokens": 1440976} {"current_steps": 2540, "total_steps": 40000, "loss": 0.0, "lr": 4.95045777092402e-05, "epoch": 44.56637168141593, "percentage": 6.35, "elapsed_time": "0:18:14", "remaining_time": "4:29:05", "throughput": 1319.13, "total_tokens": 1444160} {"current_steps": 2545, "total_steps": 40000, "loss": 0.0, "lr": 4.950263104047031e-05, "epoch": 44.65486725663717, "percentage": 6.36, "elapsed_time": "0:18:16", "remaining_time": "4:29:02", "throughput": 1319.19, "total_tokens": 1446944} {"current_steps": 2550, "total_steps": 40000, "loss": 0.0, "lr": 4.9500680593086775e-05, "epoch": 44.743362831858406, "percentage": 6.38, "elapsed_time": "0:18:18", "remaining_time": "4:28:58", "throughput": 1319.81, "total_tokens": 1450336} {"current_steps": 2555, "total_steps": 40000, "loss": 0.0, "lr": 4.94987263673904e-05, "epoch": 44.83185840707964, "percentage": 6.39, "elapsed_time": "0:18:20", "remaining_time": "4:28:55", "throughput": 1320.04, "total_tokens": 1453328} {"current_steps": 2560, "total_steps": 40000, "loss": 0.0, "lr": 4.949676836368256e-05, "epoch": 44.92035398230089, "percentage": 6.4, "elapsed_time": "0:18:23", "remaining_time": "4:28:52", "throughput": 1320.17, "total_tokens": 1456208} {"current_steps": 2565, "total_steps": 40000, "loss": 0.0, "lr": 4.949480658226518e-05, "epoch": 45.0, "percentage": 6.41, "elapsed_time": "0:18:25", "remaining_time": "4:28:47", "throughput": 1319.81, "total_tokens": 1458448} {"current_steps": 2570, "total_steps": 40000, "loss": 0.0, "lr": 4.949284102344082e-05, "epoch": 45.08849557522124, "percentage": 6.42, "elapsed_time": "0:18:27", "remaining_time": "4:28:47", "throughput": 1319.93, "total_tokens": 1461616} {"current_steps": 2575, "total_steps": 40000, "loss": 0.0, "lr": 4.9490871687512565e-05, "epoch": 45.176991150442475, "percentage": 6.44, "elapsed_time": "0:18:29", "remaining_time": "4:28:44", "throughput": 1319.94, "total_tokens": 1464352} {"current_steps": 2580, "total_steps": 40000, "loss": 0.0, "lr": 4.948889857478413e-05, "epoch": 45.26548672566372, "percentage": 6.45, "elapsed_time": "0:18:31", "remaining_time": "4:28:40", "throughput": 1320.07, "total_tokens": 1467232} {"current_steps": 2585, "total_steps": 40000, "loss": 0.0, "lr": 4.948692168555978e-05, "epoch": 45.35398230088496, "percentage": 6.46, "elapsed_time": "0:18:33", "remaining_time": "4:28:37", "throughput": 1320.24, "total_tokens": 1470144} {"current_steps": 2590, "total_steps": 40000, "loss": 0.0, "lr": 4.94849410201444e-05, "epoch": 45.442477876106196, "percentage": 6.48, "elapsed_time": "0:18:35", "remaining_time": "4:28:33", "throughput": 1320.47, "total_tokens": 1473120} {"current_steps": 2595, "total_steps": 40000, "loss": 0.0, "lr": 4.948295657884341e-05, "epoch": 45.530973451327434, "percentage": 6.49, "elapsed_time": "0:18:37", "remaining_time": "4:28:30", "throughput": 1320.48, "total_tokens": 1475856} {"current_steps": 2600, "total_steps": 40000, "loss": 0.0, "lr": 4.9480968361962835e-05, "epoch": 45.61946902654867, "percentage": 6.5, "elapsed_time": "0:18:39", "remaining_time": "4:28:26", "throughput": 1320.59, "total_tokens": 1478704} {"current_steps": 2600, "total_steps": 40000, "eval_loss": 0.3589751124382019, "epoch": 45.61946902654867, "percentage": 6.5, "elapsed_time": "0:18:40", "remaining_time": "4:28:42", "throughput": 1319.33, "total_tokens": 1478704} {"current_steps": 2605, "total_steps": 40000, "loss": 0.0, "lr": 4.9478976369809305e-05, "epoch": 45.70796460176991, "percentage": 6.51, "elapsed_time": "0:18:44", "remaining_time": "4:29:02", "throughput": 1317.14, "total_tokens": 1481120} {"current_steps": 2610, "total_steps": 40000, "loss": 0.0, "lr": 4.947698060268999e-05, "epoch": 45.796460176991154, "percentage": 6.53, "elapsed_time": "0:18:46", "remaining_time": "4:28:58", "throughput": 1317.55, "total_tokens": 1484320} {"current_steps": 2615, "total_steps": 40000, "loss": 0.0, "lr": 4.9474981060912665e-05, "epoch": 45.88495575221239, "percentage": 6.54, "elapsed_time": "0:18:48", "remaining_time": "4:28:55", "throughput": 1318.03, "total_tokens": 1487568} {"current_steps": 2620, "total_steps": 40000, "loss": 0.0, "lr": 4.94729777447857e-05, "epoch": 45.97345132743363, "percentage": 6.55, "elapsed_time": "0:18:50", "remaining_time": "4:28:51", "throughput": 1318.07, "total_tokens": 1490304} {"current_steps": 2625, "total_steps": 40000, "loss": 0.0, "lr": 4.947097065461801e-05, "epoch": 46.05309734513274, "percentage": 6.56, "elapsed_time": "0:18:52", "remaining_time": "4:28:50", "throughput": 1317.42, "total_tokens": 1492544} {"current_steps": 2630, "total_steps": 40000, "loss": 0.0, "lr": 4.9468959790719125e-05, "epoch": 46.14159292035398, "percentage": 6.58, "elapsed_time": "0:18:54", "remaining_time": "4:28:47", "throughput": 1317.75, "total_tokens": 1495632} {"current_steps": 2635, "total_steps": 40000, "loss": 0.0, "lr": 4.9466945153399146e-05, "epoch": 46.230088495575224, "percentage": 6.59, "elapsed_time": "0:18:57", "remaining_time": "4:28:43", "throughput": 1317.89, "total_tokens": 1498528} {"current_steps": 2640, "total_steps": 40000, "loss": 0.0, "lr": 4.9464926742968755e-05, "epoch": 46.31858407079646, "percentage": 6.6, "elapsed_time": "0:18:59", "remaining_time": "4:28:40", "throughput": 1318.25, "total_tokens": 1501648} {"current_steps": 2645, "total_steps": 40000, "loss": 0.0, "lr": 4.946290455973921e-05, "epoch": 46.4070796460177, "percentage": 6.61, "elapsed_time": "0:19:01", "remaining_time": "4:28:37", "throughput": 1318.22, "total_tokens": 1504352} {"current_steps": 2650, "total_steps": 40000, "loss": 0.0, "lr": 4.9460878604022365e-05, "epoch": 46.49557522123894, "percentage": 6.62, "elapsed_time": "0:19:03", "remaining_time": "4:28:33", "throughput": 1318.47, "total_tokens": 1507360} {"current_steps": 2655, "total_steps": 40000, "loss": 0.0, "lr": 4.945884887613065e-05, "epoch": 46.584070796460175, "percentage": 6.64, "elapsed_time": "0:19:05", "remaining_time": "4:28:30", "throughput": 1318.42, "total_tokens": 1510032} {"current_steps": 2660, "total_steps": 40000, "loss": 0.0, "lr": 4.9456815376377055e-05, "epoch": 46.67256637168141, "percentage": 6.65, "elapsed_time": "0:19:07", "remaining_time": "4:28:26", "throughput": 1318.75, "total_tokens": 1513136} {"current_steps": 2665, "total_steps": 40000, "loss": 0.0, "lr": 4.9454778105075195e-05, "epoch": 46.76106194690266, "percentage": 6.66, "elapsed_time": "0:19:09", "remaining_time": "4:28:23", "throughput": 1318.46, "total_tokens": 1515520} {"current_steps": 2670, "total_steps": 40000, "loss": 0.0, "lr": 4.945273706253924e-05, "epoch": 46.849557522123895, "percentage": 6.68, "elapsed_time": "0:19:11", "remaining_time": "4:28:19", "throughput": 1318.73, "total_tokens": 1518544} {"current_steps": 2675, "total_steps": 40000, "loss": 0.0, "lr": 4.9450692249083925e-05, "epoch": 46.93805309734513, "percentage": 6.69, "elapsed_time": "0:19:13", "remaining_time": "4:28:16", "throughput": 1318.75, "total_tokens": 1521280} {"current_steps": 2680, "total_steps": 40000, "loss": 0.0, "lr": 4.9448643665024605e-05, "epoch": 47.017699115044245, "percentage": 6.7, "elapsed_time": "0:19:15", "remaining_time": "4:28:15", "throughput": 1318.2, "total_tokens": 1523616} {"current_steps": 2685, "total_steps": 40000, "loss": 0.0, "lr": 4.944659131067719e-05, "epoch": 47.10619469026549, "percentage": 6.71, "elapsed_time": "0:19:17", "remaining_time": "4:28:12", "throughput": 1318.6, "total_tokens": 1526816} {"current_steps": 2690, "total_steps": 40000, "loss": 0.0, "lr": 4.944453518635818e-05, "epoch": 47.19469026548673, "percentage": 6.73, "elapsed_time": "0:19:19", "remaining_time": "4:28:08", "throughput": 1318.81, "total_tokens": 1529776} {"current_steps": 2695, "total_steps": 40000, "loss": 0.0, "lr": 4.944247529238465e-05, "epoch": 47.283185840707965, "percentage": 6.74, "elapsed_time": "0:19:22", "remaining_time": "4:28:05", "throughput": 1318.92, "total_tokens": 1532624} {"current_steps": 2700, "total_steps": 40000, "loss": 0.0, "lr": 4.944041162907427e-05, "epoch": 47.3716814159292, "percentage": 6.75, "elapsed_time": "0:19:24", "remaining_time": "4:28:01", "throughput": 1319.0, "total_tokens": 1535440} {"current_steps": 2705, "total_steps": 40000, "loss": 0.0, "lr": 4.943834419674529e-05, "epoch": 47.46017699115044, "percentage": 6.76, "elapsed_time": "0:19:26", "remaining_time": "4:27:58", "throughput": 1319.15, "total_tokens": 1538336} {"current_steps": 2710, "total_steps": 40000, "loss": 0.0, "lr": 4.9436272995716506e-05, "epoch": 47.54867256637168, "percentage": 6.78, "elapsed_time": "0:19:28", "remaining_time": "4:27:54", "throughput": 1319.12, "total_tokens": 1541024} {"current_steps": 2715, "total_steps": 40000, "loss": 0.0, "lr": 4.943419802630735e-05, "epoch": 47.63716814159292, "percentage": 6.79, "elapsed_time": "0:19:30", "remaining_time": "4:27:51", "throughput": 1319.45, "total_tokens": 1544160} {"current_steps": 2720, "total_steps": 40000, "loss": 0.0, "lr": 4.94321192888378e-05, "epoch": 47.72566371681416, "percentage": 6.8, "elapsed_time": "0:19:32", "remaining_time": "4:27:48", "throughput": 1319.45, "total_tokens": 1546880} {"current_steps": 2725, "total_steps": 40000, "loss": 0.0, "lr": 4.943003678362842e-05, "epoch": 47.8141592920354, "percentage": 6.81, "elapsed_time": "0:19:34", "remaining_time": "4:27:44", "throughput": 1319.12, "total_tokens": 1549216} {"current_steps": 2730, "total_steps": 40000, "loss": 0.0, "lr": 4.942795051100036e-05, "epoch": 47.902654867256636, "percentage": 6.83, "elapsed_time": "0:19:36", "remaining_time": "4:27:41", "throughput": 1318.87, "total_tokens": 1551648} {"current_steps": 2735, "total_steps": 40000, "loss": 0.0, "lr": 4.942586047127536e-05, "epoch": 47.991150442477874, "percentage": 6.84, "elapsed_time": "0:19:38", "remaining_time": "4:27:37", "throughput": 1319.22, "total_tokens": 1554752} {"current_steps": 2740, "total_steps": 40000, "loss": 0.0, "lr": 4.942376666477571e-05, "epoch": 48.07079646017699, "percentage": 6.85, "elapsed_time": "0:19:40", "remaining_time": "4:27:37", "throughput": 1318.84, "total_tokens": 1557288} {"current_steps": 2745, "total_steps": 40000, "loss": 0.0, "lr": 4.9421669091824304e-05, "epoch": 48.15929203539823, "percentage": 6.86, "elapsed_time": "0:19:42", "remaining_time": "4:27:33", "throughput": 1319.18, "total_tokens": 1560408} {"current_steps": 2750, "total_steps": 40000, "loss": 0.0, "lr": 4.9419567752744634e-05, "epoch": 48.24778761061947, "percentage": 6.88, "elapsed_time": "0:19:44", "remaining_time": "4:27:30", "throughput": 1319.2, "total_tokens": 1563160} {"current_steps": 2755, "total_steps": 40000, "loss": 0.0, "lr": 4.941746264786074e-05, "epoch": 48.336283185840706, "percentage": 6.89, "elapsed_time": "0:19:47", "remaining_time": "4:27:27", "throughput": 1319.2, "total_tokens": 1565896} {"current_steps": 2760, "total_steps": 40000, "loss": 0.0, "lr": 4.9415353777497254e-05, "epoch": 48.424778761061944, "percentage": 6.9, "elapsed_time": "0:19:49", "remaining_time": "4:27:23", "throughput": 1319.34, "total_tokens": 1568776} {"current_steps": 2765, "total_steps": 40000, "loss": 0.0, "lr": 4.9413241141979394e-05, "epoch": 48.51327433628319, "percentage": 6.91, "elapsed_time": "0:19:51", "remaining_time": "4:27:20", "throughput": 1319.54, "total_tokens": 1571736} {"current_steps": 2770, "total_steps": 40000, "loss": 0.0, "lr": 4.9411124741632956e-05, "epoch": 48.60176991150443, "percentage": 6.93, "elapsed_time": "0:19:53", "remaining_time": "4:27:16", "throughput": 1320.01, "total_tokens": 1575016} {"current_steps": 2775, "total_steps": 40000, "loss": 0.0, "lr": 4.940900457678431e-05, "epoch": 48.690265486725664, "percentage": 6.94, "elapsed_time": "0:19:55", "remaining_time": "4:27:13", "throughput": 1319.77, "total_tokens": 1577448} {"current_steps": 2780, "total_steps": 40000, "loss": 0.0, "lr": 4.9406880647760425e-05, "epoch": 48.7787610619469, "percentage": 6.95, "elapsed_time": "0:19:57", "remaining_time": "4:27:10", "throughput": 1319.68, "total_tokens": 1580056} {"current_steps": 2785, "total_steps": 40000, "loss": 0.0, "lr": 4.9404752954888824e-05, "epoch": 48.86725663716814, "percentage": 6.96, "elapsed_time": "0:19:59", "remaining_time": "4:27:06", "throughput": 1319.95, "total_tokens": 1583096} {"current_steps": 2790, "total_steps": 40000, "loss": 0.0, "lr": 4.940262149849762e-05, "epoch": 48.95575221238938, "percentage": 6.98, "elapsed_time": "0:20:01", "remaining_time": "4:27:03", "throughput": 1319.99, "total_tokens": 1585864} {"current_steps": 2795, "total_steps": 40000, "loss": 0.0, "lr": 4.9400486278915526e-05, "epoch": 49.0353982300885, "percentage": 6.99, "elapsed_time": "0:20:03", "remaining_time": "4:27:02", "throughput": 1319.72, "total_tokens": 1588512} {"current_steps": 2800, "total_steps": 40000, "loss": 0.0, "lr": 4.939834729647181e-05, "epoch": 49.123893805309734, "percentage": 7.0, "elapsed_time": "0:20:05", "remaining_time": "4:26:59", "throughput": 1319.88, "total_tokens": 1591424} {"current_steps": 2800, "total_steps": 40000, "eval_loss": 0.36007025837898254, "epoch": 49.123893805309734, "percentage": 7.0, "elapsed_time": "0:20:06", "remaining_time": "4:27:13", "throughput": 1318.72, "total_tokens": 1591424} {"current_steps": 2805, "total_steps": 40000, "loss": 0.0, "lr": 4.9396204551496326e-05, "epoch": 49.21238938053097, "percentage": 7.01, "elapsed_time": "0:20:10", "remaining_time": "4:27:31", "throughput": 1316.65, "total_tokens": 1593840} {"current_steps": 2810, "total_steps": 40000, "loss": 0.0, "lr": 4.939405804431952e-05, "epoch": 49.30088495575221, "percentage": 7.03, "elapsed_time": "0:20:12", "remaining_time": "4:27:28", "throughput": 1317.19, "total_tokens": 1597232} {"current_steps": 2815, "total_steps": 40000, "loss": 0.0, "lr": 4.9391907775272414e-05, "epoch": 49.389380530973455, "percentage": 7.04, "elapsed_time": "0:20:14", "remaining_time": "4:27:25", "throughput": 1317.34, "total_tokens": 1600144} {"current_steps": 2820, "total_steps": 40000, "loss": 0.0, "lr": 4.9389753744686604e-05, "epoch": 49.47787610619469, "percentage": 7.05, "elapsed_time": "0:20:16", "remaining_time": "4:27:21", "throughput": 1317.29, "total_tokens": 1602800} {"current_steps": 2825, "total_steps": 40000, "loss": 0.0, "lr": 4.938759595289426e-05, "epoch": 49.56637168141593, "percentage": 7.06, "elapsed_time": "0:20:18", "remaining_time": "4:27:18", "throughput": 1317.58, "total_tokens": 1605872} {"current_steps": 2830, "total_steps": 40000, "loss": 0.0, "lr": 4.938543440022815e-05, "epoch": 49.65486725663717, "percentage": 7.07, "elapsed_time": "0:20:20", "remaining_time": "4:27:15", "throughput": 1317.73, "total_tokens": 1608768} {"current_steps": 2835, "total_steps": 40000, "loss": 0.0, "lr": 4.938326908702161e-05, "epoch": 49.743362831858406, "percentage": 7.09, "elapsed_time": "0:20:22", "remaining_time": "4:27:11", "throughput": 1317.73, "total_tokens": 1611488} {"current_steps": 2840, "total_steps": 40000, "loss": 0.0, "lr": 4.9381100013608554e-05, "epoch": 49.83185840707964, "percentage": 7.1, "elapsed_time": "0:20:24", "remaining_time": "4:27:08", "throughput": 1317.93, "total_tokens": 1614448} {"current_steps": 2845, "total_steps": 40000, "loss": 0.0, "lr": 4.9378927180323485e-05, "epoch": 49.92035398230089, "percentage": 7.11, "elapsed_time": "0:20:27", "remaining_time": "4:27:04", "throughput": 1317.62, "total_tokens": 1616784} {"current_steps": 2850, "total_steps": 40000, "loss": 0.0, "lr": 4.937675058750148e-05, "epoch": 50.0, "percentage": 7.12, "elapsed_time": "0:20:29", "remaining_time": "4:27:00", "throughput": 1317.57, "total_tokens": 1619360} {"current_steps": 2855, "total_steps": 40000, "loss": 0.0, "lr": 4.937457023547819e-05, "epoch": 50.08849557522124, "percentage": 7.14, "elapsed_time": "0:20:31", "remaining_time": "4:27:00", "throughput": 1317.6, "total_tokens": 1622448} {"current_steps": 2860, "total_steps": 40000, "loss": 0.0, "lr": 4.9372386124589876e-05, "epoch": 50.176991150442475, "percentage": 7.15, "elapsed_time": "0:20:33", "remaining_time": "4:26:57", "throughput": 1317.9, "total_tokens": 1625536} {"current_steps": 2865, "total_steps": 40000, "loss": 0.0, "lr": 4.937019825517333e-05, "epoch": 50.26548672566372, "percentage": 7.16, "elapsed_time": "0:20:35", "remaining_time": "4:26:53", "throughput": 1317.84, "total_tokens": 1628176} {"current_steps": 2870, "total_steps": 40000, "loss": 0.0, "lr": 4.9368006627565954e-05, "epoch": 50.35398230088496, "percentage": 7.17, "elapsed_time": "0:20:37", "remaining_time": "4:26:50", "throughput": 1317.63, "total_tokens": 1630640} {"current_steps": 2875, "total_steps": 40000, "loss": 0.0, "lr": 4.936581124210573e-05, "epoch": 50.442477876106196, "percentage": 7.19, "elapsed_time": "0:20:39", "remaining_time": "4:26:47", "throughput": 1317.4, "total_tokens": 1633072} {"current_steps": 2880, "total_steps": 40000, "loss": 0.0, "lr": 4.9363612099131216e-05, "epoch": 50.530973451327434, "percentage": 7.2, "elapsed_time": "0:20:41", "remaining_time": "4:26:43", "throughput": 1317.3, "total_tokens": 1635664} {"current_steps": 2885, "total_steps": 40000, "loss": 0.0, "lr": 4.936140919898155e-05, "epoch": 50.61946902654867, "percentage": 7.21, "elapsed_time": "0:20:43", "remaining_time": "4:26:40", "throughput": 1317.65, "total_tokens": 1638816} {"current_steps": 2890, "total_steps": 40000, "loss": 0.0, "lr": 4.9359202541996426e-05, "epoch": 50.70796460176991, "percentage": 7.22, "elapsed_time": "0:20:45", "remaining_time": "4:26:37", "throughput": 1317.99, "total_tokens": 1641968} {"current_steps": 2895, "total_steps": 40000, "loss": 0.0, "lr": 4.935699212851616e-05, "epoch": 50.796460176991154, "percentage": 7.24, "elapsed_time": "0:20:47", "remaining_time": "4:26:33", "throughput": 1318.21, "total_tokens": 1644960} {"current_steps": 2900, "total_steps": 40000, "loss": 0.0, "lr": 4.935477795888162e-05, "epoch": 50.88495575221239, "percentage": 7.25, "elapsed_time": "0:20:49", "remaining_time": "4:26:30", "throughput": 1318.69, "total_tokens": 1648272} {"current_steps": 2905, "total_steps": 40000, "loss": 0.0, "lr": 4.935256003343426e-05, "epoch": 50.97345132743363, "percentage": 7.26, "elapsed_time": "0:20:51", "remaining_time": "4:26:26", "throughput": 1318.84, "total_tokens": 1651152} {"current_steps": 2910, "total_steps": 40000, "loss": 0.0, "lr": 4.93503383525161e-05, "epoch": 51.05309734513274, "percentage": 7.27, "elapsed_time": "0:20:54", "remaining_time": "4:26:25", "throughput": 1318.35, "total_tokens": 1653504} {"current_steps": 2915, "total_steps": 40000, "loss": 0.0, "lr": 4.934811291646977e-05, "epoch": 51.14159292035398, "percentage": 7.29, "elapsed_time": "0:20:56", "remaining_time": "4:26:22", "throughput": 1318.67, "total_tokens": 1656624} {"current_steps": 2920, "total_steps": 40000, "loss": 0.0, "lr": 4.934588372563845e-05, "epoch": 51.230088495575224, "percentage": 7.3, "elapsed_time": "0:20:58", "remaining_time": "4:26:19", "throughput": 1318.73, "total_tokens": 1659424} {"current_steps": 2925, "total_steps": 40000, "loss": 0.0, "lr": 4.93436507803659e-05, "epoch": 51.31858407079646, "percentage": 7.31, "elapsed_time": "0:21:00", "remaining_time": "4:26:16", "throughput": 1319.03, "total_tokens": 1662528} {"current_steps": 2930, "total_steps": 40000, "loss": 0.0, "lr": 4.934141408099649e-05, "epoch": 51.4070796460177, "percentage": 7.32, "elapsed_time": "0:21:02", "remaining_time": "4:26:12", "throughput": 1319.34, "total_tokens": 1665632} {"current_steps": 2935, "total_steps": 40000, "loss": 0.0, "lr": 4.9339173627875135e-05, "epoch": 51.49557522123894, "percentage": 7.34, "elapsed_time": "0:21:04", "remaining_time": "4:26:09", "throughput": 1319.48, "total_tokens": 1668544} {"current_steps": 2940, "total_steps": 40000, "loss": 0.0, "lr": 4.9336929421347335e-05, "epoch": 51.584070796460175, "percentage": 7.35, "elapsed_time": "0:21:06", "remaining_time": "4:26:06", "throughput": 1319.41, "total_tokens": 1671184} {"current_steps": 2945, "total_steps": 40000, "loss": 0.0, "lr": 4.933468146175918e-05, "epoch": 51.67256637168141, "percentage": 7.36, "elapsed_time": "0:21:08", "remaining_time": "4:26:03", "throughput": 1319.73, "total_tokens": 1674320} {"current_steps": 2950, "total_steps": 40000, "loss": 0.0, "lr": 4.933242974945734e-05, "epoch": 51.76106194690266, "percentage": 7.38, "elapsed_time": "0:21:10", "remaining_time": "4:25:59", "throughput": 1319.87, "total_tokens": 1677216} {"current_steps": 2955, "total_steps": 40000, "loss": 0.0, "lr": 4.933017428478906e-05, "epoch": 51.849557522123895, "percentage": 7.39, "elapsed_time": "0:21:12", "remaining_time": "4:25:56", "throughput": 1319.89, "total_tokens": 1679968} {"current_steps": 2960, "total_steps": 40000, "loss": 0.0, "lr": 4.932791506810214e-05, "epoch": 51.93805309734513, "percentage": 7.4, "elapsed_time": "0:21:14", "remaining_time": "4:25:53", "throughput": 1319.72, "total_tokens": 1682480} {"current_steps": 2965, "total_steps": 40000, "loss": 0.0, "lr": 4.932565209974499e-05, "epoch": 52.017699115044245, "percentage": 7.41, "elapsed_time": "0:21:17", "remaining_time": "4:25:52", "throughput": 1319.65, "total_tokens": 1685352} {"current_steps": 2970, "total_steps": 40000, "loss": 0.0, "lr": 4.93233853800666e-05, "epoch": 52.10619469026549, "percentage": 7.42, "elapsed_time": "0:21:19", "remaining_time": "4:25:48", "throughput": 1319.42, "total_tokens": 1687784} {"current_steps": 2975, "total_steps": 40000, "loss": 0.0, "lr": 4.932111490941651e-05, "epoch": 52.19469026548673, "percentage": 7.44, "elapsed_time": "0:21:21", "remaining_time": "4:25:45", "throughput": 1320.13, "total_tokens": 1691416} {"current_steps": 2980, "total_steps": 40000, "loss": 0.0, "lr": 4.9318840688144876e-05, "epoch": 52.283185840707965, "percentage": 7.45, "elapsed_time": "0:21:23", "remaining_time": "4:25:42", "throughput": 1320.29, "total_tokens": 1694344} {"current_steps": 2985, "total_steps": 40000, "loss": 0.0, "lr": 4.9316562716602387e-05, "epoch": 52.3716814159292, "percentage": 7.46, "elapsed_time": "0:21:25", "remaining_time": "4:25:39", "throughput": 1320.12, "total_tokens": 1696840} {"current_steps": 2990, "total_steps": 40000, "loss": 0.0, "lr": 4.9314280995140346e-05, "epoch": 52.46017699115044, "percentage": 7.47, "elapsed_time": "0:21:27", "remaining_time": "4:25:35", "throughput": 1319.92, "total_tokens": 1699304} {"current_steps": 2995, "total_steps": 40000, "loss": 0.0, "lr": 4.931199552411063e-05, "epoch": 52.54867256637168, "percentage": 7.49, "elapsed_time": "0:21:29", "remaining_time": "4:25:32", "throughput": 1319.8, "total_tokens": 1701880} {"current_steps": 3000, "total_steps": 40000, "loss": 0.0, "lr": 4.930970630386568e-05, "epoch": 52.63716814159292, "percentage": 7.5, "elapsed_time": "0:21:31", "remaining_time": "4:25:29", "throughput": 1320.1, "total_tokens": 1705000} {"current_steps": 3000, "total_steps": 40000, "eval_loss": 0.35832923650741577, "epoch": 52.63716814159292, "percentage": 7.5, "elapsed_time": "0:21:32", "remaining_time": "4:25:42", "throughput": 1319.01, "total_tokens": 1705000} {"current_steps": 3005, "total_steps": 40000, "loss": 0.0, "lr": 4.9307413334758524e-05, "epoch": 52.72566371681416, "percentage": 7.51, "elapsed_time": "0:21:36", "remaining_time": "4:26:02", "throughput": 1317.21, "total_tokens": 1707896} {"current_steps": 3010, "total_steps": 40000, "loss": 0.0, "lr": 4.930511661714276e-05, "epoch": 52.8141592920354, "percentage": 7.52, "elapsed_time": "0:21:38", "remaining_time": "4:25:59", "throughput": 1317.39, "total_tokens": 1710840} {"current_steps": 3015, "total_steps": 40000, "loss": 0.0, "lr": 4.9302816151372576e-05, "epoch": 52.902654867256636, "percentage": 7.54, "elapsed_time": "0:21:40", "remaining_time": "4:25:55", "throughput": 1317.34, "total_tokens": 1713480} {"current_steps": 3020, "total_steps": 40000, "loss": 0.0, "lr": 4.930051193780274e-05, "epoch": 52.991150442477874, "percentage": 7.55, "elapsed_time": "0:21:42", "remaining_time": "4:25:52", "throughput": 1317.75, "total_tokens": 1716696} {"current_steps": 3025, "total_steps": 40000, "loss": 0.0, "lr": 4.929820397678858e-05, "epoch": 53.07079646017699, "percentage": 7.56, "elapsed_time": "0:21:45", "remaining_time": "4:25:51", "throughput": 1317.47, "total_tokens": 1719344} {"current_steps": 3030, "total_steps": 40000, "loss": 0.0, "lr": 4.9295892268686015e-05, "epoch": 53.15929203539823, "percentage": 7.58, "elapsed_time": "0:21:47", "remaining_time": "4:25:48", "throughput": 1317.69, "total_tokens": 1722352} {"current_steps": 3035, "total_steps": 40000, "loss": 0.0, "lr": 4.9293576813851536e-05, "epoch": 53.24778761061947, "percentage": 7.59, "elapsed_time": "0:21:49", "remaining_time": "4:25:45", "throughput": 1317.88, "total_tokens": 1725312} {"current_steps": 3040, "total_steps": 40000, "loss": 0.0, "lr": 4.929125761264223e-05, "epoch": 53.336283185840706, "percentage": 7.6, "elapsed_time": "0:21:51", "remaining_time": "4:25:41", "throughput": 1318.01, "total_tokens": 1728208} {"current_steps": 3045, "total_steps": 40000, "loss": 0.0, "lr": 4.928893466541573e-05, "epoch": 53.424778761061944, "percentage": 7.61, "elapsed_time": "0:21:53", "remaining_time": "4:25:38", "throughput": 1318.12, "total_tokens": 1731056} {"current_steps": 3050, "total_steps": 40000, "loss": 0.0, "lr": 4.928660797253027e-05, "epoch": 53.51327433628319, "percentage": 7.62, "elapsed_time": "0:21:55", "remaining_time": "4:25:34", "throughput": 1318.52, "total_tokens": 1734304} {"current_steps": 3055, "total_steps": 40000, "loss": 0.0, "lr": 4.928427753434467e-05, "epoch": 53.60176991150443, "percentage": 7.64, "elapsed_time": "0:21:57", "remaining_time": "4:25:31", "throughput": 1318.64, "total_tokens": 1737168} {"current_steps": 3060, "total_steps": 40000, "loss": 0.0, "lr": 4.9281943351218286e-05, "epoch": 53.690265486725664, "percentage": 7.65, "elapsed_time": "0:21:59", "remaining_time": "4:25:28", "throughput": 1318.75, "total_tokens": 1740048} {"current_steps": 3065, "total_steps": 40000, "loss": 0.0, "lr": 4.9279605423511095e-05, "epoch": 53.7787610619469, "percentage": 7.66, "elapsed_time": "0:22:01", "remaining_time": "4:25:25", "throughput": 1318.88, "total_tokens": 1742960} {"current_steps": 3070, "total_steps": 40000, "loss": 0.0, "lr": 4.927726375158363e-05, "epoch": 53.86725663716814, "percentage": 7.67, "elapsed_time": "0:22:03", "remaining_time": "4:25:21", "throughput": 1318.66, "total_tokens": 1745376} {"current_steps": 3075, "total_steps": 40000, "loss": 0.0, "lr": 4.9274918335797004e-05, "epoch": 53.95575221238938, "percentage": 7.69, "elapsed_time": "0:22:05", "remaining_time": "4:25:18", "throughput": 1318.72, "total_tokens": 1748160} {"current_steps": 3080, "total_steps": 40000, "loss": 0.0, "lr": 4.927256917651292e-05, "epoch": 54.0353982300885, "percentage": 7.7, "elapsed_time": "0:22:07", "remaining_time": "4:25:17", "throughput": 1318.24, "total_tokens": 1750480} {"current_steps": 3085, "total_steps": 40000, "loss": 0.0, "lr": 4.927021627409364e-05, "epoch": 54.123893805309734, "percentage": 7.71, "elapsed_time": "0:22:09", "remaining_time": "4:25:14", "throughput": 1318.46, "total_tokens": 1753504} {"current_steps": 3090, "total_steps": 40000, "loss": 0.0, "lr": 4.9267859628902005e-05, "epoch": 54.21238938053097, "percentage": 7.72, "elapsed_time": "0:22:12", "remaining_time": "4:25:10", "throughput": 1318.39, "total_tokens": 1756128} {"current_steps": 3095, "total_steps": 40000, "loss": 0.0, "lr": 4.9265499241301454e-05, "epoch": 54.30088495575221, "percentage": 7.74, "elapsed_time": "0:22:14", "remaining_time": "4:25:07", "throughput": 1318.36, "total_tokens": 1758800} {"current_steps": 3100, "total_steps": 40000, "loss": 0.0, "lr": 4.926313511165598e-05, "epoch": 54.389380530973455, "percentage": 7.75, "elapsed_time": "0:22:16", "remaining_time": "4:25:04", "throughput": 1318.63, "total_tokens": 1761888} {"current_steps": 3105, "total_steps": 40000, "loss": 0.0, "lr": 4.926076724033016e-05, "epoch": 54.47787610619469, "percentage": 7.76, "elapsed_time": "0:22:18", "remaining_time": "4:25:01", "throughput": 1319.08, "total_tokens": 1765200} {"current_steps": 3110, "total_steps": 40000, "loss": 0.0, "lr": 4.9258395627689146e-05, "epoch": 54.56637168141593, "percentage": 7.78, "elapsed_time": "0:22:20", "remaining_time": "4:24:58", "throughput": 1318.91, "total_tokens": 1767712} {"current_steps": 3115, "total_steps": 40000, "loss": 0.0, "lr": 4.925602027409868e-05, "epoch": 54.65486725663717, "percentage": 7.79, "elapsed_time": "0:22:22", "remaining_time": "4:24:54", "throughput": 1318.52, "total_tokens": 1769920} {"current_steps": 3120, "total_steps": 40000, "loss": 0.0, "lr": 4.925364117992507e-05, "epoch": 54.743362831858406, "percentage": 7.8, "elapsed_time": "0:22:24", "remaining_time": "4:24:51", "throughput": 1319.03, "total_tokens": 1773312} {"current_steps": 3125, "total_steps": 40000, "loss": 0.0, "lr": 4.92512583455352e-05, "epoch": 54.83185840707964, "percentage": 7.81, "elapsed_time": "0:22:26", "remaining_time": "4:24:48", "throughput": 1319.1, "total_tokens": 1776128} {"current_steps": 3130, "total_steps": 40000, "loss": 0.0, "lr": 4.9248871771296536e-05, "epoch": 54.92035398230089, "percentage": 7.83, "elapsed_time": "0:22:28", "remaining_time": "4:24:45", "throughput": 1319.28, "total_tokens": 1779088} {"current_steps": 3135, "total_steps": 40000, "loss": 0.0, "lr": 4.924648145757711e-05, "epoch": 55.0, "percentage": 7.84, "elapsed_time": "0:22:30", "remaining_time": "4:24:41", "throughput": 1319.43, "total_tokens": 1781944} {"current_steps": 3140, "total_steps": 40000, "loss": 0.0, "lr": 4.924408740474554e-05, "epoch": 55.08849557522124, "percentage": 7.85, "elapsed_time": "0:22:32", "remaining_time": "4:24:40", "throughput": 1319.13, "total_tokens": 1784568} {"current_steps": 3145, "total_steps": 40000, "loss": 0.0, "lr": 4.924168961317103e-05, "epoch": 55.176991150442475, "percentage": 7.86, "elapsed_time": "0:22:34", "remaining_time": "4:24:37", "throughput": 1319.33, "total_tokens": 1787560} {"current_steps": 3150, "total_steps": 40000, "loss": 0.0, "lr": 4.9239288083223334e-05, "epoch": 55.26548672566372, "percentage": 7.88, "elapsed_time": "0:22:36", "remaining_time": "4:24:34", "throughput": 1319.73, "total_tokens": 1790824} {"current_steps": 3155, "total_steps": 40000, "loss": 0.0, "lr": 4.9236882815272803e-05, "epoch": 55.35398230088496, "percentage": 7.89, "elapsed_time": "0:22:39", "remaining_time": "4:24:31", "throughput": 1319.46, "total_tokens": 1793176} {"current_steps": 3160, "total_steps": 40000, "loss": 0.0, "lr": 4.9234473809690365e-05, "epoch": 55.442477876106196, "percentage": 7.9, "elapsed_time": "0:22:41", "remaining_time": "4:24:27", "throughput": 1319.53, "total_tokens": 1796008} {"current_steps": 3165, "total_steps": 40000, "loss": 0.0, "lr": 4.923206106684752e-05, "epoch": 55.530973451327434, "percentage": 7.91, "elapsed_time": "0:22:43", "remaining_time": "4:24:24", "throughput": 1319.8, "total_tokens": 1799096} {"current_steps": 3170, "total_steps": 40000, "loss": 0.0, "lr": 4.922964458711634e-05, "epoch": 55.61946902654867, "percentage": 7.92, "elapsed_time": "0:22:45", "remaining_time": "4:24:21", "throughput": 1320.0, "total_tokens": 1802104} {"current_steps": 3175, "total_steps": 40000, "loss": 0.0, "lr": 4.9227224370869474e-05, "epoch": 55.70796460176991, "percentage": 7.94, "elapsed_time": "0:22:47", "remaining_time": "4:24:18", "throughput": 1319.99, "total_tokens": 1804808} {"current_steps": 3180, "total_steps": 40000, "loss": 0.0, "lr": 4.9224800418480155e-05, "epoch": 55.796460176991154, "percentage": 7.95, "elapsed_time": "0:22:49", "remaining_time": "4:24:15", "throughput": 1320.12, "total_tokens": 1807704} {"current_steps": 3185, "total_steps": 40000, "loss": 0.0, "lr": 4.9222372730322176e-05, "epoch": 55.88495575221239, "percentage": 7.96, "elapsed_time": "0:22:51", "remaining_time": "4:24:11", "throughput": 1320.13, "total_tokens": 1810440} {"current_steps": 3190, "total_steps": 40000, "loss": 0.0, "lr": 4.921994130676993e-05, "epoch": 55.97345132743363, "percentage": 7.98, "elapsed_time": "0:22:53", "remaining_time": "4:24:08", "throughput": 1320.21, "total_tokens": 1813272} {"current_steps": 3195, "total_steps": 40000, "loss": 0.0, "lr": 4.9217506148198366e-05, "epoch": 56.05309734513274, "percentage": 7.99, "elapsed_time": "0:22:55", "remaining_time": "4:24:07", "throughput": 1319.75, "total_tokens": 1815616} {"current_steps": 3200, "total_steps": 40000, "loss": 0.0, "lr": 4.921506725498302e-05, "epoch": 56.14159292035398, "percentage": 8.0, "elapsed_time": "0:22:57", "remaining_time": "4:24:04", "throughput": 1320.01, "total_tokens": 1818688} {"current_steps": 3200, "total_steps": 40000, "eval_loss": 0.35879766941070557, "epoch": 56.14159292035398, "percentage": 8.0, "elapsed_time": "0:22:58", "remaining_time": "4:24:16", "throughput": 1318.99, "total_tokens": 1818688} {"current_steps": 3205, "total_steps": 40000, "loss": 0.0, "lr": 4.9212624627499994e-05, "epoch": 56.230088495575224, "percentage": 8.01, "elapsed_time": "0:23:02", "remaining_time": "4:24:32", "throughput": 1317.18, "total_tokens": 1821104} {"current_steps": 3210, "total_steps": 40000, "loss": 0.0, "lr": 4.921017826612597e-05, "epoch": 56.31858407079646, "percentage": 8.03, "elapsed_time": "0:23:04", "remaining_time": "4:24:29", "throughput": 1317.41, "total_tokens": 1824144} {"current_steps": 3215, "total_steps": 40000, "loss": 0.0, "lr": 4.9207728171238223e-05, "epoch": 56.4070796460177, "percentage": 8.04, "elapsed_time": "0:23:06", "remaining_time": "4:24:26", "throughput": 1317.9, "total_tokens": 1827536} {"current_steps": 3220, "total_steps": 40000, "loss": 0.0, "lr": 4.920527434321458e-05, "epoch": 56.49557522123894, "percentage": 8.05, "elapsed_time": "0:23:08", "remaining_time": "4:24:22", "throughput": 1318.17, "total_tokens": 1830624} {"current_steps": 3225, "total_steps": 40000, "loss": 0.0, "lr": 4.920281678243345e-05, "epoch": 56.584070796460175, "percentage": 8.06, "elapsed_time": "0:23:10", "remaining_time": "4:24:19", "throughput": 1317.92, "total_tokens": 1832992} {"current_steps": 3230, "total_steps": 40000, "loss": 0.0, "lr": 4.920035548927381e-05, "epoch": 56.67256637168141, "percentage": 8.08, "elapsed_time": "0:23:12", "remaining_time": "4:24:16", "throughput": 1318.09, "total_tokens": 1835936} {"current_steps": 3235, "total_steps": 40000, "loss": 0.0, "lr": 4.919789046411525e-05, "epoch": 56.76106194690266, "percentage": 8.09, "elapsed_time": "0:23:14", "remaining_time": "4:24:13", "throughput": 1318.16, "total_tokens": 1838768} {"current_steps": 3240, "total_steps": 40000, "loss": 0.0, "lr": 4.919542170733787e-05, "epoch": 56.849557522123895, "percentage": 8.1, "elapsed_time": "0:23:17", "remaining_time": "4:24:10", "throughput": 1318.15, "total_tokens": 1841488} {"current_steps": 3245, "total_steps": 40000, "loss": 0.0, "lr": 4.919294921932242e-05, "epoch": 56.93805309734513, "percentage": 8.11, "elapsed_time": "0:23:19", "remaining_time": "4:24:06", "throughput": 1318.5, "total_tokens": 1844688} {"current_steps": 3250, "total_steps": 40000, "loss": 0.0, "lr": 4.919047300045016e-05, "epoch": 57.017699115044245, "percentage": 8.12, "elapsed_time": "0:23:21", "remaining_time": "4:24:05", "throughput": 1318.2, "total_tokens": 1847216} {"current_steps": 3255, "total_steps": 40000, "loss": 0.0, "lr": 4.918799305110299e-05, "epoch": 57.10619469026549, "percentage": 8.14, "elapsed_time": "0:23:23", "remaining_time": "4:24:02", "throughput": 1318.14, "total_tokens": 1849856} {"current_steps": 3260, "total_steps": 40000, "loss": 0.0, "lr": 4.918550937166331e-05, "epoch": 57.19469026548673, "percentage": 8.15, "elapsed_time": "0:23:25", "remaining_time": "4:23:59", "throughput": 1318.14, "total_tokens": 1852576} {"current_steps": 3265, "total_steps": 40000, "loss": 0.0, "lr": 4.918302196251415e-05, "epoch": 57.283185840707965, "percentage": 8.16, "elapsed_time": "0:23:27", "remaining_time": "4:23:56", "throughput": 1318.54, "total_tokens": 1855872} {"current_steps": 3270, "total_steps": 40000, "loss": 0.0, "lr": 4.91805308240391e-05, "epoch": 57.3716814159292, "percentage": 8.18, "elapsed_time": "0:23:29", "remaining_time": "4:23:52", "throughput": 1318.42, "total_tokens": 1858416} {"current_steps": 3275, "total_steps": 40000, "loss": 0.0, "lr": 4.9178035956622326e-05, "epoch": 57.46017699115044, "percentage": 8.19, "elapsed_time": "0:23:31", "remaining_time": "4:23:49", "throughput": 1318.34, "total_tokens": 1861024} {"current_steps": 3280, "total_steps": 40000, "loss": 0.0, "lr": 4.917553736064857e-05, "epoch": 57.54867256637168, "percentage": 8.2, "elapsed_time": "0:23:33", "remaining_time": "4:23:46", "throughput": 1318.25, "total_tokens": 1863616} {"current_steps": 3285, "total_steps": 40000, "loss": 0.0, "lr": 4.917303503650314e-05, "epoch": 57.63716814159292, "percentage": 8.21, "elapsed_time": "0:23:35", "remaining_time": "4:23:43", "throughput": 1318.49, "total_tokens": 1866672} {"current_steps": 3290, "total_steps": 40000, "loss": 0.0, "lr": 4.917052898457194e-05, "epoch": 57.72566371681416, "percentage": 8.22, "elapsed_time": "0:23:37", "remaining_time": "4:23:40", "throughput": 1318.54, "total_tokens": 1869456} {"current_steps": 3295, "total_steps": 40000, "loss": 0.0, "lr": 4.916801920524141e-05, "epoch": 57.8141592920354, "percentage": 8.24, "elapsed_time": "0:23:39", "remaining_time": "4:23:36", "throughput": 1318.44, "total_tokens": 1872032} {"current_steps": 3300, "total_steps": 40000, "loss": 0.0, "lr": 4.916550569889862e-05, "epoch": 57.902654867256636, "percentage": 8.25, "elapsed_time": "0:23:41", "remaining_time": "4:23:33", "throughput": 1318.69, "total_tokens": 1875104} {"current_steps": 3305, "total_steps": 40000, "loss": 0.0, "lr": 4.916298846593116e-05, "epoch": 57.991150442477874, "percentage": 8.26, "elapsed_time": "0:23:43", "remaining_time": "4:23:30", "throughput": 1319.3, "total_tokens": 1878672} {"current_steps": 3310, "total_steps": 40000, "loss": 0.0, "lr": 4.916046750672722e-05, "epoch": 58.07079646017699, "percentage": 8.28, "elapsed_time": "0:23:46", "remaining_time": "4:23:29", "throughput": 1318.85, "total_tokens": 1881032} {"current_steps": 3315, "total_steps": 40000, "loss": 0.0, "lr": 4.915794282167559e-05, "epoch": 58.15929203539823, "percentage": 8.29, "elapsed_time": "0:23:48", "remaining_time": "4:23:26", "throughput": 1318.65, "total_tokens": 1883480} {"current_steps": 3320, "total_steps": 40000, "loss": 0.0, "lr": 4.915541441116558e-05, "epoch": 58.24778761061947, "percentage": 8.3, "elapsed_time": "0:23:50", "remaining_time": "4:23:23", "throughput": 1318.96, "total_tokens": 1886648} {"current_steps": 3325, "total_steps": 40000, "loss": 0.0, "lr": 4.915288227558711e-05, "epoch": 58.336283185840706, "percentage": 8.31, "elapsed_time": "0:23:52", "remaining_time": "4:23:20", "throughput": 1319.56, "total_tokens": 1890216} {"current_steps": 3330, "total_steps": 40000, "loss": 0.0, "lr": 4.915034641533066e-05, "epoch": 58.424778761061944, "percentage": 8.33, "elapsed_time": "0:23:54", "remaining_time": "4:23:16", "throughput": 1319.53, "total_tokens": 1892888} {"current_steps": 3335, "total_steps": 40000, "loss": 0.0, "lr": 4.914780683078731e-05, "epoch": 58.51327433628319, "percentage": 8.34, "elapsed_time": "0:23:56", "remaining_time": "4:23:13", "throughput": 1319.76, "total_tokens": 1895944} {"current_steps": 3340, "total_steps": 40000, "loss": 0.0, "lr": 4.9145263522348695e-05, "epoch": 58.60176991150443, "percentage": 8.35, "elapsed_time": "0:23:58", "remaining_time": "4:23:10", "throughput": 1319.88, "total_tokens": 1898840} {"current_steps": 3345, "total_steps": 40000, "loss": 0.0, "lr": 4.9142716490407e-05, "epoch": 58.690265486725664, "percentage": 8.36, "elapsed_time": "0:24:00", "remaining_time": "4:23:07", "throughput": 1319.87, "total_tokens": 1901560} {"current_steps": 3350, "total_steps": 40000, "loss": 0.0, "lr": 4.914016573535504e-05, "epoch": 58.7787610619469, "percentage": 8.38, "elapsed_time": "0:24:02", "remaining_time": "4:23:04", "throughput": 1319.84, "total_tokens": 1904248} {"current_steps": 3355, "total_steps": 40000, "loss": 0.0, "lr": 4.9137611257586154e-05, "epoch": 58.86725663716814, "percentage": 8.39, "elapsed_time": "0:24:04", "remaining_time": "4:23:01", "throughput": 1319.8, "total_tokens": 1906904} {"current_steps": 3360, "total_steps": 40000, "loss": 0.0, "lr": 4.9135053057494274e-05, "epoch": 58.95575221238938, "percentage": 8.4, "elapsed_time": "0:24:06", "remaining_time": "4:22:57", "throughput": 1319.93, "total_tokens": 1909800} {"current_steps": 3365, "total_steps": 40000, "loss": 0.0, "lr": 4.913249113547392e-05, "epoch": 59.0353982300885, "percentage": 8.41, "elapsed_time": "0:24:09", "remaining_time": "4:22:56", "throughput": 1319.53, "total_tokens": 1912184} {"current_steps": 3370, "total_steps": 40000, "loss": 0.0, "lr": 4.912992549192016e-05, "epoch": 59.123893805309734, "percentage": 8.43, "elapsed_time": "0:24:11", "remaining_time": "4:22:53", "throughput": 1319.25, "total_tokens": 1914504} {"current_steps": 3375, "total_steps": 40000, "loss": 0.0, "lr": 4.9127356127228665e-05, "epoch": 59.21238938053097, "percentage": 8.44, "elapsed_time": "0:24:13", "remaining_time": "4:22:50", "throughput": 1319.23, "total_tokens": 1917192} {"current_steps": 3380, "total_steps": 40000, "loss": 0.0, "lr": 4.912478304179564e-05, "epoch": 59.30088495575221, "percentage": 8.45, "elapsed_time": "0:24:15", "remaining_time": "4:22:47", "throughput": 1319.32, "total_tokens": 1920056} {"current_steps": 3385, "total_steps": 40000, "loss": 0.0, "lr": 4.9122206236017896e-05, "epoch": 59.389380530973455, "percentage": 8.46, "elapsed_time": "0:24:17", "remaining_time": "4:22:44", "throughput": 1319.51, "total_tokens": 1923048} {"current_steps": 3390, "total_steps": 40000, "loss": 0.0, "lr": 4.911962571029282e-05, "epoch": 59.47787610619469, "percentage": 8.48, "elapsed_time": "0:24:19", "remaining_time": "4:22:41", "throughput": 1319.9, "total_tokens": 1926328} {"current_steps": 3395, "total_steps": 40000, "loss": 0.0, "lr": 4.9117041465018353e-05, "epoch": 59.56637168141593, "percentage": 8.49, "elapsed_time": "0:24:21", "remaining_time": "4:22:38", "throughput": 1320.3, "total_tokens": 1929640} {"current_steps": 3400, "total_steps": 40000, "loss": 0.0, "lr": 4.911445350059302e-05, "epoch": 59.65486725663717, "percentage": 8.5, "elapsed_time": "0:24:23", "remaining_time": "4:22:34", "throughput": 1320.23, "total_tokens": 1932248} {"current_steps": 3400, "total_steps": 40000, "eval_loss": 0.3547935485839844, "epoch": 59.65486725663717, "percentage": 8.5, "elapsed_time": "0:24:24", "remaining_time": "4:22:46", "throughput": 1319.27, "total_tokens": 1932248} {"current_steps": 3405, "total_steps": 40000, "loss": 0.0, "lr": 4.9111861817415905e-05, "epoch": 59.743362831858406, "percentage": 8.51, "elapsed_time": "0:24:28", "remaining_time": "4:23:00", "throughput": 1317.95, "total_tokens": 1935208} {"current_steps": 3410, "total_steps": 40000, "loss": 0.0, "lr": 4.91092664158867e-05, "epoch": 59.83185840707964, "percentage": 8.53, "elapsed_time": "0:24:30", "remaining_time": "4:22:57", "throughput": 1318.14, "total_tokens": 1938216} {"current_steps": 3415, "total_steps": 40000, "loss": 0.0, "lr": 4.910666729640563e-05, "epoch": 59.92035398230089, "percentage": 8.54, "elapsed_time": "0:24:32", "remaining_time": "4:22:54", "throughput": 1318.18, "total_tokens": 1941000} {"current_steps": 3420, "total_steps": 40000, "loss": 0.0, "lr": 4.910406445937353e-05, "epoch": 60.0, "percentage": 8.55, "elapsed_time": "0:24:34", "remaining_time": "4:22:50", "throughput": 1318.12, "total_tokens": 1943544} {"current_steps": 3425, "total_steps": 40000, "loss": 0.0, "lr": 4.9101457905191774e-05, "epoch": 60.08849557522124, "percentage": 8.56, "elapsed_time": "0:24:36", "remaining_time": "4:22:50", "throughput": 1317.83, "total_tokens": 1946152} {"current_steps": 3430, "total_steps": 40000, "loss": 0.0, "lr": 4.909884763426233e-05, "epoch": 60.176991150442475, "percentage": 8.58, "elapsed_time": "0:24:38", "remaining_time": "4:22:47", "throughput": 1318.08, "total_tokens": 1949240} {"current_steps": 3435, "total_steps": 40000, "loss": 0.0, "lr": 4.9096233646987736e-05, "epoch": 60.26548672566372, "percentage": 8.59, "elapsed_time": "0:24:40", "remaining_time": "4:22:44", "throughput": 1318.27, "total_tokens": 1952248} {"current_steps": 3440, "total_steps": 40000, "loss": 0.0, "lr": 4.9093615943771104e-05, "epoch": 60.35398230088496, "percentage": 8.6, "elapsed_time": "0:24:42", "remaining_time": "4:22:41", "throughput": 1318.32, "total_tokens": 1955064} {"current_steps": 3445, "total_steps": 40000, "loss": 0.0, "lr": 4.909099452501611e-05, "epoch": 60.442477876106196, "percentage": 8.61, "elapsed_time": "0:24:45", "remaining_time": "4:22:38", "throughput": 1318.39, "total_tokens": 1957896} {"current_steps": 3450, "total_steps": 40000, "loss": 0.0, "lr": 4.908836939112702e-05, "epoch": 60.530973451327434, "percentage": 8.62, "elapsed_time": "0:24:47", "remaining_time": "4:22:34", "throughput": 1318.4, "total_tokens": 1960632} {"current_steps": 3455, "total_steps": 40000, "loss": 0.0, "lr": 4.908574054250865e-05, "epoch": 60.61946902654867, "percentage": 8.64, "elapsed_time": "0:24:49", "remaining_time": "4:22:31", "throughput": 1318.44, "total_tokens": 1963416} {"current_steps": 3460, "total_steps": 40000, "loss": 0.0, "lr": 4.9083107979566414e-05, "epoch": 60.70796460176991, "percentage": 8.65, "elapsed_time": "0:24:51", "remaining_time": "4:22:28", "throughput": 1318.61, "total_tokens": 1966376} {"current_steps": 3465, "total_steps": 40000, "loss": 0.0, "lr": 4.908047170270628e-05, "epoch": 60.796460176991154, "percentage": 8.66, "elapsed_time": "0:24:53", "remaining_time": "4:22:25", "throughput": 1318.73, "total_tokens": 1969272} {"current_steps": 3470, "total_steps": 40000, "loss": 0.0, "lr": 4.9077831712334784e-05, "epoch": 60.88495575221239, "percentage": 8.67, "elapsed_time": "0:24:55", "remaining_time": "4:22:22", "throughput": 1318.85, "total_tokens": 1972168} {"current_steps": 3475, "total_steps": 40000, "loss": 0.0, "lr": 4.907518800885907e-05, "epoch": 60.97345132743363, "percentage": 8.69, "elapsed_time": "0:24:57", "remaining_time": "4:22:18", "throughput": 1319.23, "total_tokens": 1975432} {"current_steps": 3480, "total_steps": 40000, "loss": 0.0, "lr": 4.907254059268681e-05, "epoch": 61.05309734513274, "percentage": 8.7, "elapsed_time": "0:24:59", "remaining_time": "4:22:17", "throughput": 1319.03, "total_tokens": 1978104} {"current_steps": 3485, "total_steps": 40000, "loss": 0.0, "lr": 4.906988946422628e-05, "epoch": 61.14159292035398, "percentage": 8.71, "elapsed_time": "0:25:01", "remaining_time": "4:22:14", "throughput": 1319.06, "total_tokens": 1980872} {"current_steps": 3490, "total_steps": 40000, "loss": 0.0, "lr": 4.9067234623886315e-05, "epoch": 61.230088495575224, "percentage": 8.72, "elapsed_time": "0:25:03", "remaining_time": "4:22:11", "throughput": 1319.24, "total_tokens": 1983864} {"current_steps": 3495, "total_steps": 40000, "loss": 0.0, "lr": 4.9064576072076316e-05, "epoch": 61.31858407079646, "percentage": 8.74, "elapsed_time": "0:25:05", "remaining_time": "4:22:08", "throughput": 1319.14, "total_tokens": 1986440} {"current_steps": 3500, "total_steps": 40000, "loss": 0.0, "lr": 4.906191380920628e-05, "epoch": 61.4070796460177, "percentage": 8.75, "elapsed_time": "0:25:07", "remaining_time": "4:22:05", "throughput": 1319.26, "total_tokens": 1989336} {"current_steps": 3505, "total_steps": 40000, "loss": 0.0, "lr": 4.905924783568675e-05, "epoch": 61.49557522123894, "percentage": 8.76, "elapsed_time": "0:25:09", "remaining_time": "4:22:02", "throughput": 1318.97, "total_tokens": 1991624} {"current_steps": 3510, "total_steps": 40000, "loss": 0.0, "lr": 4.905657815192886e-05, "epoch": 61.584070796460175, "percentage": 8.77, "elapsed_time": "0:25:12", "remaining_time": "4:21:59", "throughput": 1319.02, "total_tokens": 1994440} {"current_steps": 3515, "total_steps": 40000, "loss": 0.0, "lr": 4.90539047583443e-05, "epoch": 61.67256637168141, "percentage": 8.79, "elapsed_time": "0:25:14", "remaining_time": "4:21:56", "throughput": 1319.39, "total_tokens": 1997704} {"current_steps": 3520, "total_steps": 40000, "loss": 0.0, "lr": 4.905122765534534e-05, "epoch": 61.76106194690266, "percentage": 8.8, "elapsed_time": "0:25:16", "remaining_time": "4:21:53", "throughput": 1319.31, "total_tokens": 2000312} {"current_steps": 3525, "total_steps": 40000, "loss": 0.0, "lr": 4.9048546843344846e-05, "epoch": 61.849557522123895, "percentage": 8.81, "elapsed_time": "0:25:18", "remaining_time": "4:21:50", "throughput": 1319.35, "total_tokens": 2003096} {"current_steps": 3530, "total_steps": 40000, "loss": 0.0, "lr": 4.9045862322756206e-05, "epoch": 61.93805309734513, "percentage": 8.82, "elapsed_time": "0:25:20", "remaining_time": "4:21:46", "throughput": 1319.51, "total_tokens": 2006040} {"current_steps": 3535, "total_steps": 40000, "loss": 0.0, "lr": 4.904317409399342e-05, "epoch": 62.017699115044245, "percentage": 8.84, "elapsed_time": "0:25:22", "remaining_time": "4:21:45", "throughput": 1319.32, "total_tokens": 2008712} {"current_steps": 3540, "total_steps": 40000, "loss": 0.0, "lr": 4.904048215747104e-05, "epoch": 62.10619469026549, "percentage": 8.85, "elapsed_time": "0:25:24", "remaining_time": "4:21:42", "throughput": 1319.48, "total_tokens": 2011672} {"current_steps": 3545, "total_steps": 40000, "loss": 0.0, "lr": 4.90377865136042e-05, "epoch": 62.19469026548673, "percentage": 8.86, "elapsed_time": "0:25:26", "remaining_time": "4:21:39", "throughput": 1319.75, "total_tokens": 2014808} {"current_steps": 3550, "total_steps": 40000, "loss": 0.0, "lr": 4.90350871628086e-05, "epoch": 62.283185840707965, "percentage": 8.88, "elapsed_time": "0:25:28", "remaining_time": "4:21:36", "throughput": 1320.07, "total_tokens": 2018024} {"current_steps": 3555, "total_steps": 40000, "loss": 0.0, "lr": 4.903238410550052e-05, "epoch": 62.3716814159292, "percentage": 8.89, "elapsed_time": "0:25:30", "remaining_time": "4:21:33", "throughput": 1319.81, "total_tokens": 2020360} {"current_steps": 3560, "total_steps": 40000, "loss": 0.0, "lr": 4.90296773420968e-05, "epoch": 62.46017699115044, "percentage": 8.9, "elapsed_time": "0:25:32", "remaining_time": "4:21:30", "throughput": 1319.79, "total_tokens": 2023064} {"current_steps": 3565, "total_steps": 40000, "loss": 0.0, "lr": 4.902696687301486e-05, "epoch": 62.54867256637168, "percentage": 8.91, "elapsed_time": "0:25:34", "remaining_time": "4:21:27", "throughput": 1319.96, "total_tokens": 2026040} {"current_steps": 3570, "total_steps": 40000, "loss": 0.0, "lr": 4.902425269867268e-05, "epoch": 62.63716814159292, "percentage": 8.92, "elapsed_time": "0:25:36", "remaining_time": "4:21:24", "throughput": 1319.91, "total_tokens": 2028696} {"current_steps": 3575, "total_steps": 40000, "loss": 0.0, "lr": 4.902153481948883e-05, "epoch": 62.72566371681416, "percentage": 8.94, "elapsed_time": "0:25:39", "remaining_time": "4:21:21", "throughput": 1320.11, "total_tokens": 2031720} {"current_steps": 3580, "total_steps": 40000, "loss": 0.0, "lr": 4.901881323588244e-05, "epoch": 62.8141592920354, "percentage": 8.95, "elapsed_time": "0:25:41", "remaining_time": "4:21:18", "throughput": 1320.32, "total_tokens": 2034760} {"current_steps": 3585, "total_steps": 40000, "loss": 0.0, "lr": 4.90160879482732e-05, "epoch": 62.902654867256636, "percentage": 8.96, "elapsed_time": "0:25:43", "remaining_time": "4:21:14", "throughput": 1320.48, "total_tokens": 2037736} {"current_steps": 3590, "total_steps": 40000, "loss": 0.0, "lr": 4.9013358957081405e-05, "epoch": 62.991150442477874, "percentage": 8.97, "elapsed_time": "0:25:45", "remaining_time": "4:21:11", "throughput": 1320.2, "total_tokens": 2040008} {"current_steps": 3595, "total_steps": 40000, "loss": 0.0, "lr": 4.901062626272789e-05, "epoch": 63.07079646017699, "percentage": 8.99, "elapsed_time": "0:25:47", "remaining_time": "4:21:10", "throughput": 1319.84, "total_tokens": 2042440} {"current_steps": 3600, "total_steps": 40000, "loss": 0.0, "lr": 4.900788986563406e-05, "epoch": 63.15929203539823, "percentage": 9.0, "elapsed_time": "0:25:49", "remaining_time": "4:21:07", "throughput": 1320.04, "total_tokens": 2045464} {"current_steps": 3600, "total_steps": 40000, "eval_loss": 0.36013948917388916, "epoch": 63.15929203539823, "percentage": 9.0, "elapsed_time": "0:25:50", "remaining_time": "4:21:18", "throughput": 1319.14, "total_tokens": 2045464} {"current_steps": 3605, "total_steps": 40000, "loss": 0.0, "lr": 4.9005149766221915e-05, "epoch": 63.24778761061947, "percentage": 9.01, "elapsed_time": "0:25:54", "remaining_time": "4:21:32", "throughput": 1317.72, "total_tokens": 2048200} {"current_steps": 3610, "total_steps": 40000, "loss": 0.0, "lr": 4.9002405964914e-05, "epoch": 63.336283185840706, "percentage": 9.03, "elapsed_time": "0:25:56", "remaining_time": "4:21:29", "throughput": 1317.82, "total_tokens": 2051080} {"current_steps": 3615, "total_steps": 40000, "loss": 0.0, "lr": 4.899965846213346e-05, "epoch": 63.424778761061944, "percentage": 9.04, "elapsed_time": "0:25:58", "remaining_time": "4:21:26", "throughput": 1317.98, "total_tokens": 2054040} {"current_steps": 3620, "total_steps": 40000, "loss": 0.0, "lr": 4.899690725830399e-05, "epoch": 63.51327433628319, "percentage": 9.05, "elapsed_time": "0:26:00", "remaining_time": "4:21:23", "throughput": 1318.11, "total_tokens": 2056968} {"current_steps": 3625, "total_steps": 40000, "loss": 0.0, "lr": 4.899415235384985e-05, "epoch": 63.60176991150443, "percentage": 9.06, "elapsed_time": "0:26:02", "remaining_time": "4:21:19", "throughput": 1318.12, "total_tokens": 2059704} {"current_steps": 3630, "total_steps": 40000, "loss": 0.0, "lr": 4.899139374919589e-05, "epoch": 63.690265486725664, "percentage": 9.07, "elapsed_time": "0:26:04", "remaining_time": "4:21:16", "throughput": 1318.18, "total_tokens": 2062520} {"current_steps": 3635, "total_steps": 40000, "loss": 0.0, "lr": 4.898863144476752e-05, "epoch": 63.7787610619469, "percentage": 9.09, "elapsed_time": "0:26:06", "remaining_time": "4:21:13", "throughput": 1318.47, "total_tokens": 2065688} {"current_steps": 3640, "total_steps": 40000, "loss": 0.0, "lr": 4.898586544099072e-05, "epoch": 63.86725663716814, "percentage": 9.1, "elapsed_time": "0:26:08", "remaining_time": "4:21:10", "throughput": 1318.51, "total_tokens": 2068472} {"current_steps": 3645, "total_steps": 40000, "loss": 0.0, "lr": 4.898309573829204e-05, "epoch": 63.95575221238938, "percentage": 9.11, "elapsed_time": "0:26:10", "remaining_time": "4:21:07", "throughput": 1318.52, "total_tokens": 2071192} {"current_steps": 3650, "total_steps": 40000, "loss": 0.0, "lr": 4.898032233709862e-05, "epoch": 64.03539823008849, "percentage": 9.12, "elapsed_time": "0:26:13", "remaining_time": "4:21:06", "throughput": 1318.05, "total_tokens": 2073424} {"current_steps": 3655, "total_steps": 40000, "loss": 0.0, "lr": 4.8977545237838123e-05, "epoch": 64.12389380530973, "percentage": 9.14, "elapsed_time": "0:26:15", "remaining_time": "4:21:03", "throughput": 1318.18, "total_tokens": 2076352} {"current_steps": 3660, "total_steps": 40000, "loss": 0.0, "lr": 4.8974764440938836e-05, "epoch": 64.21238938053098, "percentage": 9.15, "elapsed_time": "0:26:17", "remaining_time": "4:21:00", "throughput": 1318.06, "total_tokens": 2078912} {"current_steps": 3665, "total_steps": 40000, "loss": 0.0, "lr": 4.897197994682959e-05, "epoch": 64.30088495575221, "percentage": 9.16, "elapsed_time": "0:26:19", "remaining_time": "4:20:57", "throughput": 1318.24, "total_tokens": 2081904} {"current_steps": 3670, "total_steps": 40000, "loss": 0.0, "lr": 4.8969191755939786e-05, "epoch": 64.38938053097345, "percentage": 9.18, "elapsed_time": "0:26:21", "remaining_time": "4:20:54", "throughput": 1318.33, "total_tokens": 2084768} {"current_steps": 3675, "total_steps": 40000, "loss": 0.0, "lr": 4.8966399868699396e-05, "epoch": 64.47787610619469, "percentage": 9.19, "elapsed_time": "0:26:23", "remaining_time": "4:20:51", "throughput": 1318.53, "total_tokens": 2087792} {"current_steps": 3680, "total_steps": 40000, "loss": 0.0, "lr": 4.8963604285538965e-05, "epoch": 64.56637168141593, "percentage": 9.2, "elapsed_time": "0:26:25", "remaining_time": "4:20:48", "throughput": 1318.41, "total_tokens": 2090336} {"current_steps": 3685, "total_steps": 40000, "loss": 0.0, "lr": 4.8960805006889604e-05, "epoch": 64.65486725663717, "percentage": 9.21, "elapsed_time": "0:26:27", "remaining_time": "4:20:45", "throughput": 1318.55, "total_tokens": 2093264} {"current_steps": 3690, "total_steps": 40000, "loss": 0.0, "lr": 4.8958002033183004e-05, "epoch": 64.7433628318584, "percentage": 9.22, "elapsed_time": "0:26:29", "remaining_time": "4:20:42", "throughput": 1318.46, "total_tokens": 2095856} {"current_steps": 3695, "total_steps": 40000, "loss": 0.0, "lr": 4.8955195364851414e-05, "epoch": 64.83185840707965, "percentage": 9.24, "elapsed_time": "0:26:31", "remaining_time": "4:20:39", "throughput": 1319.06, "total_tokens": 2099568} {"current_steps": 3700, "total_steps": 40000, "loss": 0.0, "lr": 4.895238500232766e-05, "epoch": 64.92035398230088, "percentage": 9.25, "elapsed_time": "0:26:33", "remaining_time": "4:20:36", "throughput": 1319.32, "total_tokens": 2102688} {"current_steps": 3705, "total_steps": 40000, "loss": 0.0, "lr": 4.8949570946045143e-05, "epoch": 65.0, "percentage": 9.26, "elapsed_time": "0:26:35", "remaining_time": "4:20:32", "throughput": 1319.09, "total_tokens": 2104960} {"current_steps": 3710, "total_steps": 40000, "loss": 0.0, "lr": 4.89467531964378e-05, "epoch": 65.08849557522124, "percentage": 9.28, "elapsed_time": "0:26:38", "remaining_time": "4:20:31", "throughput": 1318.89, "total_tokens": 2107680} {"current_steps": 3715, "total_steps": 40000, "loss": 0.0, "lr": 4.894393175394019e-05, "epoch": 65.17699115044248, "percentage": 9.29, "elapsed_time": "0:26:40", "remaining_time": "4:20:28", "throughput": 1318.89, "total_tokens": 2110384} {"current_steps": 3720, "total_steps": 40000, "loss": 0.0, "lr": 4.8941106618987406e-05, "epoch": 65.26548672566372, "percentage": 9.3, "elapsed_time": "0:26:42", "remaining_time": "4:20:25", "throughput": 1318.94, "total_tokens": 2113184} {"current_steps": 3725, "total_steps": 40000, "loss": 0.0, "lr": 4.893827779201512e-05, "epoch": 65.35398230088495, "percentage": 9.31, "elapsed_time": "0:26:44", "remaining_time": "4:20:22", "throughput": 1319.03, "total_tokens": 2116048} {"current_steps": 3730, "total_steps": 40000, "loss": 0.0, "lr": 4.893544527345957e-05, "epoch": 65.4424778761062, "percentage": 9.32, "elapsed_time": "0:26:46", "remaining_time": "4:20:19", "throughput": 1319.38, "total_tokens": 2119344} {"current_steps": 3735, "total_steps": 40000, "loss": 0.0, "lr": 4.8932609063757563e-05, "epoch": 65.53097345132744, "percentage": 9.34, "elapsed_time": "0:26:48", "remaining_time": "4:20:16", "throughput": 1319.49, "total_tokens": 2122240} {"current_steps": 3740, "total_steps": 40000, "loss": 0.0, "lr": 4.8929769163346484e-05, "epoch": 65.61946902654867, "percentage": 9.35, "elapsed_time": "0:26:50", "remaining_time": "4:20:13", "throughput": 1319.45, "total_tokens": 2124912} {"current_steps": 3745, "total_steps": 40000, "loss": 0.0, "lr": 4.892692557266429e-05, "epoch": 65.70796460176992, "percentage": 9.36, "elapsed_time": "0:26:52", "remaining_time": "4:20:10", "throughput": 1319.81, "total_tokens": 2128208} {"current_steps": 3750, "total_steps": 40000, "loss": 0.0, "lr": 4.8924078292149464e-05, "epoch": 65.79646017699115, "percentage": 9.38, "elapsed_time": "0:26:54", "remaining_time": "4:20:07", "throughput": 1319.76, "total_tokens": 2130848} {"current_steps": 3755, "total_steps": 40000, "loss": 0.0, "lr": 4.892122732224114e-05, "epoch": 65.88495575221239, "percentage": 9.39, "elapsed_time": "0:26:56", "remaining_time": "4:20:04", "throughput": 1319.86, "total_tokens": 2133728} {"current_steps": 3760, "total_steps": 40000, "loss": 0.0, "lr": 4.8918372663378944e-05, "epoch": 65.97345132743362, "percentage": 9.4, "elapsed_time": "0:26:58", "remaining_time": "4:20:01", "throughput": 1319.98, "total_tokens": 2136624} {"current_steps": 3765, "total_steps": 40000, "loss": 0.0, "lr": 4.89155143160031e-05, "epoch": 66.05309734513274, "percentage": 9.41, "elapsed_time": "0:27:00", "remaining_time": "4:20:00", "throughput": 1319.6, "total_tokens": 2139000} {"current_steps": 3770, "total_steps": 40000, "loss": 0.0, "lr": 4.891265228055441e-05, "epoch": 66.14159292035399, "percentage": 9.43, "elapsed_time": "0:27:03", "remaining_time": "4:19:57", "throughput": 1319.96, "total_tokens": 2142296} {"current_steps": 3775, "total_steps": 40000, "loss": 0.0, "lr": 4.890978655747424e-05, "epoch": 66.23008849557522, "percentage": 9.44, "elapsed_time": "0:27:05", "remaining_time": "4:19:54", "throughput": 1320.22, "total_tokens": 2145432} {"current_steps": 3780, "total_steps": 40000, "loss": 0.0, "lr": 4.89069171472045e-05, "epoch": 66.31858407079646, "percentage": 9.45, "elapsed_time": "0:27:07", "remaining_time": "4:19:51", "throughput": 1320.1, "total_tokens": 2147960} {"current_steps": 3785, "total_steps": 40000, "loss": 0.0, "lr": 4.890404405018772e-05, "epoch": 66.40707964601769, "percentage": 9.46, "elapsed_time": "0:27:09", "remaining_time": "4:19:48", "throughput": 1320.36, "total_tokens": 2151112} {"current_steps": 3790, "total_steps": 40000, "loss": 0.0, "lr": 4.8901167266866934e-05, "epoch": 66.49557522123894, "percentage": 9.47, "elapsed_time": "0:27:11", "remaining_time": "4:19:45", "throughput": 1320.12, "total_tokens": 2153448} {"current_steps": 3795, "total_steps": 40000, "loss": 0.0, "lr": 4.88982867976858e-05, "epoch": 66.58407079646018, "percentage": 9.49, "elapsed_time": "0:27:13", "remaining_time": "4:19:42", "throughput": 1320.19, "total_tokens": 2156280} {"current_steps": 3800, "total_steps": 40000, "loss": 0.0, "lr": 4.889540264308852e-05, "epoch": 66.67256637168141, "percentage": 9.5, "elapsed_time": "0:27:15", "remaining_time": "4:19:39", "throughput": 1320.26, "total_tokens": 2159128} {"current_steps": 3800, "total_steps": 40000, "eval_loss": 0.36583343148231506, "epoch": 66.67256637168141, "percentage": 9.5, "elapsed_time": "0:27:16", "remaining_time": "4:19:49", "throughput": 1319.4, "total_tokens": 2159128} {"current_steps": 3805, "total_steps": 40000, "loss": 0.0, "lr": 4.889251480351986e-05, "epoch": 66.76106194690266, "percentage": 9.51, "elapsed_time": "0:27:20", "remaining_time": "4:20:01", "throughput": 1318.39, "total_tokens": 2162344} {"current_steps": 3810, "total_steps": 40000, "loss": 0.0, "lr": 4.888962327942517e-05, "epoch": 66.84955752212389, "percentage": 9.53, "elapsed_time": "0:27:22", "remaining_time": "4:19:58", "throughput": 1318.3, "total_tokens": 2164920} {"current_steps": 3815, "total_steps": 40000, "loss": 0.0, "lr": 4.8886728071250356e-05, "epoch": 66.93805309734513, "percentage": 9.54, "elapsed_time": "0:27:24", "remaining_time": "4:19:55", "throughput": 1318.53, "total_tokens": 2168024} {"current_steps": 3820, "total_steps": 40000, "loss": 0.0, "lr": 4.8883829179441884e-05, "epoch": 67.01769911504425, "percentage": 9.55, "elapsed_time": "0:27:26", "remaining_time": "4:19:54", "throughput": 1318.36, "total_tokens": 2170720} {"current_steps": 3825, "total_steps": 40000, "loss": 0.0, "lr": 4.888092660444682e-05, "epoch": 67.10619469026548, "percentage": 9.56, "elapsed_time": "0:27:28", "remaining_time": "4:19:51", "throughput": 1318.27, "total_tokens": 2173312} {"current_steps": 3830, "total_steps": 40000, "loss": 0.0, "lr": 4.887802034671276e-05, "epoch": 67.19469026548673, "percentage": 9.57, "elapsed_time": "0:27:30", "remaining_time": "4:19:48", "throughput": 1318.23, "total_tokens": 2175984} {"current_steps": 3835, "total_steps": 40000, "loss": 0.0, "lr": 4.88751104066879e-05, "epoch": 67.28318584070796, "percentage": 9.59, "elapsed_time": "0:27:32", "remaining_time": "4:19:45", "throughput": 1318.18, "total_tokens": 2178624} {"current_steps": 3840, "total_steps": 40000, "loss": 0.0, "lr": 4.887219678482098e-05, "epoch": 67.3716814159292, "percentage": 9.6, "elapsed_time": "0:27:34", "remaining_time": "4:19:42", "throughput": 1318.02, "total_tokens": 2181088} {"current_steps": 3845, "total_steps": 40000, "loss": 0.0, "lr": 4.8869279481561316e-05, "epoch": 67.46017699115045, "percentage": 9.61, "elapsed_time": "0:27:36", "remaining_time": "4:19:39", "throughput": 1318.58, "total_tokens": 2184736} {"current_steps": 3850, "total_steps": 40000, "loss": 0.0, "lr": 4.88663584973588e-05, "epoch": 67.54867256637168, "percentage": 9.62, "elapsed_time": "0:27:38", "remaining_time": "4:19:36", "throughput": 1318.48, "total_tokens": 2187296} {"current_steps": 3855, "total_steps": 40000, "loss": 0.0, "lr": 4.8863433832663874e-05, "epoch": 67.63716814159292, "percentage": 9.64, "elapsed_time": "0:27:41", "remaining_time": "4:19:33", "throughput": 1318.74, "total_tokens": 2190432} {"current_steps": 3860, "total_steps": 40000, "loss": 0.0, "lr": 4.886050548792757e-05, "epoch": 67.72566371681415, "percentage": 9.65, "elapsed_time": "0:27:43", "remaining_time": "4:19:30", "throughput": 1318.99, "total_tokens": 2193568} {"current_steps": 3865, "total_steps": 40000, "loss": 0.0, "lr": 4.8857573463601465e-05, "epoch": 67.8141592920354, "percentage": 9.66, "elapsed_time": "0:27:45", "remaining_time": "4:19:27", "throughput": 1319.08, "total_tokens": 2196464} {"current_steps": 3870, "total_steps": 40000, "loss": 0.0, "lr": 4.885463776013772e-05, "epoch": 67.90265486725664, "percentage": 9.68, "elapsed_time": "0:27:47", "remaining_time": "4:19:24", "throughput": 1319.32, "total_tokens": 2199584} {"current_steps": 3875, "total_steps": 40000, "loss": 0.0, "lr": 4.8851698377989056e-05, "epoch": 67.99115044247787, "percentage": 9.69, "elapsed_time": "0:27:49", "remaining_time": "4:19:21", "throughput": 1319.42, "total_tokens": 2202432} {"current_steps": 3880, "total_steps": 40000, "loss": 0.0, "lr": 4.884875531760876e-05, "epoch": 68.070796460177, "percentage": 9.7, "elapsed_time": "0:27:51", "remaining_time": "4:19:20", "throughput": 1319.54, "total_tokens": 2205616} {"current_steps": 3885, "total_steps": 40000, "loss": 0.0, "lr": 4.88458085794507e-05, "epoch": 68.15929203539822, "percentage": 9.71, "elapsed_time": "0:27:53", "remaining_time": "4:19:17", "throughput": 1319.69, "total_tokens": 2208608} {"current_steps": 3890, "total_steps": 40000, "loss": 0.0, "lr": 4.884285816396929e-05, "epoch": 68.24778761061947, "percentage": 9.72, "elapsed_time": "0:27:55", "remaining_time": "4:19:14", "throughput": 1319.44, "total_tokens": 2210912} {"current_steps": 3895, "total_steps": 40000, "loss": 0.0, "lr": 4.8839904071619526e-05, "epoch": 68.33628318584071, "percentage": 9.74, "elapsed_time": "0:27:57", "remaining_time": "4:19:11", "throughput": 1319.62, "total_tokens": 2213952} {"current_steps": 3900, "total_steps": 40000, "loss": 0.0, "lr": 4.8836946302856955e-05, "epoch": 68.42477876106194, "percentage": 9.75, "elapsed_time": "0:27:59", "remaining_time": "4:19:08", "throughput": 1319.83, "total_tokens": 2217024} {"current_steps": 3905, "total_steps": 40000, "loss": 0.0, "lr": 4.8833984858137715e-05, "epoch": 68.51327433628319, "percentage": 9.76, "elapsed_time": "0:28:01", "remaining_time": "4:19:05", "throughput": 1319.78, "total_tokens": 2219680} {"current_steps": 3910, "total_steps": 40000, "loss": 0.0, "lr": 4.8831019737918494e-05, "epoch": 68.60176991150442, "percentage": 9.78, "elapsed_time": "0:28:03", "remaining_time": "4:19:02", "throughput": 1319.77, "total_tokens": 2222384} {"current_steps": 3915, "total_steps": 40000, "loss": 0.0, "lr": 4.882805094265655e-05, "epoch": 68.69026548672566, "percentage": 9.79, "elapsed_time": "0:28:05", "remaining_time": "4:18:59", "throughput": 1319.63, "total_tokens": 2224864} {"current_steps": 3920, "total_steps": 40000, "loss": 0.0, "lr": 4.8825078472809706e-05, "epoch": 68.77876106194691, "percentage": 9.8, "elapsed_time": "0:28:08", "remaining_time": "4:18:56", "throughput": 1319.99, "total_tokens": 2228192} {"current_steps": 3925, "total_steps": 40000, "loss": 0.0, "lr": 4.882210232883635e-05, "epoch": 68.86725663716814, "percentage": 9.81, "elapsed_time": "0:28:10", "remaining_time": "4:18:53", "throughput": 1320.02, "total_tokens": 2230976} {"current_steps": 3930, "total_steps": 40000, "loss": 0.0, "lr": 4.881912251119546e-05, "epoch": 68.95575221238938, "percentage": 9.83, "elapsed_time": "0:28:12", "remaining_time": "4:18:50", "throughput": 1320.19, "total_tokens": 2233968} {"current_steps": 3935, "total_steps": 40000, "loss": 0.0, "lr": 4.881613902034654e-05, "epoch": 69.03539823008849, "percentage": 9.84, "elapsed_time": "0:28:14", "remaining_time": "4:18:49", "throughput": 1319.87, "total_tokens": 2236392} {"current_steps": 3940, "total_steps": 40000, "loss": 0.0, "lr": 4.88131518567497e-05, "epoch": 69.12389380530973, "percentage": 9.85, "elapsed_time": "0:28:16", "remaining_time": "4:18:46", "throughput": 1319.81, "total_tokens": 2239032} {"current_steps": 3945, "total_steps": 40000, "loss": 0.0, "lr": 4.881016102086558e-05, "epoch": 69.21238938053098, "percentage": 9.86, "elapsed_time": "0:28:18", "remaining_time": "4:18:43", "throughput": 1319.89, "total_tokens": 2241912} {"current_steps": 3950, "total_steps": 40000, "loss": 0.0, "lr": 4.8807166513155425e-05, "epoch": 69.30088495575221, "percentage": 9.88, "elapsed_time": "0:28:20", "remaining_time": "4:18:40", "throughput": 1320.12, "total_tokens": 2245016} {"current_steps": 3955, "total_steps": 40000, "loss": 0.0, "lr": 4.8804168334081004e-05, "epoch": 69.38938053097345, "percentage": 9.89, "elapsed_time": "0:28:22", "remaining_time": "4:18:37", "throughput": 1320.11, "total_tokens": 2247720} {"current_steps": 3960, "total_steps": 40000, "loss": 0.0, "lr": 4.880116648410468e-05, "epoch": 69.47787610619469, "percentage": 9.9, "elapsed_time": "0:28:24", "remaining_time": "4:18:34", "throughput": 1320.06, "total_tokens": 2250360} {"current_steps": 3965, "total_steps": 40000, "loss": 0.0, "lr": 4.879816096368939e-05, "epoch": 69.56637168141593, "percentage": 9.91, "elapsed_time": "0:28:26", "remaining_time": "4:18:31", "throughput": 1320.17, "total_tokens": 2253272} {"current_steps": 3970, "total_steps": 40000, "loss": 0.0, "lr": 4.879515177329861e-05, "epoch": 69.65486725663717, "percentage": 9.93, "elapsed_time": "0:28:28", "remaining_time": "4:18:28", "throughput": 1320.24, "total_tokens": 2256120} {"current_steps": 3975, "total_steps": 40000, "loss": 0.0, "lr": 4.8792138913396394e-05, "epoch": 69.7433628318584, "percentage": 9.94, "elapsed_time": "0:28:30", "remaining_time": "4:18:26", "throughput": 1320.56, "total_tokens": 2259400} {"current_steps": 3980, "total_steps": 40000, "loss": 0.0, "lr": 4.8789122384447374e-05, "epoch": 69.83185840707965, "percentage": 9.95, "elapsed_time": "0:28:33", "remaining_time": "4:18:23", "throughput": 1320.68, "total_tokens": 2262344} {"current_steps": 3985, "total_steps": 40000, "loss": 0.0, "lr": 4.878610218691673e-05, "epoch": 69.92035398230088, "percentage": 9.96, "elapsed_time": "0:28:35", "remaining_time": "4:18:20", "throughput": 1320.74, "total_tokens": 2265160} {"current_steps": 3990, "total_steps": 40000, "loss": 0.0, "lr": 4.87830783212702e-05, "epoch": 70.0, "percentage": 9.98, "elapsed_time": "0:28:37", "remaining_time": "4:18:16", "throughput": 1320.58, "total_tokens": 2267528} {"current_steps": 3995, "total_steps": 40000, "loss": 0.0, "lr": 4.878005078797413e-05, "epoch": 70.08849557522124, "percentage": 9.99, "elapsed_time": "0:28:39", "remaining_time": "4:18:15", "throughput": 1320.29, "total_tokens": 2270056} {"current_steps": 4000, "total_steps": 40000, "loss": 0.0, "lr": 4.877701958749539e-05, "epoch": 70.17699115044248, "percentage": 10.0, "elapsed_time": "0:28:41", "remaining_time": "4:18:12", "throughput": 1320.29, "total_tokens": 2272792} {"current_steps": 4000, "total_steps": 40000, "eval_loss": 0.37287405133247375, "epoch": 70.17699115044248, "percentage": 10.0, "elapsed_time": "0:28:42", "remaining_time": "4:18:22", "throughput": 1319.48, "total_tokens": 2272792} {"current_steps": 4005, "total_steps": 40000, "loss": 0.0, "lr": 4.877398472030142e-05, "epoch": 70.26548672566372, "percentage": 10.01, "elapsed_time": "0:28:46", "remaining_time": "4:18:34", "throughput": 1318.17, "total_tokens": 2275432} {"current_steps": 4010, "total_steps": 40000, "loss": 0.0, "lr": 4.877094618686024e-05, "epoch": 70.35398230088495, "percentage": 10.03, "elapsed_time": "0:28:48", "remaining_time": "4:18:31", "throughput": 1318.24, "total_tokens": 2278280} {"current_steps": 4015, "total_steps": 40000, "loss": 0.0, "lr": 4.876790398764045e-05, "epoch": 70.4424778761062, "percentage": 10.04, "elapsed_time": "0:28:50", "remaining_time": "4:18:28", "throughput": 1318.32, "total_tokens": 2281128} {"current_steps": 4020, "total_steps": 40000, "loss": 0.0, "lr": 4.8764858123111167e-05, "epoch": 70.53097345132744, "percentage": 10.05, "elapsed_time": "0:28:52", "remaining_time": "4:18:25", "throughput": 1318.62, "total_tokens": 2284376} {"current_steps": 4025, "total_steps": 40000, "loss": 0.0, "lr": 4.876180859374212e-05, "epoch": 70.61946902654867, "percentage": 10.06, "elapsed_time": "0:28:54", "remaining_time": "4:18:22", "throughput": 1318.7, "total_tokens": 2287208} {"current_steps": 4030, "total_steps": 40000, "loss": 0.0, "lr": 4.875875540000357e-05, "epoch": 70.70796460176992, "percentage": 10.08, "elapsed_time": "0:28:56", "remaining_time": "4:18:19", "throughput": 1318.75, "total_tokens": 2290024} {"current_steps": 4035, "total_steps": 40000, "loss": 0.0, "lr": 4.8755698542366376e-05, "epoch": 70.79646017699115, "percentage": 10.09, "elapsed_time": "0:28:58", "remaining_time": "4:18:16", "throughput": 1318.68, "total_tokens": 2292616} {"current_steps": 4040, "total_steps": 40000, "loss": 0.0, "lr": 4.875263802130193e-05, "epoch": 70.88495575221239, "percentage": 10.1, "elapsed_time": "0:29:00", "remaining_time": "4:18:13", "throughput": 1319.12, "total_tokens": 2296104} {"current_steps": 4045, "total_steps": 40000, "loss": 0.0, "lr": 4.8749573837282207e-05, "epoch": 70.97345132743362, "percentage": 10.11, "elapsed_time": "0:29:02", "remaining_time": "4:18:10", "throughput": 1319.16, "total_tokens": 2298888} {"current_steps": 4050, "total_steps": 40000, "loss": 0.0, "lr": 4.874650599077974e-05, "epoch": 71.05309734513274, "percentage": 10.12, "elapsed_time": "0:29:04", "remaining_time": "4:18:09", "throughput": 1318.78, "total_tokens": 2301192} {"current_steps": 4055, "total_steps": 40000, "loss": 0.0, "lr": 4.874343448226764e-05, "epoch": 71.14159292035399, "percentage": 10.14, "elapsed_time": "0:29:07", "remaining_time": "4:18:06", "throughput": 1319.01, "total_tokens": 2304312} {"current_steps": 4060, "total_steps": 40000, "loss": 0.0, "lr": 4.874035931221955e-05, "epoch": 71.23008849557522, "percentage": 10.15, "elapsed_time": "0:29:09", "remaining_time": "4:18:03", "throughput": 1318.89, "total_tokens": 2306824} {"current_steps": 4065, "total_steps": 40000, "loss": 0.0, "lr": 4.8737280481109724e-05, "epoch": 71.31858407079646, "percentage": 10.16, "elapsed_time": "0:29:11", "remaining_time": "4:18:00", "throughput": 1319.03, "total_tokens": 2309800} {"current_steps": 4070, "total_steps": 40000, "loss": 0.0, "lr": 4.873419798941294e-05, "epoch": 71.40707964601769, "percentage": 10.17, "elapsed_time": "0:29:13", "remaining_time": "4:17:57", "throughput": 1319.14, "total_tokens": 2312728} {"current_steps": 4075, "total_steps": 40000, "loss": 0.0, "lr": 4.873111183760458e-05, "epoch": 71.49557522123894, "percentage": 10.19, "elapsed_time": "0:29:15", "remaining_time": "4:17:54", "throughput": 1319.22, "total_tokens": 2315608} {"current_steps": 4080, "total_steps": 40000, "loss": 0.0, "lr": 4.8728022026160537e-05, "epoch": 71.58407079646018, "percentage": 10.2, "elapsed_time": "0:29:17", "remaining_time": "4:17:51", "throughput": 1319.18, "total_tokens": 2318264} {"current_steps": 4085, "total_steps": 40000, "loss": 0.0, "lr": 4.872492855555732e-05, "epoch": 71.67256637168141, "percentage": 10.21, "elapsed_time": "0:29:19", "remaining_time": "4:17:48", "throughput": 1319.2, "total_tokens": 2321032} {"current_steps": 4090, "total_steps": 40000, "loss": 0.0, "lr": 4.8721831426271956e-05, "epoch": 71.76106194690266, "percentage": 10.22, "elapsed_time": "0:29:21", "remaining_time": "4:17:45", "throughput": 1319.67, "total_tokens": 2324568} {"current_steps": 4095, "total_steps": 40000, "loss": 0.0, "lr": 4.87187306387821e-05, "epoch": 71.84955752212389, "percentage": 10.24, "elapsed_time": "0:29:23", "remaining_time": "4:17:42", "throughput": 1319.59, "total_tokens": 2327144} {"current_steps": 4100, "total_steps": 40000, "loss": 0.0, "lr": 4.87156261935659e-05, "epoch": 71.93805309734513, "percentage": 10.25, "elapsed_time": "0:29:25", "remaining_time": "4:17:39", "throughput": 1319.73, "total_tokens": 2330104} {"current_steps": 4105, "total_steps": 40000, "loss": 0.0, "lr": 4.871251809110211e-05, "epoch": 72.01769911504425, "percentage": 10.26, "elapsed_time": "0:29:27", "remaining_time": "4:17:38", "throughput": 1319.5, "total_tokens": 2332656} {"current_steps": 4110, "total_steps": 40000, "loss": 0.0, "lr": 4.8709406331870044e-05, "epoch": 72.10619469026548, "percentage": 10.27, "elapsed_time": "0:29:29", "remaining_time": "4:17:35", "throughput": 1319.61, "total_tokens": 2335584} {"current_steps": 4115, "total_steps": 40000, "loss": 0.0, "lr": 4.8706290916349574e-05, "epoch": 72.19469026548673, "percentage": 10.29, "elapsed_time": "0:29:31", "remaining_time": "4:17:32", "throughput": 1319.46, "total_tokens": 2338048} {"current_steps": 4120, "total_steps": 40000, "loss": 0.0, "lr": 4.8703171845021134e-05, "epoch": 72.28318584070796, "percentage": 10.3, "elapsed_time": "0:29:34", "remaining_time": "4:17:29", "throughput": 1319.5, "total_tokens": 2340848} {"current_steps": 4125, "total_steps": 40000, "loss": 0.0, "lr": 4.870004911836572e-05, "epoch": 72.3716814159292, "percentage": 10.31, "elapsed_time": "0:29:36", "remaining_time": "4:17:26", "throughput": 1319.81, "total_tokens": 2344112} {"current_steps": 4130, "total_steps": 40000, "loss": 0.0, "lr": 4.869692273686489e-05, "epoch": 72.46017699115045, "percentage": 10.32, "elapsed_time": "0:29:38", "remaining_time": "4:17:23", "throughput": 1319.65, "total_tokens": 2346544} {"current_steps": 4135, "total_steps": 40000, "loss": 0.0, "lr": 4.869379270100079e-05, "epoch": 72.54867256637168, "percentage": 10.34, "elapsed_time": "0:29:40", "remaining_time": "4:17:20", "throughput": 1319.75, "total_tokens": 2349456} {"current_steps": 4140, "total_steps": 40000, "loss": 0.0, "lr": 4.86906590112561e-05, "epoch": 72.63716814159292, "percentage": 10.35, "elapsed_time": "0:29:42", "remaining_time": "4:17:17", "throughput": 1319.74, "total_tokens": 2352160} {"current_steps": 4145, "total_steps": 40000, "loss": 0.0, "lr": 4.8687521668114064e-05, "epoch": 72.72566371681415, "percentage": 10.36, "elapsed_time": "0:29:44", "remaining_time": "4:17:15", "throughput": 1319.86, "total_tokens": 2355104} {"current_steps": 4150, "total_steps": 40000, "loss": 0.0, "lr": 4.868438067205853e-05, "epoch": 72.8141592920354, "percentage": 10.38, "elapsed_time": "0:29:46", "remaining_time": "4:17:12", "throughput": 1320.11, "total_tokens": 2358288} {"current_steps": 4155, "total_steps": 40000, "loss": 0.0, "lr": 4.8681236023573844e-05, "epoch": 72.90265486725664, "percentage": 10.39, "elapsed_time": "0:29:48", "remaining_time": "4:17:09", "throughput": 1320.13, "total_tokens": 2361056} {"current_steps": 4160, "total_steps": 40000, "loss": 0.0, "lr": 4.867808772314497e-05, "epoch": 72.99115044247787, "percentage": 10.4, "elapsed_time": "0:29:50", "remaining_time": "4:17:06", "throughput": 1320.36, "total_tokens": 2364160} {"current_steps": 4165, "total_steps": 40000, "loss": 0.0, "lr": 4.867493577125741e-05, "epoch": 73.070796460177, "percentage": 10.41, "elapsed_time": "0:29:52", "remaining_time": "4:17:04", "throughput": 1319.94, "total_tokens": 2366384} {"current_steps": 4170, "total_steps": 40000, "loss": 0.0, "lr": 4.867178016839725e-05, "epoch": 73.15929203539822, "percentage": 10.42, "elapsed_time": "0:29:54", "remaining_time": "4:17:02", "throughput": 1320.23, "total_tokens": 2369632} {"current_steps": 4175, "total_steps": 40000, "loss": 0.0, "lr": 4.8668620915051094e-05, "epoch": 73.24778761061947, "percentage": 10.44, "elapsed_time": "0:29:56", "remaining_time": "4:16:59", "throughput": 1320.52, "total_tokens": 2372880} {"current_steps": 4180, "total_steps": 40000, "loss": 0.0, "lr": 4.866545801170616e-05, "epoch": 73.33628318584071, "percentage": 10.45, "elapsed_time": "0:29:58", "remaining_time": "4:16:56", "throughput": 1320.38, "total_tokens": 2375344} {"current_steps": 4185, "total_steps": 40000, "loss": 0.0, "lr": 4.86622914588502e-05, "epoch": 73.42477876106194, "percentage": 10.46, "elapsed_time": "0:30:01", "remaining_time": "4:16:53", "throughput": 1320.49, "total_tokens": 2378288} {"current_steps": 4190, "total_steps": 40000, "loss": 0.0, "lr": 4.865912125697154e-05, "epoch": 73.51327433628319, "percentage": 10.47, "elapsed_time": "0:30:03", "remaining_time": "4:16:50", "throughput": 1320.82, "total_tokens": 2381600} {"current_steps": 4195, "total_steps": 40000, "loss": 0.0, "lr": 4.865594740655907e-05, "epoch": 73.60176991150442, "percentage": 10.49, "elapsed_time": "0:30:05", "remaining_time": "4:16:47", "throughput": 1320.69, "total_tokens": 2384096} {"current_steps": 4200, "total_steps": 40000, "loss": 0.0, "lr": 4.865276990810222e-05, "epoch": 73.69026548672566, "percentage": 10.5, "elapsed_time": "0:30:07", "remaining_time": "4:16:44", "throughput": 1320.97, "total_tokens": 2387344} {"current_steps": 4200, "total_steps": 40000, "eval_loss": 0.37824875116348267, "epoch": 73.69026548672566, "percentage": 10.5, "elapsed_time": "0:30:08", "remaining_time": "4:16:53", "throughput": 1320.19, "total_tokens": 2387344} {"current_steps": 4205, "total_steps": 40000, "loss": 0.0, "lr": 4.8649588762091016e-05, "epoch": 73.77876106194691, "percentage": 10.51, "elapsed_time": "0:30:12", "remaining_time": "4:17:07", "throughput": 1318.89, "total_tokens": 2390256} {"current_steps": 4210, "total_steps": 40000, "loss": 0.0, "lr": 4.8646403969016016e-05, "epoch": 73.86725663716814, "percentage": 10.53, "elapsed_time": "0:30:14", "remaining_time": "4:17:04", "throughput": 1318.93, "total_tokens": 2393056} {"current_steps": 4215, "total_steps": 40000, "loss": 0.0, "lr": 4.864321552936838e-05, "epoch": 73.95575221238938, "percentage": 10.54, "elapsed_time": "0:30:16", "remaining_time": "4:17:01", "throughput": 1318.83, "total_tokens": 2395600} {"current_steps": 4220, "total_steps": 40000, "loss": 0.0, "lr": 4.864002344363978e-05, "epoch": 74.03539823008849, "percentage": 10.55, "elapsed_time": "0:30:18", "remaining_time": "4:17:00", "throughput": 1318.39, "total_tokens": 2397832} {"current_steps": 4225, "total_steps": 40000, "loss": 0.0, "lr": 4.863682771232248e-05, "epoch": 74.12389380530973, "percentage": 10.56, "elapsed_time": "0:30:20", "remaining_time": "4:16:57", "throughput": 1318.57, "total_tokens": 2400872} {"current_steps": 4230, "total_steps": 40000, "loss": 0.0, "lr": 4.8633628335909324e-05, "epoch": 74.21238938053098, "percentage": 10.57, "elapsed_time": "0:30:22", "remaining_time": "4:16:54", "throughput": 1318.55, "total_tokens": 2403544} {"current_steps": 4235, "total_steps": 40000, "loss": 0.0, "lr": 4.8630425314893676e-05, "epoch": 74.30088495575221, "percentage": 10.59, "elapsed_time": "0:30:24", "remaining_time": "4:16:51", "throughput": 1318.81, "total_tokens": 2406744} {"current_steps": 4240, "total_steps": 40000, "loss": 0.0, "lr": 4.862721864976948e-05, "epoch": 74.38938053097345, "percentage": 10.6, "elapsed_time": "0:30:26", "remaining_time": "4:16:48", "throughput": 1319.04, "total_tokens": 2409880} {"current_steps": 4245, "total_steps": 40000, "loss": 0.0, "lr": 4.862400834103125e-05, "epoch": 74.47787610619469, "percentage": 10.61, "elapsed_time": "0:30:29", "remaining_time": "4:16:45", "throughput": 1318.94, "total_tokens": 2412408} {"current_steps": 4250, "total_steps": 40000, "loss": 0.0, "lr": 4.862079438917406e-05, "epoch": 74.56637168141593, "percentage": 10.62, "elapsed_time": "0:30:31", "remaining_time": "4:16:43", "throughput": 1319.03, "total_tokens": 2415304} {"current_steps": 4255, "total_steps": 40000, "loss": 0.0, "lr": 4.8617576794693536e-05, "epoch": 74.65486725663717, "percentage": 10.64, "elapsed_time": "0:30:33", "remaining_time": "4:16:40", "throughput": 1319.06, "total_tokens": 2418088} {"current_steps": 4260, "total_steps": 40000, "loss": 0.0, "lr": 4.8614355558085875e-05, "epoch": 74.7433628318584, "percentage": 10.65, "elapsed_time": "0:30:35", "remaining_time": "4:16:37", "throughput": 1319.09, "total_tokens": 2420872} {"current_steps": 4265, "total_steps": 40000, "loss": 0.0, "lr": 4.861113067984783e-05, "epoch": 74.83185840707965, "percentage": 10.66, "elapsed_time": "0:30:37", "remaining_time": "4:16:34", "throughput": 1319.1, "total_tokens": 2423592} {"current_steps": 4270, "total_steps": 40000, "loss": 0.0, "lr": 4.860790216047671e-05, "epoch": 74.92035398230088, "percentage": 10.67, "elapsed_time": "0:30:39", "remaining_time": "4:16:31", "throughput": 1319.24, "total_tokens": 2426584} {"current_steps": 4275, "total_steps": 40000, "loss": 0.0, "lr": 4.860467000047041e-05, "epoch": 75.0, "percentage": 10.69, "elapsed_time": "0:30:41", "remaining_time": "4:16:27", "throughput": 1318.97, "total_tokens": 2428728} {"current_steps": 4280, "total_steps": 40000, "loss": 0.0, "lr": 4.860143420032737e-05, "epoch": 75.08849557522124, "percentage": 10.7, "elapsed_time": "0:30:43", "remaining_time": "4:16:26", "throughput": 1318.87, "total_tokens": 2431576} {"current_steps": 4285, "total_steps": 40000, "loss": 0.0, "lr": 4.859819476054657e-05, "epoch": 75.17699115044248, "percentage": 10.71, "elapsed_time": "0:30:45", "remaining_time": "4:16:24", "throughput": 1318.97, "total_tokens": 2434488} {"current_steps": 4290, "total_steps": 40000, "loss": 0.0, "lr": 4.859495168162758e-05, "epoch": 75.26548672566372, "percentage": 10.72, "elapsed_time": "0:30:47", "remaining_time": "4:16:21", "throughput": 1318.96, "total_tokens": 2437208} {"current_steps": 4295, "total_steps": 40000, "loss": 0.0, "lr": 4.859170496407054e-05, "epoch": 75.35398230088495, "percentage": 10.74, "elapsed_time": "0:30:49", "remaining_time": "4:16:18", "throughput": 1319.07, "total_tokens": 2440120} {"current_steps": 4300, "total_steps": 40000, "loss": 0.0, "lr": 4.8588454608376114e-05, "epoch": 75.4424778761062, "percentage": 10.75, "elapsed_time": "0:30:51", "remaining_time": "4:16:15", "throughput": 1319.08, "total_tokens": 2442856} {"current_steps": 4305, "total_steps": 40000, "loss": 0.0, "lr": 4.8585200615045555e-05, "epoch": 75.53097345132744, "percentage": 10.76, "elapsed_time": "0:30:54", "remaining_time": "4:16:12", "throughput": 1319.21, "total_tokens": 2445816} {"current_steps": 4310, "total_steps": 40000, "loss": 0.0, "lr": 4.8581942984580674e-05, "epoch": 75.61946902654867, "percentage": 10.78, "elapsed_time": "0:30:56", "remaining_time": "4:16:09", "throughput": 1319.2, "total_tokens": 2448520} {"current_steps": 4315, "total_steps": 40000, "loss": 0.0, "lr": 4.857868171748384e-05, "epoch": 75.70796460176992, "percentage": 10.79, "elapsed_time": "0:30:58", "remaining_time": "4:16:06", "throughput": 1319.45, "total_tokens": 2451704} {"current_steps": 4320, "total_steps": 40000, "loss": 0.0, "lr": 4.8575416814257976e-05, "epoch": 75.79646017699115, "percentage": 10.8, "elapsed_time": "0:31:00", "remaining_time": "4:16:03", "throughput": 1319.42, "total_tokens": 2454392} {"current_steps": 4325, "total_steps": 40000, "loss": 0.0, "lr": 4.857214827540657e-05, "epoch": 75.88495575221239, "percentage": 10.81, "elapsed_time": "0:31:02", "remaining_time": "4:16:01", "throughput": 1319.52, "total_tokens": 2457304} {"current_steps": 4330, "total_steps": 40000, "loss": 0.0, "lr": 4.856887610143367e-05, "epoch": 75.97345132743362, "percentage": 10.82, "elapsed_time": "0:31:04", "remaining_time": "4:15:58", "throughput": 1319.91, "total_tokens": 2460728} {"current_steps": 4335, "total_steps": 40000, "loss": 0.0, "lr": 4.8565600292843896e-05, "epoch": 76.05309734513274, "percentage": 10.84, "elapsed_time": "0:31:06", "remaining_time": "4:15:56", "throughput": 1319.69, "total_tokens": 2463304} {"current_steps": 4340, "total_steps": 40000, "loss": 0.0, "lr": 4.856232085014241e-05, "epoch": 76.14159292035399, "percentage": 10.85, "elapsed_time": "0:31:08", "remaining_time": "4:15:53", "throughput": 1319.53, "total_tokens": 2465720} {"current_steps": 4345, "total_steps": 40000, "loss": 0.0, "lr": 4.855903777383495e-05, "epoch": 76.23008849557522, "percentage": 10.86, "elapsed_time": "0:31:10", "remaining_time": "4:15:50", "throughput": 1319.73, "total_tokens": 2468824} {"current_steps": 4350, "total_steps": 40000, "loss": 0.0, "lr": 4.85557510644278e-05, "epoch": 76.31858407079646, "percentage": 10.88, "elapsed_time": "0:31:12", "remaining_time": "4:15:48", "throughput": 1319.99, "total_tokens": 2472040} {"current_steps": 4355, "total_steps": 40000, "loss": 0.0, "lr": 4.855246072242782e-05, "epoch": 76.40707964601769, "percentage": 10.89, "elapsed_time": "0:31:14", "remaining_time": "4:15:45", "throughput": 1320.08, "total_tokens": 2474936} {"current_steps": 4360, "total_steps": 40000, "loss": 0.0, "lr": 4.8549166748342414e-05, "epoch": 76.49557522123894, "percentage": 10.9, "elapsed_time": "0:31:16", "remaining_time": "4:15:42", "throughput": 1320.12, "total_tokens": 2477736} {"current_steps": 4365, "total_steps": 40000, "loss": 0.0, "lr": 4.8545869142679556e-05, "epoch": 76.58407079646018, "percentage": 10.91, "elapsed_time": "0:31:18", "remaining_time": "4:15:39", "throughput": 1320.04, "total_tokens": 2480296} {"current_steps": 4370, "total_steps": 40000, "loss": 0.0, "lr": 4.8542567905947776e-05, "epoch": 76.67256637168141, "percentage": 10.93, "elapsed_time": "0:31:21", "remaining_time": "4:15:36", "throughput": 1320.16, "total_tokens": 2483256} {"current_steps": 4375, "total_steps": 40000, "loss": 0.0, "lr": 4.853926303865618e-05, "epoch": 76.76106194690266, "percentage": 10.94, "elapsed_time": "0:31:23", "remaining_time": "4:15:33", "throughput": 1320.36, "total_tokens": 2486360} {"current_steps": 4380, "total_steps": 40000, "loss": 0.0, "lr": 4.853595454131441e-05, "epoch": 76.84955752212389, "percentage": 10.95, "elapsed_time": "0:31:25", "remaining_time": "4:15:30", "throughput": 1320.51, "total_tokens": 2489352} {"current_steps": 4385, "total_steps": 40000, "loss": 0.0, "lr": 4.8532642414432674e-05, "epoch": 76.93805309734513, "percentage": 10.96, "elapsed_time": "0:31:27", "remaining_time": "4:15:27", "throughput": 1320.54, "total_tokens": 2492136} {"current_steps": 4390, "total_steps": 40000, "loss": 0.0, "lr": 4.8529326658521754e-05, "epoch": 77.01769911504425, "percentage": 10.97, "elapsed_time": "0:31:29", "remaining_time": "4:15:26", "throughput": 1320.09, "total_tokens": 2494240} {"current_steps": 4395, "total_steps": 40000, "loss": 0.0, "lr": 4.8526007274092965e-05, "epoch": 77.10619469026548, "percentage": 10.99, "elapsed_time": "0:31:31", "remaining_time": "4:15:23", "throughput": 1320.29, "total_tokens": 2497360} {"current_steps": 4400, "total_steps": 40000, "loss": 0.0, "lr": 4.852268426165822e-05, "epoch": 77.19469026548673, "percentage": 11.0, "elapsed_time": "0:31:33", "remaining_time": "4:15:20", "throughput": 1320.33, "total_tokens": 2500160} {"current_steps": 4400, "total_steps": 40000, "eval_loss": 0.38144075870513916, "epoch": 77.19469026548673, "percentage": 11.0, "elapsed_time": "0:31:34", "remaining_time": "4:15:29", "throughput": 1319.59, "total_tokens": 2500160} {"current_steps": 4405, "total_steps": 40000, "loss": 0.0, "lr": 4.851935762172995e-05, "epoch": 77.28318584070796, "percentage": 11.01, "elapsed_time": "0:31:38", "remaining_time": "4:15:40", "throughput": 1318.58, "total_tokens": 2503184} {"current_steps": 4410, "total_steps": 40000, "loss": 0.0, "lr": 4.8516027354821175e-05, "epoch": 77.3716814159292, "percentage": 11.03, "elapsed_time": "0:31:40", "remaining_time": "4:15:37", "throughput": 1318.54, "total_tokens": 2505808} {"current_steps": 4415, "total_steps": 40000, "loss": 0.0, "lr": 4.851269346144546e-05, "epoch": 77.46017699115045, "percentage": 11.04, "elapsed_time": "0:31:42", "remaining_time": "4:15:34", "throughput": 1318.32, "total_tokens": 2508128} {"current_steps": 4420, "total_steps": 40000, "loss": 0.0, "lr": 4.850935594211693e-05, "epoch": 77.54867256637168, "percentage": 11.05, "elapsed_time": "0:31:44", "remaining_time": "4:15:31", "throughput": 1318.34, "total_tokens": 2510896} {"current_steps": 4425, "total_steps": 40000, "loss": 0.0, "lr": 4.850601479735029e-05, "epoch": 77.63716814159292, "percentage": 11.06, "elapsed_time": "0:31:46", "remaining_time": "4:15:28", "throughput": 1318.43, "total_tokens": 2513792} {"current_steps": 4430, "total_steps": 40000, "loss": 0.0, "lr": 4.850267002766076e-05, "epoch": 77.72566371681415, "percentage": 11.07, "elapsed_time": "0:31:48", "remaining_time": "4:15:25", "throughput": 1318.43, "total_tokens": 2516512} {"current_steps": 4435, "total_steps": 40000, "loss": 0.0, "lr": 4.849932163356417e-05, "epoch": 77.8141592920354, "percentage": 11.09, "elapsed_time": "0:31:50", "remaining_time": "4:15:22", "throughput": 1319.07, "total_tokens": 2520448} {"current_steps": 4440, "total_steps": 40000, "loss": 0.0, "lr": 4.8495969615576864e-05, "epoch": 77.90265486725664, "percentage": 11.1, "elapsed_time": "0:31:52", "remaining_time": "4:15:19", "throughput": 1319.13, "total_tokens": 2523264} {"current_steps": 4445, "total_steps": 40000, "loss": 0.0, "lr": 4.849261397421577e-05, "epoch": 77.99115044247787, "percentage": 11.11, "elapsed_time": "0:31:54", "remaining_time": "4:15:16", "throughput": 1319.08, "total_tokens": 2525888} {"current_steps": 4450, "total_steps": 40000, "loss": 0.0, "lr": 4.848925470999839e-05, "epoch": 78.070796460177, "percentage": 11.12, "elapsed_time": "0:31:57", "remaining_time": "4:15:15", "throughput": 1318.95, "total_tokens": 2528640} {"current_steps": 4455, "total_steps": 40000, "loss": 0.0, "lr": 4.848589182344273e-05, "epoch": 78.15929203539822, "percentage": 11.14, "elapsed_time": "0:31:59", "remaining_time": "4:15:12", "throughput": 1319.01, "total_tokens": 2531472} {"current_steps": 4460, "total_steps": 40000, "loss": 0.0, "lr": 4.848252531506742e-05, "epoch": 78.24778761061947, "percentage": 11.15, "elapsed_time": "0:32:01", "remaining_time": "4:15:10", "throughput": 1318.88, "total_tokens": 2533968} {"current_steps": 4465, "total_steps": 40000, "loss": 0.0, "lr": 4.847915518539161e-05, "epoch": 78.33628318584071, "percentage": 11.16, "elapsed_time": "0:32:03", "remaining_time": "4:15:07", "throughput": 1318.77, "total_tokens": 2536464} {"current_steps": 4470, "total_steps": 40000, "loss": 0.0, "lr": 4.847578143493501e-05, "epoch": 78.42477876106194, "percentage": 11.18, "elapsed_time": "0:32:05", "remaining_time": "4:15:04", "throughput": 1318.68, "total_tokens": 2539008} {"current_steps": 4475, "total_steps": 40000, "loss": 0.0, "lr": 4.847240406421789e-05, "epoch": 78.51327433628319, "percentage": 11.19, "elapsed_time": "0:32:07", "remaining_time": "4:15:01", "throughput": 1319.01, "total_tokens": 2542368} {"current_steps": 4480, "total_steps": 40000, "loss": 0.0, "lr": 4.84690230737611e-05, "epoch": 78.60176991150442, "percentage": 11.2, "elapsed_time": "0:32:09", "remaining_time": "4:14:58", "throughput": 1319.06, "total_tokens": 2545184} {"current_steps": 4485, "total_steps": 40000, "loss": 0.0, "lr": 4.846563846408602e-05, "epoch": 78.69026548672566, "percentage": 11.21, "elapsed_time": "0:32:11", "remaining_time": "4:14:55", "throughput": 1319.22, "total_tokens": 2548224} {"current_steps": 4490, "total_steps": 40000, "loss": 0.0, "lr": 4.84622502357146e-05, "epoch": 78.77876106194691, "percentage": 11.22, "elapsed_time": "0:32:13", "remaining_time": "4:14:52", "throughput": 1319.29, "total_tokens": 2551072} {"current_steps": 4495, "total_steps": 40000, "loss": 0.0, "lr": 4.8458858389169345e-05, "epoch": 78.86725663716814, "percentage": 11.24, "elapsed_time": "0:32:15", "remaining_time": "4:14:50", "throughput": 1319.4, "total_tokens": 2554016} {"current_steps": 4500, "total_steps": 40000, "loss": 0.0, "lr": 4.8455462924973334e-05, "epoch": 78.95575221238938, "percentage": 11.25, "elapsed_time": "0:32:17", "remaining_time": "4:14:47", "throughput": 1319.52, "total_tokens": 2556960} {"current_steps": 4505, "total_steps": 40000, "loss": 0.0, "lr": 4.845206384365018e-05, "epoch": 79.03539823008849, "percentage": 11.26, "elapsed_time": "0:32:20", "remaining_time": "4:14:45", "throughput": 1319.17, "total_tokens": 2559240} {"current_steps": 4510, "total_steps": 40000, "loss": 0.0, "lr": 4.844866114572405e-05, "epoch": 79.12389380530973, "percentage": 11.28, "elapsed_time": "0:32:22", "remaining_time": "4:14:42", "throughput": 1319.22, "total_tokens": 2562056} {"current_steps": 4515, "total_steps": 40000, "loss": 0.0, "lr": 4.8445254831719706e-05, "epoch": 79.21238938053098, "percentage": 11.29, "elapsed_time": "0:32:24", "remaining_time": "4:14:39", "throughput": 1319.2, "total_tokens": 2564744} {"current_steps": 4520, "total_steps": 40000, "loss": 0.0, "lr": 4.8441844902162434e-05, "epoch": 79.30088495575221, "percentage": 11.3, "elapsed_time": "0:32:26", "remaining_time": "4:14:37", "throughput": 1319.5, "total_tokens": 2568040} {"current_steps": 4525, "total_steps": 40000, "loss": 0.0, "lr": 4.843843135757809e-05, "epoch": 79.38938053097345, "percentage": 11.31, "elapsed_time": "0:32:28", "remaining_time": "4:14:34", "throughput": 1319.52, "total_tokens": 2570808} {"current_steps": 4530, "total_steps": 40000, "loss": 0.0, "lr": 4.843501419849308e-05, "epoch": 79.47787610619469, "percentage": 11.33, "elapsed_time": "0:32:30", "remaining_time": "4:14:31", "throughput": 1319.74, "total_tokens": 2573992} {"current_steps": 4535, "total_steps": 40000, "loss": 0.0, "lr": 4.8431593425434386e-05, "epoch": 79.56637168141593, "percentage": 11.34, "elapsed_time": "0:32:32", "remaining_time": "4:14:30", "throughput": 1319.58, "total_tokens": 2576744} {"current_steps": 4540, "total_steps": 40000, "loss": 0.0, "lr": 4.8428169038929526e-05, "epoch": 79.65486725663717, "percentage": 11.35, "elapsed_time": "0:32:34", "remaining_time": "4:14:27", "throughput": 1319.78, "total_tokens": 2579864} {"current_steps": 4545, "total_steps": 40000, "loss": 0.0, "lr": 4.8424741039506575e-05, "epoch": 79.7433628318584, "percentage": 11.36, "elapsed_time": "0:32:36", "remaining_time": "4:14:24", "throughput": 1319.81, "total_tokens": 2582632} {"current_steps": 4550, "total_steps": 40000, "loss": 0.0, "lr": 4.842130942769419e-05, "epoch": 79.83185840707965, "percentage": 11.38, "elapsed_time": "0:32:38", "remaining_time": "4:14:22", "throughput": 1319.98, "total_tokens": 2585688} {"current_steps": 4555, "total_steps": 40000, "loss": 0.0, "lr": 4.841787420402156e-05, "epoch": 79.92035398230088, "percentage": 11.39, "elapsed_time": "0:32:40", "remaining_time": "4:14:19", "throughput": 1320.03, "total_tokens": 2588504} {"current_steps": 4560, "total_steps": 40000, "loss": 0.0, "lr": 4.841443536901844e-05, "epoch": 80.0, "percentage": 11.4, "elapsed_time": "0:32:42", "remaining_time": "4:14:15", "throughput": 1319.94, "total_tokens": 2590976} {"current_steps": 4565, "total_steps": 40000, "loss": 0.0, "lr": 4.841099292321514e-05, "epoch": 80.08849557522124, "percentage": 11.41, "elapsed_time": "0:32:45", "remaining_time": "4:14:14", "throughput": 1319.83, "total_tokens": 2593808} {"current_steps": 4570, "total_steps": 40000, "loss": 0.0, "lr": 4.8407546867142525e-05, "epoch": 80.17699115044248, "percentage": 11.43, "elapsed_time": "0:32:47", "remaining_time": "4:14:12", "throughput": 1319.97, "total_tokens": 2596800} {"current_steps": 4575, "total_steps": 40000, "loss": 0.0, "lr": 4.840409720133203e-05, "epoch": 80.26548672566372, "percentage": 11.44, "elapsed_time": "0:32:49", "remaining_time": "4:14:09", "throughput": 1320.01, "total_tokens": 2599616} {"current_steps": 4580, "total_steps": 40000, "loss": 0.0, "lr": 4.8400643926315634e-05, "epoch": 80.35398230088495, "percentage": 11.45, "elapsed_time": "0:32:51", "remaining_time": "4:14:06", "throughput": 1320.06, "total_tokens": 2602432} {"current_steps": 4585, "total_steps": 40000, "loss": 0.0, "lr": 4.839718704262587e-05, "epoch": 80.4424778761062, "percentage": 11.46, "elapsed_time": "0:32:53", "remaining_time": "4:14:03", "throughput": 1320.03, "total_tokens": 2605104} {"current_steps": 4590, "total_steps": 40000, "loss": 0.0, "lr": 4.839372655079585e-05, "epoch": 80.53097345132744, "percentage": 11.47, "elapsed_time": "0:32:55", "remaining_time": "4:14:00", "throughput": 1320.12, "total_tokens": 2607984} {"current_steps": 4595, "total_steps": 40000, "loss": 0.0, "lr": 4.83902624513592e-05, "epoch": 80.61946902654867, "percentage": 11.49, "elapsed_time": "0:32:57", "remaining_time": "4:13:57", "throughput": 1320.18, "total_tokens": 2610832} {"current_steps": 4600, "total_steps": 40000, "loss": 0.0, "lr": 4.838679474485014e-05, "epoch": 80.70796460176992, "percentage": 11.5, "elapsed_time": "0:32:59", "remaining_time": "4:13:55", "throughput": 1320.42, "total_tokens": 2614032} {"current_steps": 4600, "total_steps": 40000, "eval_loss": 0.362618625164032, "epoch": 80.70796460176992, "percentage": 11.5, "elapsed_time": "0:33:00", "remaining_time": "4:14:03", "throughput": 1319.71, "total_tokens": 2614032} {"current_steps": 4605, "total_steps": 40000, "loss": 0.0, "lr": 4.838332343180343e-05, "epoch": 80.79646017699115, "percentage": 11.51, "elapsed_time": "0:33:04", "remaining_time": "4:14:12", "throughput": 1318.66, "total_tokens": 2616800} {"current_steps": 4610, "total_steps": 40000, "loss": 0.0, "lr": 4.83798485127544e-05, "epoch": 80.88495575221239, "percentage": 11.53, "elapsed_time": "0:33:06", "remaining_time": "4:14:10", "throughput": 1318.71, "total_tokens": 2619648} {"current_steps": 4615, "total_steps": 40000, "loss": 0.0, "lr": 4.837636998823892e-05, "epoch": 80.97345132743362, "percentage": 11.54, "elapsed_time": "0:33:08", "remaining_time": "4:14:07", "throughput": 1318.97, "total_tokens": 2622864} {"current_steps": 4620, "total_steps": 40000, "loss": 0.0, "lr": 4.8372887858793414e-05, "epoch": 81.05309734513274, "percentage": 11.55, "elapsed_time": "0:33:10", "remaining_time": "4:14:05", "throughput": 1318.67, "total_tokens": 2625232} {"current_steps": 4625, "total_steps": 40000, "loss": 0.0, "lr": 4.836940212495489e-05, "epoch": 81.14159292035399, "percentage": 11.56, "elapsed_time": "0:33:12", "remaining_time": "4:14:02", "throughput": 1318.85, "total_tokens": 2628320} {"current_steps": 4630, "total_steps": 40000, "loss": 0.0, "lr": 4.836591278726087e-05, "epoch": 81.23008849557522, "percentage": 11.58, "elapsed_time": "0:33:14", "remaining_time": "4:14:00", "throughput": 1318.86, "total_tokens": 2631056} {"current_steps": 4635, "total_steps": 40000, "loss": 0.0, "lr": 4.836241984624947e-05, "epoch": 81.31858407079646, "percentage": 11.59, "elapsed_time": "0:33:17", "remaining_time": "4:13:57", "throughput": 1318.86, "total_tokens": 2633792} {"current_steps": 4640, "total_steps": 40000, "loss": 0.0, "lr": 4.8358923302459336e-05, "epoch": 81.40707964601769, "percentage": 11.6, "elapsed_time": "0:33:19", "remaining_time": "4:13:54", "throughput": 1318.75, "total_tokens": 2636288} {"current_steps": 4645, "total_steps": 40000, "loss": 0.0, "lr": 4.835542315642968e-05, "epoch": 81.49557522123894, "percentage": 11.61, "elapsed_time": "0:33:21", "remaining_time": "4:13:51", "throughput": 1319.02, "total_tokens": 2639536} {"current_steps": 4650, "total_steps": 40000, "loss": 0.0, "lr": 4.8351919408700274e-05, "epoch": 81.58407079646018, "percentage": 11.62, "elapsed_time": "0:33:23", "remaining_time": "4:13:48", "throughput": 1319.02, "total_tokens": 2642256} {"current_steps": 4655, "total_steps": 40000, "loss": 0.0, "lr": 4.834841205981144e-05, "epoch": 81.67256637168141, "percentage": 11.64, "elapsed_time": "0:33:25", "remaining_time": "4:13:45", "throughput": 1319.17, "total_tokens": 2645280} {"current_steps": 4660, "total_steps": 40000, "loss": 0.0, "lr": 4.8344901110304054e-05, "epoch": 81.76106194690266, "percentage": 11.65, "elapsed_time": "0:33:27", "remaining_time": "4:13:42", "throughput": 1319.48, "total_tokens": 2648624} {"current_steps": 4665, "total_steps": 40000, "loss": 0.0, "lr": 4.8341386560719534e-05, "epoch": 81.84955752212389, "percentage": 11.66, "elapsed_time": "0:33:29", "remaining_time": "4:13:39", "throughput": 1319.73, "total_tokens": 2651824} {"current_steps": 4670, "total_steps": 40000, "loss": 0.0, "lr": 4.833786841159989e-05, "epoch": 81.93805309734513, "percentage": 11.68, "elapsed_time": "0:33:31", "remaining_time": "4:13:37", "throughput": 1319.63, "total_tokens": 2654352} {"current_steps": 4675, "total_steps": 40000, "loss": 0.0, "lr": 4.833434666348765e-05, "epoch": 82.01769911504425, "percentage": 11.69, "elapsed_time": "0:33:33", "remaining_time": "4:13:35", "throughput": 1319.47, "total_tokens": 2656984} {"current_steps": 4680, "total_steps": 40000, "loss": 0.0, "lr": 4.833082131692592e-05, "epoch": 82.10619469026548, "percentage": 11.7, "elapsed_time": "0:33:35", "remaining_time": "4:13:32", "throughput": 1319.48, "total_tokens": 2659736} {"current_steps": 4685, "total_steps": 40000, "loss": 0.0, "lr": 4.832729237245835e-05, "epoch": 82.19469026548673, "percentage": 11.71, "elapsed_time": "0:33:37", "remaining_time": "4:13:30", "throughput": 1319.45, "total_tokens": 2662392} {"current_steps": 4690, "total_steps": 40000, "loss": 0.0, "lr": 4.8323759830629145e-05, "epoch": 82.28318584070796, "percentage": 11.72, "elapsed_time": "0:33:39", "remaining_time": "4:13:27", "throughput": 1319.29, "total_tokens": 2664808} {"current_steps": 4695, "total_steps": 40000, "loss": 0.0, "lr": 4.8320223691983066e-05, "epoch": 82.3716814159292, "percentage": 11.74, "elapsed_time": "0:33:41", "remaining_time": "4:13:24", "throughput": 1319.31, "total_tokens": 2667560} {"current_steps": 4700, "total_steps": 40000, "loss": 0.0, "lr": 4.831668395706544e-05, "epoch": 82.46017699115045, "percentage": 11.75, "elapsed_time": "0:33:44", "remaining_time": "4:13:21", "throughput": 1319.28, "total_tokens": 2670232} {"current_steps": 4705, "total_steps": 40000, "loss": 0.0, "lr": 4.8313140626422125e-05, "epoch": 82.54867256637168, "percentage": 11.76, "elapsed_time": "0:33:46", "remaining_time": "4:13:18", "throughput": 1319.54, "total_tokens": 2673512} {"current_steps": 4710, "total_steps": 40000, "loss": 0.0, "lr": 4.830959370059956e-05, "epoch": 82.63716814159292, "percentage": 11.77, "elapsed_time": "0:33:48", "remaining_time": "4:13:16", "throughput": 1319.66, "total_tokens": 2676472} {"current_steps": 4715, "total_steps": 40000, "loss": 0.0, "lr": 4.830604318014472e-05, "epoch": 82.72566371681415, "percentage": 11.79, "elapsed_time": "0:33:50", "remaining_time": "4:13:13", "throughput": 1319.92, "total_tokens": 2679736} {"current_steps": 4720, "total_steps": 40000, "loss": 0.0, "lr": 4.830248906560514e-05, "epoch": 82.8141592920354, "percentage": 11.8, "elapsed_time": "0:33:52", "remaining_time": "4:13:10", "throughput": 1319.93, "total_tokens": 2682456} {"current_steps": 4725, "total_steps": 40000, "loss": 0.0, "lr": 4.829893135752891e-05, "epoch": 82.90265486725664, "percentage": 11.81, "elapsed_time": "0:33:54", "remaining_time": "4:13:07", "throughput": 1320.27, "total_tokens": 2685880} {"current_steps": 4730, "total_steps": 40000, "loss": 0.0, "lr": 4.829537005646466e-05, "epoch": 82.99115044247787, "percentage": 11.82, "elapsed_time": "0:33:56", "remaining_time": "4:13:04", "throughput": 1320.37, "total_tokens": 2688776} {"current_steps": 4735, "total_steps": 40000, "loss": 0.0, "lr": 4.8291805162961615e-05, "epoch": 83.070796460177, "percentage": 11.84, "elapsed_time": "0:33:58", "remaining_time": "4:13:03", "throughput": 1320.01, "total_tokens": 2691032} {"current_steps": 4740, "total_steps": 40000, "loss": 0.0, "lr": 4.82882366775695e-05, "epoch": 83.15929203539822, "percentage": 11.85, "elapsed_time": "0:34:00", "remaining_time": "4:13:00", "throughput": 1319.95, "total_tokens": 2693656} {"current_steps": 4745, "total_steps": 40000, "loss": 0.0, "lr": 4.828466460083864e-05, "epoch": 83.24778761061947, "percentage": 11.86, "elapsed_time": "0:34:02", "remaining_time": "4:12:57", "throughput": 1319.89, "total_tokens": 2696248} {"current_steps": 4750, "total_steps": 40000, "loss": 0.0, "lr": 4.8281088933319877e-05, "epoch": 83.33628318584071, "percentage": 11.88, "elapsed_time": "0:34:04", "remaining_time": "4:12:54", "throughput": 1320.23, "total_tokens": 2699672} {"current_steps": 4755, "total_steps": 40000, "loss": 0.0, "lr": 4.827750967556464e-05, "epoch": 83.42477876106194, "percentage": 11.89, "elapsed_time": "0:34:06", "remaining_time": "4:12:52", "throughput": 1320.21, "total_tokens": 2702344} {"current_steps": 4760, "total_steps": 40000, "loss": 0.0, "lr": 4.827392682812488e-05, "epoch": 83.51327433628319, "percentage": 11.9, "elapsed_time": "0:34:08", "remaining_time": "4:12:49", "throughput": 1320.33, "total_tokens": 2705304} {"current_steps": 4765, "total_steps": 40000, "loss": 0.0, "lr": 4.827034039155312e-05, "epoch": 83.60176991150442, "percentage": 11.91, "elapsed_time": "0:34:11", "remaining_time": "4:12:46", "throughput": 1320.47, "total_tokens": 2708328} {"current_steps": 4770, "total_steps": 40000, "loss": 0.0, "lr": 4.8266750366402445e-05, "epoch": 83.69026548672566, "percentage": 11.92, "elapsed_time": "0:34:13", "remaining_time": "4:12:43", "throughput": 1320.62, "total_tokens": 2711352} {"current_steps": 4775, "total_steps": 40000, "loss": 0.0, "lr": 4.8263156753226476e-05, "epoch": 83.77876106194691, "percentage": 11.94, "elapsed_time": "0:34:15", "remaining_time": "4:12:40", "throughput": 1320.73, "total_tokens": 2714312} {"current_steps": 4780, "total_steps": 40000, "loss": 0.0, "lr": 4.8259559552579394e-05, "epoch": 83.86725663716814, "percentage": 11.95, "elapsed_time": "0:34:17", "remaining_time": "4:12:38", "throughput": 1320.98, "total_tokens": 2717544} {"current_steps": 4785, "total_steps": 40000, "loss": 0.0, "lr": 4.825595876501593e-05, "epoch": 83.95575221238938, "percentage": 11.96, "elapsed_time": "0:34:19", "remaining_time": "4:12:35", "throughput": 1321.02, "total_tokens": 2720344} {"current_steps": 4790, "total_steps": 40000, "loss": 0.0, "lr": 4.825235439109137e-05, "epoch": 84.03539823008849, "percentage": 11.97, "elapsed_time": "0:34:21", "remaining_time": "4:12:33", "throughput": 1320.8, "total_tokens": 2722840} {"current_steps": 4795, "total_steps": 40000, "loss": 0.0, "lr": 4.824874643136156e-05, "epoch": 84.12389380530973, "percentage": 11.99, "elapsed_time": "0:34:23", "remaining_time": "4:12:30", "throughput": 1320.84, "total_tokens": 2725656} {"current_steps": 4800, "total_steps": 40000, "loss": 0.0, "lr": 4.824513488638288e-05, "epoch": 84.21238938053098, "percentage": 12.0, "elapsed_time": "0:34:25", "remaining_time": "4:12:27", "throughput": 1320.9, "total_tokens": 2728488} {"current_steps": 4800, "total_steps": 40000, "eval_loss": 0.3679148554801941, "epoch": 84.21238938053098, "percentage": 12.0, "elapsed_time": "0:34:26", "remaining_time": "4:12:35", "throughput": 1320.22, "total_tokens": 2728488} {"current_steps": 4805, "total_steps": 40000, "loss": 0.0, "lr": 4.8241519756712293e-05, "epoch": 84.30088495575221, "percentage": 12.01, "elapsed_time": "0:34:30", "remaining_time": "4:12:44", "throughput": 1319.13, "total_tokens": 2731112} {"current_steps": 4810, "total_steps": 40000, "loss": 0.0, "lr": 4.8237901042907285e-05, "epoch": 84.38938053097345, "percentage": 12.03, "elapsed_time": "0:34:32", "remaining_time": "4:12:42", "throughput": 1319.37, "total_tokens": 2734328} {"current_steps": 4815, "total_steps": 40000, "loss": 0.0, "lr": 4.823427874552591e-05, "epoch": 84.47787610619469, "percentage": 12.04, "elapsed_time": "0:34:34", "remaining_time": "4:12:39", "throughput": 1319.48, "total_tokens": 2737272} {"current_steps": 4820, "total_steps": 40000, "loss": 0.0, "lr": 4.823065286512677e-05, "epoch": 84.56637168141593, "percentage": 12.05, "elapsed_time": "0:34:36", "remaining_time": "4:12:36", "throughput": 1319.5, "total_tokens": 2740040} {"current_steps": 4825, "total_steps": 40000, "loss": 0.0, "lr": 4.8227023402269025e-05, "epoch": 84.65486725663717, "percentage": 12.06, "elapsed_time": "0:34:38", "remaining_time": "4:12:33", "throughput": 1319.67, "total_tokens": 2743128} {"current_steps": 4830, "total_steps": 40000, "loss": 0.0, "lr": 4.822339035751239e-05, "epoch": 84.7433628318584, "percentage": 12.07, "elapsed_time": "0:34:40", "remaining_time": "4:12:30", "throughput": 1319.58, "total_tokens": 2745656} {"current_steps": 4835, "total_steps": 40000, "loss": 0.0, "lr": 4.8219753731417104e-05, "epoch": 84.83185840707965, "percentage": 12.09, "elapsed_time": "0:34:42", "remaining_time": "4:12:28", "throughput": 1319.45, "total_tokens": 2748120} {"current_steps": 4840, "total_steps": 40000, "loss": 0.0, "lr": 4.821611352454401e-05, "epoch": 84.92035398230088, "percentage": 12.1, "elapsed_time": "0:34:44", "remaining_time": "4:12:25", "throughput": 1319.78, "total_tokens": 2751528} {"current_steps": 4845, "total_steps": 40000, "loss": 0.0, "lr": 4.8212469737454444e-05, "epoch": 85.0, "percentage": 12.11, "elapsed_time": "0:34:46", "remaining_time": "4:12:22", "throughput": 1319.69, "total_tokens": 2754000} {"current_steps": 4850, "total_steps": 40000, "loss": 0.0, "lr": 4.820882237071035e-05, "epoch": 85.08849557522124, "percentage": 12.12, "elapsed_time": "0:34:49", "remaining_time": "4:12:20", "throughput": 1319.67, "total_tokens": 2756992} {"current_steps": 4855, "total_steps": 40000, "loss": 0.0, "lr": 4.820517142487417e-05, "epoch": 85.17699115044248, "percentage": 12.14, "elapsed_time": "0:34:51", "remaining_time": "4:12:18", "throughput": 1319.8, "total_tokens": 2760000} {"current_steps": 4860, "total_steps": 40000, "loss": 0.0, "lr": 4.8201516900508956e-05, "epoch": 85.26548672566372, "percentage": 12.15, "elapsed_time": "0:34:53", "remaining_time": "4:12:15", "throughput": 1319.79, "total_tokens": 2762704} {"current_steps": 4865, "total_steps": 40000, "loss": 0.0, "lr": 4.819785879817827e-05, "epoch": 85.35398230088495, "percentage": 12.16, "elapsed_time": "0:34:55", "remaining_time": "4:12:12", "throughput": 1319.86, "total_tokens": 2765568} {"current_steps": 4870, "total_steps": 40000, "loss": 0.0, "lr": 4.8194197118446226e-05, "epoch": 85.4424778761062, "percentage": 12.17, "elapsed_time": "0:34:57", "remaining_time": "4:12:09", "throughput": 1320.01, "total_tokens": 2768592} {"current_steps": 4875, "total_steps": 40000, "loss": 0.0, "lr": 4.819053186187752e-05, "epoch": 85.53097345132744, "percentage": 12.19, "elapsed_time": "0:34:59", "remaining_time": "4:12:06", "throughput": 1320.1, "total_tokens": 2771504} {"current_steps": 4880, "total_steps": 40000, "loss": 0.0, "lr": 4.818686302903736e-05, "epoch": 85.61946902654867, "percentage": 12.2, "elapsed_time": "0:35:01", "remaining_time": "4:12:04", "throughput": 1320.27, "total_tokens": 2774592} {"current_steps": 4885, "total_steps": 40000, "loss": 0.0, "lr": 4.818319062049154e-05, "epoch": 85.70796460176992, "percentage": 12.21, "elapsed_time": "0:35:03", "remaining_time": "4:12:01", "throughput": 1320.38, "total_tokens": 2777552} {"current_steps": 4890, "total_steps": 40000, "loss": 0.0, "lr": 4.817951463680639e-05, "epoch": 85.79646017699115, "percentage": 12.22, "elapsed_time": "0:35:05", "remaining_time": "4:11:58", "throughput": 1320.38, "total_tokens": 2780272} {"current_steps": 4895, "total_steps": 40000, "loss": 0.0, "lr": 4.817583507854879e-05, "epoch": 85.88495575221239, "percentage": 12.24, "elapsed_time": "0:35:07", "remaining_time": "4:11:55", "throughput": 1320.39, "total_tokens": 2783008} {"current_steps": 4900, "total_steps": 40000, "loss": 0.0, "lr": 4.817215194628617e-05, "epoch": 85.97345132743362, "percentage": 12.25, "elapsed_time": "0:35:09", "remaining_time": "4:11:52", "throughput": 1320.49, "total_tokens": 2785936} {"current_steps": 4905, "total_steps": 40000, "loss": 0.0, "lr": 4.816846524058653e-05, "epoch": 86.05309734513274, "percentage": 12.26, "elapsed_time": "0:35:12", "remaining_time": "4:11:51", "throughput": 1320.14, "total_tokens": 2788192} {"current_steps": 4910, "total_steps": 40000, "loss": 0.0, "lr": 4.816477496201839e-05, "epoch": 86.14159292035399, "percentage": 12.28, "elapsed_time": "0:35:14", "remaining_time": "4:11:48", "throughput": 1320.35, "total_tokens": 2791344} {"current_steps": 4915, "total_steps": 40000, "loss": 0.0, "lr": 4.8161081111150845e-05, "epoch": 86.23008849557522, "percentage": 12.29, "elapsed_time": "0:35:16", "remaining_time": "4:11:45", "throughput": 1320.21, "total_tokens": 2793792} {"current_steps": 4920, "total_steps": 40000, "loss": 0.0, "lr": 4.815738368855354e-05, "epoch": 86.31858407079646, "percentage": 12.3, "elapsed_time": "0:35:18", "remaining_time": "4:11:43", "throughput": 1320.11, "total_tokens": 2796320} {"current_steps": 4925, "total_steps": 40000, "loss": 0.0, "lr": 4.815368269479664e-05, "epoch": 86.40707964601769, "percentage": 12.31, "elapsed_time": "0:35:20", "remaining_time": "4:11:40", "throughput": 1320.27, "total_tokens": 2799360} {"current_steps": 4930, "total_steps": 40000, "loss": 0.0, "lr": 4.814997813045092e-05, "epoch": 86.49557522123894, "percentage": 12.32, "elapsed_time": "0:35:22", "remaining_time": "4:11:37", "throughput": 1320.14, "total_tokens": 2801824} {"current_steps": 4935, "total_steps": 40000, "loss": 0.0, "lr": 4.814626999608764e-05, "epoch": 86.58407079646018, "percentage": 12.34, "elapsed_time": "0:35:24", "remaining_time": "4:11:34", "throughput": 1320.22, "total_tokens": 2804704} {"current_steps": 4940, "total_steps": 40000, "loss": 0.0, "lr": 4.814255829227865e-05, "epoch": 86.67256637168141, "percentage": 12.35, "elapsed_time": "0:35:26", "remaining_time": "4:11:32", "throughput": 1320.22, "total_tokens": 2807424} {"current_steps": 4945, "total_steps": 40000, "loss": 0.0, "lr": 4.813884301959635e-05, "epoch": 86.76106194690266, "percentage": 12.36, "elapsed_time": "0:35:28", "remaining_time": "4:11:29", "throughput": 1320.29, "total_tokens": 2810304} {"current_steps": 4950, "total_steps": 40000, "loss": 0.0, "lr": 4.813512417861368e-05, "epoch": 86.84955752212389, "percentage": 12.38, "elapsed_time": "0:35:30", "remaining_time": "4:11:26", "throughput": 1320.43, "total_tokens": 2813328} {"current_steps": 4955, "total_steps": 40000, "loss": 0.0, "lr": 4.813140176990411e-05, "epoch": 86.93805309734513, "percentage": 12.39, "elapsed_time": "0:35:32", "remaining_time": "4:11:23", "throughput": 1320.61, "total_tokens": 2816432} {"current_steps": 4960, "total_steps": 40000, "loss": 0.0, "lr": 4.8127675794041714e-05, "epoch": 87.01769911504425, "percentage": 12.4, "elapsed_time": "0:35:34", "remaining_time": "4:11:22", "throughput": 1320.54, "total_tokens": 2819264} {"current_steps": 4965, "total_steps": 40000, "loss": 0.0, "lr": 4.812394625160107e-05, "epoch": 87.10619469026548, "percentage": 12.41, "elapsed_time": "0:35:36", "remaining_time": "4:11:19", "throughput": 1320.54, "total_tokens": 2821984} {"current_steps": 4970, "total_steps": 40000, "loss": 0.0, "lr": 4.812021314315732e-05, "epoch": 87.19469026548673, "percentage": 12.43, "elapsed_time": "0:35:39", "remaining_time": "4:11:16", "throughput": 1320.58, "total_tokens": 2824784} {"current_steps": 4975, "total_steps": 40000, "loss": 0.0, "lr": 4.811647646928616e-05, "epoch": 87.28318584070796, "percentage": 12.44, "elapsed_time": "0:35:41", "remaining_time": "4:11:13", "throughput": 1320.55, "total_tokens": 2827456} {"current_steps": 4980, "total_steps": 40000, "loss": 0.0, "lr": 4.8112736230563814e-05, "epoch": 87.3716814159292, "percentage": 12.45, "elapsed_time": "0:35:43", "remaining_time": "4:11:11", "throughput": 1320.75, "total_tokens": 2830592} {"current_steps": 4985, "total_steps": 40000, "loss": 0.0, "lr": 4.81089924275671e-05, "epoch": 87.46017699115045, "percentage": 12.46, "elapsed_time": "0:35:45", "remaining_time": "4:11:08", "throughput": 1320.75, "total_tokens": 2833328} {"current_steps": 4990, "total_steps": 40000, "loss": 0.0, "lr": 4.810524506087335e-05, "epoch": 87.54867256637168, "percentage": 12.47, "elapsed_time": "0:35:47", "remaining_time": "4:11:05", "throughput": 1321.07, "total_tokens": 2836752} {"current_steps": 4995, "total_steps": 40000, "loss": 0.0, "lr": 4.810149413106044e-05, "epoch": 87.63716814159292, "percentage": 12.49, "elapsed_time": "0:35:49", "remaining_time": "4:11:02", "throughput": 1321.32, "total_tokens": 2840000} {"current_steps": 5000, "total_steps": 40000, "loss": 0.0, "lr": 4.809773963870684e-05, "epoch": 87.72566371681415, "percentage": 12.5, "elapsed_time": "0:35:51", "remaining_time": "4:10:59", "throughput": 1321.29, "total_tokens": 2842656} {"current_steps": 5000, "total_steps": 40000, "eval_loss": 0.3791765868663788, "epoch": 87.72566371681415, "percentage": 12.5, "elapsed_time": "0:35:52", "remaining_time": "4:11:07", "throughput": 1320.64, "total_tokens": 2842656} {"current_steps": 5005, "total_steps": 40000, "loss": 0.0, "lr": 4.809398158439151e-05, "epoch": 87.8141592920354, "percentage": 12.51, "elapsed_time": "0:35:56", "remaining_time": "4:11:17", "throughput": 1319.51, "total_tokens": 2845328} {"current_steps": 5010, "total_steps": 40000, "loss": 0.0, "lr": 4.8090219968694005e-05, "epoch": 87.90265486725664, "percentage": 12.53, "elapsed_time": "0:35:58", "remaining_time": "4:11:14", "throughput": 1319.74, "total_tokens": 2848560} {"current_steps": 5015, "total_steps": 40000, "loss": 0.0, "lr": 4.808645479219442e-05, "epoch": 87.99115044247787, "percentage": 12.54, "elapsed_time": "0:36:00", "remaining_time": "4:11:11", "throughput": 1319.71, "total_tokens": 2851200} {"current_steps": 5020, "total_steps": 40000, "loss": 0.0, "lr": 4.8082686055473375e-05, "epoch": 88.070796460177, "percentage": 12.55, "elapsed_time": "0:36:02", "remaining_time": "4:11:10", "throughput": 1319.34, "total_tokens": 2853392} {"current_steps": 5025, "total_steps": 40000, "loss": 0.0, "lr": 4.8078913759112066e-05, "epoch": 88.15929203539822, "percentage": 12.56, "elapsed_time": "0:36:04", "remaining_time": "4:11:07", "throughput": 1319.3, "total_tokens": 2856016} {"current_steps": 5030, "total_steps": 40000, "loss": 0.0, "lr": 4.807513790369223e-05, "epoch": 88.24778761061947, "percentage": 12.57, "elapsed_time": "0:36:06", "remaining_time": "4:11:04", "throughput": 1319.47, "total_tokens": 2859104} {"current_steps": 5035, "total_steps": 40000, "loss": 0.0, "lr": 4.8071358489796145e-05, "epoch": 88.33628318584071, "percentage": 12.59, "elapsed_time": "0:36:08", "remaining_time": "4:11:01", "throughput": 1319.56, "total_tokens": 2862016} {"current_steps": 5040, "total_steps": 40000, "loss": 0.0, "lr": 4.806757551800665e-05, "epoch": 88.42477876106194, "percentage": 12.6, "elapsed_time": "0:36:10", "remaining_time": "4:10:59", "throughput": 1319.59, "total_tokens": 2864800} {"current_steps": 5045, "total_steps": 40000, "loss": 0.0, "lr": 4.806378898890713e-05, "epoch": 88.51327433628319, "percentage": 12.61, "elapsed_time": "0:36:13", "remaining_time": "4:10:56", "throughput": 1319.48, "total_tokens": 2867296} {"current_steps": 5050, "total_steps": 40000, "loss": 0.0, "lr": 4.80599989030815e-05, "epoch": 88.60176991150442, "percentage": 12.62, "elapsed_time": "0:36:15", "remaining_time": "4:10:53", "throughput": 1319.74, "total_tokens": 2870608} {"current_steps": 5055, "total_steps": 40000, "loss": 0.0, "lr": 4.805620526111426e-05, "epoch": 88.69026548672566, "percentage": 12.64, "elapsed_time": "0:36:17", "remaining_time": "4:10:50", "throughput": 1319.81, "total_tokens": 2873472} {"current_steps": 5060, "total_steps": 40000, "loss": 0.0, "lr": 4.805240806359042e-05, "epoch": 88.77876106194691, "percentage": 12.65, "elapsed_time": "0:36:19", "remaining_time": "4:10:48", "throughput": 1319.99, "total_tokens": 2876592} {"current_steps": 5065, "total_steps": 40000, "loss": 0.0, "lr": 4.804860731109557e-05, "epoch": 88.86725663716814, "percentage": 12.66, "elapsed_time": "0:36:21", "remaining_time": "4:10:45", "throughput": 1320.05, "total_tokens": 2879440} {"current_steps": 5070, "total_steps": 40000, "loss": 0.0, "lr": 4.804480300421581e-05, "epoch": 88.95575221238938, "percentage": 12.68, "elapsed_time": "0:36:23", "remaining_time": "4:10:42", "throughput": 1320.23, "total_tokens": 2882560} {"current_steps": 5075, "total_steps": 40000, "loss": 0.0, "lr": 4.804099514353784e-05, "epoch": 89.03539823008849, "percentage": 12.69, "elapsed_time": "0:36:25", "remaining_time": "4:10:41", "throughput": 1319.9, "total_tokens": 2884808} {"current_steps": 5080, "total_steps": 40000, "loss": 0.0, "lr": 4.8037183729648867e-05, "epoch": 89.12389380530973, "percentage": 12.7, "elapsed_time": "0:36:27", "remaining_time": "4:10:38", "throughput": 1319.94, "total_tokens": 2887656} {"current_steps": 5085, "total_steps": 40000, "loss": 0.0, "lr": 4.803336876313666e-05, "epoch": 89.21238938053098, "percentage": 12.71, "elapsed_time": "0:36:29", "remaining_time": "4:10:35", "throughput": 1320.02, "total_tokens": 2890552} {"current_steps": 5090, "total_steps": 40000, "loss": 0.0, "lr": 4.802955024458953e-05, "epoch": 89.30088495575221, "percentage": 12.72, "elapsed_time": "0:36:31", "remaining_time": "4:10:32", "throughput": 1320.02, "total_tokens": 2893288} {"current_steps": 5095, "total_steps": 40000, "loss": 0.0, "lr": 4.802572817459634e-05, "epoch": 89.38938053097345, "percentage": 12.74, "elapsed_time": "0:36:33", "remaining_time": "4:10:30", "throughput": 1320.02, "total_tokens": 2896008} {"current_steps": 5100, "total_steps": 40000, "loss": 0.0, "lr": 4.802190255374651e-05, "epoch": 89.47787610619469, "percentage": 12.75, "elapsed_time": "0:36:35", "remaining_time": "4:10:27", "throughput": 1320.19, "total_tokens": 2899096} {"current_steps": 5105, "total_steps": 40000, "loss": 0.0, "lr": 4.801807338263e-05, "epoch": 89.56637168141593, "percentage": 12.76, "elapsed_time": "0:36:38", "remaining_time": "4:10:24", "throughput": 1320.07, "total_tokens": 2901544} {"current_steps": 5110, "total_steps": 40000, "loss": 0.0, "lr": 4.8014240661837306e-05, "epoch": 89.65486725663717, "percentage": 12.78, "elapsed_time": "0:36:40", "remaining_time": "4:10:21", "throughput": 1320.23, "total_tokens": 2904632} {"current_steps": 5115, "total_steps": 40000, "loss": 0.0, "lr": 4.80104043919595e-05, "epoch": 89.7433628318584, "percentage": 12.79, "elapsed_time": "0:36:42", "remaining_time": "4:10:18", "throughput": 1320.52, "total_tokens": 2907992} {"current_steps": 5120, "total_steps": 40000, "loss": 0.0, "lr": 4.800656457358815e-05, "epoch": 89.83185840707965, "percentage": 12.8, "elapsed_time": "0:36:44", "remaining_time": "4:10:16", "throughput": 1320.74, "total_tokens": 2911192} {"current_steps": 5125, "total_steps": 40000, "loss": 0.0, "lr": 4.800272120731544e-05, "epoch": 89.92035398230088, "percentage": 12.81, "elapsed_time": "0:36:46", "remaining_time": "4:10:13", "throughput": 1320.73, "total_tokens": 2913912} {"current_steps": 5130, "total_steps": 40000, "loss": 0.0, "lr": 4.799887429373404e-05, "epoch": 90.0, "percentage": 12.83, "elapsed_time": "0:36:48", "remaining_time": "4:10:10", "throughput": 1320.68, "total_tokens": 2916440} {"current_steps": 5135, "total_steps": 40000, "loss": 0.0, "lr": 4.79950238334372e-05, "epoch": 90.08849557522124, "percentage": 12.84, "elapsed_time": "0:36:50", "remaining_time": "4:10:09", "throughput": 1320.46, "total_tokens": 2919000} {"current_steps": 5140, "total_steps": 40000, "loss": 0.0, "lr": 4.799116982701872e-05, "epoch": 90.17699115044248, "percentage": 12.85, "elapsed_time": "0:36:52", "remaining_time": "4:10:06", "throughput": 1320.82, "total_tokens": 2922520} {"current_steps": 5145, "total_steps": 40000, "loss": 0.0, "lr": 4.7987312275072926e-05, "epoch": 90.26548672566372, "percentage": 12.86, "elapsed_time": "0:36:54", "remaining_time": "4:10:03", "throughput": 1320.78, "total_tokens": 2925144} {"current_steps": 5150, "total_steps": 40000, "loss": 0.0, "lr": 4.79834511781947e-05, "epoch": 90.35398230088495, "percentage": 12.88, "elapsed_time": "0:36:56", "remaining_time": "4:10:00", "throughput": 1320.94, "total_tokens": 2928216} {"current_steps": 5155, "total_steps": 40000, "loss": 0.0, "lr": 4.797958653697947e-05, "epoch": 90.4424778761062, "percentage": 12.89, "elapsed_time": "0:36:58", "remaining_time": "4:09:58", "throughput": 1321.15, "total_tokens": 2931416} {"current_steps": 5160, "total_steps": 40000, "loss": 0.0, "lr": 4.7975718352023225e-05, "epoch": 90.53097345132744, "percentage": 12.9, "elapsed_time": "0:37:00", "remaining_time": "4:09:55", "throughput": 1321.24, "total_tokens": 2934360} {"current_steps": 5165, "total_steps": 40000, "loss": 0.0, "lr": 4.7971846623922476e-05, "epoch": 90.61946902654867, "percentage": 12.91, "elapsed_time": "0:37:02", "remaining_time": "4:09:52", "throughput": 1321.25, "total_tokens": 2937096} {"current_steps": 5170, "total_steps": 40000, "loss": 0.0, "lr": 4.7967971353274294e-05, "epoch": 90.70796460176992, "percentage": 12.93, "elapsed_time": "0:37:05", "remaining_time": "4:09:49", "throughput": 1321.2, "total_tokens": 2939720} {"current_steps": 5175, "total_steps": 40000, "loss": 0.0, "lr": 4.79640925406763e-05, "epoch": 90.79646017699115, "percentage": 12.94, "elapsed_time": "0:37:07", "remaining_time": "4:09:47", "throughput": 1321.3, "total_tokens": 2942648} {"current_steps": 5180, "total_steps": 40000, "loss": 0.0, "lr": 4.796021018672664e-05, "epoch": 90.88495575221239, "percentage": 12.95, "elapsed_time": "0:37:09", "remaining_time": "4:09:44", "throughput": 1321.14, "total_tokens": 2945032} {"current_steps": 5185, "total_steps": 40000, "loss": 0.0, "lr": 4.795632429202405e-05, "epoch": 90.97345132743362, "percentage": 12.96, "elapsed_time": "0:37:11", "remaining_time": "4:09:41", "throughput": 1321.34, "total_tokens": 2948184} {"current_steps": 5190, "total_steps": 40000, "loss": 0.0, "lr": 4.795243485716775e-05, "epoch": 91.05309734513274, "percentage": 12.97, "elapsed_time": "0:37:13", "remaining_time": "4:09:40", "throughput": 1321.11, "total_tokens": 2950648} {"current_steps": 5195, "total_steps": 40000, "loss": 0.0, "lr": 4.794854188275757e-05, "epoch": 91.14159292035399, "percentage": 12.99, "elapsed_time": "0:37:15", "remaining_time": "4:09:37", "throughput": 1321.42, "total_tokens": 2954088} {"current_steps": 5200, "total_steps": 40000, "loss": 0.0, "lr": 4.794464536939384e-05, "epoch": 91.23008849557522, "percentage": 13.0, "elapsed_time": "0:37:17", "remaining_time": "4:09:34", "throughput": 1321.43, "total_tokens": 2956824} {"current_steps": 5200, "total_steps": 40000, "eval_loss": 0.3791448175907135, "epoch": 91.23008849557522, "percentage": 13.0, "elapsed_time": "0:37:18", "remaining_time": "4:09:41", "throughput": 1320.8, "total_tokens": 2956824} {"current_steps": 5205, "total_steps": 40000, "loss": 0.0, "lr": 4.794074531767745e-05, "epoch": 91.31858407079646, "percentage": 13.01, "elapsed_time": "0:37:22", "remaining_time": "4:09:50", "throughput": 1319.79, "total_tokens": 2959496} {"current_steps": 5210, "total_steps": 40000, "loss": 0.0, "lr": 4.7936841728209834e-05, "epoch": 91.40707964601769, "percentage": 13.03, "elapsed_time": "0:37:24", "remaining_time": "4:09:47", "throughput": 1320.03, "total_tokens": 2962744} {"current_steps": 5215, "total_steps": 40000, "loss": 0.0, "lr": 4.7932934601593e-05, "epoch": 91.49557522123894, "percentage": 13.04, "elapsed_time": "0:37:26", "remaining_time": "4:09:44", "throughput": 1320.08, "total_tokens": 2965576} {"current_steps": 5220, "total_steps": 40000, "loss": 0.0, "lr": 4.792902393842943e-05, "epoch": 91.58407079646018, "percentage": 13.05, "elapsed_time": "0:37:28", "remaining_time": "4:09:41", "throughput": 1320.06, "total_tokens": 2968264} {"current_steps": 5225, "total_steps": 40000, "loss": 0.0, "lr": 4.792510973932225e-05, "epoch": 91.67256637168141, "percentage": 13.06, "elapsed_time": "0:37:30", "remaining_time": "4:09:39", "throughput": 1320.06, "total_tokens": 2971000} {"current_steps": 5230, "total_steps": 40000, "loss": 0.0, "lr": 4.7921192004875036e-05, "epoch": 91.76106194690266, "percentage": 13.08, "elapsed_time": "0:37:32", "remaining_time": "4:09:36", "throughput": 1320.01, "total_tokens": 2973608} {"current_steps": 5235, "total_steps": 40000, "loss": 0.0, "lr": 4.791727073569198e-05, "epoch": 91.84955752212389, "percentage": 13.09, "elapsed_time": "0:37:34", "remaining_time": "4:09:33", "throughput": 1319.94, "total_tokens": 2976184} {"current_steps": 5240, "total_steps": 40000, "loss": 0.0, "lr": 4.7913345932377775e-05, "epoch": 91.93805309734513, "percentage": 13.1, "elapsed_time": "0:37:36", "remaining_time": "4:09:30", "throughput": 1320.08, "total_tokens": 2979208} {"current_steps": 5245, "total_steps": 40000, "loss": 0.0, "lr": 4.790941759553769e-05, "epoch": 92.01769911504425, "percentage": 13.11, "elapsed_time": "0:37:39", "remaining_time": "4:09:29", "throughput": 1319.93, "total_tokens": 2981840} {"current_steps": 5250, "total_steps": 40000, "loss": 0.0, "lr": 4.79054857257775e-05, "epoch": 92.10619469026548, "percentage": 13.12, "elapsed_time": "0:37:41", "remaining_time": "4:09:26", "throughput": 1319.88, "total_tokens": 2984448} {"current_steps": 5255, "total_steps": 40000, "loss": 0.0, "lr": 4.790155032370357e-05, "epoch": 92.19469026548673, "percentage": 13.14, "elapsed_time": "0:37:43", "remaining_time": "4:09:23", "throughput": 1319.97, "total_tokens": 2987360} {"current_steps": 5260, "total_steps": 40000, "loss": 0.0, "lr": 4.789761138992278e-05, "epoch": 92.28318584070796, "percentage": 13.15, "elapsed_time": "0:37:45", "remaining_time": "4:09:21", "throughput": 1319.94, "total_tokens": 2990048} {"current_steps": 5265, "total_steps": 40000, "loss": 0.0, "lr": 4.7893668925042565e-05, "epoch": 92.3716814159292, "percentage": 13.16, "elapsed_time": "0:37:47", "remaining_time": "4:09:18", "throughput": 1320.04, "total_tokens": 2992992} {"current_steps": 5270, "total_steps": 40000, "loss": 0.0, "lr": 4.78897229296709e-05, "epoch": 92.46017699115045, "percentage": 13.18, "elapsed_time": "0:37:49", "remaining_time": "4:09:15", "throughput": 1320.09, "total_tokens": 2995824} {"current_steps": 5275, "total_steps": 40000, "loss": 0.0, "lr": 4.7885773404416315e-05, "epoch": 92.54867256637168, "percentage": 13.19, "elapsed_time": "0:37:51", "remaining_time": "4:09:12", "throughput": 1320.16, "total_tokens": 2998688} {"current_steps": 5280, "total_steps": 40000, "loss": 0.0, "lr": 4.788182034988786e-05, "epoch": 92.63716814159292, "percentage": 13.2, "elapsed_time": "0:37:53", "remaining_time": "4:09:10", "throughput": 1320.08, "total_tokens": 3001248} {"current_steps": 5285, "total_steps": 40000, "loss": 0.0, "lr": 4.787786376669516e-05, "epoch": 92.72566371681415, "percentage": 13.21, "elapsed_time": "0:37:55", "remaining_time": "4:09:07", "throughput": 1320.03, "total_tokens": 3003856} {"current_steps": 5290, "total_steps": 40000, "loss": 0.0, "lr": 4.787390365544837e-05, "epoch": 92.8141592920354, "percentage": 13.23, "elapsed_time": "0:37:57", "remaining_time": "4:09:04", "throughput": 1320.31, "total_tokens": 3007216} {"current_steps": 5295, "total_steps": 40000, "loss": 0.0, "lr": 4.786994001675818e-05, "epoch": 92.90265486725664, "percentage": 13.24, "elapsed_time": "0:37:59", "remaining_time": "4:09:01", "throughput": 1320.53, "total_tokens": 3010432} {"current_steps": 5300, "total_steps": 40000, "loss": 0.0, "lr": 4.786597285123584e-05, "epoch": 92.99115044247787, "percentage": 13.25, "elapsed_time": "0:38:01", "remaining_time": "4:08:59", "throughput": 1320.49, "total_tokens": 3013056} {"current_steps": 5305, "total_steps": 40000, "loss": 0.0, "lr": 4.7862002159493135e-05, "epoch": 93.070796460177, "percentage": 13.26, "elapsed_time": "0:38:04", "remaining_time": "4:08:57", "throughput": 1320.36, "total_tokens": 3015736} {"current_steps": 5310, "total_steps": 40000, "loss": 0.0, "lr": 4.785802794214239e-05, "epoch": 93.15929203539822, "percentage": 13.28, "elapsed_time": "0:38:06", "remaining_time": "4:08:54", "throughput": 1320.4, "total_tokens": 3018552} {"current_steps": 5315, "total_steps": 40000, "loss": 0.0, "lr": 4.7854050199796495e-05, "epoch": 93.24778761061947, "percentage": 13.29, "elapsed_time": "0:38:08", "remaining_time": "4:08:52", "throughput": 1320.45, "total_tokens": 3021416} {"current_steps": 5320, "total_steps": 40000, "loss": 0.0, "lr": 4.7850068933068845e-05, "epoch": 93.33628318584071, "percentage": 13.3, "elapsed_time": "0:38:10", "remaining_time": "4:08:49", "throughput": 1320.47, "total_tokens": 3024168} {"current_steps": 5325, "total_steps": 40000, "loss": 0.0, "lr": 4.7846084142573425e-05, "epoch": 93.42477876106194, "percentage": 13.31, "elapsed_time": "0:38:12", "remaining_time": "4:08:46", "throughput": 1320.45, "total_tokens": 3026856} {"current_steps": 5330, "total_steps": 40000, "loss": 0.0, "lr": 4.7842095828924725e-05, "epoch": 93.51327433628319, "percentage": 13.33, "elapsed_time": "0:38:14", "remaining_time": "4:08:44", "throughput": 1320.58, "total_tokens": 3029864} {"current_steps": 5335, "total_steps": 40000, "loss": 0.0, "lr": 4.783810399273779e-05, "epoch": 93.60176991150442, "percentage": 13.34, "elapsed_time": "0:38:16", "remaining_time": "4:08:41", "throughput": 1320.7, "total_tokens": 3032888} {"current_steps": 5340, "total_steps": 40000, "loss": 0.0, "lr": 4.7834108634628226e-05, "epoch": 93.69026548672566, "percentage": 13.35, "elapsed_time": "0:38:18", "remaining_time": "4:08:38", "throughput": 1320.69, "total_tokens": 3035608} {"current_steps": 5345, "total_steps": 40000, "loss": 0.0, "lr": 4.783010975521216e-05, "epoch": 93.77876106194691, "percentage": 13.36, "elapsed_time": "0:38:20", "remaining_time": "4:08:35", "throughput": 1320.78, "total_tokens": 3038536} {"current_steps": 5350, "total_steps": 40000, "loss": 0.0, "lr": 4.782610735510626e-05, "epoch": 93.86725663716814, "percentage": 13.38, "elapsed_time": "0:38:22", "remaining_time": "4:08:33", "throughput": 1320.64, "total_tokens": 3040920} {"current_steps": 5355, "total_steps": 40000, "loss": 0.0, "lr": 4.782210143492776e-05, "epoch": 93.95575221238938, "percentage": 13.39, "elapsed_time": "0:38:24", "remaining_time": "4:08:30", "throughput": 1320.66, "total_tokens": 3043688} {"current_steps": 5360, "total_steps": 40000, "loss": 0.0, "lr": 4.781809199529442e-05, "epoch": 94.03539823008849, "percentage": 13.4, "elapsed_time": "0:38:26", "remaining_time": "4:08:28", "throughput": 1320.48, "total_tokens": 3046240} {"current_steps": 5365, "total_steps": 40000, "loss": 0.0, "lr": 4.781407903682454e-05, "epoch": 94.12389380530973, "percentage": 13.41, "elapsed_time": "0:38:28", "remaining_time": "4:08:26", "throughput": 1320.53, "total_tokens": 3049072} {"current_steps": 5370, "total_steps": 40000, "loss": 0.0, "lr": 4.781006256013698e-05, "epoch": 94.21238938053098, "percentage": 13.43, "elapsed_time": "0:38:31", "remaining_time": "4:08:23", "throughput": 1320.6, "total_tokens": 3052000} {"current_steps": 5375, "total_steps": 40000, "loss": 0.0, "lr": 4.7806042565851115e-05, "epoch": 94.30088495575221, "percentage": 13.44, "elapsed_time": "0:38:33", "remaining_time": "4:08:20", "throughput": 1320.62, "total_tokens": 3054752} {"current_steps": 5380, "total_steps": 40000, "loss": 0.0, "lr": 4.7802019054586895e-05, "epoch": 94.38938053097345, "percentage": 13.45, "elapsed_time": "0:38:35", "remaining_time": "4:08:18", "throughput": 1320.76, "total_tokens": 3057792} {"current_steps": 5385, "total_steps": 40000, "loss": 0.0, "lr": 4.779799202696479e-05, "epoch": 94.47787610619469, "percentage": 13.46, "elapsed_time": "0:38:37", "remaining_time": "4:08:15", "throughput": 1320.93, "total_tokens": 3060912} {"current_steps": 5390, "total_steps": 40000, "loss": 0.0, "lr": 4.779396148360581e-05, "epoch": 94.56637168141593, "percentage": 13.48, "elapsed_time": "0:38:39", "remaining_time": "4:08:12", "throughput": 1321.13, "total_tokens": 3064096} {"current_steps": 5395, "total_steps": 40000, "loss": 0.0, "lr": 4.7789927425131517e-05, "epoch": 94.65486725663717, "percentage": 13.49, "elapsed_time": "0:38:41", "remaining_time": "4:08:09", "throughput": 1321.16, "total_tokens": 3066896} {"current_steps": 5400, "total_steps": 40000, "loss": 0.0, "lr": 4.778588985216403e-05, "epoch": 94.7433628318584, "percentage": 13.5, "elapsed_time": "0:38:43", "remaining_time": "4:08:07", "throughput": 1321.25, "total_tokens": 3069840} {"current_steps": 5400, "total_steps": 40000, "eval_loss": 0.40042489767074585, "epoch": 94.7433628318584, "percentage": 13.5, "elapsed_time": "0:38:44", "remaining_time": "4:08:14", "throughput": 1320.65, "total_tokens": 3069840} {"current_steps": 5405, "total_steps": 40000, "loss": 0.0, "lr": 4.778184876532598e-05, "epoch": 94.83185840707965, "percentage": 13.51, "elapsed_time": "0:38:48", "remaining_time": "4:08:22", "throughput": 1319.56, "total_tokens": 3072432} {"current_steps": 5410, "total_steps": 40000, "loss": 0.0, "lr": 4.7777804165240556e-05, "epoch": 94.92035398230088, "percentage": 13.53, "elapsed_time": "0:38:50", "remaining_time": "4:08:20", "throughput": 1319.55, "total_tokens": 3075152} {"current_steps": 5415, "total_steps": 40000, "loss": 0.0, "lr": 4.7773756052531485e-05, "epoch": 95.0, "percentage": 13.54, "elapsed_time": "0:38:52", "remaining_time": "4:08:17", "throughput": 1319.48, "total_tokens": 3077616} {"current_steps": 5420, "total_steps": 40000, "loss": 0.0, "lr": 4.7769704427823035e-05, "epoch": 95.08849557522124, "percentage": 13.55, "elapsed_time": "0:38:54", "remaining_time": "4:08:15", "throughput": 1319.33, "total_tokens": 3080304} {"current_steps": 5425, "total_steps": 40000, "loss": 0.0, "lr": 4.776564929174003e-05, "epoch": 95.17699115044248, "percentage": 13.56, "elapsed_time": "0:38:56", "remaining_time": "4:08:13", "throughput": 1319.38, "total_tokens": 3083168} {"current_steps": 5430, "total_steps": 40000, "loss": 0.0, "lr": 4.7761590644907806e-05, "epoch": 95.26548672566372, "percentage": 13.58, "elapsed_time": "0:38:58", "remaining_time": "4:08:10", "throughput": 1319.69, "total_tokens": 3086608} {"current_steps": 5435, "total_steps": 40000, "loss": 0.0, "lr": 4.7757528487952263e-05, "epoch": 95.35398230088495, "percentage": 13.59, "elapsed_time": "0:39:00", "remaining_time": "4:08:07", "throughput": 1319.89, "total_tokens": 3089840} {"current_steps": 5440, "total_steps": 40000, "loss": 0.0, "lr": 4.7753462821499836e-05, "epoch": 95.4424778761062, "percentage": 13.6, "elapsed_time": "0:39:03", "remaining_time": "4:08:05", "throughput": 1319.85, "total_tokens": 3092464} {"current_steps": 5445, "total_steps": 40000, "loss": 0.0, "lr": 4.774939364617751e-05, "epoch": 95.53097345132744, "percentage": 13.61, "elapsed_time": "0:39:05", "remaining_time": "4:08:02", "throughput": 1319.93, "total_tokens": 3095376} {"current_steps": 5450, "total_steps": 40000, "loss": 0.0, "lr": 4.7745320962612795e-05, "epoch": 95.61946902654867, "percentage": 13.63, "elapsed_time": "0:39:07", "remaining_time": "4:07:59", "throughput": 1320.04, "total_tokens": 3098352} {"current_steps": 5455, "total_steps": 40000, "loss": 0.0, "lr": 4.7741244771433756e-05, "epoch": 95.70796460176992, "percentage": 13.64, "elapsed_time": "0:39:09", "remaining_time": "4:07:57", "throughput": 1320.0, "total_tokens": 3100992} {"current_steps": 5460, "total_steps": 40000, "loss": 0.0, "lr": 4.7737165073268985e-05, "epoch": 95.79646017699115, "percentage": 13.65, "elapsed_time": "0:39:11", "remaining_time": "4:07:54", "throughput": 1320.12, "total_tokens": 3104016} {"current_steps": 5465, "total_steps": 40000, "loss": 0.0, "lr": 4.7733081868747626e-05, "epoch": 95.88495575221239, "percentage": 13.66, "elapsed_time": "0:39:13", "remaining_time": "4:07:51", "throughput": 1320.27, "total_tokens": 3107088} {"current_steps": 5470, "total_steps": 40000, "loss": 0.0, "lr": 4.772899515849936e-05, "epoch": 95.97345132743362, "percentage": 13.68, "elapsed_time": "0:39:15", "remaining_time": "4:07:48", "throughput": 1320.22, "total_tokens": 3109696} {"current_steps": 5475, "total_steps": 40000, "loss": 0.0, "lr": 4.7724904943154414e-05, "epoch": 96.05309734513274, "percentage": 13.69, "elapsed_time": "0:39:17", "remaining_time": "4:07:47", "throughput": 1319.88, "total_tokens": 3111880} {"current_steps": 5480, "total_steps": 40000, "loss": 0.0, "lr": 4.772081122334354e-05, "epoch": 96.14159292035399, "percentage": 13.7, "elapsed_time": "0:39:19", "remaining_time": "4:07:44", "throughput": 1319.92, "total_tokens": 3114696} {"current_steps": 5485, "total_steps": 40000, "loss": 0.0, "lr": 4.771671399969806e-05, "epoch": 96.23008849557522, "percentage": 13.71, "elapsed_time": "0:39:21", "remaining_time": "4:07:42", "throughput": 1320.18, "total_tokens": 3118040} {"current_steps": 5490, "total_steps": 40000, "loss": 0.0, "lr": 4.7712613272849794e-05, "epoch": 96.31858407079646, "percentage": 13.73, "elapsed_time": "0:39:23", "remaining_time": "4:07:39", "throughput": 1320.22, "total_tokens": 3120856} {"current_steps": 5495, "total_steps": 40000, "loss": 0.0, "lr": 4.770850904343114e-05, "epoch": 96.40707964601769, "percentage": 13.74, "elapsed_time": "0:39:25", "remaining_time": "4:07:36", "throughput": 1320.21, "total_tokens": 3123560} {"current_steps": 5500, "total_steps": 40000, "loss": 0.0, "lr": 4.770440131207502e-05, "epoch": 96.49557522123894, "percentage": 13.75, "elapsed_time": "0:39:28", "remaining_time": "4:07:33", "throughput": 1320.18, "total_tokens": 3126200} {"current_steps": 5505, "total_steps": 40000, "loss": 0.0, "lr": 4.7700290079414896e-05, "epoch": 96.58407079646018, "percentage": 13.76, "elapsed_time": "0:39:30", "remaining_time": "4:07:31", "throughput": 1320.35, "total_tokens": 3129336} {"current_steps": 5510, "total_steps": 40000, "loss": 0.0, "lr": 4.769617534608477e-05, "epoch": 96.67256637168141, "percentage": 13.78, "elapsed_time": "0:39:32", "remaining_time": "4:07:28", "throughput": 1320.45, "total_tokens": 3132296} {"current_steps": 5515, "total_steps": 40000, "loss": 0.0, "lr": 4.7692057112719193e-05, "epoch": 96.76106194690266, "percentage": 13.79, "elapsed_time": "0:39:34", "remaining_time": "4:07:25", "throughput": 1320.51, "total_tokens": 3135160} {"current_steps": 5520, "total_steps": 40000, "loss": 0.0, "lr": 4.7687935379953234e-05, "epoch": 96.84955752212389, "percentage": 13.8, "elapsed_time": "0:39:36", "remaining_time": "4:07:23", "throughput": 1320.52, "total_tokens": 3137912} {"current_steps": 5525, "total_steps": 40000, "loss": 0.0, "lr": 4.7683810148422534e-05, "epoch": 96.93805309734513, "percentage": 13.81, "elapsed_time": "0:39:38", "remaining_time": "4:07:20", "throughput": 1320.62, "total_tokens": 3140872} {"current_steps": 5530, "total_steps": 40000, "loss": 0.0, "lr": 4.767968141876324e-05, "epoch": 97.01769911504425, "percentage": 13.83, "elapsed_time": "0:39:40", "remaining_time": "4:07:18", "throughput": 1320.51, "total_tokens": 3143568} {"current_steps": 5535, "total_steps": 40000, "loss": 0.0, "lr": 4.767554919161207e-05, "epoch": 97.10619469026548, "percentage": 13.84, "elapsed_time": "0:39:42", "remaining_time": "4:07:16", "throughput": 1320.54, "total_tokens": 3146368} {"current_steps": 5540, "total_steps": 40000, "loss": 0.0, "lr": 4.767141346760624e-05, "epoch": 97.19469026548673, "percentage": 13.85, "elapsed_time": "0:39:44", "remaining_time": "4:07:13", "throughput": 1320.51, "total_tokens": 3149040} {"current_steps": 5545, "total_steps": 40000, "loss": 0.0, "lr": 4.766727424738356e-05, "epoch": 97.28318584070796, "percentage": 13.86, "elapsed_time": "0:39:46", "remaining_time": "4:07:10", "throughput": 1320.7, "total_tokens": 3152224} {"current_steps": 5550, "total_steps": 40000, "loss": 0.0, "lr": 4.7663131531582325e-05, "epoch": 97.3716814159292, "percentage": 13.88, "elapsed_time": "0:39:48", "remaining_time": "4:07:08", "throughput": 1320.82, "total_tokens": 3155216} {"current_steps": 5555, "total_steps": 40000, "loss": 0.0, "lr": 4.765898532084142e-05, "epoch": 97.46017699115045, "percentage": 13.89, "elapsed_time": "0:39:50", "remaining_time": "4:07:05", "throughput": 1320.83, "total_tokens": 3157984} {"current_steps": 5560, "total_steps": 40000, "loss": 0.0, "lr": 4.765483561580022e-05, "epoch": 97.54867256637168, "percentage": 13.9, "elapsed_time": "0:39:52", "remaining_time": "4:07:02", "throughput": 1320.92, "total_tokens": 3160928} {"current_steps": 5565, "total_steps": 40000, "loss": 0.0, "lr": 4.7650682417098666e-05, "epoch": 97.63716814159292, "percentage": 13.91, "elapsed_time": "0:39:55", "remaining_time": "4:06:59", "throughput": 1321.03, "total_tokens": 3163920} {"current_steps": 5570, "total_steps": 40000, "loss": 0.0, "lr": 4.7646525725377244e-05, "epoch": 97.72566371681415, "percentage": 13.93, "elapsed_time": "0:39:57", "remaining_time": "4:06:57", "throughput": 1320.93, "total_tokens": 3166416} {"current_steps": 5575, "total_steps": 40000, "loss": 0.0, "lr": 4.764236554127696e-05, "epoch": 97.8141592920354, "percentage": 13.94, "elapsed_time": "0:39:59", "remaining_time": "4:06:54", "throughput": 1321.07, "total_tokens": 3169456} {"current_steps": 5580, "total_steps": 40000, "loss": 0.0, "lr": 4.7638201865439356e-05, "epoch": 97.90265486725664, "percentage": 13.95, "elapsed_time": "0:40:01", "remaining_time": "4:06:51", "throughput": 1321.07, "total_tokens": 3172208} {"current_steps": 5585, "total_steps": 40000, "loss": 0.0, "lr": 4.7634034698506545e-05, "epoch": 97.99115044247787, "percentage": 13.96, "elapsed_time": "0:40:03", "remaining_time": "4:06:49", "throughput": 1321.34, "total_tokens": 3175584} {"current_steps": 5590, "total_steps": 40000, "loss": 0.0, "lr": 4.762986404112115e-05, "epoch": 98.070796460177, "percentage": 13.98, "elapsed_time": "0:40:05", "remaining_time": "4:06:47", "throughput": 1321.14, "total_tokens": 3178096} {"current_steps": 5595, "total_steps": 40000, "loss": 0.0, "lr": 4.762568989392633e-05, "epoch": 98.15929203539822, "percentage": 13.99, "elapsed_time": "0:40:07", "remaining_time": "4:06:45", "throughput": 1321.28, "total_tokens": 3181152} {"current_steps": 5600, "total_steps": 40000, "loss": 0.0, "lr": 4.76215122575658e-05, "epoch": 98.24778761061947, "percentage": 14.0, "elapsed_time": "0:40:09", "remaining_time": "4:06:42", "throughput": 1321.16, "total_tokens": 3183600} {"current_steps": 5600, "total_steps": 40000, "eval_loss": 0.3896600306034088, "epoch": 98.24778761061947, "percentage": 14.0, "elapsed_time": "0:40:10", "remaining_time": "4:06:48", "throughput": 1320.58, "total_tokens": 3183600} {"current_steps": 5605, "total_steps": 40000, "loss": 0.0, "lr": 4.7617331132683795e-05, "epoch": 98.33628318584071, "percentage": 14.01, "elapsed_time": "0:40:14", "remaining_time": "4:06:57", "throughput": 1319.68, "total_tokens": 3186528} {"current_steps": 5610, "total_steps": 40000, "loss": 0.0, "lr": 4.7613146519925105e-05, "epoch": 98.42477876106194, "percentage": 14.03, "elapsed_time": "0:40:16", "remaining_time": "4:06:54", "throughput": 1319.92, "total_tokens": 3189840} {"current_steps": 5615, "total_steps": 40000, "loss": 0.0, "lr": 4.7608958419935045e-05, "epoch": 98.51327433628319, "percentage": 14.04, "elapsed_time": "0:40:18", "remaining_time": "4:06:51", "throughput": 1319.9, "total_tokens": 3192512} {"current_steps": 5620, "total_steps": 40000, "loss": 0.0, "lr": 4.760476683335948e-05, "epoch": 98.60176991150442, "percentage": 14.05, "elapsed_time": "0:40:20", "remaining_time": "4:06:49", "throughput": 1320.08, "total_tokens": 3195648} {"current_steps": 5625, "total_steps": 40000, "loss": 0.0, "lr": 4.760057176084479e-05, "epoch": 98.69026548672566, "percentage": 14.06, "elapsed_time": "0:40:22", "remaining_time": "4:06:46", "throughput": 1319.99, "total_tokens": 3198160} {"current_steps": 5630, "total_steps": 40000, "loss": 0.0, "lr": 4.759637320303793e-05, "epoch": 98.77876106194691, "percentage": 14.07, "elapsed_time": "0:40:24", "remaining_time": "4:06:43", "throughput": 1320.11, "total_tokens": 3201184} {"current_steps": 5635, "total_steps": 40000, "loss": 0.0, "lr": 4.759217116058635e-05, "epoch": 98.86725663716814, "percentage": 14.09, "elapsed_time": "0:40:27", "remaining_time": "4:06:41", "throughput": 1320.15, "total_tokens": 3204016} {"current_steps": 5640, "total_steps": 40000, "loss": 0.0, "lr": 4.758796563413807e-05, "epoch": 98.95575221238938, "percentage": 14.1, "elapsed_time": "0:40:29", "remaining_time": "4:06:38", "throughput": 1320.11, "total_tokens": 3206624} {"current_steps": 5645, "total_steps": 40000, "loss": 0.0, "lr": 4.758375662434163e-05, "epoch": 99.03539823008849, "percentage": 14.11, "elapsed_time": "0:40:31", "remaining_time": "4:06:36", "throughput": 1319.8, "total_tokens": 3208856} {"current_steps": 5650, "total_steps": 40000, "loss": 0.0, "lr": 4.7579544131846114e-05, "epoch": 99.12389380530973, "percentage": 14.12, "elapsed_time": "0:40:33", "remaining_time": "4:06:34", "throughput": 1319.97, "total_tokens": 3211992} {"current_steps": 5655, "total_steps": 40000, "loss": 0.0, "lr": 4.757532815730114e-05, "epoch": 99.21238938053098, "percentage": 14.14, "elapsed_time": "0:40:35", "remaining_time": "4:06:31", "throughput": 1320.11, "total_tokens": 3215064} {"current_steps": 5660, "total_steps": 40000, "loss": 0.0, "lr": 4.7571108701356865e-05, "epoch": 99.30088495575221, "percentage": 14.15, "elapsed_time": "0:40:37", "remaining_time": "4:06:28", "throughput": 1320.09, "total_tokens": 3217736} {"current_steps": 5665, "total_steps": 40000, "loss": 0.0, "lr": 4.756688576466398e-05, "epoch": 99.38938053097345, "percentage": 14.16, "elapsed_time": "0:40:39", "remaining_time": "4:06:26", "throughput": 1320.15, "total_tokens": 3220600} {"current_steps": 5670, "total_steps": 40000, "loss": 0.0, "lr": 4.756265934787372e-05, "epoch": 99.47787610619469, "percentage": 14.17, "elapsed_time": "0:40:41", "remaining_time": "4:06:23", "throughput": 1320.26, "total_tokens": 3223592} {"current_steps": 5675, "total_steps": 40000, "loss": 0.0, "lr": 4.755842945163785e-05, "epoch": 99.56637168141593, "percentage": 14.19, "elapsed_time": "0:40:43", "remaining_time": "4:06:20", "throughput": 1320.24, "total_tokens": 3226248} {"current_steps": 5680, "total_steps": 40000, "loss": 0.0, "lr": 4.755419607660867e-05, "epoch": 99.65486725663717, "percentage": 14.2, "elapsed_time": "0:40:45", "remaining_time": "4:06:17", "throughput": 1320.42, "total_tokens": 3229432} {"current_steps": 5685, "total_steps": 40000, "loss": 0.0, "lr": 4.7549959223439016e-05, "epoch": 99.7433628318584, "percentage": 14.21, "elapsed_time": "0:40:47", "remaining_time": "4:06:15", "throughput": 1320.31, "total_tokens": 3231896} {"current_steps": 5690, "total_steps": 40000, "loss": 0.0, "lr": 4.754571889278228e-05, "epoch": 99.83185840707965, "percentage": 14.22, "elapsed_time": "0:40:49", "remaining_time": "4:06:12", "throughput": 1320.48, "total_tokens": 3235032} {"current_steps": 5695, "total_steps": 40000, "loss": 0.0, "lr": 4.754147508529235e-05, "epoch": 99.92035398230088, "percentage": 14.24, "elapsed_time": "0:40:51", "remaining_time": "4:06:09", "throughput": 1320.48, "total_tokens": 3237752} {"current_steps": 5700, "total_steps": 40000, "loss": 0.0, "lr": 4.75372278016237e-05, "epoch": 100.0, "percentage": 14.25, "elapsed_time": "0:40:53", "remaining_time": "4:06:06", "throughput": 1320.28, "total_tokens": 3239888} {"current_steps": 5705, "total_steps": 40000, "loss": 0.0, "lr": 4.753297704243129e-05, "epoch": 100.08849557522124, "percentage": 14.26, "elapsed_time": "0:40:56", "remaining_time": "4:06:05", "throughput": 1320.17, "total_tokens": 3242672} {"current_steps": 5710, "total_steps": 40000, "loss": 0.0, "lr": 4.752872280837066e-05, "epoch": 100.17699115044248, "percentage": 14.27, "elapsed_time": "0:40:58", "remaining_time": "4:06:02", "throughput": 1320.16, "total_tokens": 3245408} {"current_steps": 5715, "total_steps": 40000, "loss": 0.0, "lr": 4.752446510009786e-05, "epoch": 100.26548672566372, "percentage": 14.29, "elapsed_time": "0:41:00", "remaining_time": "4:06:00", "throughput": 1320.34, "total_tokens": 3248592} {"current_steps": 5720, "total_steps": 40000, "loss": 0.0, "lr": 4.7520203918269476e-05, "epoch": 100.35398230088495, "percentage": 14.3, "elapsed_time": "0:41:02", "remaining_time": "4:05:57", "throughput": 1320.24, "total_tokens": 3251072} {"current_steps": 5725, "total_steps": 40000, "loss": 0.0, "lr": 4.751593926354265e-05, "epoch": 100.4424778761062, "percentage": 14.31, "elapsed_time": "0:41:04", "remaining_time": "4:05:55", "throughput": 1320.27, "total_tokens": 3253872} {"current_steps": 5730, "total_steps": 40000, "loss": 0.0, "lr": 4.751167113657503e-05, "epoch": 100.53097345132744, "percentage": 14.32, "elapsed_time": "0:41:06", "remaining_time": "4:05:52", "throughput": 1320.33, "total_tokens": 3256752} {"current_steps": 5735, "total_steps": 40000, "loss": 0.0, "lr": 4.7507399538024834e-05, "epoch": 100.61946902654867, "percentage": 14.34, "elapsed_time": "0:41:08", "remaining_time": "4:05:49", "throughput": 1320.38, "total_tokens": 3259584} {"current_steps": 5740, "total_steps": 40000, "loss": 0.0, "lr": 4.750312446855077e-05, "epoch": 100.70796460176992, "percentage": 14.35, "elapsed_time": "0:41:10", "remaining_time": "4:05:46", "throughput": 1320.71, "total_tokens": 3263120} {"current_steps": 5745, "total_steps": 40000, "loss": 0.0, "lr": 4.749884592881212e-05, "epoch": 100.79646017699115, "percentage": 14.36, "elapsed_time": "0:41:12", "remaining_time": "4:05:44", "throughput": 1320.78, "total_tokens": 3266032} {"current_steps": 5750, "total_steps": 40000, "loss": 0.0, "lr": 4.74945639194687e-05, "epoch": 100.88495575221239, "percentage": 14.37, "elapsed_time": "0:41:14", "remaining_time": "4:05:41", "throughput": 1320.77, "total_tokens": 3268736} {"current_steps": 5755, "total_steps": 40000, "loss": 0.0, "lr": 4.749027844118083e-05, "epoch": 100.97345132743362, "percentage": 14.39, "elapsed_time": "0:41:16", "remaining_time": "4:05:38", "throughput": 1321.0, "total_tokens": 3272016} {"current_steps": 5760, "total_steps": 40000, "loss": 0.0, "lr": 4.7485989494609395e-05, "epoch": 101.05309734513274, "percentage": 14.4, "elapsed_time": "0:41:19", "remaining_time": "4:05:37", "throughput": 1320.76, "total_tokens": 3274392} {"current_steps": 5765, "total_steps": 40000, "loss": 0.0, "lr": 4.748169708041581e-05, "epoch": 101.14159292035399, "percentage": 14.41, "elapsed_time": "0:41:21", "remaining_time": "4:05:34", "throughput": 1320.69, "total_tokens": 3276952} {"current_steps": 5770, "total_steps": 40000, "loss": 0.0, "lr": 4.7477401199262004e-05, "epoch": 101.23008849557522, "percentage": 14.42, "elapsed_time": "0:41:23", "remaining_time": "4:05:31", "throughput": 1320.87, "total_tokens": 3280104} {"current_steps": 5775, "total_steps": 40000, "loss": 0.0, "lr": 4.747310185181048e-05, "epoch": 101.31858407079646, "percentage": 14.44, "elapsed_time": "0:41:25", "remaining_time": "4:05:29", "throughput": 1320.87, "total_tokens": 3282840} {"current_steps": 5780, "total_steps": 40000, "loss": 0.0, "lr": 4.746879903872422e-05, "epoch": 101.40707964601769, "percentage": 14.45, "elapsed_time": "0:41:27", "remaining_time": "4:05:26", "throughput": 1320.92, "total_tokens": 3285672} {"current_steps": 5785, "total_steps": 40000, "loss": 0.0, "lr": 4.746449276066679e-05, "epoch": 101.49557522123894, "percentage": 14.46, "elapsed_time": "0:41:29", "remaining_time": "4:05:23", "throughput": 1321.11, "total_tokens": 3288872} {"current_steps": 5790, "total_steps": 40000, "loss": 0.0, "lr": 4.746018301830227e-05, "epoch": 101.58407079646018, "percentage": 14.47, "elapsed_time": "0:41:31", "remaining_time": "4:05:21", "throughput": 1321.36, "total_tokens": 3292264} {"current_steps": 5795, "total_steps": 40000, "loss": 0.0, "lr": 4.7455869812295275e-05, "epoch": 101.67256637168141, "percentage": 14.49, "elapsed_time": "0:41:33", "remaining_time": "4:05:18", "throughput": 1321.29, "total_tokens": 3294808} {"current_steps": 5800, "total_steps": 40000, "loss": 0.0, "lr": 4.7451553143310964e-05, "epoch": 101.76106194690266, "percentage": 14.5, "elapsed_time": "0:41:35", "remaining_time": "4:05:15", "throughput": 1321.44, "total_tokens": 3297896} {"current_steps": 5800, "total_steps": 40000, "eval_loss": 0.38237905502319336, "epoch": 101.76106194690266, "percentage": 14.5, "elapsed_time": "0:41:36", "remaining_time": "4:05:22", "throughput": 1320.88, "total_tokens": 3297896} {"current_steps": 5805, "total_steps": 40000, "loss": 0.0, "lr": 4.744723301201501e-05, "epoch": 101.84955752212389, "percentage": 14.51, "elapsed_time": "0:41:40", "remaining_time": "4:05:29", "throughput": 1320.01, "total_tokens": 3300648} {"current_steps": 5810, "total_steps": 40000, "loss": 0.0, "lr": 4.744290941907364e-05, "epoch": 101.93805309734513, "percentage": 14.52, "elapsed_time": "0:41:42", "remaining_time": "4:05:26", "throughput": 1320.02, "total_tokens": 3303400} {"current_steps": 5815, "total_steps": 40000, "loss": 0.0, "lr": 4.7438582365153594e-05, "epoch": 102.01769911504425, "percentage": 14.54, "elapsed_time": "0:41:44", "remaining_time": "4:05:25", "throughput": 1319.79, "total_tokens": 3305792} {"current_steps": 5820, "total_steps": 40000, "loss": 0.0, "lr": 4.743425185092217e-05, "epoch": 102.10619469026548, "percentage": 14.55, "elapsed_time": "0:41:46", "remaining_time": "4:05:22", "throughput": 1319.93, "total_tokens": 3308880} {"current_steps": 5825, "total_steps": 40000, "loss": 0.0, "lr": 4.742991787704719e-05, "epoch": 102.19469026548673, "percentage": 14.56, "elapsed_time": "0:41:48", "remaining_time": "4:05:19", "throughput": 1320.23, "total_tokens": 3312368} {"current_steps": 5830, "total_steps": 40000, "loss": 0.0, "lr": 4.7425580444196994e-05, "epoch": 102.28318584070796, "percentage": 14.57, "elapsed_time": "0:41:50", "remaining_time": "4:05:17", "throughput": 1320.22, "total_tokens": 3315072} {"current_steps": 5835, "total_steps": 40000, "loss": 0.0, "lr": 4.742123955304048e-05, "epoch": 102.3716814159292, "percentage": 14.59, "elapsed_time": "0:41:53", "remaining_time": "4:05:14", "throughput": 1320.19, "total_tokens": 3317728} {"current_steps": 5840, "total_steps": 40000, "loss": 0.0, "lr": 4.741689520424706e-05, "epoch": 102.46017699115045, "percentage": 14.6, "elapsed_time": "0:41:55", "remaining_time": "4:05:11", "throughput": 1320.25, "total_tokens": 3320592} {"current_steps": 5845, "total_steps": 40000, "loss": 0.0, "lr": 4.741254739848669e-05, "epoch": 102.54867256637168, "percentage": 14.61, "elapsed_time": "0:41:57", "remaining_time": "4:05:09", "throughput": 1320.11, "total_tokens": 3322976} {"current_steps": 5850, "total_steps": 40000, "loss": 0.0, "lr": 4.740819613642987e-05, "epoch": 102.63716814159292, "percentage": 14.62, "elapsed_time": "0:41:59", "remaining_time": "4:05:06", "throughput": 1320.18, "total_tokens": 3325872} {"current_steps": 5855, "total_steps": 40000, "loss": 0.0, "lr": 4.74038414187476e-05, "epoch": 102.72566371681415, "percentage": 14.64, "elapsed_time": "0:42:01", "remaining_time": "4:05:03", "throughput": 1320.11, "total_tokens": 3328432} {"current_steps": 5860, "total_steps": 40000, "loss": 0.0, "lr": 4.739948324611144e-05, "epoch": 102.8141592920354, "percentage": 14.65, "elapsed_time": "0:42:03", "remaining_time": "4:05:01", "throughput": 1320.28, "total_tokens": 3331600} {"current_steps": 5865, "total_steps": 40000, "loss": 0.0, "lr": 4.7395121619193465e-05, "epoch": 102.90265486725664, "percentage": 14.66, "elapsed_time": "0:42:05", "remaining_time": "4:04:58", "throughput": 1320.57, "total_tokens": 3335040} {"current_steps": 5870, "total_steps": 40000, "loss": 0.0, "lr": 4.7390756538666313e-05, "epoch": 102.99115044247787, "percentage": 14.67, "elapsed_time": "0:42:07", "remaining_time": "4:04:55", "throughput": 1320.64, "total_tokens": 3337920} {"current_steps": 5875, "total_steps": 40000, "loss": 0.0, "lr": 4.738638800520311e-05, "epoch": 103.070796460177, "percentage": 14.69, "elapsed_time": "0:42:09", "remaining_time": "4:04:54", "throughput": 1320.49, "total_tokens": 3340552} {"current_steps": 5880, "total_steps": 40000, "loss": 0.0, "lr": 4.738201601947757e-05, "epoch": 103.15929203539822, "percentage": 14.7, "elapsed_time": "0:42:11", "remaining_time": "4:04:51", "throughput": 1320.34, "total_tokens": 3342904} {"current_steps": 5885, "total_steps": 40000, "loss": 0.0, "lr": 4.7377640582163876e-05, "epoch": 103.24778761061947, "percentage": 14.71, "elapsed_time": "0:42:13", "remaining_time": "4:04:48", "throughput": 1320.28, "total_tokens": 3345480} {"current_steps": 5890, "total_steps": 40000, "loss": 0.0, "lr": 4.7373261693936786e-05, "epoch": 103.33628318584071, "percentage": 14.72, "elapsed_time": "0:42:15", "remaining_time": "4:04:46", "throughput": 1320.37, "total_tokens": 3348456} {"current_steps": 5895, "total_steps": 40000, "loss": 0.0, "lr": 4.7368879355471595e-05, "epoch": 103.42477876106194, "percentage": 14.74, "elapsed_time": "0:42:18", "remaining_time": "4:04:43", "throughput": 1320.3, "total_tokens": 3351000} {"current_steps": 5900, "total_steps": 40000, "loss": 0.0, "lr": 4.736449356744409e-05, "epoch": 103.51327433628319, "percentage": 14.75, "elapsed_time": "0:42:20", "remaining_time": "4:04:41", "throughput": 1320.26, "total_tokens": 3353624} {"current_steps": 5905, "total_steps": 40000, "loss": 0.0, "lr": 4.736010433053064e-05, "epoch": 103.60176991150442, "percentage": 14.76, "elapsed_time": "0:42:22", "remaining_time": "4:04:38", "throughput": 1320.32, "total_tokens": 3356504} {"current_steps": 5910, "total_steps": 40000, "loss": 0.0, "lr": 4.73557116454081e-05, "epoch": 103.69026548672566, "percentage": 14.77, "elapsed_time": "0:42:24", "remaining_time": "4:04:35", "throughput": 1320.26, "total_tokens": 3359080} {"current_steps": 5915, "total_steps": 40000, "loss": 0.0, "lr": 4.735131551275389e-05, "epoch": 103.77876106194691, "percentage": 14.79, "elapsed_time": "0:42:26", "remaining_time": "4:04:33", "throughput": 1320.42, "total_tokens": 3362216} {"current_steps": 5920, "total_steps": 40000, "loss": 0.0, "lr": 4.734691593324594e-05, "epoch": 103.86725663716814, "percentage": 14.8, "elapsed_time": "0:42:28", "remaining_time": "4:04:30", "throughput": 1320.82, "total_tokens": 3365960} {"current_steps": 5925, "total_steps": 40000, "loss": 0.0, "lr": 4.734251290756272e-05, "epoch": 103.95575221238938, "percentage": 14.81, "elapsed_time": "0:42:30", "remaining_time": "4:04:27", "throughput": 1321.02, "total_tokens": 3369192} {"current_steps": 5930, "total_steps": 40000, "loss": 0.0, "lr": 4.7338106436383246e-05, "epoch": 104.03539823008849, "percentage": 14.82, "elapsed_time": "0:42:32", "remaining_time": "4:04:26", "throughput": 1320.89, "total_tokens": 3371848} {"current_steps": 5935, "total_steps": 40000, "loss": 0.0, "lr": 4.733369652038703e-05, "epoch": 104.12389380530973, "percentage": 14.84, "elapsed_time": "0:42:34", "remaining_time": "4:04:23", "throughput": 1320.97, "total_tokens": 3374792} {"current_steps": 5940, "total_steps": 40000, "loss": 0.0, "lr": 4.7329283160254156e-05, "epoch": 104.21238938053098, "percentage": 14.85, "elapsed_time": "0:42:36", "remaining_time": "4:04:20", "throughput": 1321.09, "total_tokens": 3377816} {"current_steps": 5945, "total_steps": 40000, "loss": 0.0, "lr": 4.732486635666521e-05, "epoch": 104.30088495575221, "percentage": 14.86, "elapsed_time": "0:42:38", "remaining_time": "4:04:18", "throughput": 1321.19, "total_tokens": 3380808} {"current_steps": 5950, "total_steps": 40000, "loss": 0.0, "lr": 4.732044611030132e-05, "epoch": 104.38938053097345, "percentage": 14.88, "elapsed_time": "0:42:40", "remaining_time": "4:04:15", "throughput": 1321.38, "total_tokens": 3384008} {"current_steps": 5955, "total_steps": 40000, "loss": 0.0, "lr": 4.731602242184414e-05, "epoch": 104.47787610619469, "percentage": 14.89, "elapsed_time": "0:42:43", "remaining_time": "4:04:12", "throughput": 1321.27, "total_tokens": 3386472} {"current_steps": 5960, "total_steps": 40000, "loss": 0.0, "lr": 4.7311595291975864e-05, "epoch": 104.56637168141593, "percentage": 14.9, "elapsed_time": "0:42:45", "remaining_time": "4:04:10", "throughput": 1321.29, "total_tokens": 3389272} {"current_steps": 5965, "total_steps": 40000, "loss": 0.0, "lr": 4.7307164721379216e-05, "epoch": 104.65486725663717, "percentage": 14.91, "elapsed_time": "0:42:47", "remaining_time": "4:04:07", "throughput": 1321.44, "total_tokens": 3392392} {"current_steps": 5970, "total_steps": 40000, "loss": 0.0, "lr": 4.730273071073743e-05, "epoch": 104.7433628318584, "percentage": 14.92, "elapsed_time": "0:42:49", "remaining_time": "4:04:05", "throughput": 1321.51, "total_tokens": 3395304} {"current_steps": 5975, "total_steps": 40000, "loss": 0.0, "lr": 4.729829326073429e-05, "epoch": 104.83185840707965, "percentage": 14.94, "elapsed_time": "0:42:51", "remaining_time": "4:04:02", "throughput": 1321.46, "total_tokens": 3397896} {"current_steps": 5980, "total_steps": 40000, "loss": 0.0, "lr": 4.7293852372054126e-05, "epoch": 104.92035398230088, "percentage": 14.95, "elapsed_time": "0:42:53", "remaining_time": "4:03:59", "throughput": 1321.44, "total_tokens": 3400552} {"current_steps": 5985, "total_steps": 40000, "loss": 0.0, "lr": 4.728940804538176e-05, "epoch": 105.0, "percentage": 14.96, "elapsed_time": "0:42:55", "remaining_time": "4:03:56", "throughput": 1321.34, "total_tokens": 3402936} {"current_steps": 5990, "total_steps": 40000, "loss": 0.0, "lr": 4.7284960281402556e-05, "epoch": 105.08849557522124, "percentage": 14.97, "elapsed_time": "0:42:57", "remaining_time": "4:03:55", "throughput": 1321.21, "total_tokens": 3405640} {"current_steps": 5995, "total_steps": 40000, "loss": 0.0, "lr": 4.728050908080244e-05, "epoch": 105.17699115044248, "percentage": 14.99, "elapsed_time": "0:42:59", "remaining_time": "4:03:52", "throughput": 1321.15, "total_tokens": 3408232} {"current_steps": 6000, "total_steps": 40000, "loss": 0.0, "lr": 4.727605444426782e-05, "epoch": 105.26548672566372, "percentage": 15.0, "elapsed_time": "0:43:01", "remaining_time": "4:03:50", "throughput": 1321.37, "total_tokens": 3411544} {"current_steps": 6000, "total_steps": 40000, "eval_loss": 0.38351133465766907, "epoch": 105.26548672566372, "percentage": 15.0, "elapsed_time": "0:43:02", "remaining_time": "4:03:56", "throughput": 1320.83, "total_tokens": 3411544} {"current_steps": 6005, "total_steps": 40000, "loss": 0.0, "lr": 4.727159637248567e-05, "epoch": 105.35398230088495, "percentage": 15.01, "elapsed_time": "0:43:06", "remaining_time": "4:04:02", "throughput": 1320.14, "total_tokens": 3414664} {"current_steps": 6010, "total_steps": 40000, "loss": 0.0, "lr": 4.7267134866143474e-05, "epoch": 105.4424778761062, "percentage": 15.02, "elapsed_time": "0:43:08", "remaining_time": "4:04:00", "throughput": 1320.2, "total_tokens": 3417528} {"current_steps": 6015, "total_steps": 40000, "loss": 0.0, "lr": 4.726266992592926e-05, "epoch": 105.53097345132744, "percentage": 15.04, "elapsed_time": "0:43:10", "remaining_time": "4:03:57", "throughput": 1320.26, "total_tokens": 3420408} {"current_steps": 6020, "total_steps": 40000, "loss": 0.0, "lr": 4.725820155253157e-05, "epoch": 105.61946902654867, "percentage": 15.05, "elapsed_time": "0:43:12", "remaining_time": "4:03:54", "throughput": 1320.31, "total_tokens": 3423272} {"current_steps": 6025, "total_steps": 40000, "loss": 0.0, "lr": 4.725372974663948e-05, "epoch": 105.70796460176992, "percentage": 15.06, "elapsed_time": "0:43:15", "remaining_time": "4:03:53", "throughput": 1320.27, "total_tokens": 3426264} {"current_steps": 6030, "total_steps": 40000, "loss": 0.0, "lr": 4.724925450894262e-05, "epoch": 105.79646017699115, "percentage": 15.07, "elapsed_time": "0:43:17", "remaining_time": "4:03:51", "throughput": 1320.4, "total_tokens": 3429304} {"current_steps": 6035, "total_steps": 40000, "loss": 0.0, "lr": 4.72447758401311e-05, "epoch": 105.88495575221239, "percentage": 15.09, "elapsed_time": "0:43:19", "remaining_time": "4:03:48", "throughput": 1320.43, "total_tokens": 3432120} {"current_steps": 6040, "total_steps": 40000, "loss": 0.0, "lr": 4.7240293740895616e-05, "epoch": 105.97345132743362, "percentage": 15.1, "elapsed_time": "0:43:21", "remaining_time": "4:03:45", "throughput": 1320.33, "total_tokens": 3434552} {"current_steps": 6045, "total_steps": 40000, "loss": 0.0, "lr": 4.723580821192733e-05, "epoch": 106.05309734513274, "percentage": 15.11, "elapsed_time": "0:43:23", "remaining_time": "4:03:44", "throughput": 1319.96, "total_tokens": 3436568} {"current_steps": 6050, "total_steps": 40000, "loss": 0.0, "lr": 4.7231319253917996e-05, "epoch": 106.14159292035399, "percentage": 15.12, "elapsed_time": "0:43:25", "remaining_time": "4:03:41", "throughput": 1320.27, "total_tokens": 3440088} {"current_steps": 6055, "total_steps": 40000, "loss": 0.0, "lr": 4.722682686755986e-05, "epoch": 106.23008849557522, "percentage": 15.14, "elapsed_time": "0:43:27", "remaining_time": "4:03:38", "throughput": 1320.49, "total_tokens": 3443400} {"current_steps": 6060, "total_steps": 40000, "loss": 0.0, "lr": 4.722233105354569e-05, "epoch": 106.31858407079646, "percentage": 15.15, "elapsed_time": "0:43:29", "remaining_time": "4:03:36", "throughput": 1320.49, "total_tokens": 3446120} {"current_steps": 6065, "total_steps": 40000, "loss": 0.0, "lr": 4.7217831812568815e-05, "epoch": 106.40707964601769, "percentage": 15.16, "elapsed_time": "0:43:31", "remaining_time": "4:03:33", "throughput": 1320.36, "total_tokens": 3448520} {"current_steps": 6070, "total_steps": 40000, "loss": 0.0, "lr": 4.721332914532307e-05, "epoch": 106.49557522123894, "percentage": 15.17, "elapsed_time": "0:43:33", "remaining_time": "4:03:30", "throughput": 1320.35, "total_tokens": 3451192} {"current_steps": 6075, "total_steps": 40000, "loss": 0.0, "lr": 4.720882305250281e-05, "epoch": 106.58407079646018, "percentage": 15.19, "elapsed_time": "0:43:35", "remaining_time": "4:03:28", "throughput": 1320.53, "total_tokens": 3454376} {"current_steps": 6080, "total_steps": 40000, "loss": 0.0, "lr": 4.720431353480295e-05, "epoch": 106.67256637168141, "percentage": 15.2, "elapsed_time": "0:43:37", "remaining_time": "4:03:25", "throughput": 1320.44, "total_tokens": 3456872} {"current_steps": 6085, "total_steps": 40000, "loss": 0.0, "lr": 4.719980059291891e-05, "epoch": 106.76106194690266, "percentage": 15.21, "elapsed_time": "0:43:40", "remaining_time": "4:03:22", "throughput": 1320.41, "total_tokens": 3459512} {"current_steps": 6090, "total_steps": 40000, "loss": 0.0, "lr": 4.7195284227546634e-05, "epoch": 106.84955752212389, "percentage": 15.22, "elapsed_time": "0:43:42", "remaining_time": "4:03:20", "throughput": 1320.49, "total_tokens": 3462472} {"current_steps": 6095, "total_steps": 40000, "loss": 0.0, "lr": 4.7190764439382604e-05, "epoch": 106.93805309734513, "percentage": 15.24, "elapsed_time": "0:43:44", "remaining_time": "4:03:17", "throughput": 1320.46, "total_tokens": 3465096} {"current_steps": 6100, "total_steps": 40000, "loss": 0.0, "lr": 4.7186241229123826e-05, "epoch": 107.01769911504425, "percentage": 15.25, "elapsed_time": "0:43:46", "remaining_time": "4:03:15", "throughput": 1320.26, "total_tokens": 3467568} {"current_steps": 6105, "total_steps": 40000, "loss": 0.0, "lr": 4.718171459746785e-05, "epoch": 107.10619469026548, "percentage": 15.26, "elapsed_time": "0:43:48", "remaining_time": "4:03:13", "throughput": 1320.47, "total_tokens": 3470832} {"current_steps": 6110, "total_steps": 40000, "loss": 0.0, "lr": 4.717718454511273e-05, "epoch": 107.19469026548673, "percentage": 15.28, "elapsed_time": "0:43:50", "remaining_time": "4:03:10", "throughput": 1320.65, "total_tokens": 3474032} {"current_steps": 6115, "total_steps": 40000, "loss": 0.0, "lr": 4.7172651072757056e-05, "epoch": 107.28318584070796, "percentage": 15.29, "elapsed_time": "0:43:52", "remaining_time": "4:03:08", "throughput": 1320.72, "total_tokens": 3476944} {"current_steps": 6120, "total_steps": 40000, "loss": 0.0, "lr": 4.7168114181099945e-05, "epoch": 107.3716814159292, "percentage": 15.3, "elapsed_time": "0:43:54", "remaining_time": "4:03:05", "throughput": 1320.79, "total_tokens": 3479840} {"current_steps": 6125, "total_steps": 40000, "loss": 0.0, "lr": 4.716357387084105e-05, "epoch": 107.46017699115045, "percentage": 15.31, "elapsed_time": "0:43:56", "remaining_time": "4:03:02", "throughput": 1320.94, "total_tokens": 3482960} {"current_steps": 6130, "total_steps": 40000, "loss": 0.0, "lr": 4.715903014268054e-05, "epoch": 107.54867256637168, "percentage": 15.32, "elapsed_time": "0:43:58", "remaining_time": "4:03:00", "throughput": 1320.79, "total_tokens": 3485280} {"current_steps": 6135, "total_steps": 40000, "loss": 0.0, "lr": 4.715448299731911e-05, "epoch": 107.63716814159292, "percentage": 15.34, "elapsed_time": "0:44:00", "remaining_time": "4:02:57", "throughput": 1320.89, "total_tokens": 3488304} {"current_steps": 6140, "total_steps": 40000, "loss": 0.0, "lr": 4.7149932435457986e-05, "epoch": 107.72566371681415, "percentage": 15.35, "elapsed_time": "0:44:02", "remaining_time": "4:02:54", "throughput": 1320.97, "total_tokens": 3491232} {"current_steps": 6145, "total_steps": 40000, "loss": 0.0, "lr": 4.714537845779894e-05, "epoch": 107.8141592920354, "percentage": 15.36, "elapsed_time": "0:44:04", "remaining_time": "4:02:52", "throughput": 1321.13, "total_tokens": 3494368} {"current_steps": 6150, "total_steps": 40000, "loss": 0.0, "lr": 4.714082106504423e-05, "epoch": 107.90265486725664, "percentage": 15.38, "elapsed_time": "0:44:07", "remaining_time": "4:02:49", "throughput": 1321.06, "total_tokens": 3496912} {"current_steps": 6155, "total_steps": 40000, "loss": 0.0, "lr": 4.713626025789667e-05, "epoch": 107.99115044247787, "percentage": 15.39, "elapsed_time": "0:44:09", "remaining_time": "4:02:46", "throughput": 1321.07, "total_tokens": 3499632} {"current_steps": 6160, "total_steps": 40000, "loss": 0.0, "lr": 4.7131696037059606e-05, "epoch": 108.070796460177, "percentage": 15.4, "elapsed_time": "0:44:11", "remaining_time": "4:02:45", "throughput": 1320.95, "total_tokens": 3502320} {"current_steps": 6165, "total_steps": 40000, "loss": 0.0, "lr": 4.712712840323689e-05, "epoch": 108.15929203539822, "percentage": 15.41, "elapsed_time": "0:44:13", "remaining_time": "4:02:42", "throughput": 1320.97, "total_tokens": 3505104} {"current_steps": 6170, "total_steps": 40000, "loss": 0.0, "lr": 4.71225573571329e-05, "epoch": 108.24778761061947, "percentage": 15.43, "elapsed_time": "0:44:15", "remaining_time": "4:02:40", "throughput": 1320.93, "total_tokens": 3507744} {"current_steps": 6175, "total_steps": 40000, "loss": 0.0, "lr": 4.711798289945256e-05, "epoch": 108.33628318584071, "percentage": 15.44, "elapsed_time": "0:44:17", "remaining_time": "4:02:37", "throughput": 1321.08, "total_tokens": 3510848} {"current_steps": 6180, "total_steps": 40000, "loss": 0.0, "lr": 4.71134050309013e-05, "epoch": 108.42477876106194, "percentage": 15.45, "elapsed_time": "0:44:19", "remaining_time": "4:02:34", "throughput": 1321.22, "total_tokens": 3513952} {"current_steps": 6185, "total_steps": 40000, "loss": 0.0, "lr": 4.710882375218509e-05, "epoch": 108.51327433628319, "percentage": 15.46, "elapsed_time": "0:44:21", "remaining_time": "4:02:32", "throughput": 1321.34, "total_tokens": 3516992} {"current_steps": 6190, "total_steps": 40000, "loss": 0.0, "lr": 4.7104239064010424e-05, "epoch": 108.60176991150442, "percentage": 15.47, "elapsed_time": "0:44:23", "remaining_time": "4:02:29", "throughput": 1321.43, "total_tokens": 3519952} {"current_steps": 6195, "total_steps": 40000, "loss": 0.0, "lr": 4.709965096708432e-05, "epoch": 108.69026548672566, "percentage": 15.49, "elapsed_time": "0:44:25", "remaining_time": "4:02:26", "throughput": 1321.44, "total_tokens": 3522688} {"current_steps": 6200, "total_steps": 40000, "loss": 0.0, "lr": 4.709505946211431e-05, "epoch": 108.77876106194691, "percentage": 15.5, "elapsed_time": "0:44:27", "remaining_time": "4:02:24", "throughput": 1321.46, "total_tokens": 3525472} {"current_steps": 6200, "total_steps": 40000, "eval_loss": 0.3907127380371094, "epoch": 108.77876106194691, "percentage": 15.5, "elapsed_time": "0:44:28", "remaining_time": "4:02:29", "throughput": 1320.93, "total_tokens": 3525472} {"current_steps": 6205, "total_steps": 40000, "loss": 0.0, "lr": 4.709046454980846e-05, "epoch": 108.86725663716814, "percentage": 15.51, "elapsed_time": "0:44:32", "remaining_time": "4:02:36", "throughput": 1320.3, "total_tokens": 3528720} {"current_steps": 6210, "total_steps": 40000, "loss": 0.0, "lr": 4.708586623087538e-05, "epoch": 108.95575221238938, "percentage": 15.53, "elapsed_time": "0:44:34", "remaining_time": "4:02:33", "throughput": 1320.23, "total_tokens": 3531264} {"current_steps": 6215, "total_steps": 40000, "loss": 0.0, "lr": 4.708126450602418e-05, "epoch": 109.03539823008849, "percentage": 15.54, "elapsed_time": "0:44:36", "remaining_time": "4:02:32", "throughput": 1319.94, "total_tokens": 3533456} {"current_steps": 6220, "total_steps": 40000, "loss": 0.0, "lr": 4.7076659375964495e-05, "epoch": 109.12389380530973, "percentage": 15.55, "elapsed_time": "0:44:39", "remaining_time": "4:02:29", "throughput": 1320.11, "total_tokens": 3536624} {"current_steps": 6225, "total_steps": 40000, "loss": 0.0, "lr": 4.707205084140651e-05, "epoch": 109.21238938053098, "percentage": 15.56, "elapsed_time": "0:44:41", "remaining_time": "4:02:26", "throughput": 1320.17, "total_tokens": 3539520} {"current_steps": 6230, "total_steps": 40000, "loss": 0.0, "lr": 4.7067438903060904e-05, "epoch": 109.30088495575221, "percentage": 15.57, "elapsed_time": "0:44:43", "remaining_time": "4:02:24", "throughput": 1320.14, "total_tokens": 3542160} {"current_steps": 6235, "total_steps": 40000, "loss": 0.0, "lr": 4.70628235616389e-05, "epoch": 109.38938053097345, "percentage": 15.59, "elapsed_time": "0:44:45", "remaining_time": "4:02:21", "throughput": 1320.16, "total_tokens": 3544944} {"current_steps": 6240, "total_steps": 40000, "loss": 0.0, "lr": 4.7058204817852256e-05, "epoch": 109.47787610619469, "percentage": 15.6, "elapsed_time": "0:44:47", "remaining_time": "4:02:18", "throughput": 1320.07, "total_tokens": 3547424} {"current_steps": 6245, "total_steps": 40000, "loss": 0.0, "lr": 4.705358267241322e-05, "epoch": 109.56637168141593, "percentage": 15.61, "elapsed_time": "0:44:49", "remaining_time": "4:02:16", "throughput": 1320.17, "total_tokens": 3550416} {"current_steps": 6250, "total_steps": 40000, "loss": 0.0, "lr": 4.704895712603459e-05, "epoch": 109.65486725663717, "percentage": 15.62, "elapsed_time": "0:44:51", "remaining_time": "4:02:13", "throughput": 1320.39, "total_tokens": 3553728} {"current_steps": 6255, "total_steps": 40000, "loss": 0.0, "lr": 4.704432817942969e-05, "epoch": 109.7433628318584, "percentage": 15.64, "elapsed_time": "0:44:53", "remaining_time": "4:02:11", "throughput": 1320.59, "total_tokens": 3556992} {"current_steps": 6260, "total_steps": 40000, "loss": 0.0, "lr": 4.703969583331236e-05, "epoch": 109.83185840707965, "percentage": 15.65, "elapsed_time": "0:44:55", "remaining_time": "4:02:08", "throughput": 1320.61, "total_tokens": 3559776} {"current_steps": 6265, "total_steps": 40000, "loss": 0.0, "lr": 4.7035060088396965e-05, "epoch": 109.92035398230088, "percentage": 15.66, "elapsed_time": "0:44:57", "remaining_time": "4:02:05", "throughput": 1320.67, "total_tokens": 3562640} {"current_steps": 6270, "total_steps": 40000, "loss": 0.0, "lr": 4.703042094539839e-05, "epoch": 110.0, "percentage": 15.68, "elapsed_time": "0:44:59", "remaining_time": "4:02:02", "throughput": 1320.57, "total_tokens": 3565040} {"current_steps": 6275, "total_steps": 40000, "loss": 0.0, "lr": 4.702577840503206e-05, "epoch": 110.08849557522124, "percentage": 15.69, "elapsed_time": "0:45:01", "remaining_time": "4:02:01", "throughput": 1320.4, "total_tokens": 3567632} {"current_steps": 6280, "total_steps": 40000, "loss": 0.0, "lr": 4.70211324680139e-05, "epoch": 110.17699115044248, "percentage": 15.7, "elapsed_time": "0:45:04", "remaining_time": "4:01:58", "throughput": 1320.57, "total_tokens": 3570816} {"current_steps": 6285, "total_steps": 40000, "loss": 0.0, "lr": 4.7016483135060386e-05, "epoch": 110.26548672566372, "percentage": 15.71, "elapsed_time": "0:45:06", "remaining_time": "4:01:56", "throughput": 1320.51, "total_tokens": 3573392} {"current_steps": 6290, "total_steps": 40000, "loss": 0.0, "lr": 4.701183040688849e-05, "epoch": 110.35398230088495, "percentage": 15.72, "elapsed_time": "0:45:08", "remaining_time": "4:01:53", "throughput": 1320.54, "total_tokens": 3576192} {"current_steps": 6295, "total_steps": 40000, "loss": 0.0, "lr": 4.700717428421573e-05, "epoch": 110.4424778761062, "percentage": 15.74, "elapsed_time": "0:45:10", "remaining_time": "4:01:51", "throughput": 1320.55, "total_tokens": 3578928} {"current_steps": 6300, "total_steps": 40000, "loss": 0.0, "lr": 4.700251476776014e-05, "epoch": 110.53097345132744, "percentage": 15.75, "elapsed_time": "0:45:12", "remaining_time": "4:01:48", "throughput": 1320.56, "total_tokens": 3581680} {"current_steps": 6305, "total_steps": 40000, "loss": 0.0, "lr": 4.699785185824026e-05, "epoch": 110.61946902654867, "percentage": 15.76, "elapsed_time": "0:45:14", "remaining_time": "4:01:45", "throughput": 1320.73, "total_tokens": 3584880} {"current_steps": 6310, "total_steps": 40000, "loss": 0.0, "lr": 4.699318555637519e-05, "epoch": 110.70796460176992, "percentage": 15.78, "elapsed_time": "0:45:16", "remaining_time": "4:01:43", "throughput": 1320.78, "total_tokens": 3587760} {"current_steps": 6315, "total_steps": 40000, "loss": 0.0, "lr": 4.6988515862884525e-05, "epoch": 110.79646017699115, "percentage": 15.79, "elapsed_time": "0:45:18", "remaining_time": "4:01:40", "throughput": 1320.88, "total_tokens": 3590752} {"current_steps": 6320, "total_steps": 40000, "loss": 0.0, "lr": 4.698384277848838e-05, "epoch": 110.88495575221239, "percentage": 15.8, "elapsed_time": "0:45:20", "remaining_time": "4:01:37", "throughput": 1320.95, "total_tokens": 3593648} {"current_steps": 6325, "total_steps": 40000, "loss": 0.0, "lr": 4.6979166303907425e-05, "epoch": 110.97345132743362, "percentage": 15.81, "elapsed_time": "0:45:22", "remaining_time": "4:01:35", "throughput": 1320.96, "total_tokens": 3596384} {"current_steps": 6330, "total_steps": 40000, "loss": 0.0, "lr": 4.697448643986281e-05, "epoch": 111.05309734513274, "percentage": 15.82, "elapsed_time": "0:45:24", "remaining_time": "4:01:33", "throughput": 1320.7, "total_tokens": 3598640} {"current_steps": 6335, "total_steps": 40000, "loss": 0.0, "lr": 4.696980318707624e-05, "epoch": 111.14159292035399, "percentage": 15.84, "elapsed_time": "0:45:26", "remaining_time": "4:01:30", "throughput": 1320.68, "total_tokens": 3601328} {"current_steps": 6340, "total_steps": 40000, "loss": 0.0, "lr": 4.6965116546269924e-05, "epoch": 111.23008849557522, "percentage": 15.85, "elapsed_time": "0:45:28", "remaining_time": "4:01:28", "throughput": 1320.73, "total_tokens": 3604192} {"current_steps": 6345, "total_steps": 40000, "loss": 0.0, "lr": 4.6960426518166615e-05, "epoch": 111.31858407079646, "percentage": 15.86, "elapsed_time": "0:45:31", "remaining_time": "4:01:25", "throughput": 1320.67, "total_tokens": 3606800} {"current_steps": 6350, "total_steps": 40000, "loss": 0.0, "lr": 4.6955733103489556e-05, "epoch": 111.40707964601769, "percentage": 15.88, "elapsed_time": "0:45:33", "remaining_time": "4:01:23", "throughput": 1320.75, "total_tokens": 3609728} {"current_steps": 6355, "total_steps": 40000, "loss": 0.0, "lr": 4.695103630296255e-05, "epoch": 111.49557522123894, "percentage": 15.89, "elapsed_time": "0:45:35", "remaining_time": "4:01:20", "throughput": 1320.76, "total_tokens": 3612480} {"current_steps": 6360, "total_steps": 40000, "loss": 0.0, "lr": 4.694633611730988e-05, "epoch": 111.58407079646018, "percentage": 15.9, "elapsed_time": "0:45:37", "remaining_time": "4:01:17", "throughput": 1320.96, "total_tokens": 3615760} {"current_steps": 6365, "total_steps": 40000, "loss": 0.0, "lr": 4.694163254725639e-05, "epoch": 111.67256637168141, "percentage": 15.91, "elapsed_time": "0:45:39", "remaining_time": "4:01:15", "throughput": 1321.02, "total_tokens": 3618656} {"current_steps": 6370, "total_steps": 40000, "loss": 0.0, "lr": 4.693692559352743e-05, "epoch": 111.76106194690266, "percentage": 15.93, "elapsed_time": "0:45:41", "remaining_time": "4:01:12", "throughput": 1320.98, "total_tokens": 3621264} {"current_steps": 6375, "total_steps": 40000, "loss": 0.0, "lr": 4.693221525684886e-05, "epoch": 111.84955752212389, "percentage": 15.94, "elapsed_time": "0:45:43", "remaining_time": "4:01:10", "throughput": 1320.99, "total_tokens": 3624000} {"current_steps": 6380, "total_steps": 40000, "loss": 0.0, "lr": 4.6927501537947084e-05, "epoch": 111.93805309734513, "percentage": 15.95, "elapsed_time": "0:45:45", "remaining_time": "4:01:07", "throughput": 1321.11, "total_tokens": 3627072} {"current_steps": 6385, "total_steps": 40000, "loss": 0.0, "lr": 4.692278443754901e-05, "epoch": 112.01769911504425, "percentage": 15.96, "elapsed_time": "0:45:47", "remaining_time": "4:01:05", "throughput": 1321.06, "total_tokens": 3629896} {"current_steps": 6390, "total_steps": 40000, "loss": 0.0, "lr": 4.691806395638208e-05, "epoch": 112.10619469026548, "percentage": 15.97, "elapsed_time": "0:45:49", "remaining_time": "4:01:03", "throughput": 1321.03, "total_tokens": 3632520} {"current_steps": 6395, "total_steps": 40000, "loss": 0.0, "lr": 4.6913340095174255e-05, "epoch": 112.19469026548673, "percentage": 15.99, "elapsed_time": "0:45:51", "remaining_time": "4:01:00", "throughput": 1321.09, "total_tokens": 3635432} {"current_steps": 6400, "total_steps": 40000, "loss": 0.0, "lr": 4.690861285465399e-05, "epoch": 112.28318584070796, "percentage": 16.0, "elapsed_time": "0:45:53", "remaining_time": "4:00:57", "throughput": 1321.25, "total_tokens": 3638584} {"current_steps": 6400, "total_steps": 40000, "eval_loss": 0.40295475721359253, "epoch": 112.28318584070796, "percentage": 16.0, "elapsed_time": "0:45:54", "remaining_time": "4:01:03", "throughput": 1320.74, "total_tokens": 3638584} {"current_steps": 6405, "total_steps": 40000, "loss": 0.0, "lr": 4.690388223555031e-05, "epoch": 112.3716814159292, "percentage": 16.01, "elapsed_time": "0:45:58", "remaining_time": "4:01:11", "throughput": 1319.81, "total_tokens": 3641288} {"current_steps": 6410, "total_steps": 40000, "loss": 0.0, "lr": 4.689914823859273e-05, "epoch": 112.46017699115045, "percentage": 16.02, "elapsed_time": "0:46:01", "remaining_time": "4:01:08", "throughput": 1319.71, "total_tokens": 3643800} {"current_steps": 6415, "total_steps": 40000, "loss": 0.0, "lr": 4.689441086451129e-05, "epoch": 112.54867256637168, "percentage": 16.04, "elapsed_time": "0:46:03", "remaining_time": "4:01:06", "throughput": 1319.81, "total_tokens": 3646792} {"current_steps": 6420, "total_steps": 40000, "loss": 0.0, "lr": 4.688967011403655e-05, "epoch": 112.63716814159292, "percentage": 16.05, "elapsed_time": "0:46:05", "remaining_time": "4:01:03", "throughput": 1319.97, "total_tokens": 3649960} {"current_steps": 6425, "total_steps": 40000, "loss": 0.0, "lr": 4.68849259878996e-05, "epoch": 112.72566371681415, "percentage": 16.06, "elapsed_time": "0:46:07", "remaining_time": "4:01:00", "throughput": 1320.12, "total_tokens": 3653080} {"current_steps": 6430, "total_steps": 40000, "loss": 0.0, "lr": 4.6880178486832036e-05, "epoch": 112.8141592920354, "percentage": 16.07, "elapsed_time": "0:46:09", "remaining_time": "4:00:58", "throughput": 1319.98, "total_tokens": 3655432} {"current_steps": 6435, "total_steps": 40000, "loss": 0.0, "lr": 4.687542761156598e-05, "epoch": 112.90265486725664, "percentage": 16.09, "elapsed_time": "0:46:11", "remaining_time": "4:00:55", "throughput": 1320.03, "total_tokens": 3658296} {"current_steps": 6440, "total_steps": 40000, "loss": 0.0, "lr": 4.6870673362834096e-05, "epoch": 112.99115044247787, "percentage": 16.1, "elapsed_time": "0:46:13", "remaining_time": "4:00:52", "throughput": 1320.05, "total_tokens": 3661048} {"current_steps": 6445, "total_steps": 40000, "loss": 0.0, "lr": 4.6865915741369526e-05, "epoch": 113.070796460177, "percentage": 16.11, "elapsed_time": "0:46:15", "remaining_time": "4:00:51", "throughput": 1319.95, "total_tokens": 3663752} {"current_steps": 6450, "total_steps": 40000, "loss": 0.0, "lr": 4.686115474790597e-05, "epoch": 113.15929203539822, "percentage": 16.12, "elapsed_time": "0:46:17", "remaining_time": "4:00:48", "throughput": 1319.96, "total_tokens": 3666504} {"current_steps": 6455, "total_steps": 40000, "loss": 0.0, "lr": 4.685639038317762e-05, "epoch": 113.24778761061947, "percentage": 16.14, "elapsed_time": "0:46:19", "remaining_time": "4:00:45", "throughput": 1320.04, "total_tokens": 3669464} {"current_steps": 6460, "total_steps": 40000, "loss": 0.0, "lr": 4.685162264791921e-05, "epoch": 113.33628318584071, "percentage": 16.15, "elapsed_time": "0:46:21", "remaining_time": "4:00:43", "throughput": 1320.19, "total_tokens": 3672584} {"current_steps": 6465, "total_steps": 40000, "loss": 0.0, "lr": 4.684685154286599e-05, "epoch": 113.42477876106194, "percentage": 16.16, "elapsed_time": "0:46:23", "remaining_time": "4:00:40", "throughput": 1320.22, "total_tokens": 3675400} {"current_steps": 6470, "total_steps": 40000, "loss": 0.0, "lr": 4.684207706875371e-05, "epoch": 113.51327433628319, "percentage": 16.18, "elapsed_time": "0:46:26", "remaining_time": "4:00:38", "throughput": 1320.35, "total_tokens": 3678488} {"current_steps": 6475, "total_steps": 40000, "loss": 0.0, "lr": 4.683729922631866e-05, "epoch": 113.60176991150442, "percentage": 16.19, "elapsed_time": "0:46:28", "remaining_time": "4:00:35", "throughput": 1320.36, "total_tokens": 3681240} {"current_steps": 6480, "total_steps": 40000, "loss": 0.0, "lr": 4.683251801629765e-05, "epoch": 113.69026548672566, "percentage": 16.2, "elapsed_time": "0:46:30", "remaining_time": "4:00:32", "throughput": 1320.53, "total_tokens": 3684456} {"current_steps": 6485, "total_steps": 40000, "loss": 0.0, "lr": 4.6827733439428e-05, "epoch": 113.77876106194691, "percentage": 16.21, "elapsed_time": "0:46:32", "remaining_time": "4:00:30", "throughput": 1320.55, "total_tokens": 3687240} {"current_steps": 6490, "total_steps": 40000, "loss": 0.0, "lr": 4.682294549644754e-05, "epoch": 113.86725663716814, "percentage": 16.23, "elapsed_time": "0:46:34", "remaining_time": "4:00:27", "throughput": 1320.47, "total_tokens": 3689736} {"current_steps": 6495, "total_steps": 40000, "loss": 0.0, "lr": 4.681815418809464e-05, "epoch": 113.95575221238938, "percentage": 16.24, "elapsed_time": "0:46:36", "remaining_time": "4:00:24", "throughput": 1320.52, "total_tokens": 3692584} {"current_steps": 6500, "total_steps": 40000, "loss": 0.0, "lr": 4.681335951510819e-05, "epoch": 114.03539823008849, "percentage": 16.25, "elapsed_time": "0:46:38", "remaining_time": "4:00:23", "throughput": 1320.18, "total_tokens": 3694592} {"current_steps": 6505, "total_steps": 40000, "loss": 0.0, "lr": 4.6808561478227576e-05, "epoch": 114.12389380530973, "percentage": 16.26, "elapsed_time": "0:46:40", "remaining_time": "4:00:20", "throughput": 1320.26, "total_tokens": 3697552} {"current_steps": 6510, "total_steps": 40000, "loss": 0.0, "lr": 4.680376007819271e-05, "epoch": 114.21238938053098, "percentage": 16.28, "elapsed_time": "0:46:42", "remaining_time": "4:00:18", "throughput": 1320.25, "total_tokens": 3700240} {"current_steps": 6515, "total_steps": 40000, "loss": 0.0, "lr": 4.679895531574405e-05, "epoch": 114.30088495575221, "percentage": 16.29, "elapsed_time": "0:46:44", "remaining_time": "4:00:15", "throughput": 1320.36, "total_tokens": 3703280} {"current_steps": 6520, "total_steps": 40000, "loss": 0.0, "lr": 4.679414719162253e-05, "epoch": 114.38938053097345, "percentage": 16.3, "elapsed_time": "0:46:46", "remaining_time": "4:00:12", "throughput": 1320.49, "total_tokens": 3706368} {"current_steps": 6525, "total_steps": 40000, "loss": 0.0, "lr": 4.6789335706569635e-05, "epoch": 114.47787610619469, "percentage": 16.31, "elapsed_time": "0:46:48", "remaining_time": "4:00:10", "throughput": 1320.45, "total_tokens": 3708960} {"current_steps": 6530, "total_steps": 40000, "loss": 0.0, "lr": 4.678452086132734e-05, "epoch": 114.56637168141593, "percentage": 16.32, "elapsed_time": "0:46:50", "remaining_time": "4:00:07", "throughput": 1320.58, "total_tokens": 3712064} {"current_steps": 6535, "total_steps": 40000, "loss": 0.0, "lr": 4.677970265663818e-05, "epoch": 114.65486725663717, "percentage": 16.34, "elapsed_time": "0:46:52", "remaining_time": "4:00:04", "throughput": 1320.69, "total_tokens": 3715072} {"current_steps": 6540, "total_steps": 40000, "loss": 0.0, "lr": 4.677488109324517e-05, "epoch": 114.7433628318584, "percentage": 16.35, "elapsed_time": "0:46:55", "remaining_time": "4:00:02", "throughput": 1320.87, "total_tokens": 3718304} {"current_steps": 6545, "total_steps": 40000, "loss": 0.0, "lr": 4.6770056171891846e-05, "epoch": 114.83185840707965, "percentage": 16.36, "elapsed_time": "0:46:57", "remaining_time": "3:59:59", "throughput": 1320.84, "total_tokens": 3720928} {"current_steps": 6550, "total_steps": 40000, "loss": 0.0, "lr": 4.6765227893322286e-05, "epoch": 114.92035398230088, "percentage": 16.38, "elapsed_time": "0:46:59", "remaining_time": "3:59:57", "throughput": 1320.89, "total_tokens": 3723792} {"current_steps": 6555, "total_steps": 40000, "loss": 0.0, "lr": 4.676039625828107e-05, "epoch": 115.0, "percentage": 16.39, "elapsed_time": "0:47:01", "remaining_time": "3:59:54", "throughput": 1320.81, "total_tokens": 3726240} {"current_steps": 6560, "total_steps": 40000, "loss": 0.0, "lr": 4.675556126751328e-05, "epoch": 115.08849557522124, "percentage": 16.4, "elapsed_time": "0:47:03", "remaining_time": "3:59:52", "throughput": 1320.78, "total_tokens": 3729184} {"current_steps": 6565, "total_steps": 40000, "loss": 0.0, "lr": 4.6750722921764556e-05, "epoch": 115.17699115044248, "percentage": 16.41, "elapsed_time": "0:47:05", "remaining_time": "3:59:50", "throughput": 1320.96, "total_tokens": 3732400} {"current_steps": 6570, "total_steps": 40000, "loss": 0.0, "lr": 4.674588122178102e-05, "epoch": 115.26548672566372, "percentage": 16.43, "elapsed_time": "0:47:07", "remaining_time": "3:59:47", "throughput": 1321.03, "total_tokens": 3735344} {"current_steps": 6575, "total_steps": 40000, "loss": 0.0, "lr": 4.674103616830931e-05, "epoch": 115.35398230088495, "percentage": 16.44, "elapsed_time": "0:47:09", "remaining_time": "3:59:45", "throughput": 1321.08, "total_tokens": 3738208} {"current_steps": 6580, "total_steps": 40000, "loss": 0.0, "lr": 4.673618776209663e-05, "epoch": 115.4424778761062, "percentage": 16.45, "elapsed_time": "0:47:11", "remaining_time": "3:59:42", "throughput": 1321.17, "total_tokens": 3741184} {"current_steps": 6585, "total_steps": 40000, "loss": 0.0, "lr": 4.673133600389063e-05, "epoch": 115.53097345132744, "percentage": 16.46, "elapsed_time": "0:47:13", "remaining_time": "3:59:39", "throughput": 1321.08, "total_tokens": 3743648} {"current_steps": 6590, "total_steps": 40000, "loss": 0.0, "lr": 4.672648089443953e-05, "epoch": 115.61946902654867, "percentage": 16.48, "elapsed_time": "0:47:15", "remaining_time": "3:59:37", "throughput": 1321.13, "total_tokens": 3746544} {"current_steps": 6595, "total_steps": 40000, "loss": 0.0, "lr": 4.672162243449204e-05, "epoch": 115.70796460176992, "percentage": 16.49, "elapsed_time": "0:47:17", "remaining_time": "3:59:34", "throughput": 1321.03, "total_tokens": 3749008} {"current_steps": 6600, "total_steps": 40000, "loss": 0.0, "lr": 4.67167606247974e-05, "epoch": 115.79646017699115, "percentage": 16.5, "elapsed_time": "0:47:20", "remaining_time": "3:59:32", "throughput": 1321.34, "total_tokens": 3752608} {"current_steps": 6600, "total_steps": 40000, "eval_loss": 0.40091925859451294, "epoch": 115.79646017699115, "percentage": 16.5, "elapsed_time": "0:47:21", "remaining_time": "3:59:37", "throughput": 1320.84, "total_tokens": 3752608} {"current_steps": 6605, "total_steps": 40000, "loss": 0.0, "lr": 4.671189546610536e-05, "epoch": 115.88495575221239, "percentage": 16.51, "elapsed_time": "0:47:24", "remaining_time": "3:59:43", "throughput": 1320.01, "total_tokens": 3755152} {"current_steps": 6610, "total_steps": 40000, "loss": 0.0, "lr": 4.67070269591662e-05, "epoch": 115.97345132743362, "percentage": 16.53, "elapsed_time": "0:47:26", "remaining_time": "3:59:40", "throughput": 1320.08, "total_tokens": 3758048} {"current_steps": 6615, "total_steps": 40000, "loss": 0.0, "lr": 4.670215510473068e-05, "epoch": 116.05309734513274, "percentage": 16.54, "elapsed_time": "0:47:29", "remaining_time": "3:59:38", "throughput": 1319.99, "total_tokens": 3760768} {"current_steps": 6620, "total_steps": 40000, "loss": 0.0, "lr": 4.669727990355013e-05, "epoch": 116.14159292035399, "percentage": 16.55, "elapsed_time": "0:47:31", "remaining_time": "3:59:36", "throughput": 1319.92, "total_tokens": 3763296} {"current_steps": 6625, "total_steps": 40000, "loss": 0.0, "lr": 4.669240135637635e-05, "epoch": 116.23008849557522, "percentage": 16.56, "elapsed_time": "0:47:33", "remaining_time": "3:59:33", "throughput": 1320.14, "total_tokens": 3766656} {"current_steps": 6630, "total_steps": 40000, "loss": 0.0, "lr": 4.6687519463961675e-05, "epoch": 116.31858407079646, "percentage": 16.57, "elapsed_time": "0:47:35", "remaining_time": "3:59:31", "throughput": 1320.21, "total_tokens": 3769568} {"current_steps": 6635, "total_steps": 40000, "loss": 0.0, "lr": 4.668263422705896e-05, "epoch": 116.40707964601769, "percentage": 16.59, "elapsed_time": "0:47:37", "remaining_time": "3:59:28", "throughput": 1320.27, "total_tokens": 3772480} {"current_steps": 6640, "total_steps": 40000, "loss": 0.0, "lr": 4.667774564642156e-05, "epoch": 116.49557522123894, "percentage": 16.6, "elapsed_time": "0:47:39", "remaining_time": "3:59:25", "throughput": 1320.33, "total_tokens": 3775360} {"current_steps": 6645, "total_steps": 40000, "loss": 0.0, "lr": 4.6672853722803365e-05, "epoch": 116.58407079646018, "percentage": 16.61, "elapsed_time": "0:47:41", "remaining_time": "3:59:23", "throughput": 1320.42, "total_tokens": 3778352} {"current_steps": 6650, "total_steps": 40000, "loss": 0.0, "lr": 4.666795845695877e-05, "epoch": 116.67256637168141, "percentage": 16.62, "elapsed_time": "0:47:43", "remaining_time": "3:59:20", "throughput": 1320.47, "total_tokens": 3781216} {"current_steps": 6655, "total_steps": 40000, "loss": 0.0, "lr": 4.666305984964269e-05, "epoch": 116.76106194690266, "percentage": 16.64, "elapsed_time": "0:47:45", "remaining_time": "3:59:18", "throughput": 1320.36, "total_tokens": 3783664} {"current_steps": 6660, "total_steps": 40000, "loss": 0.0, "lr": 4.6658157901610535e-05, "epoch": 116.84955752212389, "percentage": 16.65, "elapsed_time": "0:47:47", "remaining_time": "3:59:15", "throughput": 1320.42, "total_tokens": 3786576} {"current_steps": 6665, "total_steps": 40000, "loss": 0.0, "lr": 4.665325261361826e-05, "epoch": 116.93805309734513, "percentage": 16.66, "elapsed_time": "0:47:49", "remaining_time": "3:59:13", "throughput": 1320.5, "total_tokens": 3789504} {"current_steps": 6670, "total_steps": 40000, "loss": 0.0, "lr": 4.664834398642232e-05, "epoch": 117.01769911504425, "percentage": 16.68, "elapsed_time": "0:47:51", "remaining_time": "3:59:11", "throughput": 1320.25, "total_tokens": 3791752} {"current_steps": 6675, "total_steps": 40000, "loss": 0.0, "lr": 4.6643432020779686e-05, "epoch": 117.10619469026548, "percentage": 16.69, "elapsed_time": "0:47:54", "remaining_time": "3:59:08", "throughput": 1320.26, "total_tokens": 3794520} {"current_steps": 6680, "total_steps": 40000, "loss": 0.0, "lr": 4.663851671744786e-05, "epoch": 117.19469026548673, "percentage": 16.7, "elapsed_time": "0:47:56", "remaining_time": "3:59:06", "throughput": 1320.21, "total_tokens": 3797096} {"current_steps": 6685, "total_steps": 40000, "loss": 0.0, "lr": 4.6633598077184815e-05, "epoch": 117.28318584070796, "percentage": 16.71, "elapsed_time": "0:47:58", "remaining_time": "3:59:03", "throughput": 1320.13, "total_tokens": 3799576} {"current_steps": 6690, "total_steps": 40000, "loss": 0.0, "lr": 4.662867610074908e-05, "epoch": 117.3716814159292, "percentage": 16.73, "elapsed_time": "0:48:00", "remaining_time": "3:59:01", "throughput": 1320.24, "total_tokens": 3802632} {"current_steps": 6695, "total_steps": 40000, "loss": 0.0, "lr": 4.6623750788899696e-05, "epoch": 117.46017699115045, "percentage": 16.74, "elapsed_time": "0:48:02", "remaining_time": "3:58:58", "throughput": 1320.41, "total_tokens": 3805864} {"current_steps": 6700, "total_steps": 40000, "loss": 0.0, "lr": 4.6618822142396195e-05, "epoch": 117.54867256637168, "percentage": 16.75, "elapsed_time": "0:48:04", "remaining_time": "3:58:55", "throughput": 1320.59, "total_tokens": 3809096} {"current_steps": 6705, "total_steps": 40000, "loss": 0.0, "lr": 4.661389016199864e-05, "epoch": 117.63716814159292, "percentage": 16.76, "elapsed_time": "0:48:06", "remaining_time": "3:58:53", "throughput": 1320.63, "total_tokens": 3811912} {"current_steps": 6710, "total_steps": 40000, "loss": 0.0, "lr": 4.660895484846761e-05, "epoch": 117.72566371681415, "percentage": 16.78, "elapsed_time": "0:48:08", "remaining_time": "3:58:50", "throughput": 1320.55, "total_tokens": 3814424} {"current_steps": 6715, "total_steps": 40000, "loss": 0.0, "lr": 4.660401620256418e-05, "epoch": 117.8141592920354, "percentage": 16.79, "elapsed_time": "0:48:10", "remaining_time": "3:58:48", "throughput": 1320.67, "total_tokens": 3817496} {"current_steps": 6720, "total_steps": 40000, "loss": 0.0, "lr": 4.659907422504997e-05, "epoch": 117.90265486725664, "percentage": 16.8, "elapsed_time": "0:48:12", "remaining_time": "3:58:45", "throughput": 1320.65, "total_tokens": 3820184} {"current_steps": 6725, "total_steps": 40000, "loss": 0.0, "lr": 4.6594128916687074e-05, "epoch": 117.99115044247787, "percentage": 16.81, "elapsed_time": "0:48:14", "remaining_time": "3:58:42", "throughput": 1320.82, "total_tokens": 3823400} {"current_steps": 6730, "total_steps": 40000, "loss": 0.0, "lr": 4.658918027823813e-05, "epoch": 118.070796460177, "percentage": 16.83, "elapsed_time": "0:48:16", "remaining_time": "3:58:41", "throughput": 1320.67, "total_tokens": 3825952} {"current_steps": 6735, "total_steps": 40000, "loss": 0.0, "lr": 4.658422831046628e-05, "epoch": 118.15929203539822, "percentage": 16.84, "elapsed_time": "0:48:19", "remaining_time": "3:58:38", "throughput": 1320.75, "total_tokens": 3828912} {"current_steps": 6740, "total_steps": 40000, "loss": 0.0, "lr": 4.657927301413518e-05, "epoch": 118.24778761061947, "percentage": 16.85, "elapsed_time": "0:48:21", "remaining_time": "3:58:36", "throughput": 1320.81, "total_tokens": 3831824} {"current_steps": 6745, "total_steps": 40000, "loss": 0.0, "lr": 4.657431439000901e-05, "epoch": 118.33628318584071, "percentage": 16.86, "elapsed_time": "0:48:23", "remaining_time": "3:58:33", "throughput": 1320.86, "total_tokens": 3834688} {"current_steps": 6750, "total_steps": 40000, "loss": 0.0, "lr": 4.656935243885243e-05, "epoch": 118.42477876106194, "percentage": 16.88, "elapsed_time": "0:48:25", "remaining_time": "3:58:31", "throughput": 1320.95, "total_tokens": 3837680} {"current_steps": 6755, "total_steps": 40000, "loss": 0.0, "lr": 4.656438716143066e-05, "epoch": 118.51327433628319, "percentage": 16.89, "elapsed_time": "0:48:27", "remaining_time": "3:58:28", "throughput": 1320.87, "total_tokens": 3840176} {"current_steps": 6760, "total_steps": 40000, "loss": 0.0, "lr": 4.6559418558509384e-05, "epoch": 118.60176991150442, "percentage": 16.9, "elapsed_time": "0:48:29", "remaining_time": "3:58:25", "throughput": 1321.09, "total_tokens": 3843536} {"current_steps": 6765, "total_steps": 40000, "loss": 0.0, "lr": 4.6554446630854833e-05, "epoch": 118.69026548672566, "percentage": 16.91, "elapsed_time": "0:48:31", "remaining_time": "3:58:23", "throughput": 1321.17, "total_tokens": 3846512} {"current_steps": 6770, "total_steps": 40000, "loss": 0.0, "lr": 4.654947137923374e-05, "epoch": 118.77876106194691, "percentage": 16.93, "elapsed_time": "0:48:33", "remaining_time": "3:58:20", "throughput": 1321.15, "total_tokens": 3849184} {"current_steps": 6775, "total_steps": 40000, "loss": 0.0, "lr": 4.654449280441335e-05, "epoch": 118.86725663716814, "percentage": 16.94, "elapsed_time": "0:48:35", "remaining_time": "3:58:18", "throughput": 1321.2, "total_tokens": 3852064} {"current_steps": 6780, "total_steps": 40000, "loss": 0.0, "lr": 4.653951090716143e-05, "epoch": 118.95575221238938, "percentage": 16.95, "elapsed_time": "0:48:37", "remaining_time": "3:58:15", "throughput": 1321.18, "total_tokens": 3854688} {"current_steps": 6785, "total_steps": 40000, "loss": 0.0, "lr": 4.653452568824625e-05, "epoch": 119.03539823008849, "percentage": 16.96, "elapsed_time": "0:48:39", "remaining_time": "3:58:13", "throughput": 1320.91, "total_tokens": 3856896} {"current_steps": 6790, "total_steps": 40000, "loss": 0.0, "lr": 4.6529537148436585e-05, "epoch": 119.12389380530973, "percentage": 16.98, "elapsed_time": "0:48:41", "remaining_time": "3:58:11", "throughput": 1320.75, "total_tokens": 3859152} {"current_steps": 6795, "total_steps": 40000, "loss": 0.0, "lr": 4.6524545288501734e-05, "epoch": 119.21238938053098, "percentage": 16.99, "elapsed_time": "0:48:44", "remaining_time": "3:58:08", "throughput": 1320.88, "total_tokens": 3862256} {"current_steps": 6800, "total_steps": 40000, "loss": 0.0, "lr": 4.6519550109211506e-05, "epoch": 119.30088495575221, "percentage": 17.0, "elapsed_time": "0:48:46", "remaining_time": "3:58:06", "throughput": 1321.01, "total_tokens": 3865376} {"current_steps": 6800, "total_steps": 40000, "eval_loss": 0.4005506932735443, "epoch": 119.30088495575221, "percentage": 17.0, "elapsed_time": "0:48:47", "remaining_time": "3:58:11", "throughput": 1320.53, "total_tokens": 3865376} {"current_steps": 6805, "total_steps": 40000, "loss": 0.0, "lr": 4.651455161133622e-05, "epoch": 119.38938053097345, "percentage": 17.01, "elapsed_time": "0:48:51", "remaining_time": "3:58:17", "throughput": 1319.67, "total_tokens": 3868048} {"current_steps": 6810, "total_steps": 40000, "loss": 0.0, "lr": 4.6509549795646704e-05, "epoch": 119.47787610619469, "percentage": 17.03, "elapsed_time": "0:48:53", "remaining_time": "3:58:15", "throughput": 1319.68, "total_tokens": 3870816} {"current_steps": 6815, "total_steps": 40000, "loss": 0.0, "lr": 4.6504544662914306e-05, "epoch": 119.56637168141593, "percentage": 17.04, "elapsed_time": "0:48:55", "remaining_time": "3:58:12", "throughput": 1319.85, "total_tokens": 3874048} {"current_steps": 6820, "total_steps": 40000, "loss": 0.0, "lr": 4.6499536213910876e-05, "epoch": 119.65486725663717, "percentage": 17.05, "elapsed_time": "0:48:57", "remaining_time": "3:58:10", "throughput": 1319.87, "total_tokens": 3876832} {"current_steps": 6825, "total_steps": 40000, "loss": 0.0, "lr": 4.6494524449408786e-05, "epoch": 119.7433628318584, "percentage": 17.06, "elapsed_time": "0:48:59", "remaining_time": "3:58:07", "throughput": 1319.79, "total_tokens": 3879296} {"current_steps": 6830, "total_steps": 40000, "loss": 0.0, "lr": 4.6489509370180903e-05, "epoch": 119.83185840707965, "percentage": 17.08, "elapsed_time": "0:49:01", "remaining_time": "3:58:04", "throughput": 1319.98, "total_tokens": 3882592} {"current_steps": 6835, "total_steps": 40000, "loss": 0.0, "lr": 4.648449097700063e-05, "epoch": 119.92035398230088, "percentage": 17.09, "elapsed_time": "0:49:03", "remaining_time": "3:58:02", "throughput": 1320.07, "total_tokens": 3885584} {"current_steps": 6840, "total_steps": 40000, "loss": 0.0, "lr": 4.647946927064185e-05, "epoch": 120.0, "percentage": 17.1, "elapsed_time": "0:49:05", "remaining_time": "3:57:59", "throughput": 1320.01, "total_tokens": 3888056} {"current_steps": 6845, "total_steps": 40000, "loss": 0.0, "lr": 4.647444425187898e-05, "epoch": 120.08849557522124, "percentage": 17.11, "elapsed_time": "0:49:07", "remaining_time": "3:57:58", "throughput": 1319.88, "total_tokens": 3890744} {"current_steps": 6850, "total_steps": 40000, "loss": 0.0, "lr": 4.646941592148695e-05, "epoch": 120.17699115044248, "percentage": 17.12, "elapsed_time": "0:49:09", "remaining_time": "3:57:55", "throughput": 1319.94, "total_tokens": 3893640} {"current_steps": 6855, "total_steps": 40000, "loss": 0.0, "lr": 4.646438428024117e-05, "epoch": 120.26548672566372, "percentage": 17.14, "elapsed_time": "0:49:11", "remaining_time": "3:57:52", "throughput": 1319.91, "total_tokens": 3896264} {"current_steps": 6860, "total_steps": 40000, "loss": 0.0, "lr": 4.64593493289176e-05, "epoch": 120.35398230088495, "percentage": 17.15, "elapsed_time": "0:49:13", "remaining_time": "3:57:50", "throughput": 1319.98, "total_tokens": 3899192} {"current_steps": 6865, "total_steps": 40000, "loss": 0.0, "lr": 4.64543110682927e-05, "epoch": 120.4424778761062, "percentage": 17.16, "elapsed_time": "0:49:16", "remaining_time": "3:57:47", "throughput": 1319.96, "total_tokens": 3901880} {"current_steps": 6870, "total_steps": 40000, "loss": 0.0, "lr": 4.644926949914341e-05, "epoch": 120.53097345132744, "percentage": 17.18, "elapsed_time": "0:49:18", "remaining_time": "3:57:45", "throughput": 1320.04, "total_tokens": 3904824} {"current_steps": 6875, "total_steps": 40000, "loss": 0.0, "lr": 4.644422462224722e-05, "epoch": 120.61946902654867, "percentage": 17.19, "elapsed_time": "0:49:20", "remaining_time": "3:57:42", "throughput": 1320.1, "total_tokens": 3907720} {"current_steps": 6880, "total_steps": 40000, "loss": 0.0, "lr": 4.643917643838211e-05, "epoch": 120.70796460176992, "percentage": 17.2, "elapsed_time": "0:49:22", "remaining_time": "3:57:40", "throughput": 1320.31, "total_tokens": 3911064} {"current_steps": 6885, "total_steps": 40000, "loss": 0.0, "lr": 4.6434124948326564e-05, "epoch": 120.79646017699115, "percentage": 17.21, "elapsed_time": "0:49:24", "remaining_time": "3:57:37", "throughput": 1320.31, "total_tokens": 3913784} {"current_steps": 6890, "total_steps": 40000, "loss": 0.0, "lr": 4.6429070152859594e-05, "epoch": 120.88495575221239, "percentage": 17.22, "elapsed_time": "0:49:26", "remaining_time": "3:57:34", "throughput": 1320.3, "total_tokens": 3916504} {"current_steps": 6895, "total_steps": 40000, "loss": 0.0, "lr": 4.6424012052760714e-05, "epoch": 120.97345132743362, "percentage": 17.24, "elapsed_time": "0:49:28", "remaining_time": "3:57:32", "throughput": 1320.37, "total_tokens": 3919400} {"current_steps": 6900, "total_steps": 40000, "loss": 0.0, "lr": 4.6418950648809945e-05, "epoch": 121.05309734513274, "percentage": 17.25, "elapsed_time": "0:49:30", "remaining_time": "3:57:30", "throughput": 1320.2, "total_tokens": 3921912} {"current_steps": 6905, "total_steps": 40000, "loss": 0.0, "lr": 4.641388594178782e-05, "epoch": 121.14159292035399, "percentage": 17.26, "elapsed_time": "0:49:32", "remaining_time": "3:57:28", "throughput": 1320.37, "total_tokens": 3925128} {"current_steps": 6910, "total_steps": 40000, "loss": 0.0, "lr": 4.640881793247538e-05, "epoch": 121.23008849557522, "percentage": 17.27, "elapsed_time": "0:49:34", "remaining_time": "3:57:25", "throughput": 1320.51, "total_tokens": 3928264} {"current_steps": 6915, "total_steps": 40000, "loss": 0.0, "lr": 4.6403746621654173e-05, "epoch": 121.31858407079646, "percentage": 17.29, "elapsed_time": "0:49:36", "remaining_time": "3:57:22", "throughput": 1320.45, "total_tokens": 3930824} {"current_steps": 6920, "total_steps": 40000, "loss": 0.0, "lr": 4.639867201010626e-05, "epoch": 121.40707964601769, "percentage": 17.3, "elapsed_time": "0:49:38", "remaining_time": "3:57:20", "throughput": 1320.56, "total_tokens": 3933864} {"current_steps": 6925, "total_steps": 40000, "loss": 0.0, "lr": 4.6393594098614204e-05, "epoch": 121.49557522123894, "percentage": 17.31, "elapsed_time": "0:49:40", "remaining_time": "3:57:17", "throughput": 1320.53, "total_tokens": 3936504} {"current_steps": 6930, "total_steps": 40000, "loss": 0.0, "lr": 4.63885128879611e-05, "epoch": 121.58407079646018, "percentage": 17.32, "elapsed_time": "0:49:43", "remaining_time": "3:57:15", "throughput": 1320.71, "total_tokens": 3939752} {"current_steps": 6935, "total_steps": 40000, "loss": 0.0, "lr": 4.638342837893052e-05, "epoch": 121.67256637168141, "percentage": 17.34, "elapsed_time": "0:49:45", "remaining_time": "3:57:12", "throughput": 1320.84, "total_tokens": 3942872} {"current_steps": 6940, "total_steps": 40000, "loss": 0.0, "lr": 4.6378340572306565e-05, "epoch": 121.76106194690266, "percentage": 17.35, "elapsed_time": "0:49:47", "remaining_time": "3:57:10", "throughput": 1320.76, "total_tokens": 3945368} {"current_steps": 6945, "total_steps": 40000, "loss": 0.0, "lr": 4.6373249468873833e-05, "epoch": 121.84955752212389, "percentage": 17.36, "elapsed_time": "0:49:49", "remaining_time": "3:57:07", "throughput": 1320.77, "total_tokens": 3948120} {"current_steps": 6950, "total_steps": 40000, "loss": 0.0, "lr": 4.636815506941744e-05, "epoch": 121.93805309734513, "percentage": 17.38, "elapsed_time": "0:49:51", "remaining_time": "3:57:04", "throughput": 1320.89, "total_tokens": 3951208} {"current_steps": 6955, "total_steps": 40000, "loss": 0.0, "lr": 4.6363057374723004e-05, "epoch": 122.01769911504425, "percentage": 17.39, "elapsed_time": "0:49:53", "remaining_time": "3:57:03", "throughput": 1320.69, "total_tokens": 3953560} {"current_steps": 6960, "total_steps": 40000, "loss": 0.0, "lr": 4.635795638557666e-05, "epoch": 122.10619469026548, "percentage": 17.4, "elapsed_time": "0:49:55", "remaining_time": "3:57:00", "throughput": 1320.58, "total_tokens": 3955960} {"current_steps": 6965, "total_steps": 40000, "loss": 0.0, "lr": 4.635285210276504e-05, "epoch": 122.19469026548673, "percentage": 17.41, "elapsed_time": "0:49:57", "remaining_time": "3:56:58", "throughput": 1320.68, "total_tokens": 3958984} {"current_steps": 6970, "total_steps": 40000, "loss": 0.0, "lr": 4.6347744527075295e-05, "epoch": 122.28318584070796, "percentage": 17.42, "elapsed_time": "0:49:59", "remaining_time": "3:56:55", "throughput": 1320.84, "total_tokens": 3962200} {"current_steps": 6975, "total_steps": 40000, "loss": 0.0, "lr": 4.634263365929506e-05, "epoch": 122.3716814159292, "percentage": 17.44, "elapsed_time": "0:50:01", "remaining_time": "3:56:53", "throughput": 1320.75, "total_tokens": 3964696} {"current_steps": 6980, "total_steps": 40000, "loss": 0.0, "lr": 4.6337519500212515e-05, "epoch": 122.46017699115045, "percentage": 17.45, "elapsed_time": "0:50:03", "remaining_time": "3:56:50", "throughput": 1320.86, "total_tokens": 3967752} {"current_steps": 6985, "total_steps": 40000, "loss": 0.0, "lr": 4.633240205061632e-05, "epoch": 122.54867256637168, "percentage": 17.46, "elapsed_time": "0:50:05", "remaining_time": "3:56:47", "throughput": 1320.94, "total_tokens": 3970712} {"current_steps": 6990, "total_steps": 40000, "loss": 0.0, "lr": 4.632728131129565e-05, "epoch": 122.63716814159292, "percentage": 17.47, "elapsed_time": "0:50:08", "remaining_time": "3:56:45", "throughput": 1321.13, "total_tokens": 3974008} {"current_steps": 6995, "total_steps": 40000, "loss": 0.0, "lr": 4.632215728304018e-05, "epoch": 122.72566371681415, "percentage": 17.49, "elapsed_time": "0:50:10", "remaining_time": "3:56:42", "throughput": 1321.04, "total_tokens": 3976472} {"current_steps": 7000, "total_steps": 40000, "loss": 0.0, "lr": 4.63170299666401e-05, "epoch": 122.8141592920354, "percentage": 17.5, "elapsed_time": "0:50:12", "remaining_time": "3:56:40", "throughput": 1321.13, "total_tokens": 3979464} {"current_steps": 7000, "total_steps": 40000, "eval_loss": 0.40326330065727234, "epoch": 122.8141592920354, "percentage": 17.5, "elapsed_time": "0:50:13", "remaining_time": "3:56:45", "throughput": 1320.66, "total_tokens": 3979464} {"current_steps": 7005, "total_steps": 40000, "loss": 0.0, "lr": 4.631189936288612e-05, "epoch": 122.90265486725664, "percentage": 17.51, "elapsed_time": "0:50:16", "remaining_time": "3:56:50", "throughput": 1319.99, "total_tokens": 3982408} {"current_steps": 7010, "total_steps": 40000, "loss": 0.0, "lr": 4.630676547256944e-05, "epoch": 122.99115044247787, "percentage": 17.52, "elapsed_time": "0:50:19", "remaining_time": "3:56:47", "throughput": 1319.99, "total_tokens": 3985096} {"current_steps": 7015, "total_steps": 40000, "loss": 0.0, "lr": 4.630162829648176e-05, "epoch": 123.070796460177, "percentage": 17.54, "elapsed_time": "0:50:21", "remaining_time": "3:56:46", "throughput": 1320.09, "total_tokens": 3988384} {"current_steps": 7020, "total_steps": 40000, "loss": 0.0, "lr": 4.629648783541531e-05, "epoch": 123.15929203539822, "percentage": 17.55, "elapsed_time": "0:50:23", "remaining_time": "3:56:43", "throughput": 1320.17, "total_tokens": 3991360} {"current_steps": 7025, "total_steps": 40000, "loss": 0.0, "lr": 4.6291344090162804e-05, "epoch": 123.24778761061947, "percentage": 17.56, "elapsed_time": "0:50:25", "remaining_time": "3:56:41", "throughput": 1320.2, "total_tokens": 3994176} {"current_steps": 7030, "total_steps": 40000, "loss": 0.0, "lr": 4.628619706151748e-05, "epoch": 123.33628318584071, "percentage": 17.57, "elapsed_time": "0:50:27", "remaining_time": "3:56:38", "throughput": 1320.17, "total_tokens": 3996816} {"current_steps": 7035, "total_steps": 40000, "loss": 0.0, "lr": 4.628104675027306e-05, "epoch": 123.42477876106194, "percentage": 17.59, "elapsed_time": "0:50:29", "remaining_time": "3:56:36", "throughput": 1320.18, "total_tokens": 3999552} {"current_steps": 7040, "total_steps": 40000, "loss": 0.0, "lr": 4.6275893157223805e-05, "epoch": 123.51327433628319, "percentage": 17.6, "elapsed_time": "0:50:31", "remaining_time": "3:56:33", "throughput": 1320.18, "total_tokens": 4002288} {"current_steps": 7045, "total_steps": 40000, "loss": 0.0, "lr": 4.627073628316445e-05, "epoch": 123.60176991150442, "percentage": 17.61, "elapsed_time": "0:50:33", "remaining_time": "3:56:30", "throughput": 1320.26, "total_tokens": 4005264} {"current_steps": 7050, "total_steps": 40000, "loss": 0.0, "lr": 4.626557612889026e-05, "epoch": 123.69026548672566, "percentage": 17.62, "elapsed_time": "0:50:35", "remaining_time": "3:56:28", "throughput": 1320.38, "total_tokens": 4008352} {"current_steps": 7055, "total_steps": 40000, "loss": 0.0, "lr": 4.626041269519699e-05, "epoch": 123.77876106194691, "percentage": 17.64, "elapsed_time": "0:50:37", "remaining_time": "3:56:25", "throughput": 1320.3, "total_tokens": 4010816} {"current_steps": 7060, "total_steps": 40000, "loss": 0.0, "lr": 4.6255245982880905e-05, "epoch": 123.86725663716814, "percentage": 17.65, "elapsed_time": "0:50:39", "remaining_time": "3:56:23", "throughput": 1320.31, "total_tokens": 4013584} {"current_steps": 7065, "total_steps": 40000, "loss": 0.0, "lr": 4.625007599273879e-05, "epoch": 123.95575221238938, "percentage": 17.66, "elapsed_time": "0:50:41", "remaining_time": "3:56:20", "throughput": 1320.34, "total_tokens": 4016400} {"current_steps": 7070, "total_steps": 40000, "loss": 0.0, "lr": 4.6244902725567895e-05, "epoch": 124.03539823008849, "percentage": 17.68, "elapsed_time": "0:50:44", "remaining_time": "3:56:18", "throughput": 1320.24, "total_tokens": 4019080} {"current_steps": 7075, "total_steps": 40000, "loss": 0.0, "lr": 4.6239726182166024e-05, "epoch": 124.12389380530973, "percentage": 17.69, "elapsed_time": "0:50:46", "remaining_time": "3:56:16", "throughput": 1320.46, "total_tokens": 4022488} {"current_steps": 7080, "total_steps": 40000, "loss": 0.0, "lr": 4.623454636333147e-05, "epoch": 124.21238938053098, "percentage": 17.7, "elapsed_time": "0:50:48", "remaining_time": "3:56:13", "throughput": 1320.43, "total_tokens": 4025128} {"current_steps": 7085, "total_steps": 40000, "loss": 0.0, "lr": 4.622936326986301e-05, "epoch": 124.30088495575221, "percentage": 17.71, "elapsed_time": "0:50:50", "remaining_time": "3:56:11", "throughput": 1320.47, "total_tokens": 4027976} {"current_steps": 7090, "total_steps": 40000, "loss": 0.0, "lr": 4.6224176902559946e-05, "epoch": 124.38938053097345, "percentage": 17.72, "elapsed_time": "0:50:52", "remaining_time": "3:56:08", "throughput": 1320.73, "total_tokens": 4031496} {"current_steps": 7095, "total_steps": 40000, "loss": 0.0, "lr": 4.621898726222209e-05, "epoch": 124.47787610619469, "percentage": 17.74, "elapsed_time": "0:50:54", "remaining_time": "3:56:06", "throughput": 1320.83, "total_tokens": 4034536} {"current_steps": 7100, "total_steps": 40000, "loss": 0.0, "lr": 4.6213794349649744e-05, "epoch": 124.56637168141593, "percentage": 17.75, "elapsed_time": "0:50:56", "remaining_time": "3:56:03", "throughput": 1320.78, "total_tokens": 4037096} {"current_steps": 7105, "total_steps": 40000, "loss": 0.0, "lr": 4.6208598165643715e-05, "epoch": 124.65486725663717, "percentage": 17.76, "elapsed_time": "0:50:58", "remaining_time": "3:56:01", "throughput": 1320.65, "total_tokens": 4039448} {"current_steps": 7110, "total_steps": 40000, "loss": 0.0, "lr": 4.620339871100533e-05, "epoch": 124.7433628318584, "percentage": 17.77, "elapsed_time": "0:51:00", "remaining_time": "3:55:58", "throughput": 1320.84, "total_tokens": 4042760} {"current_steps": 7115, "total_steps": 40000, "loss": 0.0, "lr": 4.6198195986536394e-05, "epoch": 124.83185840707965, "percentage": 17.79, "elapsed_time": "0:51:02", "remaining_time": "3:55:56", "throughput": 1320.74, "total_tokens": 4045176} {"current_steps": 7120, "total_steps": 40000, "loss": 0.0, "lr": 4.619298999303926e-05, "epoch": 124.92035398230088, "percentage": 17.8, "elapsed_time": "0:51:04", "remaining_time": "3:55:53", "throughput": 1320.73, "total_tokens": 4047864} {"current_steps": 7125, "total_steps": 40000, "loss": 0.0, "lr": 4.618778073131673e-05, "epoch": 125.0, "percentage": 17.81, "elapsed_time": "0:51:06", "remaining_time": "3:55:50", "throughput": 1320.64, "total_tokens": 4050248} {"current_steps": 7130, "total_steps": 40000, "loss": 0.0, "lr": 4.618256820217215e-05, "epoch": 125.08849557522124, "percentage": 17.82, "elapsed_time": "0:51:09", "remaining_time": "3:55:49", "throughput": 1320.66, "total_tokens": 4053352} {"current_steps": 7135, "total_steps": 40000, "loss": 0.0, "lr": 4.617735240640936e-05, "epoch": 125.17699115044248, "percentage": 17.84, "elapsed_time": "0:51:11", "remaining_time": "3:55:46", "throughput": 1320.66, "total_tokens": 4056088} {"current_steps": 7140, "total_steps": 40000, "loss": 0.0, "lr": 4.6172133344832705e-05, "epoch": 125.26548672566372, "percentage": 17.85, "elapsed_time": "0:51:13", "remaining_time": "3:55:44", "throughput": 1320.71, "total_tokens": 4058968} {"current_steps": 7145, "total_steps": 40000, "loss": 0.0, "lr": 4.6166911018247004e-05, "epoch": 125.35398230088495, "percentage": 17.86, "elapsed_time": "0:51:15", "remaining_time": "3:55:41", "throughput": 1320.8, "total_tokens": 4061976} {"current_steps": 7150, "total_steps": 40000, "loss": 0.0, "lr": 4.616168542745764e-05, "epoch": 125.4424778761062, "percentage": 17.88, "elapsed_time": "0:51:17", "remaining_time": "3:55:39", "throughput": 1320.8, "total_tokens": 4064696} {"current_steps": 7155, "total_steps": 40000, "loss": 0.0, "lr": 4.6156456573270446e-05, "epoch": 125.53097345132744, "percentage": 17.89, "elapsed_time": "0:51:19", "remaining_time": "3:55:36", "throughput": 1320.85, "total_tokens": 4067592} {"current_steps": 7160, "total_steps": 40000, "loss": 0.0, "lr": 4.615122445649177e-05, "epoch": 125.61946902654867, "percentage": 17.9, "elapsed_time": "0:51:21", "remaining_time": "3:55:33", "throughput": 1320.97, "total_tokens": 4070696} {"current_steps": 7165, "total_steps": 40000, "loss": 0.0, "lr": 4.6145989077928486e-05, "epoch": 125.70796460176992, "percentage": 17.91, "elapsed_time": "0:51:23", "remaining_time": "3:55:31", "throughput": 1320.87, "total_tokens": 4073112} {"current_steps": 7170, "total_steps": 40000, "loss": 0.0, "lr": 4.6140750438387953e-05, "epoch": 125.79646017699115, "percentage": 17.93, "elapsed_time": "0:51:25", "remaining_time": "3:55:28", "throughput": 1320.95, "total_tokens": 4076072} {"current_steps": 7175, "total_steps": 40000, "loss": 0.0, "lr": 4.613550853867803e-05, "epoch": 125.88495575221239, "percentage": 17.94, "elapsed_time": "0:51:27", "remaining_time": "3:55:26", "throughput": 1320.99, "total_tokens": 4078920} {"current_steps": 7180, "total_steps": 40000, "loss": 0.0, "lr": 4.613026337960708e-05, "epoch": 125.97345132743362, "percentage": 17.95, "elapsed_time": "0:51:29", "remaining_time": "3:55:23", "throughput": 1321.15, "total_tokens": 4082120} {"current_steps": 7185, "total_steps": 40000, "loss": 0.0, "lr": 4.612501496198398e-05, "epoch": 126.05309734513274, "percentage": 17.96, "elapsed_time": "0:51:32", "remaining_time": "3:55:22", "throughput": 1320.97, "total_tokens": 4084544} {"current_steps": 7190, "total_steps": 40000, "loss": 0.0, "lr": 4.61197632866181e-05, "epoch": 126.14159292035399, "percentage": 17.97, "elapsed_time": "0:51:34", "remaining_time": "3:55:19", "throughput": 1321.11, "total_tokens": 4087728} {"current_steps": 7195, "total_steps": 40000, "loss": 0.0, "lr": 4.611450835431931e-05, "epoch": 126.23008849557522, "percentage": 17.99, "elapsed_time": "0:51:36", "remaining_time": "3:55:16", "throughput": 1321.19, "total_tokens": 4090704} {"current_steps": 7200, "total_steps": 40000, "loss": 0.0, "lr": 4.6109250165898e-05, "epoch": 126.31858407079646, "percentage": 18.0, "elapsed_time": "0:51:38", "remaining_time": "3:55:14", "throughput": 1321.15, "total_tokens": 4093296} {"current_steps": 7200, "total_steps": 40000, "eval_loss": 0.40944311022758484, "epoch": 126.31858407079646, "percentage": 18.0, "elapsed_time": "0:51:39", "remaining_time": "3:55:19", "throughput": 1320.7, "total_tokens": 4093296} {"current_steps": 7205, "total_steps": 40000, "loss": 0.0, "lr": 4.610398872216503e-05, "epoch": 126.40707964601769, "percentage": 18.01, "elapsed_time": "0:51:43", "remaining_time": "3:55:24", "throughput": 1320.02, "total_tokens": 4096144} {"current_steps": 7210, "total_steps": 40000, "loss": 0.0, "lr": 4.6098724023931796e-05, "epoch": 126.49557522123894, "percentage": 18.02, "elapsed_time": "0:51:45", "remaining_time": "3:55:21", "throughput": 1319.93, "total_tokens": 4098608} {"current_steps": 7215, "total_steps": 40000, "loss": 0.0, "lr": 4.609345607201017e-05, "epoch": 126.58407079646018, "percentage": 18.04, "elapsed_time": "0:51:47", "remaining_time": "3:55:19", "throughput": 1320.07, "total_tokens": 4101792} {"current_steps": 7220, "total_steps": 40000, "loss": 0.0, "lr": 4.608818486721254e-05, "epoch": 126.67256637168141, "percentage": 18.05, "elapsed_time": "0:51:49", "remaining_time": "3:55:16", "throughput": 1320.28, "total_tokens": 4105184} {"current_steps": 7225, "total_steps": 40000, "loss": 0.0, "lr": 4.608291041035179e-05, "epoch": 126.76106194690266, "percentage": 18.06, "elapsed_time": "0:51:51", "remaining_time": "3:55:14", "throughput": 1320.3, "total_tokens": 4107952} {"current_steps": 7230, "total_steps": 40000, "loss": 0.0, "lr": 4.607763270224132e-05, "epoch": 126.84955752212389, "percentage": 18.07, "elapsed_time": "0:51:53", "remaining_time": "3:55:11", "throughput": 1320.24, "total_tokens": 4110480} {"current_steps": 7235, "total_steps": 40000, "loss": 0.0, "lr": 4.6072351743695e-05, "epoch": 126.93805309734513, "percentage": 18.09, "elapsed_time": "0:51:55", "remaining_time": "3:55:09", "throughput": 1320.26, "total_tokens": 4113280} {"current_steps": 7240, "total_steps": 40000, "loss": 0.0, "lr": 4.606706753552723e-05, "epoch": 127.01769911504425, "percentage": 18.1, "elapsed_time": "0:51:57", "remaining_time": "3:55:07", "throughput": 1320.15, "total_tokens": 4115912} {"current_steps": 7245, "total_steps": 40000, "loss": 0.0, "lr": 4.6061780078552906e-05, "epoch": 127.10619469026548, "percentage": 18.11, "elapsed_time": "0:51:59", "remaining_time": "3:55:04", "throughput": 1320.22, "total_tokens": 4118840} {"current_steps": 7250, "total_steps": 40000, "loss": 0.0, "lr": 4.605648937358742e-05, "epoch": 127.19469026548673, "percentage": 18.12, "elapsed_time": "0:52:01", "remaining_time": "3:55:02", "throughput": 1320.23, "total_tokens": 4121624} {"current_steps": 7255, "total_steps": 40000, "loss": 0.0, "lr": 4.605119542144665e-05, "epoch": 127.28318584070796, "percentage": 18.14, "elapsed_time": "0:52:03", "remaining_time": "3:54:59", "throughput": 1320.17, "total_tokens": 4124152} {"current_steps": 7260, "total_steps": 40000, "loss": 0.0, "lr": 4.604589822294701e-05, "epoch": 127.3716814159292, "percentage": 18.15, "elapsed_time": "0:52:06", "remaining_time": "3:54:57", "throughput": 1320.22, "total_tokens": 4127016} {"current_steps": 7265, "total_steps": 40000, "loss": 0.0, "lr": 4.604059777890537e-05, "epoch": 127.46017699115045, "percentage": 18.16, "elapsed_time": "0:52:08", "remaining_time": "3:54:54", "throughput": 1320.17, "total_tokens": 4129592} {"current_steps": 7270, "total_steps": 40000, "loss": 0.0, "lr": 4.6035294090139145e-05, "epoch": 127.54867256637168, "percentage": 18.18, "elapsed_time": "0:52:10", "remaining_time": "3:54:52", "throughput": 1320.37, "total_tokens": 4132920} {"current_steps": 7275, "total_steps": 40000, "loss": 0.0, "lr": 4.6029987157466226e-05, "epoch": 127.63716814159292, "percentage": 18.19, "elapsed_time": "0:52:12", "remaining_time": "3:54:49", "throughput": 1320.49, "total_tokens": 4136024} {"current_steps": 7280, "total_steps": 40000, "loss": 0.0, "lr": 4.602467698170502e-05, "epoch": 127.72566371681415, "percentage": 18.2, "elapsed_time": "0:52:14", "remaining_time": "3:54:46", "throughput": 1320.52, "total_tokens": 4138840} {"current_steps": 7285, "total_steps": 40000, "loss": 0.0, "lr": 4.601936356367439e-05, "epoch": 127.8141592920354, "percentage": 18.21, "elapsed_time": "0:52:16", "remaining_time": "3:54:44", "throughput": 1320.7, "total_tokens": 4142152} {"current_steps": 7290, "total_steps": 40000, "loss": 0.0, "lr": 4.601404690419377e-05, "epoch": 127.90265486725664, "percentage": 18.22, "elapsed_time": "0:52:18", "remaining_time": "3:54:41", "throughput": 1320.69, "total_tokens": 4144856} {"current_steps": 7295, "total_steps": 40000, "loss": 0.0, "lr": 4.600872700408303e-05, "epoch": 127.99115044247787, "percentage": 18.24, "elapsed_time": "0:52:20", "remaining_time": "3:54:39", "throughput": 1320.86, "total_tokens": 4148088} {"current_steps": 7300, "total_steps": 40000, "loss": 0.0, "lr": 4.600340386416258e-05, "epoch": 128.07079646017698, "percentage": 18.25, "elapsed_time": "0:52:22", "remaining_time": "3:54:37", "throughput": 1320.74, "total_tokens": 4150680} {"current_steps": 7305, "total_steps": 40000, "loss": 0.0, "lr": 4.5998077485253296e-05, "epoch": 128.15929203539824, "percentage": 18.26, "elapsed_time": "0:52:24", "remaining_time": "3:54:35", "throughput": 1320.78, "total_tokens": 4153544} {"current_steps": 7310, "total_steps": 40000, "loss": 0.0, "lr": 4.59927478681766e-05, "epoch": 128.24778761061947, "percentage": 18.27, "elapsed_time": "0:52:26", "remaining_time": "3:54:32", "throughput": 1320.74, "total_tokens": 4156136} {"current_steps": 7315, "total_steps": 40000, "loss": 0.0, "lr": 4.5987415013754366e-05, "epoch": 128.3362831858407, "percentage": 18.29, "elapsed_time": "0:52:28", "remaining_time": "3:54:29", "throughput": 1320.72, "total_tokens": 4158792} {"current_steps": 7320, "total_steps": 40000, "loss": 0.0, "lr": 4.598207892280899e-05, "epoch": 128.42477876106196, "percentage": 18.3, "elapsed_time": "0:52:30", "remaining_time": "3:54:27", "throughput": 1320.76, "total_tokens": 4161672} {"current_steps": 7325, "total_steps": 40000, "loss": 0.0, "lr": 4.597673959616337e-05, "epoch": 128.5132743362832, "percentage": 18.31, "elapsed_time": "0:52:33", "remaining_time": "3:54:24", "throughput": 1320.84, "total_tokens": 4164632} {"current_steps": 7330, "total_steps": 40000, "loss": 0.0, "lr": 4.597139703464089e-05, "epoch": 128.60176991150442, "percentage": 18.32, "elapsed_time": "0:52:35", "remaining_time": "3:54:22", "throughput": 1320.97, "total_tokens": 4167768} {"current_steps": 7335, "total_steps": 40000, "loss": 0.0, "lr": 4.596605123906545e-05, "epoch": 128.69026548672565, "percentage": 18.34, "elapsed_time": "0:52:37", "remaining_time": "3:54:19", "throughput": 1321.0, "total_tokens": 4170616} {"current_steps": 7340, "total_steps": 40000, "loss": 0.0, "lr": 4.596070221026143e-05, "epoch": 128.7787610619469, "percentage": 18.35, "elapsed_time": "0:52:39", "remaining_time": "3:54:17", "throughput": 1320.99, "total_tokens": 4173320} {"current_steps": 7345, "total_steps": 40000, "loss": 0.0, "lr": 4.595534994905372e-05, "epoch": 128.86725663716814, "percentage": 18.36, "elapsed_time": "0:52:41", "remaining_time": "3:54:14", "throughput": 1321.04, "total_tokens": 4176216} {"current_steps": 7350, "total_steps": 40000, "loss": 0.0, "lr": 4.594999445626771e-05, "epoch": 128.95575221238937, "percentage": 18.38, "elapsed_time": "0:52:43", "remaining_time": "3:54:12", "throughput": 1320.99, "total_tokens": 4178760} {"current_steps": 7355, "total_steps": 40000, "loss": 0.0, "lr": 4.5944635732729276e-05, "epoch": 129.0353982300885, "percentage": 18.39, "elapsed_time": "0:52:45", "remaining_time": "3:54:10", "throughput": 1320.81, "total_tokens": 4181184} {"current_steps": 7360, "total_steps": 40000, "loss": 0.0, "lr": 4.5939273779264804e-05, "epoch": 129.12389380530973, "percentage": 18.4, "elapsed_time": "0:52:47", "remaining_time": "3:54:08", "throughput": 1320.9, "total_tokens": 4184208} {"current_steps": 7365, "total_steps": 40000, "loss": 0.0, "lr": 4.593390859670118e-05, "epoch": 129.21238938053096, "percentage": 18.41, "elapsed_time": "0:52:49", "remaining_time": "3:54:05", "throughput": 1321.14, "total_tokens": 4187680} {"current_steps": 7370, "total_steps": 40000, "loss": 0.0, "lr": 4.5928540185865776e-05, "epoch": 129.30088495575222, "percentage": 18.43, "elapsed_time": "0:52:51", "remaining_time": "3:54:02", "throughput": 1321.13, "total_tokens": 4190400} {"current_steps": 7375, "total_steps": 40000, "loss": 0.0, "lr": 4.592316854758648e-05, "epoch": 129.38938053097345, "percentage": 18.44, "elapsed_time": "0:52:53", "remaining_time": "3:54:00", "throughput": 1321.0, "total_tokens": 4192720} {"current_steps": 7380, "total_steps": 40000, "loss": 0.0, "lr": 4.5917793682691646e-05, "epoch": 129.47787610619469, "percentage": 18.45, "elapsed_time": "0:52:55", "remaining_time": "3:53:57", "throughput": 1321.05, "total_tokens": 4195584} {"current_steps": 7385, "total_steps": 40000, "loss": 0.0, "lr": 4.5912415592010164e-05, "epoch": 129.56637168141592, "percentage": 18.46, "elapsed_time": "0:52:58", "remaining_time": "3:53:55", "throughput": 1320.97, "total_tokens": 4198048} {"current_steps": 7390, "total_steps": 40000, "loss": 0.0, "lr": 4.5907034276371386e-05, "epoch": 129.65486725663717, "percentage": 18.48, "elapsed_time": "0:53:00", "remaining_time": "3:53:52", "throughput": 1321.09, "total_tokens": 4201184} {"current_steps": 7395, "total_steps": 40000, "loss": 0.0, "lr": 4.5901649736605196e-05, "epoch": 129.7433628318584, "percentage": 18.49, "elapsed_time": "0:53:02", "remaining_time": "3:53:50", "throughput": 1321.1, "total_tokens": 4203936} {"current_steps": 7400, "total_steps": 40000, "loss": 0.0, "lr": 4.589626197354195e-05, "epoch": 129.83185840707964, "percentage": 18.5, "elapsed_time": "0:53:04", "remaining_time": "3:53:47", "throughput": 1321.25, "total_tokens": 4207120} {"current_steps": 7400, "total_steps": 40000, "eval_loss": 0.4079572260379791, "epoch": 129.83185840707964, "percentage": 18.5, "elapsed_time": "0:53:05", "remaining_time": "3:53:52", "throughput": 1320.8, "total_tokens": 4207120} {"current_steps": 7405, "total_steps": 40000, "loss": 0.0, "lr": 4.5890870988012504e-05, "epoch": 129.9203539823009, "percentage": 18.51, "elapsed_time": "0:53:09", "remaining_time": "3:53:58", "throughput": 1320.12, "total_tokens": 4210320} {"current_steps": 7410, "total_steps": 40000, "loss": 0.0, "lr": 4.5885476780848226e-05, "epoch": 130.0, "percentage": 18.52, "elapsed_time": "0:53:11", "remaining_time": "3:53:55", "throughput": 1319.9, "total_tokens": 4212296} {"current_steps": 7415, "total_steps": 40000, "loss": 0.0, "lr": 4.5880079352880964e-05, "epoch": 130.08849557522123, "percentage": 18.54, "elapsed_time": "0:53:13", "remaining_time": "3:53:54", "throughput": 1319.9, "total_tokens": 4215336} {"current_steps": 7420, "total_steps": 40000, "loss": 0.0, "lr": 4.5874678704943065e-05, "epoch": 130.1769911504425, "percentage": 18.55, "elapsed_time": "0:53:15", "remaining_time": "3:53:52", "throughput": 1319.97, "total_tokens": 4218280} {"current_steps": 7425, "total_steps": 40000, "loss": 0.0, "lr": 4.5869274837867394e-05, "epoch": 130.26548672566372, "percentage": 18.56, "elapsed_time": "0:53:18", "remaining_time": "3:53:50", "throughput": 1319.99, "total_tokens": 4221432} {"current_steps": 7430, "total_steps": 40000, "loss": 0.0, "lr": 4.5863867752487275e-05, "epoch": 130.35398230088495, "percentage": 18.57, "elapsed_time": "0:53:20", "remaining_time": "3:53:48", "throughput": 1319.98, "total_tokens": 4224120} {"current_steps": 7435, "total_steps": 40000, "loss": 0.0, "lr": 4.5858457449636554e-05, "epoch": 130.44247787610618, "percentage": 18.59, "elapsed_time": "0:53:22", "remaining_time": "3:53:45", "throughput": 1319.97, "total_tokens": 4226808} {"current_steps": 7440, "total_steps": 40000, "loss": 0.0, "lr": 4.5853043930149574e-05, "epoch": 130.53097345132744, "percentage": 18.6, "elapsed_time": "0:53:24", "remaining_time": "3:53:42", "throughput": 1320.08, "total_tokens": 4229880} {"current_steps": 7445, "total_steps": 40000, "loss": 0.0, "lr": 4.584762719486117e-05, "epoch": 130.61946902654867, "percentage": 18.61, "elapsed_time": "0:53:26", "remaining_time": "3:53:40", "throughput": 1319.99, "total_tokens": 4232296} {"current_steps": 7450, "total_steps": 40000, "loss": 0.0, "lr": 4.584220724460665e-05, "epoch": 130.7079646017699, "percentage": 18.62, "elapsed_time": "0:53:28", "remaining_time": "3:53:37", "throughput": 1320.01, "total_tokens": 4235080} {"current_steps": 7455, "total_steps": 40000, "loss": 0.0, "lr": 4.5836784080221865e-05, "epoch": 130.79646017699116, "percentage": 18.64, "elapsed_time": "0:53:30", "remaining_time": "3:53:35", "throughput": 1320.17, "total_tokens": 4238360} {"current_steps": 7460, "total_steps": 40000, "loss": 0.0, "lr": 4.583135770254312e-05, "epoch": 130.8849557522124, "percentage": 18.65, "elapsed_time": "0:53:32", "remaining_time": "3:53:32", "throughput": 1320.15, "total_tokens": 4241000} {"current_steps": 7465, "total_steps": 40000, "loss": 0.0, "lr": 4.5825928112407236e-05, "epoch": 130.97345132743362, "percentage": 18.66, "elapsed_time": "0:53:34", "remaining_time": "3:53:30", "throughput": 1320.39, "total_tokens": 4244472} {"current_steps": 7470, "total_steps": 40000, "loss": 0.0, "lr": 4.582049531065152e-05, "epoch": 131.05309734513276, "percentage": 18.68, "elapsed_time": "0:53:36", "remaining_time": "3:53:28", "throughput": 1320.1, "total_tokens": 4246536} {"current_steps": 7475, "total_steps": 40000, "loss": 0.0, "lr": 4.5815059298113783e-05, "epoch": 131.141592920354, "percentage": 18.69, "elapsed_time": "0:53:38", "remaining_time": "3:53:25", "throughput": 1320.19, "total_tokens": 4249544} {"current_steps": 7480, "total_steps": 40000, "loss": 0.0, "lr": 4.580962007563232e-05, "epoch": 131.23008849557522, "percentage": 18.7, "elapsed_time": "0:53:40", "remaining_time": "3:53:23", "throughput": 1320.36, "total_tokens": 4252808} {"current_steps": 7485, "total_steps": 40000, "loss": 0.0, "lr": 4.5804177644045935e-05, "epoch": 131.31858407079645, "percentage": 18.71, "elapsed_time": "0:53:43", "remaining_time": "3:53:20", "throughput": 1320.36, "total_tokens": 4255528} {"current_steps": 7490, "total_steps": 40000, "loss": 0.0, "lr": 4.579873200419391e-05, "epoch": 131.4070796460177, "percentage": 18.73, "elapsed_time": "0:53:45", "remaining_time": "3:53:18", "throughput": 1320.42, "total_tokens": 4258472} {"current_steps": 7495, "total_steps": 40000, "loss": 0.0, "lr": 4.5793283156916046e-05, "epoch": 131.49557522123894, "percentage": 18.74, "elapsed_time": "0:53:47", "remaining_time": "3:53:15", "throughput": 1320.5, "total_tokens": 4261464} {"current_steps": 7500, "total_steps": 40000, "loss": 0.0, "lr": 4.578783110305261e-05, "epoch": 131.58407079646017, "percentage": 18.75, "elapsed_time": "0:53:49", "remaining_time": "3:53:13", "throughput": 1320.38, "total_tokens": 4263784} {"current_steps": 7505, "total_steps": 40000, "loss": 0.0, "lr": 4.578237584344438e-05, "epoch": 131.67256637168143, "percentage": 18.76, "elapsed_time": "0:53:51", "remaining_time": "3:53:10", "throughput": 1320.54, "total_tokens": 4267032} {"current_steps": 7510, "total_steps": 40000, "loss": 0.0, "lr": 4.577691737893263e-05, "epoch": 131.76106194690266, "percentage": 18.77, "elapsed_time": "0:53:53", "remaining_time": "3:53:08", "throughput": 1320.49, "total_tokens": 4269560} {"current_steps": 7515, "total_steps": 40000, "loss": 0.0, "lr": 4.577145571035912e-05, "epoch": 131.8495575221239, "percentage": 18.79, "elapsed_time": "0:53:55", "remaining_time": "3:53:05", "throughput": 1320.6, "total_tokens": 4272664} {"current_steps": 7520, "total_steps": 40000, "loss": 0.0, "lr": 4.576599083856611e-05, "epoch": 131.93805309734512, "percentage": 18.8, "elapsed_time": "0:53:57", "remaining_time": "3:53:02", "throughput": 1320.68, "total_tokens": 4275608} {"current_steps": 7525, "total_steps": 40000, "loss": 0.0, "lr": 4.576052276439635e-05, "epoch": 132.01769911504425, "percentage": 18.81, "elapsed_time": "0:53:59", "remaining_time": "3:53:01", "throughput": 1320.45, "total_tokens": 4277864} {"current_steps": 7530, "total_steps": 40000, "loss": 0.0, "lr": 4.575505148869308e-05, "epoch": 132.10619469026548, "percentage": 18.82, "elapsed_time": "0:54:01", "remaining_time": "3:52:58", "throughput": 1320.48, "total_tokens": 4280696} {"current_steps": 7535, "total_steps": 40000, "loss": 0.0, "lr": 4.574957701230006e-05, "epoch": 132.1946902654867, "percentage": 18.84, "elapsed_time": "0:54:03", "remaining_time": "3:52:56", "throughput": 1320.48, "total_tokens": 4283400} {"current_steps": 7540, "total_steps": 40000, "loss": 0.0, "lr": 4.57440993360615e-05, "epoch": 132.28318584070797, "percentage": 18.85, "elapsed_time": "0:54:05", "remaining_time": "3:52:53", "throughput": 1320.64, "total_tokens": 4286648} {"current_steps": 7545, "total_steps": 40000, "loss": 0.0, "lr": 4.5738618460822134e-05, "epoch": 132.3716814159292, "percentage": 18.86, "elapsed_time": "0:54:07", "remaining_time": "3:52:51", "throughput": 1320.68, "total_tokens": 4289512} {"current_steps": 7550, "total_steps": 40000, "loss": 0.0, "lr": 4.573313438742719e-05, "epoch": 132.46017699115043, "percentage": 18.88, "elapsed_time": "0:54:10", "remaining_time": "3:52:48", "throughput": 1320.76, "total_tokens": 4292472} {"current_steps": 7555, "total_steps": 40000, "loss": 0.0, "lr": 4.5727647116722374e-05, "epoch": 132.5486725663717, "percentage": 18.89, "elapsed_time": "0:54:12", "remaining_time": "3:52:46", "throughput": 1320.84, "total_tokens": 4295480} {"current_steps": 7560, "total_steps": 40000, "loss": 0.0, "lr": 4.5722156649553884e-05, "epoch": 132.63716814159292, "percentage": 18.9, "elapsed_time": "0:54:14", "remaining_time": "3:52:43", "throughput": 1320.95, "total_tokens": 4298536} {"current_steps": 7565, "total_steps": 40000, "loss": 0.0, "lr": 4.571666298676843e-05, "epoch": 132.72566371681415, "percentage": 18.91, "elapsed_time": "0:54:16", "remaining_time": "3:52:40", "throughput": 1321.03, "total_tokens": 4301528} {"current_steps": 7570, "total_steps": 40000, "loss": 0.0, "lr": 4.571116612921321e-05, "epoch": 132.81415929203538, "percentage": 18.93, "elapsed_time": "0:54:18", "remaining_time": "3:52:38", "throughput": 1321.05, "total_tokens": 4304312} {"current_steps": 7575, "total_steps": 40000, "loss": 0.0, "lr": 4.57056660777359e-05, "epoch": 132.90265486725664, "percentage": 18.94, "elapsed_time": "0:54:20", "remaining_time": "3:52:35", "throughput": 1320.9, "total_tokens": 4306552} {"current_steps": 7580, "total_steps": 40000, "loss": 0.0, "lr": 4.5700162833184666e-05, "epoch": 132.99115044247787, "percentage": 18.95, "elapsed_time": "0:54:22", "remaining_time": "3:52:33", "throughput": 1320.91, "total_tokens": 4309288} {"current_steps": 7585, "total_steps": 40000, "loss": 0.0, "lr": 4.5694656396408195e-05, "epoch": 133.07079646017698, "percentage": 18.96, "elapsed_time": "0:54:24", "remaining_time": "3:52:31", "throughput": 1320.84, "total_tokens": 4312024} {"current_steps": 7590, "total_steps": 40000, "loss": 0.0, "lr": 4.5689146768255646e-05, "epoch": 133.15929203539824, "percentage": 18.98, "elapsed_time": "0:54:26", "remaining_time": "3:52:28", "throughput": 1320.84, "total_tokens": 4314760} {"current_steps": 7595, "total_steps": 40000, "loss": 0.0, "lr": 4.568363394957667e-05, "epoch": 133.24778761061947, "percentage": 18.99, "elapsed_time": "0:54:28", "remaining_time": "3:52:26", "throughput": 1320.82, "total_tokens": 4317400} {"current_steps": 7600, "total_steps": 40000, "loss": 0.0, "lr": 4.567811794122141e-05, "epoch": 133.3362831858407, "percentage": 19.0, "elapsed_time": "0:54:30", "remaining_time": "3:52:23", "throughput": 1320.95, "total_tokens": 4320568} {"current_steps": 7600, "total_steps": 40000, "eval_loss": 0.4073774218559265, "epoch": 133.3362831858407, "percentage": 19.0, "elapsed_time": "0:54:31", "remaining_time": "3:52:28", "throughput": 1320.52, "total_tokens": 4320568} {"current_steps": 7605, "total_steps": 40000, "loss": 0.0, "lr": 4.56725987440405e-05, "epoch": 133.42477876106196, "percentage": 19.01, "elapsed_time": "0:54:35", "remaining_time": "3:52:33", "throughput": 1319.74, "total_tokens": 4322968} {"current_steps": 7610, "total_steps": 40000, "loss": 0.0, "lr": 4.566707635888508e-05, "epoch": 133.5132743362832, "percentage": 19.02, "elapsed_time": "0:54:37", "remaining_time": "3:52:30", "throughput": 1319.78, "total_tokens": 4325864} {"current_steps": 7615, "total_steps": 40000, "loss": 0.0, "lr": 4.566155078660677e-05, "epoch": 133.60176991150442, "percentage": 19.04, "elapsed_time": "0:54:39", "remaining_time": "3:52:28", "throughput": 1319.76, "total_tokens": 4328504} {"current_steps": 7620, "total_steps": 40000, "loss": 0.0, "lr": 4.565602202805768e-05, "epoch": 133.69026548672565, "percentage": 19.05, "elapsed_time": "0:54:41", "remaining_time": "3:52:25", "throughput": 1319.7, "total_tokens": 4331016} {"current_steps": 7625, "total_steps": 40000, "loss": 0.0, "lr": 4.56504900840904e-05, "epoch": 133.7787610619469, "percentage": 19.06, "elapsed_time": "0:54:43", "remaining_time": "3:52:23", "throughput": 1319.77, "total_tokens": 4333976} {"current_steps": 7630, "total_steps": 40000, "loss": 0.0, "lr": 4.564495495555805e-05, "epoch": 133.86725663716814, "percentage": 19.07, "elapsed_time": "0:54:45", "remaining_time": "3:52:20", "throughput": 1319.84, "total_tokens": 4336936} {"current_steps": 7635, "total_steps": 40000, "loss": 0.0, "lr": 4.5639416643314204e-05, "epoch": 133.95575221238937, "percentage": 19.09, "elapsed_time": "0:54:48", "remaining_time": "3:52:17", "throughput": 1319.96, "total_tokens": 4340040} {"current_steps": 7640, "total_steps": 40000, "loss": 0.0, "lr": 4.5633875148212946e-05, "epoch": 134.0353982300885, "percentage": 19.1, "elapsed_time": "0:54:50", "remaining_time": "3:52:16", "throughput": 1319.83, "total_tokens": 4342576} {"current_steps": 7645, "total_steps": 40000, "loss": 0.0, "lr": 4.562833047110883e-05, "epoch": 134.12389380530973, "percentage": 19.11, "elapsed_time": "0:54:52", "remaining_time": "3:52:13", "throughput": 1319.81, "total_tokens": 4345248} {"current_steps": 7650, "total_steps": 40000, "loss": 0.0, "lr": 4.5622782612856923e-05, "epoch": 134.21238938053096, "percentage": 19.12, "elapsed_time": "0:54:54", "remaining_time": "3:52:11", "throughput": 1320.14, "total_tokens": 4349056} {"current_steps": 7655, "total_steps": 40000, "loss": 0.0, "lr": 4.561723157431278e-05, "epoch": 134.30088495575222, "percentage": 19.14, "elapsed_time": "0:54:56", "remaining_time": "3:52:08", "throughput": 1320.18, "total_tokens": 4351904} {"current_steps": 7660, "total_steps": 40000, "loss": 0.0, "lr": 4.5611677356332435e-05, "epoch": 134.38938053097345, "percentage": 19.15, "elapsed_time": "0:54:58", "remaining_time": "3:52:06", "throughput": 1320.26, "total_tokens": 4354880} {"current_steps": 7665, "total_steps": 40000, "loss": 0.0, "lr": 4.560611995977242e-05, "epoch": 134.47787610619469, "percentage": 19.16, "elapsed_time": "0:55:00", "remaining_time": "3:52:03", "throughput": 1320.21, "total_tokens": 4357456} {"current_steps": 7670, "total_steps": 40000, "loss": 0.0, "lr": 4.560055938548975e-05, "epoch": 134.56637168141592, "percentage": 19.18, "elapsed_time": "0:55:02", "remaining_time": "3:52:01", "throughput": 1320.17, "total_tokens": 4360032} {"current_steps": 7675, "total_steps": 40000, "loss": 0.0, "lr": 4.5594995634341944e-05, "epoch": 134.65486725663717, "percentage": 19.19, "elapsed_time": "0:55:04", "remaining_time": "3:51:58", "throughput": 1320.17, "total_tokens": 4362768} {"current_steps": 7680, "total_steps": 40000, "loss": 0.0, "lr": 4.5589428707187e-05, "epoch": 134.7433628318584, "percentage": 19.2, "elapsed_time": "0:55:06", "remaining_time": "3:51:55", "throughput": 1320.18, "total_tokens": 4365536} {"current_steps": 7685, "total_steps": 40000, "loss": 0.0, "lr": 4.55838586048834e-05, "epoch": 134.83185840707964, "percentage": 19.21, "elapsed_time": "0:55:08", "remaining_time": "3:51:53", "throughput": 1320.31, "total_tokens": 4368656} {"current_steps": 7690, "total_steps": 40000, "loss": 0.0, "lr": 4.557828532829013e-05, "epoch": 134.9203539823009, "percentage": 19.23, "elapsed_time": "0:55:10", "remaining_time": "3:51:50", "throughput": 1320.32, "total_tokens": 4371408} {"current_steps": 7695, "total_steps": 40000, "loss": 0.0, "lr": 4.557270887826667e-05, "epoch": 135.0, "percentage": 19.24, "elapsed_time": "0:55:12", "remaining_time": "3:51:48", "throughput": 1320.28, "total_tokens": 4373936} {"current_steps": 7700, "total_steps": 40000, "loss": 0.0, "lr": 4.556712925567296e-05, "epoch": 135.08849557522123, "percentage": 19.25, "elapsed_time": "0:55:15", "remaining_time": "3:51:46", "throughput": 1320.16, "total_tokens": 4376576} {"current_steps": 7705, "total_steps": 40000, "loss": 0.0, "lr": 4.5561546461369454e-05, "epoch": 135.1769911504425, "percentage": 19.26, "elapsed_time": "0:55:17", "remaining_time": "3:51:44", "throughput": 1320.13, "total_tokens": 4379200} {"current_steps": 7710, "total_steps": 40000, "loss": 0.0, "lr": 4.55559604962171e-05, "epoch": 135.26548672566372, "percentage": 19.28, "elapsed_time": "0:55:19", "remaining_time": "3:51:41", "throughput": 1320.08, "total_tokens": 4381760} {"current_steps": 7715, "total_steps": 40000, "loss": 0.0, "lr": 4.55503713610773e-05, "epoch": 135.35398230088495, "percentage": 19.29, "elapsed_time": "0:55:21", "remaining_time": "3:51:38", "throughput": 1320.05, "total_tokens": 4384368} {"current_steps": 7720, "total_steps": 40000, "loss": 0.0, "lr": 4.5544779056812e-05, "epoch": 135.44247787610618, "percentage": 19.3, "elapsed_time": "0:55:23", "remaining_time": "3:51:36", "throughput": 1320.19, "total_tokens": 4387568} {"current_steps": 7725, "total_steps": 40000, "loss": 0.0, "lr": 4.553918358428358e-05, "epoch": 135.53097345132744, "percentage": 19.31, "elapsed_time": "0:55:25", "remaining_time": "3:51:33", "throughput": 1320.23, "total_tokens": 4390400} {"current_steps": 7730, "total_steps": 40000, "loss": 0.0, "lr": 4.553358494435494e-05, "epoch": 135.61946902654867, "percentage": 19.32, "elapsed_time": "0:55:27", "remaining_time": "3:51:31", "throughput": 1320.41, "total_tokens": 4393760} {"current_steps": 7735, "total_steps": 40000, "loss": 0.0, "lr": 4.5527983137889464e-05, "epoch": 135.7079646017699, "percentage": 19.34, "elapsed_time": "0:55:29", "remaining_time": "3:51:28", "throughput": 1320.59, "total_tokens": 4397072} {"current_steps": 7740, "total_steps": 40000, "loss": 0.0, "lr": 4.5522378165751015e-05, "epoch": 135.79646017699116, "percentage": 19.35, "elapsed_time": "0:55:31", "remaining_time": "3:51:26", "throughput": 1320.78, "total_tokens": 4400416} {"current_steps": 7745, "total_steps": 40000, "loss": 0.0, "lr": 4.5516770028803954e-05, "epoch": 135.8849557522124, "percentage": 19.36, "elapsed_time": "0:55:33", "remaining_time": "3:51:23", "throughput": 1320.84, "total_tokens": 4403344} {"current_steps": 7750, "total_steps": 40000, "loss": 0.0, "lr": 4.5511158727913116e-05, "epoch": 135.97345132743362, "percentage": 19.38, "elapsed_time": "0:55:35", "remaining_time": "3:51:21", "throughput": 1320.85, "total_tokens": 4406080} {"current_steps": 7755, "total_steps": 40000, "loss": 0.0, "lr": 4.5505544263943856e-05, "epoch": 136.05309734513276, "percentage": 19.39, "elapsed_time": "0:55:38", "remaining_time": "3:51:19", "throughput": 1320.61, "total_tokens": 4408264} {"current_steps": 7760, "total_steps": 40000, "loss": 0.0, "lr": 4.549992663776197e-05, "epoch": 136.141592920354, "percentage": 19.4, "elapsed_time": "0:55:40", "remaining_time": "3:51:17", "throughput": 1320.55, "total_tokens": 4410808} {"current_steps": 7765, "total_steps": 40000, "loss": 0.0, "lr": 4.5494305850233786e-05, "epoch": 136.23008849557522, "percentage": 19.41, "elapsed_time": "0:55:42", "remaining_time": "3:51:14", "throughput": 1320.49, "total_tokens": 4413320} {"current_steps": 7770, "total_steps": 40000, "loss": 0.0, "lr": 4.5488681902226094e-05, "epoch": 136.31858407079645, "percentage": 19.43, "elapsed_time": "0:55:44", "remaining_time": "3:51:11", "throughput": 1320.44, "total_tokens": 4415896} {"current_steps": 7775, "total_steps": 40000, "loss": 0.0, "lr": 4.5483054794606174e-05, "epoch": 136.4070796460177, "percentage": 19.44, "elapsed_time": "0:55:46", "remaining_time": "3:51:09", "throughput": 1320.33, "total_tokens": 4418248} {"current_steps": 7780, "total_steps": 40000, "loss": 0.0, "lr": 4.547742452824179e-05, "epoch": 136.49557522123894, "percentage": 19.45, "elapsed_time": "0:55:48", "remaining_time": "3:51:06", "throughput": 1320.49, "total_tokens": 4421496} {"current_steps": 7785, "total_steps": 40000, "loss": 0.0, "lr": 4.5471791104001215e-05, "epoch": 136.58407079646017, "percentage": 19.46, "elapsed_time": "0:55:50", "remaining_time": "3:51:04", "throughput": 1320.7, "total_tokens": 4424920} {"current_steps": 7790, "total_steps": 40000, "loss": 0.0, "lr": 4.546615452275319e-05, "epoch": 136.67256637168143, "percentage": 19.48, "elapsed_time": "0:55:52", "remaining_time": "3:51:01", "throughput": 1320.84, "total_tokens": 4428104} {"current_steps": 7795, "total_steps": 40000, "loss": 0.0, "lr": 4.5460514785366944e-05, "epoch": 136.76106194690266, "percentage": 19.49, "elapsed_time": "0:55:54", "remaining_time": "3:50:59", "throughput": 1320.9, "total_tokens": 4431048} {"current_steps": 7800, "total_steps": 40000, "loss": 0.0, "lr": 4.545487189271219e-05, "epoch": 136.8495575221239, "percentage": 19.5, "elapsed_time": "0:55:56", "remaining_time": "3:50:56", "throughput": 1320.99, "total_tokens": 4434056} {"current_steps": 7800, "total_steps": 40000, "eval_loss": 0.41203686594963074, "epoch": 136.8495575221239, "percentage": 19.5, "elapsed_time": "0:55:57", "remaining_time": "3:51:01", "throughput": 1320.57, "total_tokens": 4434056} {"current_steps": 7805, "total_steps": 40000, "loss": 0.0, "lr": 4.544922584565914e-05, "epoch": 136.93805309734512, "percentage": 19.51, "elapsed_time": "0:56:01", "remaining_time": "3:51:05", "throughput": 1320.01, "total_tokens": 4437096} {"current_steps": 7810, "total_steps": 40000, "loss": 0.0, "lr": 4.544357664507848e-05, "epoch": 137.01769911504425, "percentage": 19.53, "elapsed_time": "0:56:03", "remaining_time": "3:51:03", "throughput": 1319.88, "total_tokens": 4439648} {"current_steps": 7815, "total_steps": 40000, "loss": 0.0, "lr": 4.54379242918414e-05, "epoch": 137.10619469026548, "percentage": 19.54, "elapsed_time": "0:56:05", "remaining_time": "3:51:01", "throughput": 1319.86, "total_tokens": 4442304} {"current_steps": 7820, "total_steps": 40000, "loss": 0.0, "lr": 4.543226878681955e-05, "epoch": 137.1946902654867, "percentage": 19.55, "elapsed_time": "0:56:07", "remaining_time": "3:50:58", "throughput": 1319.9, "total_tokens": 4445168} {"current_steps": 7825, "total_steps": 40000, "loss": 0.0, "lr": 4.5426610130885087e-05, "epoch": 137.28318584070797, "percentage": 19.56, "elapsed_time": "0:56:09", "remaining_time": "3:50:56", "throughput": 1319.89, "total_tokens": 4447856} {"current_steps": 7830, "total_steps": 40000, "loss": 0.0, "lr": 4.542094832491064e-05, "epoch": 137.3716814159292, "percentage": 19.57, "elapsed_time": "0:56:11", "remaining_time": "3:50:53", "throughput": 1319.83, "total_tokens": 4450352} {"current_steps": 7835, "total_steps": 40000, "loss": 0.0, "lr": 4.541528336976934e-05, "epoch": 137.46017699115043, "percentage": 19.59, "elapsed_time": "0:56:13", "remaining_time": "3:50:51", "throughput": 1319.75, "total_tokens": 4452832} {"current_steps": 7840, "total_steps": 40000, "loss": 0.0, "lr": 4.540961526633479e-05, "epoch": 137.5486725663717, "percentage": 19.6, "elapsed_time": "0:56:16", "remaining_time": "3:50:48", "throughput": 1319.89, "total_tokens": 4456032} {"current_steps": 7845, "total_steps": 40000, "loss": 0.0, "lr": 4.540394401548108e-05, "epoch": 137.63716814159292, "percentage": 19.61, "elapsed_time": "0:56:18", "remaining_time": "3:50:46", "throughput": 1320.02, "total_tokens": 4459216} {"current_steps": 7850, "total_steps": 40000, "loss": 0.0, "lr": 4.539826961808279e-05, "epoch": 137.72566371681415, "percentage": 19.62, "elapsed_time": "0:56:20", "remaining_time": "3:50:43", "throughput": 1320.17, "total_tokens": 4462432} {"current_steps": 7855, "total_steps": 40000, "loss": 0.0, "lr": 4.5392592075014994e-05, "epoch": 137.81415929203538, "percentage": 19.64, "elapsed_time": "0:56:22", "remaining_time": "3:50:41", "throughput": 1320.2, "total_tokens": 4465264} {"current_steps": 7860, "total_steps": 40000, "loss": 0.0, "lr": 4.538691138715322e-05, "epoch": 137.90265486725664, "percentage": 19.65, "elapsed_time": "0:56:24", "remaining_time": "3:50:38", "throughput": 1320.19, "total_tokens": 4467952} {"current_steps": 7865, "total_steps": 40000, "loss": 0.0, "lr": 4.5381227555373516e-05, "epoch": 137.99115044247787, "percentage": 19.66, "elapsed_time": "0:56:26", "remaining_time": "3:50:36", "throughput": 1320.21, "total_tokens": 4470720} {"current_steps": 7870, "total_steps": 40000, "loss": 0.0, "lr": 4.537554058055239e-05, "epoch": 138.07079646017698, "percentage": 19.68, "elapsed_time": "0:56:28", "remaining_time": "3:50:34", "throughput": 1320.1, "total_tokens": 4473336} {"current_steps": 7875, "total_steps": 40000, "loss": 0.0, "lr": 4.5369850463566865e-05, "epoch": 138.15929203539824, "percentage": 19.69, "elapsed_time": "0:56:30", "remaining_time": "3:50:31", "throughput": 1319.99, "total_tokens": 4475688} {"current_steps": 7880, "total_steps": 40000, "loss": 0.0, "lr": 4.5364157205294404e-05, "epoch": 138.24778761061947, "percentage": 19.7, "elapsed_time": "0:56:32", "remaining_time": "3:50:29", "throughput": 1320.01, "total_tokens": 4478488} {"current_steps": 7885, "total_steps": 40000, "loss": 0.0, "lr": 4.5358460806612996e-05, "epoch": 138.3362831858407, "percentage": 19.71, "elapsed_time": "0:56:34", "remaining_time": "3:50:26", "throughput": 1320.08, "total_tokens": 4481448} {"current_steps": 7890, "total_steps": 40000, "loss": 0.0, "lr": 4.535276126840109e-05, "epoch": 138.42477876106196, "percentage": 19.73, "elapsed_time": "0:56:36", "remaining_time": "3:50:24", "throughput": 1320.13, "total_tokens": 4484328} {"current_steps": 7895, "total_steps": 40000, "loss": 0.0, "lr": 4.5347058591537626e-05, "epoch": 138.5132743362832, "percentage": 19.74, "elapsed_time": "0:56:38", "remaining_time": "3:50:21", "throughput": 1320.19, "total_tokens": 4487240} {"current_steps": 7900, "total_steps": 40000, "loss": 0.0, "lr": 4.534135277690203e-05, "epoch": 138.60176991150442, "percentage": 19.75, "elapsed_time": "0:56:41", "remaining_time": "3:50:19", "throughput": 1320.21, "total_tokens": 4490040} {"current_steps": 7905, "total_steps": 40000, "loss": 0.0, "lr": 4.533564382537421e-05, "epoch": 138.69026548672565, "percentage": 19.76, "elapsed_time": "0:56:43", "remaining_time": "3:50:16", "throughput": 1320.25, "total_tokens": 4492888} {"current_steps": 7910, "total_steps": 40000, "loss": 0.0, "lr": 4.532993173783456e-05, "epoch": 138.7787610619469, "percentage": 19.78, "elapsed_time": "0:56:45", "remaining_time": "3:50:14", "throughput": 1320.41, "total_tokens": 4496184} {"current_steps": 7915, "total_steps": 40000, "loss": 0.0, "lr": 4.5324216515163954e-05, "epoch": 138.86725663716814, "percentage": 19.79, "elapsed_time": "0:56:47", "remaining_time": "3:50:11", "throughput": 1320.44, "total_tokens": 4499032} {"current_steps": 7920, "total_steps": 40000, "loss": 0.0, "lr": 4.531849815824375e-05, "epoch": 138.95575221238937, "percentage": 19.8, "elapsed_time": "0:56:49", "remaining_time": "3:50:09", "throughput": 1320.44, "total_tokens": 4501736} {"current_steps": 7925, "total_steps": 40000, "loss": 0.0, "lr": 4.5312776667955795e-05, "epoch": 139.0353982300885, "percentage": 19.81, "elapsed_time": "0:56:51", "remaining_time": "3:50:07", "throughput": 1320.28, "total_tokens": 4504168} {"current_steps": 7930, "total_steps": 40000, "loss": 0.0, "lr": 4.5307052045182405e-05, "epoch": 139.12389380530973, "percentage": 19.82, "elapsed_time": "0:56:53", "remaining_time": "3:50:04", "throughput": 1320.41, "total_tokens": 4507304} {"current_steps": 7935, "total_steps": 40000, "loss": 0.0, "lr": 4.53013242908064e-05, "epoch": 139.21238938053096, "percentage": 19.84, "elapsed_time": "0:56:55", "remaining_time": "3:50:02", "throughput": 1320.39, "total_tokens": 4509976} {"current_steps": 7940, "total_steps": 40000, "loss": 0.0, "lr": 4.529559340571107e-05, "epoch": 139.30088495575222, "percentage": 19.85, "elapsed_time": "0:56:57", "remaining_time": "3:49:59", "throughput": 1320.38, "total_tokens": 4512648} {"current_steps": 7945, "total_steps": 40000, "loss": 0.0, "lr": 4.528985939078018e-05, "epoch": 139.38938053097345, "percentage": 19.86, "elapsed_time": "0:56:59", "remaining_time": "3:49:57", "throughput": 1320.38, "total_tokens": 4515400} {"current_steps": 7950, "total_steps": 40000, "loss": 0.0, "lr": 4.5284122246898e-05, "epoch": 139.47787610619469, "percentage": 19.88, "elapsed_time": "0:57:01", "remaining_time": "3:49:54", "throughput": 1320.56, "total_tokens": 4518744} {"current_steps": 7955, "total_steps": 40000, "loss": 0.0, "lr": 4.527838197494926e-05, "epoch": 139.56637168141592, "percentage": 19.89, "elapsed_time": "0:57:03", "remaining_time": "3:49:52", "throughput": 1320.64, "total_tokens": 4521736} {"current_steps": 7960, "total_steps": 40000, "loss": 0.0, "lr": 4.527263857581918e-05, "epoch": 139.65486725663717, "percentage": 19.9, "elapsed_time": "0:57:05", "remaining_time": "3:49:49", "throughput": 1320.69, "total_tokens": 4524632} {"current_steps": 7965, "total_steps": 40000, "loss": 0.0, "lr": 4.526689205039347e-05, "epoch": 139.7433628318584, "percentage": 19.91, "elapsed_time": "0:57:08", "remaining_time": "3:49:47", "throughput": 1320.71, "total_tokens": 4527400} {"current_steps": 7970, "total_steps": 40000, "loss": 0.0, "lr": 4.5261142399558324e-05, "epoch": 139.83185840707964, "percentage": 19.93, "elapsed_time": "0:57:10", "remaining_time": "3:49:44", "throughput": 1320.74, "total_tokens": 4530216} {"current_steps": 7975, "total_steps": 40000, "loss": 0.0, "lr": 4.525538962420041e-05, "epoch": 139.9203539823009, "percentage": 19.94, "elapsed_time": "0:57:12", "remaining_time": "3:49:42", "throughput": 1320.79, "total_tokens": 4533128} {"current_steps": 7980, "total_steps": 40000, "loss": 0.0, "lr": 4.524963372520685e-05, "epoch": 140.0, "percentage": 19.95, "elapsed_time": "0:57:14", "remaining_time": "3:49:39", "throughput": 1320.73, "total_tokens": 4535568} {"current_steps": 7985, "total_steps": 40000, "loss": 0.0, "lr": 4.524387470346531e-05, "epoch": 140.08849557522123, "percentage": 19.96, "elapsed_time": "0:57:16", "remaining_time": "3:49:38", "throughput": 1320.81, "total_tokens": 4538912} {"current_steps": 7990, "total_steps": 40000, "loss": 0.0, "lr": 4.5238112559863885e-05, "epoch": 140.1769911504425, "percentage": 19.98, "elapsed_time": "0:57:18", "remaining_time": "3:49:35", "throughput": 1320.84, "total_tokens": 4541728} {"current_steps": 7995, "total_steps": 40000, "loss": 0.0, "lr": 4.5232347295291175e-05, "epoch": 140.26548672566372, "percentage": 19.99, "elapsed_time": "0:57:20", "remaining_time": "3:49:33", "throughput": 1321.01, "total_tokens": 4545056} {"current_steps": 8000, "total_steps": 40000, "loss": 0.0, "lr": 4.522657891063626e-05, "epoch": 140.35398230088495, "percentage": 20.0, "elapsed_time": "0:57:22", "remaining_time": "3:49:30", "throughput": 1321.03, "total_tokens": 4547840} {"current_steps": 8000, "total_steps": 40000, "eval_loss": 0.42564472556114197, "epoch": 140.35398230088495, "percentage": 20.0, "elapsed_time": "0:57:23", "remaining_time": "3:49:34", "throughput": 1320.62, "total_tokens": 4547840} {"current_steps": 8005, "total_steps": 40000, "loss": 0.0, "lr": 4.52208074067887e-05, "epoch": 140.44247787610618, "percentage": 20.01, "elapsed_time": "0:57:27", "remaining_time": "3:49:39", "throughput": 1319.97, "total_tokens": 4550544} {"current_steps": 8010, "total_steps": 40000, "loss": 0.0, "lr": 4.5215032784638516e-05, "epoch": 140.53097345132744, "percentage": 20.03, "elapsed_time": "0:57:29", "remaining_time": "3:49:36", "throughput": 1320.05, "total_tokens": 4553536} {"current_steps": 8015, "total_steps": 40000, "loss": 0.0, "lr": 4.5209255045076245e-05, "epoch": 140.61946902654867, "percentage": 20.04, "elapsed_time": "0:57:31", "remaining_time": "3:49:34", "throughput": 1320.0, "total_tokens": 4556096} {"current_steps": 8020, "total_steps": 40000, "loss": 0.0, "lr": 4.5203474188992875e-05, "epoch": 140.7079646017699, "percentage": 20.05, "elapsed_time": "0:57:33", "remaining_time": "3:49:31", "throughput": 1319.99, "total_tokens": 4558784} {"current_steps": 8025, "total_steps": 40000, "loss": 0.0, "lr": 4.51976902172799e-05, "epoch": 140.79646017699116, "percentage": 20.06, "elapsed_time": "0:57:35", "remaining_time": "3:49:28", "throughput": 1319.92, "total_tokens": 4561232} {"current_steps": 8030, "total_steps": 40000, "loss": 0.0, "lr": 4.519190313082927e-05, "epoch": 140.8849557522124, "percentage": 20.08, "elapsed_time": "0:57:37", "remaining_time": "3:49:26", "throughput": 1320.09, "total_tokens": 4564544} {"current_steps": 8035, "total_steps": 40000, "loss": 0.0, "lr": 4.518611293053343e-05, "epoch": 140.97345132743362, "percentage": 20.09, "elapsed_time": "0:57:39", "remaining_time": "3:49:23", "throughput": 1320.1, "total_tokens": 4567280} {"current_steps": 8040, "total_steps": 40000, "loss": 0.0, "lr": 4.51803196172853e-05, "epoch": 141.05309734513276, "percentage": 20.1, "elapsed_time": "0:57:42", "remaining_time": "3:49:22", "throughput": 1319.87, "total_tokens": 4569480} {"current_steps": 8045, "total_steps": 40000, "loss": 0.0, "lr": 4.517452319197828e-05, "epoch": 141.141592920354, "percentage": 20.11, "elapsed_time": "0:57:44", "remaining_time": "3:49:19", "throughput": 1319.92, "total_tokens": 4572360} {"current_steps": 8050, "total_steps": 40000, "loss": 0.0, "lr": 4.5168723655506265e-05, "epoch": 141.23008849557522, "percentage": 20.12, "elapsed_time": "0:57:46", "remaining_time": "3:49:17", "throughput": 1319.98, "total_tokens": 4575320} {"current_steps": 8055, "total_steps": 40000, "loss": 0.0, "lr": 4.51629210087636e-05, "epoch": 141.31858407079645, "percentage": 20.14, "elapsed_time": "0:57:48", "remaining_time": "3:49:14", "throughput": 1320.0, "total_tokens": 4578104} {"current_steps": 8060, "total_steps": 40000, "loss": 0.0, "lr": 4.515711525264513e-05, "epoch": 141.4070796460177, "percentage": 20.15, "elapsed_time": "0:57:50", "remaining_time": "3:49:12", "throughput": 1320.08, "total_tokens": 4581096} {"current_steps": 8065, "total_steps": 40000, "loss": 0.0, "lr": 4.5151306388046175e-05, "epoch": 141.49557522123894, "percentage": 20.16, "elapsed_time": "0:57:52", "remaining_time": "3:49:09", "throughput": 1320.19, "total_tokens": 4584184} {"current_steps": 8070, "total_steps": 40000, "loss": 0.0, "lr": 4.514549441586255e-05, "epoch": 141.58407079646017, "percentage": 20.18, "elapsed_time": "0:57:54", "remaining_time": "3:49:07", "throughput": 1320.31, "total_tokens": 4587320} {"current_steps": 8075, "total_steps": 40000, "loss": 0.0, "lr": 4.513967933699051e-05, "epoch": 141.67256637168143, "percentage": 20.19, "elapsed_time": "0:57:56", "remaining_time": "3:49:04", "throughput": 1320.28, "total_tokens": 4589944} {"current_steps": 8080, "total_steps": 40000, "loss": 0.0, "lr": 4.513386115232684e-05, "epoch": 141.76106194690266, "percentage": 20.2, "elapsed_time": "0:57:58", "remaining_time": "3:49:02", "throughput": 1320.25, "total_tokens": 4592568} {"current_steps": 8085, "total_steps": 40000, "loss": 0.0, "lr": 4.5128039862768745e-05, "epoch": 141.8495575221239, "percentage": 20.21, "elapsed_time": "0:58:00", "remaining_time": "3:48:59", "throughput": 1320.41, "total_tokens": 4595848} {"current_steps": 8090, "total_steps": 40000, "loss": 0.0, "lr": 4.512221546921397e-05, "epoch": 141.93805309734512, "percentage": 20.23, "elapsed_time": "0:58:02", "remaining_time": "3:48:56", "throughput": 1320.43, "total_tokens": 4598648} {"current_steps": 8095, "total_steps": 40000, "loss": 0.0, "lr": 4.5116387972560694e-05, "epoch": 142.01769911504425, "percentage": 20.24, "elapsed_time": "0:58:04", "remaining_time": "3:48:55", "throughput": 1320.35, "total_tokens": 4601320} {"current_steps": 8100, "total_steps": 40000, "loss": 0.0, "lr": 4.511055737370759e-05, "epoch": 142.10619469026548, "percentage": 20.25, "elapsed_time": "0:58:06", "remaining_time": "3:48:52", "throughput": 1320.48, "total_tokens": 4604488} {"current_steps": 8105, "total_steps": 40000, "loss": 0.0, "lr": 4.510472367355383e-05, "epoch": 142.1946902654867, "percentage": 20.26, "elapsed_time": "0:58:09", "remaining_time": "3:48:50", "throughput": 1320.43, "total_tokens": 4607032} {"current_steps": 8110, "total_steps": 40000, "loss": 0.0, "lr": 4.509888687299901e-05, "epoch": 142.28318584070797, "percentage": 20.28, "elapsed_time": "0:58:11", "remaining_time": "3:48:47", "throughput": 1320.36, "total_tokens": 4609544} {"current_steps": 8115, "total_steps": 40000, "loss": 0.0, "lr": 4.5093046972943266e-05, "epoch": 142.3716814159292, "percentage": 20.29, "elapsed_time": "0:58:13", "remaining_time": "3:48:45", "throughput": 1320.48, "total_tokens": 4612680} {"current_steps": 8120, "total_steps": 40000, "loss": 0.0, "lr": 4.508720397428717e-05, "epoch": 142.46017699115043, "percentage": 20.3, "elapsed_time": "0:58:15", "remaining_time": "3:48:42", "throughput": 1320.52, "total_tokens": 4615560} {"current_steps": 8125, "total_steps": 40000, "loss": 0.0, "lr": 4.508135787793178e-05, "epoch": 142.5486725663717, "percentage": 20.31, "elapsed_time": "0:58:17", "remaining_time": "3:48:40", "throughput": 1320.49, "total_tokens": 4618184} {"current_steps": 8130, "total_steps": 40000, "loss": 0.0, "lr": 4.5075508684778664e-05, "epoch": 142.63716814159292, "percentage": 20.32, "elapsed_time": "0:58:19", "remaining_time": "3:48:37", "throughput": 1320.42, "total_tokens": 4620632} {"current_steps": 8135, "total_steps": 40000, "loss": 0.0, "lr": 4.506965639572982e-05, "epoch": 142.72566371681415, "percentage": 20.34, "elapsed_time": "0:58:21", "remaining_time": "3:48:35", "throughput": 1320.54, "total_tokens": 4623784} {"current_steps": 8140, "total_steps": 40000, "loss": 0.0, "lr": 4.506380101168774e-05, "epoch": 142.81415929203538, "percentage": 20.35, "elapsed_time": "0:58:23", "remaining_time": "3:48:32", "throughput": 1320.71, "total_tokens": 4627128} {"current_steps": 8145, "total_steps": 40000, "loss": 0.0, "lr": 4.505794253355542e-05, "epoch": 142.90265486725664, "percentage": 20.36, "elapsed_time": "0:58:25", "remaining_time": "3:48:30", "throughput": 1320.93, "total_tokens": 4630616} {"current_steps": 8150, "total_steps": 40000, "loss": 0.0, "lr": 4.5052080962236286e-05, "epoch": 142.99115044247787, "percentage": 20.38, "elapsed_time": "0:58:27", "remaining_time": "3:48:27", "throughput": 1320.88, "total_tokens": 4633144} {"current_steps": 8155, "total_steps": 40000, "loss": 0.0, "lr": 4.504621629863428e-05, "epoch": 143.07079646017698, "percentage": 20.39, "elapsed_time": "0:58:29", "remaining_time": "3:48:25", "throughput": 1320.74, "total_tokens": 4635648} {"current_steps": 8160, "total_steps": 40000, "loss": 0.0, "lr": 4.504034854365381e-05, "epoch": 143.15929203539824, "percentage": 20.4, "elapsed_time": "0:58:31", "remaining_time": "3:48:23", "throughput": 1320.87, "total_tokens": 4638848} {"current_steps": 8165, "total_steps": 40000, "loss": 0.0, "lr": 4.503447769819974e-05, "epoch": 143.24778761061947, "percentage": 20.41, "elapsed_time": "0:58:34", "remaining_time": "3:48:21", "throughput": 1320.92, "total_tokens": 4641744} {"current_steps": 8170, "total_steps": 40000, "loss": 0.0, "lr": 4.502860376317745e-05, "epoch": 143.3362831858407, "percentage": 20.42, "elapsed_time": "0:58:36", "remaining_time": "3:48:18", "throughput": 1320.94, "total_tokens": 4644528} {"current_steps": 8175, "total_steps": 40000, "loss": 0.0, "lr": 4.502272673949276e-05, "epoch": 143.42477876106196, "percentage": 20.44, "elapsed_time": "0:58:38", "remaining_time": "3:48:15", "throughput": 1321.05, "total_tokens": 4647616} {"current_steps": 8180, "total_steps": 40000, "loss": 0.0, "lr": 4.501684662805199e-05, "epoch": 143.5132743362832, "percentage": 20.45, "elapsed_time": "0:58:40", "remaining_time": "3:48:13", "throughput": 1321.05, "total_tokens": 4650352} {"current_steps": 8185, "total_steps": 40000, "loss": 0.0, "lr": 4.5010963429761924e-05, "epoch": 143.60176991150442, "percentage": 20.46, "elapsed_time": "0:58:42", "remaining_time": "3:48:10", "throughput": 1321.03, "total_tokens": 4652992} {"current_steps": 8190, "total_steps": 40000, "loss": 0.0, "lr": 4.500507714552982e-05, "epoch": 143.69026548672565, "percentage": 20.47, "elapsed_time": "0:58:44", "remaining_time": "3:48:08", "throughput": 1321.1, "total_tokens": 4655984} {"current_steps": 8195, "total_steps": 40000, "loss": 0.0, "lr": 4.499918777626342e-05, "epoch": 143.7787610619469, "percentage": 20.49, "elapsed_time": "0:58:46", "remaining_time": "3:48:06", "throughput": 1321.2, "total_tokens": 4659088} {"current_steps": 8200, "total_steps": 40000, "loss": 0.0, "lr": 4.499329532287093e-05, "epoch": 143.86725663716814, "percentage": 20.5, "elapsed_time": "0:58:48", "remaining_time": "3:48:03", "throughput": 1321.31, "total_tokens": 4662192} {"current_steps": 8200, "total_steps": 40000, "eval_loss": 0.4116646647453308, "epoch": 143.86725663716814, "percentage": 20.5, "elapsed_time": "0:58:49", "remaining_time": "3:48:07", "throughput": 1320.91, "total_tokens": 4662192} {"current_steps": 8205, "total_steps": 40000, "loss": 0.0, "lr": 4.4987399786261064e-05, "epoch": 143.95575221238937, "percentage": 20.51, "elapsed_time": "0:58:53", "remaining_time": "3:48:13", "throughput": 1320.07, "total_tokens": 4664672} {"current_steps": 8210, "total_steps": 40000, "loss": 0.0, "lr": 4.498150116734297e-05, "epoch": 144.0353982300885, "percentage": 20.52, "elapsed_time": "0:58:55", "remaining_time": "3:48:11", "throughput": 1319.81, "total_tokens": 4666768} {"current_steps": 8215, "total_steps": 40000, "loss": 0.0, "lr": 4.4975599467026294e-05, "epoch": 144.12389380530973, "percentage": 20.54, "elapsed_time": "0:58:57", "remaining_time": "3:48:08", "throughput": 1319.69, "total_tokens": 4669056} {"current_steps": 8220, "total_steps": 40000, "loss": 0.0, "lr": 4.496969468622114e-05, "epoch": 144.21238938053096, "percentage": 20.55, "elapsed_time": "0:59:00", "remaining_time": "3:48:06", "throughput": 1319.77, "total_tokens": 4672064} {"current_steps": 8225, "total_steps": 40000, "loss": 0.0, "lr": 4.496378682583813e-05, "epoch": 144.30088495575222, "percentage": 20.56, "elapsed_time": "0:59:02", "remaining_time": "3:48:04", "throughput": 1319.92, "total_tokens": 4675344} {"current_steps": 8230, "total_steps": 40000, "loss": 0.0, "lr": 4.495787588678829e-05, "epoch": 144.38938053097345, "percentage": 20.57, "elapsed_time": "0:59:04", "remaining_time": "3:48:01", "throughput": 1320.02, "total_tokens": 4678432} {"current_steps": 8235, "total_steps": 40000, "loss": 0.0, "lr": 4.4951961869983196e-05, "epoch": 144.47787610619469, "percentage": 20.59, "elapsed_time": "0:59:06", "remaining_time": "3:47:59", "throughput": 1320.08, "total_tokens": 4681344} {"current_steps": 8240, "total_steps": 40000, "loss": 0.0, "lr": 4.494604477633485e-05, "epoch": 144.56637168141592, "percentage": 20.6, "elapsed_time": "0:59:08", "remaining_time": "3:47:56", "throughput": 1320.11, "total_tokens": 4684192} {"current_steps": 8245, "total_steps": 40000, "loss": 0.0, "lr": 4.4940124606755734e-05, "epoch": 144.65486725663717, "percentage": 20.61, "elapsed_time": "0:59:10", "remaining_time": "3:47:54", "throughput": 1320.05, "total_tokens": 4686688} {"current_steps": 8250, "total_steps": 40000, "loss": 0.0, "lr": 4.493420136215882e-05, "epoch": 144.7433628318584, "percentage": 20.62, "elapsed_time": "0:59:12", "remaining_time": "3:47:51", "throughput": 1320.15, "total_tokens": 4689776} {"current_steps": 8255, "total_steps": 40000, "loss": 0.0, "lr": 4.492827504345756e-05, "epoch": 144.83185840707964, "percentage": 20.64, "elapsed_time": "0:59:14", "remaining_time": "3:47:49", "throughput": 1320.12, "total_tokens": 4692384} {"current_steps": 8260, "total_steps": 40000, "loss": 0.0, "lr": 4.492234565156584e-05, "epoch": 144.9203539823009, "percentage": 20.65, "elapsed_time": "0:59:16", "remaining_time": "3:47:46", "throughput": 1320.29, "total_tokens": 4695744} {"current_steps": 8265, "total_steps": 40000, "loss": 0.0, "lr": 4.491641318739807e-05, "epoch": 145.0, "percentage": 20.66, "elapsed_time": "0:59:18", "remaining_time": "3:47:43", "throughput": 1320.23, "total_tokens": 4698160} {"current_steps": 8270, "total_steps": 40000, "loss": 0.0, "lr": 4.4910477651869096e-05, "epoch": 145.08849557522123, "percentage": 20.67, "elapsed_time": "0:59:20", "remaining_time": "3:47:42", "throughput": 1320.25, "total_tokens": 4701280} {"current_steps": 8275, "total_steps": 40000, "loss": 0.0, "lr": 4.4904539045894254e-05, "epoch": 145.1769911504425, "percentage": 20.69, "elapsed_time": "0:59:22", "remaining_time": "3:47:39", "throughput": 1320.18, "total_tokens": 4703744} {"current_steps": 8280, "total_steps": 40000, "loss": 0.0, "lr": 4.4898597370389364e-05, "epoch": 145.26548672566372, "percentage": 20.7, "elapsed_time": "0:59:25", "remaining_time": "3:47:37", "throughput": 1320.25, "total_tokens": 4706736} {"current_steps": 8285, "total_steps": 40000, "loss": 0.0, "lr": 4.489265262627069e-05, "epoch": 145.35398230088495, "percentage": 20.71, "elapsed_time": "0:59:27", "remaining_time": "3:47:34", "throughput": 1320.21, "total_tokens": 4709312} {"current_steps": 8290, "total_steps": 40000, "loss": 0.0, "lr": 4.488670481445499e-05, "epoch": 145.44247787610618, "percentage": 20.72, "elapsed_time": "0:59:29", "remaining_time": "3:47:32", "throughput": 1320.28, "total_tokens": 4712288} {"current_steps": 8295, "total_steps": 40000, "loss": 0.0, "lr": 4.488075393585951e-05, "epoch": 145.53097345132744, "percentage": 20.74, "elapsed_time": "0:59:31", "remaining_time": "3:47:29", "throughput": 1320.33, "total_tokens": 4715216} {"current_steps": 8300, "total_steps": 40000, "loss": 0.0, "lr": 4.487479999140193e-05, "epoch": 145.61946902654867, "percentage": 20.75, "elapsed_time": "0:59:33", "remaining_time": "3:47:27", "throughput": 1320.31, "total_tokens": 4717840} {"current_steps": 8305, "total_steps": 40000, "loss": 0.0, "lr": 4.4868842982000425e-05, "epoch": 145.7079646017699, "percentage": 20.76, "elapsed_time": "0:59:35", "remaining_time": "3:47:24", "throughput": 1320.3, "total_tokens": 4720560} {"current_steps": 8310, "total_steps": 40000, "loss": 0.0, "lr": 4.486288290857365e-05, "epoch": 145.79646017699116, "percentage": 20.77, "elapsed_time": "0:59:37", "remaining_time": "3:47:22", "throughput": 1320.45, "total_tokens": 4723824} {"current_steps": 8315, "total_steps": 40000, "loss": 0.0, "lr": 4.4856919772040715e-05, "epoch": 145.8849557522124, "percentage": 20.79, "elapsed_time": "0:59:39", "remaining_time": "3:47:19", "throughput": 1320.5, "total_tokens": 4726704} {"current_steps": 8320, "total_steps": 40000, "loss": 0.0, "lr": 4.485095357332122e-05, "epoch": 145.97345132743362, "percentage": 20.8, "elapsed_time": "0:59:41", "remaining_time": "3:47:17", "throughput": 1320.55, "total_tokens": 4729616} {"current_steps": 8325, "total_steps": 40000, "loss": 0.0, "lr": 4.484498431333521e-05, "epoch": 146.05309734513276, "percentage": 20.81, "elapsed_time": "0:59:43", "remaining_time": "3:47:15", "throughput": 1320.34, "total_tokens": 4731848} {"current_steps": 8330, "total_steps": 40000, "loss": 0.0, "lr": 4.4839011993003245e-05, "epoch": 146.141592920354, "percentage": 20.82, "elapsed_time": "0:59:45", "remaining_time": "3:47:13", "throughput": 1320.41, "total_tokens": 4734840} {"current_steps": 8335, "total_steps": 40000, "loss": 0.0, "lr": 4.4833036613246305e-05, "epoch": 146.23008849557522, "percentage": 20.84, "elapsed_time": "0:59:47", "remaining_time": "3:47:10", "throughput": 1320.43, "total_tokens": 4737624} {"current_steps": 8340, "total_steps": 40000, "loss": 0.0, "lr": 4.482705817498589e-05, "epoch": 146.31858407079645, "percentage": 20.85, "elapsed_time": "0:59:50", "remaining_time": "3:47:08", "throughput": 1320.53, "total_tokens": 4740712} {"current_steps": 8345, "total_steps": 40000, "loss": 0.0, "lr": 4.4821076679143934e-05, "epoch": 146.4070796460177, "percentage": 20.86, "elapsed_time": "0:59:52", "remaining_time": "3:47:05", "throughput": 1320.59, "total_tokens": 4743656} {"current_steps": 8350, "total_steps": 40000, "loss": 0.0, "lr": 4.481509212664288e-05, "epoch": 146.49557522123894, "percentage": 20.88, "elapsed_time": "0:59:54", "remaining_time": "3:47:03", "throughput": 1320.53, "total_tokens": 4746168} {"current_steps": 8355, "total_steps": 40000, "loss": 0.0, "lr": 4.480910451840559e-05, "epoch": 146.58407079646017, "percentage": 20.89, "elapsed_time": "0:59:56", "remaining_time": "3:47:00", "throughput": 1320.48, "total_tokens": 4748712} {"current_steps": 8360, "total_steps": 40000, "loss": 0.0, "lr": 4.480311385535546e-05, "epoch": 146.67256637168143, "percentage": 20.9, "elapsed_time": "0:59:58", "remaining_time": "3:46:58", "throughput": 1320.59, "total_tokens": 4751848} {"current_steps": 8365, "total_steps": 40000, "loss": 0.0, "lr": 4.47971201384163e-05, "epoch": 146.76106194690266, "percentage": 20.91, "elapsed_time": "1:00:00", "remaining_time": "3:46:55", "throughput": 1320.67, "total_tokens": 4754888} {"current_steps": 8370, "total_steps": 40000, "loss": 0.0, "lr": 4.4791123368512446e-05, "epoch": 146.8495575221239, "percentage": 20.93, "elapsed_time": "1:00:02", "remaining_time": "3:46:53", "throughput": 1320.76, "total_tokens": 4757928} {"current_steps": 8375, "total_steps": 40000, "loss": 0.0, "lr": 4.478512354656864e-05, "epoch": 146.93805309734512, "percentage": 20.94, "elapsed_time": "1:00:04", "remaining_time": "3:46:50", "throughput": 1320.8, "total_tokens": 4760760} {"current_steps": 8380, "total_steps": 40000, "loss": 0.0, "lr": 4.477912067351016e-05, "epoch": 147.01769911504425, "percentage": 20.95, "elapsed_time": "1:00:06", "remaining_time": "3:46:49", "throughput": 1320.63, "total_tokens": 4763120} {"current_steps": 8385, "total_steps": 40000, "loss": 0.0, "lr": 4.477311475026271e-05, "epoch": 147.10619469026548, "percentage": 20.96, "elapsed_time": "1:00:08", "remaining_time": "3:46:46", "throughput": 1320.61, "total_tokens": 4765792} {"current_steps": 8390, "total_steps": 40000, "loss": 0.0, "lr": 4.476710577775248e-05, "epoch": 147.1946902654867, "percentage": 20.97, "elapsed_time": "1:00:10", "remaining_time": "3:46:44", "throughput": 1320.68, "total_tokens": 4768768} {"current_steps": 8395, "total_steps": 40000, "loss": 0.0, "lr": 4.476109375690612e-05, "epoch": 147.28318584070797, "percentage": 20.99, "elapsed_time": "1:00:12", "remaining_time": "3:46:41", "throughput": 1320.73, "total_tokens": 4771664} {"current_steps": 8400, "total_steps": 40000, "loss": 0.0, "lr": 4.4755078688650784e-05, "epoch": 147.3716814159292, "percentage": 21.0, "elapsed_time": "1:00:14", "remaining_time": "3:46:39", "throughput": 1320.66, "total_tokens": 4774160} {"current_steps": 8400, "total_steps": 40000, "eval_loss": 0.4215090572834015, "epoch": 147.3716814159292, "percentage": 21.0, "elapsed_time": "1:00:16", "remaining_time": "3:46:43", "throughput": 1320.27, "total_tokens": 4774160} {"current_steps": 8405, "total_steps": 40000, "loss": 0.0, "lr": 4.474906057391406e-05, "epoch": 147.46017699115043, "percentage": 21.01, "elapsed_time": "1:00:19", "remaining_time": "3:46:46", "throughput": 1319.67, "total_tokens": 4776896} {"current_steps": 8410, "total_steps": 40000, "loss": 0.0, "lr": 4.4743039413624e-05, "epoch": 147.5486725663717, "percentage": 21.02, "elapsed_time": "1:00:21", "remaining_time": "3:46:44", "throughput": 1319.67, "total_tokens": 4779664} {"current_steps": 8415, "total_steps": 40000, "loss": 0.0, "lr": 4.473701520870916e-05, "epoch": 147.63716814159292, "percentage": 21.04, "elapsed_time": "1:00:23", "remaining_time": "3:46:42", "throughput": 1319.68, "total_tokens": 4782400} {"current_steps": 8420, "total_steps": 40000, "loss": 0.0, "lr": 4.4730987960098544e-05, "epoch": 147.72566371681415, "percentage": 21.05, "elapsed_time": "1:00:25", "remaining_time": "3:46:39", "throughput": 1319.68, "total_tokens": 4785120} {"current_steps": 8425, "total_steps": 40000, "loss": 0.0, "lr": 4.4724957668721635e-05, "epoch": 147.81415929203538, "percentage": 21.06, "elapsed_time": "1:00:28", "remaining_time": "3:46:37", "throughput": 1319.71, "total_tokens": 4787952} {"current_steps": 8430, "total_steps": 40000, "loss": 0.0, "lr": 4.471892433550836e-05, "epoch": 147.90265486725664, "percentage": 21.07, "elapsed_time": "1:00:30", "remaining_time": "3:46:34", "throughput": 1319.72, "total_tokens": 4790736} {"current_steps": 8435, "total_steps": 40000, "loss": 0.0, "lr": 4.471288796138916e-05, "epoch": 147.99115044247787, "percentage": 21.09, "elapsed_time": "1:00:32", "remaining_time": "3:46:32", "throughput": 1319.88, "total_tokens": 4794000} {"current_steps": 8440, "total_steps": 40000, "loss": 0.0, "lr": 4.470684854729491e-05, "epoch": 148.07079646017698, "percentage": 21.1, "elapsed_time": "1:00:34", "remaining_time": "3:46:30", "throughput": 1319.71, "total_tokens": 4796384} {"current_steps": 8445, "total_steps": 40000, "loss": 0.0, "lr": 4.4700806094156955e-05, "epoch": 148.15929203539824, "percentage": 21.11, "elapsed_time": "1:00:36", "remaining_time": "3:46:27", "throughput": 1319.83, "total_tokens": 4799536} {"current_steps": 8450, "total_steps": 40000, "loss": 0.0, "lr": 4.469476060290713e-05, "epoch": 148.24778761061947, "percentage": 21.12, "elapsed_time": "1:00:38", "remaining_time": "3:46:25", "throughput": 1319.74, "total_tokens": 4801936} {"current_steps": 8455, "total_steps": 40000, "loss": 0.0, "lr": 4.468871207447772e-05, "epoch": 148.3362831858407, "percentage": 21.14, "elapsed_time": "1:00:40", "remaining_time": "3:46:22", "throughput": 1319.67, "total_tokens": 4804416} {"current_steps": 8460, "total_steps": 40000, "loss": 0.0, "lr": 4.4682660509801486e-05, "epoch": 148.42477876106196, "percentage": 21.15, "elapsed_time": "1:00:42", "remaining_time": "3:46:20", "throughput": 1319.69, "total_tokens": 4807184} {"current_steps": 8465, "total_steps": 40000, "loss": 0.0, "lr": 4.467660590981165e-05, "epoch": 148.5132743362832, "percentage": 21.16, "elapsed_time": "1:00:44", "remaining_time": "3:46:17", "throughput": 1319.69, "total_tokens": 4809936} {"current_steps": 8470, "total_steps": 40000, "loss": 0.0, "lr": 4.467054827544191e-05, "epoch": 148.60176991150442, "percentage": 21.18, "elapsed_time": "1:00:46", "remaining_time": "3:46:15", "throughput": 1319.7, "total_tokens": 4812720} {"current_steps": 8475, "total_steps": 40000, "loss": 0.0, "lr": 4.4664487607626434e-05, "epoch": 148.69026548672565, "percentage": 21.19, "elapsed_time": "1:00:48", "remaining_time": "3:46:12", "throughput": 1319.85, "total_tokens": 4815968} {"current_steps": 8480, "total_steps": 40000, "loss": 0.0, "lr": 4.4658423907299845e-05, "epoch": 148.7787610619469, "percentage": 21.2, "elapsed_time": "1:00:50", "remaining_time": "3:46:10", "throughput": 1319.9, "total_tokens": 4818896} {"current_steps": 8485, "total_steps": 40000, "loss": 0.0, "lr": 4.465235717539725e-05, "epoch": 148.86725663716814, "percentage": 21.21, "elapsed_time": "1:00:53", "remaining_time": "3:46:08", "throughput": 1319.99, "total_tokens": 4821952} {"current_steps": 8490, "total_steps": 40000, "loss": 0.0, "lr": 4.464628741285421e-05, "epoch": 148.95575221238937, "percentage": 21.22, "elapsed_time": "1:00:55", "remaining_time": "3:46:05", "throughput": 1320.04, "total_tokens": 4824848} {"current_steps": 8495, "total_steps": 40000, "loss": 0.0, "lr": 4.4640214620606754e-05, "epoch": 149.0353982300885, "percentage": 21.24, "elapsed_time": "1:00:57", "remaining_time": "3:46:03", "throughput": 1320.0, "total_tokens": 4827704} {"current_steps": 8500, "total_steps": 40000, "loss": 0.0, "lr": 4.46341387995914e-05, "epoch": 149.12389380530973, "percentage": 21.25, "elapsed_time": "1:00:59", "remaining_time": "3:46:01", "throughput": 1320.03, "total_tokens": 4830552} {"current_steps": 8505, "total_steps": 40000, "loss": 0.0, "lr": 4.4628059950745106e-05, "epoch": 149.21238938053096, "percentage": 21.26, "elapsed_time": "1:01:01", "remaining_time": "3:45:58", "throughput": 1320.06, "total_tokens": 4833368} {"current_steps": 8510, "total_steps": 40000, "loss": 0.0, "lr": 4.4621978075005297e-05, "epoch": 149.30088495575222, "percentage": 21.27, "elapsed_time": "1:01:03", "remaining_time": "3:45:56", "throughput": 1320.19, "total_tokens": 4836584} {"current_steps": 8515, "total_steps": 40000, "loss": 0.0, "lr": 4.461589317330989e-05, "epoch": 149.38938053097345, "percentage": 21.29, "elapsed_time": "1:01:05", "remaining_time": "3:45:53", "throughput": 1320.27, "total_tokens": 4839592} {"current_steps": 8520, "total_steps": 40000, "loss": 0.0, "lr": 4.460980524659724e-05, "epoch": 149.47787610619469, "percentage": 21.3, "elapsed_time": "1:01:07", "remaining_time": "3:45:51", "throughput": 1320.27, "total_tokens": 4842328} {"current_steps": 8525, "total_steps": 40000, "loss": 0.0, "lr": 4.46037142958062e-05, "epoch": 149.56637168141592, "percentage": 21.31, "elapsed_time": "1:01:09", "remaining_time": "3:45:49", "throughput": 1320.18, "total_tokens": 4844728} {"current_steps": 8530, "total_steps": 40000, "loss": 0.0, "lr": 4.4597620321876046e-05, "epoch": 149.65486725663717, "percentage": 21.32, "elapsed_time": "1:01:11", "remaining_time": "3:45:46", "throughput": 1320.14, "total_tokens": 4847288} {"current_steps": 8535, "total_steps": 40000, "loss": 0.0, "lr": 4.459152332574656e-05, "epoch": 149.7433628318584, "percentage": 21.34, "elapsed_time": "1:01:13", "remaining_time": "3:45:44", "throughput": 1320.25, "total_tokens": 4850424} {"current_steps": 8540, "total_steps": 40000, "loss": 0.0, "lr": 4.4585423308357985e-05, "epoch": 149.83185840707964, "percentage": 21.35, "elapsed_time": "1:01:15", "remaining_time": "3:45:41", "throughput": 1320.34, "total_tokens": 4853496} {"current_steps": 8545, "total_steps": 40000, "loss": 0.0, "lr": 4.457932027065102e-05, "epoch": 149.9203539823009, "percentage": 21.36, "elapsed_time": "1:01:18", "remaining_time": "3:45:39", "throughput": 1320.36, "total_tokens": 4856296} {"current_steps": 8550, "total_steps": 40000, "loss": 0.0, "lr": 4.45732142135668e-05, "epoch": 150.0, "percentage": 21.38, "elapsed_time": "1:01:20", "remaining_time": "3:45:36", "throughput": 1320.38, "total_tokens": 4859016} {"current_steps": 8555, "total_steps": 40000, "loss": 0.0, "lr": 4.4567105138046986e-05, "epoch": 150.08849557522123, "percentage": 21.39, "elapsed_time": "1:01:22", "remaining_time": "3:45:34", "throughput": 1320.25, "total_tokens": 4861608} {"current_steps": 8560, "total_steps": 40000, "loss": 0.0, "lr": 4.456099304503365e-05, "epoch": 150.1769911504425, "percentage": 21.4, "elapsed_time": "1:01:24", "remaining_time": "3:45:32", "throughput": 1320.33, "total_tokens": 4864600} {"current_steps": 8565, "total_steps": 40000, "loss": 0.0, "lr": 4.455487793546939e-05, "epoch": 150.26548672566372, "percentage": 21.41, "elapsed_time": "1:01:26", "remaining_time": "3:45:29", "throughput": 1320.34, "total_tokens": 4867384} {"current_steps": 8570, "total_steps": 40000, "loss": 0.0, "lr": 4.454875981029719e-05, "epoch": 150.35398230088495, "percentage": 21.43, "elapsed_time": "1:01:28", "remaining_time": "3:45:27", "throughput": 1320.37, "total_tokens": 4870200} {"current_steps": 8575, "total_steps": 40000, "loss": 0.0, "lr": 4.454263867046057e-05, "epoch": 150.44247787610618, "percentage": 21.44, "elapsed_time": "1:01:30", "remaining_time": "3:45:24", "throughput": 1320.4, "total_tokens": 4873048} {"current_steps": 8580, "total_steps": 40000, "loss": 0.0, "lr": 4.4536514516903484e-05, "epoch": 150.53097345132744, "percentage": 21.45, "elapsed_time": "1:01:32", "remaining_time": "3:45:22", "throughput": 1320.39, "total_tokens": 4875720} {"current_steps": 8585, "total_steps": 40000, "loss": 0.0, "lr": 4.453038735057034e-05, "epoch": 150.61946902654867, "percentage": 21.46, "elapsed_time": "1:01:34", "remaining_time": "3:45:20", "throughput": 1320.51, "total_tokens": 4878888} {"current_steps": 8590, "total_steps": 40000, "loss": 0.0, "lr": 4.4524257172406034e-05, "epoch": 150.7079646017699, "percentage": 21.48, "elapsed_time": "1:01:36", "remaining_time": "3:45:17", "throughput": 1320.59, "total_tokens": 4881928} {"current_steps": 8595, "total_steps": 40000, "loss": 0.0, "lr": 4.451812398335592e-05, "epoch": 150.79646017699116, "percentage": 21.49, "elapsed_time": "1:01:38", "remaining_time": "3:45:15", "throughput": 1320.65, "total_tokens": 4884856} {"current_steps": 8600, "total_steps": 40000, "loss": 0.0, "lr": 4.4511987784365805e-05, "epoch": 150.8849557522124, "percentage": 21.5, "elapsed_time": "1:01:40", "remaining_time": "3:45:12", "throughput": 1320.66, "total_tokens": 4887640} {"current_steps": 8600, "total_steps": 40000, "eval_loss": 0.4240879714488983, "epoch": 150.8849557522124, "percentage": 21.5, "elapsed_time": "1:01:41", "remaining_time": "3:45:16", "throughput": 1320.28, "total_tokens": 4887640} {"current_steps": 8605, "total_steps": 40000, "loss": 0.0, "lr": 4.450584857638197e-05, "epoch": 150.97345132743362, "percentage": 21.51, "elapsed_time": "1:01:45", "remaining_time": "3:45:20", "throughput": 1319.81, "total_tokens": 4890808} {"current_steps": 8610, "total_steps": 40000, "loss": 0.0, "lr": 4.449970636035116e-05, "epoch": 151.05309734513276, "percentage": 21.52, "elapsed_time": "1:01:47", "remaining_time": "3:45:18", "throughput": 1319.62, "total_tokens": 4893112} {"current_steps": 8615, "total_steps": 40000, "loss": 0.0, "lr": 4.4493561137220574e-05, "epoch": 151.141592920354, "percentage": 21.54, "elapsed_time": "1:01:50", "remaining_time": "3:45:15", "throughput": 1319.55, "total_tokens": 4895576} {"current_steps": 8620, "total_steps": 40000, "loss": 0.0, "lr": 4.44874129079379e-05, "epoch": 151.23008849557522, "percentage": 21.55, "elapsed_time": "1:01:52", "remaining_time": "3:45:13", "throughput": 1319.59, "total_tokens": 4898424} {"current_steps": 8625, "total_steps": 40000, "loss": 0.0, "lr": 4.4481261673451255e-05, "epoch": 151.31858407079645, "percentage": 21.56, "elapsed_time": "1:01:54", "remaining_time": "3:45:10", "throughput": 1319.69, "total_tokens": 4901528} {"current_steps": 8630, "total_steps": 40000, "loss": 0.0, "lr": 4.4475107434709245e-05, "epoch": 151.4070796460177, "percentage": 21.57, "elapsed_time": "1:01:56", "remaining_time": "3:45:08", "throughput": 1319.71, "total_tokens": 4904328} {"current_steps": 8635, "total_steps": 40000, "loss": 0.0, "lr": 4.446895019266093e-05, "epoch": 151.49557522123894, "percentage": 21.59, "elapsed_time": "1:01:58", "remaining_time": "3:45:05", "throughput": 1319.8, "total_tokens": 4907400} {"current_steps": 8640, "total_steps": 40000, "loss": 0.0, "lr": 4.446278994825583e-05, "epoch": 151.58407079646017, "percentage": 21.6, "elapsed_time": "1:02:00", "remaining_time": "3:45:03", "throughput": 1319.93, "total_tokens": 4910600} {"current_steps": 8645, "total_steps": 40000, "loss": 0.0, "lr": 4.445662670244394e-05, "epoch": 151.67256637168143, "percentage": 21.61, "elapsed_time": "1:02:02", "remaining_time": "3:45:01", "throughput": 1320.11, "total_tokens": 4914008} {"current_steps": 8650, "total_steps": 40000, "loss": 0.0, "lr": 4.44504604561757e-05, "epoch": 151.76106194690266, "percentage": 21.62, "elapsed_time": "1:02:04", "remaining_time": "3:44:58", "throughput": 1320.12, "total_tokens": 4916760} {"current_steps": 8655, "total_steps": 40000, "loss": 0.0, "lr": 4.4444291210402035e-05, "epoch": 151.8495575221239, "percentage": 21.64, "elapsed_time": "1:02:06", "remaining_time": "3:44:56", "throughput": 1320.25, "total_tokens": 4919976} {"current_steps": 8660, "total_steps": 40000, "loss": 0.0, "lr": 4.443811896607431e-05, "epoch": 151.93805309734512, "percentage": 21.65, "elapsed_time": "1:02:08", "remaining_time": "3:44:53", "throughput": 1320.26, "total_tokens": 4922728} {"current_steps": 8665, "total_steps": 40000, "loss": 0.0, "lr": 4.443194372414436e-05, "epoch": 152.01769911504425, "percentage": 21.66, "elapsed_time": "1:02:10", "remaining_time": "3:44:51", "throughput": 1320.11, "total_tokens": 4925128} {"current_steps": 8670, "total_steps": 40000, "loss": 0.0, "lr": 4.442576548556449e-05, "epoch": 152.10619469026548, "percentage": 21.68, "elapsed_time": "1:02:12", "remaining_time": "3:44:49", "throughput": 1320.07, "total_tokens": 4927704} {"current_steps": 8675, "total_steps": 40000, "loss": 0.0, "lr": 4.441958425128747e-05, "epoch": 152.1946902654867, "percentage": 21.69, "elapsed_time": "1:02:14", "remaining_time": "3:44:46", "throughput": 1320.06, "total_tokens": 4930392} {"current_steps": 8680, "total_steps": 40000, "loss": 0.0, "lr": 4.4413400022266515e-05, "epoch": 152.28318584070797, "percentage": 21.7, "elapsed_time": "1:02:17", "remaining_time": "3:44:44", "throughput": 1320.19, "total_tokens": 4933624} {"current_steps": 8685, "total_steps": 40000, "loss": 0.0, "lr": 4.4407212799455313e-05, "epoch": 152.3716814159292, "percentage": 21.71, "elapsed_time": "1:02:19", "remaining_time": "3:44:41", "throughput": 1320.19, "total_tokens": 4936360} {"current_steps": 8690, "total_steps": 40000, "loss": 0.0, "lr": 4.4401022583808003e-05, "epoch": 152.46017699115043, "percentage": 21.73, "elapsed_time": "1:02:21", "remaining_time": "3:44:39", "throughput": 1320.27, "total_tokens": 4939368} {"current_steps": 8695, "total_steps": 40000, "loss": 0.0, "lr": 4.439482937627921e-05, "epoch": 152.5486725663717, "percentage": 21.74, "elapsed_time": "1:02:23", "remaining_time": "3:44:36", "throughput": 1320.45, "total_tokens": 4942776} {"current_steps": 8700, "total_steps": 40000, "loss": 0.0, "lr": 4.4388633177824004e-05, "epoch": 152.63716814159292, "percentage": 21.75, "elapsed_time": "1:02:25", "remaining_time": "3:44:34", "throughput": 1320.49, "total_tokens": 4945656} {"current_steps": 8705, "total_steps": 40000, "loss": 0.0, "lr": 4.4382433989397895e-05, "epoch": 152.72566371681415, "percentage": 21.76, "elapsed_time": "1:02:27", "remaining_time": "3:44:32", "throughput": 1320.47, "total_tokens": 4948312} {"current_steps": 8710, "total_steps": 40000, "loss": 0.0, "lr": 4.4376231811956895e-05, "epoch": 152.81415929203538, "percentage": 21.77, "elapsed_time": "1:02:29", "remaining_time": "3:44:29", "throughput": 1320.65, "total_tokens": 4951720} {"current_steps": 8715, "total_steps": 40000, "loss": 0.0, "lr": 4.437002664645745e-05, "epoch": 152.90265486725664, "percentage": 21.79, "elapsed_time": "1:02:31", "remaining_time": "3:44:27", "throughput": 1320.63, "total_tokens": 4954392} {"current_steps": 8720, "total_steps": 40000, "loss": 0.0, "lr": 4.436381849385649e-05, "epoch": 152.99115044247787, "percentage": 21.8, "elapsed_time": "1:02:33", "remaining_time": "3:44:24", "throughput": 1320.66, "total_tokens": 4957192} {"current_steps": 8725, "total_steps": 40000, "loss": 0.0, "lr": 4.435760735511136e-05, "epoch": 153.07079646017698, "percentage": 21.81, "elapsed_time": "1:02:35", "remaining_time": "3:44:22", "throughput": 1320.44, "total_tokens": 4959344} {"current_steps": 8730, "total_steps": 40000, "loss": 0.0, "lr": 4.435139323117992e-05, "epoch": 153.15929203539824, "percentage": 21.82, "elapsed_time": "1:02:37", "remaining_time": "3:44:20", "throughput": 1320.72, "total_tokens": 4963120} {"current_steps": 8735, "total_steps": 40000, "loss": 0.0, "lr": 4.434517612302046e-05, "epoch": 153.24778761061947, "percentage": 21.84, "elapsed_time": "1:02:39", "remaining_time": "3:44:17", "throughput": 1320.74, "total_tokens": 4965952} {"current_steps": 8740, "total_steps": 40000, "loss": 0.0, "lr": 4.433895603159174e-05, "epoch": 153.3362831858407, "percentage": 21.85, "elapsed_time": "1:02:42", "remaining_time": "3:44:15", "throughput": 1320.68, "total_tokens": 4968464} {"current_steps": 8745, "total_steps": 40000, "loss": 0.0, "lr": 4.433273295785296e-05, "epoch": 153.42477876106196, "percentage": 21.86, "elapsed_time": "1:02:44", "remaining_time": "3:44:13", "throughput": 1320.87, "total_tokens": 4971920} {"current_steps": 8750, "total_steps": 40000, "loss": 0.0, "lr": 4.432650690276382e-05, "epoch": 153.5132743362832, "percentage": 21.88, "elapsed_time": "1:02:46", "remaining_time": "3:44:10", "throughput": 1320.83, "total_tokens": 4974480} {"current_steps": 8755, "total_steps": 40000, "loss": 0.0, "lr": 4.4320277867284435e-05, "epoch": 153.60176991150442, "percentage": 21.89, "elapsed_time": "1:02:48", "remaining_time": "3:44:08", "throughput": 1320.88, "total_tokens": 4977408} {"current_steps": 8760, "total_steps": 40000, "loss": 0.0, "lr": 4.431404585237541e-05, "epoch": 153.69026548672565, "percentage": 21.9, "elapsed_time": "1:02:50", "remaining_time": "3:44:05", "throughput": 1320.95, "total_tokens": 4980384} {"current_steps": 8765, "total_steps": 40000, "loss": 0.0, "lr": 4.43078108589978e-05, "epoch": 153.7787610619469, "percentage": 21.91, "elapsed_time": "1:02:52", "remaining_time": "3:44:03", "throughput": 1321.02, "total_tokens": 4983376} {"current_steps": 8770, "total_steps": 40000, "loss": 0.0, "lr": 4.4301572888113116e-05, "epoch": 153.86725663716814, "percentage": 21.93, "elapsed_time": "1:02:54", "remaining_time": "3:44:00", "throughput": 1321.0, "total_tokens": 4986032} {"current_steps": 8775, "total_steps": 40000, "loss": 0.0, "lr": 4.4295331940683337e-05, "epoch": 153.95575221238937, "percentage": 21.94, "elapsed_time": "1:02:56", "remaining_time": "3:43:58", "throughput": 1320.96, "total_tokens": 4988576} {"current_steps": 8780, "total_steps": 40000, "loss": 0.0, "lr": 4.428908801767089e-05, "epoch": 154.0353982300885, "percentage": 21.95, "elapsed_time": "1:02:58", "remaining_time": "3:43:56", "throughput": 1320.77, "total_tokens": 4990864} {"current_steps": 8785, "total_steps": 40000, "loss": 0.0, "lr": 4.428284112003868e-05, "epoch": 154.12389380530973, "percentage": 21.96, "elapsed_time": "1:03:00", "remaining_time": "3:43:54", "throughput": 1320.83, "total_tokens": 4993824} {"current_steps": 8790, "total_steps": 40000, "loss": 0.0, "lr": 4.4276591248750033e-05, "epoch": 154.21238938053096, "percentage": 21.98, "elapsed_time": "1:03:02", "remaining_time": "3:43:51", "throughput": 1320.97, "total_tokens": 4997072} {"current_steps": 8795, "total_steps": 40000, "loss": 0.0, "lr": 4.4270338404768774e-05, "epoch": 154.30088495575222, "percentage": 21.99, "elapsed_time": "1:03:04", "remaining_time": "3:43:49", "throughput": 1320.94, "total_tokens": 4999696} {"current_steps": 8800, "total_steps": 40000, "loss": 0.0, "lr": 4.426408258905917e-05, "epoch": 154.38938053097345, "percentage": 22.0, "elapsed_time": "1:03:07", "remaining_time": "3:43:46", "throughput": 1321.06, "total_tokens": 5002864} {"current_steps": 8800, "total_steps": 40000, "eval_loss": 0.42251870036125183, "epoch": 154.38938053097345, "percentage": 22.0, "elapsed_time": "1:03:08", "remaining_time": "3:43:50", "throughput": 1320.69, "total_tokens": 5002864} {"current_steps": 8805, "total_steps": 40000, "loss": 0.0, "lr": 4.425782380258594e-05, "epoch": 154.47787610619469, "percentage": 22.01, "elapsed_time": "1:03:12", "remaining_time": "3:43:54", "throughput": 1320.01, "total_tokens": 5005568} {"current_steps": 8810, "total_steps": 40000, "loss": 0.0, "lr": 4.425156204631427e-05, "epoch": 154.56637168141592, "percentage": 22.02, "elapsed_time": "1:03:14", "remaining_time": "3:43:52", "throughput": 1320.11, "total_tokens": 5008672} {"current_steps": 8815, "total_steps": 40000, "loss": 0.0, "lr": 4.424529732120981e-05, "epoch": 154.65486725663717, "percentage": 22.04, "elapsed_time": "1:03:16", "remaining_time": "3:43:49", "throughput": 1320.11, "total_tokens": 5011440} {"current_steps": 8820, "total_steps": 40000, "loss": 0.0, "lr": 4.423902962823864e-05, "epoch": 154.7433628318584, "percentage": 22.05, "elapsed_time": "1:03:18", "remaining_time": "3:43:47", "throughput": 1320.22, "total_tokens": 5014576} {"current_steps": 8825, "total_steps": 40000, "loss": 0.0, "lr": 4.423275896836733e-05, "epoch": 154.83185840707964, "percentage": 22.06, "elapsed_time": "1:03:20", "remaining_time": "3:43:45", "throughput": 1320.26, "total_tokens": 5017440} {"current_steps": 8830, "total_steps": 40000, "loss": 0.0, "lr": 4.42264853425629e-05, "epoch": 154.9203539823009, "percentage": 22.07, "elapsed_time": "1:03:22", "remaining_time": "3:43:42", "throughput": 1320.21, "total_tokens": 5019984} {"current_steps": 8835, "total_steps": 40000, "loss": 0.0, "lr": 4.4220208751792816e-05, "epoch": 155.0, "percentage": 22.09, "elapsed_time": "1:03:24", "remaining_time": "3:43:39", "throughput": 1320.12, "total_tokens": 5022264} {"current_steps": 8840, "total_steps": 40000, "loss": 0.0, "lr": 4.421392919702499e-05, "epoch": 155.08849557522123, "percentage": 22.1, "elapsed_time": "1:03:26", "remaining_time": "3:43:38", "throughput": 1320.09, "total_tokens": 5025208} {"current_steps": 8845, "total_steps": 40000, "loss": 0.0, "lr": 4.4207646679227846e-05, "epoch": 155.1769911504425, "percentage": 22.11, "elapsed_time": "1:03:28", "remaining_time": "3:43:35", "throughput": 1320.08, "total_tokens": 5027896} {"current_steps": 8850, "total_steps": 40000, "loss": 0.0, "lr": 4.42013611993702e-05, "epoch": 155.26548672566372, "percentage": 22.12, "elapsed_time": "1:03:30", "remaining_time": "3:43:33", "throughput": 1320.19, "total_tokens": 5031048} {"current_steps": 8855, "total_steps": 40000, "loss": 0.0, "lr": 4.419507275842135e-05, "epoch": 155.35398230088495, "percentage": 22.14, "elapsed_time": "1:03:32", "remaining_time": "3:43:30", "throughput": 1320.17, "total_tokens": 5033688} {"current_steps": 8860, "total_steps": 40000, "loss": 0.0, "lr": 4.418878135735106e-05, "epoch": 155.44247787610618, "percentage": 22.15, "elapsed_time": "1:03:34", "remaining_time": "3:43:28", "throughput": 1320.28, "total_tokens": 5036840} {"current_steps": 8865, "total_steps": 40000, "loss": 0.0, "lr": 4.418248699712955e-05, "epoch": 155.53097345132744, "percentage": 22.16, "elapsed_time": "1:03:37", "remaining_time": "3:43:26", "throughput": 1320.3, "total_tokens": 5039656} {"current_steps": 8870, "total_steps": 40000, "loss": 0.0, "lr": 4.417618967872748e-05, "epoch": 155.61946902654867, "percentage": 22.18, "elapsed_time": "1:03:39", "remaining_time": "3:43:23", "throughput": 1320.34, "total_tokens": 5042568} {"current_steps": 8875, "total_steps": 40000, "loss": 0.0, "lr": 4.4169889403115985e-05, "epoch": 155.7079646017699, "percentage": 22.19, "elapsed_time": "1:03:41", "remaining_time": "3:43:21", "throughput": 1320.38, "total_tokens": 5045416} {"current_steps": 8880, "total_steps": 40000, "loss": 0.0, "lr": 4.4163586171266627e-05, "epoch": 155.79646017699116, "percentage": 22.2, "elapsed_time": "1:03:43", "remaining_time": "3:43:18", "throughput": 1320.37, "total_tokens": 5048088} {"current_steps": 8885, "total_steps": 40000, "loss": 0.0, "lr": 4.415727998415147e-05, "epoch": 155.8849557522124, "percentage": 22.21, "elapsed_time": "1:03:45", "remaining_time": "3:43:16", "throughput": 1320.35, "total_tokens": 5050776} {"current_steps": 8890, "total_steps": 40000, "loss": 0.0, "lr": 4.4150970842742985e-05, "epoch": 155.97345132743362, "percentage": 22.23, "elapsed_time": "1:03:47", "remaining_time": "3:43:13", "throughput": 1320.47, "total_tokens": 5053928} {"current_steps": 8895, "total_steps": 40000, "loss": 0.0, "lr": 4.4144658748014134e-05, "epoch": 156.05309734513276, "percentage": 22.24, "elapsed_time": "1:03:49", "remaining_time": "3:43:11", "throughput": 1320.33, "total_tokens": 5056392} {"current_steps": 8900, "total_steps": 40000, "loss": 0.0, "lr": 4.413834370093831e-05, "epoch": 156.141592920354, "percentage": 22.25, "elapsed_time": "1:03:51", "remaining_time": "3:43:09", "throughput": 1320.39, "total_tokens": 5059352} {"current_steps": 8905, "total_steps": 40000, "loss": 0.0, "lr": 4.413202570248939e-05, "epoch": 156.23008849557522, "percentage": 22.26, "elapsed_time": "1:03:53", "remaining_time": "3:43:06", "throughput": 1320.46, "total_tokens": 5062344} {"current_steps": 8910, "total_steps": 40000, "loss": 0.0, "lr": 4.412570475364167e-05, "epoch": 156.31858407079645, "percentage": 22.27, "elapsed_time": "1:03:55", "remaining_time": "3:43:04", "throughput": 1320.52, "total_tokens": 5065304} {"current_steps": 8915, "total_steps": 40000, "loss": 0.0, "lr": 4.411938085536994e-05, "epoch": 156.4070796460177, "percentage": 22.29, "elapsed_time": "1:03:57", "remaining_time": "3:43:02", "throughput": 1320.44, "total_tokens": 5067720} {"current_steps": 8920, "total_steps": 40000, "loss": 0.0, "lr": 4.41130540086494e-05, "epoch": 156.49557522123894, "percentage": 22.3, "elapsed_time": "1:04:00", "remaining_time": "3:43:00", "throughput": 1320.54, "total_tokens": 5071192} {"current_steps": 8925, "total_steps": 40000, "loss": 0.0, "lr": 4.4106724214455754e-05, "epoch": 156.58407079646017, "percentage": 22.31, "elapsed_time": "1:04:02", "remaining_time": "3:42:58", "throughput": 1320.61, "total_tokens": 5074184} {"current_steps": 8930, "total_steps": 40000, "loss": 0.0, "lr": 4.4100391473765115e-05, "epoch": 156.67256637168143, "percentage": 22.32, "elapsed_time": "1:04:04", "remaining_time": "3:42:55", "throughput": 1320.54, "total_tokens": 5076616} {"current_steps": 8935, "total_steps": 40000, "loss": 0.0, "lr": 4.409405578755408e-05, "epoch": 156.76106194690266, "percentage": 22.34, "elapsed_time": "1:04:06", "remaining_time": "3:42:53", "throughput": 1320.42, "total_tokens": 5078904} {"current_steps": 8940, "total_steps": 40000, "loss": 0.0, "lr": 4.4087717156799705e-05, "epoch": 156.8495575221239, "percentage": 22.35, "elapsed_time": "1:04:08", "remaining_time": "3:42:50", "throughput": 1320.5, "total_tokens": 5081912} {"current_steps": 8945, "total_steps": 40000, "loss": 0.0, "lr": 4.408137558247946e-05, "epoch": 156.93805309734512, "percentage": 22.36, "elapsed_time": "1:04:10", "remaining_time": "3:42:48", "throughput": 1320.64, "total_tokens": 5085192} {"current_steps": 8950, "total_steps": 40000, "loss": 0.0, "lr": 4.4075031065571306e-05, "epoch": 157.01769911504425, "percentage": 22.38, "elapsed_time": "1:04:12", "remaining_time": "3:42:46", "throughput": 1320.43, "total_tokens": 5087352} {"current_steps": 8955, "total_steps": 40000, "loss": 0.0, "lr": 4.406868360705366e-05, "epoch": 157.10619469026548, "percentage": 22.39, "elapsed_time": "1:04:14", "remaining_time": "3:42:44", "throughput": 1320.57, "total_tokens": 5090616} {"current_steps": 8960, "total_steps": 40000, "loss": 0.0, "lr": 4.406233320790536e-05, "epoch": 157.1946902654867, "percentage": 22.4, "elapsed_time": "1:04:16", "remaining_time": "3:42:41", "throughput": 1320.61, "total_tokens": 5093528} {"current_steps": 8965, "total_steps": 40000, "loss": 0.0, "lr": 4.4055979869105734e-05, "epoch": 157.28318584070797, "percentage": 22.41, "elapsed_time": "1:04:19", "remaining_time": "3:42:39", "throughput": 1320.61, "total_tokens": 5096264} {"current_steps": 8970, "total_steps": 40000, "loss": 0.0, "lr": 4.404962359163454e-05, "epoch": 157.3716814159292, "percentage": 22.43, "elapsed_time": "1:04:21", "remaining_time": "3:42:36", "throughput": 1320.69, "total_tokens": 5099288} {"current_steps": 8975, "total_steps": 40000, "loss": 0.0, "lr": 4.404326437647199e-05, "epoch": 157.46017699115043, "percentage": 22.44, "elapsed_time": "1:04:23", "remaining_time": "3:42:34", "throughput": 1320.72, "total_tokens": 5102136} {"current_steps": 8980, "total_steps": 40000, "loss": 0.0, "lr": 4.403690222459877e-05, "epoch": 157.5486725663717, "percentage": 22.45, "elapsed_time": "1:04:25", "remaining_time": "3:42:31", "throughput": 1320.75, "total_tokens": 5104952} {"current_steps": 8985, "total_steps": 40000, "loss": 0.0, "lr": 4.4030537136995984e-05, "epoch": 157.63716814159292, "percentage": 22.46, "elapsed_time": "1:04:27", "remaining_time": "3:42:29", "throughput": 1320.75, "total_tokens": 5107672} {"current_steps": 8990, "total_steps": 40000, "loss": 0.0, "lr": 4.402416911464523e-05, "epoch": 157.72566371681415, "percentage": 22.48, "elapsed_time": "1:04:29", "remaining_time": "3:42:26", "throughput": 1320.77, "total_tokens": 5110504} {"current_steps": 8995, "total_steps": 40000, "loss": 0.0, "lr": 4.4017798158528516e-05, "epoch": 157.81415929203538, "percentage": 22.49, "elapsed_time": "1:04:31", "remaining_time": "3:42:24", "throughput": 1320.75, "total_tokens": 5113192} {"current_steps": 9000, "total_steps": 40000, "loss": 0.0, "lr": 4.401142426962834e-05, "epoch": 157.90265486725664, "percentage": 22.5, "elapsed_time": "1:04:33", "remaining_time": "3:42:21", "throughput": 1320.83, "total_tokens": 5116216} {"current_steps": 9000, "total_steps": 40000, "eval_loss": 0.4309137165546417, "epoch": 157.90265486725664, "percentage": 22.5, "elapsed_time": "1:04:34", "remaining_time": "3:42:25", "throughput": 1320.47, "total_tokens": 5116216} {"current_steps": 9005, "total_steps": 40000, "loss": 0.0, "lr": 4.400504744892763e-05, "epoch": 157.99115044247787, "percentage": 22.51, "elapsed_time": "1:04:38", "remaining_time": "3:42:28", "throughput": 1319.95, "total_tokens": 5119064} {"current_steps": 9010, "total_steps": 40000, "loss": 0.0, "lr": 4.399866769740975e-05, "epoch": 158.07079646017698, "percentage": 22.53, "elapsed_time": "1:04:40", "remaining_time": "3:42:26", "throughput": 1319.8, "total_tokens": 5121440} {"current_steps": 9015, "total_steps": 40000, "loss": 0.0, "lr": 4.399228501605859e-05, "epoch": 158.15929203539824, "percentage": 22.54, "elapsed_time": "1:04:42", "remaining_time": "3:42:24", "throughput": 1319.77, "total_tokens": 5124080} {"current_steps": 9020, "total_steps": 40000, "loss": 0.0, "lr": 4.398589940585839e-05, "epoch": 158.24778761061947, "percentage": 22.55, "elapsed_time": "1:04:44", "remaining_time": "3:42:22", "throughput": 1319.72, "total_tokens": 5126608} {"current_steps": 9025, "total_steps": 40000, "loss": 0.0, "lr": 4.3979510867793917e-05, "epoch": 158.3362831858407, "percentage": 22.56, "elapsed_time": "1:04:46", "remaining_time": "3:42:19", "throughput": 1319.85, "total_tokens": 5129872} {"current_steps": 9030, "total_steps": 40000, "loss": 0.0, "lr": 4.3973119402850346e-05, "epoch": 158.42477876106196, "percentage": 22.57, "elapsed_time": "1:04:48", "remaining_time": "3:42:17", "throughput": 1319.9, "total_tokens": 5132784} {"current_steps": 9035, "total_steps": 40000, "loss": 0.0, "lr": 4.396672501201334e-05, "epoch": 158.5132743362832, "percentage": 22.59, "elapsed_time": "1:04:50", "remaining_time": "3:42:14", "throughput": 1319.89, "total_tokens": 5135456} {"current_steps": 9040, "total_steps": 40000, "loss": 0.0, "lr": 4.396032769626899e-05, "epoch": 158.60176991150442, "percentage": 22.6, "elapsed_time": "1:04:52", "remaining_time": "3:42:12", "throughput": 1320.03, "total_tokens": 5138720} {"current_steps": 9045, "total_steps": 40000, "loss": 0.0, "lr": 4.395392745660384e-05, "epoch": 158.69026548672565, "percentage": 22.61, "elapsed_time": "1:04:54", "remaining_time": "3:42:09", "throughput": 1320.02, "total_tokens": 5141424} {"current_steps": 9050, "total_steps": 40000, "loss": 0.0, "lr": 4.394752429400488e-05, "epoch": 158.7787610619469, "percentage": 22.62, "elapsed_time": "1:04:57", "remaining_time": "3:42:07", "throughput": 1320.13, "total_tokens": 5144544} {"current_steps": 9055, "total_steps": 40000, "loss": 0.0, "lr": 4.394111820945957e-05, "epoch": 158.86725663716814, "percentage": 22.64, "elapsed_time": "1:04:59", "remaining_time": "3:42:04", "throughput": 1320.13, "total_tokens": 5147264} {"current_steps": 9060, "total_steps": 40000, "loss": 0.0, "lr": 4.393470920395579e-05, "epoch": 158.95575221238937, "percentage": 22.65, "elapsed_time": "1:05:01", "remaining_time": "3:42:02", "throughput": 1320.28, "total_tokens": 5150592} {"current_steps": 9065, "total_steps": 40000, "loss": 0.0, "lr": 4.392829727848192e-05, "epoch": 159.0353982300885, "percentage": 22.66, "elapsed_time": "1:05:03", "remaining_time": "3:42:00", "throughput": 1320.22, "total_tokens": 5153320} {"current_steps": 9070, "total_steps": 40000, "loss": 0.0, "lr": 4.392188243402673e-05, "epoch": 159.12389380530973, "percentage": 22.68, "elapsed_time": "1:05:05", "remaining_time": "3:41:58", "throughput": 1320.28, "total_tokens": 5156296} {"current_steps": 9075, "total_steps": 40000, "loss": 0.0, "lr": 4.391546467157949e-05, "epoch": 159.21238938053096, "percentage": 22.69, "elapsed_time": "1:05:07", "remaining_time": "3:41:55", "throughput": 1320.33, "total_tokens": 5159224} {"current_steps": 9080, "total_steps": 40000, "loss": 0.0, "lr": 4.390904399212988e-05, "epoch": 159.30088495575222, "percentage": 22.7, "elapsed_time": "1:05:09", "remaining_time": "3:41:53", "throughput": 1320.36, "total_tokens": 5162072} {"current_steps": 9085, "total_steps": 40000, "loss": 0.0, "lr": 4.390262039666807e-05, "epoch": 159.38938053097345, "percentage": 22.71, "elapsed_time": "1:05:11", "remaining_time": "3:41:50", "throughput": 1320.36, "total_tokens": 5164808} {"current_steps": 9090, "total_steps": 40000, "loss": 0.0, "lr": 4.389619388618464e-05, "epoch": 159.47787610619469, "percentage": 22.73, "elapsed_time": "1:05:13", "remaining_time": "3:41:48", "throughput": 1320.41, "total_tokens": 5167720} {"current_steps": 9095, "total_steps": 40000, "loss": 0.0, "lr": 4.3889764461670655e-05, "epoch": 159.56637168141592, "percentage": 22.74, "elapsed_time": "1:05:15", "remaining_time": "3:41:45", "throughput": 1320.42, "total_tokens": 5170504} {"current_steps": 9100, "total_steps": 40000, "loss": 0.0, "lr": 4.38833321241176e-05, "epoch": 159.65486725663717, "percentage": 22.75, "elapsed_time": "1:05:17", "remaining_time": "3:41:43", "throughput": 1320.56, "total_tokens": 5173800} {"current_steps": 9105, "total_steps": 40000, "loss": 0.0, "lr": 4.3876896874517434e-05, "epoch": 159.7433628318584, "percentage": 22.76, "elapsed_time": "1:05:19", "remaining_time": "3:41:41", "throughput": 1320.65, "total_tokens": 5176872} {"current_steps": 9110, "total_steps": 40000, "loss": 0.0, "lr": 4.3870458713862554e-05, "epoch": 159.83185840707964, "percentage": 22.78, "elapsed_time": "1:05:21", "remaining_time": "3:41:38", "throughput": 1320.6, "total_tokens": 5179384} {"current_steps": 9115, "total_steps": 40000, "loss": 0.0, "lr": 4.386401764314579e-05, "epoch": 159.9203539823009, "percentage": 22.79, "elapsed_time": "1:05:24", "remaining_time": "3:41:36", "throughput": 1320.53, "total_tokens": 5181848} {"current_steps": 9120, "total_steps": 40000, "loss": 0.0, "lr": 4.385757366336045e-05, "epoch": 160.0, "percentage": 22.8, "elapsed_time": "1:05:26", "remaining_time": "3:41:33", "throughput": 1320.43, "total_tokens": 5184128} {"current_steps": 9125, "total_steps": 40000, "loss": 0.0, "lr": 4.385112677550027e-05, "epoch": 160.08849557522123, "percentage": 22.81, "elapsed_time": "1:05:28", "remaining_time": "3:41:31", "throughput": 1320.43, "total_tokens": 5187152} {"current_steps": 9130, "total_steps": 40000, "loss": 0.0, "lr": 4.384467698055945e-05, "epoch": 160.1769911504425, "percentage": 22.82, "elapsed_time": "1:05:30", "remaining_time": "3:41:29", "throughput": 1320.43, "total_tokens": 5189888} {"current_steps": 9135, "total_steps": 40000, "loss": 0.0, "lr": 4.383822427953261e-05, "epoch": 160.26548672566372, "percentage": 22.84, "elapsed_time": "1:05:32", "remaining_time": "3:41:27", "throughput": 1320.5, "total_tokens": 5192880} {"current_steps": 9140, "total_steps": 40000, "loss": 0.0, "lr": 4.3831768673414864e-05, "epoch": 160.35398230088495, "percentage": 22.85, "elapsed_time": "1:05:34", "remaining_time": "3:41:24", "throughput": 1320.51, "total_tokens": 5195648} {"current_steps": 9145, "total_steps": 40000, "loss": 0.0, "lr": 4.382531016320173e-05, "epoch": 160.44247787610618, "percentage": 22.86, "elapsed_time": "1:05:36", "remaining_time": "3:41:22", "throughput": 1320.51, "total_tokens": 5198352} {"current_steps": 9150, "total_steps": 40000, "loss": 0.0, "lr": 4.3818848749889184e-05, "epoch": 160.53097345132744, "percentage": 22.88, "elapsed_time": "1:05:38", "remaining_time": "3:41:19", "throughput": 1320.49, "total_tokens": 5200992} {"current_steps": 9155, "total_steps": 40000, "loss": 0.0, "lr": 4.381238443447368e-05, "epoch": 160.61946902654867, "percentage": 22.89, "elapsed_time": "1:05:40", "remaining_time": "3:41:17", "throughput": 1320.57, "total_tokens": 5204016} {"current_steps": 9160, "total_steps": 40000, "loss": 0.0, "lr": 4.380591721795208e-05, "epoch": 160.7079646017699, "percentage": 22.9, "elapsed_time": "1:05:42", "remaining_time": "3:41:14", "throughput": 1320.65, "total_tokens": 5207072} {"current_steps": 9165, "total_steps": 40000, "loss": 0.0, "lr": 4.3799447101321723e-05, "epoch": 160.79646017699116, "percentage": 22.91, "elapsed_time": "1:05:44", "remaining_time": "3:41:12", "throughput": 1320.77, "total_tokens": 5210256} {"current_steps": 9170, "total_steps": 40000, "loss": 0.0, "lr": 4.379297408558036e-05, "epoch": 160.8849557522124, "percentage": 22.93, "elapsed_time": "1:05:46", "remaining_time": "3:41:09", "throughput": 1320.8, "total_tokens": 5213088} {"current_steps": 9175, "total_steps": 40000, "loss": 0.0, "lr": 4.378649817172624e-05, "epoch": 160.97345132743362, "percentage": 22.94, "elapsed_time": "1:05:48", "remaining_time": "3:41:07", "throughput": 1320.83, "total_tokens": 5215904} {"current_steps": 9180, "total_steps": 40000, "loss": 0.0, "lr": 4.378001936075801e-05, "epoch": 161.05309734513276, "percentage": 22.95, "elapsed_time": "1:05:51", "remaining_time": "3:41:05", "throughput": 1320.66, "total_tokens": 5218216} {"current_steps": 9185, "total_steps": 40000, "loss": 0.0, "lr": 4.377353765367479e-05, "epoch": 161.141592920354, "percentage": 22.96, "elapsed_time": "1:05:53", "remaining_time": "3:41:03", "throughput": 1320.64, "total_tokens": 5220856} {"current_steps": 9190, "total_steps": 40000, "loss": 0.0, "lr": 4.376705305147614e-05, "epoch": 161.23008849557522, "percentage": 22.98, "elapsed_time": "1:05:55", "remaining_time": "3:41:00", "throughput": 1320.58, "total_tokens": 5223368} {"current_steps": 9195, "total_steps": 40000, "loss": 0.0, "lr": 4.376056555516206e-05, "epoch": 161.31858407079645, "percentage": 22.99, "elapsed_time": "1:05:57", "remaining_time": "3:40:58", "throughput": 1320.57, "total_tokens": 5226040} {"current_steps": 9200, "total_steps": 40000, "loss": 0.0, "lr": 4.375407516573302e-05, "epoch": 161.4070796460177, "percentage": 23.0, "elapsed_time": "1:05:59", "remaining_time": "3:40:55", "throughput": 1320.76, "total_tokens": 5229496} {"current_steps": 9200, "total_steps": 40000, "eval_loss": 0.42694327235221863, "epoch": 161.4070796460177, "percentage": 23.0, "elapsed_time": "1:06:00", "remaining_time": "3:40:59", "throughput": 1320.4, "total_tokens": 5229496} {"current_steps": 9205, "total_steps": 40000, "loss": 0.0, "lr": 4.3747581884189913e-05, "epoch": 161.49557522123894, "percentage": 23.01, "elapsed_time": "1:06:04", "remaining_time": "3:41:03", "throughput": 1319.82, "total_tokens": 5232456} {"current_steps": 9210, "total_steps": 40000, "loss": 0.0, "lr": 4.374108571153408e-05, "epoch": 161.58407079646017, "percentage": 23.03, "elapsed_time": "1:06:06", "remaining_time": "3:41:00", "throughput": 1319.87, "total_tokens": 5235352} {"current_steps": 9215, "total_steps": 40000, "loss": 0.0, "lr": 4.3734586648767316e-05, "epoch": 161.67256637168143, "percentage": 23.04, "elapsed_time": "1:06:08", "remaining_time": "3:40:58", "throughput": 1319.99, "total_tokens": 5238584} {"current_steps": 9220, "total_steps": 40000, "loss": 0.0, "lr": 4.372808469689186e-05, "epoch": 161.76106194690266, "percentage": 23.05, "elapsed_time": "1:06:10", "remaining_time": "3:40:55", "throughput": 1320.03, "total_tokens": 5241432} {"current_steps": 9225, "total_steps": 40000, "loss": 0.0, "lr": 4.372157985691039e-05, "epoch": 161.8495575221239, "percentage": 23.06, "elapsed_time": "1:06:12", "remaining_time": "3:40:53", "throughput": 1319.96, "total_tokens": 5243896} {"current_steps": 9230, "total_steps": 40000, "loss": 0.0, "lr": 4.371507212982603e-05, "epoch": 161.93805309734512, "percentage": 23.08, "elapsed_time": "1:06:14", "remaining_time": "3:40:50", "throughput": 1319.91, "total_tokens": 5246424} {"current_steps": 9235, "total_steps": 40000, "loss": 0.0, "lr": 4.370856151664236e-05, "epoch": 162.01769911504425, "percentage": 23.09, "elapsed_time": "1:06:17", "remaining_time": "3:40:49", "throughput": 1319.75, "total_tokens": 5248776} {"current_steps": 9240, "total_steps": 40000, "loss": 0.0, "lr": 4.3702048018363404e-05, "epoch": 162.10619469026548, "percentage": 23.1, "elapsed_time": "1:06:19", "remaining_time": "3:40:46", "throughput": 1319.77, "total_tokens": 5251608} {"current_steps": 9245, "total_steps": 40000, "loss": 0.0, "lr": 4.369553163599362e-05, "epoch": 162.1946902654867, "percentage": 23.11, "elapsed_time": "1:06:21", "remaining_time": "3:40:44", "throughput": 1319.75, "total_tokens": 5254232} {"current_steps": 9250, "total_steps": 40000, "loss": 0.0, "lr": 4.3689012370537904e-05, "epoch": 162.28318584070797, "percentage": 23.12, "elapsed_time": "1:06:23", "remaining_time": "3:40:41", "throughput": 1319.79, "total_tokens": 5257112} {"current_steps": 9255, "total_steps": 40000, "loss": 0.0, "lr": 4.368249022300164e-05, "epoch": 162.3716814159292, "percentage": 23.14, "elapsed_time": "1:06:25", "remaining_time": "3:40:39", "throughput": 1319.79, "total_tokens": 5259864} {"current_steps": 9260, "total_steps": 40000, "loss": 0.0, "lr": 4.367596519439059e-05, "epoch": 162.46017699115043, "percentage": 23.15, "elapsed_time": "1:06:27", "remaining_time": "3:40:36", "throughput": 1319.94, "total_tokens": 5263208} {"current_steps": 9265, "total_steps": 40000, "loss": 0.0, "lr": 4.366943728571101e-05, "epoch": 162.5486725663717, "percentage": 23.16, "elapsed_time": "1:06:29", "remaining_time": "3:40:34", "throughput": 1319.97, "total_tokens": 5266040} {"current_steps": 9270, "total_steps": 40000, "loss": 0.0, "lr": 4.366290649796959e-05, "epoch": 162.63716814159292, "percentage": 23.18, "elapsed_time": "1:06:31", "remaining_time": "3:40:32", "throughput": 1319.96, "total_tokens": 5268712} {"current_steps": 9275, "total_steps": 40000, "loss": 0.0, "lr": 4.3656372832173456e-05, "epoch": 162.72566371681415, "percentage": 23.19, "elapsed_time": "1:06:33", "remaining_time": "3:40:29", "throughput": 1319.98, "total_tokens": 5271544} {"current_steps": 9280, "total_steps": 40000, "loss": 0.0, "lr": 4.364983628933017e-05, "epoch": 162.81415929203538, "percentage": 23.2, "elapsed_time": "1:06:35", "remaining_time": "3:40:27", "throughput": 1320.07, "total_tokens": 5274616} {"current_steps": 9285, "total_steps": 40000, "loss": 0.0, "lr": 4.364329687044777e-05, "epoch": 162.90265486725664, "percentage": 23.21, "elapsed_time": "1:06:37", "remaining_time": "3:40:24", "throughput": 1320.15, "total_tokens": 5277656} {"current_steps": 9290, "total_steps": 40000, "loss": 0.0, "lr": 4.36367545765347e-05, "epoch": 162.99115044247787, "percentage": 23.23, "elapsed_time": "1:06:39", "remaining_time": "3:40:22", "throughput": 1320.25, "total_tokens": 5280744} {"current_steps": 9295, "total_steps": 40000, "loss": 0.0, "lr": 4.363020940859988e-05, "epoch": 163.07079646017698, "percentage": 23.24, "elapsed_time": "1:06:42", "remaining_time": "3:40:20", "throughput": 1320.16, "total_tokens": 5283384} {"current_steps": 9300, "total_steps": 40000, "loss": 0.0, "lr": 4.362366136765263e-05, "epoch": 163.15929203539824, "percentage": 23.25, "elapsed_time": "1:06:44", "remaining_time": "3:40:17", "throughput": 1320.16, "total_tokens": 5286088} {"current_steps": 9305, "total_steps": 40000, "loss": 0.0, "lr": 4.361711045470278e-05, "epoch": 163.24778761061947, "percentage": 23.26, "elapsed_time": "1:06:46", "remaining_time": "3:40:15", "throughput": 1320.2, "total_tokens": 5289016} {"current_steps": 9310, "total_steps": 40000, "loss": 0.0, "lr": 4.3610556670760524e-05, "epoch": 163.3362831858407, "percentage": 23.28, "elapsed_time": "1:06:48", "remaining_time": "3:40:13", "throughput": 1320.25, "total_tokens": 5291928} {"current_steps": 9315, "total_steps": 40000, "loss": 0.0, "lr": 4.360400001683657e-05, "epoch": 163.42477876106196, "percentage": 23.29, "elapsed_time": "1:06:50", "remaining_time": "3:40:10", "throughput": 1320.28, "total_tokens": 5294776} {"current_steps": 9320, "total_steps": 40000, "loss": 0.0, "lr": 4.3597440493942e-05, "epoch": 163.5132743362832, "percentage": 23.3, "elapsed_time": "1:06:52", "remaining_time": "3:40:08", "throughput": 1320.21, "total_tokens": 5297224} {"current_steps": 9325, "total_steps": 40000, "loss": 0.0, "lr": 4.3590878103088405e-05, "epoch": 163.60176991150442, "percentage": 23.31, "elapsed_time": "1:06:54", "remaining_time": "3:40:05", "throughput": 1320.24, "total_tokens": 5300056} {"current_steps": 9330, "total_steps": 40000, "loss": 0.0, "lr": 4.358431284528779e-05, "epoch": 163.69026548672565, "percentage": 23.33, "elapsed_time": "1:06:56", "remaining_time": "3:40:03", "throughput": 1320.3, "total_tokens": 5303032} {"current_steps": 9335, "total_steps": 40000, "loss": 0.0, "lr": 4.357774472155257e-05, "epoch": 163.7787610619469, "percentage": 23.34, "elapsed_time": "1:06:58", "remaining_time": "3:40:00", "throughput": 1320.4, "total_tokens": 5306136} {"current_steps": 9340, "total_steps": 40000, "loss": 0.0, "lr": 4.3571173732895664e-05, "epoch": 163.86725663716814, "percentage": 23.35, "elapsed_time": "1:07:00", "remaining_time": "3:39:58", "throughput": 1320.53, "total_tokens": 5309416} {"current_steps": 9345, "total_steps": 40000, "loss": 0.0, "lr": 4.356459988033039e-05, "epoch": 163.95575221238937, "percentage": 23.36, "elapsed_time": "1:07:02", "remaining_time": "3:39:55", "throughput": 1320.51, "total_tokens": 5312040} {"current_steps": 9350, "total_steps": 40000, "loss": 0.0, "lr": 4.355802316487051e-05, "epoch": 164.0353982300885, "percentage": 23.38, "elapsed_time": "1:07:04", "remaining_time": "3:39:54", "throughput": 1320.29, "total_tokens": 5314136} {"current_steps": 9355, "total_steps": 40000, "loss": 0.0, "lr": 4.355144358753025e-05, "epoch": 164.12389380530973, "percentage": 23.39, "elapsed_time": "1:07:07", "remaining_time": "3:39:51", "throughput": 1320.35, "total_tokens": 5317080} {"current_steps": 9360, "total_steps": 40000, "loss": 0.0, "lr": 4.354486114932425e-05, "epoch": 164.21238938053096, "percentage": 23.4, "elapsed_time": "1:07:09", "remaining_time": "3:39:49", "throughput": 1320.43, "total_tokens": 5320120} {"current_steps": 9365, "total_steps": 40000, "loss": 0.0, "lr": 4.353827585126762e-05, "epoch": 164.30088495575222, "percentage": 23.41, "elapsed_time": "1:07:11", "remaining_time": "3:39:46", "throughput": 1320.48, "total_tokens": 5323048} {"current_steps": 9370, "total_steps": 40000, "loss": 0.0, "lr": 4.353168769437588e-05, "epoch": 164.38938053097345, "percentage": 23.43, "elapsed_time": "1:07:13", "remaining_time": "3:39:44", "throughput": 1320.5, "total_tokens": 5325864} {"current_steps": 9375, "total_steps": 40000, "loss": 0.0, "lr": 4.3525096679665014e-05, "epoch": 164.47787610619469, "percentage": 23.44, "elapsed_time": "1:07:15", "remaining_time": "3:39:42", "throughput": 1320.55, "total_tokens": 5328824} {"current_steps": 9380, "total_steps": 40000, "loss": 0.0, "lr": 4.351850280815144e-05, "epoch": 164.56637168141592, "percentage": 23.45, "elapsed_time": "1:07:17", "remaining_time": "3:39:39", "throughput": 1320.53, "total_tokens": 5331480} {"current_steps": 9385, "total_steps": 40000, "loss": 0.0, "lr": 4.3511906080852014e-05, "epoch": 164.65486725663717, "percentage": 23.46, "elapsed_time": "1:07:19", "remaining_time": "3:39:37", "throughput": 1320.61, "total_tokens": 5334504} {"current_steps": 9390, "total_steps": 40000, "loss": 0.0, "lr": 4.350530649878404e-05, "epoch": 164.7433628318584, "percentage": 23.47, "elapsed_time": "1:07:21", "remaining_time": "3:39:34", "throughput": 1320.74, "total_tokens": 5337752} {"current_steps": 9395, "total_steps": 40000, "loss": 0.0, "lr": 4.3498704062965246e-05, "epoch": 164.83185840707964, "percentage": 23.49, "elapsed_time": "1:07:23", "remaining_time": "3:39:32", "throughput": 1320.77, "total_tokens": 5340600} {"current_steps": 9400, "total_steps": 40000, "loss": 0.0, "lr": 4.3492098774413815e-05, "epoch": 164.9203539823009, "percentage": 23.5, "elapsed_time": "1:07:25", "remaining_time": "3:39:29", "throughput": 1320.81, "total_tokens": 5343528} {"current_steps": 9400, "total_steps": 40000, "eval_loss": 0.42724984884262085, "epoch": 164.9203539823009, "percentage": 23.5, "elapsed_time": "1:07:26", "remaining_time": "3:39:33", "throughput": 1320.47, "total_tokens": 5343528} {"current_steps": 9405, "total_steps": 40000, "loss": 0.0, "lr": 4.3485490634148375e-05, "epoch": 165.0, "percentage": 23.51, "elapsed_time": "1:07:30", "remaining_time": "3:39:36", "throughput": 1319.75, "total_tokens": 5345792} {"current_steps": 9410, "total_steps": 40000, "loss": 0.0, "lr": 4.347887964318797e-05, "epoch": 165.08849557522123, "percentage": 23.52, "elapsed_time": "1:07:32", "remaining_time": "3:39:35", "throughput": 1319.79, "total_tokens": 5349024} {"current_steps": 9415, "total_steps": 40000, "loss": 0.0, "lr": 4.34722658025521e-05, "epoch": 165.1769911504425, "percentage": 23.54, "elapsed_time": "1:07:35", "remaining_time": "3:39:32", "throughput": 1319.76, "total_tokens": 5351648} {"current_steps": 9420, "total_steps": 40000, "loss": 0.0, "lr": 4.346564911326071e-05, "epoch": 165.26548672566372, "percentage": 23.55, "elapsed_time": "1:07:37", "remaining_time": "3:39:30", "throughput": 1319.85, "total_tokens": 5354752} {"current_steps": 9425, "total_steps": 40000, "loss": 0.0, "lr": 4.345902957633418e-05, "epoch": 165.35398230088495, "percentage": 23.56, "elapsed_time": "1:07:39", "remaining_time": "3:39:28", "throughput": 1319.95, "total_tokens": 5357888} {"current_steps": 9430, "total_steps": 40000, "loss": 0.0, "lr": 4.345240719279331e-05, "epoch": 165.44247787610618, "percentage": 23.57, "elapsed_time": "1:07:41", "remaining_time": "3:39:25", "throughput": 1319.92, "total_tokens": 5360512} {"current_steps": 9435, "total_steps": 40000, "loss": 0.0, "lr": 4.3445781963659374e-05, "epoch": 165.53097345132744, "percentage": 23.59, "elapsed_time": "1:07:43", "remaining_time": "3:39:23", "throughput": 1319.92, "total_tokens": 5363216} {"current_steps": 9440, "total_steps": 40000, "loss": 0.0, "lr": 4.3439153889954045e-05, "epoch": 165.61946902654867, "percentage": 23.6, "elapsed_time": "1:07:45", "remaining_time": "3:39:20", "throughput": 1319.93, "total_tokens": 5366000} {"current_steps": 9445, "total_steps": 40000, "loss": 0.0, "lr": 4.343252297269946e-05, "epoch": 165.7079646017699, "percentage": 23.61, "elapsed_time": "1:07:47", "remaining_time": "3:39:18", "throughput": 1319.88, "total_tokens": 5368528} {"current_steps": 9450, "total_steps": 40000, "loss": 0.0, "lr": 4.342588921291821e-05, "epoch": 165.79646017699116, "percentage": 23.62, "elapsed_time": "1:07:49", "remaining_time": "3:39:15", "throughput": 1319.84, "total_tokens": 5371136} {"current_steps": 9455, "total_steps": 40000, "loss": 0.0, "lr": 4.341925261163328e-05, "epoch": 165.8849557522124, "percentage": 23.64, "elapsed_time": "1:07:51", "remaining_time": "3:39:13", "throughput": 1319.95, "total_tokens": 5374288} {"current_steps": 9460, "total_steps": 40000, "loss": 0.0, "lr": 4.341261316986813e-05, "epoch": 165.97345132743362, "percentage": 23.65, "elapsed_time": "1:07:53", "remaining_time": "3:39:11", "throughput": 1320.06, "total_tokens": 5377472} {"current_steps": 9465, "total_steps": 40000, "loss": 0.0, "lr": 4.340597088864664e-05, "epoch": 166.05309734513276, "percentage": 23.66, "elapsed_time": "1:07:55", "remaining_time": "3:39:09", "throughput": 1319.84, "total_tokens": 5379560} {"current_steps": 9470, "total_steps": 40000, "loss": 0.0, "lr": 4.339932576899313e-05, "epoch": 166.141592920354, "percentage": 23.67, "elapsed_time": "1:07:57", "remaining_time": "3:39:06", "throughput": 1319.89, "total_tokens": 5382488} {"current_steps": 9475, "total_steps": 40000, "loss": 0.0, "lr": 4.3392677811932375e-05, "epoch": 166.23008849557522, "percentage": 23.69, "elapsed_time": "1:08:00", "remaining_time": "3:39:04", "throughput": 1320.13, "total_tokens": 5386232} {"current_steps": 9480, "total_steps": 40000, "loss": 0.0, "lr": 4.338602701848956e-05, "epoch": 166.31858407079645, "percentage": 23.7, "elapsed_time": "1:08:02", "remaining_time": "3:39:02", "throughput": 1320.16, "total_tokens": 5389112} {"current_steps": 9485, "total_steps": 40000, "loss": 0.0, "lr": 4.337937338969033e-05, "epoch": 166.4070796460177, "percentage": 23.71, "elapsed_time": "1:08:04", "remaining_time": "3:38:59", "throughput": 1320.13, "total_tokens": 5391752} {"current_steps": 9490, "total_steps": 40000, "loss": 0.0, "lr": 4.337271692656075e-05, "epoch": 166.49557522123894, "percentage": 23.72, "elapsed_time": "1:08:06", "remaining_time": "3:38:57", "throughput": 1320.02, "total_tokens": 5394056} {"current_steps": 9495, "total_steps": 40000, "loss": 0.0, "lr": 4.336605763012733e-05, "epoch": 166.58407079646017, "percentage": 23.74, "elapsed_time": "1:08:08", "remaining_time": "3:38:55", "throughput": 1320.01, "total_tokens": 5396792} {"current_steps": 9500, "total_steps": 40000, "loss": 0.0, "lr": 4.3359395501417026e-05, "epoch": 166.67256637168143, "percentage": 23.75, "elapsed_time": "1:08:10", "remaining_time": "3:38:52", "throughput": 1320.11, "total_tokens": 5399960} {"current_steps": 9505, "total_steps": 40000, "loss": 0.0, "lr": 4.335273054145722e-05, "epoch": 166.76106194690266, "percentage": 23.76, "elapsed_time": "1:08:12", "remaining_time": "3:38:50", "throughput": 1320.19, "total_tokens": 5403048} {"current_steps": 9510, "total_steps": 40000, "loss": 0.0, "lr": 4.334606275127572e-05, "epoch": 166.8495575221239, "percentage": 23.77, "elapsed_time": "1:08:14", "remaining_time": "3:38:48", "throughput": 1320.25, "total_tokens": 5406024} {"current_steps": 9515, "total_steps": 40000, "loss": 0.0, "lr": 4.33393921319008e-05, "epoch": 166.93805309734512, "percentage": 23.79, "elapsed_time": "1:08:16", "remaining_time": "3:38:45", "throughput": 1320.24, "total_tokens": 5408744} {"current_steps": 9520, "total_steps": 40000, "loss": 0.0, "lr": 4.3332718684361146e-05, "epoch": 167.01769911504425, "percentage": 23.8, "elapsed_time": "1:08:19", "remaining_time": "3:38:43", "throughput": 1320.04, "total_tokens": 5410896} {"current_steps": 9525, "total_steps": 40000, "loss": 0.0, "lr": 4.332604240968588e-05, "epoch": 167.10619469026548, "percentage": 23.81, "elapsed_time": "1:08:21", "remaining_time": "3:38:41", "throughput": 1320.01, "total_tokens": 5413488} {"current_steps": 9530, "total_steps": 40000, "loss": 0.0, "lr": 4.331936330890459e-05, "epoch": 167.1946902654867, "percentage": 23.82, "elapsed_time": "1:08:23", "remaining_time": "3:38:38", "throughput": 1320.01, "total_tokens": 5416224} {"current_steps": 9535, "total_steps": 40000, "loss": 0.0, "lr": 4.331268138304725e-05, "epoch": 167.28318584070797, "percentage": 23.84, "elapsed_time": "1:08:25", "remaining_time": "3:38:36", "throughput": 1320.01, "total_tokens": 5418960} {"current_steps": 9540, "total_steps": 40000, "loss": 0.0, "lr": 4.330599663314431e-05, "epoch": 167.3716814159292, "percentage": 23.85, "elapsed_time": "1:08:27", "remaining_time": "3:38:34", "throughput": 1319.96, "total_tokens": 5421488} {"current_steps": 9545, "total_steps": 40000, "loss": 0.0, "lr": 4.329930906022665e-05, "epoch": 167.46017699115043, "percentage": 23.86, "elapsed_time": "1:08:29", "remaining_time": "3:38:31", "throughput": 1320.04, "total_tokens": 5424528} {"current_steps": 9550, "total_steps": 40000, "loss": 0.0, "lr": 4.3292618665325564e-05, "epoch": 167.5486725663717, "percentage": 23.88, "elapsed_time": "1:08:31", "remaining_time": "3:38:29", "throughput": 1320.04, "total_tokens": 5427264} {"current_steps": 9555, "total_steps": 40000, "loss": 0.0, "lr": 4.3285925449472796e-05, "epoch": 167.63716814159292, "percentage": 23.89, "elapsed_time": "1:08:33", "remaining_time": "3:38:26", "throughput": 1320.11, "total_tokens": 5430304} {"current_steps": 9560, "total_steps": 40000, "loss": 0.0, "lr": 4.327922941370054e-05, "epoch": 167.72566371681415, "percentage": 23.9, "elapsed_time": "1:08:35", "remaining_time": "3:38:24", "throughput": 1320.17, "total_tokens": 5433264} {"current_steps": 9565, "total_steps": 40000, "loss": 0.0, "lr": 4.3272530559041384e-05, "epoch": 167.81415929203538, "percentage": 23.91, "elapsed_time": "1:08:37", "remaining_time": "3:38:22", "throughput": 1320.28, "total_tokens": 5436464} {"current_steps": 9570, "total_steps": 40000, "loss": 0.0, "lr": 4.32658288865284e-05, "epoch": 167.90265486725664, "percentage": 23.93, "elapsed_time": "1:08:39", "remaining_time": "3:38:19", "throughput": 1320.35, "total_tokens": 5439456} {"current_steps": 9575, "total_steps": 40000, "loss": 0.0, "lr": 4.325912439719505e-05, "epoch": 167.99115044247787, "percentage": 23.94, "elapsed_time": "1:08:41", "remaining_time": "3:38:17", "throughput": 1320.44, "total_tokens": 5442544} {"current_steps": 9580, "total_steps": 40000, "loss": 0.0, "lr": 4.3252417092075266e-05, "epoch": 168.07079646017698, "percentage": 23.95, "elapsed_time": "1:08:44", "remaining_time": "3:38:15", "throughput": 1320.2, "total_tokens": 5444544} {"current_steps": 9585, "total_steps": 40000, "loss": 0.0, "lr": 4.3245706972203385e-05, "epoch": 168.15929203539824, "percentage": 23.96, "elapsed_time": "1:08:46", "remaining_time": "3:38:12", "throughput": 1320.21, "total_tokens": 5447296} {"current_steps": 9590, "total_steps": 40000, "loss": 0.0, "lr": 4.323899403861421e-05, "epoch": 168.24778761061947, "percentage": 23.97, "elapsed_time": "1:08:48", "remaining_time": "3:38:10", "throughput": 1320.17, "total_tokens": 5449888} {"current_steps": 9595, "total_steps": 40000, "loss": 0.0, "lr": 4.3232278292342935e-05, "epoch": 168.3362831858407, "percentage": 23.99, "elapsed_time": "1:08:50", "remaining_time": "3:38:08", "throughput": 1320.13, "total_tokens": 5452416} {"current_steps": 9600, "total_steps": 40000, "loss": 0.0, "lr": 4.322555973442524e-05, "epoch": 168.42477876106196, "percentage": 24.0, "elapsed_time": "1:08:52", "remaining_time": "3:38:05", "throughput": 1320.22, "total_tokens": 5455520} {"current_steps": 9600, "total_steps": 40000, "eval_loss": 0.42814141511917114, "epoch": 168.42477876106196, "percentage": 24.0, "elapsed_time": "1:08:53", "remaining_time": "3:38:08", "throughput": 1319.88, "total_tokens": 5455520} {"current_steps": 9605, "total_steps": 40000, "loss": 0.0, "lr": 4.3218838365897184e-05, "epoch": 168.5132743362832, "percentage": 24.01, "elapsed_time": "1:08:57", "remaining_time": "3:38:11", "throughput": 1319.29, "total_tokens": 5457984} {"current_steps": 9610, "total_steps": 40000, "loss": 0.0, "lr": 4.3212114187795306e-05, "epoch": 168.60176991150442, "percentage": 24.02, "elapsed_time": "1:08:59", "remaining_time": "3:38:09", "throughput": 1319.36, "total_tokens": 5460992} {"current_steps": 9615, "total_steps": 40000, "loss": 0.0, "lr": 4.320538720115656e-05, "epoch": 168.69026548672565, "percentage": 24.04, "elapsed_time": "1:09:01", "remaining_time": "3:38:06", "throughput": 1319.53, "total_tokens": 5464464} {"current_steps": 9620, "total_steps": 40000, "loss": 0.0, "lr": 4.319865740701831e-05, "epoch": 168.7787610619469, "percentage": 24.05, "elapsed_time": "1:09:03", "remaining_time": "3:38:04", "throughput": 1319.55, "total_tokens": 5467280} {"current_steps": 9625, "total_steps": 40000, "loss": 0.0, "lr": 4.3191924806418396e-05, "epoch": 168.86725663716814, "percentage": 24.06, "elapsed_time": "1:09:05", "remaining_time": "3:38:02", "throughput": 1319.57, "total_tokens": 5470064} {"current_steps": 9630, "total_steps": 40000, "loss": 0.0, "lr": 4.318518940039507e-05, "epoch": 168.95575221238937, "percentage": 24.07, "elapsed_time": "1:09:07", "remaining_time": "3:37:59", "throughput": 1319.77, "total_tokens": 5473632} {"current_steps": 9635, "total_steps": 40000, "loss": 0.0, "lr": 4.3178451189987e-05, "epoch": 169.0353982300885, "percentage": 24.09, "elapsed_time": "1:09:09", "remaining_time": "3:37:57", "throughput": 1319.64, "total_tokens": 5476040} {"current_steps": 9640, "total_steps": 40000, "loss": 0.0, "lr": 4.3171710176233315e-05, "epoch": 169.12389380530973, "percentage": 24.1, "elapsed_time": "1:09:11", "remaining_time": "3:37:55", "throughput": 1319.81, "total_tokens": 5479496} {"current_steps": 9645, "total_steps": 40000, "loss": 0.0, "lr": 4.316496636017355e-05, "epoch": 169.21238938053096, "percentage": 24.11, "elapsed_time": "1:09:13", "remaining_time": "3:37:52", "throughput": 1319.84, "total_tokens": 5482344} {"current_steps": 9650, "total_steps": 40000, "loss": 0.0, "lr": 4.315821974284771e-05, "epoch": 169.30088495575222, "percentage": 24.12, "elapsed_time": "1:09:15", "remaining_time": "3:37:50", "throughput": 1319.86, "total_tokens": 5485160} {"current_steps": 9655, "total_steps": 40000, "loss": 0.0, "lr": 4.315147032529619e-05, "epoch": 169.38938053097345, "percentage": 24.14, "elapsed_time": "1:09:17", "remaining_time": "3:37:48", "throughput": 1320.01, "total_tokens": 5488504} {"current_steps": 9660, "total_steps": 40000, "loss": 0.0, "lr": 4.3144718108559845e-05, "epoch": 169.47787610619469, "percentage": 24.15, "elapsed_time": "1:09:20", "remaining_time": "3:37:45", "throughput": 1320.04, "total_tokens": 5491368} {"current_steps": 9665, "total_steps": 40000, "loss": 0.0, "lr": 4.3137963093679945e-05, "epoch": 169.56637168141592, "percentage": 24.16, "elapsed_time": "1:09:22", "remaining_time": "3:37:43", "throughput": 1320.04, "total_tokens": 5494088} {"current_steps": 9670, "total_steps": 40000, "loss": 0.0, "lr": 4.31312052816982e-05, "epoch": 169.65486725663717, "percentage": 24.18, "elapsed_time": "1:09:24", "remaining_time": "3:37:40", "throughput": 1319.98, "total_tokens": 5496600} {"current_steps": 9675, "total_steps": 40000, "loss": 0.0, "lr": 4.312444467365675e-05, "epoch": 169.7433628318584, "percentage": 24.19, "elapsed_time": "1:09:26", "remaining_time": "3:37:38", "throughput": 1320.07, "total_tokens": 5499688} {"current_steps": 9680, "total_steps": 40000, "loss": 0.0, "lr": 4.311768127059816e-05, "epoch": 169.83185840707964, "percentage": 24.2, "elapsed_time": "1:09:28", "remaining_time": "3:37:35", "throughput": 1320.07, "total_tokens": 5502408} {"current_steps": 9685, "total_steps": 40000, "loss": 0.0, "lr": 4.3110915073565444e-05, "epoch": 169.9203539823009, "percentage": 24.21, "elapsed_time": "1:09:30", "remaining_time": "3:37:33", "throughput": 1319.95, "total_tokens": 5504648} {"current_steps": 9690, "total_steps": 40000, "loss": 0.0, "lr": 4.310414608360203e-05, "epoch": 170.0, "percentage": 24.22, "elapsed_time": "1:09:32", "remaining_time": "3:37:31", "throughput": 1320.0, "total_tokens": 5507520} {"current_steps": 9695, "total_steps": 40000, "loss": 0.0, "lr": 4.309737430175177e-05, "epoch": 170.08849557522123, "percentage": 24.24, "elapsed_time": "1:09:34", "remaining_time": "3:37:29", "throughput": 1319.96, "total_tokens": 5510368} {"current_steps": 9700, "total_steps": 40000, "loss": 0.0, "lr": 4.309059972905897e-05, "epoch": 170.1769911504425, "percentage": 24.25, "elapsed_time": "1:09:36", "remaining_time": "3:37:26", "throughput": 1320.01, "total_tokens": 5513312} {"current_steps": 9705, "total_steps": 40000, "loss": 0.0, "lr": 4.308382236656836e-05, "epoch": 170.26548672566372, "percentage": 24.26, "elapsed_time": "1:09:38", "remaining_time": "3:37:24", "throughput": 1320.04, "total_tokens": 5516144} {"current_steps": 9710, "total_steps": 40000, "loss": 0.0, "lr": 4.307704221532507e-05, "epoch": 170.35398230088495, "percentage": 24.27, "elapsed_time": "1:09:40", "remaining_time": "3:37:22", "throughput": 1320.21, "total_tokens": 5519584} {"current_steps": 9715, "total_steps": 40000, "loss": 0.0, "lr": 4.307025927637471e-05, "epoch": 170.44247787610618, "percentage": 24.29, "elapsed_time": "1:09:42", "remaining_time": "3:37:19", "throughput": 1320.32, "total_tokens": 5522768} {"current_steps": 9720, "total_steps": 40000, "loss": 0.0, "lr": 4.306347355076328e-05, "epoch": 170.53097345132744, "percentage": 24.3, "elapsed_time": "1:09:44", "remaining_time": "3:37:17", "throughput": 1320.41, "total_tokens": 5525888} {"current_steps": 9725, "total_steps": 40000, "loss": 0.0, "lr": 4.305668503953724e-05, "epoch": 170.61946902654867, "percentage": 24.31, "elapsed_time": "1:09:47", "remaining_time": "3:37:14", "throughput": 1320.49, "total_tokens": 5528976} {"current_steps": 9730, "total_steps": 40000, "loss": 0.0, "lr": 4.3049893743743436e-05, "epoch": 170.7079646017699, "percentage": 24.32, "elapsed_time": "1:09:49", "remaining_time": "3:37:12", "throughput": 1320.47, "total_tokens": 5531600} {"current_steps": 9735, "total_steps": 40000, "loss": 0.0, "lr": 4.304309966442919e-05, "epoch": 170.79646017699116, "percentage": 24.34, "elapsed_time": "1:09:51", "remaining_time": "3:37:09", "throughput": 1320.41, "total_tokens": 5534096} {"current_steps": 9740, "total_steps": 40000, "loss": 0.0, "lr": 4.303630280264224e-05, "epoch": 170.8849557522124, "percentage": 24.35, "elapsed_time": "1:09:53", "remaining_time": "3:37:07", "throughput": 1320.46, "total_tokens": 5537040} {"current_steps": 9745, "total_steps": 40000, "loss": 0.0, "lr": 4.302950315943074e-05, "epoch": 170.97345132743362, "percentage": 24.36, "elapsed_time": "1:09:55", "remaining_time": "3:37:05", "throughput": 1320.38, "total_tokens": 5539408} {"current_steps": 9750, "total_steps": 40000, "loss": 0.0, "lr": 4.3022700735843275e-05, "epoch": 171.05309734513276, "percentage": 24.38, "elapsed_time": "1:09:57", "remaining_time": "3:37:03", "throughput": 1320.26, "total_tokens": 5541880} {"current_steps": 9755, "total_steps": 40000, "loss": 0.0, "lr": 4.301589553292887e-05, "epoch": 171.141592920354, "percentage": 24.39, "elapsed_time": "1:09:59", "remaining_time": "3:37:00", "throughput": 1320.27, "total_tokens": 5544680} {"current_steps": 9760, "total_steps": 40000, "loss": 0.0, "lr": 4.300908755173697e-05, "epoch": 171.23008849557522, "percentage": 24.4, "elapsed_time": "1:10:01", "remaining_time": "3:36:58", "throughput": 1320.26, "total_tokens": 5547368} {"current_steps": 9765, "total_steps": 40000, "loss": 0.0, "lr": 4.300227679331745e-05, "epoch": 171.31858407079645, "percentage": 24.41, "elapsed_time": "1:10:03", "remaining_time": "3:36:56", "throughput": 1320.44, "total_tokens": 5550840} {"current_steps": 9770, "total_steps": 40000, "loss": 0.0, "lr": 4.299546325872063e-05, "epoch": 171.4070796460177, "percentage": 24.43, "elapsed_time": "1:10:05", "remaining_time": "3:36:53", "throughput": 1320.52, "total_tokens": 5553928} {"current_steps": 9775, "total_steps": 40000, "loss": 0.0, "lr": 4.2988646948997225e-05, "epoch": 171.49557522123894, "percentage": 24.44, "elapsed_time": "1:10:07", "remaining_time": "3:36:51", "throughput": 1320.73, "total_tokens": 5557528} {"current_steps": 9780, "total_steps": 40000, "loss": 0.0, "lr": 4.29818278651984e-05, "epoch": 171.58407079646017, "percentage": 24.45, "elapsed_time": "1:10:09", "remaining_time": "3:36:48", "throughput": 1320.72, "total_tokens": 5560232} {"current_steps": 9785, "total_steps": 40000, "loss": 0.0, "lr": 4.297500600837574e-05, "epoch": 171.67256637168143, "percentage": 24.46, "elapsed_time": "1:10:12", "remaining_time": "3:36:46", "throughput": 1320.81, "total_tokens": 5563320} {"current_steps": 9790, "total_steps": 40000, "loss": 0.0, "lr": 4.2968181379581276e-05, "epoch": 171.76106194690266, "percentage": 24.47, "elapsed_time": "1:10:14", "remaining_time": "3:36:43", "throughput": 1320.81, "total_tokens": 5566072} {"current_steps": 9795, "total_steps": 40000, "loss": 0.0, "lr": 4.296135397986743e-05, "epoch": 171.8495575221239, "percentage": 24.49, "elapsed_time": "1:10:16", "remaining_time": "3:36:41", "throughput": 1320.81, "total_tokens": 5568776} {"current_steps": 9800, "total_steps": 40000, "loss": 0.0, "lr": 4.295452381028709e-05, "epoch": 171.93805309734512, "percentage": 24.5, "elapsed_time": "1:10:18", "remaining_time": "3:36:39", "throughput": 1320.72, "total_tokens": 5571144} {"current_steps": 9800, "total_steps": 40000, "eval_loss": 0.42372962832450867, "epoch": 171.93805309734512, "percentage": 24.5, "elapsed_time": "1:10:19", "remaining_time": "3:36:42", "throughput": 1320.39, "total_tokens": 5571144} {"current_steps": 9805, "total_steps": 40000, "loss": 0.0, "lr": 4.294769087189354e-05, "epoch": 172.01769911504425, "percentage": 24.51, "elapsed_time": "1:10:24", "remaining_time": "3:36:48", "throughput": 1319.49, "total_tokens": 5573536} {"current_steps": 9810, "total_steps": 40000, "loss": 0.0, "lr": 4.294085516574052e-05, "epoch": 172.10619469026548, "percentage": 24.52, "elapsed_time": "1:10:26", "remaining_time": "3:36:45", "throughput": 1319.71, "total_tokens": 5577200} {"current_steps": 9815, "total_steps": 40000, "loss": 0.0, "lr": 4.2934016692882176e-05, "epoch": 172.1946902654867, "percentage": 24.54, "elapsed_time": "1:10:28", "remaining_time": "3:36:43", "throughput": 1319.67, "total_tokens": 5579760} {"current_steps": 9820, "total_steps": 40000, "loss": 0.0, "lr": 4.292717545437308e-05, "epoch": 172.28318584070797, "percentage": 24.55, "elapsed_time": "1:10:30", "remaining_time": "3:36:40", "throughput": 1319.62, "total_tokens": 5582272} {"current_steps": 9825, "total_steps": 40000, "loss": 0.0, "lr": 4.292033145126825e-05, "epoch": 172.3716814159292, "percentage": 24.56, "elapsed_time": "1:10:32", "remaining_time": "3:36:38", "throughput": 1319.61, "total_tokens": 5584960} {"current_steps": 9830, "total_steps": 40000, "loss": 0.0, "lr": 4.29134846846231e-05, "epoch": 172.46017699115043, "percentage": 24.57, "elapsed_time": "1:10:34", "remaining_time": "3:36:35", "throughput": 1319.68, "total_tokens": 5587952} {"current_steps": 9835, "total_steps": 40000, "loss": 0.0, "lr": 4.29066351554935e-05, "epoch": 172.5486725663717, "percentage": 24.59, "elapsed_time": "1:10:36", "remaining_time": "3:36:33", "throughput": 1319.71, "total_tokens": 5590816} {"current_steps": 9840, "total_steps": 40000, "loss": 0.0, "lr": 4.289978286493574e-05, "epoch": 172.63716814159292, "percentage": 24.6, "elapsed_time": "1:10:38", "remaining_time": "3:36:31", "throughput": 1319.72, "total_tokens": 5593600} {"current_steps": 9845, "total_steps": 40000, "loss": 0.0, "lr": 4.28929278140065e-05, "epoch": 172.72566371681415, "percentage": 24.61, "elapsed_time": "1:10:40", "remaining_time": "3:36:28", "throughput": 1319.75, "total_tokens": 5596416} {"current_steps": 9850, "total_steps": 40000, "loss": 0.0, "lr": 4.288607000376295e-05, "epoch": 172.81415929203538, "percentage": 24.62, "elapsed_time": "1:10:42", "remaining_time": "3:36:26", "throughput": 1319.79, "total_tokens": 5599328} {"current_steps": 9855, "total_steps": 40000, "loss": 0.0, "lr": 4.2879209435262624e-05, "epoch": 172.90265486725664, "percentage": 24.64, "elapsed_time": "1:10:44", "remaining_time": "3:36:23", "throughput": 1319.84, "total_tokens": 5602256} {"current_steps": 9860, "total_steps": 40000, "loss": 0.0, "lr": 4.287234610956353e-05, "epoch": 172.99115044247787, "percentage": 24.65, "elapsed_time": "1:10:46", "remaining_time": "3:36:21", "throughput": 1319.93, "total_tokens": 5605344} {"current_steps": 9865, "total_steps": 40000, "loss": 0.0, "lr": 4.2865480027724056e-05, "epoch": 173.07079646017698, "percentage": 24.66, "elapsed_time": "1:10:48", "remaining_time": "3:36:19", "throughput": 1319.85, "total_tokens": 5608000} {"current_steps": 9870, "total_steps": 40000, "loss": 0.0, "lr": 4.285861119080306e-05, "epoch": 173.15929203539824, "percentage": 24.68, "elapsed_time": "1:10:51", "remaining_time": "3:36:17", "throughput": 1319.89, "total_tokens": 5610912} {"current_steps": 9875, "total_steps": 40000, "loss": 0.0, "lr": 4.2851739599859784e-05, "epoch": 173.24778761061947, "percentage": 24.69, "elapsed_time": "1:10:53", "remaining_time": "3:36:14", "throughput": 1319.85, "total_tokens": 5613472} {"current_steps": 9880, "total_steps": 40000, "loss": 0.0, "lr": 4.2844865255953934e-05, "epoch": 173.3362831858407, "percentage": 24.7, "elapsed_time": "1:10:55", "remaining_time": "3:36:12", "throughput": 1320.0, "total_tokens": 5616848} {"current_steps": 9885, "total_steps": 40000, "loss": 0.0, "lr": 4.2837988160145605e-05, "epoch": 173.42477876106196, "percentage": 24.71, "elapsed_time": "1:10:57", "remaining_time": "3:36:09", "throughput": 1320.05, "total_tokens": 5619792} {"current_steps": 9890, "total_steps": 40000, "loss": 0.0, "lr": 4.2831108313495336e-05, "epoch": 173.5132743362832, "percentage": 24.73, "elapsed_time": "1:10:59", "remaining_time": "3:36:07", "throughput": 1320.04, "total_tokens": 5622464} {"current_steps": 9895, "total_steps": 40000, "loss": 0.0, "lr": 4.282422571706408e-05, "epoch": 173.60176991150442, "percentage": 24.74, "elapsed_time": "1:11:01", "remaining_time": "3:36:05", "throughput": 1320.01, "total_tokens": 5625072} {"current_steps": 9900, "total_steps": 40000, "loss": 0.0, "lr": 4.281734037191323e-05, "epoch": 173.69026548672565, "percentage": 24.75, "elapsed_time": "1:11:03", "remaining_time": "3:36:02", "throughput": 1320.04, "total_tokens": 5627920} {"current_steps": 9905, "total_steps": 40000, "loss": 0.0, "lr": 4.281045227910459e-05, "epoch": 173.7787610619469, "percentage": 24.76, "elapsed_time": "1:11:05", "remaining_time": "3:36:00", "throughput": 1320.16, "total_tokens": 5631152} {"current_steps": 9910, "total_steps": 40000, "loss": 0.0, "lr": 4.280356143970038e-05, "epoch": 173.86725663716814, "percentage": 24.77, "elapsed_time": "1:11:07", "remaining_time": "3:35:57", "throughput": 1320.18, "total_tokens": 5633968} {"current_steps": 9915, "total_steps": 40000, "loss": 0.0, "lr": 4.279666785476327e-05, "epoch": 173.95575221238937, "percentage": 24.79, "elapsed_time": "1:11:09", "remaining_time": "3:35:55", "throughput": 1320.23, "total_tokens": 5636880} {"current_steps": 9920, "total_steps": 40000, "loss": 0.0, "lr": 4.2789771525356325e-05, "epoch": 174.0353982300885, "percentage": 24.8, "elapsed_time": "1:11:11", "remaining_time": "3:35:53", "throughput": 1320.03, "total_tokens": 5638976} {"current_steps": 9925, "total_steps": 40000, "loss": 0.0, "lr": 4.2782872452543056e-05, "epoch": 174.12389380530973, "percentage": 24.81, "elapsed_time": "1:11:13", "remaining_time": "3:35:50", "throughput": 1320.08, "total_tokens": 5641904} {"current_steps": 9930, "total_steps": 40000, "loss": 0.0, "lr": 4.2775970637387376e-05, "epoch": 174.21238938053096, "percentage": 24.82, "elapsed_time": "1:11:16", "remaining_time": "3:35:48", "throughput": 1320.09, "total_tokens": 5644704} {"current_steps": 9935, "total_steps": 40000, "loss": 0.0, "lr": 4.276906608095363e-05, "epoch": 174.30088495575222, "percentage": 24.84, "elapsed_time": "1:11:18", "remaining_time": "3:35:46", "throughput": 1320.16, "total_tokens": 5647760} {"current_steps": 9940, "total_steps": 40000, "loss": 0.0, "lr": 4.276215878430661e-05, "epoch": 174.38938053097345, "percentage": 24.85, "elapsed_time": "1:11:20", "remaining_time": "3:35:43", "throughput": 1320.26, "total_tokens": 5650896} {"current_steps": 9945, "total_steps": 40000, "loss": 0.0, "lr": 4.275524874851149e-05, "epoch": 174.47787610619469, "percentage": 24.86, "elapsed_time": "1:11:22", "remaining_time": "3:35:41", "throughput": 1320.3, "total_tokens": 5653824} {"current_steps": 9950, "total_steps": 40000, "loss": 0.0, "lr": 4.274833597463388e-05, "epoch": 174.56637168141592, "percentage": 24.88, "elapsed_time": "1:11:24", "remaining_time": "3:35:38", "throughput": 1320.29, "total_tokens": 5656496} {"current_steps": 9955, "total_steps": 40000, "loss": 0.0, "lr": 4.2741420463739824e-05, "epoch": 174.65486725663717, "percentage": 24.89, "elapsed_time": "1:11:26", "remaining_time": "3:35:36", "throughput": 1320.41, "total_tokens": 5659728} {"current_steps": 9960, "total_steps": 40000, "loss": 0.0, "lr": 4.273450221689578e-05, "epoch": 174.7433628318584, "percentage": 24.9, "elapsed_time": "1:11:28", "remaining_time": "3:35:34", "throughput": 1320.46, "total_tokens": 5662688} {"current_steps": 9965, "total_steps": 40000, "loss": 0.0, "lr": 4.272758123516863e-05, "epoch": 174.83185840707964, "percentage": 24.91, "elapsed_time": "1:11:30", "remaining_time": "3:35:31", "throughput": 1320.44, "total_tokens": 5665344} {"current_steps": 9970, "total_steps": 40000, "loss": 0.0, "lr": 4.272065751962567e-05, "epoch": 174.9203539823009, "percentage": 24.93, "elapsed_time": "1:11:32", "remaining_time": "3:35:29", "throughput": 1320.51, "total_tokens": 5668368} {"current_steps": 9975, "total_steps": 40000, "loss": 0.0, "lr": 4.271373107133464e-05, "epoch": 175.0, "percentage": 24.94, "elapsed_time": "1:11:34", "remaining_time": "3:35:26", "throughput": 1320.43, "total_tokens": 5670672} {"current_steps": 9980, "total_steps": 40000, "loss": 0.0, "lr": 4.270680189136366e-05, "epoch": 175.08849557522123, "percentage": 24.95, "elapsed_time": "1:11:36", "remaining_time": "3:35:25", "throughput": 1320.38, "total_tokens": 5673520} {"current_steps": 9985, "total_steps": 40000, "loss": 0.0, "lr": 4.269986998078132e-05, "epoch": 175.1769911504425, "percentage": 24.96, "elapsed_time": "1:11:38", "remaining_time": "3:35:22", "throughput": 1320.43, "total_tokens": 5676432} {"current_steps": 9990, "total_steps": 40000, "loss": 0.0, "lr": 4.2692935340656595e-05, "epoch": 175.26548672566372, "percentage": 24.98, "elapsed_time": "1:11:40", "remaining_time": "3:35:20", "throughput": 1320.4, "total_tokens": 5679040} {"current_steps": 9995, "total_steps": 40000, "loss": 0.0, "lr": 4.26859979720589e-05, "epoch": 175.35398230088495, "percentage": 24.99, "elapsed_time": "1:11:43", "remaining_time": "3:35:17", "throughput": 1320.51, "total_tokens": 5682224} {"current_steps": 10000, "total_steps": 40000, "loss": 0.0, "lr": 4.267905787605806e-05, "epoch": 175.44247787610618, "percentage": 25.0, "elapsed_time": "1:11:45", "remaining_time": "3:35:15", "throughput": 1320.46, "total_tokens": 5684752} {"current_steps": 10000, "total_steps": 40000, "eval_loss": 0.44014638662338257, "epoch": 175.44247787610618, "percentage": 25.0, "elapsed_time": "1:11:46", "remaining_time": "3:35:18", "throughput": 1320.13, "total_tokens": 5684752} {"current_steps": 10005, "total_steps": 40000, "loss": 0.0, "lr": 4.267211505372433e-05, "epoch": 175.53097345132744, "percentage": 25.01, "elapsed_time": "1:11:50", "remaining_time": "3:35:22", "throughput": 1319.51, "total_tokens": 5687408} {"current_steps": 10010, "total_steps": 40000, "loss": 0.0, "lr": 4.266516950612837e-05, "epoch": 175.61946902654867, "percentage": 25.02, "elapsed_time": "1:11:52", "remaining_time": "3:35:19", "throughput": 1319.61, "total_tokens": 5690576} {"current_steps": 10015, "total_steps": 40000, "loss": 0.0, "lr": 4.265822123434128e-05, "epoch": 175.7079646017699, "percentage": 25.04, "elapsed_time": "1:11:54", "remaining_time": "3:35:17", "throughput": 1319.73, "total_tokens": 5693824} {"current_steps": 10020, "total_steps": 40000, "loss": 0.0, "lr": 4.265127023943457e-05, "epoch": 175.79646017699116, "percentage": 25.05, "elapsed_time": "1:11:56", "remaining_time": "3:35:14", "throughput": 1319.65, "total_tokens": 5696208} {"current_steps": 10025, "total_steps": 40000, "loss": 0.0, "lr": 4.2644316522480176e-05, "epoch": 175.8849557522124, "percentage": 25.06, "elapsed_time": "1:11:58", "remaining_time": "3:35:12", "throughput": 1319.67, "total_tokens": 5699024} {"current_steps": 10030, "total_steps": 40000, "loss": 0.0, "lr": 4.263736008455044e-05, "epoch": 175.97345132743362, "percentage": 25.07, "elapsed_time": "1:12:00", "remaining_time": "3:35:10", "throughput": 1319.82, "total_tokens": 5702400} {"current_steps": 10035, "total_steps": 40000, "loss": 0.0, "lr": 4.2630400926718125e-05, "epoch": 176.05309734513276, "percentage": 25.09, "elapsed_time": "1:12:02", "remaining_time": "3:35:08", "throughput": 1319.74, "total_tokens": 5705040} {"current_steps": 10040, "total_steps": 40000, "loss": 0.0, "lr": 4.262343905005644e-05, "epoch": 176.141592920354, "percentage": 25.1, "elapsed_time": "1:12:04", "remaining_time": "3:35:05", "throughput": 1319.76, "total_tokens": 5707824} {"current_steps": 10045, "total_steps": 40000, "loss": 0.0, "lr": 4.261647445563897e-05, "epoch": 176.23008849557522, "percentage": 25.11, "elapsed_time": "1:12:06", "remaining_time": "3:35:03", "throughput": 1319.84, "total_tokens": 5710928} {"current_steps": 10050, "total_steps": 40000, "loss": 0.0, "lr": 4.260950714453976e-05, "epoch": 176.31858407079645, "percentage": 25.12, "elapsed_time": "1:12:09", "remaining_time": "3:35:00", "throughput": 1319.92, "total_tokens": 5713984} {"current_steps": 10055, "total_steps": 40000, "loss": 0.0, "lr": 4.2602537117833266e-05, "epoch": 176.4070796460177, "percentage": 25.14, "elapsed_time": "1:12:11", "remaining_time": "3:34:58", "throughput": 1319.91, "total_tokens": 5716688} {"current_steps": 10060, "total_steps": 40000, "loss": 0.0, "lr": 4.259556437659433e-05, "epoch": 176.49557522123894, "percentage": 25.15, "elapsed_time": "1:12:13", "remaining_time": "3:34:56", "throughput": 1319.93, "total_tokens": 5719504} {"current_steps": 10065, "total_steps": 40000, "loss": 0.0, "lr": 4.258858892189825e-05, "epoch": 176.58407079646017, "percentage": 25.16, "elapsed_time": "1:12:15", "remaining_time": "3:34:53", "throughput": 1320.12, "total_tokens": 5723040} {"current_steps": 10070, "total_steps": 40000, "loss": 0.0, "lr": 4.2581610754820725e-05, "epoch": 176.67256637168143, "percentage": 25.17, "elapsed_time": "1:12:17", "remaining_time": "3:34:51", "throughput": 1320.25, "total_tokens": 5726336} {"current_steps": 10075, "total_steps": 40000, "loss": 0.0, "lr": 4.2574629876437876e-05, "epoch": 176.76106194690266, "percentage": 25.19, "elapsed_time": "1:12:19", "remaining_time": "3:34:48", "throughput": 1320.18, "total_tokens": 5728752} {"current_steps": 10080, "total_steps": 40000, "loss": 0.0, "lr": 4.256764628782625e-05, "epoch": 176.8495575221239, "percentage": 25.2, "elapsed_time": "1:12:21", "remaining_time": "3:34:46", "throughput": 1320.24, "total_tokens": 5731760} {"current_steps": 10085, "total_steps": 40000, "loss": 0.0, "lr": 4.256065999006279e-05, "epoch": 176.93805309734512, "percentage": 25.21, "elapsed_time": "1:12:23", "remaining_time": "3:34:44", "throughput": 1320.25, "total_tokens": 5734512} {"current_steps": 10090, "total_steps": 40000, "loss": 0.0, "lr": 4.2553670984224885e-05, "epoch": 177.01769911504425, "percentage": 25.22, "elapsed_time": "1:12:25", "remaining_time": "3:34:42", "throughput": 1320.04, "total_tokens": 5736544} {"current_steps": 10095, "total_steps": 40000, "loss": 0.0, "lr": 4.254667927139032e-05, "epoch": 177.10619469026548, "percentage": 25.24, "elapsed_time": "1:12:27", "remaining_time": "3:34:39", "throughput": 1320.03, "total_tokens": 5739264} {"current_steps": 10100, "total_steps": 40000, "loss": 0.0, "lr": 4.2539684852637295e-05, "epoch": 177.1946902654867, "percentage": 25.25, "elapsed_time": "1:12:29", "remaining_time": "3:34:37", "throughput": 1319.94, "total_tokens": 5741616} {"current_steps": 10105, "total_steps": 40000, "loss": 0.0, "lr": 4.253268772904446e-05, "epoch": 177.28318584070797, "percentage": 25.26, "elapsed_time": "1:12:31", "remaining_time": "3:34:35", "throughput": 1319.99, "total_tokens": 5744560} {"current_steps": 10110, "total_steps": 40000, "loss": 0.0, "lr": 4.252568790169085e-05, "epoch": 177.3716814159292, "percentage": 25.27, "elapsed_time": "1:12:34", "remaining_time": "3:34:32", "throughput": 1320.04, "total_tokens": 5747488} {"current_steps": 10115, "total_steps": 40000, "loss": 0.0, "lr": 4.251868537165592e-05, "epoch": 177.46017699115043, "percentage": 25.29, "elapsed_time": "1:12:36", "remaining_time": "3:34:30", "throughput": 1320.08, "total_tokens": 5750416} {"current_steps": 10120, "total_steps": 40000, "loss": 0.0, "lr": 4.251168014001955e-05, "epoch": 177.5486725663717, "percentage": 25.3, "elapsed_time": "1:12:38", "remaining_time": "3:34:27", "throughput": 1320.15, "total_tokens": 5753440} {"current_steps": 10125, "total_steps": 40000, "loss": 0.0, "lr": 4.250467220786204e-05, "epoch": 177.63716814159292, "percentage": 25.31, "elapsed_time": "1:12:40", "remaining_time": "3:34:25", "throughput": 1320.22, "total_tokens": 5756464} {"current_steps": 10130, "total_steps": 40000, "loss": 0.0, "lr": 4.249766157626409e-05, "epoch": 177.72566371681415, "percentage": 25.32, "elapsed_time": "1:12:42", "remaining_time": "3:34:23", "throughput": 1320.32, "total_tokens": 5759648} {"current_steps": 10135, "total_steps": 40000, "loss": 0.0, "lr": 4.249064824630684e-05, "epoch": 177.81415929203538, "percentage": 25.34, "elapsed_time": "1:12:44", "remaining_time": "3:34:20", "throughput": 1320.35, "total_tokens": 5762496} {"current_steps": 10140, "total_steps": 40000, "loss": 0.0, "lr": 4.248363221907183e-05, "epoch": 177.90265486725664, "percentage": 25.35, "elapsed_time": "1:12:46", "remaining_time": "3:34:18", "throughput": 1320.32, "total_tokens": 5765104} {"current_steps": 10145, "total_steps": 40000, "loss": 0.0, "lr": 4.2476613495641026e-05, "epoch": 177.99115044247787, "percentage": 25.36, "elapsed_time": "1:12:48", "remaining_time": "3:34:15", "throughput": 1320.37, "total_tokens": 5768032} {"current_steps": 10150, "total_steps": 40000, "loss": 0.0, "lr": 4.246959207709679e-05, "epoch": 178.07079646017698, "percentage": 25.37, "elapsed_time": "1:12:50", "remaining_time": "3:34:13", "throughput": 1320.27, "total_tokens": 5770576} {"current_steps": 10155, "total_steps": 40000, "loss": 0.0, "lr": 4.246256796452192e-05, "epoch": 178.15929203539824, "percentage": 25.39, "elapsed_time": "1:12:52", "remaining_time": "3:34:11", "throughput": 1320.25, "total_tokens": 5773232} {"current_steps": 10160, "total_steps": 40000, "loss": 0.0, "lr": 4.245554115899962e-05, "epoch": 178.24778761061947, "percentage": 25.4, "elapsed_time": "1:12:54", "remaining_time": "3:34:09", "throughput": 1320.32, "total_tokens": 5776272} {"current_steps": 10165, "total_steps": 40000, "loss": 0.0, "lr": 4.2448511661613514e-05, "epoch": 178.3362831858407, "percentage": 25.41, "elapsed_time": "1:12:56", "remaining_time": "3:34:06", "throughput": 1320.34, "total_tokens": 5779056} {"current_steps": 10170, "total_steps": 40000, "loss": 0.0, "lr": 4.2441479473447635e-05, "epoch": 178.42477876106196, "percentage": 25.42, "elapsed_time": "1:12:59", "remaining_time": "3:34:04", "throughput": 1320.43, "total_tokens": 5782176} {"current_steps": 10175, "total_steps": 40000, "loss": 0.0, "lr": 4.243444459558644e-05, "epoch": 178.5132743362832, "percentage": 25.44, "elapsed_time": "1:13:01", "remaining_time": "3:34:01", "throughput": 1320.37, "total_tokens": 5784656} {"current_steps": 10180, "total_steps": 40000, "loss": 0.0, "lr": 4.24274070291148e-05, "epoch": 178.60176991150442, "percentage": 25.45, "elapsed_time": "1:13:03", "remaining_time": "3:33:59", "throughput": 1320.39, "total_tokens": 5787488} {"current_steps": 10185, "total_steps": 40000, "loss": 0.0, "lr": 4.242036677511798e-05, "epoch": 178.69026548672565, "percentage": 25.46, "elapsed_time": "1:13:05", "remaining_time": "3:33:57", "throughput": 1320.45, "total_tokens": 5790464} {"current_steps": 10190, "total_steps": 40000, "loss": 0.0, "lr": 4.241332383468169e-05, "epoch": 178.7787610619469, "percentage": 25.47, "elapsed_time": "1:13:07", "remaining_time": "3:33:54", "throughput": 1320.54, "total_tokens": 5793568} {"current_steps": 10195, "total_steps": 40000, "loss": 0.0, "lr": 4.2406278208892034e-05, "epoch": 178.86725663716814, "percentage": 25.49, "elapsed_time": "1:13:09", "remaining_time": "3:33:52", "throughput": 1320.52, "total_tokens": 5796240} {"current_steps": 10200, "total_steps": 40000, "loss": 0.0, "lr": 4.2399229898835536e-05, "epoch": 178.95575221238937, "percentage": 25.5, "elapsed_time": "1:13:11", "remaining_time": "3:33:49", "throughput": 1320.56, "total_tokens": 5799088} {"current_steps": 10200, "total_steps": 40000, "eval_loss": 0.42910388112068176, "epoch": 178.95575221238937, "percentage": 25.5, "elapsed_time": "1:13:12", "remaining_time": "3:33:52", "throughput": 1320.24, "total_tokens": 5799088} {"current_steps": 10205, "total_steps": 40000, "loss": 0.0, "lr": 4.239217890559914e-05, "epoch": 179.0353982300885, "percentage": 25.51, "elapsed_time": "1:13:16", "remaining_time": "3:33:56", "throughput": 1319.56, "total_tokens": 5801504} {"current_steps": 10210, "total_steps": 40000, "loss": 0.0, "lr": 4.238512523027019e-05, "epoch": 179.12389380530973, "percentage": 25.52, "elapsed_time": "1:13:18", "remaining_time": "3:33:53", "throughput": 1319.67, "total_tokens": 5804720} {"current_steps": 10215, "total_steps": 40000, "loss": 0.0, "lr": 4.237806887393645e-05, "epoch": 179.21238938053096, "percentage": 25.54, "elapsed_time": "1:13:20", "remaining_time": "3:33:51", "throughput": 1319.75, "total_tokens": 5807760} {"current_steps": 10220, "total_steps": 40000, "loss": 0.0, "lr": 4.237100983768611e-05, "epoch": 179.30088495575222, "percentage": 25.55, "elapsed_time": "1:13:22", "remaining_time": "3:33:49", "throughput": 1319.73, "total_tokens": 5810400} {"current_steps": 10225, "total_steps": 40000, "loss": 0.0, "lr": 4.2363948122607756e-05, "epoch": 179.38938053097345, "percentage": 25.56, "elapsed_time": "1:13:24", "remaining_time": "3:33:46", "throughput": 1319.71, "total_tokens": 5813040} {"current_steps": 10230, "total_steps": 40000, "loss": 0.0, "lr": 4.235688372979039e-05, "epoch": 179.47787610619469, "percentage": 25.57, "elapsed_time": "1:13:26", "remaining_time": "3:33:44", "throughput": 1319.7, "total_tokens": 5815760} {"current_steps": 10235, "total_steps": 40000, "loss": 0.0, "lr": 4.234981666032343e-05, "epoch": 179.56637168141592, "percentage": 25.59, "elapsed_time": "1:13:28", "remaining_time": "3:33:41", "throughput": 1319.8, "total_tokens": 5818896} {"current_steps": 10240, "total_steps": 40000, "loss": 0.0, "lr": 4.2342746915296704e-05, "epoch": 179.65486725663717, "percentage": 25.6, "elapsed_time": "1:13:31", "remaining_time": "3:33:39", "throughput": 1319.82, "total_tokens": 5821712} {"current_steps": 10245, "total_steps": 40000, "loss": 0.0, "lr": 4.233567449580047e-05, "epoch": 179.7433628318584, "percentage": 25.61, "elapsed_time": "1:13:33", "remaining_time": "3:33:37", "throughput": 1319.91, "total_tokens": 5824880} {"current_steps": 10250, "total_steps": 40000, "loss": 0.0, "lr": 4.232859940292537e-05, "epoch": 179.83185840707964, "percentage": 25.62, "elapsed_time": "1:13:35", "remaining_time": "3:33:34", "throughput": 1319.8, "total_tokens": 5827120} {"current_steps": 10255, "total_steps": 40000, "loss": 0.0, "lr": 4.232152163776248e-05, "epoch": 179.9203539823009, "percentage": 25.64, "elapsed_time": "1:13:37", "remaining_time": "3:33:32", "throughput": 1319.77, "total_tokens": 5829744} {"current_steps": 10260, "total_steps": 40000, "loss": 0.0, "lr": 4.231444120140328e-05, "epoch": 180.0, "percentage": 25.65, "elapsed_time": "1:13:39", "remaining_time": "3:33:29", "throughput": 1319.82, "total_tokens": 5832608} {"current_steps": 10265, "total_steps": 40000, "loss": 0.0, "lr": 4.230735809493967e-05, "epoch": 180.08849557522123, "percentage": 25.66, "elapsed_time": "1:13:41", "remaining_time": "3:33:28", "throughput": 1319.75, "total_tokens": 5835344} {"current_steps": 10270, "total_steps": 40000, "loss": 0.0, "lr": 4.2300272319463926e-05, "epoch": 180.1769911504425, "percentage": 25.67, "elapsed_time": "1:13:43", "remaining_time": "3:33:25", "throughput": 1319.73, "total_tokens": 5838000} {"current_steps": 10275, "total_steps": 40000, "loss": 0.0, "lr": 4.2293183876068786e-05, "epoch": 180.26548672566372, "percentage": 25.69, "elapsed_time": "1:13:45", "remaining_time": "3:33:23", "throughput": 1319.89, "total_tokens": 5841456} {"current_steps": 10280, "total_steps": 40000, "loss": 0.0, "lr": 4.228609276584737e-05, "epoch": 180.35398230088495, "percentage": 25.7, "elapsed_time": "1:13:47", "remaining_time": "3:33:20", "throughput": 1320.02, "total_tokens": 5844736} {"current_steps": 10285, "total_steps": 40000, "loss": 0.0, "lr": 4.227899898989323e-05, "epoch": 180.44247787610618, "percentage": 25.71, "elapsed_time": "1:13:49", "remaining_time": "3:33:18", "throughput": 1320.06, "total_tokens": 5847664} {"current_steps": 10290, "total_steps": 40000, "loss": 0.0, "lr": 4.2271902549300293e-05, "epoch": 180.53097345132744, "percentage": 25.72, "elapsed_time": "1:13:51", "remaining_time": "3:33:16", "throughput": 1320.12, "total_tokens": 5850640} {"current_steps": 10295, "total_steps": 40000, "loss": 0.0, "lr": 4.226480344516294e-05, "epoch": 180.61946902654867, "percentage": 25.74, "elapsed_time": "1:13:53", "remaining_time": "3:33:13", "throughput": 1320.18, "total_tokens": 5853648} {"current_steps": 10300, "total_steps": 40000, "loss": 0.0, "lr": 4.2257701678575925e-05, "epoch": 180.7079646017699, "percentage": 25.75, "elapsed_time": "1:13:56", "remaining_time": "3:33:11", "throughput": 1320.17, "total_tokens": 5856320} {"current_steps": 10305, "total_steps": 40000, "loss": 0.0, "lr": 4.225059725063444e-05, "epoch": 180.79646017699116, "percentage": 25.76, "elapsed_time": "1:13:58", "remaining_time": "3:33:08", "throughput": 1320.27, "total_tokens": 5859488} {"current_steps": 10310, "total_steps": 40000, "loss": 0.0, "lr": 4.2243490162434074e-05, "epoch": 180.8849557522124, "percentage": 25.77, "elapsed_time": "1:14:00", "remaining_time": "3:33:06", "throughput": 1320.21, "total_tokens": 5862000} {"current_steps": 10315, "total_steps": 40000, "loss": 0.0, "lr": 4.223638041507083e-05, "epoch": 180.97345132743362, "percentage": 25.79, "elapsed_time": "1:14:02", "remaining_time": "3:33:04", "throughput": 1320.23, "total_tokens": 5864784} {"current_steps": 10320, "total_steps": 40000, "loss": 0.0, "lr": 4.2229268009641124e-05, "epoch": 181.05309734513276, "percentage": 25.8, "elapsed_time": "1:14:04", "remaining_time": "3:33:02", "throughput": 1320.1, "total_tokens": 5867224} {"current_steps": 10325, "total_steps": 40000, "loss": 0.0, "lr": 4.222215294724177e-05, "epoch": 181.141592920354, "percentage": 25.81, "elapsed_time": "1:14:06", "remaining_time": "3:32:59", "throughput": 1320.14, "total_tokens": 5870120} {"current_steps": 10330, "total_steps": 40000, "loss": 0.0, "lr": 4.2215035228970005e-05, "epoch": 181.23008849557522, "percentage": 25.82, "elapsed_time": "1:14:08", "remaining_time": "3:32:57", "throughput": 1320.21, "total_tokens": 5873176} {"current_steps": 10335, "total_steps": 40000, "loss": 0.0, "lr": 4.2207914855923464e-05, "epoch": 181.31858407079645, "percentage": 25.84, "elapsed_time": "1:14:10", "remaining_time": "3:32:55", "throughput": 1320.15, "total_tokens": 5875640} {"current_steps": 10340, "total_steps": 40000, "loss": 0.0, "lr": 4.220079182920021e-05, "epoch": 181.4070796460177, "percentage": 25.85, "elapsed_time": "1:14:12", "remaining_time": "3:32:52", "throughput": 1320.13, "total_tokens": 5878280} {"current_steps": 10345, "total_steps": 40000, "loss": 0.0, "lr": 4.2193666149898705e-05, "epoch": 181.49557522123894, "percentage": 25.86, "elapsed_time": "1:14:14", "remaining_time": "3:32:50", "throughput": 1320.13, "total_tokens": 5881016} {"current_steps": 10350, "total_steps": 40000, "loss": 0.0, "lr": 4.21865378191178e-05, "epoch": 181.58407079646017, "percentage": 25.87, "elapsed_time": "1:14:16", "remaining_time": "3:32:47", "throughput": 1320.22, "total_tokens": 5884168} {"current_steps": 10355, "total_steps": 40000, "loss": 0.0, "lr": 4.217940683795678e-05, "epoch": 181.67256637168143, "percentage": 25.89, "elapsed_time": "1:14:19", "remaining_time": "3:32:45", "throughput": 1320.18, "total_tokens": 5886712} {"current_steps": 10360, "total_steps": 40000, "loss": 0.0, "lr": 4.217227320751534e-05, "epoch": 181.76106194690266, "percentage": 25.9, "elapsed_time": "1:14:21", "remaining_time": "3:32:43", "throughput": 1320.21, "total_tokens": 5889544} {"current_steps": 10365, "total_steps": 40000, "loss": 0.0, "lr": 4.216513692889358e-05, "epoch": 181.8495575221239, "percentage": 25.91, "elapsed_time": "1:14:23", "remaining_time": "3:32:40", "throughput": 1320.24, "total_tokens": 5892392} {"current_steps": 10370, "total_steps": 40000, "loss": 0.0, "lr": 4.215799800319199e-05, "epoch": 181.93805309734512, "percentage": 25.92, "elapsed_time": "1:14:25", "remaining_time": "3:32:38", "throughput": 1320.35, "total_tokens": 5895608} {"current_steps": 10375, "total_steps": 40000, "loss": 0.0, "lr": 4.2150856431511485e-05, "epoch": 182.01769911504425, "percentage": 25.94, "elapsed_time": "1:14:27", "remaining_time": "3:32:36", "throughput": 1320.25, "total_tokens": 5898128} {"current_steps": 10380, "total_steps": 40000, "loss": 0.0, "lr": 4.214371221495339e-05, "epoch": 182.10619469026548, "percentage": 25.95, "elapsed_time": "1:14:29", "remaining_time": "3:32:34", "throughput": 1320.25, "total_tokens": 5900848} {"current_steps": 10385, "total_steps": 40000, "loss": 0.0, "lr": 4.213656535461942e-05, "epoch": 182.1946902654867, "percentage": 25.96, "elapsed_time": "1:14:31", "remaining_time": "3:32:31", "throughput": 1320.22, "total_tokens": 5903488} {"current_steps": 10390, "total_steps": 40000, "loss": 0.0, "lr": 4.2129415851611734e-05, "epoch": 182.28318584070797, "percentage": 25.97, "elapsed_time": "1:14:33", "remaining_time": "3:32:29", "throughput": 1320.19, "total_tokens": 5906112} {"current_steps": 10395, "total_steps": 40000, "loss": 0.0, "lr": 4.2122263707032855e-05, "epoch": 182.3716814159292, "percentage": 25.99, "elapsed_time": "1:14:35", "remaining_time": "3:32:26", "throughput": 1320.24, "total_tokens": 5909056} {"current_steps": 10400, "total_steps": 40000, "loss": 0.0, "lr": 4.211510892198574e-05, "epoch": 182.46017699115043, "percentage": 26.0, "elapsed_time": "1:14:37", "remaining_time": "3:32:24", "throughput": 1320.26, "total_tokens": 5911888} {"current_steps": 10400, "total_steps": 40000, "eval_loss": 0.4353715777397156, "epoch": 182.46017699115043, "percentage": 26.0, "elapsed_time": "1:14:38", "remaining_time": "3:32:27", "throughput": 1319.95, "total_tokens": 5911888} {"current_steps": 10405, "total_steps": 40000, "loss": 0.0, "lr": 4.210795149757375e-05, "epoch": 182.5486725663717, "percentage": 26.01, "elapsed_time": "1:14:42", "remaining_time": "3:32:30", "throughput": 1319.51, "total_tokens": 5914992} {"current_steps": 10410, "total_steps": 40000, "loss": 0.0, "lr": 4.210079143490065e-05, "epoch": 182.63716814159292, "percentage": 26.02, "elapsed_time": "1:14:44", "remaining_time": "3:32:27", "throughput": 1319.58, "total_tokens": 5918080} {"current_steps": 10415, "total_steps": 40000, "loss": 0.0, "lr": 4.2093628735070604e-05, "epoch": 182.72566371681415, "percentage": 26.04, "elapsed_time": "1:14:46", "remaining_time": "3:32:25", "throughput": 1319.55, "total_tokens": 5920704} {"current_steps": 10420, "total_steps": 40000, "loss": 0.0, "lr": 4.208646339918819e-05, "epoch": 182.81415929203538, "percentage": 26.05, "elapsed_time": "1:14:48", "remaining_time": "3:32:23", "throughput": 1319.61, "total_tokens": 5923680} {"current_steps": 10425, "total_steps": 40000, "loss": 0.0, "lr": 4.2079295428358414e-05, "epoch": 182.90265486725664, "percentage": 26.06, "elapsed_time": "1:14:51", "remaining_time": "3:32:20", "throughput": 1319.69, "total_tokens": 5926752} {"current_steps": 10430, "total_steps": 40000, "loss": 0.0, "lr": 4.207212482368664e-05, "epoch": 182.99115044247787, "percentage": 26.07, "elapsed_time": "1:14:53", "remaining_time": "3:32:18", "throughput": 1319.7, "total_tokens": 5929520} {"current_steps": 10435, "total_steps": 40000, "loss": 0.0, "lr": 4.206495158627867e-05, "epoch": 183.07079646017698, "percentage": 26.09, "elapsed_time": "1:14:55", "remaining_time": "3:32:16", "throughput": 1319.6, "total_tokens": 5932064} {"current_steps": 10440, "total_steps": 40000, "loss": 0.0, "lr": 4.205777571724073e-05, "epoch": 183.15929203539824, "percentage": 26.1, "elapsed_time": "1:14:57", "remaining_time": "3:32:14", "throughput": 1319.72, "total_tokens": 5935312} {"current_steps": 10445, "total_steps": 40000, "loss": 0.0, "lr": 4.20505972176794e-05, "epoch": 183.24778761061947, "percentage": 26.11, "elapsed_time": "1:14:59", "remaining_time": "3:32:11", "throughput": 1319.73, "total_tokens": 5938096} {"current_steps": 10450, "total_steps": 40000, "loss": 0.0, "lr": 4.204341608870171e-05, "epoch": 183.3362831858407, "percentage": 26.12, "elapsed_time": "1:15:01", "remaining_time": "3:32:09", "throughput": 1319.85, "total_tokens": 5941376} {"current_steps": 10455, "total_steps": 40000, "loss": 0.0, "lr": 4.203623233141508e-05, "epoch": 183.42477876106196, "percentage": 26.14, "elapsed_time": "1:15:03", "remaining_time": "3:32:06", "throughput": 1319.91, "total_tokens": 5944368} {"current_steps": 10460, "total_steps": 40000, "loss": 0.0, "lr": 4.2029045946927334e-05, "epoch": 183.5132743362832, "percentage": 26.15, "elapsed_time": "1:15:05", "remaining_time": "3:32:04", "throughput": 1319.85, "total_tokens": 5946816} {"current_steps": 10465, "total_steps": 40000, "loss": 0.0, "lr": 4.20218569363467e-05, "epoch": 183.60176991150442, "percentage": 26.16, "elapsed_time": "1:15:07", "remaining_time": "3:32:02", "throughput": 1319.83, "total_tokens": 5949456} {"current_steps": 10470, "total_steps": 40000, "loss": 0.0, "lr": 4.2014665300781834e-05, "epoch": 183.69026548672565, "percentage": 26.17, "elapsed_time": "1:15:09", "remaining_time": "3:31:59", "throughput": 1319.91, "total_tokens": 5952544} {"current_steps": 10475, "total_steps": 40000, "loss": 0.0, "lr": 4.200747104134174e-05, "epoch": 183.7787610619469, "percentage": 26.19, "elapsed_time": "1:15:12", "remaining_time": "3:31:58", "throughput": 1319.87, "total_tokens": 5955488} {"current_steps": 10480, "total_steps": 40000, "loss": 0.0, "lr": 4.200027415913588e-05, "epoch": 183.86725663716814, "percentage": 26.2, "elapsed_time": "1:15:14", "remaining_time": "3:31:55", "throughput": 1319.85, "total_tokens": 5958112} {"current_steps": 10485, "total_steps": 40000, "loss": 0.0, "lr": 4.1993074655274126e-05, "epoch": 183.95575221238937, "percentage": 26.21, "elapsed_time": "1:15:16", "remaining_time": "3:31:53", "throughput": 1319.82, "total_tokens": 5960688} {"current_steps": 10490, "total_steps": 40000, "loss": 0.0, "lr": 4.198587253086669e-05, "epoch": 184.0353982300885, "percentage": 26.22, "elapsed_time": "1:15:18", "remaining_time": "3:31:51", "throughput": 1319.69, "total_tokens": 5963120} {"current_steps": 10495, "total_steps": 40000, "loss": 0.0, "lr": 4.197866778702426e-05, "epoch": 184.12389380530973, "percentage": 26.24, "elapsed_time": "1:15:20", "remaining_time": "3:31:49", "throughput": 1319.7, "total_tokens": 5965872} {"current_steps": 10500, "total_steps": 40000, "loss": 0.0, "lr": 4.197146042485789e-05, "epoch": 184.21238938053096, "percentage": 26.25, "elapsed_time": "1:15:22", "remaining_time": "3:31:46", "throughput": 1319.68, "total_tokens": 5968512} {"current_steps": 10505, "total_steps": 40000, "loss": 0.0, "lr": 4.1964250445479046e-05, "epoch": 184.30088495575222, "percentage": 26.26, "elapsed_time": "1:15:24", "remaining_time": "3:31:44", "throughput": 1319.86, "total_tokens": 5972032} {"current_steps": 10510, "total_steps": 40000, "loss": 0.0, "lr": 4.19570378499996e-05, "epoch": 184.38938053097345, "percentage": 26.27, "elapsed_time": "1:15:26", "remaining_time": "3:31:41", "throughput": 1319.96, "total_tokens": 5975248} {"current_steps": 10515, "total_steps": 40000, "loss": 0.0, "lr": 4.194982263953182e-05, "epoch": 184.47787610619469, "percentage": 26.29, "elapsed_time": "1:15:28", "remaining_time": "3:31:39", "throughput": 1319.96, "total_tokens": 5977968} {"current_steps": 10520, "total_steps": 40000, "loss": 0.0, "lr": 4.194260481518838e-05, "epoch": 184.56637168141592, "percentage": 26.3, "elapsed_time": "1:15:30", "remaining_time": "3:31:37", "throughput": 1319.95, "total_tokens": 5980656} {"current_steps": 10525, "total_steps": 40000, "loss": 0.0, "lr": 4.1935384378082366e-05, "epoch": 184.65486725663717, "percentage": 26.31, "elapsed_time": "1:15:33", "remaining_time": "3:31:34", "throughput": 1319.96, "total_tokens": 5983440} {"current_steps": 10530, "total_steps": 40000, "loss": 0.0, "lr": 4.1928161329327267e-05, "epoch": 184.7433628318584, "percentage": 26.32, "elapsed_time": "1:15:35", "remaining_time": "3:31:32", "throughput": 1319.94, "total_tokens": 5986064} {"current_steps": 10535, "total_steps": 40000, "loss": 0.0, "lr": 4.1920935670036945e-05, "epoch": 184.83185840707964, "percentage": 26.34, "elapsed_time": "1:15:37", "remaining_time": "3:31:29", "throughput": 1319.91, "total_tokens": 5988640} {"current_steps": 10540, "total_steps": 40000, "loss": 0.0, "lr": 4.1913707401325705e-05, "epoch": 184.9203539823009, "percentage": 26.35, "elapsed_time": "1:15:39", "remaining_time": "3:31:27", "throughput": 1319.86, "total_tokens": 5991168} {"current_steps": 10545, "total_steps": 40000, "loss": 0.0, "lr": 4.1906476524308235e-05, "epoch": 185.0, "percentage": 26.36, "elapsed_time": "1:15:41", "remaining_time": "3:31:24", "throughput": 1319.89, "total_tokens": 5993944} {"current_steps": 10550, "total_steps": 40000, "loss": 0.0, "lr": 4.189924304009962e-05, "epoch": 185.08849557522123, "percentage": 26.38, "elapsed_time": "1:15:43", "remaining_time": "3:31:23", "throughput": 1319.87, "total_tokens": 5996888} {"current_steps": 10555, "total_steps": 40000, "loss": 0.0, "lr": 4.189200694981537e-05, "epoch": 185.1769911504425, "percentage": 26.39, "elapsed_time": "1:15:45", "remaining_time": "3:31:20", "throughput": 1319.98, "total_tokens": 6000120} {"current_steps": 10560, "total_steps": 40000, "loss": 0.0, "lr": 4.188476825457136e-05, "epoch": 185.26548672566372, "percentage": 26.4, "elapsed_time": "1:15:47", "remaining_time": "3:31:18", "throughput": 1320.04, "total_tokens": 6003112} {"current_steps": 10565, "total_steps": 40000, "loss": 0.0, "lr": 4.18775269554839e-05, "epoch": 185.35398230088495, "percentage": 26.41, "elapsed_time": "1:15:49", "remaining_time": "3:31:16", "throughput": 1320.01, "total_tokens": 6005704} {"current_steps": 10570, "total_steps": 40000, "loss": 0.0, "lr": 4.187028305366969e-05, "epoch": 185.44247787610618, "percentage": 26.42, "elapsed_time": "1:15:51", "remaining_time": "3:31:13", "throughput": 1320.04, "total_tokens": 6008600} {"current_steps": 10575, "total_steps": 40000, "loss": 0.0, "lr": 4.1863036550245824e-05, "epoch": 185.53097345132744, "percentage": 26.44, "elapsed_time": "1:15:53", "remaining_time": "3:31:11", "throughput": 1320.08, "total_tokens": 6011480} {"current_steps": 10580, "total_steps": 40000, "loss": 0.0, "lr": 4.1855787446329806e-05, "epoch": 185.61946902654867, "percentage": 26.45, "elapsed_time": "1:15:55", "remaining_time": "3:31:08", "throughput": 1320.12, "total_tokens": 6014408} {"current_steps": 10585, "total_steps": 40000, "loss": 0.0, "lr": 4.184853574303955e-05, "epoch": 185.7079646017699, "percentage": 26.46, "elapsed_time": "1:15:58", "remaining_time": "3:31:06", "throughput": 1320.13, "total_tokens": 6017176} {"current_steps": 10590, "total_steps": 40000, "loss": 0.0, "lr": 4.184128144149334e-05, "epoch": 185.79646017699116, "percentage": 26.47, "elapsed_time": "1:16:00", "remaining_time": "3:31:04", "throughput": 1320.1, "total_tokens": 6019752} {"current_steps": 10595, "total_steps": 40000, "loss": 0.0, "lr": 4.1834024542809896e-05, "epoch": 185.8849557522124, "percentage": 26.49, "elapsed_time": "1:16:02", "remaining_time": "3:31:01", "throughput": 1320.15, "total_tokens": 6022696} {"current_steps": 10600, "total_steps": 40000, "loss": 0.0, "lr": 4.1826765048108315e-05, "epoch": 185.97345132743362, "percentage": 26.5, "elapsed_time": "1:16:04", "remaining_time": "3:30:59", "throughput": 1320.18, "total_tokens": 6025544} {"current_steps": 10600, "total_steps": 40000, "eval_loss": 0.44329676032066345, "epoch": 185.97345132743362, "percentage": 26.5, "elapsed_time": "1:16:05", "remaining_time": "3:31:02", "throughput": 1319.87, "total_tokens": 6025544} {"current_steps": 10605, "total_steps": 40000, "loss": 0.0, "lr": 4.181950295850811e-05, "epoch": 186.05309734513276, "percentage": 26.51, "elapsed_time": "1:16:09", "remaining_time": "3:31:05", "throughput": 1319.11, "total_tokens": 6027568} {"current_steps": 10610, "total_steps": 40000, "loss": 0.0, "lr": 4.181223827512918e-05, "epoch": 186.141592920354, "percentage": 26.52, "elapsed_time": "1:16:11", "remaining_time": "3:31:03", "throughput": 1319.15, "total_tokens": 6030480} {"current_steps": 10615, "total_steps": 40000, "loss": 0.0, "lr": 4.180497099909183e-05, "epoch": 186.23008849557522, "percentage": 26.54, "elapsed_time": "1:16:13", "remaining_time": "3:31:00", "throughput": 1319.2, "total_tokens": 6033408} {"current_steps": 10620, "total_steps": 40000, "loss": 0.0, "lr": 4.179770113151677e-05, "epoch": 186.31858407079645, "percentage": 26.55, "elapsed_time": "1:16:15", "remaining_time": "3:30:58", "throughput": 1319.21, "total_tokens": 6036192} {"current_steps": 10625, "total_steps": 40000, "loss": 0.0, "lr": 4.179042867352511e-05, "epoch": 186.4070796460177, "percentage": 26.56, "elapsed_time": "1:16:17", "remaining_time": "3:30:55", "throughput": 1319.2, "total_tokens": 6038880} {"current_steps": 10630, "total_steps": 40000, "loss": 0.0, "lr": 4.1783153626238334e-05, "epoch": 186.49557522123894, "percentage": 26.57, "elapsed_time": "1:16:19", "remaining_time": "3:30:53", "throughput": 1319.25, "total_tokens": 6041856} {"current_steps": 10635, "total_steps": 40000, "loss": 0.0, "lr": 4.177587599077836e-05, "epoch": 186.58407079646017, "percentage": 26.59, "elapsed_time": "1:16:21", "remaining_time": "3:30:51", "throughput": 1319.29, "total_tokens": 6044752} {"current_steps": 10640, "total_steps": 40000, "loss": 0.0, "lr": 4.1768595768267494e-05, "epoch": 186.67256637168143, "percentage": 26.6, "elapsed_time": "1:16:23", "remaining_time": "3:30:48", "throughput": 1319.32, "total_tokens": 6047632} {"current_steps": 10645, "total_steps": 40000, "loss": 0.0, "lr": 4.176131295982843e-05, "epoch": 186.76106194690266, "percentage": 26.61, "elapsed_time": "1:16:25", "remaining_time": "3:30:46", "throughput": 1319.35, "total_tokens": 6050464} {"current_steps": 10650, "total_steps": 40000, "loss": 0.0, "lr": 4.1754027566584276e-05, "epoch": 186.8495575221239, "percentage": 26.62, "elapsed_time": "1:16:28", "remaining_time": "3:30:43", "throughput": 1319.52, "total_tokens": 6053968} {"current_steps": 10655, "total_steps": 40000, "loss": 0.0, "lr": 4.174673958965852e-05, "epoch": 186.93805309734512, "percentage": 26.64, "elapsed_time": "1:16:30", "remaining_time": "3:30:41", "throughput": 1319.55, "total_tokens": 6056832} {"current_steps": 10660, "total_steps": 40000, "loss": 0.0, "lr": 4.173944903017507e-05, "epoch": 187.01769911504425, "percentage": 26.65, "elapsed_time": "1:16:32", "remaining_time": "3:30:39", "throughput": 1319.47, "total_tokens": 6059416} {"current_steps": 10665, "total_steps": 40000, "loss": 0.0, "lr": 4.173215588925822e-05, "epoch": 187.10619469026548, "percentage": 26.66, "elapsed_time": "1:16:34", "remaining_time": "3:30:37", "throughput": 1319.39, "total_tokens": 6061800} {"current_steps": 10670, "total_steps": 40000, "loss": 0.0, "lr": 4.172486016803266e-05, "epoch": 187.1946902654867, "percentage": 26.67, "elapsed_time": "1:16:36", "remaining_time": "3:30:34", "throughput": 1319.55, "total_tokens": 6065224} {"current_steps": 10675, "total_steps": 40000, "loss": 0.0, "lr": 4.171756186762349e-05, "epoch": 187.28318584070797, "percentage": 26.69, "elapsed_time": "1:16:38", "remaining_time": "3:30:32", "throughput": 1319.6, "total_tokens": 6068200} {"current_steps": 10680, "total_steps": 40000, "loss": 0.0, "lr": 4.171026098915619e-05, "epoch": 187.3716814159292, "percentage": 26.7, "elapsed_time": "1:16:40", "remaining_time": "3:30:30", "throughput": 1319.64, "total_tokens": 6071112} {"current_steps": 10685, "total_steps": 40000, "loss": 0.0, "lr": 4.170295753375665e-05, "epoch": 187.46017699115043, "percentage": 26.71, "elapsed_time": "1:16:42", "remaining_time": "3:30:27", "throughput": 1319.69, "total_tokens": 6074088} {"current_steps": 10690, "total_steps": 40000, "loss": 0.0, "lr": 4.169565150255117e-05, "epoch": 187.5486725663717, "percentage": 26.72, "elapsed_time": "1:16:44", "remaining_time": "3:30:25", "throughput": 1319.63, "total_tokens": 6076520} {"current_steps": 10695, "total_steps": 40000, "loss": 0.0, "lr": 4.16883428966664e-05, "epoch": 187.63716814159292, "percentage": 26.74, "elapsed_time": "1:16:46", "remaining_time": "3:30:22", "throughput": 1319.68, "total_tokens": 6079496} {"current_steps": 10700, "total_steps": 40000, "loss": 0.0, "lr": 4.168103171722944e-05, "epoch": 187.72566371681415, "percentage": 26.75, "elapsed_time": "1:16:48", "remaining_time": "3:30:20", "throughput": 1319.67, "total_tokens": 6082168} {"current_steps": 10705, "total_steps": 40000, "loss": 0.0, "lr": 4.167371796536777e-05, "epoch": 187.81415929203538, "percentage": 26.76, "elapsed_time": "1:16:50", "remaining_time": "3:30:18", "throughput": 1319.72, "total_tokens": 6085144} {"current_steps": 10710, "total_steps": 40000, "loss": 0.0, "lr": 4.166640164220924e-05, "epoch": 187.90265486725664, "percentage": 26.77, "elapsed_time": "1:16:52", "remaining_time": "3:30:15", "throughput": 1319.83, "total_tokens": 6088328} {"current_steps": 10715, "total_steps": 40000, "loss": 0.0, "lr": 4.1659082748882144e-05, "epoch": 187.99115044247787, "percentage": 26.79, "elapsed_time": "1:16:55", "remaining_time": "3:30:13", "throughput": 1319.82, "total_tokens": 6090984} {"current_steps": 10720, "total_steps": 40000, "loss": 0.0, "lr": 4.1651761286515135e-05, "epoch": 188.07079646017698, "percentage": 26.8, "elapsed_time": "1:16:57", "remaining_time": "3:30:11", "throughput": 1319.71, "total_tokens": 6093456} {"current_steps": 10725, "total_steps": 40000, "loss": 0.0, "lr": 4.164443725623728e-05, "epoch": 188.15929203539824, "percentage": 26.81, "elapsed_time": "1:16:59", "remaining_time": "3:30:08", "throughput": 1319.88, "total_tokens": 6096960} {"current_steps": 10730, "total_steps": 40000, "loss": 0.0, "lr": 4.163711065917802e-05, "epoch": 188.24778761061947, "percentage": 26.82, "elapsed_time": "1:17:01", "remaining_time": "3:30:06", "throughput": 1319.85, "total_tokens": 6099568} {"current_steps": 10735, "total_steps": 40000, "loss": 0.0, "lr": 4.1629781496467234e-05, "epoch": 188.3362831858407, "percentage": 26.84, "elapsed_time": "1:17:03", "remaining_time": "3:30:04", "throughput": 1319.85, "total_tokens": 6102288} {"current_steps": 10740, "total_steps": 40000, "loss": 0.0, "lr": 4.1622449769235164e-05, "epoch": 188.42477876106196, "percentage": 26.85, "elapsed_time": "1:17:05", "remaining_time": "3:30:01", "throughput": 1320.04, "total_tokens": 6105888} {"current_steps": 10745, "total_steps": 40000, "loss": 0.0, "lr": 4.161511547861243e-05, "epoch": 188.5132743362832, "percentage": 26.86, "elapsed_time": "1:17:07", "remaining_time": "3:29:59", "throughput": 1320.1, "total_tokens": 6108912} {"current_steps": 10750, "total_steps": 40000, "loss": 0.0, "lr": 4.1607778625730104e-05, "epoch": 188.60176991150442, "percentage": 26.88, "elapsed_time": "1:17:09", "remaining_time": "3:29:56", "throughput": 1320.13, "total_tokens": 6111760} {"current_steps": 10755, "total_steps": 40000, "loss": 0.0, "lr": 4.160043921171961e-05, "epoch": 188.69026548672565, "percentage": 26.89, "elapsed_time": "1:17:11", "remaining_time": "3:29:54", "throughput": 1320.19, "total_tokens": 6114768} {"current_steps": 10760, "total_steps": 40000, "loss": 0.0, "lr": 4.159309723771276e-05, "epoch": 188.7787610619469, "percentage": 26.9, "elapsed_time": "1:17:13", "remaining_time": "3:29:52", "throughput": 1320.09, "total_tokens": 6116992} {"current_steps": 10765, "total_steps": 40000, "loss": 0.0, "lr": 4.158575270484181e-05, "epoch": 188.86725663716814, "percentage": 26.91, "elapsed_time": "1:17:15", "remaining_time": "3:29:49", "throughput": 1320.03, "total_tokens": 6119472} {"current_steps": 10770, "total_steps": 40000, "loss": 0.0, "lr": 4.157840561423936e-05, "epoch": 188.95575221238937, "percentage": 26.92, "elapsed_time": "1:17:17", "remaining_time": "3:29:47", "throughput": 1320.1, "total_tokens": 6122544} {"current_steps": 10775, "total_steps": 40000, "loss": 0.0, "lr": 4.1571055967038416e-05, "epoch": 189.0353982300885, "percentage": 26.94, "elapsed_time": "1:17:20", "remaining_time": "3:29:45", "throughput": 1320.0, "total_tokens": 6125072} {"current_steps": 10780, "total_steps": 40000, "loss": 0.0, "lr": 4.156370376437241e-05, "epoch": 189.12389380530973, "percentage": 26.95, "elapsed_time": "1:17:22", "remaining_time": "3:29:43", "throughput": 1320.07, "total_tokens": 6128112} {"current_steps": 10785, "total_steps": 40000, "loss": 0.0, "lr": 4.155634900737513e-05, "epoch": 189.21238938053096, "percentage": 26.96, "elapsed_time": "1:17:24", "remaining_time": "3:29:40", "throughput": 1320.07, "total_tokens": 6130800} {"current_steps": 10790, "total_steps": 40000, "loss": 0.0, "lr": 4.1548991697180764e-05, "epoch": 189.30088495575222, "percentage": 26.97, "elapsed_time": "1:17:26", "remaining_time": "3:29:38", "throughput": 1320.05, "total_tokens": 6133456} {"current_steps": 10795, "total_steps": 40000, "loss": 0.0, "lr": 4.1541631834923914e-05, "epoch": 189.38938053097345, "percentage": 26.99, "elapsed_time": "1:17:28", "remaining_time": "3:29:35", "throughput": 1320.1, "total_tokens": 6136384} {"current_steps": 10800, "total_steps": 40000, "loss": 0.0, "lr": 4.153426942173956e-05, "epoch": 189.47787610619469, "percentage": 27.0, "elapsed_time": "1:17:30", "remaining_time": "3:29:33", "throughput": 1320.13, "total_tokens": 6139264} {"current_steps": 10800, "total_steps": 40000, "eval_loss": 0.4492727816104889, "epoch": 189.47787610619469, "percentage": 27.0, "elapsed_time": "1:17:31", "remaining_time": "3:29:36", "throughput": 1319.83, "total_tokens": 6139264} {"current_steps": 10805, "total_steps": 40000, "loss": 0.0, "lr": 4.152690445876308e-05, "epoch": 189.56637168141592, "percentage": 27.01, "elapsed_time": "1:17:35", "remaining_time": "3:29:38", "throughput": 1319.37, "total_tokens": 6142000} {"current_steps": 10810, "total_steps": 40000, "loss": 0.0, "lr": 4.1519536947130245e-05, "epoch": 189.65486725663717, "percentage": 27.02, "elapsed_time": "1:17:37", "remaining_time": "3:29:36", "throughput": 1319.39, "total_tokens": 6144832} {"current_steps": 10815, "total_steps": 40000, "loss": 0.0, "lr": 4.151216688797722e-05, "epoch": 189.7433628318584, "percentage": 27.04, "elapsed_time": "1:17:39", "remaining_time": "3:29:33", "throughput": 1319.37, "total_tokens": 6147456} {"current_steps": 10820, "total_steps": 40000, "loss": 0.0, "lr": 4.150479428244054e-05, "epoch": 189.83185840707964, "percentage": 27.05, "elapsed_time": "1:17:41", "remaining_time": "3:29:31", "throughput": 1319.51, "total_tokens": 6150800} {"current_steps": 10825, "total_steps": 40000, "loss": 0.0, "lr": 4.1497419131657176e-05, "epoch": 189.9203539823009, "percentage": 27.06, "elapsed_time": "1:17:43", "remaining_time": "3:29:28", "throughput": 1319.67, "total_tokens": 6154256} {"current_steps": 10830, "total_steps": 40000, "loss": 0.0, "lr": 4.149004143676447e-05, "epoch": 190.0, "percentage": 27.07, "elapsed_time": "1:17:45", "remaining_time": "3:29:26", "throughput": 1319.58, "total_tokens": 6156512} {"current_steps": 10835, "total_steps": 40000, "loss": 0.0, "lr": 4.148266119890015e-05, "epoch": 190.08849557522123, "percentage": 27.09, "elapsed_time": "1:17:47", "remaining_time": "3:29:24", "throughput": 1319.65, "total_tokens": 6159904} {"current_steps": 10840, "total_steps": 40000, "loss": 0.0, "lr": 4.1475278419202324e-05, "epoch": 190.1769911504425, "percentage": 27.1, "elapsed_time": "1:17:49", "remaining_time": "3:29:22", "throughput": 1319.72, "total_tokens": 6162944} {"current_steps": 10845, "total_steps": 40000, "loss": 0.0, "lr": 4.146789309880953e-05, "epoch": 190.26548672566372, "percentage": 27.11, "elapsed_time": "1:17:51", "remaining_time": "3:29:19", "throughput": 1319.72, "total_tokens": 6165680} {"current_steps": 10850, "total_steps": 40000, "loss": 0.0, "lr": 4.146050523886068e-05, "epoch": 190.35398230088495, "percentage": 27.12, "elapsed_time": "1:17:54", "remaining_time": "3:29:17", "throughput": 1319.73, "total_tokens": 6168448} {"current_steps": 10855, "total_steps": 40000, "loss": 0.0, "lr": 4.1453114840495055e-05, "epoch": 190.44247787610618, "percentage": 27.14, "elapsed_time": "1:17:56", "remaining_time": "3:29:15", "throughput": 1319.72, "total_tokens": 6171136} {"current_steps": 10860, "total_steps": 40000, "loss": 0.0, "lr": 4.1445721904852364e-05, "epoch": 190.53097345132744, "percentage": 27.15, "elapsed_time": "1:17:58", "remaining_time": "3:29:12", "throughput": 1319.69, "total_tokens": 6173744} {"current_steps": 10865, "total_steps": 40000, "loss": 0.0, "lr": 4.143832643307269e-05, "epoch": 190.61946902654867, "percentage": 27.16, "elapsed_time": "1:18:00", "remaining_time": "3:29:10", "throughput": 1319.68, "total_tokens": 6176416} {"current_steps": 10870, "total_steps": 40000, "loss": 0.0, "lr": 4.1430928426296503e-05, "epoch": 190.7079646017699, "percentage": 27.18, "elapsed_time": "1:18:02", "remaining_time": "3:29:07", "throughput": 1319.72, "total_tokens": 6179328} {"current_steps": 10875, "total_steps": 40000, "loss": 0.0, "lr": 4.142352788566466e-05, "epoch": 190.79646017699116, "percentage": 27.19, "elapsed_time": "1:18:04", "remaining_time": "3:29:05", "throughput": 1319.8, "total_tokens": 6182416} {"current_steps": 10880, "total_steps": 40000, "loss": 0.0, "lr": 4.1416124812318424e-05, "epoch": 190.8849557522124, "percentage": 27.2, "elapsed_time": "1:18:06", "remaining_time": "3:29:03", "throughput": 1319.79, "total_tokens": 6185072} {"current_steps": 10885, "total_steps": 40000, "loss": 0.0, "lr": 4.1408719207399453e-05, "epoch": 190.97345132743362, "percentage": 27.21, "elapsed_time": "1:18:08", "remaining_time": "3:29:00", "throughput": 1319.81, "total_tokens": 6187904} {"current_steps": 10890, "total_steps": 40000, "loss": 0.0, "lr": 4.140131107204978e-05, "epoch": 191.05309734513276, "percentage": 27.22, "elapsed_time": "1:18:10", "remaining_time": "3:28:58", "throughput": 1319.64, "total_tokens": 6190096} {"current_steps": 10895, "total_steps": 40000, "loss": 0.0, "lr": 4.139390040741182e-05, "epoch": 191.141592920354, "percentage": 27.24, "elapsed_time": "1:18:12", "remaining_time": "3:28:56", "throughput": 1319.69, "total_tokens": 6193072} {"current_steps": 10900, "total_steps": 40000, "loss": 0.0, "lr": 4.1386487214628396e-05, "epoch": 191.23008849557522, "percentage": 27.25, "elapsed_time": "1:18:14", "remaining_time": "3:28:54", "throughput": 1319.66, "total_tokens": 6195648} {"current_steps": 10905, "total_steps": 40000, "loss": 0.0, "lr": 4.137907149484272e-05, "epoch": 191.31858407079645, "percentage": 27.26, "elapsed_time": "1:18:16", "remaining_time": "3:28:51", "throughput": 1319.77, "total_tokens": 6198896} {"current_steps": 10910, "total_steps": 40000, "loss": 0.0, "lr": 4.137165324919839e-05, "epoch": 191.4070796460177, "percentage": 27.27, "elapsed_time": "1:18:19", "remaining_time": "3:28:49", "throughput": 1319.74, "total_tokens": 6201488} {"current_steps": 10915, "total_steps": 40000, "loss": 0.0, "lr": 4.136423247883939e-05, "epoch": 191.49557522123894, "percentage": 27.29, "elapsed_time": "1:18:21", "remaining_time": "3:28:46", "throughput": 1319.85, "total_tokens": 6204720} {"current_steps": 10920, "total_steps": 40000, "loss": 0.0, "lr": 4.135680918491009e-05, "epoch": 191.58407079646017, "percentage": 27.3, "elapsed_time": "1:18:23", "remaining_time": "3:28:44", "throughput": 1319.79, "total_tokens": 6207168} {"current_steps": 10925, "total_steps": 40000, "loss": 0.0, "lr": 4.1349383368555265e-05, "epoch": 191.67256637168143, "percentage": 27.31, "elapsed_time": "1:18:25", "remaining_time": "3:28:42", "throughput": 1319.82, "total_tokens": 6210000} {"current_steps": 10930, "total_steps": 40000, "loss": 0.0, "lr": 4.1341955030920065e-05, "epoch": 191.76106194690266, "percentage": 27.32, "elapsed_time": "1:18:27", "remaining_time": "3:28:39", "throughput": 1319.81, "total_tokens": 6212704} {"current_steps": 10935, "total_steps": 40000, "loss": 0.0, "lr": 4.1334524173150036e-05, "epoch": 191.8495575221239, "percentage": 27.34, "elapsed_time": "1:18:29", "remaining_time": "3:28:37", "throughput": 1319.86, "total_tokens": 6215680} {"current_steps": 10940, "total_steps": 40000, "loss": 0.0, "lr": 4.13270907963911e-05, "epoch": 191.93805309734512, "percentage": 27.35, "elapsed_time": "1:18:31", "remaining_time": "3:28:34", "throughput": 1319.95, "total_tokens": 6218800} {"current_steps": 10945, "total_steps": 40000, "loss": 0.0, "lr": 4.131965490178959e-05, "epoch": 192.01769911504425, "percentage": 27.36, "elapsed_time": "1:18:33", "remaining_time": "3:28:33", "throughput": 1319.82, "total_tokens": 6221184} {"current_steps": 10950, "total_steps": 40000, "loss": 0.0, "lr": 4.131221649049222e-05, "epoch": 192.10619469026548, "percentage": 27.38, "elapsed_time": "1:18:35", "remaining_time": "3:28:30", "throughput": 1319.83, "total_tokens": 6223936} {"current_steps": 10955, "total_steps": 40000, "loss": 0.0, "lr": 4.130477556364606e-05, "epoch": 192.1946902654867, "percentage": 27.39, "elapsed_time": "1:18:37", "remaining_time": "3:28:28", "throughput": 1319.95, "total_tokens": 6227248} {"current_steps": 10960, "total_steps": 40000, "loss": 0.0, "lr": 4.129733212239861e-05, "epoch": 192.28318584070797, "percentage": 27.4, "elapsed_time": "1:18:39", "remaining_time": "3:28:25", "throughput": 1319.95, "total_tokens": 6229952} {"current_steps": 10965, "total_steps": 40000, "loss": 0.0, "lr": 4.128988616789774e-05, "epoch": 192.3716814159292, "percentage": 27.41, "elapsed_time": "1:18:41", "remaining_time": "3:28:23", "throughput": 1319.98, "total_tokens": 6232816} {"current_steps": 10970, "total_steps": 40000, "loss": 0.0, "lr": 4.1282437701291724e-05, "epoch": 192.46017699115043, "percentage": 27.43, "elapsed_time": "1:18:43", "remaining_time": "3:28:21", "throughput": 1319.98, "total_tokens": 6235552} {"current_steps": 10975, "total_steps": 40000, "loss": 0.0, "lr": 4.1274986723729184e-05, "epoch": 192.5486725663717, "percentage": 27.44, "elapsed_time": "1:18:46", "remaining_time": "3:28:18", "throughput": 1320.02, "total_tokens": 6238512} {"current_steps": 10980, "total_steps": 40000, "loss": 0.0, "lr": 4.126753323635917e-05, "epoch": 192.63716814159292, "percentage": 27.45, "elapsed_time": "1:18:48", "remaining_time": "3:28:16", "throughput": 1320.0, "total_tokens": 6241136} {"current_steps": 10985, "total_steps": 40000, "loss": 0.0, "lr": 4.12600772403311e-05, "epoch": 192.72566371681415, "percentage": 27.46, "elapsed_time": "1:18:50", "remaining_time": "3:28:13", "throughput": 1320.05, "total_tokens": 6244112} {"current_steps": 10990, "total_steps": 40000, "loss": 0.0, "lr": 4.125261873679479e-05, "epoch": 192.81415929203538, "percentage": 27.47, "elapsed_time": "1:18:52", "remaining_time": "3:28:11", "throughput": 1320.14, "total_tokens": 6247248} {"current_steps": 10995, "total_steps": 40000, "loss": 0.0, "lr": 4.124515772690042e-05, "epoch": 192.90265486725664, "percentage": 27.49, "elapsed_time": "1:18:54", "remaining_time": "3:28:09", "throughput": 1320.17, "total_tokens": 6250080} {"current_steps": 11000, "total_steps": 40000, "loss": 0.0, "lr": 4.123769421179858e-05, "epoch": 192.99115044247787, "percentage": 27.5, "elapsed_time": "1:18:56", "remaining_time": "3:28:06", "throughput": 1320.18, "total_tokens": 6252832} {"current_steps": 11000, "total_steps": 40000, "eval_loss": 0.4487813711166382, "epoch": 192.99115044247787, "percentage": 27.5, "elapsed_time": "1:18:57", "remaining_time": "3:28:09", "throughput": 1319.88, "total_tokens": 6252832} {"current_steps": 11005, "total_steps": 40000, "loss": 0.0, "lr": 4.1230228192640236e-05, "epoch": 193.07079646017698, "percentage": 27.51, "elapsed_time": "1:19:01", "remaining_time": "3:28:12", "throughput": 1319.23, "total_tokens": 6254912} {"current_steps": 11010, "total_steps": 40000, "loss": 0.0, "lr": 4.122275967057675e-05, "epoch": 193.15929203539824, "percentage": 27.52, "elapsed_time": "1:19:03", "remaining_time": "3:28:09", "throughput": 1319.24, "total_tokens": 6257696} {"current_steps": 11015, "total_steps": 40000, "loss": 0.0, "lr": 4.1215288646759846e-05, "epoch": 193.24778761061947, "percentage": 27.54, "elapsed_time": "1:19:05", "remaining_time": "3:28:07", "throughput": 1319.21, "total_tokens": 6260304} {"current_steps": 11020, "total_steps": 40000, "loss": 0.0, "lr": 4.120781512234166e-05, "epoch": 193.3362831858407, "percentage": 27.55, "elapsed_time": "1:19:07", "remaining_time": "3:28:04", "throughput": 1319.27, "total_tokens": 6263312} {"current_steps": 11025, "total_steps": 40000, "loss": 0.0, "lr": 4.120033909847471e-05, "epoch": 193.42477876106196, "percentage": 27.56, "elapsed_time": "1:19:09", "remaining_time": "3:28:02", "throughput": 1319.46, "total_tokens": 6266928} {"current_steps": 11030, "total_steps": 40000, "loss": 0.0, "lr": 4.119286057631187e-05, "epoch": 193.5132743362832, "percentage": 27.57, "elapsed_time": "1:19:11", "remaining_time": "3:28:00", "throughput": 1319.49, "total_tokens": 6269808} {"current_steps": 11035, "total_steps": 40000, "loss": 0.0, "lr": 4.118537955700646e-05, "epoch": 193.60176991150442, "percentage": 27.59, "elapsed_time": "1:19:13", "remaining_time": "3:27:57", "throughput": 1319.49, "total_tokens": 6272512} {"current_steps": 11040, "total_steps": 40000, "loss": 0.0, "lr": 4.11778960417121e-05, "epoch": 193.69026548672565, "percentage": 27.6, "elapsed_time": "1:19:15", "remaining_time": "3:27:55", "throughput": 1319.62, "total_tokens": 6275904} {"current_steps": 11045, "total_steps": 40000, "loss": 0.0, "lr": 4.117041003158288e-05, "epoch": 193.7787610619469, "percentage": 27.61, "elapsed_time": "1:19:17", "remaining_time": "3:27:53", "throughput": 1319.77, "total_tokens": 6279312} {"current_steps": 11050, "total_steps": 40000, "loss": 0.0, "lr": 4.1162921527773215e-05, "epoch": 193.86725663716814, "percentage": 27.62, "elapsed_time": "1:19:19", "remaining_time": "3:27:50", "throughput": 1319.71, "total_tokens": 6281760} {"current_steps": 11055, "total_steps": 40000, "loss": 0.0, "lr": 4.115543053143794e-05, "epoch": 193.95575221238937, "percentage": 27.64, "elapsed_time": "1:19:22", "remaining_time": "3:27:48", "throughput": 1319.75, "total_tokens": 6284656} {"current_steps": 11060, "total_steps": 40000, "loss": 0.0, "lr": 4.114793704373226e-05, "epoch": 194.0353982300885, "percentage": 27.65, "elapsed_time": "1:19:24", "remaining_time": "3:27:46", "throughput": 1319.62, "total_tokens": 6286984} {"current_steps": 11065, "total_steps": 40000, "loss": 0.0, "lr": 4.114044106581175e-05, "epoch": 194.12389380530973, "percentage": 27.66, "elapsed_time": "1:19:26", "remaining_time": "3:27:43", "throughput": 1319.66, "total_tokens": 6289928} {"current_steps": 11070, "total_steps": 40000, "loss": 0.0, "lr": 4.11329425988324e-05, "epoch": 194.21238938053096, "percentage": 27.68, "elapsed_time": "1:19:28", "remaining_time": "3:27:41", "throughput": 1319.7, "total_tokens": 6292840} {"current_steps": 11075, "total_steps": 40000, "loss": 0.0, "lr": 4.112544164395056e-05, "epoch": 194.30088495575222, "percentage": 27.69, "elapsed_time": "1:19:30", "remaining_time": "3:27:39", "throughput": 1319.71, "total_tokens": 6295624} {"current_steps": 11080, "total_steps": 40000, "loss": 0.0, "lr": 4.111793820232297e-05, "epoch": 194.38938053097345, "percentage": 27.7, "elapsed_time": "1:19:32", "remaining_time": "3:27:36", "throughput": 1319.66, "total_tokens": 6298104} {"current_steps": 11085, "total_steps": 40000, "loss": 0.0, "lr": 4.1110432275106767e-05, "epoch": 194.47787610619469, "percentage": 27.71, "elapsed_time": "1:19:34", "remaining_time": "3:27:34", "throughput": 1319.65, "total_tokens": 6300776} {"current_steps": 11090, "total_steps": 40000, "loss": 0.0, "lr": 4.110292386345944e-05, "epoch": 194.56637168141592, "percentage": 27.73, "elapsed_time": "1:19:36", "remaining_time": "3:27:32", "throughput": 1319.66, "total_tokens": 6303560} {"current_steps": 11095, "total_steps": 40000, "loss": 0.0, "lr": 4.109541296853891e-05, "epoch": 194.65486725663717, "percentage": 27.74, "elapsed_time": "1:19:38", "remaining_time": "3:27:29", "throughput": 1319.66, "total_tokens": 6306280} {"current_steps": 11100, "total_steps": 40000, "loss": 0.0, "lr": 4.108789959150341e-05, "epoch": 194.7433628318584, "percentage": 27.75, "elapsed_time": "1:19:40", "remaining_time": "3:27:27", "throughput": 1319.74, "total_tokens": 6309400} {"current_steps": 11105, "total_steps": 40000, "loss": 0.0, "lr": 4.108038373351163e-05, "epoch": 194.83185840707964, "percentage": 27.76, "elapsed_time": "1:19:42", "remaining_time": "3:27:24", "throughput": 1319.88, "total_tokens": 6312760} {"current_steps": 11110, "total_steps": 40000, "loss": 0.0, "lr": 4.10728653957226e-05, "epoch": 194.9203539823009, "percentage": 27.77, "elapsed_time": "1:19:44", "remaining_time": "3:27:22", "throughput": 1319.91, "total_tokens": 6315624} {"current_steps": 11115, "total_steps": 40000, "loss": 0.0, "lr": 4.106534457929575e-05, "epoch": 195.0, "percentage": 27.79, "elapsed_time": "1:19:46", "remaining_time": "3:27:19", "throughput": 1319.92, "total_tokens": 6318352} {"current_steps": 11120, "total_steps": 40000, "loss": 0.0, "lr": 4.105782128539086e-05, "epoch": 195.08849557522123, "percentage": 27.8, "elapsed_time": "1:19:49", "remaining_time": "3:27:18", "throughput": 1319.91, "total_tokens": 6321360} {"current_steps": 11125, "total_steps": 40000, "loss": 0.0, "lr": 4.1050295515168144e-05, "epoch": 195.1769911504425, "percentage": 27.81, "elapsed_time": "1:19:51", "remaining_time": "3:27:15", "throughput": 1319.95, "total_tokens": 6324256} {"current_steps": 11130, "total_steps": 40000, "loss": 0.0, "lr": 4.1042767269788155e-05, "epoch": 195.26548672566372, "percentage": 27.82, "elapsed_time": "1:19:53", "remaining_time": "3:27:13", "throughput": 1319.93, "total_tokens": 6326896} {"current_steps": 11135, "total_steps": 40000, "loss": 0.0, "lr": 4.103523655041185e-05, "epoch": 195.35398230088495, "percentage": 27.84, "elapsed_time": "1:19:55", "remaining_time": "3:27:11", "throughput": 1319.92, "total_tokens": 6329600} {"current_steps": 11140, "total_steps": 40000, "loss": 0.0, "lr": 4.102770335820055e-05, "epoch": 195.44247787610618, "percentage": 27.85, "elapsed_time": "1:19:57", "remaining_time": "3:27:08", "throughput": 1320.02, "total_tokens": 6332768} {"current_steps": 11145, "total_steps": 40000, "loss": 0.0, "lr": 4.1020167694315984e-05, "epoch": 195.53097345132744, "percentage": 27.86, "elapsed_time": "1:19:59", "remaining_time": "3:27:06", "throughput": 1320.03, "total_tokens": 6335536} {"current_steps": 11150, "total_steps": 40000, "loss": 0.0, "lr": 4.101262955992023e-05, "epoch": 195.61946902654867, "percentage": 27.88, "elapsed_time": "1:20:01", "remaining_time": "3:27:03", "throughput": 1319.98, "total_tokens": 6338064} {"current_steps": 11155, "total_steps": 40000, "loss": 0.0, "lr": 4.100508895617578e-05, "epoch": 195.7079646017699, "percentage": 27.89, "elapsed_time": "1:20:03", "remaining_time": "3:27:01", "throughput": 1320.03, "total_tokens": 6341056} {"current_steps": 11160, "total_steps": 40000, "loss": 0.0, "lr": 4.099754588424547e-05, "epoch": 195.79646017699116, "percentage": 27.9, "elapsed_time": "1:20:05", "remaining_time": "3:26:59", "throughput": 1320.05, "total_tokens": 6343856} {"current_steps": 11165, "total_steps": 40000, "loss": 0.0, "lr": 4.0990000345292546e-05, "epoch": 195.8849557522124, "percentage": 27.91, "elapsed_time": "1:20:07", "remaining_time": "3:26:56", "throughput": 1320.12, "total_tokens": 6346928} {"current_steps": 11170, "total_steps": 40000, "loss": 0.0, "lr": 4.098245234048064e-05, "epoch": 195.97345132743362, "percentage": 27.93, "elapsed_time": "1:20:09", "remaining_time": "3:26:54", "throughput": 1320.18, "total_tokens": 6349888} {"current_steps": 11175, "total_steps": 40000, "loss": 0.0, "lr": 4.0974901870973726e-05, "epoch": 196.05309734513276, "percentage": 27.94, "elapsed_time": "1:20:12", "remaining_time": "3:26:52", "throughput": 1320.07, "total_tokens": 6352344} {"current_steps": 11180, "total_steps": 40000, "loss": 0.0, "lr": 4.096734893793619e-05, "epoch": 196.141592920354, "percentage": 27.95, "elapsed_time": "1:20:14", "remaining_time": "3:26:50", "throughput": 1320.18, "total_tokens": 6355608} {"current_steps": 11185, "total_steps": 40000, "loss": 0.0, "lr": 4.095979354253279e-05, "epoch": 196.23008849557522, "percentage": 27.96, "elapsed_time": "1:20:16", "remaining_time": "3:26:47", "throughput": 1320.22, "total_tokens": 6358552} {"current_steps": 11190, "total_steps": 40000, "loss": 0.0, "lr": 4.0952235685928656e-05, "epoch": 196.31858407079645, "percentage": 27.98, "elapsed_time": "1:20:18", "remaining_time": "3:26:45", "throughput": 1320.13, "total_tokens": 6360840} {"current_steps": 11195, "total_steps": 40000, "loss": 0.0, "lr": 4.094467536928932e-05, "epoch": 196.4070796460177, "percentage": 27.99, "elapsed_time": "1:20:20", "remaining_time": "3:26:43", "throughput": 1320.16, "total_tokens": 6363720} {"current_steps": 11200, "total_steps": 40000, "loss": 0.0, "lr": 4.093711259378067e-05, "epoch": 196.49557522123894, "percentage": 28.0, "elapsed_time": "1:20:22", "remaining_time": "3:26:40", "throughput": 1320.16, "total_tokens": 6366440} {"current_steps": 11200, "total_steps": 40000, "eval_loss": 0.4484032988548279, "epoch": 196.49557522123894, "percentage": 28.0, "elapsed_time": "1:20:23", "remaining_time": "3:26:43", "throughput": 1319.87, "total_tokens": 6366440} {"current_steps": 11205, "total_steps": 40000, "loss": 0.0, "lr": 4.092954736056897e-05, "epoch": 196.58407079646017, "percentage": 28.01, "elapsed_time": "1:20:28", "remaining_time": "3:26:48", "throughput": 1319.17, "total_tokens": 6369384} {"current_steps": 11210, "total_steps": 40000, "loss": 0.0, "lr": 4.09219796708209e-05, "epoch": 196.67256637168143, "percentage": 28.02, "elapsed_time": "1:20:30", "remaining_time": "3:26:45", "throughput": 1319.16, "total_tokens": 6372072} {"current_steps": 11215, "total_steps": 40000, "loss": 0.0, "lr": 4.0914409525703464e-05, "epoch": 196.76106194690266, "percentage": 28.04, "elapsed_time": "1:20:32", "remaining_time": "3:26:43", "throughput": 1319.19, "total_tokens": 6374968} {"current_steps": 11220, "total_steps": 40000, "loss": 0.0, "lr": 4.090683692638408e-05, "epoch": 196.8495575221239, "percentage": 28.05, "elapsed_time": "1:20:34", "remaining_time": "3:26:40", "throughput": 1319.17, "total_tokens": 6377592} {"current_steps": 11225, "total_steps": 40000, "loss": 0.0, "lr": 4.089926187403056e-05, "epoch": 196.93805309734512, "percentage": 28.06, "elapsed_time": "1:20:36", "remaining_time": "3:26:38", "throughput": 1319.29, "total_tokens": 6380888} {"current_steps": 11230, "total_steps": 40000, "loss": 0.0, "lr": 4.0891684369811044e-05, "epoch": 197.01769911504425, "percentage": 28.07, "elapsed_time": "1:20:38", "remaining_time": "3:26:36", "throughput": 1319.14, "total_tokens": 6383104} {"current_steps": 11235, "total_steps": 40000, "loss": 0.0, "lr": 4.0884104414894107e-05, "epoch": 197.10619469026548, "percentage": 28.09, "elapsed_time": "1:20:40", "remaining_time": "3:26:34", "throughput": 1319.26, "total_tokens": 6386400} {"current_steps": 11240, "total_steps": 40000, "loss": 0.0, "lr": 4.087652201044864e-05, "epoch": 197.1946902654867, "percentage": 28.1, "elapsed_time": "1:20:42", "remaining_time": "3:26:31", "throughput": 1319.31, "total_tokens": 6389392} {"current_steps": 11245, "total_steps": 40000, "loss": 0.0, "lr": 4.086893715764397e-05, "epoch": 197.28318584070797, "percentage": 28.11, "elapsed_time": "1:20:45", "remaining_time": "3:26:29", "throughput": 1319.27, "total_tokens": 6391968} {"current_steps": 11250, "total_steps": 40000, "loss": 0.0, "lr": 4.086134985764977e-05, "epoch": 197.3716814159292, "percentage": 28.12, "elapsed_time": "1:20:47", "remaining_time": "3:26:27", "throughput": 1319.28, "total_tokens": 6394720} {"current_steps": 11255, "total_steps": 40000, "loss": 0.0, "lr": 4.0853760111636085e-05, "epoch": 197.46017699115043, "percentage": 28.14, "elapsed_time": "1:20:49", "remaining_time": "3:26:24", "throughput": 1319.36, "total_tokens": 6397808} {"current_steps": 11260, "total_steps": 40000, "loss": 0.0, "lr": 4.084616792077337e-05, "epoch": 197.5486725663717, "percentage": 28.15, "elapsed_time": "1:20:51", "remaining_time": "3:26:22", "throughput": 1319.34, "total_tokens": 6400448} {"current_steps": 11265, "total_steps": 40000, "loss": 0.0, "lr": 4.083857328623243e-05, "epoch": 197.63716814159292, "percentage": 28.16, "elapsed_time": "1:20:53", "remaining_time": "3:26:19", "throughput": 1319.33, "total_tokens": 6403136} {"current_steps": 11270, "total_steps": 40000, "loss": 0.0, "lr": 4.083097620918444e-05, "epoch": 197.72566371681415, "percentage": 28.18, "elapsed_time": "1:20:55", "remaining_time": "3:26:17", "throughput": 1319.41, "total_tokens": 6406288} {"current_steps": 11275, "total_steps": 40000, "loss": 0.0, "lr": 4.082337669080097e-05, "epoch": 197.81415929203538, "percentage": 28.19, "elapsed_time": "1:20:57", "remaining_time": "3:26:15", "throughput": 1319.39, "total_tokens": 6408896} {"current_steps": 11280, "total_steps": 40000, "loss": 0.0, "lr": 4.081577473225398e-05, "epoch": 197.90265486725664, "percentage": 28.2, "elapsed_time": "1:20:59", "remaining_time": "3:26:12", "throughput": 1319.41, "total_tokens": 6411728} {"current_steps": 11285, "total_steps": 40000, "loss": 0.0, "lr": 4.080817033471577e-05, "epoch": 197.99115044247787, "percentage": 28.21, "elapsed_time": "1:21:01", "remaining_time": "3:26:10", "throughput": 1319.44, "total_tokens": 6414592} {"current_steps": 11290, "total_steps": 40000, "loss": 0.0, "lr": 4.080056349935903e-05, "epoch": 198.07079646017698, "percentage": 28.23, "elapsed_time": "1:21:03", "remaining_time": "3:26:08", "throughput": 1319.31, "total_tokens": 6416920} {"current_steps": 11295, "total_steps": 40000, "loss": 0.0, "lr": 4.079295422735684e-05, "epoch": 198.15929203539824, "percentage": 28.24, "elapsed_time": "1:21:05", "remaining_time": "3:26:06", "throughput": 1319.24, "total_tokens": 6419336} {"current_steps": 11300, "total_steps": 40000, "loss": 0.0, "lr": 4.078534251988264e-05, "epoch": 198.24778761061947, "percentage": 28.25, "elapsed_time": "1:21:07", "remaining_time": "3:26:03", "throughput": 1319.31, "total_tokens": 6422376} {"current_steps": 11305, "total_steps": 40000, "loss": 0.0, "lr": 4.077772837811025e-05, "epoch": 198.3362831858407, "percentage": 28.26, "elapsed_time": "1:21:10", "remaining_time": "3:26:01", "throughput": 1319.35, "total_tokens": 6425320} {"current_steps": 11310, "total_steps": 40000, "loss": 0.0, "lr": 4.0770111803213874e-05, "epoch": 198.42477876106196, "percentage": 28.27, "elapsed_time": "1:21:12", "remaining_time": "3:25:59", "throughput": 1319.36, "total_tokens": 6428056} {"current_steps": 11315, "total_steps": 40000, "loss": 0.0, "lr": 4.076249279636807e-05, "epoch": 198.5132743362832, "percentage": 28.29, "elapsed_time": "1:21:14", "remaining_time": "3:25:56", "throughput": 1319.5, "total_tokens": 6431480} {"current_steps": 11320, "total_steps": 40000, "loss": 0.0, "lr": 4.075487135874781e-05, "epoch": 198.60176991150442, "percentage": 28.3, "elapsed_time": "1:21:16", "remaining_time": "3:25:54", "throughput": 1319.45, "total_tokens": 6433976} {"current_steps": 11325, "total_steps": 40000, "loss": 0.0, "lr": 4.074724749152837e-05, "epoch": 198.69026548672565, "percentage": 28.31, "elapsed_time": "1:21:18", "remaining_time": "3:25:51", "throughput": 1319.53, "total_tokens": 6437080} {"current_steps": 11330, "total_steps": 40000, "loss": 0.0, "lr": 4.07396211958855e-05, "epoch": 198.7787610619469, "percentage": 28.32, "elapsed_time": "1:21:20", "remaining_time": "3:25:49", "throughput": 1319.55, "total_tokens": 6439896} {"current_steps": 11335, "total_steps": 40000, "loss": 0.0, "lr": 4.073199247299523e-05, "epoch": 198.86725663716814, "percentage": 28.34, "elapsed_time": "1:21:22", "remaining_time": "3:25:47", "throughput": 1319.6, "total_tokens": 6442888} {"current_steps": 11340, "total_steps": 40000, "loss": 0.0, "lr": 4.072436132403403e-05, "epoch": 198.95575221238937, "percentage": 28.35, "elapsed_time": "1:21:24", "remaining_time": "3:25:44", "throughput": 1319.57, "total_tokens": 6445448} {"current_steps": 11345, "total_steps": 40000, "loss": 0.0, "lr": 4.0716727750178704e-05, "epoch": 199.0353982300885, "percentage": 28.36, "elapsed_time": "1:21:26", "remaining_time": "3:25:42", "throughput": 1319.43, "total_tokens": 6447712} {"current_steps": 11350, "total_steps": 40000, "loss": 0.0, "lr": 4.0709091752606455e-05, "epoch": 199.12389380530973, "percentage": 28.38, "elapsed_time": "1:21:28", "remaining_time": "3:25:40", "throughput": 1319.41, "total_tokens": 6450336} {"current_steps": 11355, "total_steps": 40000, "loss": 0.0, "lr": 4.070145333249484e-05, "epoch": 199.21238938053096, "percentage": 28.39, "elapsed_time": "1:21:30", "remaining_time": "3:25:38", "throughput": 1319.51, "total_tokens": 6453584} {"current_steps": 11360, "total_steps": 40000, "loss": 0.0, "lr": 4.069381249102181e-05, "epoch": 199.30088495575222, "percentage": 28.4, "elapsed_time": "1:21:32", "remaining_time": "3:25:35", "throughput": 1319.6, "total_tokens": 6456752} {"current_steps": 11365, "total_steps": 40000, "loss": 0.0, "lr": 4.0686169229365665e-05, "epoch": 199.38938053097345, "percentage": 28.41, "elapsed_time": "1:21:35", "remaining_time": "3:25:33", "throughput": 1319.61, "total_tokens": 6459536} {"current_steps": 11370, "total_steps": 40000, "loss": 0.0, "lr": 4.067852354870511e-05, "epoch": 199.47787610619469, "percentage": 28.43, "elapsed_time": "1:21:37", "remaining_time": "3:25:31", "throughput": 1319.59, "total_tokens": 6462160} {"current_steps": 11375, "total_steps": 40000, "loss": 0.0, "lr": 4.067087545021919e-05, "epoch": 199.56637168141592, "percentage": 28.44, "elapsed_time": "1:21:39", "remaining_time": "3:25:28", "throughput": 1319.63, "total_tokens": 6465072} {"current_steps": 11380, "total_steps": 40000, "loss": 0.0, "lr": 4.066322493508734e-05, "epoch": 199.65486725663717, "percentage": 28.45, "elapsed_time": "1:21:41", "remaining_time": "3:25:26", "throughput": 1319.66, "total_tokens": 6467920} {"current_steps": 11385, "total_steps": 40000, "loss": 0.0, "lr": 4.065557200448937e-05, "epoch": 199.7433628318584, "percentage": 28.46, "elapsed_time": "1:21:43", "remaining_time": "3:25:23", "throughput": 1319.61, "total_tokens": 6470416} {"current_steps": 11390, "total_steps": 40000, "loss": 0.0, "lr": 4.064791665960546e-05, "epoch": 199.83185840707964, "percentage": 28.48, "elapsed_time": "1:21:45", "remaining_time": "3:25:21", "throughput": 1319.64, "total_tokens": 6473280} {"current_steps": 11395, "total_steps": 40000, "loss": 0.0, "lr": 4.064025890161615e-05, "epoch": 199.9203539823009, "percentage": 28.49, "elapsed_time": "1:21:47", "remaining_time": "3:25:19", "throughput": 1319.74, "total_tokens": 6476512} {"current_steps": 11400, "total_steps": 40000, "loss": 0.0, "lr": 4.0632598731702373e-05, "epoch": 200.0, "percentage": 28.5, "elapsed_time": "1:21:49", "remaining_time": "3:25:16", "throughput": 1319.66, "total_tokens": 6478776} {"current_steps": 11400, "total_steps": 40000, "eval_loss": 0.4492186903953552, "epoch": 200.0, "percentage": 28.5, "elapsed_time": "1:21:50", "remaining_time": "3:25:19", "throughput": 1319.37, "total_tokens": 6478776} {"current_steps": 11405, "total_steps": 40000, "loss": 0.0, "lr": 4.0624936151045426e-05, "epoch": 200.08849557522123, "percentage": 28.51, "elapsed_time": "1:21:54", "remaining_time": "3:25:21", "throughput": 1318.88, "total_tokens": 6481576} {"current_steps": 11410, "total_steps": 40000, "loss": 0.0, "lr": 4.061727116082696e-05, "epoch": 200.1769911504425, "percentage": 28.52, "elapsed_time": "1:21:56", "remaining_time": "3:25:19", "throughput": 1318.92, "total_tokens": 6484520} {"current_steps": 11415, "total_steps": 40000, "loss": 0.0, "lr": 4.060960376222903e-05, "epoch": 200.26548672566372, "percentage": 28.54, "elapsed_time": "1:21:58", "remaining_time": "3:25:17", "throughput": 1318.98, "total_tokens": 6487592} {"current_steps": 11420, "total_steps": 40000, "loss": 0.0, "lr": 4.0601933956434034e-05, "epoch": 200.35398230088495, "percentage": 28.55, "elapsed_time": "1:22:00", "remaining_time": "3:25:14", "throughput": 1318.95, "total_tokens": 6490152} {"current_steps": 11425, "total_steps": 40000, "loss": 0.0, "lr": 4.059426174462476e-05, "epoch": 200.44247787610618, "percentage": 28.56, "elapsed_time": "1:22:02", "remaining_time": "3:25:12", "throughput": 1318.98, "total_tokens": 6493016} {"current_steps": 11430, "total_steps": 40000, "loss": 0.0, "lr": 4.058658712798435e-05, "epoch": 200.53097345132744, "percentage": 28.57, "elapsed_time": "1:22:04", "remaining_time": "3:25:09", "throughput": 1319.05, "total_tokens": 6496104} {"current_steps": 11435, "total_steps": 40000, "loss": 0.0, "lr": 4.0578910107696336e-05, "epoch": 200.61946902654867, "percentage": 28.59, "elapsed_time": "1:22:06", "remaining_time": "3:25:07", "throughput": 1319.01, "total_tokens": 6498632} {"current_steps": 11440, "total_steps": 40000, "loss": 0.0, "lr": 4.05712306849446e-05, "epoch": 200.7079646017699, "percentage": 28.6, "elapsed_time": "1:22:08", "remaining_time": "3:25:05", "throughput": 1319.04, "total_tokens": 6501512} {"current_steps": 11445, "total_steps": 40000, "loss": 0.0, "lr": 4.0563548860913415e-05, "epoch": 200.79646017699116, "percentage": 28.61, "elapsed_time": "1:22:11", "remaining_time": "3:25:02", "throughput": 1319.04, "total_tokens": 6504200} {"current_steps": 11450, "total_steps": 40000, "loss": 0.0, "lr": 4.0555864636787414e-05, "epoch": 200.8849557522124, "percentage": 28.62, "elapsed_time": "1:22:13", "remaining_time": "3:25:00", "throughput": 1319.15, "total_tokens": 6507496} {"current_steps": 11455, "total_steps": 40000, "loss": 0.0, "lr": 4.054817801375159e-05, "epoch": 200.97345132743362, "percentage": 28.64, "elapsed_time": "1:22:15", "remaining_time": "3:24:57", "throughput": 1319.23, "total_tokens": 6510568} {"current_steps": 11460, "total_steps": 40000, "loss": 0.0, "lr": 4.054048899299134e-05, "epoch": 201.05309734513276, "percentage": 28.65, "elapsed_time": "1:22:17", "remaining_time": "3:24:56", "throughput": 1319.1, "total_tokens": 6512936} {"current_steps": 11465, "total_steps": 40000, "loss": 0.0, "lr": 4.0532797575692385e-05, "epoch": 201.141592920354, "percentage": 28.66, "elapsed_time": "1:22:19", "remaining_time": "3:24:53", "throughput": 1319.05, "total_tokens": 6515416} {"current_steps": 11470, "total_steps": 40000, "loss": 0.0, "lr": 4.052510376304085e-05, "epoch": 201.23008849557522, "percentage": 28.68, "elapsed_time": "1:22:21", "remaining_time": "3:24:51", "throughput": 1319.18, "total_tokens": 6518744} {"current_steps": 11475, "total_steps": 40000, "loss": 0.0, "lr": 4.051740755622321e-05, "epoch": 201.31858407079645, "percentage": 28.69, "elapsed_time": "1:22:23", "remaining_time": "3:24:48", "throughput": 1319.1, "total_tokens": 6521080} {"current_steps": 11480, "total_steps": 40000, "loss": 0.0, "lr": 4.050970895642632e-05, "epoch": 201.4070796460177, "percentage": 28.7, "elapsed_time": "1:22:25", "remaining_time": "3:24:46", "throughput": 1319.08, "total_tokens": 6523720} {"current_steps": 11485, "total_steps": 40000, "loss": 0.0, "lr": 4.050200796483741e-05, "epoch": 201.49557522123894, "percentage": 28.71, "elapsed_time": "1:22:27", "remaining_time": "3:24:44", "throughput": 1319.14, "total_tokens": 6526760} {"current_steps": 11490, "total_steps": 40000, "loss": 0.0, "lr": 4.049430458264405e-05, "epoch": 201.58407079646017, "percentage": 28.73, "elapsed_time": "1:22:29", "remaining_time": "3:24:41", "throughput": 1319.24, "total_tokens": 6529992} {"current_steps": 11495, "total_steps": 40000, "loss": 0.0, "lr": 4.048659881103422e-05, "epoch": 201.67256637168143, "percentage": 28.74, "elapsed_time": "1:22:31", "remaining_time": "3:24:39", "throughput": 1319.22, "total_tokens": 6532584} {"current_steps": 11500, "total_steps": 40000, "loss": 0.0, "lr": 4.0478890651196235e-05, "epoch": 201.76106194690266, "percentage": 28.75, "elapsed_time": "1:22:33", "remaining_time": "3:24:37", "throughput": 1319.31, "total_tokens": 6535768} {"current_steps": 11505, "total_steps": 40000, "loss": 0.0, "lr": 4.047118010431879e-05, "epoch": 201.8495575221239, "percentage": 28.76, "elapsed_time": "1:22:35", "remaining_time": "3:24:34", "throughput": 1319.36, "total_tokens": 6538728} {"current_steps": 11510, "total_steps": 40000, "loss": 0.0, "lr": 4.046346717159094e-05, "epoch": 201.93805309734512, "percentage": 28.78, "elapsed_time": "1:22:38", "remaining_time": "3:24:32", "throughput": 1319.34, "total_tokens": 6541320} {"current_steps": 11515, "total_steps": 40000, "loss": 0.0, "lr": 4.045575185420214e-05, "epoch": 202.01769911504425, "percentage": 28.79, "elapsed_time": "1:22:40", "remaining_time": "3:24:30", "throughput": 1319.27, "total_tokens": 6543928} {"current_steps": 11520, "total_steps": 40000, "loss": 0.0, "lr": 4.0448034153342165e-05, "epoch": 202.10619469026548, "percentage": 28.8, "elapsed_time": "1:22:42", "remaining_time": "3:24:28", "throughput": 1319.27, "total_tokens": 6546680} {"current_steps": 11525, "total_steps": 40000, "loss": 0.0, "lr": 4.0440314070201194e-05, "epoch": 202.1946902654867, "percentage": 28.81, "elapsed_time": "1:22:44", "remaining_time": "3:24:25", "throughput": 1319.27, "total_tokens": 6549400} {"current_steps": 11530, "total_steps": 40000, "loss": 0.0, "lr": 4.043259160596976e-05, "epoch": 202.28318584070797, "percentage": 28.82, "elapsed_time": "1:22:46", "remaining_time": "3:24:23", "throughput": 1319.26, "total_tokens": 6552088} {"current_steps": 11535, "total_steps": 40000, "loss": 0.0, "lr": 4.0424866761838767e-05, "epoch": 202.3716814159292, "percentage": 28.84, "elapsed_time": "1:22:48", "remaining_time": "3:24:20", "throughput": 1319.3, "total_tokens": 6555048} {"current_steps": 11540, "total_steps": 40000, "loss": 0.0, "lr": 4.041713953899948e-05, "epoch": 202.46017699115043, "percentage": 28.85, "elapsed_time": "1:22:50", "remaining_time": "3:24:18", "throughput": 1319.4, "total_tokens": 6558280} {"current_steps": 11545, "total_steps": 40000, "loss": 0.0, "lr": 4.0409409938643515e-05, "epoch": 202.5486725663717, "percentage": 28.86, "elapsed_time": "1:22:52", "remaining_time": "3:24:16", "throughput": 1319.45, "total_tokens": 6561240} {"current_steps": 11550, "total_steps": 40000, "loss": 0.0, "lr": 4.0401677961962904e-05, "epoch": 202.63716814159292, "percentage": 28.88, "elapsed_time": "1:22:54", "remaining_time": "3:24:13", "throughput": 1319.47, "total_tokens": 6564040} {"current_steps": 11555, "total_steps": 40000, "loss": 0.0, "lr": 4.039394361015001e-05, "epoch": 202.72566371681415, "percentage": 28.89, "elapsed_time": "1:22:56", "remaining_time": "3:24:11", "throughput": 1319.42, "total_tokens": 6566536} {"current_steps": 11560, "total_steps": 40000, "loss": 0.0, "lr": 4.038620688439755e-05, "epoch": 202.81415929203538, "percentage": 28.9, "elapsed_time": "1:22:58", "remaining_time": "3:24:09", "throughput": 1319.44, "total_tokens": 6569368} {"current_steps": 11565, "total_steps": 40000, "loss": 0.0, "lr": 4.037846778589862e-05, "epoch": 202.90265486725664, "percentage": 28.91, "elapsed_time": "1:23:00", "remaining_time": "3:24:06", "throughput": 1319.42, "total_tokens": 6572024} {"current_steps": 11570, "total_steps": 40000, "loss": 0.0, "lr": 4.0370726315846715e-05, "epoch": 202.99115044247787, "percentage": 28.93, "elapsed_time": "1:23:03", "remaining_time": "3:24:04", "throughput": 1319.46, "total_tokens": 6574904} {"current_steps": 11575, "total_steps": 40000, "loss": 0.0, "lr": 4.036298247543565e-05, "epoch": 203.07079646017698, "percentage": 28.94, "elapsed_time": "1:23:05", "remaining_time": "3:24:02", "throughput": 1319.32, "total_tokens": 6577192} {"current_steps": 11580, "total_steps": 40000, "loss": 0.0, "lr": 4.035523626585962e-05, "epoch": 203.15929203539824, "percentage": 28.95, "elapsed_time": "1:23:07", "remaining_time": "3:24:00", "throughput": 1319.47, "total_tokens": 6580680} {"current_steps": 11585, "total_steps": 40000, "loss": 0.0, "lr": 4.0347487688313194e-05, "epoch": 203.24778761061947, "percentage": 28.96, "elapsed_time": "1:23:09", "remaining_time": "3:23:57", "throughput": 1319.52, "total_tokens": 6583640} {"current_steps": 11590, "total_steps": 40000, "loss": 0.0, "lr": 4.0339736743991296e-05, "epoch": 203.3362831858407, "percentage": 28.98, "elapsed_time": "1:23:11", "remaining_time": "3:23:55", "throughput": 1319.58, "total_tokens": 6586648} {"current_steps": 11595, "total_steps": 40000, "loss": 0.0, "lr": 4.0331983434089227e-05, "epoch": 203.42477876106196, "percentage": 28.99, "elapsed_time": "1:23:13", "remaining_time": "3:23:52", "throughput": 1319.6, "total_tokens": 6589480} {"current_steps": 11600, "total_steps": 40000, "loss": 0.0, "lr": 4.032422775980264e-05, "epoch": 203.5132743362832, "percentage": 29.0, "elapsed_time": "1:23:15", "remaining_time": "3:23:50", "throughput": 1319.61, "total_tokens": 6592280} {"current_steps": 11600, "total_steps": 40000, "eval_loss": 0.45208242535591125, "epoch": 203.5132743362832, "percentage": 29.0, "elapsed_time": "1:23:16", "remaining_time": "3:23:53", "throughput": 1319.33, "total_tokens": 6592280} {"current_steps": 11605, "total_steps": 40000, "loss": 0.0, "lr": 4.031646972232754e-05, "epoch": 203.60176991150442, "percentage": 29.01, "elapsed_time": "1:23:20", "remaining_time": "3:23:55", "throughput": 1318.79, "total_tokens": 6594760} {"current_steps": 11610, "total_steps": 40000, "loss": 0.0, "lr": 4.0308709322860344e-05, "epoch": 203.69026548672565, "percentage": 29.03, "elapsed_time": "1:23:22", "remaining_time": "3:23:53", "throughput": 1318.9, "total_tokens": 6598040} {"current_steps": 11615, "total_steps": 40000, "loss": 0.0, "lr": 4.0300946562597784e-05, "epoch": 203.7787610619469, "percentage": 29.04, "elapsed_time": "1:23:24", "remaining_time": "3:23:50", "throughput": 1318.91, "total_tokens": 6600792} {"current_steps": 11620, "total_steps": 40000, "loss": 0.0, "lr": 4.029318144273698e-05, "epoch": 203.86725663716814, "percentage": 29.05, "elapsed_time": "1:23:26", "remaining_time": "3:23:48", "throughput": 1319.03, "total_tokens": 6604136} {"current_steps": 11625, "total_steps": 40000, "loss": 0.0, "lr": 4.0285413964475415e-05, "epoch": 203.95575221238937, "percentage": 29.06, "elapsed_time": "1:23:28", "remaining_time": "3:23:45", "throughput": 1318.94, "total_tokens": 6606392} {"current_steps": 11630, "total_steps": 40000, "loss": 0.0, "lr": 4.0277644129010927e-05, "epoch": 204.0353982300885, "percentage": 29.07, "elapsed_time": "1:23:31", "remaining_time": "3:23:44", "throughput": 1318.77, "total_tokens": 6608488} {"current_steps": 11635, "total_steps": 40000, "loss": 0.0, "lr": 4.0269871937541724e-05, "epoch": 204.12389380530973, "percentage": 29.09, "elapsed_time": "1:23:33", "remaining_time": "3:23:41", "throughput": 1318.75, "total_tokens": 6611128} {"current_steps": 11640, "total_steps": 40000, "loss": 0.0, "lr": 4.026209739126637e-05, "epoch": 204.21238938053096, "percentage": 29.1, "elapsed_time": "1:23:35", "remaining_time": "3:23:39", "throughput": 1318.74, "total_tokens": 6613832} {"current_steps": 11645, "total_steps": 40000, "loss": 0.0, "lr": 4.025432049138381e-05, "epoch": 204.30088495575222, "percentage": 29.11, "elapsed_time": "1:23:37", "remaining_time": "3:23:36", "throughput": 1318.86, "total_tokens": 6617144} {"current_steps": 11650, "total_steps": 40000, "loss": 0.0, "lr": 4.0246541239093325e-05, "epoch": 204.38938053097345, "percentage": 29.12, "elapsed_time": "1:23:39", "remaining_time": "3:23:34", "throughput": 1318.86, "total_tokens": 6619848} {"current_steps": 11655, "total_steps": 40000, "loss": 0.0, "lr": 4.023875963559459e-05, "epoch": 204.47787610619469, "percentage": 29.14, "elapsed_time": "1:23:41", "remaining_time": "3:23:32", "throughput": 1318.87, "total_tokens": 6622664} {"current_steps": 11660, "total_steps": 40000, "loss": 0.0, "lr": 4.023097568208761e-05, "epoch": 204.56637168141592, "percentage": 29.15, "elapsed_time": "1:23:43", "remaining_time": "3:23:29", "throughput": 1318.93, "total_tokens": 6625672} {"current_steps": 11665, "total_steps": 40000, "loss": 0.0, "lr": 4.022318937977277e-05, "epoch": 204.65486725663717, "percentage": 29.16, "elapsed_time": "1:23:45", "remaining_time": "3:23:27", "throughput": 1318.91, "total_tokens": 6628312} {"current_steps": 11670, "total_steps": 40000, "loss": 0.0, "lr": 4.021540072985084e-05, "epoch": 204.7433628318584, "percentage": 29.18, "elapsed_time": "1:23:47", "remaining_time": "3:23:25", "throughput": 1318.94, "total_tokens": 6631224} {"current_steps": 11675, "total_steps": 40000, "loss": 0.0, "lr": 4.020760973352289e-05, "epoch": 204.83185840707964, "percentage": 29.19, "elapsed_time": "1:23:49", "remaining_time": "3:23:22", "throughput": 1319.07, "total_tokens": 6634568} {"current_steps": 11680, "total_steps": 40000, "loss": 0.0, "lr": 4.019981639199042e-05, "epoch": 204.9203539823009, "percentage": 29.2, "elapsed_time": "1:23:51", "remaining_time": "3:23:20", "throughput": 1319.11, "total_tokens": 6637528} {"current_steps": 11685, "total_steps": 40000, "loss": 0.0, "lr": 4.0192020706455245e-05, "epoch": 205.0, "percentage": 29.21, "elapsed_time": "1:23:53", "remaining_time": "3:23:17", "throughput": 1319.0, "total_tokens": 6639624} {"current_steps": 11690, "total_steps": 40000, "loss": 0.0, "lr": 4.018422267811956e-05, "epoch": 205.08849557522123, "percentage": 29.23, "elapsed_time": "1:23:56", "remaining_time": "3:23:16", "throughput": 1318.93, "total_tokens": 6642280} {"current_steps": 11695, "total_steps": 40000, "loss": 0.0, "lr": 4.017642230818592e-05, "epoch": 205.1769911504425, "percentage": 29.24, "elapsed_time": "1:23:58", "remaining_time": "3:23:13", "throughput": 1319.08, "total_tokens": 6645784} {"current_steps": 11700, "total_steps": 40000, "loss": 0.0, "lr": 4.0168619597857246e-05, "epoch": 205.26548672566372, "percentage": 29.25, "elapsed_time": "1:24:00", "remaining_time": "3:23:11", "throughput": 1318.98, "total_tokens": 6648008} {"current_steps": 11705, "total_steps": 40000, "loss": 0.0, "lr": 4.016081454833681e-05, "epoch": 205.35398230088495, "percentage": 29.26, "elapsed_time": "1:24:02", "remaining_time": "3:23:09", "throughput": 1319.02, "total_tokens": 6650904} {"current_steps": 11710, "total_steps": 40000, "loss": 0.0, "lr": 4.0153007160828245e-05, "epoch": 205.44247787610618, "percentage": 29.28, "elapsed_time": "1:24:04", "remaining_time": "3:23:06", "throughput": 1319.06, "total_tokens": 6653848} {"current_steps": 11715, "total_steps": 40000, "loss": 0.0, "lr": 4.0145197436535555e-05, "epoch": 205.53097345132744, "percentage": 29.29, "elapsed_time": "1:24:06", "remaining_time": "3:23:04", "throughput": 1319.07, "total_tokens": 6656632} {"current_steps": 11720, "total_steps": 40000, "loss": 0.0, "lr": 4.0137385376663095e-05, "epoch": 205.61946902654867, "percentage": 29.3, "elapsed_time": "1:24:08", "remaining_time": "3:23:01", "throughput": 1319.1, "total_tokens": 6659528} {"current_steps": 11725, "total_steps": 40000, "loss": 0.0, "lr": 4.012957098241558e-05, "epoch": 205.7079646017699, "percentage": 29.31, "elapsed_time": "1:24:10", "remaining_time": "3:22:59", "throughput": 1319.25, "total_tokens": 6663000} {"current_steps": 11730, "total_steps": 40000, "loss": 0.0, "lr": 4.0121754254998076e-05, "epoch": 205.79646017699116, "percentage": 29.33, "elapsed_time": "1:24:12", "remaining_time": "3:22:57", "throughput": 1319.27, "total_tokens": 6665848} {"current_steps": 11735, "total_steps": 40000, "loss": 0.0, "lr": 4.011393519561606e-05, "epoch": 205.8849557522124, "percentage": 29.34, "elapsed_time": "1:24:14", "remaining_time": "3:22:54", "throughput": 1319.25, "total_tokens": 6668472} {"current_steps": 11740, "total_steps": 40000, "loss": 0.0, "lr": 4.010611380547529e-05, "epoch": 205.97345132743362, "percentage": 29.35, "elapsed_time": "1:24:16", "remaining_time": "3:22:52", "throughput": 1319.28, "total_tokens": 6671320} {"current_steps": 11745, "total_steps": 40000, "loss": 0.0, "lr": 4.009829008578192e-05, "epoch": 206.05309734513276, "percentage": 29.36, "elapsed_time": "1:24:19", "remaining_time": "3:22:50", "throughput": 1319.13, "total_tokens": 6673536} {"current_steps": 11750, "total_steps": 40000, "loss": 0.0, "lr": 4.00904640377425e-05, "epoch": 206.141592920354, "percentage": 29.38, "elapsed_time": "1:24:21", "remaining_time": "3:22:48", "throughput": 1319.13, "total_tokens": 6676256} {"current_steps": 11755, "total_steps": 40000, "loss": 0.0, "lr": 4.0082635662563886e-05, "epoch": 206.23008849557522, "percentage": 29.39, "elapsed_time": "1:24:23", "remaining_time": "3:22:45", "throughput": 1319.18, "total_tokens": 6679232} {"current_steps": 11760, "total_steps": 40000, "loss": 0.0, "lr": 4.007480496145331e-05, "epoch": 206.31858407079645, "percentage": 29.4, "elapsed_time": "1:24:25", "remaining_time": "3:22:43", "throughput": 1319.23, "total_tokens": 6682224} {"current_steps": 11765, "total_steps": 40000, "loss": 0.0, "lr": 4.006697193561837e-05, "epoch": 206.4070796460177, "percentage": 29.41, "elapsed_time": "1:24:27", "remaining_time": "3:22:41", "throughput": 1319.22, "total_tokens": 6684880} {"current_steps": 11770, "total_steps": 40000, "loss": 0.0, "lr": 4.005913658626701e-05, "epoch": 206.49557522123894, "percentage": 29.43, "elapsed_time": "1:24:29", "remaining_time": "3:22:38", "throughput": 1319.34, "total_tokens": 6688224} {"current_steps": 11775, "total_steps": 40000, "loss": 0.0, "lr": 4.005129891460754e-05, "epoch": 206.58407079646017, "percentage": 29.44, "elapsed_time": "1:24:31", "remaining_time": "3:22:36", "throughput": 1319.35, "total_tokens": 6691040} {"current_steps": 11780, "total_steps": 40000, "loss": 0.0, "lr": 4.004345892184864e-05, "epoch": 206.67256637168143, "percentage": 29.45, "elapsed_time": "1:24:33", "remaining_time": "3:22:34", "throughput": 1319.4, "total_tokens": 6694016} {"current_steps": 11785, "total_steps": 40000, "loss": 0.0, "lr": 4.003561660919932e-05, "epoch": 206.76106194690266, "percentage": 29.46, "elapsed_time": "1:24:35", "remaining_time": "3:22:31", "throughput": 1319.4, "total_tokens": 6696736} {"current_steps": 11790, "total_steps": 40000, "loss": 0.0, "lr": 4.002777197786897e-05, "epoch": 206.8495575221239, "percentage": 29.48, "elapsed_time": "1:24:37", "remaining_time": "3:22:29", "throughput": 1319.51, "total_tokens": 6700016} {"current_steps": 11795, "total_steps": 40000, "loss": 0.0, "lr": 4.0019925029067326e-05, "epoch": 206.93805309734512, "percentage": 29.49, "elapsed_time": "1:24:39", "remaining_time": "3:22:26", "throughput": 1319.48, "total_tokens": 6702592} {"current_steps": 11800, "total_steps": 40000, "loss": 0.0, "lr": 4.0012075764004495e-05, "epoch": 207.01769911504425, "percentage": 29.5, "elapsed_time": "1:24:41", "remaining_time": "3:22:25", "throughput": 1319.37, "total_tokens": 6704968} {"current_steps": 11800, "total_steps": 40000, "eval_loss": 0.45573821663856506, "epoch": 207.01769911504425, "percentage": 29.5, "elapsed_time": "1:24:43", "remaining_time": "3:22:27", "throughput": 1319.09, "total_tokens": 6704968} {"current_steps": 11805, "total_steps": 40000, "loss": 0.0, "lr": 4.000422418389094e-05, "epoch": 207.10619469026548, "percentage": 29.51, "elapsed_time": "1:24:46", "remaining_time": "3:22:29", "throughput": 1318.71, "total_tokens": 6708008} {"current_steps": 11810, "total_steps": 40000, "loss": 0.0, "lr": 3.999637028993744e-05, "epoch": 207.1946902654867, "percentage": 29.53, "elapsed_time": "1:24:48", "remaining_time": "3:22:26", "throughput": 1318.84, "total_tokens": 6711368} {"current_steps": 11815, "total_steps": 40000, "loss": 0.0, "lr": 3.99885140833552e-05, "epoch": 207.28318584070797, "percentage": 29.54, "elapsed_time": "1:24:50", "remaining_time": "3:22:24", "throughput": 1318.88, "total_tokens": 6714280} {"current_steps": 11820, "total_steps": 40000, "loss": 0.0, "lr": 3.998065556535572e-05, "epoch": 207.3716814159292, "percentage": 29.55, "elapsed_time": "1:24:52", "remaining_time": "3:22:22", "throughput": 1318.85, "total_tokens": 6716840} {"current_steps": 11825, "total_steps": 40000, "loss": 0.0, "lr": 3.9972794737150895e-05, "epoch": 207.46017699115043, "percentage": 29.56, "elapsed_time": "1:24:55", "remaining_time": "3:22:19", "throughput": 1318.79, "total_tokens": 6719288} {"current_steps": 11830, "total_steps": 40000, "loss": 0.0, "lr": 3.996493159995297e-05, "epoch": 207.5486725663717, "percentage": 29.58, "elapsed_time": "1:24:57", "remaining_time": "3:22:17", "throughput": 1318.89, "total_tokens": 6722488} {"current_steps": 11835, "total_steps": 40000, "loss": 0.0, "lr": 3.995706615497453e-05, "epoch": 207.63716814159292, "percentage": 29.59, "elapsed_time": "1:24:59", "remaining_time": "3:22:14", "throughput": 1318.94, "total_tokens": 6725464} {"current_steps": 11840, "total_steps": 40000, "loss": 0.0, "lr": 3.994919840342852e-05, "epoch": 207.72566371681415, "percentage": 29.6, "elapsed_time": "1:25:01", "remaining_time": "3:22:12", "throughput": 1318.97, "total_tokens": 6728376} {"current_steps": 11845, "total_steps": 40000, "loss": 0.0, "lr": 3.994132834652825e-05, "epoch": 207.81415929203538, "percentage": 29.61, "elapsed_time": "1:25:03", "remaining_time": "3:22:10", "throughput": 1318.92, "total_tokens": 6730856} {"current_steps": 11850, "total_steps": 40000, "loss": 0.0, "lr": 3.99334559854874e-05, "epoch": 207.90265486725664, "percentage": 29.62, "elapsed_time": "1:25:05", "remaining_time": "3:22:07", "throughput": 1318.93, "total_tokens": 6733608} {"current_steps": 11855, "total_steps": 40000, "loss": 0.0, "lr": 3.9925581321519955e-05, "epoch": 207.99115044247787, "percentage": 29.64, "elapsed_time": "1:25:07", "remaining_time": "3:22:05", "throughput": 1319.05, "total_tokens": 6736904} {"current_steps": 11860, "total_steps": 40000, "loss": 0.0, "lr": 3.991770435584031e-05, "epoch": 208.07079646017698, "percentage": 29.65, "elapsed_time": "1:25:09", "remaining_time": "3:22:03", "throughput": 1318.94, "total_tokens": 6739352} {"current_steps": 11865, "total_steps": 40000, "loss": 0.0, "lr": 3.990982508966319e-05, "epoch": 208.15929203539824, "percentage": 29.66, "elapsed_time": "1:25:11", "remaining_time": "3:22:01", "throughput": 1318.96, "total_tokens": 6742152} {"current_steps": 11870, "total_steps": 40000, "loss": 0.0, "lr": 3.990194352420367e-05, "epoch": 208.24778761061947, "percentage": 29.68, "elapsed_time": "1:25:13", "remaining_time": "3:21:58", "throughput": 1319.02, "total_tokens": 6745224} {"current_steps": 11875, "total_steps": 40000, "loss": 0.0, "lr": 3.9894059660677184e-05, "epoch": 208.3362831858407, "percentage": 29.69, "elapsed_time": "1:25:15", "remaining_time": "3:21:56", "throughput": 1319.07, "total_tokens": 6748200} {"current_steps": 11880, "total_steps": 40000, "loss": 0.0, "lr": 3.9886173500299526e-05, "epoch": 208.42477876106196, "percentage": 29.7, "elapsed_time": "1:25:17", "remaining_time": "3:21:54", "throughput": 1319.06, "total_tokens": 6750888} {"current_steps": 11885, "total_steps": 40000, "loss": 0.0, "lr": 3.987828504428685e-05, "epoch": 208.5132743362832, "percentage": 29.71, "elapsed_time": "1:25:20", "remaining_time": "3:21:51", "throughput": 1319.11, "total_tokens": 6753848} {"current_steps": 11890, "total_steps": 40000, "loss": 0.0, "lr": 3.987039429385565e-05, "epoch": 208.60176991150442, "percentage": 29.73, "elapsed_time": "1:25:22", "remaining_time": "3:21:49", "throughput": 1319.05, "total_tokens": 6756264} {"current_steps": 11895, "total_steps": 40000, "loss": 0.0, "lr": 3.986250125022277e-05, "epoch": 208.69026548672565, "percentage": 29.74, "elapsed_time": "1:25:24", "remaining_time": "3:21:47", "throughput": 1319.09, "total_tokens": 6759224} {"current_steps": 11900, "total_steps": 40000, "loss": 0.0, "lr": 3.985460591460544e-05, "epoch": 208.7787610619469, "percentage": 29.75, "elapsed_time": "1:25:26", "remaining_time": "3:21:44", "throughput": 1319.05, "total_tokens": 6761736} {"current_steps": 11905, "total_steps": 40000, "loss": 0.0, "lr": 3.984670828822118e-05, "epoch": 208.86725663716814, "percentage": 29.76, "elapsed_time": "1:25:28", "remaining_time": "3:21:42", "throughput": 1319.13, "total_tokens": 6764824} {"current_steps": 11910, "total_steps": 40000, "loss": 0.0, "lr": 3.983880837228794e-05, "epoch": 208.95575221238937, "percentage": 29.78, "elapsed_time": "1:25:30", "remaining_time": "3:21:40", "throughput": 1319.22, "total_tokens": 6768040} {"current_steps": 11915, "total_steps": 40000, "loss": 0.0, "lr": 3.983090616802396e-05, "epoch": 209.0353982300885, "percentage": 29.79, "elapsed_time": "1:25:32", "remaining_time": "3:21:38", "throughput": 1319.13, "total_tokens": 6770584} {"current_steps": 11920, "total_steps": 40000, "loss": 0.0, "lr": 3.982300167664788e-05, "epoch": 209.12389380530973, "percentage": 29.8, "elapsed_time": "1:25:34", "remaining_time": "3:21:35", "throughput": 1319.12, "total_tokens": 6773256} {"current_steps": 11925, "total_steps": 40000, "loss": 0.0, "lr": 3.981509489937868e-05, "epoch": 209.21238938053096, "percentage": 29.81, "elapsed_time": "1:25:36", "remaining_time": "3:21:33", "throughput": 1319.12, "total_tokens": 6775960} {"current_steps": 11930, "total_steps": 40000, "loss": 0.0, "lr": 3.9807185837435643e-05, "epoch": 209.30088495575222, "percentage": 29.83, "elapsed_time": "1:25:38", "remaining_time": "3:21:31", "throughput": 1319.15, "total_tokens": 6778840} {"current_steps": 11935, "total_steps": 40000, "loss": 0.0, "lr": 3.9799274492038484e-05, "epoch": 209.38938053097345, "percentage": 29.84, "elapsed_time": "1:25:40", "remaining_time": "3:21:28", "throughput": 1319.17, "total_tokens": 6781656} {"current_steps": 11940, "total_steps": 40000, "loss": 0.0, "lr": 3.979136086440722e-05, "epoch": 209.47787610619469, "percentage": 29.85, "elapsed_time": "1:25:42", "remaining_time": "3:21:26", "throughput": 1319.25, "total_tokens": 6784824} {"current_steps": 11945, "total_steps": 40000, "loss": 0.0, "lr": 3.9783444955762226e-05, "epoch": 209.56637168141592, "percentage": 29.86, "elapsed_time": "1:25:45", "remaining_time": "3:21:23", "throughput": 1319.26, "total_tokens": 6787592} {"current_steps": 11950, "total_steps": 40000, "loss": 0.0, "lr": 3.977552676732424e-05, "epoch": 209.65486725663717, "percentage": 29.88, "elapsed_time": "1:25:47", "remaining_time": "3:21:21", "throughput": 1319.31, "total_tokens": 6790600} {"current_steps": 11955, "total_steps": 40000, "loss": 0.0, "lr": 3.976760630031435e-05, "epoch": 209.7433628318584, "percentage": 29.89, "elapsed_time": "1:25:49", "remaining_time": "3:21:19", "throughput": 1319.26, "total_tokens": 6793096} {"current_steps": 11960, "total_steps": 40000, "loss": 0.0, "lr": 3.975968355595398e-05, "epoch": 209.83185840707964, "percentage": 29.9, "elapsed_time": "1:25:51", "remaining_time": "3:21:16", "throughput": 1319.45, "total_tokens": 6796776} {"current_steps": 11965, "total_steps": 40000, "loss": 0.0, "lr": 3.9751758535464935e-05, "epoch": 209.9203539823009, "percentage": 29.91, "elapsed_time": "1:25:53", "remaining_time": "3:21:14", "throughput": 1319.44, "total_tokens": 6799464} {"current_steps": 11970, "total_steps": 40000, "loss": 0.0, "lr": 3.9743831240069326e-05, "epoch": 210.0, "percentage": 29.93, "elapsed_time": "1:25:55", "remaining_time": "3:21:12", "throughput": 1319.43, "total_tokens": 6802096} {"current_steps": 11975, "total_steps": 40000, "loss": 0.0, "lr": 3.9735901670989675e-05, "epoch": 210.08849557522123, "percentage": 29.94, "elapsed_time": "1:25:57", "remaining_time": "3:21:10", "throughput": 1319.36, "total_tokens": 6804736} {"current_steps": 11980, "total_steps": 40000, "loss": 0.0, "lr": 3.97279698294488e-05, "epoch": 210.1769911504425, "percentage": 29.95, "elapsed_time": "1:25:59", "remaining_time": "3:21:08", "throughput": 1319.34, "total_tokens": 6807408} {"current_steps": 11985, "total_steps": 40000, "loss": 0.0, "lr": 3.9720035716669876e-05, "epoch": 210.26548672566372, "percentage": 29.96, "elapsed_time": "1:26:01", "remaining_time": "3:21:05", "throughput": 1319.39, "total_tokens": 6810368} {"current_steps": 11990, "total_steps": 40000, "loss": 0.0, "lr": 3.9712099333876474e-05, "epoch": 210.35398230088495, "percentage": 29.98, "elapsed_time": "1:26:03", "remaining_time": "3:21:03", "throughput": 1319.52, "total_tokens": 6813776} {"current_steps": 11995, "total_steps": 40000, "loss": 0.0, "lr": 3.9704160682292475e-05, "epoch": 210.44247787610618, "percentage": 29.99, "elapsed_time": "1:26:05", "remaining_time": "3:21:00", "throughput": 1319.51, "total_tokens": 6816432} {"current_steps": 12000, "total_steps": 40000, "loss": 0.0, "lr": 3.9696219763142106e-05, "epoch": 210.53097345132744, "percentage": 30.0, "elapsed_time": "1:26:07", "remaining_time": "3:20:58", "throughput": 1319.59, "total_tokens": 6819568} {"current_steps": 12000, "total_steps": 40000, "eval_loss": 0.44632595777511597, "epoch": 210.53097345132744, "percentage": 30.0, "elapsed_time": "1:26:09", "remaining_time": "3:21:01", "throughput": 1319.31, "total_tokens": 6819568} {"current_steps": 12005, "total_steps": 40000, "loss": 0.0, "lr": 3.968827657764997e-05, "epoch": 210.61946902654867, "percentage": 30.01, "elapsed_time": "1:26:12", "remaining_time": "3:21:02", "throughput": 1318.85, "total_tokens": 6822048} {"current_steps": 12010, "total_steps": 40000, "loss": 0.0, "lr": 3.9680331127041e-05, "epoch": 210.7079646017699, "percentage": 30.03, "elapsed_time": "1:26:14", "remaining_time": "3:21:00", "throughput": 1318.88, "total_tokens": 6824960} {"current_steps": 12015, "total_steps": 40000, "loss": 0.0, "lr": 3.9672383412540495e-05, "epoch": 210.79646017699116, "percentage": 30.04, "elapsed_time": "1:26:16", "remaining_time": "3:20:57", "throughput": 1318.91, "total_tokens": 6827856} {"current_steps": 12020, "total_steps": 40000, "loss": 0.0, "lr": 3.966443343537407e-05, "epoch": 210.8849557522124, "percentage": 30.05, "elapsed_time": "1:26:18", "remaining_time": "3:20:55", "throughput": 1318.99, "total_tokens": 6831024} {"current_steps": 12025, "total_steps": 40000, "loss": 0.0, "lr": 3.965648119676772e-05, "epoch": 210.97345132743362, "percentage": 30.06, "elapsed_time": "1:26:21", "remaining_time": "3:20:53", "throughput": 1319.04, "total_tokens": 6833952} {"current_steps": 12030, "total_steps": 40000, "loss": 0.0, "lr": 3.96485266979478e-05, "epoch": 211.05309734513276, "percentage": 30.08, "elapsed_time": "1:26:23", "remaining_time": "3:20:51", "throughput": 1318.86, "total_tokens": 6836016} {"current_steps": 12035, "total_steps": 40000, "loss": 0.0, "lr": 3.9640569940140974e-05, "epoch": 211.141592920354, "percentage": 30.09, "elapsed_time": "1:26:25", "remaining_time": "3:20:48", "throughput": 1318.81, "total_tokens": 6838512} {"current_steps": 12040, "total_steps": 40000, "loss": 0.0, "lr": 3.963261092457428e-05, "epoch": 211.23008849557522, "percentage": 30.1, "elapsed_time": "1:26:27", "remaining_time": "3:20:46", "throughput": 1318.84, "total_tokens": 6841424} {"current_steps": 12045, "total_steps": 40000, "loss": 0.0, "lr": 3.962464965247509e-05, "epoch": 211.31858407079645, "percentage": 30.11, "elapsed_time": "1:26:29", "remaining_time": "3:20:44", "throughput": 1318.91, "total_tokens": 6844480} {"current_steps": 12050, "total_steps": 40000, "loss": 0.0, "lr": 3.9616686125071135e-05, "epoch": 211.4070796460177, "percentage": 30.12, "elapsed_time": "1:26:31", "remaining_time": "3:20:41", "throughput": 1318.95, "total_tokens": 6847456} {"current_steps": 12055, "total_steps": 40000, "loss": 0.0, "lr": 3.9608720343590506e-05, "epoch": 211.49557522123894, "percentage": 30.14, "elapsed_time": "1:26:33", "remaining_time": "3:20:39", "throughput": 1318.94, "total_tokens": 6850112} {"current_steps": 12060, "total_steps": 40000, "loss": 0.0, "lr": 3.960075230926161e-05, "epoch": 211.58407079646017, "percentage": 30.15, "elapsed_time": "1:26:35", "remaining_time": "3:20:37", "throughput": 1318.99, "total_tokens": 6853136} {"current_steps": 12065, "total_steps": 40000, "loss": 0.0, "lr": 3.959278202331322e-05, "epoch": 211.67256637168143, "percentage": 30.16, "elapsed_time": "1:26:37", "remaining_time": "3:20:34", "throughput": 1319.07, "total_tokens": 6856240} {"current_steps": 12070, "total_steps": 40000, "loss": 0.0, "lr": 3.958480948697446e-05, "epoch": 211.76106194690266, "percentage": 30.18, "elapsed_time": "1:26:39", "remaining_time": "3:20:32", "throughput": 1319.1, "total_tokens": 6859168} {"current_steps": 12075, "total_steps": 40000, "loss": 0.0, "lr": 3.95768347014748e-05, "epoch": 211.8495575221239, "percentage": 30.19, "elapsed_time": "1:26:41", "remaining_time": "3:20:30", "throughput": 1319.17, "total_tokens": 6862240} {"current_steps": 12080, "total_steps": 40000, "loss": 0.0, "lr": 3.956885766804404e-05, "epoch": 211.93805309734512, "percentage": 30.2, "elapsed_time": "1:26:43", "remaining_time": "3:20:27", "throughput": 1319.25, "total_tokens": 6865344} {"current_steps": 12085, "total_steps": 40000, "loss": 0.0, "lr": 3.956087838791235e-05, "epoch": 212.01769911504425, "percentage": 30.21, "elapsed_time": "1:26:46", "remaining_time": "3:20:25", "throughput": 1319.22, "total_tokens": 6868176} {"current_steps": 12090, "total_steps": 40000, "loss": 0.0, "lr": 3.955289686231022e-05, "epoch": 212.10619469026548, "percentage": 30.23, "elapsed_time": "1:26:48", "remaining_time": "3:20:23", "throughput": 1319.29, "total_tokens": 6871296} {"current_steps": 12095, "total_steps": 40000, "loss": 0.0, "lr": 3.9544913092468504e-05, "epoch": 212.1946902654867, "percentage": 30.24, "elapsed_time": "1:26:50", "remaining_time": "3:20:21", "throughput": 1319.27, "total_tokens": 6873888} {"current_steps": 12100, "total_steps": 40000, "loss": 0.0, "lr": 3.9536927079618425e-05, "epoch": 212.28318584070797, "percentage": 30.25, "elapsed_time": "1:26:52", "remaining_time": "3:20:18", "throughput": 1319.31, "total_tokens": 6876848} {"current_steps": 12105, "total_steps": 40000, "loss": 0.0, "lr": 3.9528938824991494e-05, "epoch": 212.3716814159292, "percentage": 30.26, "elapsed_time": "1:26:54", "remaining_time": "3:20:16", "throughput": 1319.39, "total_tokens": 6880000} {"current_steps": 12110, "total_steps": 40000, "loss": 0.0, "lr": 3.952094832981962e-05, "epoch": 212.46017699115043, "percentage": 30.28, "elapsed_time": "1:26:56", "remaining_time": "3:20:14", "throughput": 1319.43, "total_tokens": 6882928} {"current_steps": 12115, "total_steps": 40000, "loss": 0.0, "lr": 3.951295559533503e-05, "epoch": 212.5486725663717, "percentage": 30.29, "elapsed_time": "1:26:58", "remaining_time": "3:20:11", "throughput": 1319.53, "total_tokens": 6886208} {"current_steps": 12120, "total_steps": 40000, "loss": 0.0, "lr": 3.95049606227703e-05, "epoch": 212.63716814159292, "percentage": 30.3, "elapsed_time": "1:27:01", "remaining_time": "3:20:10", "throughput": 1319.42, "total_tokens": 6888736} {"current_steps": 12125, "total_steps": 40000, "loss": 0.0, "lr": 3.949696341335838e-05, "epoch": 212.72566371681415, "percentage": 30.31, "elapsed_time": "1:27:03", "remaining_time": "3:20:07", "throughput": 1319.47, "total_tokens": 6891696} {"current_steps": 12130, "total_steps": 40000, "loss": 0.0, "lr": 3.9488963968332503e-05, "epoch": 212.81415929203538, "percentage": 30.33, "elapsed_time": "1:27:05", "remaining_time": "3:20:05", "throughput": 1319.43, "total_tokens": 6894224} {"current_steps": 12135, "total_steps": 40000, "loss": 0.0, "lr": 3.948096228892631e-05, "epoch": 212.90265486725664, "percentage": 30.34, "elapsed_time": "1:27:07", "remaining_time": "3:20:02", "throughput": 1319.39, "total_tokens": 6896720} {"current_steps": 12140, "total_steps": 40000, "loss": 0.0, "lr": 3.947295837637375e-05, "epoch": 212.99115044247787, "percentage": 30.35, "elapsed_time": "1:27:09", "remaining_time": "3:20:00", "throughput": 1319.39, "total_tokens": 6899408} {"current_steps": 12145, "total_steps": 40000, "loss": 0.0, "lr": 3.9464952231909135e-05, "epoch": 213.07079646017698, "percentage": 30.36, "elapsed_time": "1:27:11", "remaining_time": "3:19:58", "throughput": 1319.35, "total_tokens": 6902216} {"current_steps": 12150, "total_steps": 40000, "loss": 0.0, "lr": 3.945694385676711e-05, "epoch": 213.15929203539824, "percentage": 30.38, "elapsed_time": "1:27:13", "remaining_time": "3:19:56", "throughput": 1319.47, "total_tokens": 6905544} {"current_steps": 12155, "total_steps": 40000, "loss": 0.0, "lr": 3.944893325218265e-05, "epoch": 213.24778761061947, "percentage": 30.39, "elapsed_time": "1:27:15", "remaining_time": "3:19:54", "throughput": 1319.41, "total_tokens": 6907976} {"current_steps": 12160, "total_steps": 40000, "loss": 0.0, "lr": 3.944092041939112e-05, "epoch": 213.3362831858407, "percentage": 30.4, "elapsed_time": "1:27:17", "remaining_time": "3:19:51", "throughput": 1319.5, "total_tokens": 6911176} {"current_steps": 12165, "total_steps": 40000, "loss": 0.0, "lr": 3.943290535962818e-05, "epoch": 213.42477876106196, "percentage": 30.41, "elapsed_time": "1:27:19", "remaining_time": "3:19:49", "throughput": 1319.49, "total_tokens": 6913848} {"current_steps": 12170, "total_steps": 40000, "loss": 0.0, "lr": 3.942488807412985e-05, "epoch": 213.5132743362832, "percentage": 30.43, "elapsed_time": "1:27:21", "remaining_time": "3:19:46", "throughput": 1319.56, "total_tokens": 6916952} {"current_steps": 12175, "total_steps": 40000, "loss": 0.0, "lr": 3.941686856413251e-05, "epoch": 213.60176991150442, "percentage": 30.44, "elapsed_time": "1:27:23", "remaining_time": "3:19:44", "throughput": 1319.54, "total_tokens": 6919560} {"current_steps": 12180, "total_steps": 40000, "loss": 0.0, "lr": 3.9408846830872874e-05, "epoch": 213.69026548672565, "percentage": 30.45, "elapsed_time": "1:27:25", "remaining_time": "3:19:42", "throughput": 1319.57, "total_tokens": 6922472} {"current_steps": 12185, "total_steps": 40000, "loss": 0.0, "lr": 3.940082287558798e-05, "epoch": 213.7787610619469, "percentage": 30.46, "elapsed_time": "1:27:28", "remaining_time": "3:19:39", "throughput": 1319.64, "total_tokens": 6925528} {"current_steps": 12190, "total_steps": 40000, "loss": 0.0, "lr": 3.939279669951522e-05, "epoch": 213.86725663716814, "percentage": 30.48, "elapsed_time": "1:27:30", "remaining_time": "3:19:37", "throughput": 1319.6, "total_tokens": 6928072} {"current_steps": 12195, "total_steps": 40000, "loss": 0.0, "lr": 3.938476830389234e-05, "epoch": 213.95575221238937, "percentage": 30.49, "elapsed_time": "1:27:32", "remaining_time": "3:19:35", "throughput": 1319.57, "total_tokens": 6930616} {"current_steps": 12200, "total_steps": 40000, "loss": 0.0, "lr": 3.937673768995742e-05, "epoch": 214.0353982300885, "percentage": 30.5, "elapsed_time": "1:27:34", "remaining_time": "3:19:33", "throughput": 1319.51, "total_tokens": 6933264} {"current_steps": 12200, "total_steps": 40000, "eval_loss": 0.4518740773200989, "epoch": 214.0353982300885, "percentage": 30.5, "elapsed_time": "1:27:35", "remaining_time": "3:19:35", "throughput": 1319.24, "total_tokens": 6933264} {"current_steps": 12205, "total_steps": 40000, "loss": 0.0, "lr": 3.936870485894888e-05, "epoch": 214.12389380530973, "percentage": 30.51, "elapsed_time": "1:27:39", "remaining_time": "3:19:37", "throughput": 1318.79, "total_tokens": 6935952} {"current_steps": 12210, "total_steps": 40000, "loss": 0.0, "lr": 3.9360669812105475e-05, "epoch": 214.21238938053096, "percentage": 30.53, "elapsed_time": "1:27:41", "remaining_time": "3:19:35", "throughput": 1318.84, "total_tokens": 6938960} {"current_steps": 12215, "total_steps": 40000, "loss": 0.0, "lr": 3.9352632550666325e-05, "epoch": 214.30088495575222, "percentage": 30.54, "elapsed_time": "1:27:43", "remaining_time": "3:19:32", "throughput": 1318.89, "total_tokens": 6941936} {"current_steps": 12220, "total_steps": 40000, "loss": 0.0, "lr": 3.9344593075870866e-05, "epoch": 214.38938053097345, "percentage": 30.55, "elapsed_time": "1:27:45", "remaining_time": "3:19:30", "throughput": 1318.85, "total_tokens": 6944496} {"current_steps": 12225, "total_steps": 40000, "loss": 0.0, "lr": 3.933655138895889e-05, "epoch": 214.47787610619469, "percentage": 30.56, "elapsed_time": "1:27:47", "remaining_time": "3:19:27", "throughput": 1318.86, "total_tokens": 6947264} {"current_steps": 12230, "total_steps": 40000, "loss": 0.0, "lr": 3.932850749117053e-05, "epoch": 214.56637168141592, "percentage": 30.58, "elapsed_time": "1:27:49", "remaining_time": "3:19:25", "throughput": 1318.82, "total_tokens": 6949744} {"current_steps": 12235, "total_steps": 40000, "loss": 0.0, "lr": 3.932046138374624e-05, "epoch": 214.65486725663717, "percentage": 30.59, "elapsed_time": "1:27:51", "remaining_time": "3:19:23", "throughput": 1318.81, "total_tokens": 6952432} {"current_steps": 12240, "total_steps": 40000, "loss": 0.0, "lr": 3.9312413067926854e-05, "epoch": 214.7433628318584, "percentage": 30.6, "elapsed_time": "1:27:53", "remaining_time": "3:19:20", "throughput": 1318.78, "total_tokens": 6955008} {"current_steps": 12245, "total_steps": 40000, "loss": 0.0, "lr": 3.9304362544953506e-05, "epoch": 214.83185840707964, "percentage": 30.61, "elapsed_time": "1:27:55", "remaining_time": "3:19:18", "throughput": 1318.81, "total_tokens": 6957856} {"current_steps": 12250, "total_steps": 40000, "loss": 0.0, "lr": 3.929630981606769e-05, "epoch": 214.9203539823009, "percentage": 30.63, "elapsed_time": "1:27:57", "remaining_time": "3:19:16", "throughput": 1318.85, "total_tokens": 6960784} {"current_steps": 12255, "total_steps": 40000, "loss": 0.0, "lr": 3.928825488251124e-05, "epoch": 215.0, "percentage": 30.64, "elapsed_time": "1:27:59", "remaining_time": "3:19:13", "throughput": 1318.84, "total_tokens": 6963416} {"current_steps": 12260, "total_steps": 40000, "loss": 0.0, "lr": 3.9280197745526344e-05, "epoch": 215.08849557522123, "percentage": 30.65, "elapsed_time": "1:28:02", "remaining_time": "3:19:11", "throughput": 1318.8, "total_tokens": 6966216} {"current_steps": 12265, "total_steps": 40000, "loss": 0.0, "lr": 3.9272138406355495e-05, "epoch": 215.1769911504425, "percentage": 30.66, "elapsed_time": "1:28:04", "remaining_time": "3:19:09", "throughput": 1318.79, "total_tokens": 6968904} {"current_steps": 12270, "total_steps": 40000, "loss": 0.0, "lr": 3.926407686624154e-05, "epoch": 215.26548672566372, "percentage": 30.68, "elapsed_time": "1:28:06", "remaining_time": "3:19:07", "throughput": 1318.72, "total_tokens": 6971272} {"current_steps": 12275, "total_steps": 40000, "loss": 0.0, "lr": 3.9256013126427684e-05, "epoch": 215.35398230088495, "percentage": 30.69, "elapsed_time": "1:28:08", "remaining_time": "3:19:04", "throughput": 1318.72, "total_tokens": 6973976} {"current_steps": 12280, "total_steps": 40000, "loss": 0.0, "lr": 3.9247947188157455e-05, "epoch": 215.44247787610618, "percentage": 30.7, "elapsed_time": "1:28:10", "remaining_time": "3:19:02", "throughput": 1318.92, "total_tokens": 6977736} {"current_steps": 12285, "total_steps": 40000, "loss": 0.0, "lr": 3.9239879052674715e-05, "epoch": 215.53097345132744, "percentage": 30.71, "elapsed_time": "1:28:12", "remaining_time": "3:19:00", "throughput": 1319.01, "total_tokens": 6980936} {"current_steps": 12290, "total_steps": 40000, "loss": 0.0, "lr": 3.9231808721223673e-05, "epoch": 215.61946902654867, "percentage": 30.73, "elapsed_time": "1:28:14", "remaining_time": "3:18:57", "throughput": 1319.09, "total_tokens": 6984104} {"current_steps": 12295, "total_steps": 40000, "loss": 0.0, "lr": 3.9223736195048886e-05, "epoch": 215.7079646017699, "percentage": 30.74, "elapsed_time": "1:28:16", "remaining_time": "3:18:55", "throughput": 1319.06, "total_tokens": 6986696} {"current_steps": 12300, "total_steps": 40000, "loss": 0.0, "lr": 3.921566147539523e-05, "epoch": 215.79646017699116, "percentage": 30.75, "elapsed_time": "1:28:18", "remaining_time": "3:18:53", "throughput": 1319.08, "total_tokens": 6989560} {"current_steps": 12305, "total_steps": 40000, "loss": 0.0, "lr": 3.920758456350792e-05, "epoch": 215.8849557522124, "percentage": 30.76, "elapsed_time": "1:28:20", "remaining_time": "3:18:50", "throughput": 1319.09, "total_tokens": 6992344} {"current_steps": 12310, "total_steps": 40000, "loss": 0.0, "lr": 3.919950546063253e-05, "epoch": 215.97345132743362, "percentage": 30.78, "elapsed_time": "1:28:22", "remaining_time": "3:18:48", "throughput": 1319.1, "total_tokens": 6995064} {"current_steps": 12315, "total_steps": 40000, "loss": 0.0, "lr": 3.919142416801496e-05, "epoch": 216.05309734513276, "percentage": 30.79, "elapsed_time": "1:28:25", "remaining_time": "3:18:46", "throughput": 1318.98, "total_tokens": 6997408} {"current_steps": 12320, "total_steps": 40000, "loss": 0.0, "lr": 3.918334068690144e-05, "epoch": 216.141592920354, "percentage": 30.8, "elapsed_time": "1:28:27", "remaining_time": "3:18:44", "throughput": 1319.0, "total_tokens": 7000240} {"current_steps": 12325, "total_steps": 40000, "loss": 0.0, "lr": 3.917525501853855e-05, "epoch": 216.23008849557522, "percentage": 30.81, "elapsed_time": "1:28:29", "remaining_time": "3:18:41", "throughput": 1319.0, "total_tokens": 7002960} {"current_steps": 12330, "total_steps": 40000, "loss": 0.0, "lr": 3.916716716417319e-05, "epoch": 216.31858407079645, "percentage": 30.83, "elapsed_time": "1:28:31", "remaining_time": "3:18:39", "throughput": 1319.02, "total_tokens": 7005824} {"current_steps": 12335, "total_steps": 40000, "loss": 0.0, "lr": 3.915907712505263e-05, "epoch": 216.4070796460177, "percentage": 30.84, "elapsed_time": "1:28:33", "remaining_time": "3:18:37", "throughput": 1319.03, "total_tokens": 7008576} {"current_steps": 12340, "total_steps": 40000, "loss": 0.0, "lr": 3.915098490242444e-05, "epoch": 216.49557522123894, "percentage": 30.85, "elapsed_time": "1:28:35", "remaining_time": "3:18:34", "throughput": 1319.04, "total_tokens": 7011344} {"current_steps": 12345, "total_steps": 40000, "loss": 0.0, "lr": 3.914289049753654e-05, "epoch": 216.58407079646017, "percentage": 30.86, "elapsed_time": "1:28:37", "remaining_time": "3:18:32", "throughput": 1319.1, "total_tokens": 7014416} {"current_steps": 12350, "total_steps": 40000, "loss": 0.0, "lr": 3.913479391163719e-05, "epoch": 216.67256637168143, "percentage": 30.88, "elapsed_time": "1:28:39", "remaining_time": "3:18:29", "throughput": 1319.14, "total_tokens": 7017344} {"current_steps": 12355, "total_steps": 40000, "loss": 0.0, "lr": 3.9126695145975e-05, "epoch": 216.76106194690266, "percentage": 30.89, "elapsed_time": "1:28:41", "remaining_time": "3:18:27", "throughput": 1319.2, "total_tokens": 7020400} {"current_steps": 12360, "total_steps": 40000, "loss": 0.0, "lr": 3.911859420179889e-05, "epoch": 216.8495575221239, "percentage": 30.9, "elapsed_time": "1:28:43", "remaining_time": "3:18:25", "throughput": 1319.28, "total_tokens": 7023536} {"current_steps": 12365, "total_steps": 40000, "loss": 0.0, "lr": 3.911049108035813e-05, "epoch": 216.93805309734512, "percentage": 30.91, "elapsed_time": "1:28:45", "remaining_time": "3:18:22", "throughput": 1319.26, "total_tokens": 7026192} {"current_steps": 12370, "total_steps": 40000, "loss": 0.0, "lr": 3.910238578290232e-05, "epoch": 217.01769911504425, "percentage": 30.93, "elapsed_time": "1:28:48", "remaining_time": "3:18:20", "throughput": 1319.17, "total_tokens": 7028648} {"current_steps": 12375, "total_steps": 40000, "loss": 0.0, "lr": 3.90942783106814e-05, "epoch": 217.10619469026548, "percentage": 30.94, "elapsed_time": "1:28:50", "remaining_time": "3:18:18", "throughput": 1319.15, "total_tokens": 7031272} {"current_steps": 12380, "total_steps": 40000, "loss": 0.0, "lr": 3.908616866494564e-05, "epoch": 217.1946902654867, "percentage": 30.95, "elapsed_time": "1:28:52", "remaining_time": "3:18:16", "throughput": 1319.14, "total_tokens": 7033928} {"current_steps": 12385, "total_steps": 40000, "loss": 0.0, "lr": 3.907805684694566e-05, "epoch": 217.28318584070797, "percentage": 30.96, "elapsed_time": "1:28:54", "remaining_time": "3:18:13", "throughput": 1319.2, "total_tokens": 7036984} {"current_steps": 12390, "total_steps": 40000, "loss": 0.0, "lr": 3.90699428579324e-05, "epoch": 217.3716814159292, "percentage": 30.98, "elapsed_time": "1:28:56", "remaining_time": "3:18:11", "throughput": 1319.16, "total_tokens": 7039480} {"current_steps": 12395, "total_steps": 40000, "loss": 0.0, "lr": 3.906182669915713e-05, "epoch": 217.46017699115043, "percentage": 30.99, "elapsed_time": "1:28:58", "remaining_time": "3:18:09", "throughput": 1319.22, "total_tokens": 7042536} {"current_steps": 12400, "total_steps": 40000, "loss": 0.0, "lr": 3.9053708371871476e-05, "epoch": 217.5486725663717, "percentage": 31.0, "elapsed_time": "1:29:00", "remaining_time": "3:18:06", "throughput": 1319.3, "total_tokens": 7045688} {"current_steps": 12400, "total_steps": 40000, "eval_loss": 0.45370200276374817, "epoch": 217.5486725663717, "percentage": 31.0, "elapsed_time": "1:29:01", "remaining_time": "3:18:09", "throughput": 1319.03, "total_tokens": 7045688} {"current_steps": 12405, "total_steps": 40000, "loss": 0.0, "lr": 3.904558787732738e-05, "epoch": 217.63716814159292, "percentage": 31.01, "elapsed_time": "1:29:05", "remaining_time": "3:18:11", "throughput": 1318.56, "total_tokens": 7048344} {"current_steps": 12410, "total_steps": 40000, "loss": 0.0, "lr": 3.9037465216777135e-05, "epoch": 217.72566371681415, "percentage": 31.03, "elapsed_time": "1:29:07", "remaining_time": "3:18:08", "throughput": 1318.64, "total_tokens": 7051480} {"current_steps": 12415, "total_steps": 40000, "loss": 0.0, "lr": 3.902934039147334e-05, "epoch": 217.81415929203538, "percentage": 31.04, "elapsed_time": "1:29:09", "remaining_time": "3:18:06", "throughput": 1318.65, "total_tokens": 7054264} {"current_steps": 12420, "total_steps": 40000, "loss": 0.0, "lr": 3.902121340266894e-05, "epoch": 217.90265486725664, "percentage": 31.05, "elapsed_time": "1:29:11", "remaining_time": "3:18:04", "throughput": 1318.7, "total_tokens": 7057272} {"current_steps": 12425, "total_steps": 40000, "loss": 0.0, "lr": 3.9013084251617246e-05, "epoch": 217.99115044247787, "percentage": 31.06, "elapsed_time": "1:29:13", "remaining_time": "3:18:01", "throughput": 1318.72, "total_tokens": 7060104} {"current_steps": 12430, "total_steps": 40000, "loss": 0.0, "lr": 3.9004952939571865e-05, "epoch": 218.07079646017698, "percentage": 31.08, "elapsed_time": "1:29:16", "remaining_time": "3:17:59", "throughput": 1318.65, "total_tokens": 7062728} {"current_steps": 12435, "total_steps": 40000, "loss": 0.0, "lr": 3.899681946778673e-05, "epoch": 218.15929203539824, "percentage": 31.09, "elapsed_time": "1:29:18", "remaining_time": "3:17:57", "throughput": 1318.64, "total_tokens": 7065416} {"current_steps": 12440, "total_steps": 40000, "loss": 0.0, "lr": 3.898868383751615e-05, "epoch": 218.24778761061947, "percentage": 31.1, "elapsed_time": "1:29:20", "remaining_time": "3:17:55", "throughput": 1318.65, "total_tokens": 7068200} {"current_steps": 12445, "total_steps": 40000, "loss": 0.0, "lr": 3.8980546050014724e-05, "epoch": 218.3362831858407, "percentage": 31.11, "elapsed_time": "1:29:22", "remaining_time": "3:17:52", "throughput": 1318.66, "total_tokens": 7070984} {"current_steps": 12450, "total_steps": 40000, "loss": 0.0, "lr": 3.897240610653741e-05, "epoch": 218.42477876106196, "percentage": 31.13, "elapsed_time": "1:29:24", "remaining_time": "3:17:50", "throughput": 1318.78, "total_tokens": 7074312} {"current_steps": 12455, "total_steps": 40000, "loss": 0.0, "lr": 3.896426400833948e-05, "epoch": 218.5132743362832, "percentage": 31.14, "elapsed_time": "1:29:26", "remaining_time": "3:17:48", "throughput": 1318.78, "total_tokens": 7077048} {"current_steps": 12460, "total_steps": 40000, "loss": 0.0, "lr": 3.895611975667656e-05, "epoch": 218.60176991150442, "percentage": 31.15, "elapsed_time": "1:29:28", "remaining_time": "3:17:45", "throughput": 1318.78, "total_tokens": 7079784} {"current_steps": 12465, "total_steps": 40000, "loss": 0.0, "lr": 3.8947973352804584e-05, "epoch": 218.69026548672565, "percentage": 31.16, "elapsed_time": "1:29:30", "remaining_time": "3:17:43", "throughput": 1318.89, "total_tokens": 7083080} {"current_steps": 12470, "total_steps": 40000, "loss": 0.0, "lr": 3.893982479797984e-05, "epoch": 218.7787610619469, "percentage": 31.18, "elapsed_time": "1:29:32", "remaining_time": "3:17:40", "throughput": 1318.9, "total_tokens": 7085848} {"current_steps": 12475, "total_steps": 40000, "loss": 0.0, "lr": 3.8931674093458926e-05, "epoch": 218.86725663716814, "percentage": 31.19, "elapsed_time": "1:29:34", "remaining_time": "3:17:38", "throughput": 1318.93, "total_tokens": 7088760} {"current_steps": 12480, "total_steps": 40000, "loss": 0.0, "lr": 3.89235212404988e-05, "epoch": 218.95575221238937, "percentage": 31.2, "elapsed_time": "1:29:36", "remaining_time": "3:17:36", "throughput": 1319.0, "total_tokens": 7091816} {"current_steps": 12485, "total_steps": 40000, "loss": 0.0, "lr": 3.891536624035672e-05, "epoch": 219.0353982300885, "percentage": 31.21, "elapsed_time": "1:29:38", "remaining_time": "3:17:34", "throughput": 1318.93, "total_tokens": 7094424} {"current_steps": 12490, "total_steps": 40000, "loss": 0.0, "lr": 3.8907209094290295e-05, "epoch": 219.12389380530973, "percentage": 31.23, "elapsed_time": "1:29:40", "remaining_time": "3:17:31", "throughput": 1318.94, "total_tokens": 7097208} {"current_steps": 12495, "total_steps": 40000, "loss": 0.0, "lr": 3.8899049803557466e-05, "epoch": 219.21238938053096, "percentage": 31.24, "elapsed_time": "1:29:43", "remaining_time": "3:17:29", "throughput": 1319.02, "total_tokens": 7100344} {"current_steps": 12500, "total_steps": 40000, "loss": 0.0, "lr": 3.889088836941648e-05, "epoch": 219.30088495575222, "percentage": 31.25, "elapsed_time": "1:29:45", "remaining_time": "3:17:27", "throughput": 1319.06, "total_tokens": 7103320} {"current_steps": 12505, "total_steps": 40000, "loss": 0.0, "lr": 3.8882724793125946e-05, "epoch": 219.38938053097345, "percentage": 31.26, "elapsed_time": "1:29:47", "remaining_time": "3:17:24", "throughput": 1319.09, "total_tokens": 7106216} {"current_steps": 12510, "total_steps": 40000, "loss": 0.0, "lr": 3.8874559075944794e-05, "epoch": 219.47787610619469, "percentage": 31.27, "elapsed_time": "1:29:49", "remaining_time": "3:17:22", "throughput": 1319.12, "total_tokens": 7109080} {"current_steps": 12515, "total_steps": 40000, "loss": 0.0, "lr": 3.886639121913227e-05, "epoch": 219.56637168141592, "percentage": 31.29, "elapsed_time": "1:29:51", "remaining_time": "3:17:20", "throughput": 1319.19, "total_tokens": 7112168} {"current_steps": 12520, "total_steps": 40000, "loss": 0.0, "lr": 3.885822122394797e-05, "epoch": 219.65486725663717, "percentage": 31.3, "elapsed_time": "1:29:53", "remaining_time": "3:17:17", "throughput": 1319.23, "total_tokens": 7115144} {"current_steps": 12525, "total_steps": 40000, "loss": 0.0, "lr": 3.8850049091651794e-05, "epoch": 219.7433628318584, "percentage": 31.31, "elapsed_time": "1:29:55", "remaining_time": "3:17:15", "throughput": 1319.23, "total_tokens": 7117848} {"current_steps": 12530, "total_steps": 40000, "loss": 0.0, "lr": 3.8841874823504e-05, "epoch": 219.83185840707964, "percentage": 31.32, "elapsed_time": "1:29:57", "remaining_time": "3:17:13", "throughput": 1319.25, "total_tokens": 7120664} {"current_steps": 12535, "total_steps": 40000, "loss": 0.0, "lr": 3.8833698420765157e-05, "epoch": 219.9203539823009, "percentage": 31.34, "elapsed_time": "1:29:59", "remaining_time": "3:17:10", "throughput": 1319.21, "total_tokens": 7123208} {"current_steps": 12540, "total_steps": 40000, "loss": 0.0, "lr": 3.882551988469618e-05, "epoch": 220.0, "percentage": 31.35, "elapsed_time": "1:30:01", "remaining_time": "3:17:08", "throughput": 1319.15, "total_tokens": 7125552} {"current_steps": 12545, "total_steps": 40000, "loss": 0.0, "lr": 3.881733921655829e-05, "epoch": 220.08849557522123, "percentage": 31.36, "elapsed_time": "1:30:03", "remaining_time": "3:17:06", "throughput": 1319.11, "total_tokens": 7128336} {"current_steps": 12550, "total_steps": 40000, "loss": 0.0, "lr": 3.8809156417613054e-05, "epoch": 220.1769911504425, "percentage": 31.37, "elapsed_time": "1:30:05", "remaining_time": "3:17:04", "throughput": 1319.11, "total_tokens": 7131072} {"current_steps": 12555, "total_steps": 40000, "loss": 0.0, "lr": 3.8800971489122364e-05, "epoch": 220.26548672566372, "percentage": 31.39, "elapsed_time": "1:30:08", "remaining_time": "3:17:01", "throughput": 1319.11, "total_tokens": 7133808} {"current_steps": 12560, "total_steps": 40000, "loss": 0.0, "lr": 3.8792784432348434e-05, "epoch": 220.35398230088495, "percentage": 31.4, "elapsed_time": "1:30:10", "remaining_time": "3:16:59", "throughput": 1319.29, "total_tokens": 7137520} {"current_steps": 12565, "total_steps": 40000, "loss": 0.0, "lr": 3.878459524855381e-05, "epoch": 220.44247787610618, "percentage": 31.41, "elapsed_time": "1:30:12", "remaining_time": "3:16:57", "throughput": 1319.34, "total_tokens": 7140544} {"current_steps": 12570, "total_steps": 40000, "loss": 0.0, "lr": 3.8776403939001384e-05, "epoch": 220.53097345132744, "percentage": 31.42, "elapsed_time": "1:30:14", "remaining_time": "3:16:54", "throughput": 1319.33, "total_tokens": 7143216} {"current_steps": 12575, "total_steps": 40000, "loss": 0.0, "lr": 3.876821050495433e-05, "epoch": 220.61946902654867, "percentage": 31.44, "elapsed_time": "1:30:16", "remaining_time": "3:16:52", "throughput": 1319.36, "total_tokens": 7146096} {"current_steps": 12580, "total_steps": 40000, "loss": 0.0, "lr": 3.87600149476762e-05, "epoch": 220.7079646017699, "percentage": 31.45, "elapsed_time": "1:30:18", "remaining_time": "3:16:50", "throughput": 1319.42, "total_tokens": 7149184} {"current_steps": 12585, "total_steps": 40000, "loss": 0.0, "lr": 3.8751817268430843e-05, "epoch": 220.79646017699116, "percentage": 31.46, "elapsed_time": "1:30:20", "remaining_time": "3:16:47", "throughput": 1319.47, "total_tokens": 7152144} {"current_steps": 12590, "total_steps": 40000, "loss": 0.0, "lr": 3.8743617468482464e-05, "epoch": 220.8849557522124, "percentage": 31.47, "elapsed_time": "1:30:22", "remaining_time": "3:16:45", "throughput": 1319.44, "total_tokens": 7154704} {"current_steps": 12595, "total_steps": 40000, "loss": 0.0, "lr": 3.8735415549095535e-05, "epoch": 220.97345132743362, "percentage": 31.49, "elapsed_time": "1:30:24", "remaining_time": "3:16:43", "throughput": 1319.47, "total_tokens": 7157568} {"current_steps": 12600, "total_steps": 40000, "loss": 0.0, "lr": 3.8727211511534934e-05, "epoch": 221.05309734513276, "percentage": 31.5, "elapsed_time": "1:30:26", "remaining_time": "3:16:41", "throughput": 1319.34, "total_tokens": 7159888} {"current_steps": 12600, "total_steps": 40000, "eval_loss": 0.4610222280025482, "epoch": 221.05309734513276, "percentage": 31.5, "elapsed_time": "1:30:27", "remaining_time": "3:16:43", "throughput": 1319.08, "total_tokens": 7159888} {"current_steps": 12605, "total_steps": 40000, "loss": 0.0, "lr": 3.8719005357065804e-05, "epoch": 221.141592920354, "percentage": 31.51, "elapsed_time": "1:30:31", "remaining_time": "3:16:44", "throughput": 1318.7, "total_tokens": 7162768} {"current_steps": 12610, "total_steps": 40000, "loss": 0.0, "lr": 3.8710797086953645e-05, "epoch": 221.23008849557522, "percentage": 31.52, "elapsed_time": "1:30:33", "remaining_time": "3:16:42", "throughput": 1318.75, "total_tokens": 7165776} {"current_steps": 12615, "total_steps": 40000, "loss": 0.0, "lr": 3.870258670246427e-05, "epoch": 221.31858407079645, "percentage": 31.54, "elapsed_time": "1:30:35", "remaining_time": "3:16:40", "throughput": 1318.78, "total_tokens": 7168688} {"current_steps": 12620, "total_steps": 40000, "loss": 0.0, "lr": 3.869437420486384e-05, "epoch": 221.4070796460177, "percentage": 31.55, "elapsed_time": "1:30:37", "remaining_time": "3:16:37", "throughput": 1318.82, "total_tokens": 7171600} {"current_steps": 12625, "total_steps": 40000, "loss": 0.0, "lr": 3.8686159595418805e-05, "epoch": 221.49557522123894, "percentage": 31.56, "elapsed_time": "1:30:39", "remaining_time": "3:16:35", "throughput": 1318.88, "total_tokens": 7174656} {"current_steps": 12630, "total_steps": 40000, "loss": 0.0, "lr": 3.867794287539597e-05, "epoch": 221.58407079646017, "percentage": 31.57, "elapsed_time": "1:30:42", "remaining_time": "3:16:33", "throughput": 1318.93, "total_tokens": 7177648} {"current_steps": 12635, "total_steps": 40000, "loss": 0.0, "lr": 3.866972404606245e-05, "epoch": 221.67256637168143, "percentage": 31.59, "elapsed_time": "1:30:44", "remaining_time": "3:16:30", "throughput": 1318.9, "total_tokens": 7180208} {"current_steps": 12640, "total_steps": 40000, "loss": 0.0, "lr": 3.866150310868571e-05, "epoch": 221.76106194690266, "percentage": 31.6, "elapsed_time": "1:30:46", "remaining_time": "3:16:28", "throughput": 1319.0, "total_tokens": 7183504} {"current_steps": 12645, "total_steps": 40000, "loss": 0.0, "lr": 3.8653280064533506e-05, "epoch": 221.8495575221239, "percentage": 31.61, "elapsed_time": "1:30:48", "remaining_time": "3:16:26", "throughput": 1319.05, "total_tokens": 7186512} {"current_steps": 12650, "total_steps": 40000, "loss": 0.0, "lr": 3.864505491487394e-05, "epoch": 221.93805309734512, "percentage": 31.62, "elapsed_time": "1:30:50", "remaining_time": "3:16:23", "throughput": 1319.0, "total_tokens": 7188912} {"current_steps": 12655, "total_steps": 40000, "loss": 0.0, "lr": 3.8636827660975414e-05, "epoch": 222.01769911504425, "percentage": 31.64, "elapsed_time": "1:30:52", "remaining_time": "3:16:21", "throughput": 1318.93, "total_tokens": 7191504} {"current_steps": 12660, "total_steps": 40000, "loss": 0.0, "lr": 3.862859830410671e-05, "epoch": 222.10619469026548, "percentage": 31.65, "elapsed_time": "1:30:54", "remaining_time": "3:16:19", "throughput": 1318.96, "total_tokens": 7194384} {"current_steps": 12665, "total_steps": 40000, "loss": 0.0, "lr": 3.862036684553688e-05, "epoch": 222.1946902654867, "percentage": 31.66, "elapsed_time": "1:30:56", "remaining_time": "3:16:17", "throughput": 1318.93, "total_tokens": 7196960} {"current_steps": 12670, "total_steps": 40000, "loss": 0.0, "lr": 3.8612133286535314e-05, "epoch": 222.28318584070797, "percentage": 31.67, "elapsed_time": "1:30:58", "remaining_time": "3:16:14", "throughput": 1319.02, "total_tokens": 7200176} {"current_steps": 12675, "total_steps": 40000, "loss": 0.0, "lr": 3.860389762837173e-05, "epoch": 222.3716814159292, "percentage": 31.69, "elapsed_time": "1:31:00", "remaining_time": "3:16:12", "throughput": 1319.11, "total_tokens": 7203392} {"current_steps": 12680, "total_steps": 40000, "loss": 0.0, "lr": 3.859565987231618e-05, "epoch": 222.46017699115043, "percentage": 31.7, "elapsed_time": "1:31:02", "remaining_time": "3:16:10", "throughput": 1319.16, "total_tokens": 7206432} {"current_steps": 12685, "total_steps": 40000, "loss": 0.0, "lr": 3.858742001963902e-05, "epoch": 222.5486725663717, "percentage": 31.71, "elapsed_time": "1:31:04", "remaining_time": "3:16:07", "throughput": 1319.18, "total_tokens": 7209296} {"current_steps": 12690, "total_steps": 40000, "loss": 0.0, "lr": 3.857917807161094e-05, "epoch": 222.63716814159292, "percentage": 31.72, "elapsed_time": "1:31:07", "remaining_time": "3:16:05", "throughput": 1319.24, "total_tokens": 7212336} {"current_steps": 12695, "total_steps": 40000, "loss": 0.0, "lr": 3.857093402950296e-05, "epoch": 222.72566371681415, "percentage": 31.74, "elapsed_time": "1:31:09", "remaining_time": "3:16:03", "throughput": 1319.23, "total_tokens": 7214960} {"current_steps": 12700, "total_steps": 40000, "loss": 0.0, "lr": 3.8562687894586414e-05, "epoch": 222.81415929203538, "percentage": 31.75, "elapsed_time": "1:31:11", "remaining_time": "3:16:00", "throughput": 1319.2, "total_tokens": 7217520} {"current_steps": 12705, "total_steps": 40000, "loss": 0.0, "lr": 3.8554439668132946e-05, "epoch": 222.90265486725664, "percentage": 31.76, "elapsed_time": "1:31:13", "remaining_time": "3:15:58", "throughput": 1319.25, "total_tokens": 7220528} {"current_steps": 12710, "total_steps": 40000, "loss": 0.0, "lr": 3.854618935141455e-05, "epoch": 222.99115044247787, "percentage": 31.77, "elapsed_time": "1:31:15", "remaining_time": "3:15:56", "throughput": 1319.23, "total_tokens": 7223104} {"current_steps": 12715, "total_steps": 40000, "loss": 0.0, "lr": 3.8537936945703525e-05, "epoch": 223.07079646017698, "percentage": 31.79, "elapsed_time": "1:31:17", "remaining_time": "3:15:54", "throughput": 1319.13, "total_tokens": 7225568} {"current_steps": 12720, "total_steps": 40000, "loss": 0.0, "lr": 3.852968245227249e-05, "epoch": 223.15929203539824, "percentage": 31.8, "elapsed_time": "1:31:19", "remaining_time": "3:15:51", "throughput": 1319.16, "total_tokens": 7228464} {"current_steps": 12725, "total_steps": 40000, "loss": 0.0, "lr": 3.85214258723944e-05, "epoch": 223.24778761061947, "percentage": 31.81, "elapsed_time": "1:31:21", "remaining_time": "3:15:49", "throughput": 1319.13, "total_tokens": 7231024} {"current_steps": 12730, "total_steps": 40000, "loss": 0.0, "lr": 3.8513167207342524e-05, "epoch": 223.3362831858407, "percentage": 31.82, "elapsed_time": "1:31:23", "remaining_time": "3:15:47", "throughput": 1319.13, "total_tokens": 7233744} {"current_steps": 12735, "total_steps": 40000, "loss": 0.0, "lr": 3.850490645839044e-05, "epoch": 223.42477876106196, "percentage": 31.84, "elapsed_time": "1:31:25", "remaining_time": "3:15:44", "throughput": 1319.25, "total_tokens": 7237136} {"current_steps": 12740, "total_steps": 40000, "loss": 0.0, "lr": 3.849664362681207e-05, "epoch": 223.5132743362832, "percentage": 31.85, "elapsed_time": "1:31:27", "remaining_time": "3:15:42", "throughput": 1319.33, "total_tokens": 7240288} {"current_steps": 12745, "total_steps": 40000, "loss": 0.0, "lr": 3.848837871388165e-05, "epoch": 223.60176991150442, "percentage": 31.86, "elapsed_time": "1:31:29", "remaining_time": "3:15:40", "throughput": 1319.36, "total_tokens": 7243232} {"current_steps": 12750, "total_steps": 40000, "loss": 0.0, "lr": 3.848011172087371e-05, "epoch": 223.69026548672565, "percentage": 31.87, "elapsed_time": "1:31:32", "remaining_time": "3:15:37", "throughput": 1319.39, "total_tokens": 7246096} {"current_steps": 12755, "total_steps": 40000, "loss": 0.0, "lr": 3.847184264906315e-05, "epoch": 223.7787610619469, "percentage": 31.89, "elapsed_time": "1:31:34", "remaining_time": "3:15:35", "throughput": 1319.45, "total_tokens": 7249152} {"current_steps": 12760, "total_steps": 40000, "loss": 0.0, "lr": 3.846357149972516e-05, "epoch": 223.86725663716814, "percentage": 31.9, "elapsed_time": "1:31:36", "remaining_time": "3:15:33", "throughput": 1319.48, "total_tokens": 7252032} {"current_steps": 12765, "total_steps": 40000, "loss": 0.0, "lr": 3.8455298274135246e-05, "epoch": 223.95575221238937, "percentage": 31.91, "elapsed_time": "1:31:38", "remaining_time": "3:15:30", "throughput": 1319.41, "total_tokens": 7254384} {"current_steps": 12770, "total_steps": 40000, "loss": 0.0, "lr": 3.8447022973569254e-05, "epoch": 224.0353982300885, "percentage": 31.92, "elapsed_time": "1:31:40", "remaining_time": "3:15:28", "throughput": 1319.31, "total_tokens": 7256824} {"current_steps": 12775, "total_steps": 40000, "loss": 0.0, "lr": 3.843874559930332e-05, "epoch": 224.12389380530973, "percentage": 31.94, "elapsed_time": "1:31:42", "remaining_time": "3:15:26", "throughput": 1319.42, "total_tokens": 7260104} {"current_steps": 12780, "total_steps": 40000, "loss": 0.0, "lr": 3.843046615261394e-05, "epoch": 224.21238938053096, "percentage": 31.95, "elapsed_time": "1:31:44", "remaining_time": "3:15:24", "throughput": 1319.47, "total_tokens": 7263144} {"current_steps": 12785, "total_steps": 40000, "loss": 0.0, "lr": 3.842218463477791e-05, "epoch": 224.30088495575222, "percentage": 31.96, "elapsed_time": "1:31:46", "remaining_time": "3:15:21", "throughput": 1319.52, "total_tokens": 7266136} {"current_steps": 12790, "total_steps": 40000, "loss": 0.0, "lr": 3.841390104707233e-05, "epoch": 224.38938053097345, "percentage": 31.97, "elapsed_time": "1:31:48", "remaining_time": "3:15:19", "throughput": 1319.54, "total_tokens": 7268968} {"current_steps": 12795, "total_steps": 40000, "loss": 0.0, "lr": 3.8405615390774643e-05, "epoch": 224.47787610619469, "percentage": 31.99, "elapsed_time": "1:31:50", "remaining_time": "3:15:17", "throughput": 1319.5, "total_tokens": 7271496} {"current_steps": 12800, "total_steps": 40000, "loss": 0.0, "lr": 3.839732766716259e-05, "epoch": 224.56637168141592, "percentage": 32.0, "elapsed_time": "1:31:52", "remaining_time": "3:15:14", "throughput": 1319.52, "total_tokens": 7274296} {"current_steps": 12800, "total_steps": 40000, "eval_loss": 0.4564047157764435, "epoch": 224.56637168141592, "percentage": 32.0, "elapsed_time": "1:31:53", "remaining_time": "3:15:17", "throughput": 1319.26, "total_tokens": 7274296} {"current_steps": 12805, "total_steps": 40000, "loss": 0.0, "lr": 3.838903787751425e-05, "epoch": 224.65486725663717, "percentage": 32.01, "elapsed_time": "1:31:57", "remaining_time": "3:15:18", "throughput": 1318.85, "total_tokens": 7277256} {"current_steps": 12810, "total_steps": 40000, "loss": 0.0, "lr": 3.838074602310802e-05, "epoch": 224.7433628318584, "percentage": 32.02, "elapsed_time": "1:31:59", "remaining_time": "3:15:16", "throughput": 1318.88, "total_tokens": 7280152} {"current_steps": 12815, "total_steps": 40000, "loss": 0.0, "lr": 3.837245210522258e-05, "epoch": 224.83185840707964, "percentage": 32.04, "elapsed_time": "1:32:02", "remaining_time": "3:15:14", "throughput": 1318.86, "total_tokens": 7282760} {"current_steps": 12820, "total_steps": 40000, "loss": 0.0, "lr": 3.8364156125136996e-05, "epoch": 224.9203539823009, "percentage": 32.05, "elapsed_time": "1:32:04", "remaining_time": "3:15:11", "throughput": 1318.86, "total_tokens": 7285448} {"current_steps": 12825, "total_steps": 40000, "loss": 0.0, "lr": 3.835585808413059e-05, "epoch": 225.0, "percentage": 32.06, "elapsed_time": "1:32:06", "remaining_time": "3:15:09", "throughput": 1318.89, "total_tokens": 7288280} {"current_steps": 12830, "total_steps": 40000, "loss": 0.0, "lr": 3.8347557983483024e-05, "epoch": 225.08849557522123, "percentage": 32.07, "elapsed_time": "1:32:08", "remaining_time": "3:15:07", "throughput": 1318.87, "total_tokens": 7291208} {"current_steps": 12835, "total_steps": 40000, "loss": 0.0, "lr": 3.833925582447428e-05, "epoch": 225.1769911504425, "percentage": 32.09, "elapsed_time": "1:32:10", "remaining_time": "3:15:05", "throughput": 1318.87, "total_tokens": 7293928} {"current_steps": 12840, "total_steps": 40000, "loss": 0.0, "lr": 3.8330951608384656e-05, "epoch": 225.26548672566372, "percentage": 32.1, "elapsed_time": "1:32:12", "remaining_time": "3:15:02", "throughput": 1318.88, "total_tokens": 7296728} {"current_steps": 12845, "total_steps": 40000, "loss": 0.0, "lr": 3.832264533649477e-05, "epoch": 225.35398230088495, "percentage": 32.11, "elapsed_time": "1:32:14", "remaining_time": "3:15:00", "throughput": 1318.95, "total_tokens": 7299848} {"current_steps": 12850, "total_steps": 40000, "loss": 0.0, "lr": 3.8314337010085555e-05, "epoch": 225.44247787610618, "percentage": 32.12, "elapsed_time": "1:32:16", "remaining_time": "3:14:58", "throughput": 1319.05, "total_tokens": 7303112} {"current_steps": 12855, "total_steps": 40000, "loss": 0.0, "lr": 3.830602663043824e-05, "epoch": 225.53097345132744, "percentage": 32.14, "elapsed_time": "1:32:18", "remaining_time": "3:14:55", "throughput": 1319.07, "total_tokens": 7305960} {"current_steps": 12860, "total_steps": 40000, "loss": 0.0, "lr": 3.8297714198834414e-05, "epoch": 225.61946902654867, "percentage": 32.15, "elapsed_time": "1:32:20", "remaining_time": "3:14:53", "throughput": 1319.13, "total_tokens": 7308984} {"current_steps": 12865, "total_steps": 40000, "loss": 0.0, "lr": 3.828939971655595e-05, "epoch": 225.7079646017699, "percentage": 32.16, "elapsed_time": "1:32:22", "remaining_time": "3:14:51", "throughput": 1319.15, "total_tokens": 7311832} {"current_steps": 12870, "total_steps": 40000, "loss": 0.0, "lr": 3.828108318488505e-05, "epoch": 225.79646017699116, "percentage": 32.17, "elapsed_time": "1:32:24", "remaining_time": "3:14:48", "throughput": 1319.15, "total_tokens": 7314552} {"current_steps": 12875, "total_steps": 40000, "loss": 0.0, "lr": 3.8272764605104216e-05, "epoch": 225.8849557522124, "percentage": 32.19, "elapsed_time": "1:32:26", "remaining_time": "3:14:46", "throughput": 1319.23, "total_tokens": 7317736} {"current_steps": 12880, "total_steps": 40000, "loss": 0.0, "lr": 3.826444397849628e-05, "epoch": 225.97345132743362, "percentage": 32.2, "elapsed_time": "1:32:29", "remaining_time": "3:14:43", "throughput": 1319.17, "total_tokens": 7320104} {"current_steps": 12885, "total_steps": 40000, "loss": 0.0, "lr": 3.825612130634439e-05, "epoch": 226.05309734513276, "percentage": 32.21, "elapsed_time": "1:32:31", "remaining_time": "3:14:42", "throughput": 1319.02, "total_tokens": 7322248} {"current_steps": 12890, "total_steps": 40000, "loss": 0.0, "lr": 3.824779658993202e-05, "epoch": 226.141592920354, "percentage": 32.23, "elapsed_time": "1:32:33", "remaining_time": "3:14:39", "throughput": 1319.06, "total_tokens": 7325208} {"current_steps": 12895, "total_steps": 40000, "loss": 0.0, "lr": 3.823946983054292e-05, "epoch": 226.23008849557522, "percentage": 32.24, "elapsed_time": "1:32:35", "remaining_time": "3:14:37", "throughput": 1319.07, "total_tokens": 7327992} {"current_steps": 12900, "total_steps": 40000, "loss": 0.0, "lr": 3.82311410294612e-05, "epoch": 226.31858407079645, "percentage": 32.25, "elapsed_time": "1:32:37", "remaining_time": "3:14:35", "throughput": 1319.11, "total_tokens": 7330936} {"current_steps": 12905, "total_steps": 40000, "loss": 0.0, "lr": 3.822281018797127e-05, "epoch": 226.4070796460177, "percentage": 32.26, "elapsed_time": "1:32:39", "remaining_time": "3:14:32", "throughput": 1319.06, "total_tokens": 7333400} {"current_steps": 12910, "total_steps": 40000, "loss": 0.0, "lr": 3.821447730735783e-05, "epoch": 226.49557522123894, "percentage": 32.27, "elapsed_time": "1:32:41", "remaining_time": "3:14:30", "throughput": 1319.05, "total_tokens": 7336056} {"current_steps": 12915, "total_steps": 40000, "loss": 0.0, "lr": 3.820614238890592e-05, "epoch": 226.58407079646017, "percentage": 32.29, "elapsed_time": "1:32:43", "remaining_time": "3:14:28", "throughput": 1319.1, "total_tokens": 7339064} {"current_steps": 12920, "total_steps": 40000, "loss": 0.0, "lr": 3.819780543390091e-05, "epoch": 226.67256637168143, "percentage": 32.3, "elapsed_time": "1:32:45", "remaining_time": "3:14:25", "throughput": 1319.18, "total_tokens": 7342264} {"current_steps": 12925, "total_steps": 40000, "loss": 0.0, "lr": 3.818946644362844e-05, "epoch": 226.76106194690266, "percentage": 32.31, "elapsed_time": "1:32:47", "remaining_time": "3:14:23", "throughput": 1319.16, "total_tokens": 7344872} {"current_steps": 12930, "total_steps": 40000, "loss": 0.0, "lr": 3.81811254193745e-05, "epoch": 226.8495575221239, "percentage": 32.32, "elapsed_time": "1:32:49", "remaining_time": "3:14:21", "throughput": 1319.19, "total_tokens": 7347752} {"current_steps": 12935, "total_steps": 40000, "loss": 0.0, "lr": 3.8172782362425366e-05, "epoch": 226.93805309734512, "percentage": 32.34, "elapsed_time": "1:32:51", "remaining_time": "3:14:18", "throughput": 1319.21, "total_tokens": 7350632} {"current_steps": 12940, "total_steps": 40000, "loss": 0.0, "lr": 3.816443727406765e-05, "epoch": 227.01769911504425, "percentage": 32.35, "elapsed_time": "1:32:54", "remaining_time": "3:14:16", "throughput": 1319.2, "total_tokens": 7353528} {"current_steps": 12945, "total_steps": 40000, "loss": 0.0, "lr": 3.815609015558829e-05, "epoch": 227.10619469026548, "percentage": 32.36, "elapsed_time": "1:32:56", "remaining_time": "3:14:14", "throughput": 1319.24, "total_tokens": 7356520} {"current_steps": 12950, "total_steps": 40000, "loss": 0.0, "lr": 3.814774100827448e-05, "epoch": 227.1946902654867, "percentage": 32.38, "elapsed_time": "1:32:58", "remaining_time": "3:14:12", "throughput": 1319.31, "total_tokens": 7359640} {"current_steps": 12955, "total_steps": 40000, "loss": 0.0, "lr": 3.813938983341379e-05, "epoch": 227.28318584070797, "percentage": 32.39, "elapsed_time": "1:33:00", "remaining_time": "3:14:09", "throughput": 1319.34, "total_tokens": 7362504} {"current_steps": 12960, "total_steps": 40000, "loss": 0.0, "lr": 3.813103663229407e-05, "epoch": 227.3716814159292, "percentage": 32.4, "elapsed_time": "1:33:02", "remaining_time": "3:14:07", "throughput": 1319.31, "total_tokens": 7365048} {"current_steps": 12965, "total_steps": 40000, "loss": 0.0, "lr": 3.812268140620349e-05, "epoch": 227.46017699115043, "percentage": 32.41, "elapsed_time": "1:33:04", "remaining_time": "3:14:05", "throughput": 1319.34, "total_tokens": 7367976} {"current_steps": 12970, "total_steps": 40000, "loss": 0.0, "lr": 3.811432415643051e-05, "epoch": 227.5486725663717, "percentage": 32.42, "elapsed_time": "1:33:06", "remaining_time": "3:14:02", "throughput": 1319.34, "total_tokens": 7370664} {"current_steps": 12975, "total_steps": 40000, "loss": 0.0, "lr": 3.8105964884263954e-05, "epoch": 227.63716814159292, "percentage": 32.44, "elapsed_time": "1:33:08", "remaining_time": "3:14:00", "throughput": 1319.42, "total_tokens": 7373832} {"current_steps": 12980, "total_steps": 40000, "loss": 0.0, "lr": 3.809760359099291e-05, "epoch": 227.72566371681415, "percentage": 32.45, "elapsed_time": "1:33:10", "remaining_time": "3:13:58", "throughput": 1319.47, "total_tokens": 7376888} {"current_steps": 12985, "total_steps": 40000, "loss": 0.0, "lr": 3.8089240277906804e-05, "epoch": 227.81415929203538, "percentage": 32.46, "elapsed_time": "1:33:12", "remaining_time": "3:13:55", "throughput": 1319.51, "total_tokens": 7379784} {"current_steps": 12990, "total_steps": 40000, "loss": 0.0, "lr": 3.808087494629535e-05, "epoch": 227.90265486725664, "percentage": 32.48, "elapsed_time": "1:33:14", "remaining_time": "3:13:53", "throughput": 1319.55, "total_tokens": 7382792} {"current_steps": 12995, "total_steps": 40000, "loss": 0.0, "lr": 3.8072507597448595e-05, "epoch": 227.99115044247787, "percentage": 32.49, "elapsed_time": "1:33:16", "remaining_time": "3:13:51", "throughput": 1319.54, "total_tokens": 7385400} {"current_steps": 13000, "total_steps": 40000, "loss": 0.0, "lr": 3.806413823265689e-05, "epoch": 228.07079646017698, "percentage": 32.5, "elapsed_time": "1:33:19", "remaining_time": "3:13:49", "throughput": 1319.39, "total_tokens": 7387544} {"current_steps": 13000, "total_steps": 40000, "eval_loss": 0.4593886733055115, "epoch": 228.07079646017698, "percentage": 32.5, "elapsed_time": "1:33:20", "remaining_time": "3:13:51", "throughput": 1319.13, "total_tokens": 7387544} {"current_steps": 13005, "total_steps": 40000, "loss": 0.0, "lr": 3.805576685321089e-05, "epoch": 228.15929203539824, "percentage": 32.51, "elapsed_time": "1:33:24", "remaining_time": "3:13:52", "throughput": 1318.69, "total_tokens": 7390040} {"current_steps": 13010, "total_steps": 40000, "loss": 0.0, "lr": 3.804739346040158e-05, "epoch": 228.24778761061947, "percentage": 32.52, "elapsed_time": "1:33:26", "remaining_time": "3:13:50", "throughput": 1318.68, "total_tokens": 7392728} {"current_steps": 13015, "total_steps": 40000, "loss": 0.0, "lr": 3.8039018055520234e-05, "epoch": 228.3362831858407, "percentage": 32.54, "elapsed_time": "1:33:28", "remaining_time": "3:13:47", "throughput": 1318.68, "total_tokens": 7395432} {"current_steps": 13020, "total_steps": 40000, "loss": 0.0, "lr": 3.803064063985844e-05, "epoch": 228.42477876106196, "percentage": 32.55, "elapsed_time": "1:33:30", "remaining_time": "3:13:45", "throughput": 1318.65, "total_tokens": 7398024} {"current_steps": 13025, "total_steps": 40000, "loss": 0.0, "lr": 3.802226121470811e-05, "epoch": 228.5132743362832, "percentage": 32.56, "elapsed_time": "1:33:32", "remaining_time": "3:13:43", "throughput": 1318.7, "total_tokens": 7401032} {"current_steps": 13030, "total_steps": 40000, "loss": 0.0, "lr": 3.801387978136145e-05, "epoch": 228.60176991150442, "percentage": 32.57, "elapsed_time": "1:33:34", "remaining_time": "3:13:40", "throughput": 1318.72, "total_tokens": 7403880} {"current_steps": 13035, "total_steps": 40000, "loss": 0.0, "lr": 3.800549634111099e-05, "epoch": 228.69026548672565, "percentage": 32.59, "elapsed_time": "1:33:36", "remaining_time": "3:13:38", "throughput": 1318.8, "total_tokens": 7407064} {"current_steps": 13040, "total_steps": 40000, "loss": 0.0, "lr": 3.799711089524955e-05, "epoch": 228.7787610619469, "percentage": 32.6, "elapsed_time": "1:33:38", "remaining_time": "3:13:36", "throughput": 1318.81, "total_tokens": 7409832} {"current_steps": 13045, "total_steps": 40000, "loss": 0.0, "lr": 3.7988723445070285e-05, "epoch": 228.86725663716814, "percentage": 32.61, "elapsed_time": "1:33:40", "remaining_time": "3:13:33", "throughput": 1318.85, "total_tokens": 7412776} {"current_steps": 13050, "total_steps": 40000, "loss": 0.0, "lr": 3.798033399186663e-05, "epoch": 228.95575221238937, "percentage": 32.62, "elapsed_time": "1:33:42", "remaining_time": "3:13:31", "throughput": 1318.9, "total_tokens": 7415768} {"current_steps": 13055, "total_steps": 40000, "loss": 0.0, "lr": 3.797194253693237e-05, "epoch": 229.0353982300885, "percentage": 32.64, "elapsed_time": "1:33:44", "remaining_time": "3:13:29", "throughput": 1318.82, "total_tokens": 7418296} {"current_steps": 13060, "total_steps": 40000, "loss": 0.0, "lr": 3.796354908156153e-05, "epoch": 229.12389380530973, "percentage": 32.65, "elapsed_time": "1:33:47", "remaining_time": "3:13:27", "throughput": 1318.8, "total_tokens": 7420952} {"current_steps": 13065, "total_steps": 40000, "loss": 0.0, "lr": 3.795515362704853e-05, "epoch": 229.21238938053096, "percentage": 32.66, "elapsed_time": "1:33:49", "remaining_time": "3:13:25", "throughput": 1318.85, "total_tokens": 7423912} {"current_steps": 13070, "total_steps": 40000, "loss": 0.0, "lr": 3.794675617468803e-05, "epoch": 229.30088495575222, "percentage": 32.67, "elapsed_time": "1:33:51", "remaining_time": "3:13:22", "throughput": 1318.78, "total_tokens": 7426264} {"current_steps": 13075, "total_steps": 40000, "loss": 0.0, "lr": 3.793835672577503e-05, "epoch": 229.38938053097345, "percentage": 32.69, "elapsed_time": "1:33:53", "remaining_time": "3:13:20", "throughput": 1318.85, "total_tokens": 7429368} {"current_steps": 13080, "total_steps": 40000, "loss": 0.0, "lr": 3.7929955281604826e-05, "epoch": 229.47787610619469, "percentage": 32.7, "elapsed_time": "1:33:55", "remaining_time": "3:13:18", "throughput": 1318.85, "total_tokens": 7432120} {"current_steps": 13085, "total_steps": 40000, "loss": 0.0, "lr": 3.7921551843473036e-05, "epoch": 229.56637168141592, "percentage": 32.71, "elapsed_time": "1:33:57", "remaining_time": "3:13:15", "throughput": 1318.9, "total_tokens": 7435144} {"current_steps": 13090, "total_steps": 40000, "loss": 0.0, "lr": 3.791314641267557e-05, "epoch": 229.65486725663717, "percentage": 32.73, "elapsed_time": "1:33:59", "remaining_time": "3:13:13", "throughput": 1318.94, "total_tokens": 7438040} {"current_steps": 13095, "total_steps": 40000, "loss": 0.0, "lr": 3.790473899050864e-05, "epoch": 229.7433628318584, "percentage": 32.74, "elapsed_time": "1:34:01", "remaining_time": "3:13:11", "throughput": 1319.0, "total_tokens": 7441160} {"current_steps": 13100, "total_steps": 40000, "loss": 0.0, "lr": 3.7896329578268794e-05, "epoch": 229.83185840707964, "percentage": 32.75, "elapsed_time": "1:34:03", "remaining_time": "3:13:08", "throughput": 1319.1, "total_tokens": 7444408} {"current_steps": 13105, "total_steps": 40000, "loss": 0.0, "lr": 3.7887918177252855e-05, "epoch": 229.9203539823009, "percentage": 32.76, "elapsed_time": "1:34:05", "remaining_time": "3:13:06", "throughput": 1319.11, "total_tokens": 7447208} {"current_steps": 13110, "total_steps": 40000, "loss": 0.0, "lr": 3.787950478875798e-05, "epoch": 230.0, "percentage": 32.77, "elapsed_time": "1:34:07", "remaining_time": "3:13:03", "throughput": 1319.08, "total_tokens": 7449656} {"current_steps": 13115, "total_steps": 40000, "loss": 0.0, "lr": 3.787108941408162e-05, "epoch": 230.08849557522123, "percentage": 32.79, "elapsed_time": "1:34:09", "remaining_time": "3:13:02", "throughput": 1319.01, "total_tokens": 7452312} {"current_steps": 13120, "total_steps": 40000, "loss": 0.0, "lr": 3.786267205452151e-05, "epoch": 230.1769911504425, "percentage": 32.8, "elapsed_time": "1:34:11", "remaining_time": "3:12:59", "throughput": 1318.99, "total_tokens": 7454904} {"current_steps": 13125, "total_steps": 40000, "loss": 0.0, "lr": 3.785425271137573e-05, "epoch": 230.26548672566372, "percentage": 32.81, "elapsed_time": "1:34:14", "remaining_time": "3:12:57", "throughput": 1318.95, "total_tokens": 7457400} {"current_steps": 13130, "total_steps": 40000, "loss": 0.0, "lr": 3.7845831385942655e-05, "epoch": 230.35398230088495, "percentage": 32.82, "elapsed_time": "1:34:16", "remaining_time": "3:12:55", "throughput": 1319.0, "total_tokens": 7460424} {"current_steps": 13135, "total_steps": 40000, "loss": 0.0, "lr": 3.7837408079520944e-05, "epoch": 230.44247787610618, "percentage": 32.84, "elapsed_time": "1:34:18", "remaining_time": "3:12:52", "throughput": 1319.12, "total_tokens": 7463832} {"current_steps": 13140, "total_steps": 40000, "loss": 0.0, "lr": 3.782898279340957e-05, "epoch": 230.53097345132744, "percentage": 32.85, "elapsed_time": "1:34:20", "remaining_time": "3:12:50", "throughput": 1319.11, "total_tokens": 7466520} {"current_steps": 13145, "total_steps": 40000, "loss": 0.0, "lr": 3.782055552890784e-05, "epoch": 230.61946902654867, "percentage": 32.86, "elapsed_time": "1:34:22", "remaining_time": "3:12:48", "throughput": 1319.17, "total_tokens": 7469576} {"current_steps": 13150, "total_steps": 40000, "loss": 0.0, "lr": 3.781212628731534e-05, "epoch": 230.7079646017699, "percentage": 32.88, "elapsed_time": "1:34:24", "remaining_time": "3:12:45", "throughput": 1319.14, "total_tokens": 7472120} {"current_steps": 13155, "total_steps": 40000, "loss": 0.0, "lr": 3.7803695069931946e-05, "epoch": 230.79646017699116, "percentage": 32.89, "elapsed_time": "1:34:26", "remaining_time": "3:12:43", "throughput": 1319.19, "total_tokens": 7475128} {"current_steps": 13160, "total_steps": 40000, "loss": 0.0, "lr": 3.779526187805789e-05, "epoch": 230.8849557522124, "percentage": 32.9, "elapsed_time": "1:34:28", "remaining_time": "3:12:41", "throughput": 1319.32, "total_tokens": 7478616} {"current_steps": 13165, "total_steps": 40000, "loss": 0.0, "lr": 3.778682671299364e-05, "epoch": 230.97345132743362, "percentage": 32.91, "elapsed_time": "1:34:30", "remaining_time": "3:12:38", "throughput": 1319.32, "total_tokens": 7481336} {"current_steps": 13170, "total_steps": 40000, "loss": 0.0, "lr": 3.777838957604003e-05, "epoch": 231.05309734513276, "percentage": 32.92, "elapsed_time": "1:34:32", "remaining_time": "3:12:36", "throughput": 1319.21, "total_tokens": 7483656} {"current_steps": 13175, "total_steps": 40000, "loss": 0.0, "lr": 3.776995046849816e-05, "epoch": 231.141592920354, "percentage": 32.94, "elapsed_time": "1:34:34", "remaining_time": "3:12:34", "throughput": 1319.23, "total_tokens": 7486552} {"current_steps": 13180, "total_steps": 40000, "loss": 0.0, "lr": 3.776150939166945e-05, "epoch": 231.23008849557522, "percentage": 32.95, "elapsed_time": "1:34:36", "remaining_time": "3:12:32", "throughput": 1319.21, "total_tokens": 7489160} {"current_steps": 13185, "total_steps": 40000, "loss": 0.0, "lr": 3.775306634685562e-05, "epoch": 231.31858407079645, "percentage": 32.96, "elapsed_time": "1:34:39", "remaining_time": "3:12:29", "throughput": 1319.25, "total_tokens": 7492088} {"current_steps": 13190, "total_steps": 40000, "loss": 0.0, "lr": 3.7744621335358696e-05, "epoch": 231.4070796460177, "percentage": 32.98, "elapsed_time": "1:34:41", "remaining_time": "3:12:27", "throughput": 1319.25, "total_tokens": 7494856} {"current_steps": 13195, "total_steps": 40000, "loss": 0.0, "lr": 3.7736174358481e-05, "epoch": 231.49557522123894, "percentage": 32.99, "elapsed_time": "1:34:43", "remaining_time": "3:12:25", "throughput": 1319.19, "total_tokens": 7497224} {"current_steps": 13200, "total_steps": 40000, "loss": 0.0, "lr": 3.7727725417525175e-05, "epoch": 231.58407079646017, "percentage": 33.0, "elapsed_time": "1:34:45", "remaining_time": "3:12:22", "throughput": 1319.23, "total_tokens": 7500200} {"current_steps": 13200, "total_steps": 40000, "eval_loss": 0.46606552600860596, "epoch": 231.58407079646017, "percentage": 33.0, "elapsed_time": "1:34:46", "remaining_time": "3:12:25", "throughput": 1318.98, "total_tokens": 7500200} {"current_steps": 13205, "total_steps": 40000, "loss": 0.0, "lr": 3.771927451379414e-05, "epoch": 231.67256637168143, "percentage": 33.01, "elapsed_time": "1:34:50", "remaining_time": "3:12:26", "throughput": 1318.6, "total_tokens": 7503064} {"current_steps": 13210, "total_steps": 40000, "loss": 0.0, "lr": 3.7710821648591135e-05, "epoch": 231.76106194690266, "percentage": 33.02, "elapsed_time": "1:34:52", "remaining_time": "3:12:23", "throughput": 1318.68, "total_tokens": 7506248} {"current_steps": 13215, "total_steps": 40000, "loss": 0.0, "lr": 3.7702366823219694e-05, "epoch": 231.8495575221239, "percentage": 33.04, "elapsed_time": "1:34:54", "remaining_time": "3:12:21", "throughput": 1318.83, "total_tokens": 7509816} {"current_steps": 13220, "total_steps": 40000, "loss": 0.0, "lr": 3.769391003898366e-05, "epoch": 231.93805309734512, "percentage": 33.05, "elapsed_time": "1:34:56", "remaining_time": "3:12:19", "throughput": 1318.83, "total_tokens": 7512536} {"current_steps": 13225, "total_steps": 40000, "loss": 0.0, "lr": 3.768545129718718e-05, "epoch": 232.01769911504425, "percentage": 33.06, "elapsed_time": "1:34:58", "remaining_time": "3:12:17", "throughput": 1318.7, "total_tokens": 7514808} {"current_steps": 13230, "total_steps": 40000, "loss": 0.0, "lr": 3.7676990599134686e-05, "epoch": 232.10619469026548, "percentage": 33.07, "elapsed_time": "1:35:00", "remaining_time": "3:12:14", "throughput": 1318.69, "total_tokens": 7517448} {"current_steps": 13235, "total_steps": 40000, "loss": 0.0, "lr": 3.766852794613095e-05, "epoch": 232.1946902654867, "percentage": 33.09, "elapsed_time": "1:35:02", "remaining_time": "3:12:12", "throughput": 1318.72, "total_tokens": 7520392} {"current_steps": 13240, "total_steps": 40000, "loss": 0.0, "lr": 3.766006333948099e-05, "epoch": 232.28318584070797, "percentage": 33.1, "elapsed_time": "1:35:04", "remaining_time": "3:12:10", "throughput": 1318.8, "total_tokens": 7523544} {"current_steps": 13245, "total_steps": 40000, "loss": 0.0, "lr": 3.765159678049017e-05, "epoch": 232.3716814159292, "percentage": 33.11, "elapsed_time": "1:35:06", "remaining_time": "3:12:07", "throughput": 1318.81, "total_tokens": 7526312} {"current_steps": 13250, "total_steps": 40000, "loss": 0.0, "lr": 3.7643128270464134e-05, "epoch": 232.46017699115043, "percentage": 33.12, "elapsed_time": "1:35:08", "remaining_time": "3:12:05", "throughput": 1318.89, "total_tokens": 7529512} {"current_steps": 13255, "total_steps": 40000, "loss": 0.0, "lr": 3.763465781070884e-05, "epoch": 232.5486725663717, "percentage": 33.14, "elapsed_time": "1:35:11", "remaining_time": "3:12:03", "throughput": 1318.97, "total_tokens": 7532680} {"current_steps": 13260, "total_steps": 40000, "loss": 0.0, "lr": 3.762618540253052e-05, "epoch": 232.63716814159292, "percentage": 33.15, "elapsed_time": "1:35:13", "remaining_time": "3:12:00", "throughput": 1318.97, "total_tokens": 7535384} {"current_steps": 13265, "total_steps": 40000, "loss": 0.0, "lr": 3.761771104723576e-05, "epoch": 232.72566371681415, "percentage": 33.16, "elapsed_time": "1:35:15", "remaining_time": "3:11:58", "throughput": 1319.01, "total_tokens": 7538376} {"current_steps": 13270, "total_steps": 40000, "loss": 0.0, "lr": 3.7609234746131386e-05, "epoch": 232.81415929203538, "percentage": 33.17, "elapsed_time": "1:35:17", "remaining_time": "3:11:56", "throughput": 1318.95, "total_tokens": 7540728} {"current_steps": 13275, "total_steps": 40000, "loss": 0.0, "lr": 3.7600756500524556e-05, "epoch": 232.90265486725664, "percentage": 33.19, "elapsed_time": "1:35:19", "remaining_time": "3:11:54", "throughput": 1319.02, "total_tokens": 7543848} {"current_steps": 13280, "total_steps": 40000, "loss": 0.0, "lr": 3.759227631172271e-05, "epoch": 232.99115044247787, "percentage": 33.2, "elapsed_time": "1:35:21", "remaining_time": "3:11:51", "throughput": 1319.04, "total_tokens": 7546680} {"current_steps": 13285, "total_steps": 40000, "loss": 0.0, "lr": 3.758379418103363e-05, "epoch": 233.07079646017698, "percentage": 33.21, "elapsed_time": "1:35:23", "remaining_time": "3:11:49", "throughput": 1318.89, "total_tokens": 7548792} {"current_steps": 13290, "total_steps": 40000, "loss": 0.0, "lr": 3.757531010976534e-05, "epoch": 233.15929203539824, "percentage": 33.23, "elapsed_time": "1:35:25", "remaining_time": "3:11:47", "throughput": 1319.0, "total_tokens": 7552184} {"current_steps": 13295, "total_steps": 40000, "loss": 0.0, "lr": 3.75668240992262e-05, "epoch": 233.24778761061947, "percentage": 33.24, "elapsed_time": "1:35:27", "remaining_time": "3:11:45", "throughput": 1319.1, "total_tokens": 7555480} {"current_steps": 13300, "total_steps": 40000, "loss": 0.0, "lr": 3.7558336150724865e-05, "epoch": 233.3362831858407, "percentage": 33.25, "elapsed_time": "1:35:29", "remaining_time": "3:11:42", "throughput": 1319.17, "total_tokens": 7558584} {"current_steps": 13305, "total_steps": 40000, "loss": 0.0, "lr": 3.754984626557028e-05, "epoch": 233.42477876106196, "percentage": 33.26, "elapsed_time": "1:35:31", "remaining_time": "3:11:40", "throughput": 1319.14, "total_tokens": 7561160} {"current_steps": 13310, "total_steps": 40000, "loss": 0.0, "lr": 3.754135444507168e-05, "epoch": 233.5132743362832, "percentage": 33.27, "elapsed_time": "1:35:33", "remaining_time": "3:11:38", "throughput": 1319.06, "total_tokens": 7563464} {"current_steps": 13315, "total_steps": 40000, "loss": 0.0, "lr": 3.753286069053863e-05, "epoch": 233.60176991150442, "percentage": 33.29, "elapsed_time": "1:35:36", "remaining_time": "3:11:35", "throughput": 1319.08, "total_tokens": 7566280} {"current_steps": 13320, "total_steps": 40000, "loss": 0.0, "lr": 3.7524365003280945e-05, "epoch": 233.69026548672565, "percentage": 33.3, "elapsed_time": "1:35:38", "remaining_time": "3:11:33", "throughput": 1319.15, "total_tokens": 7569448} {"current_steps": 13325, "total_steps": 40000, "loss": 0.0, "lr": 3.75158673846088e-05, "epoch": 233.7787610619469, "percentage": 33.31, "elapsed_time": "1:35:40", "remaining_time": "3:11:31", "throughput": 1319.18, "total_tokens": 7572344} {"current_steps": 13330, "total_steps": 40000, "loss": 0.0, "lr": 3.750736783583262e-05, "epoch": 233.86725663716814, "percentage": 33.32, "elapsed_time": "1:35:42", "remaining_time": "3:11:28", "throughput": 1319.17, "total_tokens": 7575016} {"current_steps": 13335, "total_steps": 40000, "loss": 0.0, "lr": 3.7498866358263144e-05, "epoch": 233.95575221238937, "percentage": 33.34, "elapsed_time": "1:35:44", "remaining_time": "3:11:26", "throughput": 1319.16, "total_tokens": 7577656} {"current_steps": 13340, "total_steps": 40000, "loss": 0.0, "lr": 3.74903629532114e-05, "epoch": 234.0353982300885, "percentage": 33.35, "elapsed_time": "1:35:46", "remaining_time": "3:11:24", "throughput": 1319.05, "total_tokens": 7580016} {"current_steps": 13345, "total_steps": 40000, "loss": 0.0, "lr": 3.748185762198873e-05, "epoch": 234.12389380530973, "percentage": 33.36, "elapsed_time": "1:35:48", "remaining_time": "3:11:22", "throughput": 1319.11, "total_tokens": 7583104} {"current_steps": 13350, "total_steps": 40000, "loss": 0.0, "lr": 3.747335036590676e-05, "epoch": 234.21238938053096, "percentage": 33.38, "elapsed_time": "1:35:50", "remaining_time": "3:11:19", "throughput": 1319.13, "total_tokens": 7585952} {"current_steps": 13355, "total_steps": 40000, "loss": 0.0, "lr": 3.7464841186277405e-05, "epoch": 234.30088495575222, "percentage": 33.39, "elapsed_time": "1:35:52", "remaining_time": "3:11:17", "throughput": 1319.1, "total_tokens": 7588480} {"current_steps": 13360, "total_steps": 40000, "loss": 0.0, "lr": 3.7456330084412896e-05, "epoch": 234.38938053097345, "percentage": 33.4, "elapsed_time": "1:35:54", "remaining_time": "3:11:15", "throughput": 1319.1, "total_tokens": 7591248} {"current_steps": 13365, "total_steps": 40000, "loss": 0.0, "lr": 3.744781706162576e-05, "epoch": 234.47787610619469, "percentage": 33.41, "elapsed_time": "1:35:56", "remaining_time": "3:11:12", "throughput": 1319.2, "total_tokens": 7594544} {"current_steps": 13370, "total_steps": 40000, "loss": 0.0, "lr": 3.743930211922879e-05, "epoch": 234.56637168141592, "percentage": 33.42, "elapsed_time": "1:35:58", "remaining_time": "3:11:10", "throughput": 1319.26, "total_tokens": 7597600} {"current_steps": 13375, "total_steps": 40000, "loss": 0.0, "lr": 3.743078525853513e-05, "epoch": 234.65486725663717, "percentage": 33.44, "elapsed_time": "1:36:01", "remaining_time": "3:11:08", "throughput": 1319.26, "total_tokens": 7600336} {"current_steps": 13380, "total_steps": 40000, "loss": 0.0, "lr": 3.7422266480858154e-05, "epoch": 234.7433628318584, "percentage": 33.45, "elapsed_time": "1:36:03", "remaining_time": "3:11:05", "throughput": 1319.34, "total_tokens": 7603536} {"current_steps": 13385, "total_steps": 40000, "loss": 0.0, "lr": 3.741374578751158e-05, "epoch": 234.83185840707964, "percentage": 33.46, "elapsed_time": "1:36:05", "remaining_time": "3:11:03", "throughput": 1319.3, "total_tokens": 7606048} {"current_steps": 13390, "total_steps": 40000, "loss": 0.0, "lr": 3.740522317980941e-05, "epoch": 234.9203539823009, "percentage": 33.48, "elapsed_time": "1:36:07", "remaining_time": "3:11:01", "throughput": 1319.34, "total_tokens": 7609008} {"current_steps": 13395, "total_steps": 40000, "loss": 0.0, "lr": 3.739669865906593e-05, "epoch": 235.0, "percentage": 33.49, "elapsed_time": "1:36:09", "remaining_time": "3:10:58", "throughput": 1319.29, "total_tokens": 7611336} {"current_steps": 13400, "total_steps": 40000, "loss": 0.0, "lr": 3.738817222659573e-05, "epoch": 235.08849557522123, "percentage": 33.5, "elapsed_time": "1:36:11", "remaining_time": "3:10:57", "throughput": 1319.34, "total_tokens": 7614696} {"current_steps": 13400, "total_steps": 40000, "eval_loss": 0.4695309102535248, "epoch": 235.08849557522123, "percentage": 33.5, "elapsed_time": "1:36:12", "remaining_time": "3:10:59", "throughput": 1319.1, "total_tokens": 7614696} {"current_steps": 13405, "total_steps": 40000, "loss": 0.0, "lr": 3.73796438837137e-05, "epoch": 235.1769911504425, "percentage": 33.51, "elapsed_time": "1:36:16", "remaining_time": "3:11:00", "throughput": 1318.77, "total_tokens": 7617704} {"current_steps": 13410, "total_steps": 40000, "loss": 0.0, "lr": 3.7371113631735e-05, "epoch": 235.26548672566372, "percentage": 33.52, "elapsed_time": "1:36:18", "remaining_time": "3:10:57", "throughput": 1318.84, "total_tokens": 7620856} {"current_steps": 13415, "total_steps": 40000, "loss": 0.0, "lr": 3.736258147197512e-05, "epoch": 235.35398230088495, "percentage": 33.54, "elapsed_time": "1:36:20", "remaining_time": "3:10:55", "throughput": 1318.89, "total_tokens": 7623880} {"current_steps": 13420, "total_steps": 40000, "loss": 0.0, "lr": 3.735404740574981e-05, "epoch": 235.44247787610618, "percentage": 33.55, "elapsed_time": "1:36:22", "remaining_time": "3:10:53", "throughput": 1318.91, "total_tokens": 7626696} {"current_steps": 13425, "total_steps": 40000, "loss": 0.0, "lr": 3.7345511434375145e-05, "epoch": 235.53097345132744, "percentage": 33.56, "elapsed_time": "1:36:24", "remaining_time": "3:10:50", "throughput": 1318.87, "total_tokens": 7629208} {"current_steps": 13430, "total_steps": 40000, "loss": 0.0, "lr": 3.733697355916748e-05, "epoch": 235.61946902654867, "percentage": 33.58, "elapsed_time": "1:36:26", "remaining_time": "3:10:48", "throughput": 1318.82, "total_tokens": 7631656} {"current_steps": 13435, "total_steps": 40000, "loss": 0.0, "lr": 3.732843378144345e-05, "epoch": 235.7079646017699, "percentage": 33.59, "elapsed_time": "1:36:28", "remaining_time": "3:10:46", "throughput": 1318.82, "total_tokens": 7634376} {"current_steps": 13440, "total_steps": 40000, "loss": 0.0, "lr": 3.7319892102519995e-05, "epoch": 235.79646017699116, "percentage": 33.6, "elapsed_time": "1:36:30", "remaining_time": "3:10:43", "throughput": 1318.86, "total_tokens": 7637336} {"current_steps": 13445, "total_steps": 40000, "loss": 0.0, "lr": 3.731134852371436e-05, "epoch": 235.8849557522124, "percentage": 33.61, "elapsed_time": "1:36:32", "remaining_time": "3:10:41", "throughput": 1318.91, "total_tokens": 7640328} {"current_steps": 13450, "total_steps": 40000, "loss": 0.0, "lr": 3.730280304634408e-05, "epoch": 235.97345132743362, "percentage": 33.62, "elapsed_time": "1:36:34", "remaining_time": "3:10:39", "throughput": 1318.97, "total_tokens": 7643384} {"current_steps": 13455, "total_steps": 40000, "loss": 0.0, "lr": 3.729425567172696e-05, "epoch": 236.05309734513276, "percentage": 33.64, "elapsed_time": "1:36:37", "remaining_time": "3:10:37", "throughput": 1318.87, "total_tokens": 7645784} {"current_steps": 13460, "total_steps": 40000, "loss": 0.0, "lr": 3.728570640118111e-05, "epoch": 236.141592920354, "percentage": 33.65, "elapsed_time": "1:36:39", "remaining_time": "3:10:34", "throughput": 1318.96, "total_tokens": 7649064} {"current_steps": 13465, "total_steps": 40000, "loss": 0.0, "lr": 3.727715523602494e-05, "epoch": 236.23008849557522, "percentage": 33.66, "elapsed_time": "1:36:41", "remaining_time": "3:10:32", "throughput": 1318.98, "total_tokens": 7651896} {"current_steps": 13470, "total_steps": 40000, "loss": 0.0, "lr": 3.726860217757715e-05, "epoch": 236.31858407079645, "percentage": 33.67, "elapsed_time": "1:36:43", "remaining_time": "3:10:30", "throughput": 1319.05, "total_tokens": 7655032} {"current_steps": 13475, "total_steps": 40000, "loss": 0.0, "lr": 3.726004722715673e-05, "epoch": 236.4070796460177, "percentage": 33.69, "elapsed_time": "1:36:45", "remaining_time": "3:10:27", "throughput": 1319.0, "total_tokens": 7657464} {"current_steps": 13480, "total_steps": 40000, "loss": 0.0, "lr": 3.725149038608296e-05, "epoch": 236.49557522123894, "percentage": 33.7, "elapsed_time": "1:36:47", "remaining_time": "3:10:25", "throughput": 1319.11, "total_tokens": 7660840} {"current_steps": 13485, "total_steps": 40000, "loss": 0.0, "lr": 3.7242931655675404e-05, "epoch": 236.58407079646017, "percentage": 33.71, "elapsed_time": "1:36:49", "remaining_time": "3:10:23", "throughput": 1319.08, "total_tokens": 7663400} {"current_steps": 13490, "total_steps": 40000, "loss": 0.0, "lr": 3.7234371037253937e-05, "epoch": 236.67256637168143, "percentage": 33.73, "elapsed_time": "1:36:51", "remaining_time": "3:10:20", "throughput": 1319.08, "total_tokens": 7666120} {"current_steps": 13495, "total_steps": 40000, "loss": 0.0, "lr": 3.7225808532138705e-05, "epoch": 236.76106194690266, "percentage": 33.74, "elapsed_time": "1:36:53", "remaining_time": "3:10:18", "throughput": 1319.09, "total_tokens": 7668920} {"current_steps": 13500, "total_steps": 40000, "loss": 0.0, "lr": 3.721724414165016e-05, "epoch": 236.8495575221239, "percentage": 33.75, "elapsed_time": "1:36:55", "remaining_time": "3:10:16", "throughput": 1319.11, "total_tokens": 7671784} {"current_steps": 13505, "total_steps": 40000, "loss": 0.0, "lr": 3.720867786710904e-05, "epoch": 236.93805309734512, "percentage": 33.76, "elapsed_time": "1:36:57", "remaining_time": "3:10:13", "throughput": 1319.1, "total_tokens": 7674408} {"current_steps": 13510, "total_steps": 40000, "loss": 0.0, "lr": 3.7200109709836366e-05, "epoch": 237.01769911504425, "percentage": 33.77, "elapsed_time": "1:37:00", "remaining_time": "3:10:12", "throughput": 1319.0, "total_tokens": 7676832} {"current_steps": 13515, "total_steps": 40000, "loss": 0.0, "lr": 3.7191539671153465e-05, "epoch": 237.10619469026548, "percentage": 33.79, "elapsed_time": "1:37:02", "remaining_time": "3:10:09", "throughput": 1319.04, "total_tokens": 7679792} {"current_steps": 13520, "total_steps": 40000, "loss": 0.0, "lr": 3.718296775238193e-05, "epoch": 237.1946902654867, "percentage": 33.8, "elapsed_time": "1:37:04", "remaining_time": "3:10:07", "throughput": 1319.08, "total_tokens": 7682752} {"current_steps": 13525, "total_steps": 40000, "loss": 0.0, "lr": 3.7174393954843675e-05, "epoch": 237.28318584070797, "percentage": 33.81, "elapsed_time": "1:37:06", "remaining_time": "3:10:05", "throughput": 1319.13, "total_tokens": 7685760} {"current_steps": 13530, "total_steps": 40000, "loss": 0.0, "lr": 3.716581827986087e-05, "epoch": 237.3716814159292, "percentage": 33.83, "elapsed_time": "1:37:08", "remaining_time": "3:10:02", "throughput": 1319.25, "total_tokens": 7689168} {"current_steps": 13535, "total_steps": 40000, "loss": 0.0, "lr": 3.7157240728756004e-05, "epoch": 237.46017699115043, "percentage": 33.84, "elapsed_time": "1:37:10", "remaining_time": "3:10:00", "throughput": 1319.24, "total_tokens": 7691856} {"current_steps": 13540, "total_steps": 40000, "loss": 0.0, "lr": 3.714866130285184e-05, "epoch": 237.5486725663717, "percentage": 33.85, "elapsed_time": "1:37:12", "remaining_time": "3:09:58", "throughput": 1319.21, "total_tokens": 7694384} {"current_steps": 13545, "total_steps": 40000, "loss": 0.0, "lr": 3.714008000347143e-05, "epoch": 237.63716814159292, "percentage": 33.86, "elapsed_time": "1:37:14", "remaining_time": "3:09:55", "throughput": 1319.26, "total_tokens": 7697440} {"current_steps": 13550, "total_steps": 40000, "loss": 0.0, "lr": 3.7131496831938126e-05, "epoch": 237.72566371681415, "percentage": 33.88, "elapsed_time": "1:37:16", "remaining_time": "3:09:53", "throughput": 1319.29, "total_tokens": 7700336} {"current_steps": 13555, "total_steps": 40000, "loss": 0.0, "lr": 3.7122911789575565e-05, "epoch": 237.81415929203538, "percentage": 33.89, "elapsed_time": "1:37:18", "remaining_time": "3:09:51", "throughput": 1319.39, "total_tokens": 7703616} {"current_steps": 13560, "total_steps": 40000, "loss": 0.0, "lr": 3.711432487770765e-05, "epoch": 237.90265486725664, "percentage": 33.9, "elapsed_time": "1:37:20", "remaining_time": "3:09:48", "throughput": 1319.35, "total_tokens": 7706144} {"current_steps": 13565, "total_steps": 40000, "loss": 0.0, "lr": 3.710573609765861e-05, "epoch": 237.99115044247787, "percentage": 33.91, "elapsed_time": "1:37:22", "remaining_time": "3:09:46", "throughput": 1319.33, "total_tokens": 7708704} {"current_steps": 13570, "total_steps": 40000, "loss": 0.0, "lr": 3.709714545075292e-05, "epoch": 238.07079646017698, "percentage": 33.92, "elapsed_time": "1:37:25", "remaining_time": "3:09:44", "throughput": 1319.21, "total_tokens": 7710984} {"current_steps": 13575, "total_steps": 40000, "loss": 0.0, "lr": 3.708855293831538e-05, "epoch": 238.15929203539824, "percentage": 33.94, "elapsed_time": "1:37:27", "remaining_time": "3:09:42", "throughput": 1319.19, "total_tokens": 7713608} {"current_steps": 13580, "total_steps": 40000, "loss": 0.0, "lr": 3.707995856167107e-05, "epoch": 238.24778761061947, "percentage": 33.95, "elapsed_time": "1:37:29", "remaining_time": "3:09:39", "throughput": 1319.21, "total_tokens": 7716488} {"current_steps": 13585, "total_steps": 40000, "loss": 0.0, "lr": 3.707136232214534e-05, "epoch": 238.3362831858407, "percentage": 33.96, "elapsed_time": "1:37:31", "remaining_time": "3:09:37", "throughput": 1319.28, "total_tokens": 7719640} {"current_steps": 13590, "total_steps": 40000, "loss": 0.0, "lr": 3.7062764221063844e-05, "epoch": 238.42477876106196, "percentage": 33.98, "elapsed_time": "1:37:33", "remaining_time": "3:09:35", "throughput": 1319.25, "total_tokens": 7722200} {"current_steps": 13595, "total_steps": 40000, "loss": 0.0, "lr": 3.705416425975252e-05, "epoch": 238.5132743362832, "percentage": 33.99, "elapsed_time": "1:37:35", "remaining_time": "3:09:32", "throughput": 1319.24, "total_tokens": 7724840} {"current_steps": 13600, "total_steps": 40000, "loss": 0.0, "lr": 3.704556243953758e-05, "epoch": 238.60176991150442, "percentage": 34.0, "elapsed_time": "1:37:37", "remaining_time": "3:09:30", "throughput": 1319.25, "total_tokens": 7727608} {"current_steps": 13600, "total_steps": 40000, "eval_loss": 0.4754555821418762, "epoch": 238.60176991150442, "percentage": 34.0, "elapsed_time": "1:37:38", "remaining_time": "3:09:32", "throughput": 1319.01, "total_tokens": 7727608} {"current_steps": 13605, "total_steps": 40000, "loss": 0.0, "lr": 3.7036958761745535e-05, "epoch": 238.69026548672565, "percentage": 34.01, "elapsed_time": "1:37:42", "remaining_time": "3:09:34", "throughput": 1318.55, "total_tokens": 7730376} {"current_steps": 13610, "total_steps": 40000, "loss": 0.0, "lr": 3.702835322770318e-05, "epoch": 238.7787610619469, "percentage": 34.02, "elapsed_time": "1:37:44", "remaining_time": "3:09:32", "throughput": 1318.55, "total_tokens": 7733128} {"current_steps": 13615, "total_steps": 40000, "loss": 0.0, "lr": 3.701974583873761e-05, "epoch": 238.86725663716814, "percentage": 34.04, "elapsed_time": "1:37:46", "remaining_time": "3:09:29", "throughput": 1318.59, "total_tokens": 7736056} {"current_steps": 13620, "total_steps": 40000, "loss": 0.0, "lr": 3.701113659617618e-05, "epoch": 238.95575221238937, "percentage": 34.05, "elapsed_time": "1:37:48", "remaining_time": "3:09:27", "throughput": 1318.63, "total_tokens": 7739048} {"current_steps": 13625, "total_steps": 40000, "loss": 0.0, "lr": 3.7002525501346535e-05, "epoch": 239.0353982300885, "percentage": 34.06, "elapsed_time": "1:37:51", "remaining_time": "3:09:25", "throughput": 1318.58, "total_tokens": 7741696} {"current_steps": 13630, "total_steps": 40000, "loss": 0.0, "lr": 3.699391255557664e-05, "epoch": 239.12389380530973, "percentage": 34.08, "elapsed_time": "1:37:53", "remaining_time": "3:09:23", "throughput": 1318.57, "total_tokens": 7744384} {"current_steps": 13635, "total_steps": 40000, "loss": 0.0, "lr": 3.69852977601947e-05, "epoch": 239.21238938053096, "percentage": 34.09, "elapsed_time": "1:37:55", "remaining_time": "3:09:20", "throughput": 1318.68, "total_tokens": 7747776} {"current_steps": 13640, "total_steps": 40000, "loss": 0.0, "lr": 3.697668111652922e-05, "epoch": 239.30088495575222, "percentage": 34.1, "elapsed_time": "1:37:57", "remaining_time": "3:09:18", "throughput": 1318.66, "total_tokens": 7750400} {"current_steps": 13645, "total_steps": 40000, "loss": 0.0, "lr": 3.6968062625909005e-05, "epoch": 239.38938053097345, "percentage": 34.11, "elapsed_time": "1:37:59", "remaining_time": "3:09:16", "throughput": 1318.71, "total_tokens": 7753376} {"current_steps": 13650, "total_steps": 40000, "loss": 0.0, "lr": 3.6959442289663135e-05, "epoch": 239.47787610619469, "percentage": 34.12, "elapsed_time": "1:38:01", "remaining_time": "3:09:13", "throughput": 1318.7, "total_tokens": 7756048} {"current_steps": 13655, "total_steps": 40000, "loss": 0.0, "lr": 3.695082010912098e-05, "epoch": 239.56637168141592, "percentage": 34.14, "elapsed_time": "1:38:03", "remaining_time": "3:09:11", "throughput": 1318.69, "total_tokens": 7758720} {"current_steps": 13660, "total_steps": 40000, "loss": 0.0, "lr": 3.694219608561217e-05, "epoch": 239.65486725663717, "percentage": 34.15, "elapsed_time": "1:38:05", "remaining_time": "3:09:09", "throughput": 1318.8, "total_tokens": 7762096} {"current_steps": 13665, "total_steps": 40000, "loss": 0.0, "lr": 3.693357022046665e-05, "epoch": 239.7433628318584, "percentage": 34.16, "elapsed_time": "1:38:07", "remaining_time": "3:09:06", "throughput": 1318.82, "total_tokens": 7764944} {"current_steps": 13670, "total_steps": 40000, "loss": 0.0, "lr": 3.6924942515014644e-05, "epoch": 239.83185840707964, "percentage": 34.17, "elapsed_time": "1:38:09", "remaining_time": "3:09:04", "throughput": 1318.83, "total_tokens": 7767696} {"current_steps": 13675, "total_steps": 40000, "loss": 0.0, "lr": 3.691631297058664e-05, "epoch": 239.9203539823009, "percentage": 34.19, "elapsed_time": "1:38:11", "remaining_time": "3:09:02", "throughput": 1318.77, "total_tokens": 7770096} {"current_steps": 13680, "total_steps": 40000, "loss": 0.0, "lr": 3.6907681588513424e-05, "epoch": 240.0, "percentage": 34.2, "elapsed_time": "1:38:13", "remaining_time": "3:08:59", "throughput": 1318.74, "total_tokens": 7772536} {"current_steps": 13685, "total_steps": 40000, "loss": 0.0, "lr": 3.689904837012606e-05, "epoch": 240.08849557522123, "percentage": 34.21, "elapsed_time": "1:38:16", "remaining_time": "3:08:57", "throughput": 1318.77, "total_tokens": 7775784} {"current_steps": 13690, "total_steps": 40000, "loss": 0.0, "lr": 3.689041331675591e-05, "epoch": 240.1769911504425, "percentage": 34.23, "elapsed_time": "1:38:18", "remaining_time": "3:08:55", "throughput": 1318.74, "total_tokens": 7778312} {"current_steps": 13695, "total_steps": 40000, "loss": 0.0, "lr": 3.688177642973461e-05, "epoch": 240.26548672566372, "percentage": 34.24, "elapsed_time": "1:38:20", "remaining_time": "3:08:53", "throughput": 1318.75, "total_tokens": 7781112} {"current_steps": 13700, "total_steps": 40000, "loss": 0.0, "lr": 3.687313771039406e-05, "epoch": 240.35398230088495, "percentage": 34.25, "elapsed_time": "1:38:22", "remaining_time": "3:08:50", "throughput": 1318.77, "total_tokens": 7783944} {"current_steps": 13705, "total_steps": 40000, "loss": 0.0, "lr": 3.686449716006647e-05, "epoch": 240.44247787610618, "percentage": 34.26, "elapsed_time": "1:38:24", "remaining_time": "3:08:48", "throughput": 1318.86, "total_tokens": 7787192} {"current_steps": 13710, "total_steps": 40000, "loss": 0.0, "lr": 3.685585478008432e-05, "epoch": 240.53097345132744, "percentage": 34.27, "elapsed_time": "1:38:26", "remaining_time": "3:08:46", "throughput": 1318.92, "total_tokens": 7790280} {"current_steps": 13715, "total_steps": 40000, "loss": 0.0, "lr": 3.6847210571780364e-05, "epoch": 240.61946902654867, "percentage": 34.29, "elapsed_time": "1:38:28", "remaining_time": "3:08:43", "throughput": 1318.95, "total_tokens": 7793176} {"current_steps": 13720, "total_steps": 40000, "loss": 0.0, "lr": 3.683856453648767e-05, "epoch": 240.7079646017699, "percentage": 34.3, "elapsed_time": "1:38:30", "remaining_time": "3:08:41", "throughput": 1318.97, "total_tokens": 7796072} {"current_steps": 13725, "total_steps": 40000, "loss": 0.0, "lr": 3.682991667553954e-05, "epoch": 240.79646017699116, "percentage": 34.31, "elapsed_time": "1:38:32", "remaining_time": "3:08:39", "throughput": 1319.0, "total_tokens": 7798968} {"current_steps": 13730, "total_steps": 40000, "loss": 0.0, "lr": 3.6821266990269606e-05, "epoch": 240.8849557522124, "percentage": 34.33, "elapsed_time": "1:38:34", "remaining_time": "3:08:37", "throughput": 1318.99, "total_tokens": 7801640} {"current_steps": 13735, "total_steps": 40000, "loss": 0.0, "lr": 3.681261548201174e-05, "epoch": 240.97345132743362, "percentage": 34.34, "elapsed_time": "1:38:36", "remaining_time": "3:08:34", "throughput": 1319.01, "total_tokens": 7804472} {"current_steps": 13740, "total_steps": 40000, "loss": 0.0, "lr": 3.6803962152100125e-05, "epoch": 241.05309734513276, "percentage": 34.35, "elapsed_time": "1:38:39", "remaining_time": "3:08:32", "throughput": 1318.89, "total_tokens": 7806696} {"current_steps": 13745, "total_steps": 40000, "loss": 0.0, "lr": 3.67953070018692e-05, "epoch": 241.141592920354, "percentage": 34.36, "elapsed_time": "1:38:41", "remaining_time": "3:08:30", "throughput": 1318.87, "total_tokens": 7809304} {"current_steps": 13750, "total_steps": 40000, "loss": 0.0, "lr": 3.678665003265371e-05, "epoch": 241.23008849557522, "percentage": 34.38, "elapsed_time": "1:38:43", "remaining_time": "3:08:28", "throughput": 1318.85, "total_tokens": 7811912} {"current_steps": 13755, "total_steps": 40000, "loss": 0.0, "lr": 3.677799124578867e-05, "epoch": 241.31858407079645, "percentage": 34.39, "elapsed_time": "1:38:45", "remaining_time": "3:08:25", "throughput": 1318.95, "total_tokens": 7815256} {"current_steps": 13760, "total_steps": 40000, "loss": 0.0, "lr": 3.676933064260937e-05, "epoch": 241.4070796460177, "percentage": 34.4, "elapsed_time": "1:38:47", "remaining_time": "3:08:23", "throughput": 1318.98, "total_tokens": 7818152} {"current_steps": 13765, "total_steps": 40000, "loss": 0.0, "lr": 3.6760668224451365e-05, "epoch": 241.49557522123894, "percentage": 34.41, "elapsed_time": "1:38:49", "remaining_time": "3:08:21", "throughput": 1319.13, "total_tokens": 7821752} {"current_steps": 13770, "total_steps": 40000, "loss": 0.0, "lr": 3.675200399265054e-05, "epoch": 241.58407079646017, "percentage": 34.42, "elapsed_time": "1:38:51", "remaining_time": "3:08:18", "throughput": 1319.11, "total_tokens": 7824344} {"current_steps": 13775, "total_steps": 40000, "loss": 0.0, "lr": 3.6743337948543014e-05, "epoch": 241.67256637168143, "percentage": 34.44, "elapsed_time": "1:38:53", "remaining_time": "3:08:16", "throughput": 1319.17, "total_tokens": 7827464} {"current_steps": 13780, "total_steps": 40000, "loss": 0.0, "lr": 3.6734670093465204e-05, "epoch": 241.76106194690266, "percentage": 34.45, "elapsed_time": "1:38:55", "remaining_time": "3:08:14", "throughput": 1319.2, "total_tokens": 7830376} {"current_steps": 13785, "total_steps": 40000, "loss": 0.0, "lr": 3.672600042875379e-05, "epoch": 241.8495575221239, "percentage": 34.46, "elapsed_time": "1:38:57", "remaining_time": "3:08:11", "throughput": 1319.16, "total_tokens": 7832856} {"current_steps": 13790, "total_steps": 40000, "loss": 0.0, "lr": 3.671732895574575e-05, "epoch": 241.93805309734512, "percentage": 34.48, "elapsed_time": "1:38:59", "remaining_time": "3:08:09", "throughput": 1319.2, "total_tokens": 7835800} {"current_steps": 13795, "total_steps": 40000, "loss": 0.0, "lr": 3.670865567577834e-05, "epoch": 242.01769911504425, "percentage": 34.49, "elapsed_time": "1:39:02", "remaining_time": "3:08:07", "throughput": 1319.08, "total_tokens": 7838072} {"current_steps": 13800, "total_steps": 40000, "loss": 0.0, "lr": 3.669998059018909e-05, "epoch": 242.10619469026548, "percentage": 34.5, "elapsed_time": "1:39:04", "remaining_time": "3:08:05", "throughput": 1319.06, "total_tokens": 7840696} {"current_steps": 13800, "total_steps": 40000, "eval_loss": 0.48372510075569153, "epoch": 242.10619469026548, "percentage": 34.5, "elapsed_time": "1:39:05", "remaining_time": "3:08:07", "throughput": 1318.83, "total_tokens": 7840696} {"current_steps": 13805, "total_steps": 40000, "loss": 0.0, "lr": 3.6691303700315796e-05, "epoch": 242.1946902654867, "percentage": 34.51, "elapsed_time": "1:39:09", "remaining_time": "3:08:08", "throughput": 1318.48, "total_tokens": 7843656} {"current_steps": 13810, "total_steps": 40000, "loss": 0.0, "lr": 3.668262500749655e-05, "epoch": 242.28318584070797, "percentage": 34.52, "elapsed_time": "1:39:11", "remaining_time": "3:08:05", "throughput": 1318.51, "total_tokens": 7846568} {"current_steps": 13815, "total_steps": 40000, "loss": 0.0, "lr": 3.667394451306971e-05, "epoch": 242.3716814159292, "percentage": 34.54, "elapsed_time": "1:39:13", "remaining_time": "3:08:03", "throughput": 1318.49, "total_tokens": 7849208} {"current_steps": 13820, "total_steps": 40000, "loss": 0.0, "lr": 3.666526221837393e-05, "epoch": 242.46017699115043, "percentage": 34.55, "elapsed_time": "1:39:15", "remaining_time": "3:08:01", "throughput": 1318.48, "total_tokens": 7851832} {"current_steps": 13825, "total_steps": 40000, "loss": 0.0, "lr": 3.665657812474812e-05, "epoch": 242.5486725663717, "percentage": 34.56, "elapsed_time": "1:39:17", "remaining_time": "3:07:59", "throughput": 1318.46, "total_tokens": 7854456} {"current_steps": 13830, "total_steps": 40000, "loss": 0.0, "lr": 3.664789223353147e-05, "epoch": 242.63716814159292, "percentage": 34.58, "elapsed_time": "1:39:19", "remaining_time": "3:07:56", "throughput": 1318.5, "total_tokens": 7857464} {"current_steps": 13835, "total_steps": 40000, "loss": 0.0, "lr": 3.663920454606347e-05, "epoch": 242.72566371681415, "percentage": 34.59, "elapsed_time": "1:39:21", "remaining_time": "3:07:54", "throughput": 1318.6, "total_tokens": 7860760} {"current_steps": 13840, "total_steps": 40000, "loss": 0.0, "lr": 3.6630515063683856e-05, "epoch": 242.81415929203538, "percentage": 34.6, "elapsed_time": "1:39:23", "remaining_time": "3:07:52", "throughput": 1318.59, "total_tokens": 7863448} {"current_steps": 13845, "total_steps": 40000, "loss": 0.0, "lr": 3.662182378773267e-05, "epoch": 242.90265486725664, "percentage": 34.61, "elapsed_time": "1:39:25", "remaining_time": "3:07:49", "throughput": 1318.62, "total_tokens": 7866360} {"current_steps": 13850, "total_steps": 40000, "loss": 0.0, "lr": 3.66131307195502e-05, "epoch": 242.99115044247787, "percentage": 34.62, "elapsed_time": "1:39:27", "remaining_time": "3:07:47", "throughput": 1318.8, "total_tokens": 7870088} {"current_steps": 13855, "total_steps": 40000, "loss": 0.0, "lr": 3.6604435860477034e-05, "epoch": 243.07079646017698, "percentage": 34.64, "elapsed_time": "1:39:29", "remaining_time": "3:07:45", "throughput": 1318.64, "total_tokens": 7872152} {"current_steps": 13860, "total_steps": 40000, "loss": 0.0, "lr": 3.6595739211854025e-05, "epoch": 243.15929203539824, "percentage": 34.65, "elapsed_time": "1:39:31", "remaining_time": "3:07:43", "throughput": 1318.63, "total_tokens": 7874824} {"current_steps": 13865, "total_steps": 40000, "loss": 0.0, "lr": 3.658704077502231e-05, "epoch": 243.24778761061947, "percentage": 34.66, "elapsed_time": "1:39:34", "remaining_time": "3:07:40", "throughput": 1318.64, "total_tokens": 7877576} {"current_steps": 13870, "total_steps": 40000, "loss": 0.0, "lr": 3.65783405513233e-05, "epoch": 243.3362831858407, "percentage": 34.67, "elapsed_time": "1:39:36", "remaining_time": "3:07:38", "throughput": 1318.62, "total_tokens": 7880216} {"current_steps": 13875, "total_steps": 40000, "loss": 0.0, "lr": 3.656963854209867e-05, "epoch": 243.42477876106196, "percentage": 34.69, "elapsed_time": "1:39:38", "remaining_time": "3:07:36", "throughput": 1318.65, "total_tokens": 7883096} {"current_steps": 13880, "total_steps": 40000, "loss": 0.0, "lr": 3.656093474869038e-05, "epoch": 243.5132743362832, "percentage": 34.7, "elapsed_time": "1:39:40", "remaining_time": "3:07:33", "throughput": 1318.7, "total_tokens": 7886120} {"current_steps": 13885, "total_steps": 40000, "loss": 0.0, "lr": 3.655222917244068e-05, "epoch": 243.60176991150442, "percentage": 34.71, "elapsed_time": "1:39:42", "remaining_time": "3:07:31", "throughput": 1318.72, "total_tokens": 7889000} {"current_steps": 13890, "total_steps": 40000, "loss": 0.0, "lr": 3.6543521814692054e-05, "epoch": 243.69026548672565, "percentage": 34.73, "elapsed_time": "1:39:44", "remaining_time": "3:07:29", "throughput": 1318.8, "total_tokens": 7892168} {"current_steps": 13895, "total_steps": 40000, "loss": 0.0, "lr": 3.653481267678731e-05, "epoch": 243.7787610619469, "percentage": 34.74, "elapsed_time": "1:39:46", "remaining_time": "3:07:26", "throughput": 1318.85, "total_tokens": 7895192} {"current_steps": 13900, "total_steps": 40000, "loss": 0.0, "lr": 3.652610176006949e-05, "epoch": 243.86725663716814, "percentage": 34.75, "elapsed_time": "1:39:48", "remaining_time": "3:07:24", "throughput": 1318.9, "total_tokens": 7898216} {"current_steps": 13905, "total_steps": 40000, "loss": 0.0, "lr": 3.6517389065881925e-05, "epoch": 243.95575221238937, "percentage": 34.76, "elapsed_time": "1:39:50", "remaining_time": "3:07:22", "throughput": 1318.96, "total_tokens": 7901288} {"current_steps": 13910, "total_steps": 40000, "loss": 0.0, "lr": 3.650867459556824e-05, "epoch": 244.0353982300885, "percentage": 34.77, "elapsed_time": "1:39:52", "remaining_time": "3:07:20", "throughput": 1318.87, "total_tokens": 7903720} {"current_steps": 13915, "total_steps": 40000, "loss": 0.0, "lr": 3.64999583504723e-05, "epoch": 244.12389380530973, "percentage": 34.79, "elapsed_time": "1:39:54", "remaining_time": "3:07:17", "throughput": 1318.82, "total_tokens": 7906184} {"current_steps": 13920, "total_steps": 40000, "loss": 0.0, "lr": 3.649124033193827e-05, "epoch": 244.21238938053096, "percentage": 34.8, "elapsed_time": "1:39:56", "remaining_time": "3:07:15", "throughput": 1318.82, "total_tokens": 7908888} {"current_steps": 13925, "total_steps": 40000, "loss": 0.0, "lr": 3.648252054131057e-05, "epoch": 244.30088495575222, "percentage": 34.81, "elapsed_time": "1:39:59", "remaining_time": "3:07:13", "throughput": 1318.84, "total_tokens": 7911736} {"current_steps": 13930, "total_steps": 40000, "loss": 0.0, "lr": 3.647379897993391e-05, "epoch": 244.38938053097345, "percentage": 34.83, "elapsed_time": "1:40:01", "remaining_time": "3:07:11", "throughput": 1318.9, "total_tokens": 7914840} {"current_steps": 13935, "total_steps": 40000, "loss": 0.0, "lr": 3.646507564915325e-05, "epoch": 244.47787610619469, "percentage": 34.84, "elapsed_time": "1:40:03", "remaining_time": "3:07:08", "throughput": 1318.97, "total_tokens": 7917976} {"current_steps": 13940, "total_steps": 40000, "loss": 0.0, "lr": 3.645635055031385e-05, "epoch": 244.56637168141592, "percentage": 34.85, "elapsed_time": "1:40:05", "remaining_time": "3:07:06", "throughput": 1318.99, "total_tokens": 7920792} {"current_steps": 13945, "total_steps": 40000, "loss": 0.0, "lr": 3.6447623684761224e-05, "epoch": 244.65486725663717, "percentage": 34.86, "elapsed_time": "1:40:07", "remaining_time": "3:07:04", "throughput": 1319.06, "total_tokens": 7923960} {"current_steps": 13950, "total_steps": 40000, "loss": 0.0, "lr": 3.643889505384117e-05, "epoch": 244.7433628318584, "percentage": 34.88, "elapsed_time": "1:40:09", "remaining_time": "3:07:01", "throughput": 1319.07, "total_tokens": 7926728} {"current_steps": 13955, "total_steps": 40000, "loss": 0.0, "lr": 3.6430164658899744e-05, "epoch": 244.83185840707964, "percentage": 34.89, "elapsed_time": "1:40:11", "remaining_time": "3:06:59", "throughput": 1319.06, "total_tokens": 7929432} {"current_steps": 13960, "total_steps": 40000, "loss": 0.0, "lr": 3.642143250128329e-05, "epoch": 244.9203539823009, "percentage": 34.9, "elapsed_time": "1:40:13", "remaining_time": "3:06:57", "throughput": 1319.07, "total_tokens": 7932200} {"current_steps": 13965, "total_steps": 40000, "loss": 0.0, "lr": 3.641269858233841e-05, "epoch": 245.0, "percentage": 34.91, "elapsed_time": "1:40:15", "remaining_time": "3:06:54", "throughput": 1319.0, "total_tokens": 7934424} {"current_steps": 13970, "total_steps": 40000, "loss": 0.0, "lr": 3.640396290341199e-05, "epoch": 245.08849557522123, "percentage": 34.92, "elapsed_time": "1:40:17", "remaining_time": "3:06:52", "throughput": 1319.03, "total_tokens": 7937624} {"current_steps": 13975, "total_steps": 40000, "loss": 0.0, "lr": 3.639522546585118e-05, "epoch": 245.1769911504425, "percentage": 34.94, "elapsed_time": "1:40:19", "remaining_time": "3:06:50", "throughput": 1319.05, "total_tokens": 7940504} {"current_steps": 13980, "total_steps": 40000, "loss": 0.0, "lr": 3.6386486271003404e-05, "epoch": 245.26548672566372, "percentage": 34.95, "elapsed_time": "1:40:21", "remaining_time": "3:06:48", "throughput": 1319.1, "total_tokens": 7943528} {"current_steps": 13985, "total_steps": 40000, "loss": 0.0, "lr": 3.6377745320216346e-05, "epoch": 245.35398230088495, "percentage": 34.96, "elapsed_time": "1:40:23", "remaining_time": "3:06:45", "throughput": 1319.18, "total_tokens": 7946728} {"current_steps": 13990, "total_steps": 40000, "loss": 0.0, "lr": 3.636900261483798e-05, "epoch": 245.44247787610618, "percentage": 34.98, "elapsed_time": "1:40:26", "remaining_time": "3:06:43", "throughput": 1319.18, "total_tokens": 7949480} {"current_steps": 13995, "total_steps": 40000, "loss": 0.0, "lr": 3.636025815621654e-05, "epoch": 245.53097345132744, "percentage": 34.99, "elapsed_time": "1:40:28", "remaining_time": "3:06:41", "throughput": 1319.16, "total_tokens": 7952056} {"current_steps": 14000, "total_steps": 40000, "loss": 0.0, "lr": 3.635151194570054e-05, "epoch": 245.61946902654867, "percentage": 35.0, "elapsed_time": "1:40:30", "remaining_time": "3:06:38", "throughput": 1319.13, "total_tokens": 7954632} {"current_steps": 14000, "total_steps": 40000, "eval_loss": 0.4702353775501251, "epoch": 245.61946902654867, "percentage": 35.0, "elapsed_time": "1:40:31", "remaining_time": "3:06:40", "throughput": 1318.9, "total_tokens": 7954632} {"current_steps": 14005, "total_steps": 40000, "loss": 0.0, "lr": 3.634276398463873e-05, "epoch": 245.7079646017699, "percentage": 35.01, "elapsed_time": "1:40:35", "remaining_time": "3:06:41", "throughput": 1318.57, "total_tokens": 7957656} {"current_steps": 14010, "total_steps": 40000, "loss": 0.0, "lr": 3.633401427438018e-05, "epoch": 245.79646017699116, "percentage": 35.02, "elapsed_time": "1:40:37", "remaining_time": "3:06:39", "throughput": 1318.56, "total_tokens": 7960280} {"current_steps": 14015, "total_steps": 40000, "loss": 0.0, "lr": 3.63252628162742e-05, "epoch": 245.8849557522124, "percentage": 35.04, "elapsed_time": "1:40:39", "remaining_time": "3:06:37", "throughput": 1318.5, "total_tokens": 7962648} {"current_steps": 14020, "total_steps": 40000, "loss": 0.0, "lr": 3.6316509611670364e-05, "epoch": 245.97345132743362, "percentage": 35.05, "elapsed_time": "1:40:41", "remaining_time": "3:06:34", "throughput": 1318.58, "total_tokens": 7965832} {"current_steps": 14025, "total_steps": 40000, "loss": 0.0, "lr": 3.630775466191854e-05, "epoch": 246.05309734513276, "percentage": 35.06, "elapsed_time": "1:40:43", "remaining_time": "3:06:32", "throughput": 1318.51, "total_tokens": 7968384} {"current_steps": 14030, "total_steps": 40000, "loss": 0.0, "lr": 3.629899796836884e-05, "epoch": 246.141592920354, "percentage": 35.08, "elapsed_time": "1:40:45", "remaining_time": "3:06:30", "throughput": 1318.53, "total_tokens": 7971264} {"current_steps": 14035, "total_steps": 40000, "loss": 0.0, "lr": 3.6290239532371666e-05, "epoch": 246.23008849557522, "percentage": 35.09, "elapsed_time": "1:40:47", "remaining_time": "3:06:28", "throughput": 1318.57, "total_tokens": 7974224} {"current_steps": 14040, "total_steps": 40000, "loss": 0.0, "lr": 3.628147935527767e-05, "epoch": 246.31858407079645, "percentage": 35.1, "elapsed_time": "1:40:49", "remaining_time": "3:06:25", "throughput": 1318.65, "total_tokens": 7977392} {"current_steps": 14045, "total_steps": 40000, "loss": 0.0, "lr": 3.627271743843779e-05, "epoch": 246.4070796460177, "percentage": 35.11, "elapsed_time": "1:40:51", "remaining_time": "3:06:23", "throughput": 1318.67, "total_tokens": 7980240} {"current_steps": 14050, "total_steps": 40000, "loss": 0.0, "lr": 3.626395378320321e-05, "epoch": 246.49557522123894, "percentage": 35.12, "elapsed_time": "1:40:53", "remaining_time": "3:06:21", "throughput": 1318.62, "total_tokens": 7982688} {"current_steps": 14055, "total_steps": 40000, "loss": 0.0, "lr": 3.625518839092541e-05, "epoch": 246.58407079646017, "percentage": 35.14, "elapsed_time": "1:40:55", "remaining_time": "3:06:18", "throughput": 1318.64, "total_tokens": 7985552} {"current_steps": 14060, "total_steps": 40000, "loss": 0.0, "lr": 3.624642126295612e-05, "epoch": 246.67256637168143, "percentage": 35.15, "elapsed_time": "1:40:57", "remaining_time": "3:06:16", "throughput": 1318.72, "total_tokens": 7988720} {"current_steps": 14065, "total_steps": 40000, "loss": 0.0, "lr": 3.6237652400647345e-05, "epoch": 246.76106194690266, "percentage": 35.16, "elapsed_time": "1:41:00", "remaining_time": "3:06:14", "throughput": 1318.79, "total_tokens": 7991920} {"current_steps": 14070, "total_steps": 40000, "loss": 0.0, "lr": 3.622888180535134e-05, "epoch": 246.8495575221239, "percentage": 35.17, "elapsed_time": "1:41:02", "remaining_time": "3:06:11", "throughput": 1318.77, "total_tokens": 7994512} {"current_steps": 14075, "total_steps": 40000, "loss": 0.0, "lr": 3.6220109478420655e-05, "epoch": 246.93805309734512, "percentage": 35.19, "elapsed_time": "1:41:04", "remaining_time": "3:06:09", "throughput": 1318.82, "total_tokens": 7997504} {"current_steps": 14080, "total_steps": 40000, "loss": 0.0, "lr": 3.6211335421208084e-05, "epoch": 247.01769911504425, "percentage": 35.2, "elapsed_time": "1:41:06", "remaining_time": "3:06:07", "throughput": 1318.72, "total_tokens": 7999840} {"current_steps": 14085, "total_steps": 40000, "loss": 0.0, "lr": 3.62025596350667e-05, "epoch": 247.10619469026548, "percentage": 35.21, "elapsed_time": "1:41:08", "remaining_time": "3:06:05", "throughput": 1318.77, "total_tokens": 8002880} {"current_steps": 14090, "total_steps": 40000, "loss": 0.0, "lr": 3.619378212134984e-05, "epoch": 247.1946902654867, "percentage": 35.23, "elapsed_time": "1:41:10", "remaining_time": "3:06:03", "throughput": 1318.77, "total_tokens": 8005616} {"current_steps": 14095, "total_steps": 40000, "loss": 0.0, "lr": 3.618500288141111e-05, "epoch": 247.28318584070797, "percentage": 35.24, "elapsed_time": "1:41:12", "remaining_time": "3:06:00", "throughput": 1318.75, "total_tokens": 8008224} {"current_steps": 14100, "total_steps": 40000, "loss": 0.0, "lr": 3.617622191660438e-05, "epoch": 247.3716814159292, "percentage": 35.25, "elapsed_time": "1:41:14", "remaining_time": "3:05:58", "throughput": 1318.73, "total_tokens": 8010832} {"current_steps": 14105, "total_steps": 40000, "loss": 0.0, "lr": 3.616743922828377e-05, "epoch": 247.46017699115043, "percentage": 35.26, "elapsed_time": "1:41:16", "remaining_time": "3:05:56", "throughput": 1318.79, "total_tokens": 8013952} {"current_steps": 14110, "total_steps": 40000, "loss": 0.0, "lr": 3.615865481780371e-05, "epoch": 247.5486725663717, "percentage": 35.27, "elapsed_time": "1:41:18", "remaining_time": "3:05:53", "throughput": 1318.74, "total_tokens": 8016352} {"current_steps": 14115, "total_steps": 40000, "loss": 0.0, "lr": 3.614986868651883e-05, "epoch": 247.63716814159292, "percentage": 35.29, "elapsed_time": "1:41:20", "remaining_time": "3:05:51", "throughput": 1318.89, "total_tokens": 8019968} {"current_steps": 14120, "total_steps": 40000, "loss": 0.0, "lr": 3.614108083578409e-05, "epoch": 247.72566371681415, "percentage": 35.3, "elapsed_time": "1:41:22", "remaining_time": "3:05:49", "throughput": 1318.92, "total_tokens": 8022880} {"current_steps": 14125, "total_steps": 40000, "loss": 0.0, "lr": 3.613229126695467e-05, "epoch": 247.81415929203538, "percentage": 35.31, "elapsed_time": "1:41:24", "remaining_time": "3:05:46", "throughput": 1318.92, "total_tokens": 8025632} {"current_steps": 14130, "total_steps": 40000, "loss": 0.0, "lr": 3.612349998138605e-05, "epoch": 247.90265486725664, "percentage": 35.33, "elapsed_time": "1:41:27", "remaining_time": "3:05:44", "throughput": 1318.92, "total_tokens": 8028320} {"current_steps": 14135, "total_steps": 40000, "loss": 0.0, "lr": 3.6114706980433946e-05, "epoch": 247.99115044247787, "percentage": 35.34, "elapsed_time": "1:41:29", "remaining_time": "3:05:42", "throughput": 1318.99, "total_tokens": 8031440} {"current_steps": 14140, "total_steps": 40000, "loss": 0.0, "lr": 3.610591226545435e-05, "epoch": 248.07079646017698, "percentage": 35.35, "elapsed_time": "1:41:31", "remaining_time": "3:05:40", "throughput": 1318.93, "total_tokens": 8034088} {"current_steps": 14145, "total_steps": 40000, "loss": 0.0, "lr": 3.6097115837803505e-05, "epoch": 248.15929203539824, "percentage": 35.36, "elapsed_time": "1:41:33", "remaining_time": "3:05:37", "throughput": 1318.89, "total_tokens": 8036616} {"current_steps": 14150, "total_steps": 40000, "loss": 0.0, "lr": 3.608831769883795e-05, "epoch": 248.24778761061947, "percentage": 35.38, "elapsed_time": "1:41:35", "remaining_time": "3:05:35", "throughput": 1319.01, "total_tokens": 8040040} {"current_steps": 14155, "total_steps": 40000, "loss": 0.0, "lr": 3.607951784991446e-05, "epoch": 248.3362831858407, "percentage": 35.39, "elapsed_time": "1:41:37", "remaining_time": "3:05:33", "throughput": 1319.05, "total_tokens": 8042968} {"current_steps": 14160, "total_steps": 40000, "loss": 0.0, "lr": 3.6070716292390085e-05, "epoch": 248.42477876106196, "percentage": 35.4, "elapsed_time": "1:41:39", "remaining_time": "3:05:30", "throughput": 1319.02, "total_tokens": 8045512} {"current_steps": 14165, "total_steps": 40000, "loss": 0.0, "lr": 3.606191302762213e-05, "epoch": 248.5132743362832, "percentage": 35.41, "elapsed_time": "1:41:41", "remaining_time": "3:05:28", "throughput": 1319.09, "total_tokens": 8048696} {"current_steps": 14170, "total_steps": 40000, "loss": 0.0, "lr": 3.605310805696818e-05, "epoch": 248.60176991150442, "percentage": 35.43, "elapsed_time": "1:41:43", "remaining_time": "3:05:26", "throughput": 1319.06, "total_tokens": 8051192} {"current_steps": 14175, "total_steps": 40000, "loss": 0.0, "lr": 3.6044301381786067e-05, "epoch": 248.69026548672565, "percentage": 35.44, "elapsed_time": "1:41:45", "remaining_time": "3:05:24", "throughput": 1319.11, "total_tokens": 8054232} {"current_steps": 14180, "total_steps": 40000, "loss": 0.0, "lr": 3.6035493003433883e-05, "epoch": 248.7787610619469, "percentage": 35.45, "elapsed_time": "1:41:47", "remaining_time": "3:05:21", "throughput": 1319.09, "total_tokens": 8056824} {"current_steps": 14185, "total_steps": 40000, "loss": 0.0, "lr": 3.6026682923269994e-05, "epoch": 248.86725663716814, "percentage": 35.46, "elapsed_time": "1:41:49", "remaining_time": "3:05:19", "throughput": 1319.15, "total_tokens": 8059928} {"current_steps": 14190, "total_steps": 40000, "loss": 0.0, "lr": 3.6017871142653034e-05, "epoch": 248.95575221238937, "percentage": 35.48, "elapsed_time": "1:41:51", "remaining_time": "3:05:17", "throughput": 1319.15, "total_tokens": 8062632} {"current_steps": 14195, "total_steps": 40000, "loss": 0.0, "lr": 3.600905766294189e-05, "epoch": 249.0353982300885, "percentage": 35.49, "elapsed_time": "1:41:54", "remaining_time": "3:05:15", "throughput": 1319.13, "total_tokens": 8065512} {"current_steps": 14200, "total_steps": 40000, "loss": 0.0, "lr": 3.60002424854957e-05, "epoch": 249.12389380530973, "percentage": 35.5, "elapsed_time": "1:41:56", "remaining_time": "3:05:12", "throughput": 1319.2, "total_tokens": 8068648} {"current_steps": 14200, "total_steps": 40000, "eval_loss": 0.49092504382133484, "epoch": 249.12389380530973, "percentage": 35.5, "elapsed_time": "1:41:57", "remaining_time": "3:05:14", "throughput": 1318.97, "total_tokens": 8068648} {"current_steps": 14205, "total_steps": 40000, "loss": 0.0, "lr": 3.5991425611673876e-05, "epoch": 249.21238938053096, "percentage": 35.51, "elapsed_time": "1:42:01", "remaining_time": "3:05:15", "throughput": 1318.57, "total_tokens": 8071144} {"current_steps": 14210, "total_steps": 40000, "loss": 0.0, "lr": 3.5982607042836105e-05, "epoch": 249.30088495575222, "percentage": 35.52, "elapsed_time": "1:42:03", "remaining_time": "3:05:13", "throughput": 1318.58, "total_tokens": 8073992} {"current_steps": 14215, "total_steps": 40000, "loss": 0.0, "lr": 3.597378678034231e-05, "epoch": 249.38938053097345, "percentage": 35.54, "elapsed_time": "1:42:05", "remaining_time": "3:05:10", "throughput": 1318.56, "total_tokens": 8076584} {"current_steps": 14220, "total_steps": 40000, "loss": 0.0, "lr": 3.596496482555269e-05, "epoch": 249.47787610619469, "percentage": 35.55, "elapsed_time": "1:42:07", "remaining_time": "3:05:08", "throughput": 1318.53, "total_tokens": 8079144} {"current_steps": 14225, "total_steps": 40000, "loss": 0.0, "lr": 3.595614117982769e-05, "epoch": 249.56637168141592, "percentage": 35.56, "elapsed_time": "1:42:09", "remaining_time": "3:05:06", "throughput": 1318.58, "total_tokens": 8082184} {"current_steps": 14230, "total_steps": 40000, "loss": 0.0, "lr": 3.594731584452805e-05, "epoch": 249.65486725663717, "percentage": 35.58, "elapsed_time": "1:42:11", "remaining_time": "3:05:03", "throughput": 1318.63, "total_tokens": 8085208} {"current_steps": 14235, "total_steps": 40000, "loss": 0.0, "lr": 3.593848882101472e-05, "epoch": 249.7433628318584, "percentage": 35.59, "elapsed_time": "1:42:13", "remaining_time": "3:05:01", "throughput": 1318.72, "total_tokens": 8088440} {"current_steps": 14240, "total_steps": 40000, "loss": 0.0, "lr": 3.592966011064896e-05, "epoch": 249.83185840707964, "percentage": 35.6, "elapsed_time": "1:42:15", "remaining_time": "3:04:59", "throughput": 1318.68, "total_tokens": 8090952} {"current_steps": 14245, "total_steps": 40000, "loss": 0.0, "lr": 3.592082971479226e-05, "epoch": 249.9203539823009, "percentage": 35.61, "elapsed_time": "1:42:17", "remaining_time": "3:04:56", "throughput": 1318.7, "total_tokens": 8093816} {"current_steps": 14250, "total_steps": 40000, "loss": 0.0, "lr": 3.5911997634806385e-05, "epoch": 250.0, "percentage": 35.62, "elapsed_time": "1:42:19", "remaining_time": "3:04:54", "throughput": 1318.66, "total_tokens": 8096192} {"current_steps": 14255, "total_steps": 40000, "loss": 0.0, "lr": 3.5903163872053336e-05, "epoch": 250.08849557522123, "percentage": 35.64, "elapsed_time": "1:42:22", "remaining_time": "3:04:52", "throughput": 1318.57, "total_tokens": 8098672} {"current_steps": 14260, "total_steps": 40000, "loss": 0.0, "lr": 3.58943284278954e-05, "epoch": 250.1769911504425, "percentage": 35.65, "elapsed_time": "1:42:24", "remaining_time": "3:04:50", "throughput": 1318.59, "total_tokens": 8101504} {"current_steps": 14265, "total_steps": 40000, "loss": 0.0, "lr": 3.588549130369512e-05, "epoch": 250.26548672566372, "percentage": 35.66, "elapsed_time": "1:42:26", "remaining_time": "3:04:48", "throughput": 1318.7, "total_tokens": 8104944} {"current_steps": 14270, "total_steps": 40000, "loss": 0.0, "lr": 3.5876652500815274e-05, "epoch": 250.35398230088495, "percentage": 35.68, "elapsed_time": "1:42:28", "remaining_time": "3:04:45", "throughput": 1318.74, "total_tokens": 8107904} {"current_steps": 14275, "total_steps": 40000, "loss": 0.0, "lr": 3.586781202061894e-05, "epoch": 250.44247787610618, "percentage": 35.69, "elapsed_time": "1:42:30", "remaining_time": "3:04:43", "throughput": 1318.74, "total_tokens": 8110656} {"current_steps": 14280, "total_steps": 40000, "loss": 0.0, "lr": 3.585896986446942e-05, "epoch": 250.53097345132744, "percentage": 35.7, "elapsed_time": "1:42:32", "remaining_time": "3:04:41", "throughput": 1318.73, "total_tokens": 8113280} {"current_steps": 14285, "total_steps": 40000, "loss": 0.0, "lr": 3.585012603373028e-05, "epoch": 250.61946902654867, "percentage": 35.71, "elapsed_time": "1:42:34", "remaining_time": "3:04:38", "throughput": 1318.72, "total_tokens": 8115984} {"current_steps": 14290, "total_steps": 40000, "loss": 0.0, "lr": 3.584128052976535e-05, "epoch": 250.7079646017699, "percentage": 35.73, "elapsed_time": "1:42:36", "remaining_time": "3:04:36", "throughput": 1318.77, "total_tokens": 8119008} {"current_steps": 14295, "total_steps": 40000, "loss": 0.0, "lr": 3.5832433353938724e-05, "epoch": 250.79646017699116, "percentage": 35.74, "elapsed_time": "1:42:38", "remaining_time": "3:04:34", "throughput": 1318.78, "total_tokens": 8121792} {"current_steps": 14300, "total_steps": 40000, "loss": 0.0, "lr": 3.5823584507614746e-05, "epoch": 250.8849557522124, "percentage": 35.75, "elapsed_time": "1:42:40", "remaining_time": "3:04:31", "throughput": 1318.84, "total_tokens": 8124832} {"current_steps": 14305, "total_steps": 40000, "loss": 0.0, "lr": 3.581473399215802e-05, "epoch": 250.97345132743362, "percentage": 35.76, "elapsed_time": "1:42:42", "remaining_time": "3:04:29", "throughput": 1318.84, "total_tokens": 8127536} {"current_steps": 14310, "total_steps": 40000, "loss": 0.0, "lr": 3.580588180893341e-05, "epoch": 251.05309734513276, "percentage": 35.77, "elapsed_time": "1:42:44", "remaining_time": "3:04:27", "throughput": 1318.75, "total_tokens": 8129992} {"current_steps": 14315, "total_steps": 40000, "loss": 0.0, "lr": 3.579702795930602e-05, "epoch": 251.141592920354, "percentage": 35.79, "elapsed_time": "1:42:46", "remaining_time": "3:04:25", "throughput": 1318.79, "total_tokens": 8133000} {"current_steps": 14320, "total_steps": 40000, "loss": 0.0, "lr": 3.578817244464125e-05, "epoch": 251.23008849557522, "percentage": 35.8, "elapsed_time": "1:42:49", "remaining_time": "3:04:22", "throughput": 1318.78, "total_tokens": 8135608} {"current_steps": 14325, "total_steps": 40000, "loss": 0.0, "lr": 3.577931526630471e-05, "epoch": 251.31858407079645, "percentage": 35.81, "elapsed_time": "1:42:51", "remaining_time": "3:04:20", "throughput": 1318.85, "total_tokens": 8138792} {"current_steps": 14330, "total_steps": 40000, "loss": 0.0, "lr": 3.577045642566229e-05, "epoch": 251.4070796460177, "percentage": 35.83, "elapsed_time": "1:42:53", "remaining_time": "3:04:18", "throughput": 1318.83, "total_tokens": 8141400} {"current_steps": 14335, "total_steps": 40000, "loss": 0.0, "lr": 3.576159592408014e-05, "epoch": 251.49557522123894, "percentage": 35.84, "elapsed_time": "1:42:55", "remaining_time": "3:04:16", "throughput": 1318.86, "total_tokens": 8144280} {"current_steps": 14340, "total_steps": 40000, "loss": 0.0, "lr": 3.575273376292466e-05, "epoch": 251.58407079646017, "percentage": 35.85, "elapsed_time": "1:42:57", "remaining_time": "3:04:13", "throughput": 1318.9, "total_tokens": 8147272} {"current_steps": 14345, "total_steps": 40000, "loss": 0.0, "lr": 3.574386994356251e-05, "epoch": 251.67256637168143, "percentage": 35.86, "elapsed_time": "1:42:59", "remaining_time": "3:04:11", "throughput": 1318.93, "total_tokens": 8150232} {"current_steps": 14350, "total_steps": 40000, "loss": 0.0, "lr": 3.573500446736059e-05, "epoch": 251.76106194690266, "percentage": 35.88, "elapsed_time": "1:43:01", "remaining_time": "3:04:09", "throughput": 1318.94, "total_tokens": 8153000} {"current_steps": 14355, "total_steps": 40000, "loss": 0.0, "lr": 3.5726137335686094e-05, "epoch": 251.8495575221239, "percentage": 35.89, "elapsed_time": "1:43:03", "remaining_time": "3:04:06", "throughput": 1318.94, "total_tokens": 8155768} {"current_steps": 14360, "total_steps": 40000, "loss": 0.0, "lr": 3.571726854990642e-05, "epoch": 251.93805309734512, "percentage": 35.9, "elapsed_time": "1:43:05", "remaining_time": "3:04:04", "throughput": 1318.98, "total_tokens": 8158712} {"current_steps": 14365, "total_steps": 40000, "loss": 0.0, "lr": 3.570839811138925e-05, "epoch": 252.01769911504425, "percentage": 35.91, "elapsed_time": "1:43:07", "remaining_time": "3:04:02", "throughput": 1318.97, "total_tokens": 8161616} {"current_steps": 14370, "total_steps": 40000, "loss": 0.0, "lr": 3.569952602150252e-05, "epoch": 252.10619469026548, "percentage": 35.93, "elapsed_time": "1:43:09", "remaining_time": "3:04:00", "throughput": 1319.0, "total_tokens": 8164576} {"current_steps": 14375, "total_steps": 40000, "loss": 0.0, "lr": 3.569065228161442e-05, "epoch": 252.1946902654867, "percentage": 35.94, "elapsed_time": "1:43:12", "remaining_time": "3:03:57", "throughput": 1319.02, "total_tokens": 8167376} {"current_steps": 14380, "total_steps": 40000, "loss": 0.0, "lr": 3.5681776893093395e-05, "epoch": 252.28318584070797, "percentage": 35.95, "elapsed_time": "1:43:14", "remaining_time": "3:03:55", "throughput": 1319.01, "total_tokens": 8170064} {"current_steps": 14385, "total_steps": 40000, "loss": 0.0, "lr": 3.5672899857308134e-05, "epoch": 252.3716814159292, "percentage": 35.96, "elapsed_time": "1:43:16", "remaining_time": "3:03:53", "throughput": 1318.93, "total_tokens": 8172304} {"current_steps": 14390, "total_steps": 40000, "loss": 0.0, "lr": 3.566402117562759e-05, "epoch": 252.46017699115043, "percentage": 35.98, "elapsed_time": "1:43:18", "remaining_time": "3:03:51", "throughput": 1319.03, "total_tokens": 8175664} {"current_steps": 14395, "total_steps": 40000, "loss": 0.0, "lr": 3.565514084942097e-05, "epoch": 252.5486725663717, "percentage": 35.99, "elapsed_time": "1:43:20", "remaining_time": "3:03:48", "throughput": 1319.1, "total_tokens": 8178800} {"current_steps": 14400, "total_steps": 40000, "loss": 0.0, "lr": 3.564625888005773e-05, "epoch": 252.63716814159292, "percentage": 36.0, "elapsed_time": "1:43:22", "remaining_time": "3:03:46", "throughput": 1319.15, "total_tokens": 8181840} {"current_steps": 14400, "total_steps": 40000, "eval_loss": 0.48222678899765015, "epoch": 252.63716814159292, "percentage": 36.0, "elapsed_time": "1:43:23", "remaining_time": "3:03:48", "throughput": 1318.92, "total_tokens": 8181840} {"current_steps": 14405, "total_steps": 40000, "loss": 0.0, "lr": 3.563737526890759e-05, "epoch": 252.72566371681415, "percentage": 36.01, "elapsed_time": "1:43:27", "remaining_time": "3:03:48", "throughput": 1318.73, "total_tokens": 8185568} {"current_steps": 14410, "total_steps": 40000, "loss": 0.0, "lr": 3.562849001734049e-05, "epoch": 252.81415929203538, "percentage": 36.02, "elapsed_time": "1:43:29", "remaining_time": "3:03:46", "throughput": 1318.72, "total_tokens": 8188272} {"current_steps": 14415, "total_steps": 40000, "loss": 0.0, "lr": 3.561960312672667e-05, "epoch": 252.90265486725664, "percentage": 36.04, "elapsed_time": "1:43:31", "remaining_time": "3:03:44", "throughput": 1318.72, "total_tokens": 8190960} {"current_steps": 14420, "total_steps": 40000, "loss": 0.0, "lr": 3.5610714598436596e-05, "epoch": 252.99115044247787, "percentage": 36.05, "elapsed_time": "1:43:33", "remaining_time": "3:03:42", "throughput": 1318.66, "total_tokens": 8193312} {"current_steps": 14425, "total_steps": 40000, "loss": 0.0, "lr": 3.5601824433840986e-05, "epoch": 253.07079646017698, "percentage": 36.06, "elapsed_time": "1:43:35", "remaining_time": "3:03:40", "throughput": 1318.53, "total_tokens": 8195488} {"current_steps": 14430, "total_steps": 40000, "loss": 0.0, "lr": 3.559293263431082e-05, "epoch": 253.15929203539824, "percentage": 36.08, "elapsed_time": "1:43:37", "remaining_time": "3:03:37", "throughput": 1318.56, "total_tokens": 8198384} {"current_steps": 14435, "total_steps": 40000, "loss": 0.0, "lr": 3.558403920121732e-05, "epoch": 253.24778761061947, "percentage": 36.09, "elapsed_time": "1:43:39", "remaining_time": "3:03:35", "throughput": 1318.52, "total_tokens": 8200880} {"current_steps": 14440, "total_steps": 40000, "loss": 0.0, "lr": 3.557514413593197e-05, "epoch": 253.3362831858407, "percentage": 36.1, "elapsed_time": "1:43:41", "remaining_time": "3:03:33", "throughput": 1318.53, "total_tokens": 8203680} {"current_steps": 14445, "total_steps": 40000, "loss": 0.0, "lr": 3.55662474398265e-05, "epoch": 253.42477876106196, "percentage": 36.11, "elapsed_time": "1:43:43", "remaining_time": "3:03:30", "throughput": 1318.54, "total_tokens": 8206480} {"current_steps": 14450, "total_steps": 40000, "loss": 0.0, "lr": 3.555734911427288e-05, "epoch": 253.5132743362832, "percentage": 36.12, "elapsed_time": "1:43:45", "remaining_time": "3:03:28", "throughput": 1318.6, "total_tokens": 8209584} {"current_steps": 14455, "total_steps": 40000, "loss": 0.0, "lr": 3.5548449160643363e-05, "epoch": 253.60176991150442, "percentage": 36.14, "elapsed_time": "1:43:48", "remaining_time": "3:03:26", "throughput": 1318.67, "total_tokens": 8212720} {"current_steps": 14460, "total_steps": 40000, "loss": 0.0, "lr": 3.553954758031043e-05, "epoch": 253.69026548672565, "percentage": 36.15, "elapsed_time": "1:43:50", "remaining_time": "3:03:23", "throughput": 1318.64, "total_tokens": 8215296} {"current_steps": 14465, "total_steps": 40000, "loss": 0.0, "lr": 3.5530644374646815e-05, "epoch": 253.7787610619469, "percentage": 36.16, "elapsed_time": "1:43:52", "remaining_time": "3:03:21", "throughput": 1318.77, "total_tokens": 8218864} {"current_steps": 14470, "total_steps": 40000, "loss": 0.0, "lr": 3.552173954502549e-05, "epoch": 253.86725663716814, "percentage": 36.18, "elapsed_time": "1:43:54", "remaining_time": "3:03:19", "throughput": 1318.81, "total_tokens": 8221824} {"current_steps": 14475, "total_steps": 40000, "loss": 0.0, "lr": 3.55128330928197e-05, "epoch": 253.95575221238937, "percentage": 36.19, "elapsed_time": "1:43:56", "remaining_time": "3:03:17", "throughput": 1318.77, "total_tokens": 8224288} {"current_steps": 14480, "total_steps": 40000, "loss": 0.0, "lr": 3.550392501940294e-05, "epoch": 254.0353982300885, "percentage": 36.2, "elapsed_time": "1:43:58", "remaining_time": "3:03:15", "throughput": 1318.7, "total_tokens": 8226832} {"current_steps": 14485, "total_steps": 40000, "loss": 0.0, "lr": 3.5495015326148945e-05, "epoch": 254.12389380530973, "percentage": 36.21, "elapsed_time": "1:44:00", "remaining_time": "3:03:12", "throughput": 1318.72, "total_tokens": 8229712} {"current_steps": 14490, "total_steps": 40000, "loss": 0.0, "lr": 3.548610401443169e-05, "epoch": 254.21238938053096, "percentage": 36.23, "elapsed_time": "1:44:02", "remaining_time": "3:03:10", "throughput": 1318.65, "total_tokens": 8232016} {"current_steps": 14495, "total_steps": 40000, "loss": 0.0, "lr": 3.547719108562543e-05, "epoch": 254.30088495575222, "percentage": 36.24, "elapsed_time": "1:44:04", "remaining_time": "3:03:08", "throughput": 1318.7, "total_tokens": 8235040} {"current_steps": 14500, "total_steps": 40000, "loss": 0.0, "lr": 3.546827654110464e-05, "epoch": 254.38938053097345, "percentage": 36.25, "elapsed_time": "1:44:06", "remaining_time": "3:03:05", "throughput": 1318.86, "total_tokens": 8238784} {"current_steps": 14505, "total_steps": 40000, "loss": 0.0, "lr": 3.545936038224405e-05, "epoch": 254.47787610619469, "percentage": 36.26, "elapsed_time": "1:44:08", "remaining_time": "3:03:03", "throughput": 1318.84, "total_tokens": 8241408} {"current_steps": 14510, "total_steps": 40000, "loss": 0.0, "lr": 3.545044261041864e-05, "epoch": 254.56637168141592, "percentage": 36.27, "elapsed_time": "1:44:11", "remaining_time": "3:03:01", "throughput": 1318.87, "total_tokens": 8244320} {"current_steps": 14515, "total_steps": 40000, "loss": 0.0, "lr": 3.5441523227003657e-05, "epoch": 254.65486725663717, "percentage": 36.29, "elapsed_time": "1:44:13", "remaining_time": "3:02:59", "throughput": 1318.85, "total_tokens": 8246896} {"current_steps": 14520, "total_steps": 40000, "loss": 0.0, "lr": 3.543260223337459e-05, "epoch": 254.7433628318584, "percentage": 36.3, "elapsed_time": "1:44:15", "remaining_time": "3:02:56", "throughput": 1318.88, "total_tokens": 8249840} {"current_steps": 14525, "total_steps": 40000, "loss": 0.0, "lr": 3.542367963090714e-05, "epoch": 254.83185840707964, "percentage": 36.31, "elapsed_time": "1:44:17", "remaining_time": "3:02:54", "throughput": 1318.9, "total_tokens": 8252672} {"current_steps": 14530, "total_steps": 40000, "loss": 0.0, "lr": 3.5414755420977295e-05, "epoch": 254.9203539823009, "percentage": 36.33, "elapsed_time": "1:44:19", "remaining_time": "3:02:52", "throughput": 1318.98, "total_tokens": 8255904} {"current_steps": 14535, "total_steps": 40000, "loss": 0.0, "lr": 3.54058296049613e-05, "epoch": 255.0, "percentage": 36.34, "elapsed_time": "1:44:21", "remaining_time": "3:02:49", "throughput": 1318.95, "total_tokens": 8258352} {"current_steps": 14540, "total_steps": 40000, "loss": 0.0, "lr": 3.53969021842356e-05, "epoch": 255.08849557522123, "percentage": 36.35, "elapsed_time": "1:44:23", "remaining_time": "3:02:47", "throughput": 1318.89, "total_tokens": 8261040} {"current_steps": 14545, "total_steps": 40000, "loss": 0.0, "lr": 3.5387973160176926e-05, "epoch": 255.1769911504425, "percentage": 36.36, "elapsed_time": "1:44:25", "remaining_time": "3:02:45", "throughput": 1318.88, "total_tokens": 8263712} {"current_steps": 14550, "total_steps": 40000, "loss": 0.0, "lr": 3.537904253416224e-05, "epoch": 255.26548672566372, "percentage": 36.38, "elapsed_time": "1:44:27", "remaining_time": "3:02:43", "throughput": 1318.82, "total_tokens": 8266016} {"current_steps": 14555, "total_steps": 40000, "loss": 0.0, "lr": 3.537011030756878e-05, "epoch": 255.35398230088495, "percentage": 36.39, "elapsed_time": "1:44:29", "remaining_time": "3:02:40", "throughput": 1318.84, "total_tokens": 8268928} {"current_steps": 14560, "total_steps": 40000, "loss": 0.0, "lr": 3.536117648177399e-05, "epoch": 255.44247787610618, "percentage": 36.4, "elapsed_time": "1:44:31", "remaining_time": "3:02:38", "throughput": 1318.97, "total_tokens": 8272432} {"current_steps": 14565, "total_steps": 40000, "loss": 0.0, "lr": 3.535224105815558e-05, "epoch": 255.53097345132744, "percentage": 36.41, "elapsed_time": "1:44:33", "remaining_time": "3:02:36", "throughput": 1318.93, "total_tokens": 8274912} {"current_steps": 14570, "total_steps": 40000, "loss": 0.0, "lr": 3.5343304038091494e-05, "epoch": 255.61946902654867, "percentage": 36.43, "elapsed_time": "1:44:36", "remaining_time": "3:02:33", "throughput": 1318.99, "total_tokens": 8278032} {"current_steps": 14575, "total_steps": 40000, "loss": 0.0, "lr": 3.5334365422959955e-05, "epoch": 255.7079646017699, "percentage": 36.44, "elapsed_time": "1:44:38", "remaining_time": "3:02:31", "throughput": 1319.01, "total_tokens": 8280896} {"current_steps": 14580, "total_steps": 40000, "loss": 0.0, "lr": 3.5325425214139396e-05, "epoch": 255.79646017699116, "percentage": 36.45, "elapsed_time": "1:44:40", "remaining_time": "3:02:29", "throughput": 1319.01, "total_tokens": 8283616} {"current_steps": 14585, "total_steps": 40000, "loss": 0.0, "lr": 3.531648341300851e-05, "epoch": 255.8849557522124, "percentage": 36.46, "elapsed_time": "1:44:42", "remaining_time": "3:02:27", "throughput": 1319.02, "total_tokens": 8286352} {"current_steps": 14590, "total_steps": 40000, "loss": 0.0, "lr": 3.530754002094623e-05, "epoch": 255.97345132743362, "percentage": 36.48, "elapsed_time": "1:44:44", "remaining_time": "3:02:24", "throughput": 1319.12, "total_tokens": 8289728} {"current_steps": 14595, "total_steps": 40000, "loss": 0.0, "lr": 3.529859503933175e-05, "epoch": 256.05309734513276, "percentage": 36.49, "elapsed_time": "1:44:46", "remaining_time": "3:02:22", "throughput": 1318.97, "total_tokens": 8291776} {"current_steps": 14600, "total_steps": 40000, "loss": 0.0, "lr": 3.52896484695445e-05, "epoch": 256.14159292035396, "percentage": 36.5, "elapsed_time": "1:44:48", "remaining_time": "3:02:20", "throughput": 1319.03, "total_tokens": 8294896} {"current_steps": 14600, "total_steps": 40000, "eval_loss": 0.4791489839553833, "epoch": 256.14159292035396, "percentage": 36.5, "elapsed_time": "1:44:49", "remaining_time": "3:02:22", "throughput": 1318.81, "total_tokens": 8294896} {"current_steps": 14605, "total_steps": 40000, "loss": 0.0, "lr": 3.528070031296414e-05, "epoch": 256.2300884955752, "percentage": 36.51, "elapsed_time": "1:44:53", "remaining_time": "3:02:22", "throughput": 1318.47, "total_tokens": 8297696} {"current_steps": 14610, "total_steps": 40000, "loss": 0.0, "lr": 3.5271750570970605e-05, "epoch": 256.3185840707965, "percentage": 36.52, "elapsed_time": "1:44:55", "remaining_time": "3:02:20", "throughput": 1318.48, "total_tokens": 8300496} {"current_steps": 14615, "total_steps": 40000, "loss": 0.0, "lr": 3.526279924494405e-05, "epoch": 256.4070796460177, "percentage": 36.54, "elapsed_time": "1:44:57", "remaining_time": "3:02:18", "throughput": 1318.52, "total_tokens": 8303488} {"current_steps": 14620, "total_steps": 40000, "loss": 0.0, "lr": 3.5253846336264874e-05, "epoch": 256.49557522123894, "percentage": 36.55, "elapsed_time": "1:44:59", "remaining_time": "3:02:16", "throughput": 1318.59, "total_tokens": 8306624} {"current_steps": 14625, "total_steps": 40000, "loss": 0.0, "lr": 3.5244891846313736e-05, "epoch": 256.5840707964602, "percentage": 36.56, "elapsed_time": "1:45:01", "remaining_time": "3:02:13", "throughput": 1318.57, "total_tokens": 8309264} {"current_steps": 14630, "total_steps": 40000, "loss": 0.0, "lr": 3.5235935776471527e-05, "epoch": 256.6725663716814, "percentage": 36.58, "elapsed_time": "1:45:03", "remaining_time": "3:02:11", "throughput": 1318.61, "total_tokens": 8312208} {"current_steps": 14635, "total_steps": 40000, "loss": 0.0, "lr": 3.522697812811939e-05, "epoch": 256.76106194690266, "percentage": 36.59, "elapsed_time": "1:45:05", "remaining_time": "3:02:09", "throughput": 1318.56, "total_tokens": 8314656} {"current_steps": 14640, "total_steps": 40000, "loss": 0.0, "lr": 3.521801890263871e-05, "epoch": 256.8495575221239, "percentage": 36.6, "elapsed_time": "1:45:07", "remaining_time": "3:02:06", "throughput": 1318.62, "total_tokens": 8317728} {"current_steps": 14645, "total_steps": 40000, "loss": 0.0, "lr": 3.5209058101411114e-05, "epoch": 256.9380530973451, "percentage": 36.61, "elapsed_time": "1:45:09", "remaining_time": "3:02:04", "throughput": 1318.72, "total_tokens": 8321104} {"current_steps": 14650, "total_steps": 40000, "loss": 0.0, "lr": 3.520009572581845e-05, "epoch": 257.01769911504425, "percentage": 36.62, "elapsed_time": "1:45:12", "remaining_time": "3:02:02", "throughput": 1318.6, "total_tokens": 8323296} {"current_steps": 14655, "total_steps": 40000, "loss": 0.0, "lr": 3.519113177724285e-05, "epoch": 257.1061946902655, "percentage": 36.64, "elapsed_time": "1:45:14", "remaining_time": "3:02:00", "throughput": 1318.59, "total_tokens": 8325968} {"current_steps": 14660, "total_steps": 40000, "loss": 0.0, "lr": 3.5182166257066656e-05, "epoch": 257.1946902654867, "percentage": 36.65, "elapsed_time": "1:45:16", "remaining_time": "3:01:57", "throughput": 1318.59, "total_tokens": 8328688} {"current_steps": 14665, "total_steps": 40000, "loss": 0.0, "lr": 3.517319916667247e-05, "epoch": 257.283185840708, "percentage": 36.66, "elapsed_time": "1:45:18", "remaining_time": "3:01:55", "throughput": 1318.58, "total_tokens": 8331392} {"current_steps": 14670, "total_steps": 40000, "loss": 0.0, "lr": 3.516423050744313e-05, "epoch": 257.37168141592923, "percentage": 36.68, "elapsed_time": "1:45:20", "remaining_time": "3:01:53", "throughput": 1318.66, "total_tokens": 8334592} {"current_steps": 14675, "total_steps": 40000, "loss": 0.0, "lr": 3.5155260280761704e-05, "epoch": 257.46017699115043, "percentage": 36.69, "elapsed_time": "1:45:22", "remaining_time": "3:01:50", "throughput": 1318.69, "total_tokens": 8337504} {"current_steps": 14680, "total_steps": 40000, "loss": 0.0, "lr": 3.514628848801154e-05, "epoch": 257.5486725663717, "percentage": 36.7, "elapsed_time": "1:45:24", "remaining_time": "3:01:48", "throughput": 1318.74, "total_tokens": 8340528} {"current_steps": 14685, "total_steps": 40000, "loss": 0.0, "lr": 3.5137315130576174e-05, "epoch": 257.6371681415929, "percentage": 36.71, "elapsed_time": "1:45:26", "remaining_time": "3:01:46", "throughput": 1318.72, "total_tokens": 8343168} {"current_steps": 14690, "total_steps": 40000, "loss": 0.0, "lr": 3.512834020983942e-05, "epoch": 257.72566371681415, "percentage": 36.73, "elapsed_time": "1:45:28", "remaining_time": "3:01:44", "throughput": 1318.79, "total_tokens": 8346304} {"current_steps": 14695, "total_steps": 40000, "loss": 0.0, "lr": 3.5119363727185334e-05, "epoch": 257.8141592920354, "percentage": 36.74, "elapsed_time": "1:45:30", "remaining_time": "3:01:41", "throughput": 1318.81, "total_tokens": 8349152} {"current_steps": 14700, "total_steps": 40000, "loss": 0.0, "lr": 3.511038568399819e-05, "epoch": 257.9026548672566, "percentage": 36.75, "elapsed_time": "1:45:32", "remaining_time": "3:01:39", "throughput": 1318.82, "total_tokens": 8351952} {"current_steps": 14705, "total_steps": 40000, "loss": 0.0, "lr": 3.510140608166251e-05, "epoch": 257.9911504424779, "percentage": 36.76, "elapsed_time": "1:45:34", "remaining_time": "3:01:37", "throughput": 1318.94, "total_tokens": 8355408} {"current_steps": 14710, "total_steps": 40000, "loss": 0.0, "lr": 3.509242492156308e-05, "epoch": 258.070796460177, "percentage": 36.78, "elapsed_time": "1:45:37", "remaining_time": "3:01:35", "throughput": 1318.78, "total_tokens": 8357384} {"current_steps": 14715, "total_steps": 40000, "loss": 0.0, "lr": 3.5083442205084896e-05, "epoch": 258.1592920353982, "percentage": 36.79, "elapsed_time": "1:45:39", "remaining_time": "3:01:32", "throughput": 1318.82, "total_tokens": 8360360} {"current_steps": 14720, "total_steps": 40000, "loss": 0.0, "lr": 3.507445793361321e-05, "epoch": 258.24778761061947, "percentage": 36.8, "elapsed_time": "1:45:41", "remaining_time": "3:01:30", "throughput": 1318.82, "total_tokens": 8363064} {"current_steps": 14725, "total_steps": 40000, "loss": 0.0, "lr": 3.5065472108533505e-05, "epoch": 258.3362831858407, "percentage": 36.81, "elapsed_time": "1:45:43", "remaining_time": "3:01:28", "throughput": 1318.86, "total_tokens": 8366088} {"current_steps": 14730, "total_steps": 40000, "loss": 0.0, "lr": 3.5056484731231504e-05, "epoch": 258.42477876106193, "percentage": 36.83, "elapsed_time": "1:45:45", "remaining_time": "3:01:25", "throughput": 1318.82, "total_tokens": 8368568} {"current_steps": 14735, "total_steps": 40000, "loss": 0.0, "lr": 3.504749580309319e-05, "epoch": 258.5132743362832, "percentage": 36.84, "elapsed_time": "1:45:47", "remaining_time": "3:01:23", "throughput": 1318.94, "total_tokens": 8372072} {"current_steps": 14740, "total_steps": 40000, "loss": 0.0, "lr": 3.5038505325504753e-05, "epoch": 258.60176991150445, "percentage": 36.85, "elapsed_time": "1:45:49", "remaining_time": "3:01:21", "throughput": 1319.06, "total_tokens": 8375512} {"current_steps": 14745, "total_steps": 40000, "loss": 0.0, "lr": 3.502951329985264e-05, "epoch": 258.69026548672565, "percentage": 36.86, "elapsed_time": "1:45:51", "remaining_time": "3:01:19", "throughput": 1319.08, "total_tokens": 8378376} {"current_steps": 14750, "total_steps": 40000, "loss": 0.0, "lr": 3.502051972752354e-05, "epoch": 258.7787610619469, "percentage": 36.88, "elapsed_time": "1:45:53", "remaining_time": "3:01:16", "throughput": 1319.04, "total_tokens": 8380824} {"current_steps": 14755, "total_steps": 40000, "loss": 0.0, "lr": 3.5011524609904374e-05, "epoch": 258.86725663716817, "percentage": 36.89, "elapsed_time": "1:45:55", "remaining_time": "3:01:14", "throughput": 1319.06, "total_tokens": 8383688} {"current_steps": 14760, "total_steps": 40000, "loss": 0.0, "lr": 3.50025279483823e-05, "epoch": 258.95575221238937, "percentage": 36.9, "elapsed_time": "1:45:57", "remaining_time": "3:01:12", "throughput": 1319.09, "total_tokens": 8386616} {"current_steps": 14765, "total_steps": 40000, "loss": 0.0, "lr": 3.499352974434472e-05, "epoch": 259.0353982300885, "percentage": 36.91, "elapsed_time": "1:46:00", "remaining_time": "3:01:10", "throughput": 1319.01, "total_tokens": 8389072} {"current_steps": 14770, "total_steps": 40000, "loss": 0.0, "lr": 3.498452999917926e-05, "epoch": 259.12389380530976, "percentage": 36.93, "elapsed_time": "1:46:02", "remaining_time": "3:01:07", "throughput": 1319.05, "total_tokens": 8392064} {"current_steps": 14775, "total_steps": 40000, "loss": 0.0, "lr": 3.4975528714273795e-05, "epoch": 259.21238938053096, "percentage": 36.94, "elapsed_time": "1:46:04", "remaining_time": "3:01:05", "throughput": 1319.06, "total_tokens": 8394864} {"current_steps": 14780, "total_steps": 40000, "loss": 0.0, "lr": 3.4966525891016454e-05, "epoch": 259.3008849557522, "percentage": 36.95, "elapsed_time": "1:46:06", "remaining_time": "3:01:03", "throughput": 1319.1, "total_tokens": 8397840} {"current_steps": 14785, "total_steps": 40000, "loss": 0.0, "lr": 3.495752153079557e-05, "epoch": 259.3893805309734, "percentage": 36.96, "elapsed_time": "1:46:08", "remaining_time": "3:01:00", "throughput": 1319.06, "total_tokens": 8400288} {"current_steps": 14790, "total_steps": 40000, "loss": 0.0, "lr": 3.494851563499974e-05, "epoch": 259.4778761061947, "percentage": 36.98, "elapsed_time": "1:46:10", "remaining_time": "3:00:58", "throughput": 1319.03, "total_tokens": 8402816} {"current_steps": 14795, "total_steps": 40000, "loss": 0.0, "lr": 3.493950820501777e-05, "epoch": 259.56637168141594, "percentage": 36.99, "elapsed_time": "1:46:12", "remaining_time": "3:00:56", "throughput": 1319.04, "total_tokens": 8405616} {"current_steps": 14800, "total_steps": 40000, "loss": 0.0, "lr": 3.493049924223872e-05, "epoch": 259.65486725663715, "percentage": 37.0, "elapsed_time": "1:46:14", "remaining_time": "3:00:54", "throughput": 1319.06, "total_tokens": 8408512} {"current_steps": 14800, "total_steps": 40000, "eval_loss": 0.4914831817150116, "epoch": 259.65486725663715, "percentage": 37.0, "elapsed_time": "1:46:15", "remaining_time": "3:00:55", "throughput": 1318.84, "total_tokens": 8408512} {"current_steps": 14805, "total_steps": 40000, "loss": 0.0, "lr": 3.49214887480519e-05, "epoch": 259.7433628318584, "percentage": 37.01, "elapsed_time": "1:46:19", "remaining_time": "3:00:56", "throughput": 1318.48, "total_tokens": 8411120} {"current_steps": 14810, "total_steps": 40000, "loss": 0.0, "lr": 3.4912476723846834e-05, "epoch": 259.83185840707966, "percentage": 37.03, "elapsed_time": "1:46:21", "remaining_time": "3:00:54", "throughput": 1318.53, "total_tokens": 8414224} {"current_steps": 14815, "total_steps": 40000, "loss": 0.0, "lr": 3.490346317101328e-05, "epoch": 259.92035398230087, "percentage": 37.04, "elapsed_time": "1:46:23", "remaining_time": "3:00:51", "throughput": 1318.6, "total_tokens": 8417392} {"current_steps": 14820, "total_steps": 40000, "loss": 0.0, "lr": 3.4894448090941266e-05, "epoch": 260.0, "percentage": 37.05, "elapsed_time": "1:46:25", "remaining_time": "3:00:49", "throughput": 1318.64, "total_tokens": 8420256} {"current_steps": 14825, "total_steps": 40000, "loss": 0.0, "lr": 3.488543148502101e-05, "epoch": 260.08849557522126, "percentage": 37.06, "elapsed_time": "1:46:27", "remaining_time": "3:00:47", "throughput": 1318.62, "total_tokens": 8423168} {"current_steps": 14830, "total_steps": 40000, "loss": 0.0, "lr": 3.487641335464299e-05, "epoch": 260.17699115044246, "percentage": 37.08, "elapsed_time": "1:46:29", "remaining_time": "3:00:45", "throughput": 1318.59, "total_tokens": 8425760} {"current_steps": 14835, "total_steps": 40000, "loss": 0.0, "lr": 3.4867393701197914e-05, "epoch": 260.2654867256637, "percentage": 37.09, "elapsed_time": "1:46:32", "remaining_time": "3:00:42", "throughput": 1318.63, "total_tokens": 8428720} {"current_steps": 14840, "total_steps": 40000, "loss": 0.0, "lr": 3.485837252607673e-05, "epoch": 260.353982300885, "percentage": 37.1, "elapsed_time": "1:46:34", "remaining_time": "3:00:40", "throughput": 1318.62, "total_tokens": 8431392} {"current_steps": 14845, "total_steps": 40000, "loss": 0.0, "lr": 3.4849349830670615e-05, "epoch": 260.4424778761062, "percentage": 37.11, "elapsed_time": "1:46:36", "remaining_time": "3:00:38", "throughput": 1318.63, "total_tokens": 8434208} {"current_steps": 14850, "total_steps": 40000, "loss": 0.0, "lr": 3.4840325616370976e-05, "epoch": 260.53097345132744, "percentage": 37.12, "elapsed_time": "1:46:38", "remaining_time": "3:00:36", "throughput": 1318.62, "total_tokens": 8436864} {"current_steps": 14855, "total_steps": 40000, "loss": 0.0, "lr": 3.483129988456947e-05, "epoch": 260.6194690265487, "percentage": 37.14, "elapsed_time": "1:46:40", "remaining_time": "3:00:33", "throughput": 1318.73, "total_tokens": 8440288} {"current_steps": 14860, "total_steps": 40000, "loss": 0.0, "lr": 3.482227263665797e-05, "epoch": 260.7079646017699, "percentage": 37.15, "elapsed_time": "1:46:42", "remaining_time": "3:00:31", "throughput": 1318.7, "total_tokens": 8442832} {"current_steps": 14865, "total_steps": 40000, "loss": 0.0, "lr": 3.48132438740286e-05, "epoch": 260.79646017699116, "percentage": 37.16, "elapsed_time": "1:46:44", "remaining_time": "3:00:29", "throughput": 1318.81, "total_tokens": 8446208} {"current_steps": 14870, "total_steps": 40000, "loss": 0.0, "lr": 3.48042135980737e-05, "epoch": 260.88495575221236, "percentage": 37.18, "elapsed_time": "1:46:46", "remaining_time": "3:00:26", "throughput": 1318.78, "total_tokens": 8448752} {"current_steps": 14875, "total_steps": 40000, "loss": 0.0, "lr": 3.479518181018586e-05, "epoch": 260.9734513274336, "percentage": 37.19, "elapsed_time": "1:46:48", "remaining_time": "3:00:24", "throughput": 1318.78, "total_tokens": 8451504} {"current_steps": 14880, "total_steps": 40000, "loss": 0.0, "lr": 3.4786148511757886e-05, "epoch": 261.05309734513276, "percentage": 37.2, "elapsed_time": "1:46:50", "remaining_time": "3:00:22", "throughput": 1318.74, "total_tokens": 8454168} {"current_steps": 14885, "total_steps": 40000, "loss": 0.0, "lr": 3.477711370418284e-05, "epoch": 261.14159292035396, "percentage": 37.21, "elapsed_time": "1:46:52", "remaining_time": "3:00:20", "throughput": 1318.81, "total_tokens": 8457336} {"current_steps": 14890, "total_steps": 40000, "loss": 0.0, "lr": 3.476807738885399e-05, "epoch": 261.2300884955752, "percentage": 37.23, "elapsed_time": "1:46:54", "remaining_time": "3:00:17", "throughput": 1318.93, "total_tokens": 8460856} {"current_steps": 14895, "total_steps": 40000, "loss": 0.0, "lr": 3.475903956716485e-05, "epoch": 261.3185840707965, "percentage": 37.24, "elapsed_time": "1:46:57", "remaining_time": "3:00:15", "throughput": 1319.01, "total_tokens": 8464136} {"current_steps": 14900, "total_steps": 40000, "loss": 0.0, "lr": 3.475000024050917e-05, "epoch": 261.4070796460177, "percentage": 37.25, "elapsed_time": "1:46:59", "remaining_time": "3:00:13", "throughput": 1318.96, "total_tokens": 8466488} {"current_steps": 14905, "total_steps": 40000, "loss": 0.0, "lr": 3.4740959410280926e-05, "epoch": 261.49557522123894, "percentage": 37.26, "elapsed_time": "1:47:01", "remaining_time": "3:00:11", "throughput": 1319.01, "total_tokens": 8469592} {"current_steps": 14910, "total_steps": 40000, "loss": 0.0, "lr": 3.4731917077874324e-05, "epoch": 261.5840707964602, "percentage": 37.28, "elapsed_time": "1:47:03", "remaining_time": "3:00:08", "throughput": 1318.99, "total_tokens": 8472168} {"current_steps": 14915, "total_steps": 40000, "loss": 0.0, "lr": 3.4722873244683816e-05, "epoch": 261.6725663716814, "percentage": 37.29, "elapsed_time": "1:47:05", "remaining_time": "3:00:06", "throughput": 1318.97, "total_tokens": 8474760} {"current_steps": 14920, "total_steps": 40000, "loss": 0.0, "lr": 3.4713827912104065e-05, "epoch": 261.76106194690266, "percentage": 37.3, "elapsed_time": "1:47:07", "remaining_time": "3:00:04", "throughput": 1319.01, "total_tokens": 8477768} {"current_steps": 14925, "total_steps": 40000, "loss": 0.0, "lr": 3.470478108152998e-05, "epoch": 261.8495575221239, "percentage": 37.31, "elapsed_time": "1:47:09", "remaining_time": "3:00:01", "throughput": 1318.99, "total_tokens": 8480360} {"current_steps": 14930, "total_steps": 40000, "loss": 0.0, "lr": 3.4695732754356695e-05, "epoch": 261.9380530973451, "percentage": 37.33, "elapsed_time": "1:47:11", "remaining_time": "2:59:59", "throughput": 1319.03, "total_tokens": 8483336} {"current_steps": 14935, "total_steps": 40000, "loss": 0.0, "lr": 3.4686682931979576e-05, "epoch": 262.01769911504425, "percentage": 37.34, "elapsed_time": "1:47:13", "remaining_time": "2:59:57", "throughput": 1318.92, "total_tokens": 8485600} {"current_steps": 14940, "total_steps": 40000, "loss": 0.0, "lr": 3.467763161579422e-05, "epoch": 262.1061946902655, "percentage": 37.35, "elapsed_time": "1:47:15", "remaining_time": "2:59:55", "throughput": 1318.93, "total_tokens": 8488384} {"current_steps": 14945, "total_steps": 40000, "loss": 0.0, "lr": 3.466857880719645e-05, "epoch": 262.1946902654867, "percentage": 37.36, "elapsed_time": "1:47:17", "remaining_time": "2:59:52", "throughput": 1319.0, "total_tokens": 8491600} {"current_steps": 14950, "total_steps": 40000, "loss": 0.0, "lr": 3.465952450758233e-05, "epoch": 262.283185840708, "percentage": 37.38, "elapsed_time": "1:47:19", "remaining_time": "2:59:50", "throughput": 1319.04, "total_tokens": 8494528} {"current_steps": 14955, "total_steps": 40000, "loss": 0.0, "lr": 3.4650468718348126e-05, "epoch": 262.37168141592923, "percentage": 37.39, "elapsed_time": "1:47:22", "remaining_time": "2:59:48", "throughput": 1319.05, "total_tokens": 8497312} {"current_steps": 14960, "total_steps": 40000, "loss": 0.0, "lr": 3.464141144089038e-05, "epoch": 262.46017699115043, "percentage": 37.4, "elapsed_time": "1:47:24", "remaining_time": "2:59:46", "throughput": 1319.07, "total_tokens": 8500192} {"current_steps": 14965, "total_steps": 40000, "loss": 0.0, "lr": 3.463235267660583e-05, "epoch": 262.5486725663717, "percentage": 37.41, "elapsed_time": "1:47:26", "remaining_time": "2:59:43", "throughput": 1319.13, "total_tokens": 8503280} {"current_steps": 14970, "total_steps": 40000, "loss": 0.0, "lr": 3.462329242689145e-05, "epoch": 262.6371681415929, "percentage": 37.43, "elapsed_time": "1:47:28", "remaining_time": "2:59:41", "throughput": 1319.19, "total_tokens": 8506448} {"current_steps": 14975, "total_steps": 40000, "loss": 0.0, "lr": 3.461423069314444e-05, "epoch": 262.72566371681415, "percentage": 37.44, "elapsed_time": "1:47:30", "remaining_time": "2:59:39", "throughput": 1319.16, "total_tokens": 8508960} {"current_steps": 14980, "total_steps": 40000, "loss": 0.0, "lr": 3.460516747676224e-05, "epoch": 262.8141592920354, "percentage": 37.45, "elapsed_time": "1:47:32", "remaining_time": "2:59:36", "throughput": 1319.18, "total_tokens": 8511840} {"current_steps": 14985, "total_steps": 40000, "loss": 0.0, "lr": 3.459610277914251e-05, "epoch": 262.9026548672566, "percentage": 37.46, "elapsed_time": "1:47:34", "remaining_time": "2:59:34", "throughput": 1319.25, "total_tokens": 8514992} {"current_steps": 14990, "total_steps": 40000, "loss": 0.0, "lr": 3.458703660168314e-05, "epoch": 262.9911504424779, "percentage": 37.48, "elapsed_time": "1:47:36", "remaining_time": "2:59:32", "throughput": 1319.2, "total_tokens": 8517376} {"current_steps": 14995, "total_steps": 40000, "loss": 0.0, "lr": 3.457796894578224e-05, "epoch": 263.070796460177, "percentage": 37.49, "elapsed_time": "1:47:38", "remaining_time": "2:59:30", "throughput": 1319.17, "total_tokens": 8520168} {"current_steps": 15000, "total_steps": 40000, "loss": 0.0, "lr": 3.456889981283817e-05, "epoch": 263.1592920353982, "percentage": 37.5, "elapsed_time": "1:47:40", "remaining_time": "2:59:28", "throughput": 1319.13, "total_tokens": 8522664} {"current_steps": 15000, "total_steps": 40000, "eval_loss": 0.4853701889514923, "epoch": 263.1592920353982, "percentage": 37.5, "elapsed_time": "1:47:41", "remaining_time": "2:59:29", "throughput": 1318.92, "total_tokens": 8522664} {"current_steps": 15005, "total_steps": 40000, "loss": 0.0, "lr": 3.45598292042495e-05, "epoch": 263.24778761061947, "percentage": 37.51, "elapsed_time": "1:47:45", "remaining_time": "2:59:30", "throughput": 1318.56, "total_tokens": 8525480} {"current_steps": 15010, "total_steps": 40000, "loss": 0.0, "lr": 3.4550757121415035e-05, "epoch": 263.3362831858407, "percentage": 37.52, "elapsed_time": "1:47:47", "remaining_time": "2:59:28", "throughput": 1318.6, "total_tokens": 8528440} {"current_steps": 15015, "total_steps": 40000, "loss": 0.0, "lr": 3.454168356573378e-05, "epoch": 263.42477876106193, "percentage": 37.54, "elapsed_time": "1:47:49", "remaining_time": "2:59:25", "throughput": 1318.61, "total_tokens": 8531224} {"current_steps": 15020, "total_steps": 40000, "loss": 0.0, "lr": 3.453260853860503e-05, "epoch": 263.5132743362832, "percentage": 37.55, "elapsed_time": "1:47:51", "remaining_time": "2:59:23", "throughput": 1318.64, "total_tokens": 8534152} {"current_steps": 15025, "total_steps": 40000, "loss": 0.0, "lr": 3.452353204142824e-05, "epoch": 263.60176991150445, "percentage": 37.56, "elapsed_time": "1:47:54", "remaining_time": "2:59:21", "throughput": 1318.7, "total_tokens": 8537240} {"current_steps": 15030, "total_steps": 40000, "loss": 0.0, "lr": 3.4514454075603136e-05, "epoch": 263.69026548672565, "percentage": 37.57, "elapsed_time": "1:47:56", "remaining_time": "2:59:18", "throughput": 1318.69, "total_tokens": 8539960} {"current_steps": 15035, "total_steps": 40000, "loss": 0.0, "lr": 3.450537464252964e-05, "epoch": 263.7787610619469, "percentage": 37.59, "elapsed_time": "1:47:58", "remaining_time": "2:59:16", "throughput": 1318.81, "total_tokens": 8543400} {"current_steps": 15040, "total_steps": 40000, "loss": 0.0, "lr": 3.4496293743607925e-05, "epoch": 263.86725663716817, "percentage": 37.6, "elapsed_time": "1:48:00", "remaining_time": "2:59:14", "throughput": 1318.75, "total_tokens": 8545784} {"current_steps": 15045, "total_steps": 40000, "loss": 0.0, "lr": 3.448721138023838e-05, "epoch": 263.95575221238937, "percentage": 37.61, "elapsed_time": "1:48:02", "remaining_time": "2:59:12", "throughput": 1318.76, "total_tokens": 8548536} {"current_steps": 15050, "total_steps": 40000, "loss": 0.0, "lr": 3.447812755382162e-05, "epoch": 264.0353982300885, "percentage": 37.62, "elapsed_time": "1:48:04", "remaining_time": "2:59:10", "throughput": 1318.64, "total_tokens": 8550744} {"current_steps": 15055, "total_steps": 40000, "loss": 0.0, "lr": 3.446904226575847e-05, "epoch": 264.12389380530976, "percentage": 37.64, "elapsed_time": "1:48:06", "remaining_time": "2:59:07", "throughput": 1318.67, "total_tokens": 8553656} {"current_steps": 15060, "total_steps": 40000, "loss": 0.0, "lr": 3.445995551745002e-05, "epoch": 264.21238938053096, "percentage": 37.65, "elapsed_time": "1:48:08", "remaining_time": "2:59:05", "throughput": 1318.71, "total_tokens": 8556616} {"current_steps": 15065, "total_steps": 40000, "loss": 0.0, "lr": 3.445086731029753e-05, "epoch": 264.3008849557522, "percentage": 37.66, "elapsed_time": "1:48:10", "remaining_time": "2:59:03", "throughput": 1318.68, "total_tokens": 8559176} {"current_steps": 15070, "total_steps": 40000, "loss": 0.0, "lr": 3.444177764570255e-05, "epoch": 264.3893805309734, "percentage": 37.67, "elapsed_time": "1:48:12", "remaining_time": "2:59:00", "throughput": 1318.71, "total_tokens": 8562088} {"current_steps": 15075, "total_steps": 40000, "loss": 0.0, "lr": 3.44326865250668e-05, "epoch": 264.4778761061947, "percentage": 37.69, "elapsed_time": "1:48:14", "remaining_time": "2:58:58", "throughput": 1318.73, "total_tokens": 8564936} {"current_steps": 15080, "total_steps": 40000, "loss": 0.0, "lr": 3.442359394979225e-05, "epoch": 264.56637168141594, "percentage": 37.7, "elapsed_time": "1:48:16", "remaining_time": "2:58:56", "throughput": 1318.71, "total_tokens": 8567544} {"current_steps": 15085, "total_steps": 40000, "loss": 0.0, "lr": 3.441449992128108e-05, "epoch": 264.65486725663715, "percentage": 37.71, "elapsed_time": "1:48:18", "remaining_time": "2:58:53", "throughput": 1318.67, "total_tokens": 8570008} {"current_steps": 15090, "total_steps": 40000, "loss": 0.0, "lr": 3.440540444093573e-05, "epoch": 264.7433628318584, "percentage": 37.72, "elapsed_time": "1:48:21", "remaining_time": "2:58:51", "throughput": 1318.68, "total_tokens": 8572808} {"current_steps": 15095, "total_steps": 40000, "loss": 0.0, "lr": 3.43963075101588e-05, "epoch": 264.83185840707966, "percentage": 37.74, "elapsed_time": "1:48:23", "remaining_time": "2:58:49", "throughput": 1318.73, "total_tokens": 8575864} {"current_steps": 15100, "total_steps": 40000, "loss": 0.0, "lr": 3.438720913035318e-05, "epoch": 264.92035398230087, "percentage": 37.75, "elapsed_time": "1:48:25", "remaining_time": "2:58:47", "throughput": 1318.75, "total_tokens": 8578712} {"current_steps": 15105, "total_steps": 40000, "loss": 0.0, "lr": 3.437810930292195e-05, "epoch": 265.0, "percentage": 37.76, "elapsed_time": "1:48:27", "remaining_time": "2:58:44", "throughput": 1318.79, "total_tokens": 8581640} {"current_steps": 15110, "total_steps": 40000, "loss": 0.0, "lr": 3.43690080292684e-05, "epoch": 265.08849557522126, "percentage": 37.77, "elapsed_time": "1:48:29", "remaining_time": "2:58:42", "throughput": 1318.72, "total_tokens": 8584232} {"current_steps": 15115, "total_steps": 40000, "loss": 0.0, "lr": 3.435990531079608e-05, "epoch": 265.17699115044246, "percentage": 37.79, "elapsed_time": "1:48:31", "remaining_time": "2:58:40", "throughput": 1318.71, "total_tokens": 8586904} {"current_steps": 15120, "total_steps": 40000, "loss": 0.0, "lr": 3.435080114890874e-05, "epoch": 265.2654867256637, "percentage": 37.8, "elapsed_time": "1:48:33", "remaining_time": "2:58:38", "throughput": 1318.69, "total_tokens": 8589480} {"current_steps": 15125, "total_steps": 40000, "loss": 0.0, "lr": 3.434169554501035e-05, "epoch": 265.353982300885, "percentage": 37.81, "elapsed_time": "1:48:35", "remaining_time": "2:58:35", "throughput": 1318.72, "total_tokens": 8592392} {"current_steps": 15130, "total_steps": 40000, "loss": 0.0, "lr": 3.433258850050511e-05, "epoch": 265.4424778761062, "percentage": 37.82, "elapsed_time": "1:48:37", "remaining_time": "2:58:33", "throughput": 1318.81, "total_tokens": 8595688} {"current_steps": 15135, "total_steps": 40000, "loss": 0.0, "lr": 3.4323480016797446e-05, "epoch": 265.53097345132744, "percentage": 37.84, "elapsed_time": "1:48:39", "remaining_time": "2:58:31", "throughput": 1318.8, "total_tokens": 8598392} {"current_steps": 15140, "total_steps": 40000, "loss": 0.0, "lr": 3.4314370095291995e-05, "epoch": 265.6194690265487, "percentage": 37.85, "elapsed_time": "1:48:41", "remaining_time": "2:58:29", "throughput": 1318.8, "total_tokens": 8601064} {"current_steps": 15145, "total_steps": 40000, "loss": 0.0, "lr": 3.430525873739363e-05, "epoch": 265.7079646017699, "percentage": 37.86, "elapsed_time": "1:48:43", "remaining_time": "2:58:26", "throughput": 1318.79, "total_tokens": 8603752} {"current_steps": 15150, "total_steps": 40000, "loss": 0.0, "lr": 3.429614594450743e-05, "epoch": 265.79646017699116, "percentage": 37.88, "elapsed_time": "1:48:46", "remaining_time": "2:58:24", "throughput": 1318.79, "total_tokens": 8606504} {"current_steps": 15155, "total_steps": 40000, "loss": 0.0, "lr": 3.428703171803869e-05, "epoch": 265.88495575221236, "percentage": 37.89, "elapsed_time": "1:48:48", "remaining_time": "2:58:22", "throughput": 1318.84, "total_tokens": 8609864} {"current_steps": 15160, "total_steps": 40000, "loss": 0.0, "lr": 3.4277916059392964e-05, "epoch": 265.9734513274336, "percentage": 37.9, "elapsed_time": "1:48:50", "remaining_time": "2:58:20", "throughput": 1318.94, "total_tokens": 8613224} {"current_steps": 15165, "total_steps": 40000, "loss": 0.0, "lr": 3.426879896997598e-05, "epoch": 266.05309734513276, "percentage": 37.91, "elapsed_time": "1:48:52", "remaining_time": "2:58:18", "throughput": 1318.85, "total_tokens": 8615648} {"current_steps": 15170, "total_steps": 40000, "loss": 0.0, "lr": 3.425968045119372e-05, "epoch": 266.14159292035396, "percentage": 37.92, "elapsed_time": "1:48:54", "remaining_time": "2:58:15", "throughput": 1318.88, "total_tokens": 8618576} {"current_steps": 15175, "total_steps": 40000, "loss": 0.0, "lr": 3.425056050445237e-05, "epoch": 266.2300884955752, "percentage": 37.94, "elapsed_time": "1:48:56", "remaining_time": "2:58:13", "throughput": 1318.88, "total_tokens": 8621280} {"current_steps": 15180, "total_steps": 40000, "loss": 0.0, "lr": 3.4241439131158336e-05, "epoch": 266.3185840707965, "percentage": 37.95, "elapsed_time": "1:48:58", "remaining_time": "2:58:11", "throughput": 1318.89, "total_tokens": 8624064} {"current_steps": 15185, "total_steps": 40000, "loss": 0.0, "lr": 3.423231633271825e-05, "epoch": 266.4070796460177, "percentage": 37.96, "elapsed_time": "1:49:00", "remaining_time": "2:58:09", "throughput": 1318.88, "total_tokens": 8626768} {"current_steps": 15190, "total_steps": 40000, "loss": 0.0, "lr": 3.4223192110538985e-05, "epoch": 266.49557522123894, "percentage": 37.97, "elapsed_time": "1:49:03", "remaining_time": "2:58:06", "throughput": 1318.99, "total_tokens": 8630224} {"current_steps": 15195, "total_steps": 40000, "loss": 0.0, "lr": 3.4214066466027575e-05, "epoch": 266.5840707964602, "percentage": 37.99, "elapsed_time": "1:49:05", "remaining_time": "2:58:04", "throughput": 1319.04, "total_tokens": 8633296} {"current_steps": 15200, "total_steps": 40000, "loss": 0.0, "lr": 3.4204939400591325e-05, "epoch": 266.6725663716814, "percentage": 38.0, "elapsed_time": "1:49:07", "remaining_time": "2:58:02", "throughput": 1319.05, "total_tokens": 8636032} {"current_steps": 15200, "total_steps": 40000, "eval_loss": 0.501243531703949, "epoch": 266.6725663716814, "percentage": 38.0, "elapsed_time": "1:49:08", "remaining_time": "2:58:03", "throughput": 1318.83, "total_tokens": 8636032} {"current_steps": 15205, "total_steps": 40000, "loss": 0.0, "lr": 3.419581091563775e-05, "epoch": 266.76106194690266, "percentage": 38.01, "elapsed_time": "1:49:12", "remaining_time": "2:58:04", "throughput": 1318.44, "total_tokens": 8638768} {"current_steps": 15210, "total_steps": 40000, "loss": 0.0, "lr": 3.418668101257456e-05, "epoch": 266.8495575221239, "percentage": 38.02, "elapsed_time": "1:49:14", "remaining_time": "2:58:02", "throughput": 1318.44, "total_tokens": 8641520} {"current_steps": 15215, "total_steps": 40000, "loss": 0.0, "lr": 3.417754969280971e-05, "epoch": 266.9380530973451, "percentage": 38.04, "elapsed_time": "1:49:16", "remaining_time": "2:58:00", "throughput": 1318.49, "total_tokens": 8644592} {"current_steps": 15220, "total_steps": 40000, "loss": 0.0, "lr": 3.416841695775137e-05, "epoch": 267.01769911504425, "percentage": 38.05, "elapsed_time": "1:49:18", "remaining_time": "2:57:58", "throughput": 1318.46, "total_tokens": 8647352} {"current_steps": 15225, "total_steps": 40000, "loss": 0.0, "lr": 3.415928280880792e-05, "epoch": 267.1061946902655, "percentage": 38.06, "elapsed_time": "1:49:20", "remaining_time": "2:57:56", "throughput": 1318.54, "total_tokens": 8650632} {"current_steps": 15230, "total_steps": 40000, "loss": 0.0, "lr": 3.4150147247387965e-05, "epoch": 267.1946902654867, "percentage": 38.07, "elapsed_time": "1:49:22", "remaining_time": "2:57:53", "throughput": 1318.53, "total_tokens": 8653288} {"current_steps": 15235, "total_steps": 40000, "loss": 0.0, "lr": 3.4141010274900306e-05, "epoch": 267.283185840708, "percentage": 38.09, "elapsed_time": "1:49:24", "remaining_time": "2:57:51", "throughput": 1318.58, "total_tokens": 8656376} {"current_steps": 15240, "total_steps": 40000, "loss": 0.0, "lr": 3.413187189275399e-05, "epoch": 267.37168141592923, "percentage": 38.1, "elapsed_time": "1:49:26", "remaining_time": "2:57:49", "throughput": 1318.58, "total_tokens": 8659080} {"current_steps": 15245, "total_steps": 40000, "loss": 0.0, "lr": 3.4122732102358265e-05, "epoch": 267.46017699115043, "percentage": 38.11, "elapsed_time": "1:49:29", "remaining_time": "2:57:46", "throughput": 1318.64, "total_tokens": 8662184} {"current_steps": 15250, "total_steps": 40000, "loss": 0.0, "lr": 3.411359090512261e-05, "epoch": 267.5486725663717, "percentage": 38.12, "elapsed_time": "1:49:31", "remaining_time": "2:57:44", "throughput": 1318.55, "total_tokens": 8664328} {"current_steps": 15255, "total_steps": 40000, "loss": 0.0, "lr": 3.410444830245672e-05, "epoch": 267.6371681415929, "percentage": 38.14, "elapsed_time": "1:49:33", "remaining_time": "2:57:42", "throughput": 1318.57, "total_tokens": 8667192} {"current_steps": 15260, "total_steps": 40000, "loss": 0.0, "lr": 3.409530429577048e-05, "epoch": 267.72566371681415, "percentage": 38.15, "elapsed_time": "1:49:35", "remaining_time": "2:57:40", "throughput": 1318.57, "total_tokens": 8669912} {"current_steps": 15265, "total_steps": 40000, "loss": 0.0, "lr": 3.408615888647402e-05, "epoch": 267.8141592920354, "percentage": 38.16, "elapsed_time": "1:49:37", "remaining_time": "2:57:37", "throughput": 1318.61, "total_tokens": 8672904} {"current_steps": 15270, "total_steps": 40000, "loss": 0.0, "lr": 3.4077012075977675e-05, "epoch": 267.9026548672566, "percentage": 38.17, "elapsed_time": "1:49:39", "remaining_time": "2:57:35", "throughput": 1318.61, "total_tokens": 8675608} {"current_steps": 15275, "total_steps": 40000, "loss": 0.0, "lr": 3.4067863865692e-05, "epoch": 267.9911504424779, "percentage": 38.19, "elapsed_time": "1:49:41", "remaining_time": "2:57:33", "throughput": 1318.68, "total_tokens": 8678808} {"current_steps": 15280, "total_steps": 40000, "loss": 0.0, "lr": 3.4058714257027755e-05, "epoch": 268.070796460177, "percentage": 38.2, "elapsed_time": "1:49:43", "remaining_time": "2:57:31", "throughput": 1318.64, "total_tokens": 8681520} {"current_steps": 15285, "total_steps": 40000, "loss": 0.0, "lr": 3.404956325139594e-05, "epoch": 268.1592920353982, "percentage": 38.21, "elapsed_time": "1:49:45", "remaining_time": "2:57:28", "throughput": 1318.64, "total_tokens": 8684240} {"current_steps": 15290, "total_steps": 40000, "loss": 0.0, "lr": 3.404041085020775e-05, "epoch": 268.24778761061947, "percentage": 38.22, "elapsed_time": "1:49:47", "remaining_time": "2:57:26", "throughput": 1318.68, "total_tokens": 8687232} {"current_steps": 15295, "total_steps": 40000, "loss": 0.0, "lr": 3.403125705487459e-05, "epoch": 268.3362831858407, "percentage": 38.24, "elapsed_time": "1:49:49", "remaining_time": "2:57:24", "throughput": 1318.69, "total_tokens": 8690064} {"current_steps": 15300, "total_steps": 40000, "loss": 0.0, "lr": 3.402210186680811e-05, "epoch": 268.42477876106193, "percentage": 38.25, "elapsed_time": "1:49:51", "remaining_time": "2:57:21", "throughput": 1318.71, "total_tokens": 8692912} {"current_steps": 15305, "total_steps": 40000, "loss": 0.0, "lr": 3.4012945287420137e-05, "epoch": 268.5132743362832, "percentage": 38.26, "elapsed_time": "1:49:54", "remaining_time": "2:57:19", "throughput": 1318.71, "total_tokens": 8695648} {"current_steps": 15310, "total_steps": 40000, "loss": 0.0, "lr": 3.400378731812274e-05, "epoch": 268.60176991150445, "percentage": 38.27, "elapsed_time": "1:49:56", "remaining_time": "2:57:17", "throughput": 1318.73, "total_tokens": 8698512} {"current_steps": 15315, "total_steps": 40000, "loss": 0.0, "lr": 3.399462796032817e-05, "epoch": 268.69026548672565, "percentage": 38.29, "elapsed_time": "1:49:58", "remaining_time": "2:57:15", "throughput": 1318.73, "total_tokens": 8701232} {"current_steps": 15320, "total_steps": 40000, "loss": 0.0, "lr": 3.3985467215448954e-05, "epoch": 268.7787610619469, "percentage": 38.3, "elapsed_time": "1:50:00", "remaining_time": "2:57:12", "throughput": 1318.75, "total_tokens": 8704144} {"current_steps": 15325, "total_steps": 40000, "loss": 0.0, "lr": 3.3976305084897776e-05, "epoch": 268.86725663716817, "percentage": 38.31, "elapsed_time": "1:50:02", "remaining_time": "2:57:10", "throughput": 1318.79, "total_tokens": 8707104} {"current_steps": 15330, "total_steps": 40000, "loss": 0.0, "lr": 3.3967141570087544e-05, "epoch": 268.95575221238937, "percentage": 38.32, "elapsed_time": "1:50:04", "remaining_time": "2:57:08", "throughput": 1318.76, "total_tokens": 8709664} {"current_steps": 15335, "total_steps": 40000, "loss": 0.0, "lr": 3.39579766724314e-05, "epoch": 269.0353982300885, "percentage": 38.34, "elapsed_time": "1:50:06", "remaining_time": "2:57:06", "throughput": 1318.66, "total_tokens": 8711928} {"current_steps": 15340, "total_steps": 40000, "loss": 0.0, "lr": 3.3948810393342677e-05, "epoch": 269.12389380530976, "percentage": 38.35, "elapsed_time": "1:50:08", "remaining_time": "2:57:04", "throughput": 1318.63, "total_tokens": 8714520} {"current_steps": 15345, "total_steps": 40000, "loss": 0.0, "lr": 3.3939642734234936e-05, "epoch": 269.21238938053096, "percentage": 38.36, "elapsed_time": "1:50:10", "remaining_time": "2:57:01", "throughput": 1318.69, "total_tokens": 8717688} {"current_steps": 15350, "total_steps": 40000, "loss": 0.0, "lr": 3.393047369652194e-05, "epoch": 269.3008849557522, "percentage": 38.38, "elapsed_time": "1:50:12", "remaining_time": "2:56:59", "throughput": 1318.68, "total_tokens": 8720408} {"current_steps": 15355, "total_steps": 40000, "loss": 0.0, "lr": 3.3921303281617664e-05, "epoch": 269.3893805309734, "percentage": 38.39, "elapsed_time": "1:50:15", "remaining_time": "2:56:57", "throughput": 1318.77, "total_tokens": 8723752} {"current_steps": 15360, "total_steps": 40000, "loss": 0.0, "lr": 3.391213149093632e-05, "epoch": 269.4778761061947, "percentage": 38.4, "elapsed_time": "1:50:17", "remaining_time": "2:56:55", "throughput": 1318.78, "total_tokens": 8726568} {"current_steps": 15365, "total_steps": 40000, "loss": 0.0, "lr": 3.3902958325892303e-05, "epoch": 269.56637168141594, "percentage": 38.41, "elapsed_time": "1:50:19", "remaining_time": "2:56:52", "throughput": 1318.74, "total_tokens": 8729064} {"current_steps": 15370, "total_steps": 40000, "loss": 0.0, "lr": 3.389378378790023e-05, "epoch": 269.65486725663715, "percentage": 38.42, "elapsed_time": "1:50:21", "remaining_time": "2:56:50", "throughput": 1318.76, "total_tokens": 8731960} {"current_steps": 15375, "total_steps": 40000, "loss": 0.0, "lr": 3.388460787837493e-05, "epoch": 269.7433628318584, "percentage": 38.44, "elapsed_time": "1:50:23", "remaining_time": "2:56:48", "throughput": 1318.79, "total_tokens": 8734936} {"current_steps": 15380, "total_steps": 40000, "loss": 0.0, "lr": 3.387543059873145e-05, "epoch": 269.83185840707966, "percentage": 38.45, "elapsed_time": "1:50:25", "remaining_time": "2:56:46", "throughput": 1318.86, "total_tokens": 8738168} {"current_steps": 15385, "total_steps": 40000, "loss": 0.0, "lr": 3.386625195038503e-05, "epoch": 269.92035398230087, "percentage": 38.46, "elapsed_time": "1:50:27", "remaining_time": "2:56:43", "throughput": 1318.82, "total_tokens": 8740680} {"current_steps": 15390, "total_steps": 40000, "loss": 0.0, "lr": 3.3857071934751136e-05, "epoch": 270.0, "percentage": 38.48, "elapsed_time": "1:50:29", "remaining_time": "2:56:41", "throughput": 1318.83, "total_tokens": 8743392} {"current_steps": 15395, "total_steps": 40000, "loss": 0.0, "lr": 3.384789055324544e-05, "epoch": 270.08849557522126, "percentage": 38.49, "elapsed_time": "1:50:32", "remaining_time": "2:56:39", "throughput": 1318.75, "total_tokens": 8746000} {"current_steps": 15400, "total_steps": 40000, "loss": 0.0, "lr": 3.3838707807283843e-05, "epoch": 270.17699115044246, "percentage": 38.5, "elapsed_time": "1:50:34", "remaining_time": "2:56:37", "throughput": 1318.73, "total_tokens": 8748624} {"current_steps": 15400, "total_steps": 40000, "eval_loss": 0.5021628737449646, "epoch": 270.17699115044246, "percentage": 38.5, "elapsed_time": "1:50:35", "remaining_time": "2:56:39", "throughput": 1318.52, "total_tokens": 8748624} {"current_steps": 15405, "total_steps": 40000, "loss": 0.0, "lr": 3.382952369828243e-05, "epoch": 270.2654867256637, "percentage": 38.51, "elapsed_time": "1:50:39", "remaining_time": "2:56:39", "throughput": 1318.22, "total_tokens": 8751984} {"current_steps": 15410, "total_steps": 40000, "loss": 0.0, "lr": 3.38203382276575e-05, "epoch": 270.353982300885, "percentage": 38.52, "elapsed_time": "1:50:41", "remaining_time": "2:56:37", "throughput": 1318.2, "total_tokens": 8754560} {"current_steps": 15415, "total_steps": 40000, "loss": 0.0, "lr": 3.381115139682557e-05, "epoch": 270.4424778761062, "percentage": 38.54, "elapsed_time": "1:50:43", "remaining_time": "2:56:35", "throughput": 1318.25, "total_tokens": 8757600} {"current_steps": 15420, "total_steps": 40000, "loss": 0.0, "lr": 3.3801963207203366e-05, "epoch": 270.53097345132744, "percentage": 38.55, "elapsed_time": "1:50:45", "remaining_time": "2:56:33", "throughput": 1318.29, "total_tokens": 8760640} {"current_steps": 15425, "total_steps": 40000, "loss": 0.0, "lr": 3.379277366020782e-05, "epoch": 270.6194690265487, "percentage": 38.56, "elapsed_time": "1:50:47", "remaining_time": "2:56:30", "throughput": 1318.35, "total_tokens": 8763744} {"current_steps": 15430, "total_steps": 40000, "loss": 0.0, "lr": 3.3783582757256085e-05, "epoch": 270.7079646017699, "percentage": 38.57, "elapsed_time": "1:50:49", "remaining_time": "2:56:28", "throughput": 1318.3, "total_tokens": 8766160} {"current_steps": 15435, "total_steps": 40000, "loss": 0.0, "lr": 3.3774390499765504e-05, "epoch": 270.79646017699116, "percentage": 38.59, "elapsed_time": "1:50:51", "remaining_time": "2:56:26", "throughput": 1318.29, "total_tokens": 8768832} {"current_steps": 15440, "total_steps": 40000, "loss": 0.0, "lr": 3.376519688915364e-05, "epoch": 270.88495575221236, "percentage": 38.6, "elapsed_time": "1:50:53", "remaining_time": "2:56:23", "throughput": 1318.35, "total_tokens": 8771968} {"current_steps": 15445, "total_steps": 40000, "loss": 0.0, "lr": 3.3756001926838273e-05, "epoch": 270.9734513274336, "percentage": 38.61, "elapsed_time": "1:50:55", "remaining_time": "2:56:21", "throughput": 1318.43, "total_tokens": 8775184} {"current_steps": 15450, "total_steps": 40000, "loss": 0.0, "lr": 3.374680561423737e-05, "epoch": 271.05309734513276, "percentage": 38.62, "elapsed_time": "1:50:58", "remaining_time": "2:56:19", "throughput": 1318.4, "total_tokens": 8777984} {"current_steps": 15455, "total_steps": 40000, "loss": 0.0, "lr": 3.373760795276912e-05, "epoch": 271.14159292035396, "percentage": 38.64, "elapsed_time": "1:51:00", "remaining_time": "2:56:17", "throughput": 1318.44, "total_tokens": 8780960} {"current_steps": 15460, "total_steps": 40000, "loss": 0.0, "lr": 3.372840894385192e-05, "epoch": 271.2300884955752, "percentage": 38.65, "elapsed_time": "1:51:02", "remaining_time": "2:56:15", "throughput": 1318.53, "total_tokens": 8784320} {"current_steps": 15465, "total_steps": 40000, "loss": 0.0, "lr": 3.3719208588904375e-05, "epoch": 271.3185840707965, "percentage": 38.66, "elapsed_time": "1:51:04", "remaining_time": "2:56:12", "throughput": 1318.57, "total_tokens": 8787312} {"current_steps": 15470, "total_steps": 40000, "loss": 0.0, "lr": 3.371000688934529e-05, "epoch": 271.4070796460177, "percentage": 38.67, "elapsed_time": "1:51:06", "remaining_time": "2:56:10", "throughput": 1318.61, "total_tokens": 8790288} {"current_steps": 15475, "total_steps": 40000, "loss": 0.0, "lr": 3.370080384659369e-05, "epoch": 271.49557522123894, "percentage": 38.69, "elapsed_time": "1:51:08", "remaining_time": "2:56:08", "throughput": 1318.56, "total_tokens": 8792736} {"current_steps": 15480, "total_steps": 40000, "loss": 0.0, "lr": 3.36915994620688e-05, "epoch": 271.5840707964602, "percentage": 38.7, "elapsed_time": "1:51:10", "remaining_time": "2:56:05", "throughput": 1318.53, "total_tokens": 8795216} {"current_steps": 15485, "total_steps": 40000, "loss": 0.0, "lr": 3.3682393737190035e-05, "epoch": 271.6725663716814, "percentage": 38.71, "elapsed_time": "1:51:12", "remaining_time": "2:56:03", "throughput": 1318.55, "total_tokens": 8798064} {"current_steps": 15490, "total_steps": 40000, "loss": 0.0, "lr": 3.3673186673377054e-05, "epoch": 271.76106194690266, "percentage": 38.73, "elapsed_time": "1:51:14", "remaining_time": "2:56:01", "throughput": 1318.57, "total_tokens": 8800928} {"current_steps": 15495, "total_steps": 40000, "loss": 0.0, "lr": 3.366397827204969e-05, "epoch": 271.8495575221239, "percentage": 38.74, "elapsed_time": "1:51:16", "remaining_time": "2:55:59", "throughput": 1318.56, "total_tokens": 8803616} {"current_steps": 15500, "total_steps": 40000, "loss": 0.0, "lr": 3.3654768534628e-05, "epoch": 271.9380530973451, "percentage": 38.75, "elapsed_time": "1:51:18", "remaining_time": "2:55:56", "throughput": 1318.6, "total_tokens": 8806624} {"current_steps": 15505, "total_steps": 40000, "loss": 0.0, "lr": 3.3645557462532245e-05, "epoch": 272.01769911504425, "percentage": 38.76, "elapsed_time": "1:51:20", "remaining_time": "2:55:54", "throughput": 1318.5, "total_tokens": 8808880} {"current_steps": 15510, "total_steps": 40000, "loss": 0.0, "lr": 3.363634505718288e-05, "epoch": 272.1061946902655, "percentage": 38.77, "elapsed_time": "1:51:23", "remaining_time": "2:55:52", "throughput": 1318.59, "total_tokens": 8812192} {"current_steps": 15515, "total_steps": 40000, "loss": 0.0, "lr": 3.362713132000057e-05, "epoch": 272.1946902654867, "percentage": 38.79, "elapsed_time": "1:51:25", "remaining_time": "2:55:50", "throughput": 1318.54, "total_tokens": 8814656} {"current_steps": 15520, "total_steps": 40000, "loss": 0.0, "lr": 3.36179162524062e-05, "epoch": 272.283185840708, "percentage": 38.8, "elapsed_time": "1:51:27", "remaining_time": "2:55:47", "throughput": 1318.6, "total_tokens": 8817760} {"current_steps": 15525, "total_steps": 40000, "loss": 0.0, "lr": 3.3608699855820846e-05, "epoch": 272.37168141592923, "percentage": 38.81, "elapsed_time": "1:51:29", "remaining_time": "2:55:45", "throughput": 1318.58, "total_tokens": 8820352} {"current_steps": 15530, "total_steps": 40000, "loss": 0.0, "lr": 3.359948213166578e-05, "epoch": 272.46017699115043, "percentage": 38.82, "elapsed_time": "1:51:31", "remaining_time": "2:55:43", "throughput": 1318.71, "total_tokens": 8823968} {"current_steps": 15535, "total_steps": 40000, "loss": 0.0, "lr": 3.359026308136252e-05, "epoch": 272.5486725663717, "percentage": 38.84, "elapsed_time": "1:51:33", "remaining_time": "2:55:41", "throughput": 1318.71, "total_tokens": 8826720} {"current_steps": 15540, "total_steps": 40000, "loss": 0.0, "lr": 3.358104270633272e-05, "epoch": 272.6371681415929, "percentage": 38.85, "elapsed_time": "1:51:35", "remaining_time": "2:55:38", "throughput": 1318.76, "total_tokens": 8829792} {"current_steps": 15545, "total_steps": 40000, "loss": 0.0, "lr": 3.357182100799831e-05, "epoch": 272.72566371681415, "percentage": 38.86, "elapsed_time": "1:51:37", "remaining_time": "2:55:36", "throughput": 1318.72, "total_tokens": 8832256} {"current_steps": 15550, "total_steps": 40000, "loss": 0.0, "lr": 3.3562597987781384e-05, "epoch": 272.8141592920354, "percentage": 38.88, "elapsed_time": "1:51:39", "remaining_time": "2:55:34", "throughput": 1318.74, "total_tokens": 8835088} {"current_steps": 15555, "total_steps": 40000, "loss": 0.0, "lr": 3.355337364710424e-05, "epoch": 272.9026548672566, "percentage": 38.89, "elapsed_time": "1:51:41", "remaining_time": "2:55:31", "throughput": 1318.75, "total_tokens": 8837888} {"current_steps": 15560, "total_steps": 40000, "loss": 0.0, "lr": 3.354414798738939e-05, "epoch": 272.9911504424779, "percentage": 38.9, "elapsed_time": "1:51:43", "remaining_time": "2:55:29", "throughput": 1318.76, "total_tokens": 8840656} {"current_steps": 15565, "total_steps": 40000, "loss": 0.0, "lr": 3.353492101005955e-05, "epoch": 273.070796460177, "percentage": 38.91, "elapsed_time": "1:51:46", "remaining_time": "2:55:27", "throughput": 1318.61, "total_tokens": 8842656} {"current_steps": 15570, "total_steps": 40000, "loss": 0.0, "lr": 3.352569271653763e-05, "epoch": 273.1592920353982, "percentage": 38.92, "elapsed_time": "1:51:48", "remaining_time": "2:55:25", "throughput": 1318.58, "total_tokens": 8845168} {"current_steps": 15575, "total_steps": 40000, "loss": 0.0, "lr": 3.351646310824675e-05, "epoch": 273.24778761061947, "percentage": 38.94, "elapsed_time": "1:51:50", "remaining_time": "2:55:23", "throughput": 1318.6, "total_tokens": 8848032} {"current_steps": 15580, "total_steps": 40000, "loss": 0.0, "lr": 3.350723218661023e-05, "epoch": 273.3362831858407, "percentage": 38.95, "elapsed_time": "1:51:52", "remaining_time": "2:55:20", "throughput": 1318.69, "total_tokens": 8851328} {"current_steps": 15585, "total_steps": 40000, "loss": 0.0, "lr": 3.349799995305162e-05, "epoch": 273.42477876106193, "percentage": 38.96, "elapsed_time": "1:51:54", "remaining_time": "2:55:18", "throughput": 1318.69, "total_tokens": 8854064} {"current_steps": 15590, "total_steps": 40000, "loss": 0.0, "lr": 3.348876640899461e-05, "epoch": 273.5132743362832, "percentage": 38.98, "elapsed_time": "1:51:56", "remaining_time": "2:55:16", "throughput": 1318.7, "total_tokens": 8856848} {"current_steps": 15595, "total_steps": 40000, "loss": 0.0, "lr": 3.3479531555863144e-05, "epoch": 273.60176991150445, "percentage": 38.99, "elapsed_time": "1:51:58", "remaining_time": "2:55:13", "throughput": 1318.82, "total_tokens": 8860368} {"current_steps": 15600, "total_steps": 40000, "loss": 0.0, "lr": 3.3470295395081344e-05, "epoch": 273.69026548672565, "percentage": 39.0, "elapsed_time": "1:52:00", "remaining_time": "2:55:11", "throughput": 1318.84, "total_tokens": 8863248} {"current_steps": 15600, "total_steps": 40000, "eval_loss": 0.5094857811927795, "epoch": 273.69026548672565, "percentage": 39.0, "elapsed_time": "1:52:01", "remaining_time": "2:55:13", "throughput": 1318.63, "total_tokens": 8863248} {"current_steps": 15605, "total_steps": 40000, "loss": 0.0, "lr": 3.3461057928073556e-05, "epoch": 273.7787610619469, "percentage": 39.01, "elapsed_time": "1:52:05", "remaining_time": "2:55:13", "throughput": 1318.24, "total_tokens": 8865936} {"current_steps": 15610, "total_steps": 40000, "loss": 0.0, "lr": 3.345181915626431e-05, "epoch": 273.86725663716817, "percentage": 39.02, "elapsed_time": "1:52:07", "remaining_time": "2:55:11", "throughput": 1318.29, "total_tokens": 8868976} {"current_steps": 15615, "total_steps": 40000, "loss": 0.0, "lr": 3.344257908107834e-05, "epoch": 273.95575221238937, "percentage": 39.04, "elapsed_time": "1:52:09", "remaining_time": "2:55:09", "throughput": 1318.3, "total_tokens": 8871712} {"current_steps": 15620, "total_steps": 40000, "loss": 0.0, "lr": 3.343333770394058e-05, "epoch": 274.0353982300885, "percentage": 39.05, "elapsed_time": "1:52:11", "remaining_time": "2:55:07", "throughput": 1318.22, "total_tokens": 8874184} {"current_steps": 15625, "total_steps": 40000, "loss": 0.0, "lr": 3.342409502627616e-05, "epoch": 274.12389380530976, "percentage": 39.06, "elapsed_time": "1:52:14", "remaining_time": "2:55:05", "throughput": 1318.24, "total_tokens": 8877032} {"current_steps": 15630, "total_steps": 40000, "loss": 0.0, "lr": 3.341485104951043e-05, "epoch": 274.21238938053096, "percentage": 39.07, "elapsed_time": "1:52:16", "remaining_time": "2:55:02", "throughput": 1318.22, "total_tokens": 8879656} {"current_steps": 15635, "total_steps": 40000, "loss": 0.0, "lr": 3.340560577506892e-05, "epoch": 274.3008849557522, "percentage": 39.09, "elapsed_time": "1:52:18", "remaining_time": "2:55:00", "throughput": 1318.26, "total_tokens": 8882664} {"current_steps": 15640, "total_steps": 40000, "loss": 0.0, "lr": 3.339635920437735e-05, "epoch": 274.3893805309734, "percentage": 39.1, "elapsed_time": "1:52:20", "remaining_time": "2:54:58", "throughput": 1318.3, "total_tokens": 8885672} {"current_steps": 15645, "total_steps": 40000, "loss": 0.0, "lr": 3.338711133886169e-05, "epoch": 274.4778761061947, "percentage": 39.11, "elapsed_time": "1:52:22", "remaining_time": "2:54:55", "throughput": 1318.37, "total_tokens": 8888840} {"current_steps": 15650, "total_steps": 40000, "loss": 0.0, "lr": 3.3377862179948064e-05, "epoch": 274.56637168141594, "percentage": 39.12, "elapsed_time": "1:52:24", "remaining_time": "2:54:53", "throughput": 1318.35, "total_tokens": 8891448} {"current_steps": 15655, "total_steps": 40000, "loss": 0.0, "lr": 3.336861172906281e-05, "epoch": 274.65486725663715, "percentage": 39.14, "elapsed_time": "1:52:26", "remaining_time": "2:54:51", "throughput": 1318.44, "total_tokens": 8894760} {"current_steps": 15660, "total_steps": 40000, "loss": 0.0, "lr": 3.335935998763245e-05, "epoch": 274.7433628318584, "percentage": 39.15, "elapsed_time": "1:52:28", "remaining_time": "2:54:49", "throughput": 1318.47, "total_tokens": 8897688} {"current_steps": 15665, "total_steps": 40000, "loss": 0.0, "lr": 3.3350106957083744e-05, "epoch": 274.83185840707966, "percentage": 39.16, "elapsed_time": "1:52:30", "remaining_time": "2:54:46", "throughput": 1318.47, "total_tokens": 8900424} {"current_steps": 15670, "total_steps": 40000, "loss": 0.0, "lr": 3.33408526388436e-05, "epoch": 274.92035398230087, "percentage": 39.17, "elapsed_time": "1:52:32", "remaining_time": "2:54:44", "throughput": 1318.46, "total_tokens": 8903096} {"current_steps": 15675, "total_steps": 40000, "loss": 0.0, "lr": 3.3331597034339166e-05, "epoch": 275.0, "percentage": 39.19, "elapsed_time": "1:52:34", "remaining_time": "2:54:42", "throughput": 1318.41, "total_tokens": 8905392} {"current_steps": 15680, "total_steps": 40000, "loss": 0.0, "lr": 3.3322340144997764e-05, "epoch": 275.08849557522126, "percentage": 39.2, "elapsed_time": "1:52:36", "remaining_time": "2:54:40", "throughput": 1318.33, "total_tokens": 8907856} {"current_steps": 15685, "total_steps": 40000, "loss": 0.0, "lr": 3.331308197224693e-05, "epoch": 275.17699115044246, "percentage": 39.21, "elapsed_time": "1:52:39", "remaining_time": "2:54:37", "throughput": 1318.35, "total_tokens": 8910768} {"current_steps": 15690, "total_steps": 40000, "loss": 0.0, "lr": 3.330382251751438e-05, "epoch": 275.2654867256637, "percentage": 39.23, "elapsed_time": "1:52:41", "remaining_time": "2:54:35", "throughput": 1318.36, "total_tokens": 8913536} {"current_steps": 15695, "total_steps": 40000, "loss": 0.0, "lr": 3.3294561782228054e-05, "epoch": 275.353982300885, "percentage": 39.24, "elapsed_time": "1:52:43", "remaining_time": "2:54:33", "throughput": 1318.44, "total_tokens": 8916816} {"current_steps": 15700, "total_steps": 40000, "loss": 0.0, "lr": 3.328529976781607e-05, "epoch": 275.4424778761062, "percentage": 39.25, "elapsed_time": "1:52:45", "remaining_time": "2:54:31", "throughput": 1318.38, "total_tokens": 8919168} {"current_steps": 15705, "total_steps": 40000, "loss": 0.0, "lr": 3.327603647570673e-05, "epoch": 275.53097345132744, "percentage": 39.26, "elapsed_time": "1:52:47", "remaining_time": "2:54:28", "throughput": 1318.4, "total_tokens": 8922000} {"current_steps": 15710, "total_steps": 40000, "loss": 0.0, "lr": 3.326677190732857e-05, "epoch": 275.6194690265487, "percentage": 39.27, "elapsed_time": "1:52:49", "remaining_time": "2:54:26", "throughput": 1318.43, "total_tokens": 8924960} {"current_steps": 15715, "total_steps": 40000, "loss": 0.0, "lr": 3.325750606411029e-05, "epoch": 275.7079646017699, "percentage": 39.29, "elapsed_time": "1:52:51", "remaining_time": "2:54:24", "throughput": 1318.48, "total_tokens": 8928016} {"current_steps": 15720, "total_steps": 40000, "loss": 0.0, "lr": 3.3248238947480804e-05, "epoch": 275.79646017699116, "percentage": 39.3, "elapsed_time": "1:52:53", "remaining_time": "2:54:21", "throughput": 1318.52, "total_tokens": 8931008} {"current_steps": 15725, "total_steps": 40000, "loss": 0.0, "lr": 3.323897055886922e-05, "epoch": 275.88495575221236, "percentage": 39.31, "elapsed_time": "1:52:55", "remaining_time": "2:54:19", "throughput": 1318.53, "total_tokens": 8933776} {"current_steps": 15730, "total_steps": 40000, "loss": 0.0, "lr": 3.322970089970484e-05, "epoch": 275.9734513274336, "percentage": 39.32, "elapsed_time": "1:52:57", "remaining_time": "2:54:17", "throughput": 1318.56, "total_tokens": 8936688} {"current_steps": 15735, "total_steps": 40000, "loss": 0.0, "lr": 3.3220429971417165e-05, "epoch": 276.05309734513276, "percentage": 39.34, "elapsed_time": "1:52:59", "remaining_time": "2:54:15", "throughput": 1318.42, "total_tokens": 8938744} {"current_steps": 15740, "total_steps": 40000, "loss": 0.0, "lr": 3.321115777543588e-05, "epoch": 276.14159292035396, "percentage": 39.35, "elapsed_time": "1:53:01", "remaining_time": "2:54:13", "throughput": 1318.39, "total_tokens": 8941256} {"current_steps": 15745, "total_steps": 40000, "loss": 0.0, "lr": 3.320188431319088e-05, "epoch": 276.2300884955752, "percentage": 39.36, "elapsed_time": "1:53:04", "remaining_time": "2:54:10", "throughput": 1318.39, "total_tokens": 8943992} {"current_steps": 15750, "total_steps": 40000, "loss": 0.0, "lr": 3.319260958611224e-05, "epoch": 276.3185840707965, "percentage": 39.38, "elapsed_time": "1:53:06", "remaining_time": "2:54:08", "throughput": 1318.34, "total_tokens": 8946424} {"current_steps": 15755, "total_steps": 40000, "loss": 0.0, "lr": 3.3183333595630256e-05, "epoch": 276.4070796460177, "percentage": 39.39, "elapsed_time": "1:53:08", "remaining_time": "2:54:06", "throughput": 1318.43, "total_tokens": 8949752} {"current_steps": 15760, "total_steps": 40000, "loss": 0.0, "lr": 3.317405634317538e-05, "epoch": 276.49557522123894, "percentage": 39.4, "elapsed_time": "1:53:10", "remaining_time": "2:54:03", "throughput": 1318.55, "total_tokens": 8953256} {"current_steps": 15765, "total_steps": 40000, "loss": 0.0, "lr": 3.3164777830178315e-05, "epoch": 276.5840707964602, "percentage": 39.41, "elapsed_time": "1:53:12", "remaining_time": "2:54:01", "throughput": 1318.6, "total_tokens": 8956360} {"current_steps": 15770, "total_steps": 40000, "loss": 0.0, "lr": 3.315549805806989e-05, "epoch": 276.6725663716814, "percentage": 39.42, "elapsed_time": "1:53:14", "remaining_time": "2:53:59", "throughput": 1318.64, "total_tokens": 8959352} {"current_steps": 15775, "total_steps": 40000, "loss": 0.0, "lr": 3.314621702828118e-05, "epoch": 276.76106194690266, "percentage": 39.44, "elapsed_time": "1:53:16", "remaining_time": "2:53:57", "throughput": 1318.64, "total_tokens": 8962104} {"current_steps": 15780, "total_steps": 40000, "loss": 0.0, "lr": 3.313693474224342e-05, "epoch": 276.8495575221239, "percentage": 39.45, "elapsed_time": "1:53:18", "remaining_time": "2:53:54", "throughput": 1318.67, "total_tokens": 8964984} {"current_steps": 15785, "total_steps": 40000, "loss": 0.0, "lr": 3.312765120138809e-05, "epoch": 276.9380530973451, "percentage": 39.46, "elapsed_time": "1:53:20", "remaining_time": "2:53:52", "throughput": 1318.71, "total_tokens": 8968008} {"current_steps": 15790, "total_steps": 40000, "loss": 0.0, "lr": 3.311836640714679e-05, "epoch": 277.01769911504425, "percentage": 39.48, "elapsed_time": "1:53:22", "remaining_time": "2:53:50", "throughput": 1318.68, "total_tokens": 8970792} {"current_steps": 15795, "total_steps": 40000, "loss": 0.0, "lr": 3.310908036095137e-05, "epoch": 277.1061946902655, "percentage": 39.49, "elapsed_time": "1:53:24", "remaining_time": "2:53:48", "throughput": 1318.73, "total_tokens": 8973832} {"current_steps": 15800, "total_steps": 40000, "loss": 0.0, "lr": 3.309979306423386e-05, "epoch": 277.1946902654867, "percentage": 39.5, "elapsed_time": "1:53:26", "remaining_time": "2:53:45", "throughput": 1318.71, "total_tokens": 8976424} {"current_steps": 15800, "total_steps": 40000, "eval_loss": 0.5140652060508728, "epoch": 277.1946902654867, "percentage": 39.5, "elapsed_time": "1:53:28", "remaining_time": "2:53:47", "throughput": 1318.51, "total_tokens": 8976424} {"current_steps": 15805, "total_steps": 40000, "loss": 0.0, "lr": 3.309050451842647e-05, "epoch": 277.283185840708, "percentage": 39.51, "elapsed_time": "1:53:31", "remaining_time": "2:53:47", "throughput": 1318.11, "total_tokens": 8978760} {"current_steps": 15810, "total_steps": 40000, "loss": 0.0, "lr": 3.3081214724961604e-05, "epoch": 277.37168141592923, "percentage": 39.52, "elapsed_time": "1:53:33", "remaining_time": "2:53:45", "throughput": 1318.12, "total_tokens": 8981528} {"current_steps": 15815, "total_steps": 40000, "loss": 0.0, "lr": 3.307192368527188e-05, "epoch": 277.46017699115043, "percentage": 39.54, "elapsed_time": "1:53:35", "remaining_time": "2:53:43", "throughput": 1318.17, "total_tokens": 8984568} {"current_steps": 15820, "total_steps": 40000, "loss": 0.0, "lr": 3.306263140079008e-05, "epoch": 277.5486725663717, "percentage": 39.55, "elapsed_time": "1:53:38", "remaining_time": "2:53:40", "throughput": 1318.22, "total_tokens": 8987656} {"current_steps": 15825, "total_steps": 40000, "loss": 0.0, "lr": 3.30533378729492e-05, "epoch": 277.6371681415929, "percentage": 39.56, "elapsed_time": "1:53:40", "remaining_time": "2:53:38", "throughput": 1318.2, "total_tokens": 8990296} {"current_steps": 15830, "total_steps": 40000, "loss": 0.0, "lr": 3.304404310318242e-05, "epoch": 277.72566371681415, "percentage": 39.57, "elapsed_time": "1:53:42", "remaining_time": "2:53:36", "throughput": 1318.3, "total_tokens": 8993656} {"current_steps": 15835, "total_steps": 40000, "loss": 0.0, "lr": 3.3034747092923105e-05, "epoch": 277.8141592920354, "percentage": 39.59, "elapsed_time": "1:53:44", "remaining_time": "2:53:34", "throughput": 1318.36, "total_tokens": 8996840} {"current_steps": 15840, "total_steps": 40000, "loss": 0.0, "lr": 3.3025449843604806e-05, "epoch": 277.9026548672566, "percentage": 39.6, "elapsed_time": "1:53:46", "remaining_time": "2:53:31", "throughput": 1318.35, "total_tokens": 8999512} {"current_steps": 15845, "total_steps": 40000, "loss": 0.0, "lr": 3.30161513566613e-05, "epoch": 277.9911504424779, "percentage": 39.61, "elapsed_time": "1:53:48", "remaining_time": "2:53:29", "throughput": 1318.3, "total_tokens": 9001832} {"current_steps": 15850, "total_steps": 40000, "loss": 0.0, "lr": 3.3006851633526506e-05, "epoch": 278.070796460177, "percentage": 39.62, "elapsed_time": "1:53:50", "remaining_time": "2:53:27", "throughput": 1318.22, "total_tokens": 9004264} {"current_steps": 15855, "total_steps": 40000, "loss": 0.0, "lr": 3.2997550675634584e-05, "epoch": 278.1592920353982, "percentage": 39.64, "elapsed_time": "1:53:52", "remaining_time": "2:53:25", "throughput": 1318.21, "total_tokens": 9006920} {"current_steps": 15860, "total_steps": 40000, "loss": 0.0, "lr": 3.2988248484419825e-05, "epoch": 278.24778761061947, "percentage": 39.65, "elapsed_time": "1:53:54", "remaining_time": "2:53:22", "throughput": 1318.19, "total_tokens": 9009544} {"current_steps": 15865, "total_steps": 40000, "loss": 0.0, "lr": 3.2978945061316776e-05, "epoch": 278.3362831858407, "percentage": 39.66, "elapsed_time": "1:53:56", "remaining_time": "2:53:20", "throughput": 1318.22, "total_tokens": 9012472} {"current_steps": 15870, "total_steps": 40000, "loss": 0.0, "lr": 3.296964040776013e-05, "epoch": 278.42477876106193, "percentage": 39.67, "elapsed_time": "1:53:58", "remaining_time": "2:53:18", "throughput": 1318.24, "total_tokens": 9015304} {"current_steps": 15875, "total_steps": 40000, "loss": 0.0, "lr": 3.296033452518478e-05, "epoch": 278.5132743362832, "percentage": 39.69, "elapsed_time": "1:54:00", "remaining_time": "2:53:16", "throughput": 1318.22, "total_tokens": 9017928} {"current_steps": 15880, "total_steps": 40000, "loss": 0.0, "lr": 3.2951027415025806e-05, "epoch": 278.60176991150445, "percentage": 39.7, "elapsed_time": "1:54:03", "remaining_time": "2:53:13", "throughput": 1318.31, "total_tokens": 9021272} {"current_steps": 15885, "total_steps": 40000, "loss": 0.0, "lr": 3.294171907871849e-05, "epoch": 278.69026548672565, "percentage": 39.71, "elapsed_time": "1:54:05", "remaining_time": "2:53:11", "throughput": 1318.38, "total_tokens": 9024472} {"current_steps": 15890, "total_steps": 40000, "loss": 0.0, "lr": 3.293240951769828e-05, "epoch": 278.7787610619469, "percentage": 39.73, "elapsed_time": "1:54:07", "remaining_time": "2:53:09", "throughput": 1318.4, "total_tokens": 9027288} {"current_steps": 15895, "total_steps": 40000, "loss": 0.0, "lr": 3.2923098733400846e-05, "epoch": 278.86725663716817, "percentage": 39.74, "elapsed_time": "1:54:09", "remaining_time": "2:53:06", "throughput": 1318.4, "total_tokens": 9030024} {"current_steps": 15900, "total_steps": 40000, "loss": 0.0, "lr": 3.291378672726202e-05, "epoch": 278.95575221238937, "percentage": 39.75, "elapsed_time": "1:54:11", "remaining_time": "2:53:04", "throughput": 1318.43, "total_tokens": 9032984} {"current_steps": 15905, "total_steps": 40000, "loss": 0.0, "lr": 3.2904473500717824e-05, "epoch": 279.0353982300885, "percentage": 39.76, "elapsed_time": "1:54:13", "remaining_time": "2:53:02", "throughput": 1318.33, "total_tokens": 9035232} {"current_steps": 15910, "total_steps": 40000, "loss": 0.0, "lr": 3.289515905520449e-05, "epoch": 279.12389380530976, "percentage": 39.77, "elapsed_time": "1:54:15", "remaining_time": "2:53:00", "throughput": 1318.32, "total_tokens": 9037920} {"current_steps": 15915, "total_steps": 40000, "loss": 0.0, "lr": 3.288584339215841e-05, "epoch": 279.21238938053096, "percentage": 39.79, "elapsed_time": "1:54:17", "remaining_time": "2:52:58", "throughput": 1318.3, "total_tokens": 9040560} {"current_steps": 15920, "total_steps": 40000, "loss": 0.0, "lr": 3.287652651301617e-05, "epoch": 279.3008849557522, "percentage": 39.8, "elapsed_time": "1:54:19", "remaining_time": "2:52:55", "throughput": 1318.36, "total_tokens": 9043664} {"current_steps": 15925, "total_steps": 40000, "loss": 0.0, "lr": 3.286720841921457e-05, "epoch": 279.3893805309734, "percentage": 39.81, "elapsed_time": "1:54:21", "remaining_time": "2:52:53", "throughput": 1318.38, "total_tokens": 9046544} {"current_steps": 15930, "total_steps": 40000, "loss": 0.0, "lr": 3.285788911219056e-05, "epoch": 279.4778761061947, "percentage": 39.83, "elapsed_time": "1:54:23", "remaining_time": "2:52:51", "throughput": 1318.41, "total_tokens": 9049456} {"current_steps": 15935, "total_steps": 40000, "loss": 0.0, "lr": 3.284856859338131e-05, "epoch": 279.56637168141594, "percentage": 39.84, "elapsed_time": "1:54:26", "remaining_time": "2:52:49", "throughput": 1318.46, "total_tokens": 9052560} {"current_steps": 15940, "total_steps": 40000, "loss": 0.0, "lr": 3.283924686422414e-05, "epoch": 279.65486725663715, "percentage": 39.85, "elapsed_time": "1:54:28", "remaining_time": "2:52:46", "throughput": 1318.46, "total_tokens": 9055312} {"current_steps": 15945, "total_steps": 40000, "loss": 0.0, "lr": 3.282992392615659e-05, "epoch": 279.7433628318584, "percentage": 39.86, "elapsed_time": "1:54:30", "remaining_time": "2:52:44", "throughput": 1318.47, "total_tokens": 9058080} {"current_steps": 15950, "total_steps": 40000, "loss": 0.0, "lr": 3.282059978061638e-05, "epoch": 279.83185840707966, "percentage": 39.88, "elapsed_time": "1:54:32", "remaining_time": "2:52:42", "throughput": 1318.54, "total_tokens": 9061280} {"current_steps": 15955, "total_steps": 40000, "loss": 0.0, "lr": 3.28112744290414e-05, "epoch": 279.92035398230087, "percentage": 39.89, "elapsed_time": "1:54:34", "remaining_time": "2:52:39", "throughput": 1318.55, "total_tokens": 9064128} {"current_steps": 15960, "total_steps": 40000, "loss": 0.0, "lr": 3.280194787286974e-05, "epoch": 280.0, "percentage": 39.9, "elapsed_time": "1:54:36", "remaining_time": "2:52:37", "throughput": 1318.52, "total_tokens": 9066520} {"current_steps": 15965, "total_steps": 40000, "loss": 0.0, "lr": 3.2792620113539674e-05, "epoch": 280.08849557522126, "percentage": 39.91, "elapsed_time": "1:54:38", "remaining_time": "2:52:35", "throughput": 1318.46, "total_tokens": 9069192} {"current_steps": 15970, "total_steps": 40000, "loss": 0.0, "lr": 3.278329115248966e-05, "epoch": 280.17699115044246, "percentage": 39.92, "elapsed_time": "1:54:40", "remaining_time": "2:52:33", "throughput": 1318.51, "total_tokens": 9072264} {"current_steps": 15975, "total_steps": 40000, "loss": 0.0, "lr": 3.277396099115834e-05, "epoch": 280.2654867256637, "percentage": 39.94, "elapsed_time": "1:54:42", "remaining_time": "2:52:31", "throughput": 1318.49, "total_tokens": 9074808} {"current_steps": 15980, "total_steps": 40000, "loss": 0.0, "lr": 3.276462963098454e-05, "epoch": 280.353982300885, "percentage": 39.95, "elapsed_time": "1:54:44", "remaining_time": "2:52:28", "throughput": 1318.49, "total_tokens": 9077592} {"current_steps": 15985, "total_steps": 40000, "loss": 0.0, "lr": 3.275529707340728e-05, "epoch": 280.4424778761062, "percentage": 39.96, "elapsed_time": "1:54:46", "remaining_time": "2:52:26", "throughput": 1318.54, "total_tokens": 9080632} {"current_steps": 15990, "total_steps": 40000, "loss": 0.0, "lr": 3.274596331986574e-05, "epoch": 280.53097345132744, "percentage": 39.98, "elapsed_time": "1:54:48", "remaining_time": "2:52:24", "throughput": 1318.6, "total_tokens": 9083816} {"current_steps": 15995, "total_steps": 40000, "loss": 0.0, "lr": 3.273662837179932e-05, "epoch": 280.6194690265487, "percentage": 39.99, "elapsed_time": "1:54:51", "remaining_time": "2:52:21", "throughput": 1318.57, "total_tokens": 9086312} {"current_steps": 16000, "total_steps": 40000, "loss": 0.0, "lr": 3.272729223064758e-05, "epoch": 280.7079646017699, "percentage": 40.0, "elapsed_time": "1:54:53", "remaining_time": "2:52:19", "throughput": 1318.57, "total_tokens": 9088984} {"current_steps": 16000, "total_steps": 40000, "eval_loss": 0.5121561288833618, "epoch": 280.7079646017699, "percentage": 40.0, "elapsed_time": "1:54:54", "remaining_time": "2:52:21", "throughput": 1318.36, "total_tokens": 9088984} {"current_steps": 16005, "total_steps": 40000, "loss": 0.0, "lr": 3.2717954897850264e-05, "epoch": 280.79646017699116, "percentage": 40.01, "elapsed_time": "1:54:57", "remaining_time": "2:52:21", "throughput": 1318.03, "total_tokens": 9091704} {"current_steps": 16010, "total_steps": 40000, "loss": 0.0, "lr": 3.270861637484733e-05, "epoch": 280.88495575221236, "percentage": 40.02, "elapsed_time": "1:55:00", "remaining_time": "2:52:19", "throughput": 1318.14, "total_tokens": 9095176} {"current_steps": 16015, "total_steps": 40000, "loss": 0.0, "lr": 3.2699276663078867e-05, "epoch": 280.9734513274336, "percentage": 40.04, "elapsed_time": "1:55:02", "remaining_time": "2:52:16", "throughput": 1318.21, "total_tokens": 9098424} {"current_steps": 16020, "total_steps": 40000, "loss": 0.0, "lr": 3.268993576398519e-05, "epoch": 281.05309734513276, "percentage": 40.05, "elapsed_time": "1:55:04", "remaining_time": "2:52:14", "throughput": 1318.12, "total_tokens": 9100800} {"current_steps": 16025, "total_steps": 40000, "loss": 0.0, "lr": 3.268059367900678e-05, "epoch": 281.14159292035396, "percentage": 40.06, "elapsed_time": "1:55:06", "remaining_time": "2:52:12", "throughput": 1318.13, "total_tokens": 9103552} {"current_steps": 16030, "total_steps": 40000, "loss": 0.0, "lr": 3.26712504095843e-05, "epoch": 281.2300884955752, "percentage": 40.08, "elapsed_time": "1:55:08", "remaining_time": "2:52:10", "throughput": 1318.14, "total_tokens": 9106368} {"current_steps": 16035, "total_steps": 40000, "loss": 0.0, "lr": 3.2661905957158615e-05, "epoch": 281.3185840707965, "percentage": 40.09, "elapsed_time": "1:55:10", "remaining_time": "2:52:08", "throughput": 1318.13, "total_tokens": 9109008} {"current_steps": 16040, "total_steps": 40000, "loss": 0.0, "lr": 3.2652560323170734e-05, "epoch": 281.4070796460177, "percentage": 40.1, "elapsed_time": "1:55:12", "remaining_time": "2:52:05", "throughput": 1318.25, "total_tokens": 9112544} {"current_steps": 16045, "total_steps": 40000, "loss": 0.0, "lr": 3.264321350906189e-05, "epoch": 281.49557522123894, "percentage": 40.11, "elapsed_time": "1:55:14", "remaining_time": "2:52:03", "throughput": 1318.25, "total_tokens": 9115280} {"current_steps": 16050, "total_steps": 40000, "loss": 0.0, "lr": 3.263386551627346e-05, "epoch": 281.5840707964602, "percentage": 40.12, "elapsed_time": "1:55:16", "remaining_time": "2:52:01", "throughput": 1318.21, "total_tokens": 9117760} {"current_steps": 16055, "total_steps": 40000, "loss": 0.0, "lr": 3.2624516346247055e-05, "epoch": 281.6725663716814, "percentage": 40.14, "elapsed_time": "1:55:18", "remaining_time": "2:51:58", "throughput": 1318.24, "total_tokens": 9120688} {"current_steps": 16060, "total_steps": 40000, "loss": 0.0, "lr": 3.2615166000424404e-05, "epoch": 281.76106194690266, "percentage": 40.15, "elapsed_time": "1:55:20", "remaining_time": "2:51:56", "throughput": 1318.24, "total_tokens": 9123408} {"current_steps": 16065, "total_steps": 40000, "loss": 0.0, "lr": 3.260581448024745e-05, "epoch": 281.8495575221239, "percentage": 40.16, "elapsed_time": "1:55:22", "remaining_time": "2:51:54", "throughput": 1318.27, "total_tokens": 9126368} {"current_steps": 16070, "total_steps": 40000, "loss": 0.0, "lr": 3.2596461787158335e-05, "epoch": 281.9380530973451, "percentage": 40.17, "elapsed_time": "1:55:25", "remaining_time": "2:51:52", "throughput": 1318.34, "total_tokens": 9129552} {"current_steps": 16075, "total_steps": 40000, "loss": 0.0, "lr": 3.258710792259934e-05, "epoch": 282.01769911504425, "percentage": 40.19, "elapsed_time": "1:55:27", "remaining_time": "2:51:50", "throughput": 1318.3, "total_tokens": 9132240} {"current_steps": 16080, "total_steps": 40000, "loss": 0.0, "lr": 3.257775288801296e-05, "epoch": 282.1061946902655, "percentage": 40.2, "elapsed_time": "1:55:29", "remaining_time": "2:51:47", "throughput": 1318.27, "total_tokens": 9134768} {"current_steps": 16085, "total_steps": 40000, "loss": 0.0, "lr": 3.256839668484186e-05, "epoch": 282.1946902654867, "percentage": 40.21, "elapsed_time": "1:55:31", "remaining_time": "2:51:45", "throughput": 1318.32, "total_tokens": 9137856} {"current_steps": 16090, "total_steps": 40000, "loss": 0.0, "lr": 3.255903931452888e-05, "epoch": 282.283185840708, "percentage": 40.23, "elapsed_time": "1:55:33", "remaining_time": "2:51:43", "throughput": 1318.3, "total_tokens": 9140448} {"current_steps": 16095, "total_steps": 40000, "loss": 0.0, "lr": 3.2549680778517045e-05, "epoch": 282.37168141592923, "percentage": 40.24, "elapsed_time": "1:55:35", "remaining_time": "2:51:41", "throughput": 1318.31, "total_tokens": 9143200} {"current_steps": 16100, "total_steps": 40000, "loss": 0.0, "lr": 3.2540321078249556e-05, "epoch": 282.46017699115043, "percentage": 40.25, "elapsed_time": "1:55:37", "remaining_time": "2:51:38", "throughput": 1318.32, "total_tokens": 9146016} {"current_steps": 16105, "total_steps": 40000, "loss": 0.0, "lr": 3.2530960215169795e-05, "epoch": 282.5486725663717, "percentage": 40.26, "elapsed_time": "1:55:39", "remaining_time": "2:51:36", "throughput": 1318.29, "total_tokens": 9148576} {"current_steps": 16110, "total_steps": 40000, "loss": 0.0, "lr": 3.2521598190721345e-05, "epoch": 282.6371681415929, "percentage": 40.27, "elapsed_time": "1:55:41", "remaining_time": "2:51:34", "throughput": 1318.36, "total_tokens": 9151776} {"current_steps": 16115, "total_steps": 40000, "loss": 0.0, "lr": 3.251223500634792e-05, "epoch": 282.72566371681415, "percentage": 40.29, "elapsed_time": "1:55:43", "remaining_time": "2:51:31", "throughput": 1318.42, "total_tokens": 9154896} {"current_steps": 16120, "total_steps": 40000, "loss": 0.0, "lr": 3.2502870663493445e-05, "epoch": 282.8141592920354, "percentage": 40.3, "elapsed_time": "1:55:45", "remaining_time": "2:51:29", "throughput": 1318.43, "total_tokens": 9157744} {"current_steps": 16125, "total_steps": 40000, "loss": 0.0, "lr": 3.249350516360203e-05, "epoch": 282.9026548672566, "percentage": 40.31, "elapsed_time": "1:55:48", "remaining_time": "2:51:27", "throughput": 1318.46, "total_tokens": 9160704} {"current_steps": 16130, "total_steps": 40000, "loss": 0.0, "lr": 3.248413850811797e-05, "epoch": 282.9911504424779, "percentage": 40.33, "elapsed_time": "1:55:50", "remaining_time": "2:51:25", "throughput": 1318.56, "total_tokens": 9164096} {"current_steps": 16135, "total_steps": 40000, "loss": 0.0, "lr": 3.2474770698485677e-05, "epoch": 283.070796460177, "percentage": 40.34, "elapsed_time": "1:55:52", "remaining_time": "2:51:23", "throughput": 1318.48, "total_tokens": 9166512} {"current_steps": 16140, "total_steps": 40000, "loss": 0.0, "lr": 3.246540173614983e-05, "epoch": 283.1592920353982, "percentage": 40.35, "elapsed_time": "1:55:54", "remaining_time": "2:51:20", "throughput": 1318.51, "total_tokens": 9169456} {"current_steps": 16145, "total_steps": 40000, "loss": 0.0, "lr": 3.2456031622555197e-05, "epoch": 283.24778761061947, "percentage": 40.36, "elapsed_time": "1:55:56", "remaining_time": "2:51:18", "throughput": 1318.53, "total_tokens": 9172336} {"current_steps": 16150, "total_steps": 40000, "loss": 0.0, "lr": 3.2446660359146794e-05, "epoch": 283.3362831858407, "percentage": 40.38, "elapsed_time": "1:55:58", "remaining_time": "2:51:16", "throughput": 1318.49, "total_tokens": 9174784} {"current_steps": 16155, "total_steps": 40000, "loss": 0.0, "lr": 3.2437287947369786e-05, "epoch": 283.42477876106193, "percentage": 40.39, "elapsed_time": "1:56:00", "remaining_time": "2:51:13", "throughput": 1318.48, "total_tokens": 9177456} {"current_steps": 16160, "total_steps": 40000, "loss": 0.0, "lr": 3.2427914388669525e-05, "epoch": 283.5132743362832, "percentage": 40.4, "elapsed_time": "1:56:02", "remaining_time": "2:51:11", "throughput": 1318.45, "total_tokens": 9179952} {"current_steps": 16165, "total_steps": 40000, "loss": 0.0, "lr": 3.241853968449151e-05, "epoch": 283.60176991150445, "percentage": 40.41, "elapsed_time": "1:56:04", "remaining_time": "2:51:09", "throughput": 1318.5, "total_tokens": 9182992} {"current_steps": 16170, "total_steps": 40000, "loss": 0.0, "lr": 3.240916383628144e-05, "epoch": 283.69026548672565, "percentage": 40.42, "elapsed_time": "1:56:06", "remaining_time": "2:51:07", "throughput": 1318.58, "total_tokens": 9186336} {"current_steps": 16175, "total_steps": 40000, "loss": 0.0, "lr": 3.239978684548521e-05, "epoch": 283.7787610619469, "percentage": 40.44, "elapsed_time": "1:56:08", "remaining_time": "2:51:04", "throughput": 1318.61, "total_tokens": 9189264} {"current_steps": 16180, "total_steps": 40000, "loss": 0.0, "lr": 3.239040871354885e-05, "epoch": 283.86725663716817, "percentage": 40.45, "elapsed_time": "1:56:10", "remaining_time": "2:51:02", "throughput": 1318.69, "total_tokens": 9192480} {"current_steps": 16185, "total_steps": 40000, "loss": 0.0, "lr": 3.2381029441918596e-05, "epoch": 283.95575221238937, "percentage": 40.46, "elapsed_time": "1:56:13", "remaining_time": "2:51:00", "throughput": 1318.7, "total_tokens": 9195264} {"current_steps": 16190, "total_steps": 40000, "loss": 0.0, "lr": 3.2371649032040845e-05, "epoch": 284.0353982300885, "percentage": 40.48, "elapsed_time": "1:56:15", "remaining_time": "2:50:58", "throughput": 1318.62, "total_tokens": 9197744} {"current_steps": 16195, "total_steps": 40000, "loss": 0.0, "lr": 3.2362267485362174e-05, "epoch": 284.12389380530976, "percentage": 40.49, "elapsed_time": "1:56:17", "remaining_time": "2:50:55", "throughput": 1318.69, "total_tokens": 9200960} {"current_steps": 16200, "total_steps": 40000, "loss": 0.0, "lr": 3.235288480332934e-05, "epoch": 284.21238938053096, "percentage": 40.5, "elapsed_time": "1:56:19", "remaining_time": "2:50:53", "throughput": 1318.76, "total_tokens": 9204128} {"current_steps": 16200, "total_steps": 40000, "eval_loss": 0.5214510560035706, "epoch": 284.21238938053096, "percentage": 40.5, "elapsed_time": "1:56:20", "remaining_time": "2:50:55", "throughput": 1318.56, "total_tokens": 9204128} {"current_steps": 16205, "total_steps": 40000, "loss": 0.0, "lr": 3.234350098738927e-05, "epoch": 284.3008849557522, "percentage": 40.51, "elapsed_time": "1:56:24", "remaining_time": "2:50:55", "throughput": 1318.28, "total_tokens": 9207184} {"current_steps": 16210, "total_steps": 40000, "loss": 0.0, "lr": 3.233411603898906e-05, "epoch": 284.3893805309734, "percentage": 40.52, "elapsed_time": "1:56:26", "remaining_time": "2:50:53", "throughput": 1318.3, "total_tokens": 9210048} {"current_steps": 16215, "total_steps": 40000, "loss": 0.0, "lr": 3.232472995957599e-05, "epoch": 284.4778761061947, "percentage": 40.54, "elapsed_time": "1:56:28", "remaining_time": "2:50:50", "throughput": 1318.27, "total_tokens": 9212576} {"current_steps": 16220, "total_steps": 40000, "loss": 0.0, "lr": 3.231534275059751e-05, "epoch": 284.56637168141594, "percentage": 40.55, "elapsed_time": "1:56:30", "remaining_time": "2:50:48", "throughput": 1318.27, "total_tokens": 9215312} {"current_steps": 16225, "total_steps": 40000, "loss": 0.0, "lr": 3.230595441350125e-05, "epoch": 284.65486725663715, "percentage": 40.56, "elapsed_time": "1:56:32", "remaining_time": "2:50:46", "throughput": 1318.25, "total_tokens": 9217968} {"current_steps": 16230, "total_steps": 40000, "loss": 0.0, "lr": 3.2296564949735e-05, "epoch": 284.7433628318584, "percentage": 40.58, "elapsed_time": "1:56:34", "remaining_time": "2:50:44", "throughput": 1318.26, "total_tokens": 9220736} {"current_steps": 16235, "total_steps": 40000, "loss": 0.0, "lr": 3.228717436074675e-05, "epoch": 284.83185840707966, "percentage": 40.59, "elapsed_time": "1:56:36", "remaining_time": "2:50:41", "throughput": 1318.3, "total_tokens": 9223760} {"current_steps": 16240, "total_steps": 40000, "loss": 0.0, "lr": 3.227778264798463e-05, "epoch": 284.92035398230087, "percentage": 40.6, "elapsed_time": "1:56:38", "remaining_time": "2:50:39", "throughput": 1318.31, "total_tokens": 9226512} {"current_steps": 16245, "total_steps": 40000, "loss": 0.0, "lr": 3.226838981289698e-05, "epoch": 285.0, "percentage": 40.61, "elapsed_time": "1:56:40", "remaining_time": "2:50:37", "throughput": 1318.32, "total_tokens": 9229264} {"current_steps": 16250, "total_steps": 40000, "loss": 0.0, "lr": 3.225899585693227e-05, "epoch": 285.08849557522126, "percentage": 40.62, "elapsed_time": "1:56:43", "remaining_time": "2:50:35", "throughput": 1318.32, "total_tokens": 9232288} {"current_steps": 16255, "total_steps": 40000, "loss": 0.0, "lr": 3.224960078153918e-05, "epoch": 285.17699115044246, "percentage": 40.64, "elapsed_time": "1:56:45", "remaining_time": "2:50:33", "throughput": 1318.38, "total_tokens": 9235472} {"current_steps": 16260, "total_steps": 40000, "loss": 0.0, "lr": 3.224020458816655e-05, "epoch": 285.2654867256637, "percentage": 40.65, "elapsed_time": "1:56:47", "remaining_time": "2:50:30", "throughput": 1318.36, "total_tokens": 9238064} {"current_steps": 16265, "total_steps": 40000, "loss": 0.0, "lr": 3.223080727826337e-05, "epoch": 285.353982300885, "percentage": 40.66, "elapsed_time": "1:56:49", "remaining_time": "2:50:28", "throughput": 1318.42, "total_tokens": 9241216} {"current_steps": 16270, "total_steps": 40000, "loss": 0.0, "lr": 3.222140885327885e-05, "epoch": 285.4424778761062, "percentage": 40.67, "elapsed_time": "1:56:51", "remaining_time": "2:50:26", "throughput": 1318.41, "total_tokens": 9243888} {"current_steps": 16275, "total_steps": 40000, "loss": 0.0, "lr": 3.221200931466234e-05, "epoch": 285.53097345132744, "percentage": 40.69, "elapsed_time": "1:56:53", "remaining_time": "2:50:23", "throughput": 1318.47, "total_tokens": 9247008} {"current_steps": 16280, "total_steps": 40000, "loss": 0.0, "lr": 3.220260866386336e-05, "epoch": 285.6194690265487, "percentage": 40.7, "elapsed_time": "1:56:55", "remaining_time": "2:50:21", "throughput": 1318.51, "total_tokens": 9250032} {"current_steps": 16285, "total_steps": 40000, "loss": 0.0, "lr": 3.21932069023316e-05, "epoch": 285.7079646017699, "percentage": 40.71, "elapsed_time": "1:56:57", "remaining_time": "2:50:19", "throughput": 1318.48, "total_tokens": 9252544} {"current_steps": 16290, "total_steps": 40000, "loss": 0.0, "lr": 3.218380403151695e-05, "epoch": 285.79646017699116, "percentage": 40.73, "elapsed_time": "1:56:59", "remaining_time": "2:50:17", "throughput": 1318.45, "total_tokens": 9255056} {"current_steps": 16295, "total_steps": 40000, "loss": 0.0, "lr": 3.217440005286943e-05, "epoch": 285.88495575221236, "percentage": 40.74, "elapsed_time": "1:57:01", "remaining_time": "2:50:14", "throughput": 1318.46, "total_tokens": 9257888} {"current_steps": 16300, "total_steps": 40000, "loss": 0.0, "lr": 3.216499496783928e-05, "epoch": 285.9734513274336, "percentage": 40.75, "elapsed_time": "1:57:03", "remaining_time": "2:50:12", "throughput": 1318.5, "total_tokens": 9260832} {"current_steps": 16305, "total_steps": 40000, "loss": 0.0, "lr": 3.2155588777876856e-05, "epoch": 286.05309734513276, "percentage": 40.76, "elapsed_time": "1:57:06", "remaining_time": "2:50:10", "throughput": 1318.45, "total_tokens": 9263472} {"current_steps": 16310, "total_steps": 40000, "loss": 0.0, "lr": 3.214618148443273e-05, "epoch": 286.14159292035396, "percentage": 40.77, "elapsed_time": "1:57:08", "remaining_time": "2:50:08", "throughput": 1318.45, "total_tokens": 9266176} {"current_steps": 16315, "total_steps": 40000, "loss": 0.0, "lr": 3.2136773088957595e-05, "epoch": 286.2300884955752, "percentage": 40.79, "elapsed_time": "1:57:10", "remaining_time": "2:50:05", "throughput": 1318.47, "total_tokens": 9269056} {"current_steps": 16320, "total_steps": 40000, "loss": 0.0, "lr": 3.2127363592902374e-05, "epoch": 286.3185840707965, "percentage": 40.8, "elapsed_time": "1:57:12", "remaining_time": "2:50:03", "throughput": 1318.47, "total_tokens": 9271840} {"current_steps": 16325, "total_steps": 40000, "loss": 0.0, "lr": 3.211795299771812e-05, "epoch": 286.4070796460177, "percentage": 40.81, "elapsed_time": "1:57:14", "remaining_time": "2:50:01", "throughput": 1318.51, "total_tokens": 9274848} {"current_steps": 16330, "total_steps": 40000, "loss": 0.0, "lr": 3.210854130485605e-05, "epoch": 286.49557522123894, "percentage": 40.83, "elapsed_time": "1:57:16", "remaining_time": "2:49:59", "throughput": 1318.51, "total_tokens": 9277568} {"current_steps": 16335, "total_steps": 40000, "loss": 0.0, "lr": 3.209912851576759e-05, "epoch": 286.5840707964602, "percentage": 40.84, "elapsed_time": "1:57:18", "remaining_time": "2:49:56", "throughput": 1318.54, "total_tokens": 9280544} {"current_steps": 16340, "total_steps": 40000, "loss": 0.0, "lr": 3.208971463190431e-05, "epoch": 286.6725663716814, "percentage": 40.85, "elapsed_time": "1:57:20", "remaining_time": "2:49:54", "throughput": 1318.51, "total_tokens": 9283040} {"current_steps": 16345, "total_steps": 40000, "loss": 0.0, "lr": 3.208029965471793e-05, "epoch": 286.76106194690266, "percentage": 40.86, "elapsed_time": "1:57:22", "remaining_time": "2:49:52", "throughput": 1318.55, "total_tokens": 9286048} {"current_steps": 16350, "total_steps": 40000, "loss": 0.0, "lr": 3.2070883585660364e-05, "epoch": 286.8495575221239, "percentage": 40.88, "elapsed_time": "1:57:24", "remaining_time": "2:49:49", "throughput": 1318.64, "total_tokens": 9289392} {"current_steps": 16355, "total_steps": 40000, "loss": 0.0, "lr": 3.20614664261837e-05, "epoch": 286.9380530973451, "percentage": 40.89, "elapsed_time": "1:57:26", "remaining_time": "2:49:47", "throughput": 1318.62, "total_tokens": 9291952} {"current_steps": 16360, "total_steps": 40000, "loss": 0.0, "lr": 3.205204817774016e-05, "epoch": 287.01769911504425, "percentage": 40.9, "elapsed_time": "1:57:28", "remaining_time": "2:49:45", "throughput": 1318.51, "total_tokens": 9294184} {"current_steps": 16365, "total_steps": 40000, "loss": 0.0, "lr": 3.204262884178218e-05, "epoch": 287.1061946902655, "percentage": 40.91, "elapsed_time": "1:57:31", "remaining_time": "2:49:43", "throughput": 1318.55, "total_tokens": 9297176} {"current_steps": 16370, "total_steps": 40000, "loss": 0.0, "lr": 3.2033208419762314e-05, "epoch": 287.1946902654867, "percentage": 40.92, "elapsed_time": "1:57:33", "remaining_time": "2:49:41", "throughput": 1318.54, "total_tokens": 9299880} {"current_steps": 16375, "total_steps": 40000, "loss": 0.0, "lr": 3.2023786913133344e-05, "epoch": 287.283185840708, "percentage": 40.94, "elapsed_time": "1:57:35", "remaining_time": "2:49:38", "throughput": 1318.53, "total_tokens": 9302536} {"current_steps": 16380, "total_steps": 40000, "loss": 0.0, "lr": 3.201436432334816e-05, "epoch": 287.37168141592923, "percentage": 40.95, "elapsed_time": "1:57:37", "remaining_time": "2:49:36", "throughput": 1318.57, "total_tokens": 9305528} {"current_steps": 16385, "total_steps": 40000, "loss": 0.0, "lr": 3.2004940651859844e-05, "epoch": 287.46017699115043, "percentage": 40.96, "elapsed_time": "1:57:39", "remaining_time": "2:49:34", "throughput": 1318.6, "total_tokens": 9308488} {"current_steps": 16390, "total_steps": 40000, "loss": 0.0, "lr": 3.1995515900121655e-05, "epoch": 287.5486725663717, "percentage": 40.98, "elapsed_time": "1:57:41", "remaining_time": "2:49:32", "throughput": 1318.66, "total_tokens": 9311608} {"current_steps": 16395, "total_steps": 40000, "loss": 0.0, "lr": 3.1986090069587e-05, "epoch": 287.6371681415929, "percentage": 40.99, "elapsed_time": "1:57:43", "remaining_time": "2:49:29", "throughput": 1318.67, "total_tokens": 9314376} {"current_steps": 16400, "total_steps": 40000, "loss": 0.0, "lr": 3.1976663161709466e-05, "epoch": 287.72566371681415, "percentage": 41.0, "elapsed_time": "1:57:45", "remaining_time": "2:49:27", "throughput": 1318.68, "total_tokens": 9317208} {"current_steps": 16400, "total_steps": 40000, "eval_loss": 0.5181902647018433, "epoch": 287.72566371681415, "percentage": 41.0, "elapsed_time": "1:57:46", "remaining_time": "2:49:29", "throughput": 1318.48, "total_tokens": 9317208} {"current_steps": 16405, "total_steps": 40000, "loss": 0.0, "lr": 3.196723517794279e-05, "epoch": 287.8141592920354, "percentage": 41.01, "elapsed_time": "1:57:50", "remaining_time": "2:49:29", "throughput": 1318.23, "total_tokens": 9320456} {"current_steps": 16410, "total_steps": 40000, "loss": 0.0, "lr": 3.19578061197409e-05, "epoch": 287.9026548672566, "percentage": 41.02, "elapsed_time": "1:57:52", "remaining_time": "2:49:26", "throughput": 1318.27, "total_tokens": 9323400} {"current_steps": 16415, "total_steps": 40000, "loss": 0.0, "lr": 3.194837598855787e-05, "epoch": 287.9911504424779, "percentage": 41.04, "elapsed_time": "1:57:54", "remaining_time": "2:49:24", "throughput": 1318.25, "total_tokens": 9325992} {"current_steps": 16420, "total_steps": 40000, "loss": 0.0, "lr": 3.193894478584794e-05, "epoch": 288.070796460177, "percentage": 41.05, "elapsed_time": "1:57:56", "remaining_time": "2:49:22", "throughput": 1318.17, "total_tokens": 9328424} {"current_steps": 16425, "total_steps": 40000, "loss": 0.0, "lr": 3.192951251306553e-05, "epoch": 288.1592920353982, "percentage": 41.06, "elapsed_time": "1:57:58", "remaining_time": "2:49:20", "throughput": 1318.24, "total_tokens": 9331688} {"current_steps": 16430, "total_steps": 40000, "loss": 0.0, "lr": 3.192007917166521e-05, "epoch": 288.24778761061947, "percentage": 41.08, "elapsed_time": "1:58:00", "remaining_time": "2:49:18", "throughput": 1318.23, "total_tokens": 9334360} {"current_steps": 16435, "total_steps": 40000, "loss": 0.0, "lr": 3.191064476310171e-05, "epoch": 288.3362831858407, "percentage": 41.09, "elapsed_time": "1:58:03", "remaining_time": "2:49:15", "throughput": 1318.23, "total_tokens": 9337096} {"current_steps": 16440, "total_steps": 40000, "loss": 0.0, "lr": 3.1901209288829944e-05, "epoch": 288.42477876106193, "percentage": 41.1, "elapsed_time": "1:58:05", "remaining_time": "2:49:13", "throughput": 1318.26, "total_tokens": 9340024} {"current_steps": 16445, "total_steps": 40000, "loss": 0.0, "lr": 3.1891772750304985e-05, "epoch": 288.5132743362832, "percentage": 41.11, "elapsed_time": "1:58:07", "remaining_time": "2:49:11", "throughput": 1318.33, "total_tokens": 9343224} {"current_steps": 16450, "total_steps": 40000, "loss": 0.0, "lr": 3.188233514898206e-05, "epoch": 288.60176991150445, "percentage": 41.12, "elapsed_time": "1:58:09", "remaining_time": "2:49:09", "throughput": 1318.32, "total_tokens": 9345896} {"current_steps": 16455, "total_steps": 40000, "loss": 0.0, "lr": 3.187289648631657e-05, "epoch": 288.69026548672565, "percentage": 41.14, "elapsed_time": "1:58:11", "remaining_time": "2:49:06", "throughput": 1318.4, "total_tokens": 9349160} {"current_steps": 16460, "total_steps": 40000, "loss": 0.0, "lr": 3.186345676376406e-05, "epoch": 288.7787610619469, "percentage": 41.15, "elapsed_time": "1:58:13", "remaining_time": "2:49:04", "throughput": 1318.38, "total_tokens": 9351720} {"current_steps": 16465, "total_steps": 40000, "loss": 0.0, "lr": 3.1854015982780275e-05, "epoch": 288.86725663716817, "percentage": 41.16, "elapsed_time": "1:58:15", "remaining_time": "2:49:02", "throughput": 1318.31, "total_tokens": 9353976} {"current_steps": 16470, "total_steps": 40000, "loss": 0.0, "lr": 3.1844574144821084e-05, "epoch": 288.95575221238937, "percentage": 41.17, "elapsed_time": "1:58:17", "remaining_time": "2:48:59", "throughput": 1318.3, "total_tokens": 9356632} {"current_steps": 16475, "total_steps": 40000, "loss": 0.0, "lr": 3.1835131251342554e-05, "epoch": 289.0353982300885, "percentage": 41.19, "elapsed_time": "1:58:19", "remaining_time": "2:48:57", "throughput": 1318.26, "total_tokens": 9359328} {"current_steps": 16480, "total_steps": 40000, "loss": 0.0, "lr": 3.182568730380089e-05, "epoch": 289.12389380530976, "percentage": 41.2, "elapsed_time": "1:58:21", "remaining_time": "2:48:55", "throughput": 1318.29, "total_tokens": 9362272} {"current_steps": 16485, "total_steps": 40000, "loss": 0.0, "lr": 3.181624230365245e-05, "epoch": 289.21238938053096, "percentage": 41.21, "elapsed_time": "1:58:23", "remaining_time": "2:48:53", "throughput": 1318.28, "total_tokens": 9364960} {"current_steps": 16490, "total_steps": 40000, "loss": 0.0, "lr": 3.180679625235381e-05, "epoch": 289.3008849557522, "percentage": 41.23, "elapsed_time": "1:58:25", "remaining_time": "2:48:51", "throughput": 1318.34, "total_tokens": 9368096} {"current_steps": 16495, "total_steps": 40000, "loss": 0.0, "lr": 3.1797349151361646e-05, "epoch": 289.3893805309734, "percentage": 41.24, "elapsed_time": "1:58:28", "remaining_time": "2:48:48", "throughput": 1318.38, "total_tokens": 9371136} {"current_steps": 16500, "total_steps": 40000, "loss": 0.0, "lr": 3.178790100213281e-05, "epoch": 289.4778761061947, "percentage": 41.25, "elapsed_time": "1:58:30", "remaining_time": "2:48:46", "throughput": 1318.39, "total_tokens": 9373904} {"current_steps": 16505, "total_steps": 40000, "loss": 0.0, "lr": 3.1778451806124346e-05, "epoch": 289.56637168141594, "percentage": 41.26, "elapsed_time": "1:58:32", "remaining_time": "2:48:44", "throughput": 1318.38, "total_tokens": 9376608} {"current_steps": 16510, "total_steps": 40000, "loss": 0.0, "lr": 3.176900156479342e-05, "epoch": 289.65486725663715, "percentage": 41.27, "elapsed_time": "1:58:34", "remaining_time": "2:48:42", "throughput": 1318.34, "total_tokens": 9379040} {"current_steps": 16515, "total_steps": 40000, "loss": 0.0, "lr": 3.17595502795974e-05, "epoch": 289.7433628318584, "percentage": 41.29, "elapsed_time": "1:58:36", "remaining_time": "2:48:39", "throughput": 1318.36, "total_tokens": 9381904} {"current_steps": 16520, "total_steps": 40000, "loss": 0.0, "lr": 3.175009795199377e-05, "epoch": 289.83185840707966, "percentage": 41.3, "elapsed_time": "1:58:38", "remaining_time": "2:48:37", "throughput": 1318.4, "total_tokens": 9384944} {"current_steps": 16525, "total_steps": 40000, "loss": 0.0, "lr": 3.1740644583440224e-05, "epoch": 289.92035398230087, "percentage": 41.31, "elapsed_time": "1:58:40", "remaining_time": "2:48:35", "throughput": 1318.5, "total_tokens": 9388400} {"current_steps": 16530, "total_steps": 40000, "loss": 0.0, "lr": 3.173119017539457e-05, "epoch": 290.0, "percentage": 41.33, "elapsed_time": "1:58:42", "remaining_time": "2:48:32", "throughput": 1318.45, "total_tokens": 9390648} {"current_steps": 16535, "total_steps": 40000, "loss": 0.0, "lr": 3.172173472931479e-05, "epoch": 290.08849557522126, "percentage": 41.34, "elapsed_time": "1:58:44", "remaining_time": "2:48:30", "throughput": 1318.46, "total_tokens": 9393784} {"current_steps": 16540, "total_steps": 40000, "loss": 0.0, "lr": 3.1712278246659055e-05, "epoch": 290.17699115044246, "percentage": 41.35, "elapsed_time": "1:58:46", "remaining_time": "2:48:28", "throughput": 1318.48, "total_tokens": 9396680} {"current_steps": 16545, "total_steps": 40000, "loss": 0.0, "lr": 3.170282072888566e-05, "epoch": 290.2654867256637, "percentage": 41.36, "elapsed_time": "1:58:48", "remaining_time": "2:48:26", "throughput": 1318.53, "total_tokens": 9399784} {"current_steps": 16550, "total_steps": 40000, "loss": 0.0, "lr": 3.169336217745307e-05, "epoch": 290.353982300885, "percentage": 41.38, "elapsed_time": "1:58:51", "remaining_time": "2:48:24", "throughput": 1318.55, "total_tokens": 9402632} {"current_steps": 16555, "total_steps": 40000, "loss": 0.0, "lr": 3.1683902593819924e-05, "epoch": 290.4424778761062, "percentage": 41.39, "elapsed_time": "1:58:53", "remaining_time": "2:48:21", "throughput": 1318.55, "total_tokens": 9405368} {"current_steps": 16560, "total_steps": 40000, "loss": 0.0, "lr": 3.1674441979445e-05, "epoch": 290.53097345132744, "percentage": 41.4, "elapsed_time": "1:58:55", "remaining_time": "2:48:19", "throughput": 1318.6, "total_tokens": 9408456} {"current_steps": 16565, "total_steps": 40000, "loss": 0.0, "lr": 3.166498033578725e-05, "epoch": 290.6194690265487, "percentage": 41.41, "elapsed_time": "1:58:57", "remaining_time": "2:48:17", "throughput": 1318.56, "total_tokens": 9410920} {"current_steps": 16570, "total_steps": 40000, "loss": 0.0, "lr": 3.165551766430578e-05, "epoch": 290.7079646017699, "percentage": 41.42, "elapsed_time": "1:58:59", "remaining_time": "2:48:15", "throughput": 1318.61, "total_tokens": 9414024} {"current_steps": 16575, "total_steps": 40000, "loss": 0.0, "lr": 3.164605396645984e-05, "epoch": 290.79646017699116, "percentage": 41.44, "elapsed_time": "1:59:01", "remaining_time": "2:48:12", "throughput": 1318.67, "total_tokens": 9417144} {"current_steps": 16580, "total_steps": 40000, "loss": 0.0, "lr": 3.163658924370886e-05, "epoch": 290.88495575221236, "percentage": 41.45, "elapsed_time": "1:59:03", "remaining_time": "2:48:10", "throughput": 1318.69, "total_tokens": 9420024} {"current_steps": 16585, "total_steps": 40000, "loss": 0.0, "lr": 3.1627123497512415e-05, "epoch": 290.9734513274336, "percentage": 41.46, "elapsed_time": "1:59:05", "remaining_time": "2:48:08", "throughput": 1318.65, "total_tokens": 9422488} {"current_steps": 16590, "total_steps": 40000, "loss": 0.0, "lr": 3.1617656729330245e-05, "epoch": 291.05309734513276, "percentage": 41.48, "elapsed_time": "1:59:07", "remaining_time": "2:48:06", "throughput": 1318.57, "total_tokens": 9424856} {"current_steps": 16595, "total_steps": 40000, "loss": 0.0, "lr": 3.1608188940622255e-05, "epoch": 291.14159292035396, "percentage": 41.49, "elapsed_time": "1:59:09", "remaining_time": "2:48:03", "throughput": 1318.61, "total_tokens": 9427880} {"current_steps": 16600, "total_steps": 40000, "loss": 0.0, "lr": 3.159872013284847e-05, "epoch": 291.2300884955752, "percentage": 41.5, "elapsed_time": "1:59:11", "remaining_time": "2:48:01", "throughput": 1318.69, "total_tokens": 9431208} {"current_steps": 16600, "total_steps": 40000, "eval_loss": 0.5424460172653198, "epoch": 291.2300884955752, "percentage": 41.5, "elapsed_time": "1:59:12", "remaining_time": "2:48:03", "throughput": 1318.5, "total_tokens": 9431208} {"current_steps": 16605, "total_steps": 40000, "loss": 0.0, "lr": 3.1589250307469134e-05, "epoch": 291.3185840707965, "percentage": 41.51, "elapsed_time": "1:59:16", "remaining_time": "2:48:03", "throughput": 1318.15, "total_tokens": 9433976} {"current_steps": 16610, "total_steps": 40000, "loss": 0.0, "lr": 3.1579779465944586e-05, "epoch": 291.4070796460177, "percentage": 41.52, "elapsed_time": "1:59:19", "remaining_time": "2:48:01", "throughput": 1318.08, "total_tokens": 9436232} {"current_steps": 16615, "total_steps": 40000, "loss": 0.0, "lr": 3.1570307609735363e-05, "epoch": 291.49557522123894, "percentage": 41.54, "elapsed_time": "1:59:21", "remaining_time": "2:47:59", "throughput": 1318.1, "total_tokens": 9439112} {"current_steps": 16620, "total_steps": 40000, "loss": 0.0, "lr": 3.156083474030213e-05, "epoch": 291.5840707964602, "percentage": 41.55, "elapsed_time": "1:59:23", "remaining_time": "2:47:56", "throughput": 1318.09, "total_tokens": 9441736} {"current_steps": 16625, "total_steps": 40000, "loss": 0.0, "lr": 3.155136085910573e-05, "epoch": 291.6725663716814, "percentage": 41.56, "elapsed_time": "1:59:25", "remaining_time": "2:47:54", "throughput": 1318.09, "total_tokens": 9444504} {"current_steps": 16630, "total_steps": 40000, "loss": 0.0, "lr": 3.154188596760717e-05, "epoch": 291.76106194690266, "percentage": 41.58, "elapsed_time": "1:59:27", "remaining_time": "2:47:52", "throughput": 1318.13, "total_tokens": 9447496} {"current_steps": 16635, "total_steps": 40000, "loss": 0.0, "lr": 3.153241006726757e-05, "epoch": 291.8495575221239, "percentage": 41.59, "elapsed_time": "1:59:29", "remaining_time": "2:47:49", "throughput": 1318.19, "total_tokens": 9450648} {"current_steps": 16640, "total_steps": 40000, "loss": 0.0, "lr": 3.152293315954825e-05, "epoch": 291.9380530973451, "percentage": 41.6, "elapsed_time": "1:59:31", "remaining_time": "2:47:47", "throughput": 1318.26, "total_tokens": 9453880} {"current_steps": 16645, "total_steps": 40000, "loss": 0.0, "lr": 3.1513455245910666e-05, "epoch": 292.01769911504425, "percentage": 41.61, "elapsed_time": "1:59:33", "remaining_time": "2:47:45", "throughput": 1318.14, "total_tokens": 9455992} {"current_steps": 16650, "total_steps": 40000, "loss": 0.0, "lr": 3.150397632781643e-05, "epoch": 292.1061946902655, "percentage": 41.62, "elapsed_time": "1:59:35", "remaining_time": "2:47:43", "throughput": 1318.16, "total_tokens": 9458872} {"current_steps": 16655, "total_steps": 40000, "loss": 0.0, "lr": 3.149449640672731e-05, "epoch": 292.1946902654867, "percentage": 41.64, "elapsed_time": "1:59:37", "remaining_time": "2:47:41", "throughput": 1318.15, "total_tokens": 9461512} {"current_steps": 16660, "total_steps": 40000, "loss": 0.0, "lr": 3.148501548410523e-05, "epoch": 292.283185840708, "percentage": 41.65, "elapsed_time": "1:59:39", "remaining_time": "2:47:38", "throughput": 1318.15, "total_tokens": 9464216} {"current_steps": 16665, "total_steps": 40000, "loss": 0.0, "lr": 3.1475533561412256e-05, "epoch": 292.37168141592923, "percentage": 41.66, "elapsed_time": "1:59:42", "remaining_time": "2:47:36", "throughput": 1318.18, "total_tokens": 9467160} {"current_steps": 16670, "total_steps": 40000, "loss": 0.0, "lr": 3.146605064011065e-05, "epoch": 292.46017699115043, "percentage": 41.68, "elapsed_time": "1:59:44", "remaining_time": "2:47:34", "throughput": 1318.17, "total_tokens": 9469880} {"current_steps": 16675, "total_steps": 40000, "loss": 0.0, "lr": 3.145656672166277e-05, "epoch": 292.5486725663717, "percentage": 41.69, "elapsed_time": "1:59:46", "remaining_time": "2:47:32", "throughput": 1318.14, "total_tokens": 9472392} {"current_steps": 16680, "total_steps": 40000, "loss": 0.0, "lr": 3.144708180753116e-05, "epoch": 292.6371681415929, "percentage": 41.7, "elapsed_time": "1:59:48", "remaining_time": "2:47:29", "throughput": 1318.14, "total_tokens": 9475096} {"current_steps": 16685, "total_steps": 40000, "loss": 0.0, "lr": 3.143759589917851e-05, "epoch": 292.72566371681415, "percentage": 41.71, "elapsed_time": "1:59:50", "remaining_time": "2:47:27", "throughput": 1318.17, "total_tokens": 9478024} {"current_steps": 16690, "total_steps": 40000, "loss": 0.0, "lr": 3.142810899806768e-05, "epoch": 292.8141592920354, "percentage": 41.73, "elapsed_time": "1:59:52", "remaining_time": "2:47:25", "throughput": 1318.26, "total_tokens": 9481416} {"current_steps": 16695, "total_steps": 40000, "loss": 0.0, "lr": 3.141862110566166e-05, "epoch": 292.9026548672566, "percentage": 41.74, "elapsed_time": "1:59:54", "remaining_time": "2:47:22", "throughput": 1318.29, "total_tokens": 9484360} {"current_steps": 16700, "total_steps": 40000, "loss": 0.0, "lr": 3.1409132223423606e-05, "epoch": 292.9911504424779, "percentage": 41.75, "elapsed_time": "1:59:56", "remaining_time": "2:47:20", "throughput": 1318.32, "total_tokens": 9487320} {"current_steps": 16705, "total_steps": 40000, "loss": 0.0, "lr": 3.139964235281682e-05, "epoch": 293.070796460177, "percentage": 41.76, "elapsed_time": "1:59:58", "remaining_time": "2:47:18", "throughput": 1318.22, "total_tokens": 9489576} {"current_steps": 16710, "total_steps": 40000, "loss": 0.0, "lr": 3.139015149530476e-05, "epoch": 293.1592920353982, "percentage": 41.77, "elapsed_time": "2:00:00", "remaining_time": "2:47:16", "throughput": 1318.3, "total_tokens": 9492840} {"current_steps": 16715, "total_steps": 40000, "loss": 0.0, "lr": 3.1380659652351034e-05, "epoch": 293.24778761061947, "percentage": 41.79, "elapsed_time": "2:00:02", "remaining_time": "2:47:14", "throughput": 1318.28, "total_tokens": 9495496} {"current_steps": 16720, "total_steps": 40000, "loss": 0.0, "lr": 3.137116682541941e-05, "epoch": 293.3362831858407, "percentage": 41.8, "elapsed_time": "2:00:05", "remaining_time": "2:47:11", "throughput": 1318.32, "total_tokens": 9498504} {"current_steps": 16725, "total_steps": 40000, "loss": 0.0, "lr": 3.136167301597379e-05, "epoch": 293.42477876106193, "percentage": 41.81, "elapsed_time": "2:00:07", "remaining_time": "2:47:09", "throughput": 1318.36, "total_tokens": 9501544} {"current_steps": 16730, "total_steps": 40000, "loss": 0.0, "lr": 3.1352178225478254e-05, "epoch": 293.5132743362832, "percentage": 41.83, "elapsed_time": "2:00:09", "remaining_time": "2:47:07", "throughput": 1318.38, "total_tokens": 9504392} {"current_steps": 16735, "total_steps": 40000, "loss": 0.0, "lr": 3.1342682455396996e-05, "epoch": 293.60176991150445, "percentage": 41.84, "elapsed_time": "2:00:11", "remaining_time": "2:47:05", "throughput": 1318.4, "total_tokens": 9507256} {"current_steps": 16740, "total_steps": 40000, "loss": 0.0, "lr": 3.133318570719441e-05, "epoch": 293.69026548672565, "percentage": 41.85, "elapsed_time": "2:00:13", "remaining_time": "2:47:02", "throughput": 1318.4, "total_tokens": 9510008} {"current_steps": 16745, "total_steps": 40000, "loss": 0.0, "lr": 3.132368798233499e-05, "epoch": 293.7787610619469, "percentage": 41.86, "elapsed_time": "2:00:15", "remaining_time": "2:47:00", "throughput": 1318.45, "total_tokens": 9513064} {"current_steps": 16750, "total_steps": 40000, "loss": 0.0, "lr": 3.131418928228342e-05, "epoch": 293.86725663716817, "percentage": 41.88, "elapsed_time": "2:00:17", "remaining_time": "2:46:58", "throughput": 1318.46, "total_tokens": 9516232} {"current_steps": 16755, "total_steps": 40000, "loss": 0.0, "lr": 3.1304689608504514e-05, "epoch": 293.95575221238937, "percentage": 41.89, "elapsed_time": "2:00:19", "remaining_time": "2:46:56", "throughput": 1318.44, "total_tokens": 9518824} {"current_steps": 16760, "total_steps": 40000, "loss": 0.0, "lr": 3.129518896246324e-05, "epoch": 294.0353982300885, "percentage": 41.9, "elapsed_time": "2:00:22", "remaining_time": "2:46:54", "throughput": 1318.34, "total_tokens": 9521096} {"current_steps": 16765, "total_steps": 40000, "loss": 0.0, "lr": 3.128568734562472e-05, "epoch": 294.12389380530976, "percentage": 41.91, "elapsed_time": "2:00:24", "remaining_time": "2:46:52", "throughput": 1318.45, "total_tokens": 9524568} {"current_steps": 16770, "total_steps": 40000, "loss": 0.0, "lr": 3.127618475945421e-05, "epoch": 294.21238938053096, "percentage": 41.93, "elapsed_time": "2:00:26", "remaining_time": "2:46:49", "throughput": 1318.46, "total_tokens": 9527400} {"current_steps": 16775, "total_steps": 40000, "loss": 0.0, "lr": 3.126668120541715e-05, "epoch": 294.3008849557522, "percentage": 41.94, "elapsed_time": "2:00:28", "remaining_time": "2:46:47", "throughput": 1318.49, "total_tokens": 9530360} {"current_steps": 16780, "total_steps": 40000, "loss": 0.0, "lr": 3.1257176684979096e-05, "epoch": 294.3893805309734, "percentage": 41.95, "elapsed_time": "2:00:30", "remaining_time": "2:46:45", "throughput": 1318.48, "total_tokens": 9533032} {"current_steps": 16785, "total_steps": 40000, "loss": 0.0, "lr": 3.124767119960576e-05, "epoch": 294.4778761061947, "percentage": 41.96, "elapsed_time": "2:00:32", "remaining_time": "2:46:42", "throughput": 1318.47, "total_tokens": 9535704} {"current_steps": 16790, "total_steps": 40000, "loss": 0.0, "lr": 3.123816475076301e-05, "epoch": 294.56637168141594, "percentage": 41.98, "elapsed_time": "2:00:34", "remaining_time": "2:46:40", "throughput": 1318.48, "total_tokens": 9538488} {"current_steps": 16795, "total_steps": 40000, "loss": 0.0, "lr": 3.122865733991687e-05, "epoch": 294.65486725663715, "percentage": 41.99, "elapsed_time": "2:00:36", "remaining_time": "2:46:38", "throughput": 1318.52, "total_tokens": 9541448} {"current_steps": 16800, "total_steps": 40000, "loss": 0.0, "lr": 3.1219148968533486e-05, "epoch": 294.7433628318584, "percentage": 42.0, "elapsed_time": "2:00:38", "remaining_time": "2:46:36", "throughput": 1318.54, "total_tokens": 9544328} {"current_steps": 16800, "total_steps": 40000, "eval_loss": 0.5420147180557251, "epoch": 294.7433628318584, "percentage": 42.0, "elapsed_time": "2:00:39", "remaining_time": "2:46:37", "throughput": 1318.34, "total_tokens": 9544328} {"current_steps": 16805, "total_steps": 40000, "loss": 0.0, "lr": 3.120963963807918e-05, "epoch": 294.83185840707966, "percentage": 42.01, "elapsed_time": "2:00:43", "remaining_time": "2:46:37", "throughput": 1318.04, "total_tokens": 9547144} {"current_steps": 16810, "total_steps": 40000, "loss": 0.0, "lr": 3.12001293500204e-05, "epoch": 294.92035398230087, "percentage": 42.02, "elapsed_time": "2:00:45", "remaining_time": "2:46:35", "throughput": 1318.04, "total_tokens": 9549912} {"current_steps": 16815, "total_steps": 40000, "loss": 0.0, "lr": 3.1190618105823765e-05, "epoch": 295.0, "percentage": 42.04, "elapsed_time": "2:00:47", "remaining_time": "2:46:33", "throughput": 1318.03, "total_tokens": 9552440} {"current_steps": 16820, "total_steps": 40000, "loss": 0.0, "lr": 3.118110590695603e-05, "epoch": 295.08849557522126, "percentage": 42.05, "elapsed_time": "2:00:49", "remaining_time": "2:46:31", "throughput": 1317.96, "total_tokens": 9554984} {"current_steps": 16825, "total_steps": 40000, "loss": 0.0, "lr": 3.117159275488407e-05, "epoch": 295.17699115044246, "percentage": 42.06, "elapsed_time": "2:00:51", "remaining_time": "2:46:28", "throughput": 1318.0, "total_tokens": 9557992} {"current_steps": 16830, "total_steps": 40000, "loss": 0.0, "lr": 3.1162078651074956e-05, "epoch": 295.2654867256637, "percentage": 42.08, "elapsed_time": "2:00:53", "remaining_time": "2:46:26", "throughput": 1318.0, "total_tokens": 9560760} {"current_steps": 16835, "total_steps": 40000, "loss": 0.0, "lr": 3.1152563596995885e-05, "epoch": 295.353982300885, "percentage": 42.09, "elapsed_time": "2:00:56", "remaining_time": "2:46:24", "throughput": 1318.02, "total_tokens": 9563624} {"current_steps": 16840, "total_steps": 40000, "loss": 0.0, "lr": 3.1143047594114186e-05, "epoch": 295.4424778761062, "percentage": 42.1, "elapsed_time": "2:00:58", "remaining_time": "2:46:22", "throughput": 1318.0, "total_tokens": 9566248} {"current_steps": 16845, "total_steps": 40000, "loss": 0.0, "lr": 3.113353064389734e-05, "epoch": 295.53097345132744, "percentage": 42.11, "elapsed_time": "2:01:00", "remaining_time": "2:46:19", "throughput": 1317.99, "total_tokens": 9568904} {"current_steps": 16850, "total_steps": 40000, "loss": 0.0, "lr": 3.1124012747812993e-05, "epoch": 295.6194690265487, "percentage": 42.12, "elapsed_time": "2:01:02", "remaining_time": "2:46:17", "throughput": 1317.99, "total_tokens": 9571656} {"current_steps": 16855, "total_steps": 40000, "loss": 0.0, "lr": 3.1114493907328936e-05, "epoch": 295.7079646017699, "percentage": 42.14, "elapsed_time": "2:01:04", "remaining_time": "2:46:15", "throughput": 1318.02, "total_tokens": 9574584} {"current_steps": 16860, "total_steps": 40000, "loss": 0.0, "lr": 3.110497412391306e-05, "epoch": 295.79646017699116, "percentage": 42.15, "elapsed_time": "2:01:06", "remaining_time": "2:46:13", "throughput": 1318.06, "total_tokens": 9577592} {"current_steps": 16865, "total_steps": 40000, "loss": 0.0, "lr": 3.1095453399033466e-05, "epoch": 295.88495575221236, "percentage": 42.16, "elapsed_time": "2:01:08", "remaining_time": "2:46:10", "throughput": 1318.14, "total_tokens": 9580920} {"current_steps": 16870, "total_steps": 40000, "loss": 0.0, "lr": 3.108593173415835e-05, "epoch": 295.9734513274336, "percentage": 42.18, "elapsed_time": "2:01:10", "remaining_time": "2:46:08", "throughput": 1318.17, "total_tokens": 9583784} {"current_steps": 16875, "total_steps": 40000, "loss": 0.0, "lr": 3.107640913075609e-05, "epoch": 296.05309734513276, "percentage": 42.19, "elapsed_time": "2:01:12", "remaining_time": "2:46:06", "throughput": 1318.09, "total_tokens": 9586176} {"current_steps": 16880, "total_steps": 40000, "loss": 0.0, "lr": 3.106688559029517e-05, "epoch": 296.14159292035396, "percentage": 42.2, "elapsed_time": "2:01:14", "remaining_time": "2:46:04", "throughput": 1318.08, "total_tokens": 9588896} {"current_steps": 16885, "total_steps": 40000, "loss": 0.0, "lr": 3.105736111424425e-05, "epoch": 296.2300884955752, "percentage": 42.21, "elapsed_time": "2:01:16", "remaining_time": "2:46:01", "throughput": 1318.04, "total_tokens": 9591328} {"current_steps": 16890, "total_steps": 40000, "loss": 0.0, "lr": 3.1047835704072136e-05, "epoch": 296.3185840707965, "percentage": 42.23, "elapsed_time": "2:01:19", "remaining_time": "2:45:59", "throughput": 1318.01, "total_tokens": 9593808} {"current_steps": 16895, "total_steps": 40000, "loss": 0.0, "lr": 3.103830936124775e-05, "epoch": 296.4070796460177, "percentage": 42.24, "elapsed_time": "2:01:21", "remaining_time": "2:45:57", "throughput": 1318.06, "total_tokens": 9596912} {"current_steps": 16900, "total_steps": 40000, "loss": 0.0, "lr": 3.102878208724018e-05, "epoch": 296.49557522123894, "percentage": 42.25, "elapsed_time": "2:01:23", "remaining_time": "2:45:55", "throughput": 1318.12, "total_tokens": 9600096} {"current_steps": 16905, "total_steps": 40000, "loss": 0.0, "lr": 3.101925388351865e-05, "epoch": 296.5840707964602, "percentage": 42.26, "elapsed_time": "2:01:25", "remaining_time": "2:45:52", "throughput": 1318.08, "total_tokens": 9602528} {"current_steps": 16910, "total_steps": 40000, "loss": 0.0, "lr": 3.1009724751552515e-05, "epoch": 296.6725663716814, "percentage": 42.27, "elapsed_time": "2:01:27", "remaining_time": "2:45:50", "throughput": 1318.08, "total_tokens": 9605296} {"current_steps": 16915, "total_steps": 40000, "loss": 0.0, "lr": 3.100019469281131e-05, "epoch": 296.76106194690266, "percentage": 42.29, "elapsed_time": "2:01:29", "remaining_time": "2:45:48", "throughput": 1318.12, "total_tokens": 9608256} {"current_steps": 16920, "total_steps": 40000, "loss": 0.0, "lr": 3.0990663708764685e-05, "epoch": 296.8495575221239, "percentage": 42.3, "elapsed_time": "2:01:31", "remaining_time": "2:45:46", "throughput": 1318.19, "total_tokens": 9611536} {"current_steps": 16925, "total_steps": 40000, "loss": 0.0, "lr": 3.098113180088243e-05, "epoch": 296.9380530973451, "percentage": 42.31, "elapsed_time": "2:01:33", "remaining_time": "2:45:43", "throughput": 1318.27, "total_tokens": 9614832} {"current_steps": 16930, "total_steps": 40000, "loss": 0.0, "lr": 3.097159897063448e-05, "epoch": 297.01769911504425, "percentage": 42.33, "elapsed_time": "2:01:35", "remaining_time": "2:45:41", "throughput": 1318.21, "total_tokens": 9617344} {"current_steps": 16935, "total_steps": 40000, "loss": 0.0, "lr": 3.096206521949094e-05, "epoch": 297.1061946902655, "percentage": 42.34, "elapsed_time": "2:01:37", "remaining_time": "2:45:39", "throughput": 1318.27, "total_tokens": 9620544} {"current_steps": 16940, "total_steps": 40000, "loss": 0.0, "lr": 3.0952530548922006e-05, "epoch": 297.1946902654867, "percentage": 42.35, "elapsed_time": "2:01:39", "remaining_time": "2:45:37", "throughput": 1318.27, "total_tokens": 9623280} {"current_steps": 16945, "total_steps": 40000, "loss": 0.0, "lr": 3.0942994960398064e-05, "epoch": 297.283185840708, "percentage": 42.36, "elapsed_time": "2:01:41", "remaining_time": "2:45:34", "throughput": 1318.34, "total_tokens": 9626464} {"current_steps": 16950, "total_steps": 40000, "loss": 0.0, "lr": 3.093345845538961e-05, "epoch": 297.37168141592923, "percentage": 42.38, "elapsed_time": "2:01:44", "remaining_time": "2:45:32", "throughput": 1318.32, "total_tokens": 9629072} {"current_steps": 16955, "total_steps": 40000, "loss": 0.0, "lr": 3.09239210353673e-05, "epoch": 297.46017699115043, "percentage": 42.39, "elapsed_time": "2:01:46", "remaining_time": "2:45:30", "throughput": 1318.33, "total_tokens": 9631872} {"current_steps": 16960, "total_steps": 40000, "loss": 0.0, "lr": 3.0914382701801926e-05, "epoch": 297.5486725663717, "percentage": 42.4, "elapsed_time": "2:01:48", "remaining_time": "2:45:28", "throughput": 1318.34, "total_tokens": 9634640} {"current_steps": 16965, "total_steps": 40000, "loss": 0.0, "lr": 3.090484345616441e-05, "epoch": 297.6371681415929, "percentage": 42.41, "elapsed_time": "2:01:50", "remaining_time": "2:45:25", "throughput": 1318.34, "total_tokens": 9637360} {"current_steps": 16970, "total_steps": 40000, "loss": 0.0, "lr": 3.0895303299925825e-05, "epoch": 297.72566371681415, "percentage": 42.43, "elapsed_time": "2:01:52", "remaining_time": "2:45:23", "throughput": 1318.35, "total_tokens": 9640224} {"current_steps": 16975, "total_steps": 40000, "loss": 0.0, "lr": 3.0885762234557393e-05, "epoch": 297.8141592920354, "percentage": 42.44, "elapsed_time": "2:01:54", "remaining_time": "2:45:21", "throughput": 1318.33, "total_tokens": 9642800} {"current_steps": 16980, "total_steps": 40000, "loss": 0.0, "lr": 3.087622026153045e-05, "epoch": 297.9026548672566, "percentage": 42.45, "elapsed_time": "2:01:56", "remaining_time": "2:45:19", "throughput": 1318.34, "total_tokens": 9645600} {"current_steps": 16985, "total_steps": 40000, "loss": 0.0, "lr": 3.086667738231651e-05, "epoch": 297.9911504424779, "percentage": 42.46, "elapsed_time": "2:01:58", "remaining_time": "2:45:16", "throughput": 1318.42, "total_tokens": 9648912} {"current_steps": 16990, "total_steps": 40000, "loss": 0.0, "lr": 3.085713359838718e-05, "epoch": 298.070796460177, "percentage": 42.48, "elapsed_time": "2:02:00", "remaining_time": "2:45:14", "throughput": 1318.39, "total_tokens": 9651656} {"current_steps": 16995, "total_steps": 40000, "loss": 0.0, "lr": 3.084758891121425e-05, "epoch": 298.1592920353982, "percentage": 42.49, "elapsed_time": "2:02:02", "remaining_time": "2:45:12", "throughput": 1318.41, "total_tokens": 9654552} {"current_steps": 17000, "total_steps": 40000, "loss": 0.0, "lr": 3.083804332226963e-05, "epoch": 298.24778761061947, "percentage": 42.5, "elapsed_time": "2:02:04", "remaining_time": "2:45:10", "throughput": 1318.43, "total_tokens": 9657432} {"current_steps": 17000, "total_steps": 40000, "eval_loss": 0.5455121397972107, "epoch": 298.24778761061947, "percentage": 42.5, "elapsed_time": "2:02:05", "remaining_time": "2:45:11", "throughput": 1318.24, "total_tokens": 9657432} {"current_steps": 17005, "total_steps": 40000, "loss": 0.0, "lr": 3.082849683302536e-05, "epoch": 298.3362831858407, "percentage": 42.51, "elapsed_time": "2:02:09", "remaining_time": "2:45:11", "throughput": 1317.96, "total_tokens": 9660344} {"current_steps": 17010, "total_steps": 40000, "loss": 0.0, "lr": 3.081894944495363e-05, "epoch": 298.42477876106193, "percentage": 42.52, "elapsed_time": "2:02:11", "remaining_time": "2:45:09", "throughput": 1317.92, "total_tokens": 9662776} {"current_steps": 17015, "total_steps": 40000, "loss": 0.0, "lr": 3.080940115952677e-05, "epoch": 298.5132743362832, "percentage": 42.54, "elapsed_time": "2:02:13", "remaining_time": "2:45:07", "throughput": 1317.94, "total_tokens": 9665656} {"current_steps": 17020, "total_steps": 40000, "loss": 0.0, "lr": 3.0799851978217245e-05, "epoch": 298.60176991150445, "percentage": 42.55, "elapsed_time": "2:02:15", "remaining_time": "2:45:04", "throughput": 1317.92, "total_tokens": 9668296} {"current_steps": 17025, "total_steps": 40000, "loss": 0.0, "lr": 3.0790301902497666e-05, "epoch": 298.69026548672565, "percentage": 42.56, "elapsed_time": "2:02:18", "remaining_time": "2:45:02", "throughput": 1318.01, "total_tokens": 9671640} {"current_steps": 17030, "total_steps": 40000, "loss": 0.0, "lr": 3.078075093384076e-05, "epoch": 298.7787610619469, "percentage": 42.58, "elapsed_time": "2:02:20", "remaining_time": "2:45:00", "throughput": 1318.08, "total_tokens": 9674872} {"current_steps": 17035, "total_steps": 40000, "loss": 0.0, "lr": 3.077119907371942e-05, "epoch": 298.86725663716817, "percentage": 42.59, "elapsed_time": "2:02:22", "remaining_time": "2:44:58", "throughput": 1318.09, "total_tokens": 9677672} {"current_steps": 17040, "total_steps": 40000, "loss": 0.0, "lr": 3.076164632360666e-05, "epoch": 298.95575221238937, "percentage": 42.6, "elapsed_time": "2:02:24", "remaining_time": "2:44:55", "throughput": 1318.07, "total_tokens": 9680264} {"current_steps": 17045, "total_steps": 40000, "loss": 0.0, "lr": 3.075209268497563e-05, "epoch": 299.0353982300885, "percentage": 42.61, "elapsed_time": "2:02:26", "remaining_time": "2:44:53", "throughput": 1317.98, "total_tokens": 9682552} {"current_steps": 17050, "total_steps": 40000, "loss": 0.0, "lr": 3.074253815929961e-05, "epoch": 299.12389380530976, "percentage": 42.62, "elapsed_time": "2:02:28", "remaining_time": "2:44:51", "throughput": 1318.01, "total_tokens": 9685464} {"current_steps": 17055, "total_steps": 40000, "loss": 0.0, "lr": 3.0732982748052054e-05, "epoch": 299.21238938053096, "percentage": 42.64, "elapsed_time": "2:02:30", "remaining_time": "2:44:49", "throughput": 1318.07, "total_tokens": 9688632} {"current_steps": 17060, "total_steps": 40000, "loss": 0.0, "lr": 3.072342645270651e-05, "epoch": 299.3008849557522, "percentage": 42.65, "elapsed_time": "2:02:32", "remaining_time": "2:44:46", "throughput": 1318.05, "total_tokens": 9691288} {"current_steps": 17065, "total_steps": 40000, "loss": 0.0, "lr": 3.071386927473668e-05, "epoch": 299.3893805309734, "percentage": 42.66, "elapsed_time": "2:02:34", "remaining_time": "2:44:44", "throughput": 1318.08, "total_tokens": 9694168} {"current_steps": 17070, "total_steps": 40000, "loss": 0.0, "lr": 3.0704311215616404e-05, "epoch": 299.4778761061947, "percentage": 42.68, "elapsed_time": "2:02:36", "remaining_time": "2:44:42", "throughput": 1318.1, "total_tokens": 9697080} {"current_steps": 17075, "total_steps": 40000, "loss": 0.0, "lr": 3.0694752276819656e-05, "epoch": 299.56637168141594, "percentage": 42.69, "elapsed_time": "2:02:38", "remaining_time": "2:44:40", "throughput": 1318.11, "total_tokens": 9699832} {"current_steps": 17080, "total_steps": 40000, "loss": 0.0, "lr": 3.068519245982054e-05, "epoch": 299.65486725663715, "percentage": 42.7, "elapsed_time": "2:02:40", "remaining_time": "2:44:37", "throughput": 1318.13, "total_tokens": 9702712} {"current_steps": 17085, "total_steps": 40000, "loss": 0.0, "lr": 3.0675631766093304e-05, "epoch": 299.7433628318584, "percentage": 42.71, "elapsed_time": "2:02:43", "remaining_time": "2:44:35", "throughput": 1318.13, "total_tokens": 9705416} {"current_steps": 17090, "total_steps": 40000, "loss": 0.0, "lr": 3.066607019711232e-05, "epoch": 299.83185840707966, "percentage": 42.73, "elapsed_time": "2:02:45", "remaining_time": "2:44:33", "throughput": 1318.22, "total_tokens": 9708824} {"current_steps": 17095, "total_steps": 40000, "loss": 0.0, "lr": 3.065650775435211e-05, "epoch": 299.92035398230087, "percentage": 42.74, "elapsed_time": "2:02:47", "remaining_time": "2:44:31", "throughput": 1318.24, "total_tokens": 9711688} {"current_steps": 17100, "total_steps": 40000, "loss": 0.0, "lr": 3.0646944439287326e-05, "epoch": 300.0, "percentage": 42.75, "elapsed_time": "2:02:49", "remaining_time": "2:44:28", "throughput": 1318.17, "total_tokens": 9713848} {"current_steps": 17105, "total_steps": 40000, "loss": 0.0, "lr": 3.0637380253392736e-05, "epoch": 300.08849557522126, "percentage": 42.76, "elapsed_time": "2:02:51", "remaining_time": "2:44:26", "throughput": 1318.12, "total_tokens": 9716568} {"current_steps": 17110, "total_steps": 40000, "loss": 0.0, "lr": 3.062781519814327e-05, "epoch": 300.17699115044246, "percentage": 42.77, "elapsed_time": "2:02:53", "remaining_time": "2:44:24", "throughput": 1318.12, "total_tokens": 9719288} {"current_steps": 17115, "total_steps": 40000, "loss": 0.0, "lr": 3.0618249275013985e-05, "epoch": 300.2654867256637, "percentage": 42.79, "elapsed_time": "2:02:55", "remaining_time": "2:44:22", "throughput": 1318.17, "total_tokens": 9722344} {"current_steps": 17120, "total_steps": 40000, "loss": 0.0, "lr": 3.060868248548005e-05, "epoch": 300.353982300885, "percentage": 42.8, "elapsed_time": "2:02:57", "remaining_time": "2:44:19", "throughput": 1318.22, "total_tokens": 9725496} {"current_steps": 17125, "total_steps": 40000, "loss": 0.0, "lr": 3.0599114831016796e-05, "epoch": 300.4424778761062, "percentage": 42.81, "elapsed_time": "2:02:59", "remaining_time": "2:44:17", "throughput": 1318.25, "total_tokens": 9728456} {"current_steps": 17130, "total_steps": 40000, "loss": 0.0, "lr": 3.0589546313099666e-05, "epoch": 300.53097345132744, "percentage": 42.83, "elapsed_time": "2:03:01", "remaining_time": "2:44:15", "throughput": 1318.23, "total_tokens": 9731016} {"current_steps": 17135, "total_steps": 40000, "loss": 0.0, "lr": 3.0579976933204255e-05, "epoch": 300.6194690265487, "percentage": 42.84, "elapsed_time": "2:03:03", "remaining_time": "2:44:13", "throughput": 1318.32, "total_tokens": 9734408} {"current_steps": 17140, "total_steps": 40000, "loss": 0.0, "lr": 3.0570406692806284e-05, "epoch": 300.7079646017699, "percentage": 42.85, "elapsed_time": "2:03:06", "remaining_time": "2:44:10", "throughput": 1318.33, "total_tokens": 9737176} {"current_steps": 17145, "total_steps": 40000, "loss": 0.0, "lr": 3.05608355933816e-05, "epoch": 300.79646017699116, "percentage": 42.86, "elapsed_time": "2:03:08", "remaining_time": "2:44:08", "throughput": 1318.33, "total_tokens": 9739896} {"current_steps": 17150, "total_steps": 40000, "loss": 0.0, "lr": 3.055126363640618e-05, "epoch": 300.88495575221236, "percentage": 42.88, "elapsed_time": "2:03:10", "remaining_time": "2:44:06", "throughput": 1318.37, "total_tokens": 9742952} {"current_steps": 17155, "total_steps": 40000, "loss": 0.0, "lr": 3.0541690823356146e-05, "epoch": 300.9734513274336, "percentage": 42.89, "elapsed_time": "2:03:12", "remaining_time": "2:44:04", "throughput": 1318.4, "total_tokens": 9745896} {"current_steps": 17160, "total_steps": 40000, "loss": 0.0, "lr": 3.053211715570775e-05, "epoch": 301.05309734513276, "percentage": 42.9, "elapsed_time": "2:03:14", "remaining_time": "2:44:02", "throughput": 1318.29, "total_tokens": 9748024} {"current_steps": 17165, "total_steps": 40000, "loss": 0.0, "lr": 3.052254263493736e-05, "epoch": 301.14159292035396, "percentage": 42.91, "elapsed_time": "2:03:16", "remaining_time": "2:43:59", "throughput": 1318.27, "total_tokens": 9750664} {"current_steps": 17170, "total_steps": 40000, "loss": 0.0, "lr": 3.0512967262521498e-05, "epoch": 301.2300884955752, "percentage": 42.93, "elapsed_time": "2:03:18", "remaining_time": "2:43:57", "throughput": 1318.29, "total_tokens": 9753512} {"current_steps": 17175, "total_steps": 40000, "loss": 0.0, "lr": 3.0503391039936803e-05, "epoch": 301.3185840707965, "percentage": 42.94, "elapsed_time": "2:03:20", "remaining_time": "2:43:55", "throughput": 1318.35, "total_tokens": 9756664} {"current_steps": 17180, "total_steps": 40000, "loss": 0.0, "lr": 3.0493813968660056e-05, "epoch": 301.4070796460177, "percentage": 42.95, "elapsed_time": "2:03:22", "remaining_time": "2:43:52", "throughput": 1318.4, "total_tokens": 9759736} {"current_steps": 17185, "total_steps": 40000, "loss": 0.0, "lr": 3.0484236050168153e-05, "epoch": 301.49557522123894, "percentage": 42.96, "elapsed_time": "2:03:24", "remaining_time": "2:43:50", "throughput": 1318.43, "total_tokens": 9762728} {"current_steps": 17190, "total_steps": 40000, "loss": 0.0, "lr": 3.0474657285938123e-05, "epoch": 301.5840707964602, "percentage": 42.98, "elapsed_time": "2:03:26", "remaining_time": "2:43:48", "throughput": 1318.41, "total_tokens": 9765288} {"current_steps": 17195, "total_steps": 40000, "loss": 0.0, "lr": 3.046507767744715e-05, "epoch": 301.6725663716814, "percentage": 42.99, "elapsed_time": "2:03:28", "remaining_time": "2:43:46", "throughput": 1318.45, "total_tokens": 9768312} {"current_steps": 17200, "total_steps": 40000, "loss": 0.0, "lr": 3.045549722617252e-05, "epoch": 301.76106194690266, "percentage": 43.0, "elapsed_time": "2:03:31", "remaining_time": "2:43:43", "throughput": 1318.42, "total_tokens": 9770824} {"current_steps": 17200, "total_steps": 40000, "eval_loss": 0.555571973323822, "epoch": 301.76106194690266, "percentage": 43.0, "elapsed_time": "2:03:32", "remaining_time": "2:43:45", "throughput": 1318.23, "total_tokens": 9770824} {"current_steps": 17205, "total_steps": 40000, "loss": 0.0, "lr": 3.0445915933591658e-05, "epoch": 301.8495575221239, "percentage": 43.01, "elapsed_time": "2:03:35", "remaining_time": "2:43:45", "throughput": 1317.94, "total_tokens": 9773640} {"current_steps": 17210, "total_steps": 40000, "loss": 0.0, "lr": 3.0436333801182114e-05, "epoch": 301.9380530973451, "percentage": 43.03, "elapsed_time": "2:03:37", "remaining_time": "2:43:43", "throughput": 1318.08, "total_tokens": 9777448} {"current_steps": 17215, "total_steps": 40000, "loss": 0.0, "lr": 3.0426750830421596e-05, "epoch": 302.01769911504425, "percentage": 43.04, "elapsed_time": "2:03:40", "remaining_time": "2:43:41", "throughput": 1318.02, "total_tokens": 9779976} {"current_steps": 17220, "total_steps": 40000, "loss": 0.0, "lr": 3.0417167022787897e-05, "epoch": 302.1061946902655, "percentage": 43.05, "elapsed_time": "2:03:42", "remaining_time": "2:43:38", "throughput": 1317.98, "total_tokens": 9782440} {"current_steps": 17225, "total_steps": 40000, "loss": 0.0, "lr": 3.0407582379758966e-05, "epoch": 302.1946902654867, "percentage": 43.06, "elapsed_time": "2:03:44", "remaining_time": "2:43:36", "throughput": 1317.98, "total_tokens": 9785128} {"current_steps": 17230, "total_steps": 40000, "loss": 0.0, "lr": 3.039799690281287e-05, "epoch": 302.283185840708, "percentage": 43.08, "elapsed_time": "2:03:46", "remaining_time": "2:43:34", "throughput": 1318.0, "total_tokens": 9788056} {"current_steps": 17235, "total_steps": 40000, "loss": 0.0, "lr": 3.0388410593427823e-05, "epoch": 302.37168141592923, "percentage": 43.09, "elapsed_time": "2:03:48", "remaining_time": "2:43:31", "throughput": 1318.04, "total_tokens": 9791032} {"current_steps": 17240, "total_steps": 40000, "loss": 0.0, "lr": 3.0378823453082146e-05, "epoch": 302.46017699115043, "percentage": 43.1, "elapsed_time": "2:03:50", "remaining_time": "2:43:29", "throughput": 1318.04, "total_tokens": 9793784} {"current_steps": 17245, "total_steps": 40000, "loss": 0.0, "lr": 3.03692354832543e-05, "epoch": 302.5486725663717, "percentage": 43.11, "elapsed_time": "2:03:52", "remaining_time": "2:43:27", "throughput": 1318.08, "total_tokens": 9796808} {"current_steps": 17250, "total_steps": 40000, "loss": 0.0, "lr": 3.0359646685422865e-05, "epoch": 302.6371681415929, "percentage": 43.12, "elapsed_time": "2:03:54", "remaining_time": "2:43:25", "throughput": 1318.08, "total_tokens": 9799528} {"current_steps": 17255, "total_steps": 40000, "loss": 0.0, "lr": 3.035005706106656e-05, "epoch": 302.72566371681415, "percentage": 43.14, "elapsed_time": "2:03:56", "remaining_time": "2:43:22", "throughput": 1318.05, "total_tokens": 9802040} {"current_steps": 17260, "total_steps": 40000, "loss": 0.0, "lr": 3.034046661166422e-05, "epoch": 302.8141592920354, "percentage": 43.15, "elapsed_time": "2:03:58", "remaining_time": "2:43:20", "throughput": 1318.04, "total_tokens": 9804648} {"current_steps": 17265, "total_steps": 40000, "loss": 0.0, "lr": 3.033087533869482e-05, "epoch": 302.9026548672566, "percentage": 43.16, "elapsed_time": "2:04:00", "remaining_time": "2:43:18", "throughput": 1318.09, "total_tokens": 9807784} {"current_steps": 17270, "total_steps": 40000, "loss": 0.0, "lr": 3.0321283243637444e-05, "epoch": 302.9911504424779, "percentage": 43.18, "elapsed_time": "2:04:02", "remaining_time": "2:43:16", "throughput": 1318.17, "total_tokens": 9811080} {"current_steps": 17275, "total_steps": 40000, "loss": 0.0, "lr": 3.0311690327971326e-05, "epoch": 303.070796460177, "percentage": 43.19, "elapsed_time": "2:04:05", "remaining_time": "2:43:14", "throughput": 1318.06, "total_tokens": 9813280} {"current_steps": 17280, "total_steps": 40000, "loss": 0.0, "lr": 3.030209659317581e-05, "epoch": 303.1592920353982, "percentage": 43.2, "elapsed_time": "2:04:07", "remaining_time": "2:43:11", "throughput": 1318.13, "total_tokens": 9816496} {"current_steps": 17285, "total_steps": 40000, "loss": 0.0, "lr": 3.0292502040730362e-05, "epoch": 303.24778761061947, "percentage": 43.21, "elapsed_time": "2:04:09", "remaining_time": "2:43:09", "throughput": 1318.16, "total_tokens": 9819424} {"current_steps": 17290, "total_steps": 40000, "loss": 0.0, "lr": 3.0282906672114597e-05, "epoch": 303.3362831858407, "percentage": 43.23, "elapsed_time": "2:04:11", "remaining_time": "2:43:07", "throughput": 1318.2, "total_tokens": 9822464} {"current_steps": 17295, "total_steps": 40000, "loss": 0.0, "lr": 3.027331048880823e-05, "epoch": 303.42477876106193, "percentage": 43.24, "elapsed_time": "2:04:13", "remaining_time": "2:43:04", "throughput": 1318.24, "total_tokens": 9825504} {"current_steps": 17300, "total_steps": 40000, "loss": 0.0, "lr": 3.0263713492291123e-05, "epoch": 303.5132743362832, "percentage": 43.25, "elapsed_time": "2:04:15", "remaining_time": "2:43:02", "throughput": 1318.24, "total_tokens": 9828240} {"current_steps": 17305, "total_steps": 40000, "loss": 0.0, "lr": 3.0254115684043242e-05, "epoch": 303.60176991150445, "percentage": 43.26, "elapsed_time": "2:04:17", "remaining_time": "2:43:00", "throughput": 1318.26, "total_tokens": 9831120} {"current_steps": 17310, "total_steps": 40000, "loss": 0.0, "lr": 3.024451706554469e-05, "epoch": 303.69026548672565, "percentage": 43.28, "elapsed_time": "2:04:19", "remaining_time": "2:42:58", "throughput": 1318.33, "total_tokens": 9834368} {"current_steps": 17315, "total_steps": 40000, "loss": 0.0, "lr": 3.0234917638275705e-05, "epoch": 303.7787610619469, "percentage": 43.29, "elapsed_time": "2:04:21", "remaining_time": "2:42:55", "throughput": 1318.31, "total_tokens": 9836976} {"current_steps": 17320, "total_steps": 40000, "loss": 0.0, "lr": 3.0225317403716635e-05, "epoch": 303.86725663716817, "percentage": 43.3, "elapsed_time": "2:04:23", "remaining_time": "2:42:53", "throughput": 1318.31, "total_tokens": 9839680} {"current_steps": 17325, "total_steps": 40000, "loss": 0.0, "lr": 3.0215716363347956e-05, "epoch": 303.95575221238937, "percentage": 43.31, "elapsed_time": "2:04:25", "remaining_time": "2:42:51", "throughput": 1318.29, "total_tokens": 9842240} {"current_steps": 17330, "total_steps": 40000, "loss": 0.0, "lr": 3.0206114518650275e-05, "epoch": 304.0353982300885, "percentage": 43.33, "elapsed_time": "2:04:28", "remaining_time": "2:42:49", "throughput": 1318.24, "total_tokens": 9844824} {"current_steps": 17335, "total_steps": 40000, "loss": 0.0, "lr": 3.0196511871104304e-05, "epoch": 304.12389380530976, "percentage": 43.34, "elapsed_time": "2:04:30", "remaining_time": "2:42:47", "throughput": 1318.28, "total_tokens": 9847880} {"current_steps": 17340, "total_steps": 40000, "loss": 0.0, "lr": 3.01869084221909e-05, "epoch": 304.21238938053096, "percentage": 43.35, "elapsed_time": "2:04:32", "remaining_time": "2:42:44", "throughput": 1318.28, "total_tokens": 9850632} {"current_steps": 17345, "total_steps": 40000, "loss": 0.0, "lr": 3.0177304173391037e-05, "epoch": 304.3008849557522, "percentage": 43.36, "elapsed_time": "2:04:34", "remaining_time": "2:42:42", "throughput": 1318.26, "total_tokens": 9853176} {"current_steps": 17350, "total_steps": 40000, "loss": 0.0, "lr": 3.01676991261858e-05, "epoch": 304.3893805309734, "percentage": 43.38, "elapsed_time": "2:04:36", "remaining_time": "2:42:40", "throughput": 1318.23, "total_tokens": 9855736} {"current_steps": 17355, "total_steps": 40000, "loss": 0.0, "lr": 3.015809328205642e-05, "epoch": 304.4778761061947, "percentage": 43.39, "elapsed_time": "2:04:38", "remaining_time": "2:42:38", "throughput": 1318.24, "total_tokens": 9858520} {"current_steps": 17360, "total_steps": 40000, "loss": 0.0, "lr": 3.0148486642484248e-05, "epoch": 304.56637168141594, "percentage": 43.4, "elapsed_time": "2:04:40", "remaining_time": "2:42:35", "throughput": 1318.25, "total_tokens": 9861288} {"current_steps": 17365, "total_steps": 40000, "loss": 0.0, "lr": 3.0138879208950722e-05, "epoch": 304.65486725663715, "percentage": 43.41, "elapsed_time": "2:04:42", "remaining_time": "2:42:33", "throughput": 1318.24, "total_tokens": 9863976} {"current_steps": 17370, "total_steps": 40000, "loss": 0.0, "lr": 3.012927098293744e-05, "epoch": 304.7433628318584, "percentage": 43.43, "elapsed_time": "2:04:44", "remaining_time": "2:42:31", "throughput": 1318.31, "total_tokens": 9867192} {"current_steps": 17375, "total_steps": 40000, "loss": 0.0, "lr": 3.0119661965926123e-05, "epoch": 304.83185840707966, "percentage": 43.44, "elapsed_time": "2:04:46", "remaining_time": "2:42:29", "throughput": 1318.39, "total_tokens": 9870552} {"current_steps": 17380, "total_steps": 40000, "loss": 0.0, "lr": 3.0110052159398587e-05, "epoch": 304.92035398230087, "percentage": 43.45, "elapsed_time": "2:04:48", "remaining_time": "2:42:26", "throughput": 1318.41, "total_tokens": 9873416} {"current_steps": 17385, "total_steps": 40000, "loss": 0.0, "lr": 3.0100441564836802e-05, "epoch": 305.0, "percentage": 43.46, "elapsed_time": "2:04:50", "remaining_time": "2:42:24", "throughput": 1318.38, "total_tokens": 9875816} {"current_steps": 17390, "total_steps": 40000, "loss": 0.0, "lr": 3.0090830183722817e-05, "epoch": 305.08849557522126, "percentage": 43.48, "elapsed_time": "2:04:53", "remaining_time": "2:42:22", "throughput": 1318.41, "total_tokens": 9879064} {"current_steps": 17395, "total_steps": 40000, "loss": 0.0, "lr": 3.0081218017538852e-05, "epoch": 305.17699115044246, "percentage": 43.49, "elapsed_time": "2:04:55", "remaining_time": "2:42:20", "throughput": 1318.43, "total_tokens": 9881928} {"current_steps": 17400, "total_steps": 40000, "loss": 0.0, "lr": 3.0071605067767212e-05, "epoch": 305.2654867256637, "percentage": 43.5, "elapsed_time": "2:04:57", "remaining_time": "2:42:17", "throughput": 1318.42, "total_tokens": 9884648} {"current_steps": 17400, "total_steps": 40000, "eval_loss": 0.5646206140518188, "epoch": 305.2654867256637, "percentage": 43.5, "elapsed_time": "2:04:58", "remaining_time": "2:42:19", "throughput": 1318.24, "total_tokens": 9884648} {"current_steps": 17405, "total_steps": 40000, "loss": 0.0, "lr": 3.006199133589034e-05, "epoch": 305.353982300885, "percentage": 43.51, "elapsed_time": "2:05:02", "remaining_time": "2:42:19", "throughput": 1317.93, "total_tokens": 9887384} {"current_steps": 17410, "total_steps": 40000, "loss": 0.0, "lr": 3.005237682339079e-05, "epoch": 305.4424778761062, "percentage": 43.53, "elapsed_time": "2:05:04", "remaining_time": "2:42:17", "throughput": 1317.96, "total_tokens": 9890344} {"current_steps": 17415, "total_steps": 40000, "loss": 0.0, "lr": 3.0042761531751228e-05, "epoch": 305.53097345132744, "percentage": 43.54, "elapsed_time": "2:05:06", "remaining_time": "2:42:14", "throughput": 1317.97, "total_tokens": 9893144} {"current_steps": 17420, "total_steps": 40000, "loss": 0.0, "lr": 3.0033145462454482e-05, "epoch": 305.6194690265487, "percentage": 43.55, "elapsed_time": "2:05:08", "remaining_time": "2:42:12", "throughput": 1317.97, "total_tokens": 9895848} {"current_steps": 17425, "total_steps": 40000, "loss": 0.0, "lr": 3.002352861698345e-05, "epoch": 305.7079646017699, "percentage": 43.56, "elapsed_time": "2:05:10", "remaining_time": "2:42:10", "throughput": 1318.05, "total_tokens": 9899160} {"current_steps": 17430, "total_steps": 40000, "loss": 0.0, "lr": 3.0013910996821178e-05, "epoch": 305.79646017699116, "percentage": 43.58, "elapsed_time": "2:05:12", "remaining_time": "2:42:07", "throughput": 1318.07, "total_tokens": 9902024} {"current_steps": 17435, "total_steps": 40000, "loss": 0.0, "lr": 3.0004292603450817e-05, "epoch": 305.88495575221236, "percentage": 43.59, "elapsed_time": "2:05:14", "remaining_time": "2:42:05", "throughput": 1318.06, "total_tokens": 9904728} {"current_steps": 17440, "total_steps": 40000, "loss": 0.0, "lr": 2.9994673438355653e-05, "epoch": 305.9734513274336, "percentage": 43.6, "elapsed_time": "2:05:16", "remaining_time": "2:42:03", "throughput": 1318.08, "total_tokens": 9907576} {"current_steps": 17445, "total_steps": 40000, "loss": 0.0, "lr": 2.9985053503019078e-05, "epoch": 306.05309734513276, "percentage": 43.61, "elapsed_time": "2:05:18", "remaining_time": "2:42:01", "throughput": 1317.96, "total_tokens": 9909608} {"current_steps": 17450, "total_steps": 40000, "loss": 0.0, "lr": 2.99754327989246e-05, "epoch": 306.14159292035396, "percentage": 43.62, "elapsed_time": "2:05:20", "remaining_time": "2:41:59", "throughput": 1317.99, "total_tokens": 9912584} {"current_steps": 17455, "total_steps": 40000, "loss": 0.0, "lr": 2.9965811327555864e-05, "epoch": 306.2300884955752, "percentage": 43.64, "elapsed_time": "2:05:23", "remaining_time": "2:41:56", "throughput": 1317.97, "total_tokens": 9915208} {"current_steps": 17460, "total_steps": 40000, "loss": 0.0, "lr": 2.995618909039662e-05, "epoch": 306.3185840707965, "percentage": 43.65, "elapsed_time": "2:05:25", "remaining_time": "2:41:54", "throughput": 1318.01, "total_tokens": 9918184} {"current_steps": 17465, "total_steps": 40000, "loss": 0.0, "lr": 2.9946566088930727e-05, "epoch": 306.4070796460177, "percentage": 43.66, "elapsed_time": "2:05:27", "remaining_time": "2:41:52", "throughput": 1317.99, "total_tokens": 9920776} {"current_steps": 17470, "total_steps": 40000, "loss": 0.0, "lr": 2.9936942324642192e-05, "epoch": 306.49557522123894, "percentage": 43.68, "elapsed_time": "2:05:29", "remaining_time": "2:41:50", "throughput": 1317.98, "total_tokens": 9923400} {"current_steps": 17475, "total_steps": 40000, "loss": 0.0, "lr": 2.9927317799015097e-05, "epoch": 306.5840707964602, "percentage": 43.69, "elapsed_time": "2:05:31", "remaining_time": "2:41:47", "throughput": 1318.12, "total_tokens": 9927256} {"current_steps": 17480, "total_steps": 40000, "loss": 0.0, "lr": 2.9917692513533685e-05, "epoch": 306.6725663716814, "percentage": 43.7, "elapsed_time": "2:05:33", "remaining_time": "2:41:45", "throughput": 1318.09, "total_tokens": 9929704} {"current_steps": 17485, "total_steps": 40000, "loss": 0.0, "lr": 2.990806646968229e-05, "epoch": 306.76106194690266, "percentage": 43.71, "elapsed_time": "2:05:35", "remaining_time": "2:41:43", "throughput": 1318.15, "total_tokens": 9932872} {"current_steps": 17490, "total_steps": 40000, "loss": 0.0, "lr": 2.989843966894536e-05, "epoch": 306.8495575221239, "percentage": 43.73, "elapsed_time": "2:05:37", "remaining_time": "2:41:40", "throughput": 1318.15, "total_tokens": 9935608} {"current_steps": 17495, "total_steps": 40000, "loss": 0.0, "lr": 2.9888812112807472e-05, "epoch": 306.9380530973451, "percentage": 43.74, "elapsed_time": "2:05:39", "remaining_time": "2:41:38", "throughput": 1318.19, "total_tokens": 9938632} {"current_steps": 17500, "total_steps": 40000, "loss": 0.0, "lr": 2.987918380275333e-05, "epoch": 307.01769911504425, "percentage": 43.75, "elapsed_time": "2:05:41", "remaining_time": "2:41:36", "throughput": 1318.09, "total_tokens": 9940824} {"current_steps": 17505, "total_steps": 40000, "loss": 0.0, "lr": 2.9869554740267724e-05, "epoch": 307.1061946902655, "percentage": 43.76, "elapsed_time": "2:05:43", "remaining_time": "2:41:34", "throughput": 1318.1, "total_tokens": 9943704} {"current_steps": 17510, "total_steps": 40000, "loss": 0.0, "lr": 2.9859924926835585e-05, "epoch": 307.1946902654867, "percentage": 43.77, "elapsed_time": "2:05:46", "remaining_time": "2:41:32", "throughput": 1318.07, "total_tokens": 9946184} {"current_steps": 17515, "total_steps": 40000, "loss": 0.0, "lr": 2.9850294363941944e-05, "epoch": 307.283185840708, "percentage": 43.79, "elapsed_time": "2:05:48", "remaining_time": "2:41:29", "throughput": 1318.08, "total_tokens": 9949000} {"current_steps": 17520, "total_steps": 40000, "loss": 0.0, "lr": 2.9840663053071967e-05, "epoch": 307.37168141592923, "percentage": 43.8, "elapsed_time": "2:05:50", "remaining_time": "2:41:27", "throughput": 1318.12, "total_tokens": 9952072} {"current_steps": 17525, "total_steps": 40000, "loss": 0.0, "lr": 2.983103099571091e-05, "epoch": 307.46017699115043, "percentage": 43.81, "elapsed_time": "2:05:52", "remaining_time": "2:41:25", "throughput": 1318.08, "total_tokens": 9954440} {"current_steps": 17530, "total_steps": 40000, "loss": 0.0, "lr": 2.9821398193344164e-05, "epoch": 307.5486725663717, "percentage": 43.82, "elapsed_time": "2:05:54", "remaining_time": "2:41:23", "throughput": 1318.13, "total_tokens": 9957560} {"current_steps": 17535, "total_steps": 40000, "loss": 0.0, "lr": 2.9811764647457226e-05, "epoch": 307.6371681415929, "percentage": 43.84, "elapsed_time": "2:05:56", "remaining_time": "2:41:20", "throughput": 1318.12, "total_tokens": 9960216} {"current_steps": 17540, "total_steps": 40000, "loss": 0.0, "lr": 2.9802130359535714e-05, "epoch": 307.72566371681415, "percentage": 43.85, "elapsed_time": "2:05:58", "remaining_time": "2:41:18", "throughput": 1318.16, "total_tokens": 9963288} {"current_steps": 17545, "total_steps": 40000, "loss": 0.0, "lr": 2.979249533106535e-05, "epoch": 307.8141592920354, "percentage": 43.86, "elapsed_time": "2:06:00", "remaining_time": "2:41:16", "throughput": 1318.16, "total_tokens": 9965960} {"current_steps": 17550, "total_steps": 40000, "loss": 0.0, "lr": 2.9782859563531986e-05, "epoch": 307.9026548672566, "percentage": 43.88, "elapsed_time": "2:06:02", "remaining_time": "2:41:14", "throughput": 1318.2, "total_tokens": 9969000} {"current_steps": 17555, "total_steps": 40000, "loss": 0.0, "lr": 2.977322305842156e-05, "epoch": 307.9911504424779, "percentage": 43.89, "elapsed_time": "2:06:04", "remaining_time": "2:41:11", "throughput": 1318.23, "total_tokens": 9971928} {"current_steps": 17560, "total_steps": 40000, "loss": 0.0, "lr": 2.9763585817220162e-05, "epoch": 308.070796460177, "percentage": 43.9, "elapsed_time": "2:06:06", "remaining_time": "2:41:09", "throughput": 1318.2, "total_tokens": 9974680} {"current_steps": 17565, "total_steps": 40000, "loss": 0.0, "lr": 2.975394784141397e-05, "epoch": 308.1592920353982, "percentage": 43.91, "elapsed_time": "2:06:08", "remaining_time": "2:41:07", "throughput": 1318.19, "total_tokens": 9977352} {"current_steps": 17570, "total_steps": 40000, "loss": 0.0, "lr": 2.974430913248928e-05, "epoch": 308.24778761061947, "percentage": 43.92, "elapsed_time": "2:06:11", "remaining_time": "2:41:05", "throughput": 1318.26, "total_tokens": 9980584} {"current_steps": 17575, "total_steps": 40000, "loss": 0.0, "lr": 2.9734669691932497e-05, "epoch": 308.3362831858407, "percentage": 43.94, "elapsed_time": "2:06:13", "remaining_time": "2:41:03", "throughput": 1318.22, "total_tokens": 9983064} {"current_steps": 17580, "total_steps": 40000, "loss": 0.0, "lr": 2.9725029521230147e-05, "epoch": 308.42477876106193, "percentage": 43.95, "elapsed_time": "2:06:15", "remaining_time": "2:41:00", "throughput": 1318.22, "total_tokens": 9985768} {"current_steps": 17585, "total_steps": 40000, "loss": 0.0, "lr": 2.9715388621868873e-05, "epoch": 308.5132743362832, "percentage": 43.96, "elapsed_time": "2:06:17", "remaining_time": "2:40:58", "throughput": 1318.27, "total_tokens": 9988856} {"current_steps": 17590, "total_steps": 40000, "loss": 0.0, "lr": 2.970574699533541e-05, "epoch": 308.60176991150445, "percentage": 43.97, "elapsed_time": "2:06:19", "remaining_time": "2:40:56", "throughput": 1318.24, "total_tokens": 9991352} {"current_steps": 17595, "total_steps": 40000, "loss": 0.0, "lr": 2.969610464311662e-05, "epoch": 308.69026548672565, "percentage": 43.99, "elapsed_time": "2:06:21", "remaining_time": "2:40:53", "throughput": 1318.3, "total_tokens": 9994584} {"current_steps": 17600, "total_steps": 40000, "loss": 0.0, "lr": 2.9686461566699487e-05, "epoch": 308.7787610619469, "percentage": 44.0, "elapsed_time": "2:06:23", "remaining_time": "2:40:51", "throughput": 1318.3, "total_tokens": 9997288} {"current_steps": 17600, "total_steps": 40000, "eval_loss": 0.5576398372650146, "epoch": 308.7787610619469, "percentage": 44.0, "elapsed_time": "2:06:24", "remaining_time": "2:40:53", "throughput": 1318.12, "total_tokens": 9997288} {"current_steps": 17605, "total_steps": 40000, "loss": 0.0, "lr": 2.9676817767571086e-05, "epoch": 308.86725663716817, "percentage": 44.01, "elapsed_time": "2:06:28", "remaining_time": "2:40:53", "throughput": 1317.76, "total_tokens": 9999976} {"current_steps": 17610, "total_steps": 40000, "loss": 0.0, "lr": 2.966717324721861e-05, "epoch": 308.95575221238937, "percentage": 44.02, "elapsed_time": "2:06:30", "remaining_time": "2:40:51", "throughput": 1317.84, "total_tokens": 10003320} {"current_steps": 17615, "total_steps": 40000, "loss": 0.0, "lr": 2.9657528007129366e-05, "epoch": 309.0353982300885, "percentage": 44.04, "elapsed_time": "2:06:32", "remaining_time": "2:40:49", "throughput": 1317.76, "total_tokens": 10005664} {"current_steps": 17620, "total_steps": 40000, "loss": 0.0, "lr": 2.9647882048790777e-05, "epoch": 309.12389380530976, "percentage": 44.05, "elapsed_time": "2:06:35", "remaining_time": "2:40:46", "throughput": 1317.74, "total_tokens": 10008288} {"current_steps": 17625, "total_steps": 40000, "loss": 0.0, "lr": 2.963823537369037e-05, "epoch": 309.21238938053096, "percentage": 44.06, "elapsed_time": "2:06:37", "remaining_time": "2:40:44", "throughput": 1317.8, "total_tokens": 10011440} {"current_steps": 17630, "total_steps": 40000, "loss": 0.0, "lr": 2.9628587983315775e-05, "epoch": 309.3008849557522, "percentage": 44.07, "elapsed_time": "2:06:39", "remaining_time": "2:40:42", "throughput": 1317.87, "total_tokens": 10014720} {"current_steps": 17635, "total_steps": 40000, "loss": 0.0, "lr": 2.9618939879154746e-05, "epoch": 309.3893805309734, "percentage": 44.09, "elapsed_time": "2:06:41", "remaining_time": "2:40:39", "throughput": 1317.87, "total_tokens": 10017408} {"current_steps": 17640, "total_steps": 40000, "loss": 0.0, "lr": 2.9609291062695143e-05, "epoch": 309.4778761061947, "percentage": 44.1, "elapsed_time": "2:06:43", "remaining_time": "2:40:37", "throughput": 1317.87, "total_tokens": 10020096} {"current_steps": 17645, "total_steps": 40000, "loss": 0.0, "lr": 2.9599641535424938e-05, "epoch": 309.56637168141594, "percentage": 44.11, "elapsed_time": "2:06:45", "remaining_time": "2:40:35", "throughput": 1317.88, "total_tokens": 10022944} {"current_steps": 17650, "total_steps": 40000, "loss": 0.0, "lr": 2.9589991298832202e-05, "epoch": 309.65486725663715, "percentage": 44.12, "elapsed_time": "2:06:47", "remaining_time": "2:40:33", "throughput": 1317.83, "total_tokens": 10025344} {"current_steps": 17655, "total_steps": 40000, "loss": 0.0, "lr": 2.958034035440513e-05, "epoch": 309.7433628318584, "percentage": 44.14, "elapsed_time": "2:06:49", "remaining_time": "2:40:30", "throughput": 1317.91, "total_tokens": 10028656} {"current_steps": 17660, "total_steps": 40000, "loss": 0.0, "lr": 2.957068870363201e-05, "epoch": 309.83185840707966, "percentage": 44.15, "elapsed_time": "2:06:51", "remaining_time": "2:40:28", "throughput": 1317.94, "total_tokens": 10031616} {"current_steps": 17665, "total_steps": 40000, "loss": 0.0, "lr": 2.956103634800126e-05, "epoch": 309.92035398230087, "percentage": 44.16, "elapsed_time": "2:06:53", "remaining_time": "2:40:26", "throughput": 1317.95, "total_tokens": 10034416} {"current_steps": 17670, "total_steps": 40000, "loss": 0.0, "lr": 2.9551383289001384e-05, "epoch": 310.0, "percentage": 44.17, "elapsed_time": "2:06:55", "remaining_time": "2:40:24", "throughput": 1317.93, "total_tokens": 10036912} {"current_steps": 17675, "total_steps": 40000, "loss": 0.0, "lr": 2.9541729528121005e-05, "epoch": 310.08849557522126, "percentage": 44.19, "elapsed_time": "2:06:57", "remaining_time": "2:40:22", "throughput": 1317.86, "total_tokens": 10039408} {"current_steps": 17680, "total_steps": 40000, "loss": 0.0, "lr": 2.9532075066848856e-05, "epoch": 310.17699115044246, "percentage": 44.2, "elapsed_time": "2:07:00", "remaining_time": "2:40:19", "throughput": 1317.88, "total_tokens": 10042304} {"current_steps": 17685, "total_steps": 40000, "loss": 0.0, "lr": 2.9522419906673786e-05, "epoch": 310.2654867256637, "percentage": 44.21, "elapsed_time": "2:07:02", "remaining_time": "2:40:17", "throughput": 1317.91, "total_tokens": 10045232} {"current_steps": 17690, "total_steps": 40000, "loss": 0.0, "lr": 2.951276404908474e-05, "epoch": 310.353982300885, "percentage": 44.22, "elapsed_time": "2:07:04", "remaining_time": "2:40:15", "throughput": 1317.99, "total_tokens": 10048608} {"current_steps": 17695, "total_steps": 40000, "loss": 0.0, "lr": 2.9503107495570752e-05, "epoch": 310.4424778761062, "percentage": 44.24, "elapsed_time": "2:07:06", "remaining_time": "2:40:13", "throughput": 1318.02, "total_tokens": 10051568} {"current_steps": 17700, "total_steps": 40000, "loss": 0.0, "lr": 2.9493450247621003e-05, "epoch": 310.53097345132744, "percentage": 44.25, "elapsed_time": "2:07:08", "remaining_time": "2:40:10", "throughput": 1318.05, "total_tokens": 10054544} {"current_steps": 17705, "total_steps": 40000, "loss": 0.0, "lr": 2.948379230672476e-05, "epoch": 310.6194690265487, "percentage": 44.26, "elapsed_time": "2:07:10", "remaining_time": "2:40:08", "throughput": 1318.03, "total_tokens": 10057088} {"current_steps": 17710, "total_steps": 40000, "loss": 0.0, "lr": 2.9474133674371396e-05, "epoch": 310.7079646017699, "percentage": 44.27, "elapsed_time": "2:07:12", "remaining_time": "2:40:06", "throughput": 1318.02, "total_tokens": 10059776} {"current_steps": 17715, "total_steps": 40000, "loss": 0.0, "lr": 2.9464474352050387e-05, "epoch": 310.79646017699116, "percentage": 44.29, "elapsed_time": "2:07:14", "remaining_time": "2:40:04", "throughput": 1318.03, "total_tokens": 10062576} {"current_steps": 17720, "total_steps": 40000, "loss": 0.0, "lr": 2.9454814341251336e-05, "epoch": 310.88495575221236, "percentage": 44.3, "elapsed_time": "2:07:16", "remaining_time": "2:40:01", "throughput": 1318.08, "total_tokens": 10065632} {"current_steps": 17725, "total_steps": 40000, "loss": 0.0, "lr": 2.9445153643463942e-05, "epoch": 310.9734513274336, "percentage": 44.31, "elapsed_time": "2:07:18", "remaining_time": "2:39:59", "throughput": 1318.07, "total_tokens": 10068256} {"current_steps": 17730, "total_steps": 40000, "loss": 0.0, "lr": 2.943549226017798e-05, "epoch": 311.05309734513276, "percentage": 44.32, "elapsed_time": "2:07:20", "remaining_time": "2:39:57", "throughput": 1317.96, "total_tokens": 10070480} {"current_steps": 17735, "total_steps": 40000, "loss": 0.0, "lr": 2.942583019288337e-05, "epoch": 311.14159292035396, "percentage": 44.34, "elapsed_time": "2:07:23", "remaining_time": "2:39:55", "throughput": 1317.96, "total_tokens": 10073136} {"current_steps": 17740, "total_steps": 40000, "loss": 0.0, "lr": 2.9416167443070132e-05, "epoch": 311.2300884955752, "percentage": 44.35, "elapsed_time": "2:07:25", "remaining_time": "2:39:52", "throughput": 1317.99, "total_tokens": 10076160} {"current_steps": 17745, "total_steps": 40000, "loss": 0.0, "lr": 2.9406504012228375e-05, "epoch": 311.3185840707965, "percentage": 44.36, "elapsed_time": "2:07:27", "remaining_time": "2:39:50", "throughput": 1318.05, "total_tokens": 10079312} {"current_steps": 17750, "total_steps": 40000, "loss": 0.0, "lr": 2.939683990184832e-05, "epoch": 311.4070796460177, "percentage": 44.38, "elapsed_time": "2:07:29", "remaining_time": "2:39:48", "throughput": 1318.07, "total_tokens": 10082208} {"current_steps": 17755, "total_steps": 40000, "loss": 0.0, "lr": 2.93871751134203e-05, "epoch": 311.49557522123894, "percentage": 44.39, "elapsed_time": "2:07:31", "remaining_time": "2:39:46", "throughput": 1318.12, "total_tokens": 10085312} {"current_steps": 17760, "total_steps": 40000, "loss": 0.0, "lr": 2.9377509648434752e-05, "epoch": 311.5840707964602, "percentage": 44.4, "elapsed_time": "2:07:33", "remaining_time": "2:39:43", "throughput": 1318.16, "total_tokens": 10088352} {"current_steps": 17765, "total_steps": 40000, "loss": 0.0, "lr": 2.9367843508382203e-05, "epoch": 311.6725663716814, "percentage": 44.41, "elapsed_time": "2:07:35", "remaining_time": "2:39:41", "throughput": 1318.17, "total_tokens": 10091216} {"current_steps": 17770, "total_steps": 40000, "loss": 0.0, "lr": 2.9358176694753293e-05, "epoch": 311.76106194690266, "percentage": 44.42, "elapsed_time": "2:07:37", "remaining_time": "2:39:39", "throughput": 1318.15, "total_tokens": 10093760} {"current_steps": 17775, "total_steps": 40000, "loss": 0.0, "lr": 2.9348509209038766e-05, "epoch": 311.8495575221239, "percentage": 44.44, "elapsed_time": "2:07:39", "remaining_time": "2:39:37", "throughput": 1318.23, "total_tokens": 10097136} {"current_steps": 17780, "total_steps": 40000, "loss": 0.0, "lr": 2.933884105272947e-05, "epoch": 311.9380530973451, "percentage": 44.45, "elapsed_time": "2:07:41", "remaining_time": "2:39:34", "throughput": 1318.25, "total_tokens": 10099984} {"current_steps": 17785, "total_steps": 40000, "loss": 0.0, "lr": 2.9329172227316366e-05, "epoch": 312.01769911504425, "percentage": 44.46, "elapsed_time": "2:07:43", "remaining_time": "2:39:32", "throughput": 1318.16, "total_tokens": 10102272} {"current_steps": 17790, "total_steps": 40000, "loss": 0.0, "lr": 2.93195027342905e-05, "epoch": 312.1061946902655, "percentage": 44.47, "elapsed_time": "2:07:45", "remaining_time": "2:39:30", "throughput": 1318.13, "total_tokens": 10104768} {"current_steps": 17795, "total_steps": 40000, "loss": 0.0, "lr": 2.9309832575143024e-05, "epoch": 312.1946902654867, "percentage": 44.49, "elapsed_time": "2:07:48", "remaining_time": "2:39:28", "throughput": 1318.24, "total_tokens": 10108304} {"current_steps": 17800, "total_steps": 40000, "loss": 0.0, "lr": 2.930016175136521e-05, "epoch": 312.283185840708, "percentage": 44.5, "elapsed_time": "2:07:50", "remaining_time": "2:39:26", "throughput": 1318.29, "total_tokens": 10111472} {"current_steps": 17800, "total_steps": 40000, "eval_loss": 0.5531618595123291, "epoch": 312.283185840708, "percentage": 44.5, "elapsed_time": "2:07:51", "remaining_time": "2:39:27", "throughput": 1318.11, "total_tokens": 10111472} {"current_steps": 17805, "total_steps": 40000, "loss": 0.0, "lr": 2.9290490264448412e-05, "epoch": 312.37168141592923, "percentage": 44.51, "elapsed_time": "2:07:55", "remaining_time": "2:39:27", "throughput": 1317.76, "total_tokens": 10113968} {"current_steps": 17810, "total_steps": 40000, "loss": 0.0, "lr": 2.9280818115884094e-05, "epoch": 312.46017699115043, "percentage": 44.52, "elapsed_time": "2:07:57", "remaining_time": "2:39:25", "throughput": 1317.74, "total_tokens": 10116528} {"current_steps": 17815, "total_steps": 40000, "loss": 0.0, "lr": 2.9271145307163828e-05, "epoch": 312.5486725663717, "percentage": 44.54, "elapsed_time": "2:07:59", "remaining_time": "2:39:22", "throughput": 1317.77, "total_tokens": 10119520} {"current_steps": 17820, "total_steps": 40000, "loss": 0.0, "lr": 2.9261471839779287e-05, "epoch": 312.6371681415929, "percentage": 44.55, "elapsed_time": "2:08:01", "remaining_time": "2:39:20", "throughput": 1317.82, "total_tokens": 10122592} {"current_steps": 17825, "total_steps": 40000, "loss": 0.0, "lr": 2.925179771522223e-05, "epoch": 312.72566371681415, "percentage": 44.56, "elapsed_time": "2:08:03", "remaining_time": "2:39:18", "throughput": 1317.82, "total_tokens": 10125376} {"current_steps": 17830, "total_steps": 40000, "loss": 0.0, "lr": 2.9242122934984535e-05, "epoch": 312.8141592920354, "percentage": 44.57, "elapsed_time": "2:08:05", "remaining_time": "2:39:16", "throughput": 1317.8, "total_tokens": 10127920} {"current_steps": 17835, "total_steps": 40000, "loss": 0.0, "lr": 2.9232447500558176e-05, "epoch": 312.9026548672566, "percentage": 44.59, "elapsed_time": "2:08:07", "remaining_time": "2:39:13", "throughput": 1317.86, "total_tokens": 10131136} {"current_steps": 17840, "total_steps": 40000, "loss": 0.0, "lr": 2.9222771413435225e-05, "epoch": 312.9911504424779, "percentage": 44.6, "elapsed_time": "2:08:09", "remaining_time": "2:39:11", "throughput": 1317.84, "total_tokens": 10133664} {"current_steps": 17845, "total_steps": 40000, "loss": 0.0, "lr": 2.9213094675107848e-05, "epoch": 313.070796460177, "percentage": 44.61, "elapsed_time": "2:08:11", "remaining_time": "2:39:09", "throughput": 1317.76, "total_tokens": 10136024} {"current_steps": 17850, "total_steps": 40000, "loss": 0.0, "lr": 2.9203417287068335e-05, "epoch": 313.1592920353982, "percentage": 44.62, "elapsed_time": "2:08:13", "remaining_time": "2:39:07", "throughput": 1317.8, "total_tokens": 10139064} {"current_steps": 17855, "total_steps": 40000, "loss": 0.0, "lr": 2.9193739250809042e-05, "epoch": 313.24778761061947, "percentage": 44.64, "elapsed_time": "2:08:16", "remaining_time": "2:39:05", "throughput": 1317.82, "total_tokens": 10141944} {"current_steps": 17860, "total_steps": 40000, "loss": 0.0, "lr": 2.9184060567822463e-05, "epoch": 313.3362831858407, "percentage": 44.65, "elapsed_time": "2:08:18", "remaining_time": "2:39:02", "throughput": 1317.78, "total_tokens": 10144392} {"current_steps": 17865, "total_steps": 40000, "loss": 0.0, "lr": 2.9174381239601166e-05, "epoch": 313.42477876106193, "percentage": 44.66, "elapsed_time": "2:08:20", "remaining_time": "2:39:00", "throughput": 1317.74, "total_tokens": 10146840} {"current_steps": 17870, "total_steps": 40000, "loss": 0.0, "lr": 2.916470126763783e-05, "epoch": 313.5132743362832, "percentage": 44.67, "elapsed_time": "2:08:22", "remaining_time": "2:38:58", "throughput": 1317.81, "total_tokens": 10150104} {"current_steps": 17875, "total_steps": 40000, "loss": 0.0, "lr": 2.9155020653425203e-05, "epoch": 313.60176991150445, "percentage": 44.69, "elapsed_time": "2:08:24", "remaining_time": "2:38:56", "throughput": 1317.82, "total_tokens": 10152888} {"current_steps": 17880, "total_steps": 40000, "loss": 0.0, "lr": 2.9145339398456184e-05, "epoch": 313.69026548672565, "percentage": 44.7, "elapsed_time": "2:08:26", "remaining_time": "2:38:53", "throughput": 1317.77, "total_tokens": 10155192} {"current_steps": 17885, "total_steps": 40000, "loss": 0.0, "lr": 2.913565750422374e-05, "epoch": 313.7787610619469, "percentage": 44.71, "elapsed_time": "2:08:28", "remaining_time": "2:38:51", "throughput": 1317.77, "total_tokens": 10157976} {"current_steps": 17890, "total_steps": 40000, "loss": 0.0, "lr": 2.9125974972220938e-05, "epoch": 313.86725663716817, "percentage": 44.73, "elapsed_time": "2:08:30", "remaining_time": "2:38:49", "throughput": 1317.83, "total_tokens": 10161144} {"current_steps": 17895, "total_steps": 40000, "loss": 0.0, "lr": 2.9116291803940932e-05, "epoch": 313.95575221238937, "percentage": 44.74, "elapsed_time": "2:08:32", "remaining_time": "2:38:47", "throughput": 1317.89, "total_tokens": 10164328} {"current_steps": 17900, "total_steps": 40000, "loss": 0.0, "lr": 2.910660800087701e-05, "epoch": 314.0353982300885, "percentage": 44.75, "elapsed_time": "2:08:34", "remaining_time": "2:38:45", "throughput": 1317.87, "total_tokens": 10167128} {"current_steps": 17905, "total_steps": 40000, "loss": 0.0, "lr": 2.909692356452254e-05, "epoch": 314.12389380530976, "percentage": 44.76, "elapsed_time": "2:08:36", "remaining_time": "2:38:42", "throughput": 1317.86, "total_tokens": 10169848} {"current_steps": 17910, "total_steps": 40000, "loss": 0.0, "lr": 2.9087238496370962e-05, "epoch": 314.21238938053096, "percentage": 44.77, "elapsed_time": "2:08:38", "remaining_time": "2:38:40", "throughput": 1317.91, "total_tokens": 10172920} {"current_steps": 17915, "total_steps": 40000, "loss": 0.0, "lr": 2.907755279791583e-05, "epoch": 314.3008849557522, "percentage": 44.79, "elapsed_time": "2:08:41", "remaining_time": "2:38:38", "throughput": 1317.9, "total_tokens": 10175576} {"current_steps": 17920, "total_steps": 40000, "loss": 0.0, "lr": 2.906786647065083e-05, "epoch": 314.3893805309734, "percentage": 44.8, "elapsed_time": "2:08:43", "remaining_time": "2:38:35", "throughput": 1317.87, "total_tokens": 10178056} {"current_steps": 17925, "total_steps": 40000, "loss": 0.0, "lr": 2.9058179516069695e-05, "epoch": 314.4778761061947, "percentage": 44.81, "elapsed_time": "2:08:45", "remaining_time": "2:38:33", "throughput": 1317.97, "total_tokens": 10181608} {"current_steps": 17930, "total_steps": 40000, "loss": 0.0, "lr": 2.9048491935666282e-05, "epoch": 314.56637168141594, "percentage": 44.82, "elapsed_time": "2:08:47", "remaining_time": "2:38:31", "throughput": 1318.03, "total_tokens": 10184792} {"current_steps": 17935, "total_steps": 40000, "loss": 0.0, "lr": 2.9038803730934534e-05, "epoch": 314.65486725663715, "percentage": 44.84, "elapsed_time": "2:08:49", "remaining_time": "2:38:29", "throughput": 1318.04, "total_tokens": 10187576} {"current_steps": 17940, "total_steps": 40000, "loss": 0.0, "lr": 2.9029114903368503e-05, "epoch": 314.7433628318584, "percentage": 44.85, "elapsed_time": "2:08:51", "remaining_time": "2:38:26", "throughput": 1317.99, "total_tokens": 10189928} {"current_steps": 17945, "total_steps": 40000, "loss": 0.0, "lr": 2.9019425454462318e-05, "epoch": 314.83185840707966, "percentage": 44.86, "elapsed_time": "2:08:53", "remaining_time": "2:38:24", "throughput": 1317.99, "total_tokens": 10192616} {"current_steps": 17950, "total_steps": 40000, "loss": 0.0, "lr": 2.9009735385710212e-05, "epoch": 314.92035398230087, "percentage": 44.88, "elapsed_time": "2:08:55", "remaining_time": "2:38:22", "throughput": 1317.97, "total_tokens": 10195192} {"current_steps": 17955, "total_steps": 40000, "loss": 0.0, "lr": 2.900004469860652e-05, "epoch": 315.0, "percentage": 44.89, "elapsed_time": "2:08:57", "remaining_time": "2:38:20", "throughput": 1317.96, "total_tokens": 10197744} {"current_steps": 17960, "total_steps": 40000, "loss": 0.0, "lr": 2.8990353394645668e-05, "epoch": 315.08849557522126, "percentage": 44.9, "elapsed_time": "2:08:59", "remaining_time": "2:38:18", "throughput": 1317.95, "total_tokens": 10200736} {"current_steps": 17965, "total_steps": 40000, "loss": 0.0, "lr": 2.8980661475322186e-05, "epoch": 315.17699115044246, "percentage": 44.91, "elapsed_time": "2:09:01", "remaining_time": "2:38:15", "throughput": 1318.01, "total_tokens": 10203952} {"current_steps": 17970, "total_steps": 40000, "loss": 0.0, "lr": 2.897096894213067e-05, "epoch": 315.2654867256637, "percentage": 44.92, "elapsed_time": "2:09:04", "remaining_time": "2:38:13", "throughput": 1318.04, "total_tokens": 10206896} {"current_steps": 17975, "total_steps": 40000, "loss": 0.0, "lr": 2.8961275796565845e-05, "epoch": 315.353982300885, "percentage": 44.94, "elapsed_time": "2:09:06", "remaining_time": "2:38:11", "throughput": 1318.09, "total_tokens": 10210000} {"current_steps": 17980, "total_steps": 40000, "loss": 0.0, "lr": 2.8951582040122517e-05, "epoch": 315.4424778761062, "percentage": 44.95, "elapsed_time": "2:09:08", "remaining_time": "2:38:09", "throughput": 1318.08, "total_tokens": 10212704} {"current_steps": 17985, "total_steps": 40000, "loss": 0.0, "lr": 2.894188767429557e-05, "epoch": 315.53097345132744, "percentage": 44.96, "elapsed_time": "2:09:10", "remaining_time": "2:38:06", "throughput": 1318.05, "total_tokens": 10215136} {"current_steps": 17990, "total_steps": 40000, "loss": 0.0, "lr": 2.8932192700580014e-05, "epoch": 315.6194690265487, "percentage": 44.98, "elapsed_time": "2:09:12", "remaining_time": "2:38:04", "throughput": 1318.08, "total_tokens": 10218080} {"current_steps": 17995, "total_steps": 40000, "loss": 0.0, "lr": 2.8922497120470916e-05, "epoch": 315.7079646017699, "percentage": 44.99, "elapsed_time": "2:09:14", "remaining_time": "2:38:02", "throughput": 1318.07, "total_tokens": 10220752} {"current_steps": 18000, "total_steps": 40000, "loss": 0.0, "lr": 2.891280093546348e-05, "epoch": 315.79646017699116, "percentage": 45.0, "elapsed_time": "2:09:16", "remaining_time": "2:38:00", "throughput": 1318.09, "total_tokens": 10223648} {"current_steps": 18000, "total_steps": 40000, "eval_loss": 0.5568270087242126, "epoch": 315.79646017699116, "percentage": 45.0, "elapsed_time": "2:09:17", "remaining_time": "2:38:01", "throughput": 1317.9, "total_tokens": 10223648} {"current_steps": 18005, "total_steps": 40000, "loss": 0.0, "lr": 2.890310414705297e-05, "epoch": 315.88495575221236, "percentage": 45.01, "elapsed_time": "2:09:21", "remaining_time": "2:38:01", "throughput": 1317.57, "total_tokens": 10226400} {"current_steps": 18010, "total_steps": 40000, "loss": 0.0, "lr": 2.8893406756734742e-05, "epoch": 315.9734513274336, "percentage": 45.02, "elapsed_time": "2:09:23", "remaining_time": "2:37:59", "throughput": 1317.62, "total_tokens": 10229536} {"current_steps": 18015, "total_steps": 40000, "loss": 0.0, "lr": 2.888370876600427e-05, "epoch": 316.05309734513276, "percentage": 45.04, "elapsed_time": "2:09:25", "remaining_time": "2:37:57", "throughput": 1317.51, "total_tokens": 10231656} {"current_steps": 18020, "total_steps": 40000, "loss": 0.0, "lr": 2.8874010176357104e-05, "epoch": 316.14159292035396, "percentage": 45.05, "elapsed_time": "2:09:27", "remaining_time": "2:37:55", "throughput": 1317.49, "total_tokens": 10234248} {"current_steps": 18025, "total_steps": 40000, "loss": 0.0, "lr": 2.886431098928888e-05, "epoch": 316.2300884955752, "percentage": 45.06, "elapsed_time": "2:09:30", "remaining_time": "2:37:52", "throughput": 1317.47, "total_tokens": 10236808} {"current_steps": 18030, "total_steps": 40000, "loss": 0.0, "lr": 2.885461120629534e-05, "epoch": 316.3185840707965, "percentage": 45.07, "elapsed_time": "2:09:32", "remaining_time": "2:37:50", "throughput": 1317.46, "total_tokens": 10239496} {"current_steps": 18035, "total_steps": 40000, "loss": 0.0, "lr": 2.8844910828872317e-05, "epoch": 316.4070796460177, "percentage": 45.09, "elapsed_time": "2:09:34", "remaining_time": "2:37:48", "throughput": 1317.49, "total_tokens": 10242392} {"current_steps": 18040, "total_steps": 40000, "loss": 0.0, "lr": 2.8835209858515715e-05, "epoch": 316.49557522123894, "percentage": 45.1, "elapsed_time": "2:09:36", "remaining_time": "2:37:45", "throughput": 1317.51, "total_tokens": 10245304} {"current_steps": 18045, "total_steps": 40000, "loss": 0.0, "lr": 2.8825508296721566e-05, "epoch": 316.5840707964602, "percentage": 45.11, "elapsed_time": "2:09:38", "remaining_time": "2:37:43", "throughput": 1317.52, "total_tokens": 10248088} {"current_steps": 18050, "total_steps": 40000, "loss": 0.0, "lr": 2.881580614498596e-05, "epoch": 316.6725663716814, "percentage": 45.12, "elapsed_time": "2:09:40", "remaining_time": "2:37:41", "throughput": 1317.6, "total_tokens": 10251464} {"current_steps": 18055, "total_steps": 40000, "loss": 0.0, "lr": 2.8806103404805103e-05, "epoch": 316.76106194690266, "percentage": 45.14, "elapsed_time": "2:09:42", "remaining_time": "2:37:39", "throughput": 1317.63, "total_tokens": 10254424} {"current_steps": 18060, "total_steps": 40000, "loss": 0.0, "lr": 2.8796400077675257e-05, "epoch": 316.8495575221239, "percentage": 45.15, "elapsed_time": "2:09:44", "remaining_time": "2:37:36", "throughput": 1317.73, "total_tokens": 10257896} {"current_steps": 18065, "total_steps": 40000, "loss": 0.0, "lr": 2.8786696165092812e-05, "epoch": 316.9380530973451, "percentage": 45.16, "elapsed_time": "2:09:46", "remaining_time": "2:37:34", "throughput": 1317.7, "total_tokens": 10260424} {"current_steps": 18070, "total_steps": 40000, "loss": 0.0, "lr": 2.8776991668554236e-05, "epoch": 317.01769911504425, "percentage": 45.17, "elapsed_time": "2:09:48", "remaining_time": "2:37:32", "throughput": 1317.67, "total_tokens": 10263120} {"current_steps": 18075, "total_steps": 40000, "loss": 0.0, "lr": 2.876728658955608e-05, "epoch": 317.1061946902655, "percentage": 45.19, "elapsed_time": "2:09:50", "remaining_time": "2:37:30", "throughput": 1317.63, "total_tokens": 10265568} {"current_steps": 18080, "total_steps": 40000, "loss": 0.0, "lr": 2.8757580929594986e-05, "epoch": 317.1946902654867, "percentage": 45.2, "elapsed_time": "2:09:52", "remaining_time": "2:37:28", "throughput": 1317.62, "total_tokens": 10268208} {"current_steps": 18085, "total_steps": 40000, "loss": 0.0, "lr": 2.87478746901677e-05, "epoch": 317.283185840708, "percentage": 45.21, "elapsed_time": "2:09:55", "remaining_time": "2:37:25", "throughput": 1317.68, "total_tokens": 10271376} {"current_steps": 18090, "total_steps": 40000, "loss": 0.0, "lr": 2.873816787277103e-05, "epoch": 317.37168141592923, "percentage": 45.23, "elapsed_time": "2:09:57", "remaining_time": "2:37:23", "throughput": 1317.69, "total_tokens": 10274176} {"current_steps": 18095, "total_steps": 40000, "loss": 0.0, "lr": 2.8728460478901903e-05, "epoch": 317.46017699115043, "percentage": 45.24, "elapsed_time": "2:09:59", "remaining_time": "2:37:21", "throughput": 1317.73, "total_tokens": 10277264} {"current_steps": 18100, "total_steps": 40000, "loss": 0.0, "lr": 2.8718752510057307e-05, "epoch": 317.5486725663717, "percentage": 45.25, "elapsed_time": "2:10:01", "remaining_time": "2:37:19", "throughput": 1317.7, "total_tokens": 10279744} {"current_steps": 18105, "total_steps": 40000, "loss": 0.0, "lr": 2.870904396773435e-05, "epoch": 317.6371681415929, "percentage": 45.26, "elapsed_time": "2:10:03", "remaining_time": "2:37:16", "throughput": 1317.77, "total_tokens": 10283040} {"current_steps": 18110, "total_steps": 40000, "loss": 0.0, "lr": 2.86993348534302e-05, "epoch": 317.72566371681415, "percentage": 45.27, "elapsed_time": "2:10:05", "remaining_time": "2:37:14", "throughput": 1317.74, "total_tokens": 10285536} {"current_steps": 18115, "total_steps": 40000, "loss": 0.0, "lr": 2.868962516864212e-05, "epoch": 317.8141592920354, "percentage": 45.29, "elapsed_time": "2:10:07", "remaining_time": "2:37:12", "throughput": 1317.79, "total_tokens": 10288672} {"current_steps": 18120, "total_steps": 40000, "loss": 0.0, "lr": 2.8679914914867477e-05, "epoch": 317.9026548672566, "percentage": 45.3, "elapsed_time": "2:10:09", "remaining_time": "2:37:10", "throughput": 1317.8, "total_tokens": 10291456} {"current_steps": 18125, "total_steps": 40000, "loss": 0.0, "lr": 2.8670204093603713e-05, "epoch": 317.9911504424779, "percentage": 45.31, "elapsed_time": "2:10:11", "remaining_time": "2:37:07", "throughput": 1317.84, "total_tokens": 10294480} {"current_steps": 18130, "total_steps": 40000, "loss": 0.0, "lr": 2.8660492706348357e-05, "epoch": 318.070796460177, "percentage": 45.32, "elapsed_time": "2:10:13", "remaining_time": "2:37:05", "throughput": 1317.74, "total_tokens": 10296688} {"current_steps": 18135, "total_steps": 40000, "loss": 0.0, "lr": 2.8650780754599022e-05, "epoch": 318.1592920353982, "percentage": 45.34, "elapsed_time": "2:10:15", "remaining_time": "2:37:03", "throughput": 1317.76, "total_tokens": 10299552} {"current_steps": 18140, "total_steps": 40000, "loss": 0.0, "lr": 2.8641068239853407e-05, "epoch": 318.24778761061947, "percentage": 45.35, "elapsed_time": "2:10:18", "remaining_time": "2:37:01", "throughput": 1317.75, "total_tokens": 10302240} {"current_steps": 18145, "total_steps": 40000, "loss": 0.0, "lr": 2.863135516360932e-05, "epoch": 318.3362831858407, "percentage": 45.36, "elapsed_time": "2:10:20", "remaining_time": "2:36:59", "throughput": 1317.78, "total_tokens": 10305200} {"current_steps": 18150, "total_steps": 40000, "loss": 0.0, "lr": 2.8621641527364633e-05, "epoch": 318.42477876106193, "percentage": 45.38, "elapsed_time": "2:10:22", "remaining_time": "2:36:56", "throughput": 1317.88, "total_tokens": 10308688} {"current_steps": 18155, "total_steps": 40000, "loss": 0.0, "lr": 2.8611927332617313e-05, "epoch": 318.5132743362832, "percentage": 45.39, "elapsed_time": "2:10:24", "remaining_time": "2:36:54", "throughput": 1317.87, "total_tokens": 10311328} {"current_steps": 18160, "total_steps": 40000, "loss": 0.0, "lr": 2.8602212580865405e-05, "epoch": 318.60176991150445, "percentage": 45.4, "elapsed_time": "2:10:26", "remaining_time": "2:36:52", "throughput": 1317.86, "total_tokens": 10313952} {"current_steps": 18165, "total_steps": 40000, "loss": 0.0, "lr": 2.859249727360705e-05, "epoch": 318.69026548672565, "percentage": 45.41, "elapsed_time": "2:10:28", "remaining_time": "2:36:50", "throughput": 1317.85, "total_tokens": 10316656} {"current_steps": 18170, "total_steps": 40000, "loss": 0.0, "lr": 2.8582781412340465e-05, "epoch": 318.7787610619469, "percentage": 45.42, "elapsed_time": "2:10:30", "remaining_time": "2:36:47", "throughput": 1317.91, "total_tokens": 10319808} {"current_steps": 18175, "total_steps": 40000, "loss": 0.0, "lr": 2.857306499856397e-05, "epoch": 318.86725663716817, "percentage": 45.44, "elapsed_time": "2:10:32", "remaining_time": "2:36:45", "throughput": 1317.88, "total_tokens": 10322336} {"current_steps": 18180, "total_steps": 40000, "loss": 0.0, "lr": 2.856334803377594e-05, "epoch": 318.95575221238937, "percentage": 45.45, "elapsed_time": "2:10:34", "remaining_time": "2:36:43", "throughput": 1317.91, "total_tokens": 10325248} {"current_steps": 18185, "total_steps": 40000, "loss": 0.0, "lr": 2.8553630519474867e-05, "epoch": 319.0353982300885, "percentage": 45.46, "elapsed_time": "2:10:36", "remaining_time": "2:36:41", "throughput": 1317.88, "total_tokens": 10327968} {"current_steps": 18190, "total_steps": 40000, "loss": 0.0, "lr": 2.8543912457159317e-05, "epoch": 319.12389380530976, "percentage": 45.48, "elapsed_time": "2:10:38", "remaining_time": "2:36:38", "throughput": 1317.89, "total_tokens": 10330800} {"current_steps": 18195, "total_steps": 40000, "loss": 0.0, "lr": 2.853419384832792e-05, "epoch": 319.21238938053096, "percentage": 45.49, "elapsed_time": "2:10:40", "remaining_time": "2:36:36", "throughput": 1317.87, "total_tokens": 10333424} {"current_steps": 18200, "total_steps": 40000, "loss": 0.0, "lr": 2.8524474694479423e-05, "epoch": 319.3008849557522, "percentage": 45.5, "elapsed_time": "2:10:43", "remaining_time": "2:36:34", "throughput": 1317.96, "total_tokens": 10336864} {"current_steps": 18200, "total_steps": 40000, "eval_loss": 0.5882929563522339, "epoch": 319.3008849557522, "percentage": 45.5, "elapsed_time": "2:10:44", "remaining_time": "2:36:35", "throughput": 1317.79, "total_tokens": 10336864} {"current_steps": 18205, "total_steps": 40000, "loss": 0.0, "lr": 2.851475499711264e-05, "epoch": 319.3893805309734, "percentage": 45.51, "elapsed_time": "2:10:48", "remaining_time": "2:36:36", "throughput": 1317.43, "total_tokens": 10339680} {"current_steps": 18210, "total_steps": 40000, "loss": 0.0, "lr": 2.8505034757726468e-05, "epoch": 319.4778761061947, "percentage": 45.52, "elapsed_time": "2:10:50", "remaining_time": "2:36:33", "throughput": 1317.41, "total_tokens": 10342224} {"current_steps": 18215, "total_steps": 40000, "loss": 0.0, "lr": 2.8495313977819886e-05, "epoch": 319.56637168141594, "percentage": 45.54, "elapsed_time": "2:10:52", "remaining_time": "2:36:31", "throughput": 1317.39, "total_tokens": 10344816} {"current_steps": 18220, "total_steps": 40000, "loss": 0.0, "lr": 2.8485592658891956e-05, "epoch": 319.65486725663715, "percentage": 45.55, "elapsed_time": "2:10:54", "remaining_time": "2:36:29", "throughput": 1317.38, "total_tokens": 10347456} {"current_steps": 18225, "total_steps": 40000, "loss": 0.0, "lr": 2.8475870802441844e-05, "epoch": 319.7433628318584, "percentage": 45.56, "elapsed_time": "2:10:56", "remaining_time": "2:36:27", "throughput": 1317.43, "total_tokens": 10350592} {"current_steps": 18230, "total_steps": 40000, "loss": 0.0, "lr": 2.8466148409968774e-05, "epoch": 319.83185840707966, "percentage": 45.57, "elapsed_time": "2:10:58", "remaining_time": "2:36:24", "throughput": 1317.45, "total_tokens": 10353440} {"current_steps": 18235, "total_steps": 40000, "loss": 0.0, "lr": 2.8456425482972067e-05, "epoch": 319.92035398230087, "percentage": 45.59, "elapsed_time": "2:11:00", "remaining_time": "2:36:22", "throughput": 1317.55, "total_tokens": 10356976} {"current_steps": 18240, "total_steps": 40000, "loss": 0.0, "lr": 2.84467020229511e-05, "epoch": 320.0, "percentage": 45.6, "elapsed_time": "2:11:02", "remaining_time": "2:36:20", "throughput": 1317.52, "total_tokens": 10359368} {"current_steps": 18245, "total_steps": 40000, "loss": 0.0, "lr": 2.8436978031405375e-05, "epoch": 320.08849557522126, "percentage": 45.61, "elapsed_time": "2:11:05", "remaining_time": "2:36:18", "throughput": 1317.53, "total_tokens": 10362504} {"current_steps": 18250, "total_steps": 40000, "loss": 0.0, "lr": 2.842725350983445e-05, "epoch": 320.17699115044246, "percentage": 45.62, "elapsed_time": "2:11:07", "remaining_time": "2:36:15", "throughput": 1317.49, "total_tokens": 10364920} {"current_steps": 18255, "total_steps": 40000, "loss": 0.0, "lr": 2.8417528459737957e-05, "epoch": 320.2654867256637, "percentage": 45.64, "elapsed_time": "2:11:09", "remaining_time": "2:36:13", "throughput": 1317.55, "total_tokens": 10368104} {"current_steps": 18260, "total_steps": 40000, "loss": 0.0, "lr": 2.8407802882615624e-05, "epoch": 320.353982300885, "percentage": 45.65, "elapsed_time": "2:11:11", "remaining_time": "2:36:11", "throughput": 1317.57, "total_tokens": 10370952} {"current_steps": 18265, "total_steps": 40000, "loss": 0.0, "lr": 2.8398076779967277e-05, "epoch": 320.4424778761062, "percentage": 45.66, "elapsed_time": "2:11:13", "remaining_time": "2:36:09", "throughput": 1317.54, "total_tokens": 10373432} {"current_steps": 18270, "total_steps": 40000, "loss": 0.0, "lr": 2.8388350153292774e-05, "epoch": 320.53097345132744, "percentage": 45.67, "elapsed_time": "2:11:15", "remaining_time": "2:36:06", "throughput": 1317.55, "total_tokens": 10376280} {"current_steps": 18275, "total_steps": 40000, "loss": 0.0, "lr": 2.8378623004092103e-05, "epoch": 320.6194690265487, "percentage": 45.69, "elapsed_time": "2:11:17", "remaining_time": "2:36:04", "throughput": 1317.53, "total_tokens": 10378824} {"current_steps": 18280, "total_steps": 40000, "loss": 0.0, "lr": 2.8368895333865302e-05, "epoch": 320.7079646017699, "percentage": 45.7, "elapsed_time": "2:11:19", "remaining_time": "2:36:02", "throughput": 1317.56, "total_tokens": 10381816} {"current_steps": 18285, "total_steps": 40000, "loss": 0.0, "lr": 2.835916714411251e-05, "epoch": 320.79646017699116, "percentage": 45.71, "elapsed_time": "2:11:21", "remaining_time": "2:36:00", "throughput": 1317.57, "total_tokens": 10384568} {"current_steps": 18290, "total_steps": 40000, "loss": 0.0, "lr": 2.8349438436333926e-05, "epoch": 320.88495575221236, "percentage": 45.73, "elapsed_time": "2:11:23", "remaining_time": "2:35:57", "throughput": 1317.59, "total_tokens": 10387528} {"current_steps": 18295, "total_steps": 40000, "loss": 0.0, "lr": 2.833970921202984e-05, "epoch": 320.9734513274336, "percentage": 45.74, "elapsed_time": "2:11:25", "remaining_time": "2:35:55", "throughput": 1317.61, "total_tokens": 10390376} {"current_steps": 18300, "total_steps": 40000, "loss": 0.0, "lr": 2.8329979472700628e-05, "epoch": 321.05309734513276, "percentage": 45.75, "elapsed_time": "2:11:28", "remaining_time": "2:35:53", "throughput": 1317.57, "total_tokens": 10393016} {"current_steps": 18305, "total_steps": 40000, "loss": 0.0, "lr": 2.832024921984674e-05, "epoch": 321.14159292035396, "percentage": 45.76, "elapsed_time": "2:11:30", "remaining_time": "2:35:51", "throughput": 1317.6, "total_tokens": 10396008} {"current_steps": 18310, "total_steps": 40000, "loss": 0.0, "lr": 2.8310518454968693e-05, "epoch": 321.2300884955752, "percentage": 45.77, "elapsed_time": "2:11:32", "remaining_time": "2:35:49", "throughput": 1317.64, "total_tokens": 10399080} {"current_steps": 18315, "total_steps": 40000, "loss": 0.0, "lr": 2.8300787179567095e-05, "epoch": 321.3185840707965, "percentage": 45.79, "elapsed_time": "2:11:34", "remaining_time": "2:35:46", "throughput": 1317.67, "total_tokens": 10402072} {"current_steps": 18320, "total_steps": 40000, "loss": 0.0, "lr": 2.8291055395142636e-05, "epoch": 321.4070796460177, "percentage": 45.8, "elapsed_time": "2:11:36", "remaining_time": "2:35:44", "throughput": 1317.7, "total_tokens": 10405032} {"current_steps": 18325, "total_steps": 40000, "loss": 0.0, "lr": 2.8281323103196073e-05, "epoch": 321.49557522123894, "percentage": 45.81, "elapsed_time": "2:11:38", "remaining_time": "2:35:42", "throughput": 1317.68, "total_tokens": 10407528} {"current_steps": 18330, "total_steps": 40000, "loss": 0.0, "lr": 2.8271590305228256e-05, "epoch": 321.5840707964602, "percentage": 45.82, "elapsed_time": "2:11:40", "remaining_time": "2:35:40", "throughput": 1317.67, "total_tokens": 10410184} {"current_steps": 18335, "total_steps": 40000, "loss": 0.0, "lr": 2.82618570027401e-05, "epoch": 321.6725663716814, "percentage": 45.84, "elapsed_time": "2:11:42", "remaining_time": "2:35:37", "throughput": 1317.72, "total_tokens": 10413288} {"current_steps": 18340, "total_steps": 40000, "loss": 0.0, "lr": 2.8252123197232604e-05, "epoch": 321.76106194690266, "percentage": 45.85, "elapsed_time": "2:11:44", "remaining_time": "2:35:35", "throughput": 1317.76, "total_tokens": 10416376} {"current_steps": 18345, "total_steps": 40000, "loss": 0.0, "lr": 2.8242388890206843e-05, "epoch": 321.8495575221239, "percentage": 45.86, "elapsed_time": "2:11:46", "remaining_time": "2:35:33", "throughput": 1317.83, "total_tokens": 10419656} {"current_steps": 18350, "total_steps": 40000, "loss": 0.0, "lr": 2.8232654083163967e-05, "epoch": 321.9380530973451, "percentage": 45.88, "elapsed_time": "2:11:48", "remaining_time": "2:35:30", "throughput": 1317.83, "total_tokens": 10422376} {"current_steps": 18355, "total_steps": 40000, "loss": 0.0, "lr": 2.822291877760521e-05, "epoch": 322.01769911504425, "percentage": 45.89, "elapsed_time": "2:11:50", "remaining_time": "2:35:28", "throughput": 1317.7, "total_tokens": 10424320} {"current_steps": 18360, "total_steps": 40000, "loss": 0.0, "lr": 2.8213182975031864e-05, "epoch": 322.1061946902655, "percentage": 45.9, "elapsed_time": "2:11:53", "remaining_time": "2:35:26", "throughput": 1317.74, "total_tokens": 10427376} {"current_steps": 18365, "total_steps": 40000, "loss": 0.0, "lr": 2.8203446676945337e-05, "epoch": 322.1946902654867, "percentage": 45.91, "elapsed_time": "2:11:55", "remaining_time": "2:35:24", "throughput": 1317.76, "total_tokens": 10430240} {"current_steps": 18370, "total_steps": 40000, "loss": 0.0, "lr": 2.8193709884847075e-05, "epoch": 322.283185840708, "percentage": 45.92, "elapsed_time": "2:11:57", "remaining_time": "2:35:22", "throughput": 1317.8, "total_tokens": 10433248} {"current_steps": 18375, "total_steps": 40000, "loss": 0.0, "lr": 2.8183972600238605e-05, "epoch": 322.37168141592923, "percentage": 45.94, "elapsed_time": "2:11:59", "remaining_time": "2:35:19", "throughput": 1317.85, "total_tokens": 10436400} {"current_steps": 18380, "total_steps": 40000, "loss": 0.0, "lr": 2.817423482462156e-05, "epoch": 322.46017699115043, "percentage": 45.95, "elapsed_time": "2:12:01", "remaining_time": "2:35:17", "throughput": 1317.91, "total_tokens": 10439600} {"current_steps": 18385, "total_steps": 40000, "loss": 0.0, "lr": 2.8164496559497605e-05, "epoch": 322.5486725663717, "percentage": 45.96, "elapsed_time": "2:12:03", "remaining_time": "2:35:15", "throughput": 1317.92, "total_tokens": 10442448} {"current_steps": 18390, "total_steps": 40000, "loss": 0.0, "lr": 2.815475780636852e-05, "epoch": 322.6371681415929, "percentage": 45.98, "elapsed_time": "2:12:05", "remaining_time": "2:35:13", "throughput": 1317.88, "total_tokens": 10444864} {"current_steps": 18395, "total_steps": 40000, "loss": 0.0, "lr": 2.814501856673613e-05, "epoch": 322.72566371681415, "percentage": 45.99, "elapsed_time": "2:12:07", "remaining_time": "2:35:10", "throughput": 1317.86, "total_tokens": 10447424} {"current_steps": 18400, "total_steps": 40000, "loss": 0.0, "lr": 2.8135278842102353e-05, "epoch": 322.8141592920354, "percentage": 46.0, "elapsed_time": "2:12:09", "remaining_time": "2:35:08", "throughput": 1317.93, "total_tokens": 10450688} {"current_steps": 18400, "total_steps": 40000, "eval_loss": 0.5702996850013733, "epoch": 322.8141592920354, "percentage": 46.0, "elapsed_time": "2:12:10", "remaining_time": "2:35:09", "throughput": 1317.75, "total_tokens": 10450688} {"current_steps": 18405, "total_steps": 40000, "loss": 0.0, "lr": 2.8125538633969183e-05, "epoch": 322.9026548672566, "percentage": 46.01, "elapsed_time": "2:12:14", "remaining_time": "2:35:10", "throughput": 1317.37, "total_tokens": 10453200} {"current_steps": 18410, "total_steps": 40000, "loss": 0.0, "lr": 2.8115797943838677e-05, "epoch": 322.9911504424779, "percentage": 46.02, "elapsed_time": "2:12:17", "remaining_time": "2:35:07", "throughput": 1317.38, "total_tokens": 10456016} {"current_steps": 18415, "total_steps": 40000, "loss": 0.0, "lr": 2.810605677321298e-05, "epoch": 323.070796460177, "percentage": 46.04, "elapsed_time": "2:12:19", "remaining_time": "2:35:05", "throughput": 1317.29, "total_tokens": 10458352} {"current_steps": 18420, "total_steps": 40000, "loss": 0.0, "lr": 2.809631512359428e-05, "epoch": 323.1592920353982, "percentage": 46.05, "elapsed_time": "2:12:21", "remaining_time": "2:35:04", "throughput": 1317.3, "total_tokens": 10461456} {"current_steps": 18425, "total_steps": 40000, "loss": 0.0, "lr": 2.8086572996484884e-05, "epoch": 323.24778761061947, "percentage": 46.06, "elapsed_time": "2:12:23", "remaining_time": "2:35:01", "throughput": 1317.31, "total_tokens": 10464256} {"current_steps": 18430, "total_steps": 40000, "loss": 0.0, "lr": 2.8076830393387143e-05, "epoch": 323.3362831858407, "percentage": 46.08, "elapsed_time": "2:12:25", "remaining_time": "2:34:59", "throughput": 1317.37, "total_tokens": 10467488} {"current_steps": 18435, "total_steps": 40000, "loss": 0.0, "lr": 2.8067087315803497e-05, "epoch": 323.42477876106193, "percentage": 46.09, "elapsed_time": "2:12:27", "remaining_time": "2:34:57", "throughput": 1317.36, "total_tokens": 10470112} {"current_steps": 18440, "total_steps": 40000, "loss": 0.0, "lr": 2.8057343765236433e-05, "epoch": 323.5132743362832, "percentage": 46.1, "elapsed_time": "2:12:29", "remaining_time": "2:34:55", "throughput": 1317.41, "total_tokens": 10473312} {"current_steps": 18445, "total_steps": 40000, "loss": 0.0, "lr": 2.804759974318854e-05, "epoch": 323.60176991150445, "percentage": 46.11, "elapsed_time": "2:12:31", "remaining_time": "2:34:52", "throughput": 1317.43, "total_tokens": 10476192} {"current_steps": 18450, "total_steps": 40000, "loss": 0.0, "lr": 2.8037855251162482e-05, "epoch": 323.69026548672565, "percentage": 46.12, "elapsed_time": "2:12:34", "remaining_time": "2:34:50", "throughput": 1317.44, "total_tokens": 10478960} {"current_steps": 18455, "total_steps": 40000, "loss": 0.0, "lr": 2.802811029066096e-05, "epoch": 323.7787610619469, "percentage": 46.14, "elapsed_time": "2:12:36", "remaining_time": "2:34:48", "throughput": 1317.47, "total_tokens": 10481904} {"current_steps": 18460, "total_steps": 40000, "loss": 0.0, "lr": 2.8018364863186764e-05, "epoch": 323.86725663716817, "percentage": 46.15, "elapsed_time": "2:12:38", "remaining_time": "2:34:45", "throughput": 1317.47, "total_tokens": 10484672} {"current_steps": 18465, "total_steps": 40000, "loss": 0.0, "lr": 2.800861897024279e-05, "epoch": 323.95575221238937, "percentage": 46.16, "elapsed_time": "2:12:40", "remaining_time": "2:34:43", "throughput": 1317.47, "total_tokens": 10487344} {"current_steps": 18470, "total_steps": 40000, "loss": 0.0, "lr": 2.799887261333196e-05, "epoch": 324.0353982300885, "percentage": 46.17, "elapsed_time": "2:12:42", "remaining_time": "2:34:41", "throughput": 1317.39, "total_tokens": 10489664} {"current_steps": 18475, "total_steps": 40000, "loss": 0.0, "lr": 2.798912579395728e-05, "epoch": 324.12389380530976, "percentage": 46.19, "elapsed_time": "2:12:44", "remaining_time": "2:34:39", "throughput": 1317.39, "total_tokens": 10492464} {"current_steps": 18480, "total_steps": 40000, "loss": 0.0, "lr": 2.797937851362185e-05, "epoch": 324.21238938053096, "percentage": 46.2, "elapsed_time": "2:12:46", "remaining_time": "2:34:37", "throughput": 1317.41, "total_tokens": 10495344} {"current_steps": 18485, "total_steps": 40000, "loss": 0.0, "lr": 2.7969630773828802e-05, "epoch": 324.3008849557522, "percentage": 46.21, "elapsed_time": "2:12:48", "remaining_time": "2:34:34", "throughput": 1317.4, "total_tokens": 10497984} {"current_steps": 18490, "total_steps": 40000, "loss": 0.0, "lr": 2.7959882576081382e-05, "epoch": 324.3893805309734, "percentage": 46.23, "elapsed_time": "2:12:50", "remaining_time": "2:34:32", "throughput": 1317.45, "total_tokens": 10501120} {"current_steps": 18495, "total_steps": 40000, "loss": 0.0, "lr": 2.795013392188286e-05, "epoch": 324.4778761061947, "percentage": 46.24, "elapsed_time": "2:12:52", "remaining_time": "2:34:30", "throughput": 1317.47, "total_tokens": 10503968} {"current_steps": 18500, "total_steps": 40000, "loss": 0.0, "lr": 2.7940384812736614e-05, "epoch": 324.56637168141594, "percentage": 46.25, "elapsed_time": "2:12:54", "remaining_time": "2:34:28", "throughput": 1317.49, "total_tokens": 10506880} {"current_steps": 18505, "total_steps": 40000, "loss": 0.0, "lr": 2.7930635250146087e-05, "epoch": 324.65486725663715, "percentage": 46.26, "elapsed_time": "2:12:56", "remaining_time": "2:34:25", "throughput": 1317.48, "total_tokens": 10509520} {"current_steps": 18510, "total_steps": 40000, "loss": 0.0, "lr": 2.792088523561477e-05, "epoch": 324.7433628318584, "percentage": 46.27, "elapsed_time": "2:12:59", "remaining_time": "2:34:23", "throughput": 1317.47, "total_tokens": 10512192} {"current_steps": 18515, "total_steps": 40000, "loss": 0.0, "lr": 2.7911134770646246e-05, "epoch": 324.83185840707966, "percentage": 46.29, "elapsed_time": "2:13:01", "remaining_time": "2:34:21", "throughput": 1317.44, "total_tokens": 10514640} {"current_steps": 18520, "total_steps": 40000, "loss": 0.0, "lr": 2.7901383856744157e-05, "epoch": 324.92035398230087, "percentage": 46.3, "elapsed_time": "2:13:03", "remaining_time": "2:34:19", "throughput": 1317.5, "total_tokens": 10517840} {"current_steps": 18525, "total_steps": 40000, "loss": 0.0, "lr": 2.7891632495412217e-05, "epoch": 325.0, "percentage": 46.31, "elapsed_time": "2:13:05", "remaining_time": "2:34:16", "throughput": 1317.5, "total_tokens": 10520464} {"current_steps": 18530, "total_steps": 40000, "loss": 0.0, "lr": 2.7881880688154205e-05, "epoch": 325.08849557522126, "percentage": 46.33, "elapsed_time": "2:13:07", "remaining_time": "2:34:14", "throughput": 1317.51, "total_tokens": 10523584} {"current_steps": 18535, "total_steps": 40000, "loss": 0.0, "lr": 2.7872128436473977e-05, "epoch": 325.17699115044246, "percentage": 46.34, "elapsed_time": "2:13:09", "remaining_time": "2:34:12", "throughput": 1317.48, "total_tokens": 10526144} {"current_steps": 18540, "total_steps": 40000, "loss": 0.0, "lr": 2.7862375741875448e-05, "epoch": 325.2654867256637, "percentage": 46.35, "elapsed_time": "2:13:11", "remaining_time": "2:34:10", "throughput": 1317.46, "total_tokens": 10528656} {"current_steps": 18545, "total_steps": 40000, "loss": 0.0, "lr": 2.785262260586261e-05, "epoch": 325.353982300885, "percentage": 46.36, "elapsed_time": "2:13:13", "remaining_time": "2:34:08", "throughput": 1317.51, "total_tokens": 10531824} {"current_steps": 18550, "total_steps": 40000, "loss": 0.0, "lr": 2.7842869029939517e-05, "epoch": 325.4424778761062, "percentage": 46.38, "elapsed_time": "2:13:15", "remaining_time": "2:34:05", "throughput": 1317.52, "total_tokens": 10534576} {"current_steps": 18555, "total_steps": 40000, "loss": 0.0, "lr": 2.7833115015610296e-05, "epoch": 325.53097345132744, "percentage": 46.39, "elapsed_time": "2:13:17", "remaining_time": "2:34:03", "throughput": 1317.54, "total_tokens": 10537520} {"current_steps": 18560, "total_steps": 40000, "loss": 0.0, "lr": 2.7823360564379136e-05, "epoch": 325.6194690265487, "percentage": 46.4, "elapsed_time": "2:13:19", "remaining_time": "2:34:01", "throughput": 1317.59, "total_tokens": 10540640} {"current_steps": 18565, "total_steps": 40000, "loss": 0.0, "lr": 2.7813605677750297e-05, "epoch": 325.7079646017699, "percentage": 46.41, "elapsed_time": "2:13:21", "remaining_time": "2:33:59", "throughput": 1317.65, "total_tokens": 10543808} {"current_steps": 18570, "total_steps": 40000, "loss": 0.0, "lr": 2.7803850357228102e-05, "epoch": 325.79646017699116, "percentage": 46.42, "elapsed_time": "2:13:24", "remaining_time": "2:33:56", "throughput": 1317.7, "total_tokens": 10546896} {"current_steps": 18575, "total_steps": 40000, "loss": 0.0, "lr": 2.779409460431695e-05, "epoch": 325.88495575221236, "percentage": 46.44, "elapsed_time": "2:13:26", "remaining_time": "2:33:54", "throughput": 1317.72, "total_tokens": 10549776} {"current_steps": 18580, "total_steps": 40000, "loss": 0.0, "lr": 2.778433842052129e-05, "epoch": 325.9734513274336, "percentage": 46.45, "elapsed_time": "2:13:28", "remaining_time": "2:33:52", "throughput": 1317.68, "total_tokens": 10552192} {"current_steps": 18585, "total_steps": 40000, "loss": 0.0, "lr": 2.7774581807345664e-05, "epoch": 326.05309734513276, "percentage": 46.46, "elapsed_time": "2:13:30", "remaining_time": "2:33:50", "throughput": 1317.58, "total_tokens": 10554360} {"current_steps": 18590, "total_steps": 40000, "loss": 0.0, "lr": 2.776482476629465e-05, "epoch": 326.14159292035396, "percentage": 46.48, "elapsed_time": "2:13:32", "remaining_time": "2:33:47", "throughput": 1317.59, "total_tokens": 10557224} {"current_steps": 18595, "total_steps": 40000, "loss": 0.0, "lr": 2.7755067298872924e-05, "epoch": 326.2300884955752, "percentage": 46.49, "elapsed_time": "2:13:34", "remaining_time": "2:33:45", "throughput": 1317.57, "total_tokens": 10559768} {"current_steps": 18600, "total_steps": 40000, "loss": 0.0, "lr": 2.774530940658518e-05, "epoch": 326.3185840707965, "percentage": 46.5, "elapsed_time": "2:13:36", "remaining_time": "2:33:43", "throughput": 1317.65, "total_tokens": 10563128} {"current_steps": 18600, "total_steps": 40000, "eval_loss": 0.566409170627594, "epoch": 326.3185840707965, "percentage": 46.5, "elapsed_time": "2:13:37", "remaining_time": "2:33:44", "throughput": 1317.47, "total_tokens": 10563128} {"current_steps": 18605, "total_steps": 40000, "loss": 0.0, "lr": 2.7735551090936236e-05, "epoch": 326.4070796460177, "percentage": 46.51, "elapsed_time": "2:13:41", "remaining_time": "2:33:44", "throughput": 1317.22, "total_tokens": 10566088} {"current_steps": 18610, "total_steps": 40000, "loss": 0.0, "lr": 2.7725792353430934e-05, "epoch": 326.49557522123894, "percentage": 46.52, "elapsed_time": "2:13:43", "remaining_time": "2:33:42", "throughput": 1317.24, "total_tokens": 10569016} {"current_steps": 18615, "total_steps": 40000, "loss": 0.0, "lr": 2.77160331955742e-05, "epoch": 326.5840707964602, "percentage": 46.54, "elapsed_time": "2:13:45", "remaining_time": "2:33:39", "throughput": 1317.27, "total_tokens": 10572008} {"current_steps": 18620, "total_steps": 40000, "loss": 0.0, "lr": 2.7706273618871008e-05, "epoch": 326.6725663716814, "percentage": 46.55, "elapsed_time": "2:13:47", "remaining_time": "2:33:37", "throughput": 1317.27, "total_tokens": 10574696} {"current_steps": 18625, "total_steps": 40000, "loss": 0.0, "lr": 2.769651362482642e-05, "epoch": 326.76106194690266, "percentage": 46.56, "elapsed_time": "2:13:49", "remaining_time": "2:33:35", "throughput": 1317.31, "total_tokens": 10577720} {"current_steps": 18630, "total_steps": 40000, "loss": 0.0, "lr": 2.768675321494555e-05, "epoch": 326.8495575221239, "percentage": 46.58, "elapsed_time": "2:13:51", "remaining_time": "2:33:33", "throughput": 1317.34, "total_tokens": 10580696} {"current_steps": 18635, "total_steps": 40000, "loss": 0.0, "lr": 2.7676992390733565e-05, "epoch": 326.9380530973451, "percentage": 46.59, "elapsed_time": "2:13:53", "remaining_time": "2:33:30", "throughput": 1317.31, "total_tokens": 10583208} {"current_steps": 18640, "total_steps": 40000, "loss": 0.0, "lr": 2.766723115369571e-05, "epoch": 327.01769911504425, "percentage": 46.6, "elapsed_time": "2:13:56", "remaining_time": "2:33:28", "throughput": 1317.29, "total_tokens": 10586016} {"current_steps": 18645, "total_steps": 40000, "loss": 0.0, "lr": 2.765746950533729e-05, "epoch": 327.1061946902655, "percentage": 46.61, "elapsed_time": "2:13:58", "remaining_time": "2:33:26", "throughput": 1317.3, "total_tokens": 10588768} {"current_steps": 18650, "total_steps": 40000, "loss": 0.0, "lr": 2.7647707447163684e-05, "epoch": 327.1946902654867, "percentage": 46.62, "elapsed_time": "2:14:00", "remaining_time": "2:33:24", "throughput": 1317.39, "total_tokens": 10592224} {"current_steps": 18655, "total_steps": 40000, "loss": 0.0, "lr": 2.7637944980680315e-05, "epoch": 327.283185840708, "percentage": 46.64, "elapsed_time": "2:14:02", "remaining_time": "2:33:22", "throughput": 1317.43, "total_tokens": 10595264} {"current_steps": 18660, "total_steps": 40000, "loss": 0.0, "lr": 2.762818210739268e-05, "epoch": 327.37168141592923, "percentage": 46.65, "elapsed_time": "2:14:04", "remaining_time": "2:33:19", "throughput": 1317.4, "total_tokens": 10597792} {"current_steps": 18665, "total_steps": 40000, "loss": 0.0, "lr": 2.7618418828806332e-05, "epoch": 327.46017699115043, "percentage": 46.66, "elapsed_time": "2:14:06", "remaining_time": "2:33:17", "throughput": 1317.42, "total_tokens": 10600688} {"current_steps": 18670, "total_steps": 40000, "loss": 0.0, "lr": 2.76086551464269e-05, "epoch": 327.5486725663717, "percentage": 46.67, "elapsed_time": "2:14:08", "remaining_time": "2:33:15", "throughput": 1317.44, "total_tokens": 10603504} {"current_steps": 18675, "total_steps": 40000, "loss": 0.0, "lr": 2.759889106176006e-05, "epoch": 327.6371681415929, "percentage": 46.69, "elapsed_time": "2:14:10", "remaining_time": "2:33:13", "throughput": 1317.42, "total_tokens": 10606112} {"current_steps": 18680, "total_steps": 40000, "loss": 0.0, "lr": 2.758912657631156e-05, "epoch": 327.72566371681415, "percentage": 46.7, "elapsed_time": "2:14:12", "remaining_time": "2:33:10", "throughput": 1317.46, "total_tokens": 10609136} {"current_steps": 18685, "total_steps": 40000, "loss": 0.0, "lr": 2.7579361691587198e-05, "epoch": 327.8141592920354, "percentage": 46.71, "elapsed_time": "2:14:14", "remaining_time": "2:33:08", "throughput": 1317.43, "total_tokens": 10611664} {"current_steps": 18690, "total_steps": 40000, "loss": 0.0, "lr": 2.756959640909285e-05, "epoch": 327.9026548672566, "percentage": 46.73, "elapsed_time": "2:14:16", "remaining_time": "2:33:06", "throughput": 1317.46, "total_tokens": 10614624} {"current_steps": 18695, "total_steps": 40000, "loss": 0.0, "lr": 2.7559830730334452e-05, "epoch": 327.9911504424779, "percentage": 46.74, "elapsed_time": "2:14:18", "remaining_time": "2:33:04", "throughput": 1317.55, "total_tokens": 10618032} {"current_steps": 18700, "total_steps": 40000, "loss": 0.0, "lr": 2.7550064656817988e-05, "epoch": 328.070796460177, "percentage": 46.75, "elapsed_time": "2:14:21", "remaining_time": "2:33:01", "throughput": 1317.42, "total_tokens": 10619992} {"current_steps": 18705, "total_steps": 40000, "loss": 0.0, "lr": 2.7540298190049503e-05, "epoch": 328.1592920353982, "percentage": 46.76, "elapsed_time": "2:14:23", "remaining_time": "2:32:59", "throughput": 1317.41, "total_tokens": 10622616} {"current_steps": 18710, "total_steps": 40000, "loss": 0.0, "lr": 2.7530531331535107e-05, "epoch": 328.24778761061947, "percentage": 46.77, "elapsed_time": "2:14:25", "remaining_time": "2:32:57", "throughput": 1317.44, "total_tokens": 10625608} {"current_steps": 18715, "total_steps": 40000, "loss": 0.0, "lr": 2.752076408278099e-05, "epoch": 328.3362831858407, "percentage": 46.79, "elapsed_time": "2:14:27", "remaining_time": "2:32:55", "throughput": 1317.55, "total_tokens": 10629160} {"current_steps": 18720, "total_steps": 40000, "loss": 0.0, "lr": 2.751099644529337e-05, "epoch": 328.42477876106193, "percentage": 46.8, "elapsed_time": "2:14:29", "remaining_time": "2:32:52", "throughput": 1317.57, "total_tokens": 10632072} {"current_steps": 18725, "total_steps": 40000, "loss": 0.0, "lr": 2.7501228420578533e-05, "epoch": 328.5132743362832, "percentage": 46.81, "elapsed_time": "2:14:31", "remaining_time": "2:32:50", "throughput": 1317.58, "total_tokens": 10634872} {"current_steps": 18730, "total_steps": 40000, "loss": 0.0, "lr": 2.7491460010142857e-05, "epoch": 328.60176991150445, "percentage": 46.83, "elapsed_time": "2:14:33", "remaining_time": "2:32:48", "throughput": 1317.58, "total_tokens": 10637656} {"current_steps": 18735, "total_steps": 40000, "loss": 0.0, "lr": 2.7481691215492727e-05, "epoch": 328.69026548672565, "percentage": 46.84, "elapsed_time": "2:14:35", "remaining_time": "2:32:46", "throughput": 1317.59, "total_tokens": 10640456} {"current_steps": 18740, "total_steps": 40000, "loss": 0.0, "lr": 2.747192203813463e-05, "epoch": 328.7787610619469, "percentage": 46.85, "elapsed_time": "2:14:37", "remaining_time": "2:32:43", "throughput": 1317.63, "total_tokens": 10643512} {"current_steps": 18745, "total_steps": 40000, "loss": 0.0, "lr": 2.7462152479575087e-05, "epoch": 328.86725663716817, "percentage": 46.86, "elapsed_time": "2:14:39", "remaining_time": "2:32:41", "throughput": 1317.64, "total_tokens": 10646280} {"current_steps": 18750, "total_steps": 40000, "loss": 0.0, "lr": 2.7452382541320697e-05, "epoch": 328.95575221238937, "percentage": 46.88, "elapsed_time": "2:14:41", "remaining_time": "2:32:39", "throughput": 1317.68, "total_tokens": 10649288} {"current_steps": 18755, "total_steps": 40000, "loss": 0.0, "lr": 2.7442612224878096e-05, "epoch": 329.0353982300885, "percentage": 46.89, "elapsed_time": "2:14:44", "remaining_time": "2:32:37", "throughput": 1317.63, "total_tokens": 10651880} {"current_steps": 18760, "total_steps": 40000, "loss": 0.0, "lr": 2.7432841531753994e-05, "epoch": 329.12389380530976, "percentage": 46.9, "elapsed_time": "2:14:46", "remaining_time": "2:32:35", "throughput": 1317.63, "total_tokens": 10654648} {"current_steps": 18765, "total_steps": 40000, "loss": 0.0, "lr": 2.7423070463455147e-05, "epoch": 329.21238938053096, "percentage": 46.91, "elapsed_time": "2:14:48", "remaining_time": "2:32:32", "throughput": 1317.65, "total_tokens": 10657496} {"current_steps": 18770, "total_steps": 40000, "loss": 0.0, "lr": 2.7413299021488397e-05, "epoch": 329.3008849557522, "percentage": 46.92, "elapsed_time": "2:14:50", "remaining_time": "2:32:30", "throughput": 1317.65, "total_tokens": 10660216} {"current_steps": 18775, "total_steps": 40000, "loss": 0.0, "lr": 2.7403527207360615e-05, "epoch": 329.3893805309734, "percentage": 46.94, "elapsed_time": "2:14:52", "remaining_time": "2:32:28", "throughput": 1317.67, "total_tokens": 10663112} {"current_steps": 18780, "total_steps": 40000, "loss": 0.0, "lr": 2.7393755022578722e-05, "epoch": 329.4778761061947, "percentage": 46.95, "elapsed_time": "2:14:54", "remaining_time": "2:32:26", "throughput": 1317.68, "total_tokens": 10665928} {"current_steps": 18785, "total_steps": 40000, "loss": 0.0, "lr": 2.7383982468649714e-05, "epoch": 329.56637168141594, "percentage": 46.96, "elapsed_time": "2:14:56", "remaining_time": "2:32:23", "throughput": 1317.73, "total_tokens": 10669080} {"current_steps": 18790, "total_steps": 40000, "loss": 0.0, "lr": 2.7374209547080665e-05, "epoch": 329.65486725663715, "percentage": 46.98, "elapsed_time": "2:14:58", "remaining_time": "2:32:21", "throughput": 1317.79, "total_tokens": 10672296} {"current_steps": 18795, "total_steps": 40000, "loss": 0.0, "lr": 2.7364436259378663e-05, "epoch": 329.7433628318584, "percentage": 46.99, "elapsed_time": "2:15:00", "remaining_time": "2:32:19", "throughput": 1317.77, "total_tokens": 10674904} {"current_steps": 18800, "total_steps": 40000, "loss": 0.0, "lr": 2.735466260705088e-05, "epoch": 329.83185840707966, "percentage": 47.0, "elapsed_time": "2:15:02", "remaining_time": "2:32:17", "throughput": 1317.81, "total_tokens": 10677928} {"current_steps": 18800, "total_steps": 40000, "eval_loss": 0.5949233770370483, "epoch": 329.83185840707966, "percentage": 47.0, "elapsed_time": "2:15:03", "remaining_time": "2:32:18", "throughput": 1317.64, "total_tokens": 10677928} {"current_steps": 18805, "total_steps": 40000, "loss": 0.0, "lr": 2.7344888591604524e-05, "epoch": 329.92035398230087, "percentage": 47.01, "elapsed_time": "2:15:07", "remaining_time": "2:32:18", "throughput": 1317.41, "total_tokens": 10681080} {"current_steps": 18810, "total_steps": 40000, "loss": 0.0, "lr": 2.7335114214546893e-05, "epoch": 330.0, "percentage": 47.02, "elapsed_time": "2:15:09", "remaining_time": "2:32:15", "throughput": 1317.35, "total_tokens": 10683296} {"current_steps": 18815, "total_steps": 40000, "loss": 0.0, "lr": 2.7325339477385293e-05, "epoch": 330.08849557522126, "percentage": 47.04, "elapsed_time": "2:15:11", "remaining_time": "2:32:13", "throughput": 1317.32, "total_tokens": 10686096} {"current_steps": 18820, "total_steps": 40000, "loss": 0.0, "lr": 2.7315564381627128e-05, "epoch": 330.17699115044246, "percentage": 47.05, "elapsed_time": "2:15:14", "remaining_time": "2:32:11", "throughput": 1317.37, "total_tokens": 10689152} {"current_steps": 18825, "total_steps": 40000, "loss": 0.0, "lr": 2.7305788928779835e-05, "epoch": 330.2654867256637, "percentage": 47.06, "elapsed_time": "2:15:16", "remaining_time": "2:32:09", "throughput": 1317.36, "total_tokens": 10691856} {"current_steps": 18830, "total_steps": 40000, "loss": 0.0, "lr": 2.729601312035091e-05, "epoch": 330.353982300885, "percentage": 47.08, "elapsed_time": "2:15:18", "remaining_time": "2:32:07", "throughput": 1317.38, "total_tokens": 10694768} {"current_steps": 18835, "total_steps": 40000, "loss": 0.0, "lr": 2.7286236957847915e-05, "epoch": 330.4424778761062, "percentage": 47.09, "elapsed_time": "2:15:20", "remaining_time": "2:32:04", "throughput": 1317.37, "total_tokens": 10697328} {"current_steps": 18840, "total_steps": 40000, "loss": 0.0, "lr": 2.7276460442778446e-05, "epoch": 330.53097345132744, "percentage": 47.1, "elapsed_time": "2:15:22", "remaining_time": "2:32:02", "throughput": 1317.31, "total_tokens": 10699616} {"current_steps": 18845, "total_steps": 40000, "loss": 0.0, "lr": 2.726668357665017e-05, "epoch": 330.6194690265487, "percentage": 47.11, "elapsed_time": "2:15:24", "remaining_time": "2:32:00", "throughput": 1317.36, "total_tokens": 10702736} {"current_steps": 18850, "total_steps": 40000, "loss": 0.0, "lr": 2.7256906360970808e-05, "epoch": 330.7079646017699, "percentage": 47.12, "elapsed_time": "2:15:26", "remaining_time": "2:31:58", "throughput": 1317.39, "total_tokens": 10705728} {"current_steps": 18855, "total_steps": 40000, "loss": 0.0, "lr": 2.7247128797248117e-05, "epoch": 330.79646017699116, "percentage": 47.14, "elapsed_time": "2:15:28", "remaining_time": "2:31:55", "throughput": 1317.43, "total_tokens": 10708784} {"current_steps": 18860, "total_steps": 40000, "loss": 0.0, "lr": 2.7237350886989925e-05, "epoch": 330.88495575221236, "percentage": 47.15, "elapsed_time": "2:15:30", "remaining_time": "2:31:53", "throughput": 1317.41, "total_tokens": 10711296} {"current_steps": 18865, "total_steps": 40000, "loss": 0.0, "lr": 2.7227572631704107e-05, "epoch": 330.9734513274336, "percentage": 47.16, "elapsed_time": "2:15:32", "remaining_time": "2:31:51", "throughput": 1317.48, "total_tokens": 10714576} {"current_steps": 18870, "total_steps": 40000, "loss": 0.0, "lr": 2.7217794032898596e-05, "epoch": 331.05309734513276, "percentage": 47.17, "elapsed_time": "2:15:34", "remaining_time": "2:31:49", "throughput": 1317.41, "total_tokens": 10717048} {"current_steps": 18875, "total_steps": 40000, "loss": 0.0, "lr": 2.7208015092081384e-05, "epoch": 331.14159292035396, "percentage": 47.19, "elapsed_time": "2:15:36", "remaining_time": "2:31:46", "throughput": 1317.44, "total_tokens": 10719976} {"current_steps": 18880, "total_steps": 40000, "loss": 0.0, "lr": 2.719823581076049e-05, "epoch": 331.2300884955752, "percentage": 47.2, "elapsed_time": "2:15:39", "remaining_time": "2:31:44", "throughput": 1317.43, "total_tokens": 10722696} {"current_steps": 18885, "total_steps": 40000, "loss": 0.0, "lr": 2.718845619044401e-05, "epoch": 331.3185840707965, "percentage": 47.21, "elapsed_time": "2:15:41", "remaining_time": "2:31:42", "throughput": 1317.48, "total_tokens": 10725816} {"current_steps": 18890, "total_steps": 40000, "loss": 0.0, "lr": 2.7178676232640088e-05, "epoch": 331.4070796460177, "percentage": 47.23, "elapsed_time": "2:15:43", "remaining_time": "2:31:40", "throughput": 1317.51, "total_tokens": 10728728} {"current_steps": 18895, "total_steps": 40000, "loss": 0.0, "lr": 2.716889593885691e-05, "epoch": 331.49557522123894, "percentage": 47.24, "elapsed_time": "2:15:45", "remaining_time": "2:31:37", "throughput": 1317.62, "total_tokens": 10732424} {"current_steps": 18900, "total_steps": 40000, "loss": 0.0, "lr": 2.7159115310602716e-05, "epoch": 331.5840707964602, "percentage": 47.25, "elapsed_time": "2:15:47", "remaining_time": "2:31:35", "throughput": 1317.61, "total_tokens": 10735064} {"current_steps": 18905, "total_steps": 40000, "loss": 0.0, "lr": 2.7149334349385814e-05, "epoch": 331.6725663716814, "percentage": 47.26, "elapsed_time": "2:15:49", "remaining_time": "2:31:33", "throughput": 1317.63, "total_tokens": 10737944} {"current_steps": 18910, "total_steps": 40000, "loss": 0.0, "lr": 2.713955305671454e-05, "epoch": 331.76106194690266, "percentage": 47.27, "elapsed_time": "2:15:51", "remaining_time": "2:31:31", "throughput": 1317.62, "total_tokens": 10740568} {"current_steps": 18915, "total_steps": 40000, "loss": 0.0, "lr": 2.71297714340973e-05, "epoch": 331.8495575221239, "percentage": 47.29, "elapsed_time": "2:15:53", "remaining_time": "2:31:28", "throughput": 1317.63, "total_tokens": 10743384} {"current_steps": 18920, "total_steps": 40000, "loss": 0.0, "lr": 2.7119989483042545e-05, "epoch": 331.9380530973451, "percentage": 47.3, "elapsed_time": "2:15:55", "remaining_time": "2:31:26", "throughput": 1317.58, "total_tokens": 10745736} {"current_steps": 18925, "total_steps": 40000, "loss": 0.0, "lr": 2.7110207205058768e-05, "epoch": 332.01769911504425, "percentage": 47.31, "elapsed_time": "2:15:57", "remaining_time": "2:31:24", "throughput": 1317.5, "total_tokens": 10748000} {"current_steps": 18930, "total_steps": 40000, "loss": 0.0, "lr": 2.7100424601654517e-05, "epoch": 332.1061946902655, "percentage": 47.33, "elapsed_time": "2:15:59", "remaining_time": "2:31:22", "throughput": 1317.46, "total_tokens": 10750432} {"current_steps": 18935, "total_steps": 40000, "loss": 0.0, "lr": 2.7090641674338403e-05, "epoch": 332.1946902654867, "percentage": 47.34, "elapsed_time": "2:16:02", "remaining_time": "2:31:20", "throughput": 1317.5, "total_tokens": 10753488} {"current_steps": 18940, "total_steps": 40000, "loss": 0.0, "lr": 2.7080858424619072e-05, "epoch": 332.283185840708, "percentage": 47.35, "elapsed_time": "2:16:04", "remaining_time": "2:31:17", "throughput": 1317.55, "total_tokens": 10756592} {"current_steps": 18945, "total_steps": 40000, "loss": 0.0, "lr": 2.707107485400521e-05, "epoch": 332.37168141592923, "percentage": 47.36, "elapsed_time": "2:16:06", "remaining_time": "2:31:15", "throughput": 1317.56, "total_tokens": 10759424} {"current_steps": 18950, "total_steps": 40000, "loss": 0.0, "lr": 2.7061290964005586e-05, "epoch": 332.46017699115043, "percentage": 47.38, "elapsed_time": "2:16:08", "remaining_time": "2:31:13", "throughput": 1317.57, "total_tokens": 10762192} {"current_steps": 18955, "total_steps": 40000, "loss": 0.0, "lr": 2.7051506756129e-05, "epoch": 332.5486725663717, "percentage": 47.39, "elapsed_time": "2:16:10", "remaining_time": "2:31:11", "throughput": 1317.57, "total_tokens": 10764912} {"current_steps": 18960, "total_steps": 40000, "loss": 0.0, "lr": 2.704172223188428e-05, "epoch": 332.6371681415929, "percentage": 47.4, "elapsed_time": "2:16:12", "remaining_time": "2:31:08", "throughput": 1317.6, "total_tokens": 10767872} {"current_steps": 18965, "total_steps": 40000, "loss": 0.0, "lr": 2.7031937392780334e-05, "epoch": 332.72566371681415, "percentage": 47.41, "elapsed_time": "2:16:14", "remaining_time": "2:31:06", "throughput": 1317.67, "total_tokens": 10771152} {"current_steps": 18970, "total_steps": 40000, "loss": 0.0, "lr": 2.702215224032611e-05, "epoch": 332.8141592920354, "percentage": 47.42, "elapsed_time": "2:16:16", "remaining_time": "2:31:04", "throughput": 1317.68, "total_tokens": 10774000} {"current_steps": 18975, "total_steps": 40000, "loss": 0.0, "lr": 2.70123667760306e-05, "epoch": 332.9026548672566, "percentage": 47.44, "elapsed_time": "2:16:18", "remaining_time": "2:31:02", "throughput": 1317.68, "total_tokens": 10776688} {"current_steps": 18980, "total_steps": 40000, "loss": 0.0, "lr": 2.7002581001402845e-05, "epoch": 332.9911504424779, "percentage": 47.45, "elapsed_time": "2:16:20", "remaining_time": "2:30:59", "throughput": 1317.7, "total_tokens": 10779600} {"current_steps": 18985, "total_steps": 40000, "loss": 0.0, "lr": 2.6992794917951923e-05, "epoch": 333.070796460177, "percentage": 47.46, "elapsed_time": "2:16:22", "remaining_time": "2:30:57", "throughput": 1317.62, "total_tokens": 10781936} {"current_steps": 18990, "total_steps": 40000, "loss": 0.0, "lr": 2.6983008527187e-05, "epoch": 333.1592920353982, "percentage": 47.48, "elapsed_time": "2:16:24", "remaining_time": "2:30:55", "throughput": 1317.63, "total_tokens": 10784768} {"current_steps": 18995, "total_steps": 40000, "loss": 0.0, "lr": 2.697322183061723e-05, "epoch": 333.24778761061947, "percentage": 47.49, "elapsed_time": "2:16:27", "remaining_time": "2:30:53", "throughput": 1317.7, "total_tokens": 10788048} {"current_steps": 19000, "total_steps": 40000, "loss": 0.0, "lr": 2.696343482975186e-05, "epoch": 333.3362831858407, "percentage": 47.5, "elapsed_time": "2:16:29", "remaining_time": "2:30:51", "throughput": 1317.72, "total_tokens": 10790896} {"current_steps": 19000, "total_steps": 40000, "eval_loss": 0.5917893648147583, "epoch": 333.3362831858407, "percentage": 47.5, "elapsed_time": "2:16:30", "remaining_time": "2:30:52", "throughput": 1317.55, "total_tokens": 10790896} {"current_steps": 19005, "total_steps": 40000, "loss": 0.0, "lr": 2.695364752610016e-05, "epoch": 333.42477876106193, "percentage": 47.51, "elapsed_time": "2:16:33", "remaining_time": "2:30:51", "throughput": 1317.27, "total_tokens": 10793696} {"current_steps": 19010, "total_steps": 40000, "loss": 0.0, "lr": 2.6943859921171467e-05, "epoch": 333.5132743362832, "percentage": 47.52, "elapsed_time": "2:16:36", "remaining_time": "2:30:49", "throughput": 1317.33, "total_tokens": 10796880} {"current_steps": 19015, "total_steps": 40000, "loss": 0.0, "lr": 2.6934072016475143e-05, "epoch": 333.60176991150445, "percentage": 47.54, "elapsed_time": "2:16:38", "remaining_time": "2:30:47", "throughput": 1317.31, "total_tokens": 10799472} {"current_steps": 19020, "total_steps": 40000, "loss": 0.0, "lr": 2.6924283813520606e-05, "epoch": 333.69026548672565, "percentage": 47.55, "elapsed_time": "2:16:40", "remaining_time": "2:30:45", "throughput": 1317.27, "total_tokens": 10801856} {"current_steps": 19025, "total_steps": 40000, "loss": 0.0, "lr": 2.691449531381733e-05, "epoch": 333.7787610619469, "percentage": 47.56, "elapsed_time": "2:16:42", "remaining_time": "2:30:42", "throughput": 1317.3, "total_tokens": 10804864} {"current_steps": 19030, "total_steps": 40000, "loss": 0.0, "lr": 2.6904706518874816e-05, "epoch": 333.86725663716817, "percentage": 47.58, "elapsed_time": "2:16:44", "remaining_time": "2:30:40", "throughput": 1317.35, "total_tokens": 10807968} {"current_steps": 19035, "total_steps": 40000, "loss": 0.0, "lr": 2.6894917430202615e-05, "epoch": 333.95575221238937, "percentage": 47.59, "elapsed_time": "2:16:46", "remaining_time": "2:30:38", "throughput": 1317.4, "total_tokens": 10811104} {"current_steps": 19040, "total_steps": 40000, "loss": 0.0, "lr": 2.6885128049310343e-05, "epoch": 334.0353982300885, "percentage": 47.6, "elapsed_time": "2:16:48", "remaining_time": "2:30:36", "throughput": 1317.37, "total_tokens": 10813792} {"current_steps": 19045, "total_steps": 40000, "loss": 0.0, "lr": 2.687533837770762e-05, "epoch": 334.12389380530976, "percentage": 47.61, "elapsed_time": "2:16:50", "remaining_time": "2:30:34", "throughput": 1317.37, "total_tokens": 10816576} {"current_steps": 19050, "total_steps": 40000, "loss": 0.0, "lr": 2.6865548416904162e-05, "epoch": 334.21238938053096, "percentage": 47.62, "elapsed_time": "2:16:52", "remaining_time": "2:30:31", "throughput": 1317.41, "total_tokens": 10819632} {"current_steps": 19055, "total_steps": 40000, "loss": 0.0, "lr": 2.68557581684097e-05, "epoch": 334.3008849557522, "percentage": 47.64, "elapsed_time": "2:16:54", "remaining_time": "2:30:29", "throughput": 1317.49, "total_tokens": 10822992} {"current_steps": 19060, "total_steps": 40000, "loss": 0.0, "lr": 2.6845967633733998e-05, "epoch": 334.3893805309734, "percentage": 47.65, "elapsed_time": "2:16:56", "remaining_time": "2:30:27", "throughput": 1317.49, "total_tokens": 10825696} {"current_steps": 19065, "total_steps": 40000, "loss": 0.0, "lr": 2.683617681438689e-05, "epoch": 334.4778761061947, "percentage": 47.66, "elapsed_time": "2:16:59", "remaining_time": "2:30:25", "throughput": 1317.49, "total_tokens": 10828432} {"current_steps": 19070, "total_steps": 40000, "loss": 0.0, "lr": 2.682638571187825e-05, "epoch": 334.56637168141594, "percentage": 47.67, "elapsed_time": "2:17:01", "remaining_time": "2:30:22", "throughput": 1317.53, "total_tokens": 10831520} {"current_steps": 19075, "total_steps": 40000, "loss": 0.0, "lr": 2.6816594327717976e-05, "epoch": 334.65486725663715, "percentage": 47.69, "elapsed_time": "2:17:03", "remaining_time": "2:30:20", "throughput": 1317.49, "total_tokens": 10833904} {"current_steps": 19080, "total_steps": 40000, "loss": 0.0, "lr": 2.680680266341603e-05, "epoch": 334.7433628318584, "percentage": 47.7, "elapsed_time": "2:17:05", "remaining_time": "2:30:18", "throughput": 1317.51, "total_tokens": 10836848} {"current_steps": 19085, "total_steps": 40000, "loss": 0.0, "lr": 2.67970107204824e-05, "epoch": 334.83185840707966, "percentage": 47.71, "elapsed_time": "2:17:07", "remaining_time": "2:30:16", "throughput": 1317.49, "total_tokens": 10839440} {"current_steps": 19090, "total_steps": 40000, "loss": 0.0, "lr": 2.6787218500427142e-05, "epoch": 334.92035398230087, "percentage": 47.73, "elapsed_time": "2:17:09", "remaining_time": "2:30:13", "throughput": 1317.49, "total_tokens": 10842144} {"current_steps": 19095, "total_steps": 40000, "loss": 0.0, "lr": 2.6777426004760332e-05, "epoch": 335.0, "percentage": 47.74, "elapsed_time": "2:17:11", "remaining_time": "2:30:11", "throughput": 1317.44, "total_tokens": 10844392} {"current_steps": 19100, "total_steps": 40000, "loss": 0.0, "lr": 2.6767633234992094e-05, "epoch": 335.08849557522126, "percentage": 47.75, "elapsed_time": "2:17:13", "remaining_time": "2:30:09", "throughput": 1317.43, "total_tokens": 10847320} {"current_steps": 19105, "total_steps": 40000, "loss": 0.0, "lr": 2.6757840192632598e-05, "epoch": 335.17699115044246, "percentage": 47.76, "elapsed_time": "2:17:15", "remaining_time": "2:30:07", "throughput": 1317.5, "total_tokens": 10850632} {"current_steps": 19110, "total_steps": 40000, "loss": 0.0, "lr": 2.6748046879192052e-05, "epoch": 335.2654867256637, "percentage": 47.77, "elapsed_time": "2:17:17", "remaining_time": "2:30:05", "throughput": 1317.5, "total_tokens": 10853352} {"current_steps": 19115, "total_steps": 40000, "loss": 0.0, "lr": 2.673825329618071e-05, "epoch": 335.353982300885, "percentage": 47.79, "elapsed_time": "2:17:19", "remaining_time": "2:30:02", "throughput": 1317.48, "total_tokens": 10855960} {"current_steps": 19120, "total_steps": 40000, "loss": 0.0, "lr": 2.6728459445108866e-05, "epoch": 335.4424778761062, "percentage": 47.8, "elapsed_time": "2:17:21", "remaining_time": "2:30:00", "throughput": 1317.47, "total_tokens": 10858568} {"current_steps": 19125, "total_steps": 40000, "loss": 0.0, "lr": 2.6718665327486854e-05, "epoch": 335.53097345132744, "percentage": 47.81, "elapsed_time": "2:17:24", "remaining_time": "2:29:58", "throughput": 1317.49, "total_tokens": 10861432} {"current_steps": 19130, "total_steps": 40000, "loss": 0.0, "lr": 2.6708870944825048e-05, "epoch": 335.6194690265487, "percentage": 47.83, "elapsed_time": "2:17:26", "remaining_time": "2:29:56", "throughput": 1317.55, "total_tokens": 10864664} {"current_steps": 19135, "total_steps": 40000, "loss": 0.0, "lr": 2.6699076298633874e-05, "epoch": 335.7079646017699, "percentage": 47.84, "elapsed_time": "2:17:28", "remaining_time": "2:29:53", "throughput": 1317.56, "total_tokens": 10867512} {"current_steps": 19140, "total_steps": 40000, "loss": 0.0, "lr": 2.6689281390423788e-05, "epoch": 335.79646017699116, "percentage": 47.85, "elapsed_time": "2:17:30", "remaining_time": "2:29:51", "throughput": 1317.64, "total_tokens": 10870888} {"current_steps": 19145, "total_steps": 40000, "loss": 0.0, "lr": 2.667948622170527e-05, "epoch": 335.88495575221236, "percentage": 47.86, "elapsed_time": "2:17:32", "remaining_time": "2:29:49", "throughput": 1317.66, "total_tokens": 10873768} {"current_steps": 19150, "total_steps": 40000, "loss": 0.0, "lr": 2.6669690793988873e-05, "epoch": 335.9734513274336, "percentage": 47.88, "elapsed_time": "2:17:34", "remaining_time": "2:29:47", "throughput": 1317.63, "total_tokens": 10876248} {"current_steps": 19155, "total_steps": 40000, "loss": 0.0, "lr": 2.665989510878518e-05, "epoch": 336.05309734513276, "percentage": 47.89, "elapsed_time": "2:17:36", "remaining_time": "2:29:45", "throughput": 1317.6, "total_tokens": 10878952} {"current_steps": 19160, "total_steps": 40000, "loss": 0.0, "lr": 2.6650099167604793e-05, "epoch": 336.14159292035396, "percentage": 47.9, "elapsed_time": "2:17:38", "remaining_time": "2:29:42", "throughput": 1317.62, "total_tokens": 10881896} {"current_steps": 19165, "total_steps": 40000, "loss": 0.0, "lr": 2.6640302971958376e-05, "epoch": 336.2300884955752, "percentage": 47.91, "elapsed_time": "2:17:40", "remaining_time": "2:29:40", "throughput": 1317.7, "total_tokens": 10885224} {"current_steps": 19170, "total_steps": 40000, "loss": 0.0, "lr": 2.6630506523356635e-05, "epoch": 336.3185840707965, "percentage": 47.93, "elapsed_time": "2:17:42", "remaining_time": "2:29:38", "throughput": 1317.72, "total_tokens": 10888120} {"current_steps": 19175, "total_steps": 40000, "loss": 0.0, "lr": 2.6620709823310297e-05, "epoch": 336.4070796460177, "percentage": 47.94, "elapsed_time": "2:17:44", "remaining_time": "2:29:36", "throughput": 1317.71, "total_tokens": 10890808} {"current_steps": 19180, "total_steps": 40000, "loss": 0.0, "lr": 2.661091287333014e-05, "epoch": 336.49557522123894, "percentage": 47.95, "elapsed_time": "2:17:47", "remaining_time": "2:29:33", "throughput": 1317.73, "total_tokens": 10893752} {"current_steps": 19185, "total_steps": 40000, "loss": 0.0, "lr": 2.660111567492696e-05, "epoch": 336.5840707964602, "percentage": 47.96, "elapsed_time": "2:17:49", "remaining_time": "2:29:31", "throughput": 1317.74, "total_tokens": 10896536} {"current_steps": 19190, "total_steps": 40000, "loss": 0.0, "lr": 2.6591318229611635e-05, "epoch": 336.6725663716814, "percentage": 47.98, "elapsed_time": "2:17:51", "remaining_time": "2:29:29", "throughput": 1317.73, "total_tokens": 10899192} {"current_steps": 19195, "total_steps": 40000, "loss": 0.0, "lr": 2.6581520538895037e-05, "epoch": 336.76106194690266, "percentage": 47.99, "elapsed_time": "2:17:53", "remaining_time": "2:29:27", "throughput": 1317.74, "total_tokens": 10902008} {"current_steps": 19200, "total_steps": 40000, "loss": 0.0, "lr": 2.6571722604288102e-05, "epoch": 336.8495575221239, "percentage": 48.0, "elapsed_time": "2:17:55", "remaining_time": "2:29:24", "throughput": 1317.72, "total_tokens": 10904600} {"current_steps": 19200, "total_steps": 40000, "eval_loss": 0.5861619710922241, "epoch": 336.8495575221239, "percentage": 48.0, "elapsed_time": "2:17:56", "remaining_time": "2:29:26", "throughput": 1317.55, "total_tokens": 10904600} {"current_steps": 19205, "total_steps": 40000, "loss": 0.0, "lr": 2.656192442730179e-05, "epoch": 336.9380530973451, "percentage": 48.01, "elapsed_time": "2:18:00", "remaining_time": "2:29:25", "throughput": 1317.35, "total_tokens": 10907928} {"current_steps": 19210, "total_steps": 40000, "loss": 0.0, "lr": 2.6552126009447098e-05, "epoch": 337.01769911504425, "percentage": 48.02, "elapsed_time": "2:18:02", "remaining_time": "2:29:23", "throughput": 1317.24, "total_tokens": 10910000} {"current_steps": 19215, "total_steps": 40000, "loss": 0.0, "lr": 2.654232735223507e-05, "epoch": 337.1061946902655, "percentage": 48.04, "elapsed_time": "2:18:04", "remaining_time": "2:29:21", "throughput": 1317.27, "total_tokens": 10912960} {"current_steps": 19220, "total_steps": 40000, "loss": 0.0, "lr": 2.6532528457176787e-05, "epoch": 337.1946902654867, "percentage": 48.05, "elapsed_time": "2:18:06", "remaining_time": "2:29:19", "throughput": 1317.28, "total_tokens": 10915760} {"current_steps": 19225, "total_steps": 40000, "loss": 0.0, "lr": 2.6522729325783348e-05, "epoch": 337.283185840708, "percentage": 48.06, "elapsed_time": "2:18:08", "remaining_time": "2:29:16", "throughput": 1317.36, "total_tokens": 10919184} {"current_steps": 19230, "total_steps": 40000, "loss": 0.0, "lr": 2.6512929959565914e-05, "epoch": 337.37168141592923, "percentage": 48.08, "elapsed_time": "2:18:10", "remaining_time": "2:29:14", "throughput": 1317.39, "total_tokens": 10922128} {"current_steps": 19235, "total_steps": 40000, "loss": 0.0, "lr": 2.6503130360035673e-05, "epoch": 337.46017699115043, "percentage": 48.09, "elapsed_time": "2:18:12", "remaining_time": "2:29:12", "throughput": 1317.39, "total_tokens": 10924864} {"current_steps": 19240, "total_steps": 40000, "loss": 0.0, "lr": 2.6493330528703835e-05, "epoch": 337.5486725663717, "percentage": 48.1, "elapsed_time": "2:18:14", "remaining_time": "2:29:10", "throughput": 1317.43, "total_tokens": 10927936} {"current_steps": 19245, "total_steps": 40000, "loss": 0.0, "lr": 2.648353046708167e-05, "epoch": 337.6371681415929, "percentage": 48.11, "elapsed_time": "2:18:16", "remaining_time": "2:29:07", "throughput": 1317.46, "total_tokens": 10930928} {"current_steps": 19250, "total_steps": 40000, "loss": 0.0, "lr": 2.647373017668046e-05, "epoch": 337.72566371681415, "percentage": 48.12, "elapsed_time": "2:18:19", "remaining_time": "2:29:05", "throughput": 1317.48, "total_tokens": 10933792} {"current_steps": 19255, "total_steps": 40000, "loss": 0.0, "lr": 2.6463929659011537e-05, "epoch": 337.8141592920354, "percentage": 48.14, "elapsed_time": "2:18:21", "remaining_time": "2:29:03", "throughput": 1317.47, "total_tokens": 10936432} {"current_steps": 19260, "total_steps": 40000, "loss": 0.0, "lr": 2.6454128915586262e-05, "epoch": 337.9026548672566, "percentage": 48.15, "elapsed_time": "2:18:23", "remaining_time": "2:29:01", "throughput": 1317.47, "total_tokens": 10939152} {"current_steps": 19265, "total_steps": 40000, "loss": 0.0, "lr": 2.6444327947916036e-05, "epoch": 337.9911504424779, "percentage": 48.16, "elapsed_time": "2:18:25", "remaining_time": "2:28:58", "throughput": 1317.46, "total_tokens": 10941792} {"current_steps": 19270, "total_steps": 40000, "loss": 0.0, "lr": 2.6434526757512292e-05, "epoch": 338.070796460177, "percentage": 48.18, "elapsed_time": "2:18:27", "remaining_time": "2:28:56", "throughput": 1317.38, "total_tokens": 10944112} {"current_steps": 19275, "total_steps": 40000, "loss": 0.0, "lr": 2.6424725345886486e-05, "epoch": 338.1592920353982, "percentage": 48.19, "elapsed_time": "2:18:29", "remaining_time": "2:28:54", "throughput": 1317.45, "total_tokens": 10947408} {"current_steps": 19280, "total_steps": 40000, "loss": 0.0, "lr": 2.641492371455014e-05, "epoch": 338.24778761061947, "percentage": 48.2, "elapsed_time": "2:18:31", "remaining_time": "2:28:52", "throughput": 1317.44, "total_tokens": 10950048} {"current_steps": 19285, "total_steps": 40000, "loss": 0.0, "lr": 2.640512186501477e-05, "epoch": 338.3362831858407, "percentage": 48.21, "elapsed_time": "2:18:33", "remaining_time": "2:28:50", "throughput": 1317.52, "total_tokens": 10953424} {"current_steps": 19290, "total_steps": 40000, "loss": 0.0, "lr": 2.639531979879195e-05, "epoch": 338.42477876106193, "percentage": 48.23, "elapsed_time": "2:18:35", "remaining_time": "2:28:47", "throughput": 1317.5, "total_tokens": 10956016} {"current_steps": 19295, "total_steps": 40000, "loss": 0.0, "lr": 2.638551751739328e-05, "epoch": 338.5132743362832, "percentage": 48.24, "elapsed_time": "2:18:37", "remaining_time": "2:28:45", "throughput": 1317.53, "total_tokens": 10958960} {"current_steps": 19300, "total_steps": 40000, "loss": 0.0, "lr": 2.6375715022330404e-05, "epoch": 338.60176991150445, "percentage": 48.25, "elapsed_time": "2:18:39", "remaining_time": "2:28:43", "throughput": 1317.54, "total_tokens": 10961824} {"current_steps": 19305, "total_steps": 40000, "loss": 0.0, "lr": 2.6365912315114976e-05, "epoch": 338.69026548672565, "percentage": 48.26, "elapsed_time": "2:18:41", "remaining_time": "2:28:41", "throughput": 1317.52, "total_tokens": 10964368} {"current_steps": 19310, "total_steps": 40000, "loss": 0.0, "lr": 2.6356109397258704e-05, "epoch": 338.7787610619469, "percentage": 48.27, "elapsed_time": "2:18:44", "remaining_time": "2:28:38", "throughput": 1317.57, "total_tokens": 10967520} {"current_steps": 19315, "total_steps": 40000, "loss": 0.0, "lr": 2.6346306270273325e-05, "epoch": 338.86725663716817, "percentage": 48.29, "elapsed_time": "2:18:46", "remaining_time": "2:28:36", "throughput": 1317.58, "total_tokens": 10970288} {"current_steps": 19320, "total_steps": 40000, "loss": 0.0, "lr": 2.6336502935670608e-05, "epoch": 338.95575221238937, "percentage": 48.3, "elapsed_time": "2:18:48", "remaining_time": "2:28:34", "throughput": 1317.62, "total_tokens": 10973344} {"current_steps": 19325, "total_steps": 40000, "loss": 0.0, "lr": 2.6326699394962333e-05, "epoch": 339.0353982300885, "percentage": 48.31, "elapsed_time": "2:18:50", "remaining_time": "2:28:32", "throughput": 1317.52, "total_tokens": 10975544} {"current_steps": 19330, "total_steps": 40000, "loss": 0.0, "lr": 2.6316895649660334e-05, "epoch": 339.12389380530976, "percentage": 48.33, "elapsed_time": "2:18:52", "remaining_time": "2:28:30", "throughput": 1317.53, "total_tokens": 10978328} {"current_steps": 19335, "total_steps": 40000, "loss": 0.0, "lr": 2.6307091701276486e-05, "epoch": 339.21238938053096, "percentage": 48.34, "elapsed_time": "2:18:54", "remaining_time": "2:28:27", "throughput": 1317.52, "total_tokens": 10980952} {"current_steps": 19340, "total_steps": 40000, "loss": 0.0, "lr": 2.629728755132267e-05, "epoch": 339.3008849557522, "percentage": 48.35, "elapsed_time": "2:18:56", "remaining_time": "2:28:25", "throughput": 1317.55, "total_tokens": 10983928} {"current_steps": 19345, "total_steps": 40000, "loss": 0.0, "lr": 2.628748320131081e-05, "epoch": 339.3893805309734, "percentage": 48.36, "elapsed_time": "2:18:58", "remaining_time": "2:28:23", "throughput": 1317.59, "total_tokens": 10987000} {"current_steps": 19350, "total_steps": 40000, "loss": 0.0, "lr": 2.6277678652752856e-05, "epoch": 339.4778761061947, "percentage": 48.38, "elapsed_time": "2:19:00", "remaining_time": "2:28:21", "throughput": 1317.68, "total_tokens": 10990520} {"current_steps": 19355, "total_steps": 40000, "loss": 0.0, "lr": 2.6267873907160807e-05, "epoch": 339.56637168141594, "percentage": 48.39, "elapsed_time": "2:19:02", "remaining_time": "2:28:18", "throughput": 1317.69, "total_tokens": 10993288} {"current_steps": 19360, "total_steps": 40000, "loss": 0.0, "lr": 2.6258068966046668e-05, "epoch": 339.65486725663715, "percentage": 48.4, "elapsed_time": "2:19:04", "remaining_time": "2:28:16", "throughput": 1317.69, "total_tokens": 10996008} {"current_steps": 19365, "total_steps": 40000, "loss": 0.0, "lr": 2.6248263830922475e-05, "epoch": 339.7433628318584, "percentage": 48.41, "elapsed_time": "2:19:06", "remaining_time": "2:28:14", "throughput": 1317.74, "total_tokens": 10999176} {"current_steps": 19370, "total_steps": 40000, "loss": 0.0, "lr": 2.6238458503300318e-05, "epoch": 339.83185840707966, "percentage": 48.43, "elapsed_time": "2:19:09", "remaining_time": "2:28:12", "throughput": 1317.74, "total_tokens": 11001864} {"current_steps": 19375, "total_steps": 40000, "loss": 0.0, "lr": 2.6228652984692292e-05, "epoch": 339.92035398230087, "percentage": 48.44, "elapsed_time": "2:19:11", "remaining_time": "2:28:09", "throughput": 1317.72, "total_tokens": 11004408} {"current_steps": 19380, "total_steps": 40000, "loss": 0.0, "lr": 2.621884727661054e-05, "epoch": 340.0, "percentage": 48.45, "elapsed_time": "2:19:13", "remaining_time": "2:28:07", "throughput": 1317.67, "total_tokens": 11006656} {"current_steps": 19385, "total_steps": 40000, "loss": 0.0, "lr": 2.6209041380567222e-05, "epoch": 340.08849557522126, "percentage": 48.46, "elapsed_time": "2:19:15", "remaining_time": "2:28:05", "throughput": 1317.66, "total_tokens": 11009664} {"current_steps": 19390, "total_steps": 40000, "loss": 0.0, "lr": 2.6199235298074527e-05, "epoch": 340.17699115044246, "percentage": 48.48, "elapsed_time": "2:19:17", "remaining_time": "2:28:03", "throughput": 1317.69, "total_tokens": 11012592} {"current_steps": 19395, "total_steps": 40000, "loss": 0.0, "lr": 2.618942903064468e-05, "epoch": 340.2654867256637, "percentage": 48.49, "elapsed_time": "2:19:19", "remaining_time": "2:28:01", "throughput": 1317.69, "total_tokens": 11015328} {"current_steps": 19400, "total_steps": 40000, "loss": 0.0, "lr": 2.6179622579789932e-05, "epoch": 340.353982300885, "percentage": 48.5, "elapsed_time": "2:19:21", "remaining_time": "2:27:58", "throughput": 1317.7, "total_tokens": 11018112} {"current_steps": 19400, "total_steps": 40000, "eval_loss": 0.562694251537323, "epoch": 340.353982300885, "percentage": 48.5, "elapsed_time": "2:19:22", "remaining_time": "2:27:59", "throughput": 1317.53, "total_tokens": 11018112} {"current_steps": 19405, "total_steps": 40000, "loss": 0.0, "lr": 2.6169815947022553e-05, "epoch": 340.4424778761062, "percentage": 48.51, "elapsed_time": "2:19:26", "remaining_time": "2:27:59", "throughput": 1317.3, "total_tokens": 11021200} {"current_steps": 19410, "total_steps": 40000, "loss": 0.0, "lr": 2.6160009133854853e-05, "epoch": 340.53097345132744, "percentage": 48.52, "elapsed_time": "2:19:28", "remaining_time": "2:27:57", "throughput": 1317.35, "total_tokens": 11024320} {"current_steps": 19415, "total_steps": 40000, "loss": 0.0, "lr": 2.6150202141799168e-05, "epoch": 340.6194690265487, "percentage": 48.54, "elapsed_time": "2:19:30", "remaining_time": "2:27:55", "throughput": 1317.35, "total_tokens": 11027104} {"current_steps": 19420, "total_steps": 40000, "loss": 0.0, "lr": 2.614039497236786e-05, "epoch": 340.7079646017699, "percentage": 48.55, "elapsed_time": "2:19:32", "remaining_time": "2:27:52", "throughput": 1317.36, "total_tokens": 11029856} {"current_steps": 19425, "total_steps": 40000, "loss": 0.0, "lr": 2.6130587627073315e-05, "epoch": 340.79646017699116, "percentage": 48.56, "elapsed_time": "2:19:34", "remaining_time": "2:27:50", "throughput": 1317.36, "total_tokens": 11032640} {"current_steps": 19430, "total_steps": 40000, "loss": 0.0, "lr": 2.6120780107427956e-05, "epoch": 340.88495575221236, "percentage": 48.58, "elapsed_time": "2:19:36", "remaining_time": "2:27:48", "throughput": 1317.4, "total_tokens": 11035648} {"current_steps": 19435, "total_steps": 40000, "loss": 0.0, "lr": 2.6110972414944214e-05, "epoch": 340.9734513274336, "percentage": 48.59, "elapsed_time": "2:19:38", "remaining_time": "2:27:46", "throughput": 1317.4, "total_tokens": 11038416} {"current_steps": 19440, "total_steps": 40000, "loss": 0.0, "lr": 2.6101164551134565e-05, "epoch": 341.05309734513276, "percentage": 48.6, "elapsed_time": "2:19:41", "remaining_time": "2:27:44", "throughput": 1317.31, "total_tokens": 11040640} {"current_steps": 19445, "total_steps": 40000, "loss": 0.0, "lr": 2.6091356517511505e-05, "epoch": 341.14159292035396, "percentage": 48.61, "elapsed_time": "2:19:43", "remaining_time": "2:27:41", "throughput": 1317.29, "total_tokens": 11043136} {"current_steps": 19450, "total_steps": 40000, "loss": 0.0, "lr": 2.608154831558755e-05, "epoch": 341.2300884955752, "percentage": 48.62, "elapsed_time": "2:19:45", "remaining_time": "2:27:39", "throughput": 1317.35, "total_tokens": 11046432} {"current_steps": 19455, "total_steps": 40000, "loss": 0.0, "lr": 2.607173994687526e-05, "epoch": 341.3185840707965, "percentage": 48.64, "elapsed_time": "2:19:47", "remaining_time": "2:27:37", "throughput": 1317.4, "total_tokens": 11049520} {"current_steps": 19460, "total_steps": 40000, "loss": 0.0, "lr": 2.6061931412887196e-05, "epoch": 341.4070796460177, "percentage": 48.65, "elapsed_time": "2:19:49", "remaining_time": "2:27:35", "throughput": 1317.43, "total_tokens": 11052496} {"current_steps": 19465, "total_steps": 40000, "loss": 0.0, "lr": 2.6052122715135973e-05, "epoch": 341.49557522123894, "percentage": 48.66, "elapsed_time": "2:19:51", "remaining_time": "2:27:32", "throughput": 1317.45, "total_tokens": 11055472} {"current_steps": 19470, "total_steps": 40000, "loss": 0.0, "lr": 2.60423138551342e-05, "epoch": 341.5840707964602, "percentage": 48.68, "elapsed_time": "2:19:53", "remaining_time": "2:27:30", "throughput": 1317.43, "total_tokens": 11058000} {"current_steps": 19475, "total_steps": 40000, "loss": 0.0, "lr": 2.6032504834394527e-05, "epoch": 341.6725663716814, "percentage": 48.69, "elapsed_time": "2:19:55", "remaining_time": "2:27:28", "throughput": 1317.42, "total_tokens": 11060640} {"current_steps": 19480, "total_steps": 40000, "loss": 0.0, "lr": 2.602269565442964e-05, "epoch": 341.76106194690266, "percentage": 48.7, "elapsed_time": "2:19:57", "remaining_time": "2:27:26", "throughput": 1317.49, "total_tokens": 11064000} {"current_steps": 19485, "total_steps": 40000, "loss": 0.0, "lr": 2.6012886316752227e-05, "epoch": 341.8495575221239, "percentage": 48.71, "elapsed_time": "2:19:59", "remaining_time": "2:27:23", "throughput": 1317.54, "total_tokens": 11067120} {"current_steps": 19490, "total_steps": 40000, "loss": 0.0, "lr": 2.6003076822875018e-05, "epoch": 341.9380530973451, "percentage": 48.73, "elapsed_time": "2:20:01", "remaining_time": "2:27:21", "throughput": 1317.55, "total_tokens": 11069984} {"current_steps": 19495, "total_steps": 40000, "loss": 0.0, "lr": 2.5993267174310755e-05, "epoch": 342.01769911504425, "percentage": 48.74, "elapsed_time": "2:20:04", "remaining_time": "2:27:19", "throughput": 1317.48, "total_tokens": 11072296} {"current_steps": 19500, "total_steps": 40000, "loss": 0.0, "lr": 2.5983457372572218e-05, "epoch": 342.1061946902655, "percentage": 48.75, "elapsed_time": "2:20:06", "remaining_time": "2:27:17", "throughput": 1317.52, "total_tokens": 11075384} {"current_steps": 19505, "total_steps": 40000, "loss": 0.0, "lr": 2.597364741917219e-05, "epoch": 342.1946902654867, "percentage": 48.76, "elapsed_time": "2:20:08", "remaining_time": "2:27:15", "throughput": 1317.56, "total_tokens": 11078440} {"current_steps": 19510, "total_steps": 40000, "loss": 0.0, "lr": 2.5963837315623492e-05, "epoch": 342.283185840708, "percentage": 48.77, "elapsed_time": "2:20:10", "remaining_time": "2:27:12", "throughput": 1317.57, "total_tokens": 11081256} {"current_steps": 19515, "total_steps": 40000, "loss": 0.0, "lr": 2.595402706343897e-05, "epoch": 342.37168141592923, "percentage": 48.79, "elapsed_time": "2:20:12", "remaining_time": "2:27:10", "throughput": 1317.6, "total_tokens": 11084200} {"current_steps": 19520, "total_steps": 40000, "loss": 0.0, "lr": 2.594421666413148e-05, "epoch": 342.46017699115043, "percentage": 48.8, "elapsed_time": "2:20:14", "remaining_time": "2:27:08", "throughput": 1317.63, "total_tokens": 11087176} {"current_steps": 19525, "total_steps": 40000, "loss": 0.0, "lr": 2.5934406119213928e-05, "epoch": 342.5486725663717, "percentage": 48.81, "elapsed_time": "2:20:16", "remaining_time": "2:27:06", "throughput": 1317.62, "total_tokens": 11089848} {"current_steps": 19530, "total_steps": 40000, "loss": 0.0, "lr": 2.5924595430199193e-05, "epoch": 342.6371681415929, "percentage": 48.83, "elapsed_time": "2:20:18", "remaining_time": "2:27:03", "throughput": 1317.6, "total_tokens": 11092376} {"current_steps": 19535, "total_steps": 40000, "loss": 0.0, "lr": 2.5914784598600238e-05, "epoch": 342.72566371681415, "percentage": 48.84, "elapsed_time": "2:20:20", "remaining_time": "2:27:01", "throughput": 1317.6, "total_tokens": 11095128} {"current_steps": 19540, "total_steps": 40000, "loss": 0.0, "lr": 2.5904973625930002e-05, "epoch": 342.8141592920354, "percentage": 48.85, "elapsed_time": "2:20:22", "remaining_time": "2:26:59", "throughput": 1317.62, "total_tokens": 11098024} {"current_steps": 19545, "total_steps": 40000, "loss": 0.0, "lr": 2.5895162513701456e-05, "epoch": 342.9026548672566, "percentage": 48.86, "elapsed_time": "2:20:24", "remaining_time": "2:26:57", "throughput": 1317.65, "total_tokens": 11100968} {"current_steps": 19550, "total_steps": 40000, "loss": 0.0, "lr": 2.5885351263427593e-05, "epoch": 342.9911504424779, "percentage": 48.88, "elapsed_time": "2:20:26", "remaining_time": "2:26:54", "throughput": 1317.67, "total_tokens": 11103816} {"current_steps": 19555, "total_steps": 40000, "loss": 0.0, "lr": 2.5875539876621448e-05, "epoch": 343.070796460177, "percentage": 48.89, "elapsed_time": "2:20:29", "remaining_time": "2:26:52", "throughput": 1317.62, "total_tokens": 11106368} {"current_steps": 19560, "total_steps": 40000, "loss": 0.0, "lr": 2.586572835479605e-05, "epoch": 343.1592920353982, "percentage": 48.9, "elapsed_time": "2:20:31", "remaining_time": "2:26:50", "throughput": 1317.61, "total_tokens": 11109088} {"current_steps": 19565, "total_steps": 40000, "loss": 0.0, "lr": 2.585591669946446e-05, "epoch": 343.24778761061947, "percentage": 48.91, "elapsed_time": "2:20:33", "remaining_time": "2:26:48", "throughput": 1317.6, "total_tokens": 11111712} {"current_steps": 19570, "total_steps": 40000, "loss": 0.0, "lr": 2.5846104912139756e-05, "epoch": 343.3362831858407, "percentage": 48.93, "elapsed_time": "2:20:35", "remaining_time": "2:26:46", "throughput": 1317.61, "total_tokens": 11114560} {"current_steps": 19575, "total_steps": 40000, "loss": 0.0, "lr": 2.583629299433505e-05, "epoch": 343.42477876106193, "percentage": 48.94, "elapsed_time": "2:20:37", "remaining_time": "2:26:43", "throughput": 1317.65, "total_tokens": 11117568} {"current_steps": 19580, "total_steps": 40000, "loss": 0.0, "lr": 2.582648094756345e-05, "epoch": 343.5132743362832, "percentage": 48.95, "elapsed_time": "2:20:39", "remaining_time": "2:26:41", "throughput": 1317.65, "total_tokens": 11120320} {"current_steps": 19585, "total_steps": 40000, "loss": 0.0, "lr": 2.5816668773338098e-05, "epoch": 343.60176991150445, "percentage": 48.96, "elapsed_time": "2:20:41", "remaining_time": "2:26:39", "throughput": 1317.67, "total_tokens": 11123248} {"current_steps": 19590, "total_steps": 40000, "loss": 0.0, "lr": 2.580685647317216e-05, "epoch": 343.69026548672565, "percentage": 48.98, "elapsed_time": "2:20:43", "remaining_time": "2:26:37", "throughput": 1317.66, "total_tokens": 11125840} {"current_steps": 19595, "total_steps": 40000, "loss": 0.0, "lr": 2.5797044048578818e-05, "epoch": 343.7787610619469, "percentage": 48.99, "elapsed_time": "2:20:45", "remaining_time": "2:26:34", "throughput": 1317.67, "total_tokens": 11128672} {"current_steps": 19600, "total_steps": 40000, "loss": 0.0, "lr": 2.5787231501071262e-05, "epoch": 343.86725663716817, "percentage": 49.0, "elapsed_time": "2:20:47", "remaining_time": "2:26:32", "throughput": 1317.71, "total_tokens": 11131712} {"current_steps": 19600, "total_steps": 40000, "eval_loss": 0.6011966466903687, "epoch": 343.86725663716817, "percentage": 49.0, "elapsed_time": "2:20:48", "remaining_time": "2:26:33", "throughput": 1317.54, "total_tokens": 11131712} {"current_steps": 19605, "total_steps": 40000, "loss": 0.0, "lr": 2.577741883216272e-05, "epoch": 343.95575221238937, "percentage": 49.01, "elapsed_time": "2:20:52", "remaining_time": "2:26:33", "throughput": 1317.32, "total_tokens": 11134928} {"current_steps": 19610, "total_steps": 40000, "loss": 0.0, "lr": 2.576760604336642e-05, "epoch": 344.0353982300885, "percentage": 49.02, "elapsed_time": "2:20:54", "remaining_time": "2:26:31", "throughput": 1317.29, "total_tokens": 11137648} {"current_steps": 19615, "total_steps": 40000, "loss": 0.0, "lr": 2.575779313619563e-05, "epoch": 344.12389380530976, "percentage": 49.04, "elapsed_time": "2:20:57", "remaining_time": "2:26:29", "throughput": 1317.27, "total_tokens": 11140272} {"current_steps": 19620, "total_steps": 40000, "loss": 0.0, "lr": 2.5747980112163605e-05, "epoch": 344.21238938053096, "percentage": 49.05, "elapsed_time": "2:20:59", "remaining_time": "2:26:26", "throughput": 1317.26, "total_tokens": 11142896} {"current_steps": 19625, "total_steps": 40000, "loss": 0.0, "lr": 2.5738166972783656e-05, "epoch": 344.3008849557522, "percentage": 49.06, "elapsed_time": "2:21:01", "remaining_time": "2:26:24", "throughput": 1317.33, "total_tokens": 11146208} {"current_steps": 19630, "total_steps": 40000, "loss": 0.0, "lr": 2.5728353719569075e-05, "epoch": 344.3893805309734, "percentage": 49.08, "elapsed_time": "2:21:03", "remaining_time": "2:26:22", "throughput": 1317.41, "total_tokens": 11149584} {"current_steps": 19635, "total_steps": 40000, "loss": 0.0, "lr": 2.57185403540332e-05, "epoch": 344.4778761061947, "percentage": 49.09, "elapsed_time": "2:21:05", "remaining_time": "2:26:20", "throughput": 1317.39, "total_tokens": 11152160} {"current_steps": 19640, "total_steps": 40000, "loss": 0.0, "lr": 2.5708726877689375e-05, "epoch": 344.56637168141594, "percentage": 49.1, "elapsed_time": "2:21:07", "remaining_time": "2:26:17", "throughput": 1317.38, "total_tokens": 11154768} {"current_steps": 19645, "total_steps": 40000, "loss": 0.0, "lr": 2.5698913292050964e-05, "epoch": 344.65486725663715, "percentage": 49.11, "elapsed_time": "2:21:09", "remaining_time": "2:26:15", "throughput": 1317.37, "total_tokens": 11157456} {"current_steps": 19650, "total_steps": 40000, "loss": 0.0, "lr": 2.568909959863133e-05, "epoch": 344.7433628318584, "percentage": 49.12, "elapsed_time": "2:21:11", "remaining_time": "2:26:13", "throughput": 1317.42, "total_tokens": 11160576} {"current_steps": 19655, "total_steps": 40000, "loss": 0.0, "lr": 2.5679285798943887e-05, "epoch": 344.83185840707966, "percentage": 49.14, "elapsed_time": "2:21:13", "remaining_time": "2:26:11", "throughput": 1317.44, "total_tokens": 11163520} {"current_steps": 19660, "total_steps": 40000, "loss": 0.0, "lr": 2.5669471894502035e-05, "epoch": 344.92035398230087, "percentage": 49.15, "elapsed_time": "2:21:15", "remaining_time": "2:26:08", "throughput": 1317.43, "total_tokens": 11166160} {"current_steps": 19665, "total_steps": 40000, "loss": 0.0, "lr": 2.56596578868192e-05, "epoch": 345.0, "percentage": 49.16, "elapsed_time": "2:21:17", "remaining_time": "2:26:06", "throughput": 1317.39, "total_tokens": 11168448} {"current_steps": 19670, "total_steps": 40000, "loss": 0.0, "lr": 2.564984377740883e-05, "epoch": 345.08849557522126, "percentage": 49.18, "elapsed_time": "2:21:20", "remaining_time": "2:26:04", "throughput": 1317.33, "total_tokens": 11170944} {"current_steps": 19675, "total_steps": 40000, "loss": 0.0, "lr": 2.564002956778438e-05, "epoch": 345.17699115044246, "percentage": 49.19, "elapsed_time": "2:21:22", "remaining_time": "2:26:02", "throughput": 1317.32, "total_tokens": 11173616} {"current_steps": 19680, "total_steps": 40000, "loss": 0.0, "lr": 2.563021525945934e-05, "epoch": 345.2654867256637, "percentage": 49.2, "elapsed_time": "2:21:24", "remaining_time": "2:26:00", "throughput": 1317.32, "total_tokens": 11176368} {"current_steps": 19685, "total_steps": 40000, "loss": 0.0, "lr": 2.562040085394718e-05, "epoch": 345.353982300885, "percentage": 49.21, "elapsed_time": "2:21:26", "remaining_time": "2:25:57", "throughput": 1317.36, "total_tokens": 11179408} {"current_steps": 19690, "total_steps": 40000, "loss": 0.0, "lr": 2.56105863527614e-05, "epoch": 345.4424778761062, "percentage": 49.23, "elapsed_time": "2:21:28", "remaining_time": "2:25:55", "throughput": 1317.38, "total_tokens": 11182304} {"current_steps": 19695, "total_steps": 40000, "loss": 0.0, "lr": 2.5600771757415548e-05, "epoch": 345.53097345132744, "percentage": 49.24, "elapsed_time": "2:21:30", "remaining_time": "2:25:53", "throughput": 1317.45, "total_tokens": 11185616} {"current_steps": 19700, "total_steps": 40000, "loss": 0.0, "lr": 2.5590957069423134e-05, "epoch": 345.6194690265487, "percentage": 49.25, "elapsed_time": "2:21:32", "remaining_time": "2:25:51", "throughput": 1317.48, "total_tokens": 11188656} {"current_steps": 19705, "total_steps": 40000, "loss": 0.0, "lr": 2.5581142290297716e-05, "epoch": 345.7079646017699, "percentage": 49.26, "elapsed_time": "2:21:34", "remaining_time": "2:25:48", "throughput": 1317.52, "total_tokens": 11191712} {"current_steps": 19710, "total_steps": 40000, "loss": 0.0, "lr": 2.557132742155285e-05, "epoch": 345.79646017699116, "percentage": 49.28, "elapsed_time": "2:21:36", "remaining_time": "2:25:46", "throughput": 1317.53, "total_tokens": 11194480} {"current_steps": 19715, "total_steps": 40000, "loss": 0.0, "lr": 2.556151246470212e-05, "epoch": 345.88495575221236, "percentage": 49.29, "elapsed_time": "2:21:38", "remaining_time": "2:25:44", "throughput": 1317.56, "total_tokens": 11197456} {"current_steps": 19720, "total_steps": 40000, "loss": 0.0, "lr": 2.5551697421259114e-05, "epoch": 345.9734513274336, "percentage": 49.3, "elapsed_time": "2:21:40", "remaining_time": "2:25:42", "throughput": 1317.58, "total_tokens": 11200352} {"current_steps": 19725, "total_steps": 40000, "loss": 0.0, "lr": 2.554188229273743e-05, "epoch": 346.05309734513276, "percentage": 49.31, "elapsed_time": "2:21:42", "remaining_time": "2:25:40", "throughput": 1317.48, "total_tokens": 11202480} {"current_steps": 19730, "total_steps": 40000, "loss": 0.0, "lr": 2.5532067080650678e-05, "epoch": 346.14159292035396, "percentage": 49.33, "elapsed_time": "2:21:45", "remaining_time": "2:25:37", "throughput": 1317.46, "total_tokens": 11204992} {"current_steps": 19735, "total_steps": 40000, "loss": 0.0, "lr": 2.55222517865125e-05, "epoch": 346.2300884955752, "percentage": 49.34, "elapsed_time": "2:21:47", "remaining_time": "2:25:35", "throughput": 1317.51, "total_tokens": 11208208} {"current_steps": 19740, "total_steps": 40000, "loss": 0.0, "lr": 2.5512436411836538e-05, "epoch": 346.3185840707965, "percentage": 49.35, "elapsed_time": "2:21:49", "remaining_time": "2:25:33", "throughput": 1317.58, "total_tokens": 11211472} {"current_steps": 19745, "total_steps": 40000, "loss": 0.0, "lr": 2.5502620958136443e-05, "epoch": 346.4070796460177, "percentage": 49.36, "elapsed_time": "2:21:51", "remaining_time": "2:25:31", "throughput": 1317.63, "total_tokens": 11214624} {"current_steps": 19750, "total_steps": 40000, "loss": 0.0, "lr": 2.5492805426925874e-05, "epoch": 346.49557522123894, "percentage": 49.38, "elapsed_time": "2:21:53", "remaining_time": "2:25:28", "throughput": 1317.6, "total_tokens": 11217072} {"current_steps": 19755, "total_steps": 40000, "loss": 0.0, "lr": 2.5482989819718523e-05, "epoch": 346.5840707964602, "percentage": 49.39, "elapsed_time": "2:21:55", "remaining_time": "2:25:26", "throughput": 1317.65, "total_tokens": 11220288} {"current_steps": 19760, "total_steps": 40000, "loss": 0.0, "lr": 2.5473174138028065e-05, "epoch": 346.6725663716814, "percentage": 49.4, "elapsed_time": "2:21:57", "remaining_time": "2:25:24", "throughput": 1317.64, "total_tokens": 11222928} {"current_steps": 19765, "total_steps": 40000, "loss": 0.0, "lr": 2.5463358383368212e-05, "epoch": 346.76106194690266, "percentage": 49.41, "elapsed_time": "2:21:59", "remaining_time": "2:25:22", "throughput": 1317.67, "total_tokens": 11225856} {"current_steps": 19770, "total_steps": 40000, "loss": 0.0, "lr": 2.545354255725267e-05, "epoch": 346.8495575221239, "percentage": 49.43, "elapsed_time": "2:22:01", "remaining_time": "2:25:19", "throughput": 1317.67, "total_tokens": 11228656} {"current_steps": 19775, "total_steps": 40000, "loss": 0.0, "lr": 2.5443726661195165e-05, "epoch": 346.9380530973451, "percentage": 49.44, "elapsed_time": "2:22:03", "remaining_time": "2:25:17", "throughput": 1317.72, "total_tokens": 11231744} {"current_steps": 19780, "total_steps": 40000, "loss": 0.0, "lr": 2.543391069670944e-05, "epoch": 347.01769911504425, "percentage": 49.45, "elapsed_time": "2:22:05", "remaining_time": "2:25:15", "throughput": 1317.62, "total_tokens": 11233888} {"current_steps": 19785, "total_steps": 40000, "loss": 0.0, "lr": 2.5424094665309228e-05, "epoch": 347.1061946902655, "percentage": 49.46, "elapsed_time": "2:22:07", "remaining_time": "2:25:13", "throughput": 1317.61, "total_tokens": 11236544} {"current_steps": 19790, "total_steps": 40000, "loss": 0.0, "lr": 2.5414278568508292e-05, "epoch": 347.1946902654867, "percentage": 49.48, "elapsed_time": "2:22:10", "remaining_time": "2:25:11", "throughput": 1317.62, "total_tokens": 11239392} {"current_steps": 19795, "total_steps": 40000, "loss": 0.0, "lr": 2.540446240782039e-05, "epoch": 347.283185840708, "percentage": 49.49, "elapsed_time": "2:22:12", "remaining_time": "2:25:08", "throughput": 1317.72, "total_tokens": 11242960} {"current_steps": 19800, "total_steps": 40000, "loss": 0.0, "lr": 2.5394646184759307e-05, "epoch": 347.37168141592923, "percentage": 49.5, "elapsed_time": "2:22:14", "remaining_time": "2:25:06", "throughput": 1317.73, "total_tokens": 11245728} {"current_steps": 19800, "total_steps": 40000, "eval_loss": 0.5383446216583252, "epoch": 347.37168141592923, "percentage": 49.5, "elapsed_time": "2:22:15", "remaining_time": "2:25:07", "throughput": 1317.56, "total_tokens": 11245728} {"current_steps": 19805, "total_steps": 40000, "loss": 0.0, "lr": 2.538482990083882e-05, "epoch": 347.46017699115043, "percentage": 49.51, "elapsed_time": "2:22:19", "remaining_time": "2:25:07", "throughput": 1317.31, "total_tokens": 11248576} {"current_steps": 19810, "total_steps": 40000, "loss": 0.0, "lr": 2.5375013557572725e-05, "epoch": 347.5486725663717, "percentage": 49.53, "elapsed_time": "2:22:21", "remaining_time": "2:25:04", "throughput": 1317.3, "total_tokens": 11251264} {"current_steps": 19815, "total_steps": 40000, "loss": 0.0, "lr": 2.536519715647483e-05, "epoch": 347.6371681415929, "percentage": 49.54, "elapsed_time": "2:22:23", "remaining_time": "2:25:02", "throughput": 1317.34, "total_tokens": 11254272} {"current_steps": 19820, "total_steps": 40000, "loss": 0.0, "lr": 2.535538069905894e-05, "epoch": 347.72566371681415, "percentage": 49.55, "elapsed_time": "2:22:25", "remaining_time": "2:25:00", "throughput": 1317.34, "total_tokens": 11257008} {"current_steps": 19825, "total_steps": 40000, "loss": 0.0, "lr": 2.534556418683888e-05, "epoch": 347.8141592920354, "percentage": 49.56, "elapsed_time": "2:22:27", "remaining_time": "2:24:58", "throughput": 1317.34, "total_tokens": 11259760} {"current_steps": 19830, "total_steps": 40000, "loss": 0.0, "lr": 2.5335747621328486e-05, "epoch": 347.9026548672566, "percentage": 49.58, "elapsed_time": "2:22:29", "remaining_time": "2:24:55", "throughput": 1317.37, "total_tokens": 11262688} {"current_steps": 19835, "total_steps": 40000, "loss": 0.0, "lr": 2.5325931004041586e-05, "epoch": 347.9911504424779, "percentage": 49.59, "elapsed_time": "2:22:31", "remaining_time": "2:24:53", "throughput": 1317.36, "total_tokens": 11265312} {"current_steps": 19840, "total_steps": 40000, "loss": 0.0, "lr": 2.5316114336492032e-05, "epoch": 348.070796460177, "percentage": 49.6, "elapsed_time": "2:22:33", "remaining_time": "2:24:51", "throughput": 1317.31, "total_tokens": 11267912} {"current_steps": 19845, "total_steps": 40000, "loss": 0.0, "lr": 2.530629762019367e-05, "epoch": 348.1592920353982, "percentage": 49.61, "elapsed_time": "2:22:35", "remaining_time": "2:24:49", "throughput": 1317.3, "total_tokens": 11270536} {"current_steps": 19850, "total_steps": 40000, "loss": 0.0, "lr": 2.5296480856660364e-05, "epoch": 348.24778761061947, "percentage": 49.62, "elapsed_time": "2:22:37", "remaining_time": "2:24:47", "throughput": 1317.33, "total_tokens": 11273512} {"current_steps": 19855, "total_steps": 40000, "loss": 0.0, "lr": 2.528666404740599e-05, "epoch": 348.3362831858407, "percentage": 49.64, "elapsed_time": "2:22:39", "remaining_time": "2:24:44", "throughput": 1317.35, "total_tokens": 11276392} {"current_steps": 19860, "total_steps": 40000, "loss": 0.0, "lr": 2.527684719394442e-05, "epoch": 348.42477876106193, "percentage": 49.65, "elapsed_time": "2:22:41", "remaining_time": "2:24:42", "throughput": 1317.39, "total_tokens": 11279480} {"current_steps": 19865, "total_steps": 40000, "loss": 0.0, "lr": 2.526703029778953e-05, "epoch": 348.5132743362832, "percentage": 49.66, "elapsed_time": "2:22:44", "remaining_time": "2:24:40", "throughput": 1317.38, "total_tokens": 11282088} {"current_steps": 19870, "total_steps": 40000, "loss": 0.0, "lr": 2.5257213360455208e-05, "epoch": 348.60176991150445, "percentage": 49.68, "elapsed_time": "2:22:46", "remaining_time": "2:24:38", "throughput": 1317.44, "total_tokens": 11285400} {"current_steps": 19875, "total_steps": 40000, "loss": 0.0, "lr": 2.5247396383455353e-05, "epoch": 348.69026548672565, "percentage": 49.69, "elapsed_time": "2:22:48", "remaining_time": "2:24:35", "throughput": 1317.47, "total_tokens": 11288392} {"current_steps": 19880, "total_steps": 40000, "loss": 0.0, "lr": 2.523757936830387e-05, "epoch": 348.7787610619469, "percentage": 49.7, "elapsed_time": "2:22:50", "remaining_time": "2:24:33", "throughput": 1317.48, "total_tokens": 11291192} {"current_steps": 19885, "total_steps": 40000, "loss": 0.0, "lr": 2.5227762316514662e-05, "epoch": 348.86725663716817, "percentage": 49.71, "elapsed_time": "2:22:52", "remaining_time": "2:24:31", "throughput": 1317.46, "total_tokens": 11293768} {"current_steps": 19890, "total_steps": 40000, "loss": 0.0, "lr": 2.5217945229601648e-05, "epoch": 348.95575221238937, "percentage": 49.73, "elapsed_time": "2:22:54", "remaining_time": "2:24:29", "throughput": 1317.52, "total_tokens": 11296952} {"current_steps": 19895, "total_steps": 40000, "loss": 0.0, "lr": 2.5208128109078738e-05, "epoch": 349.0353982300885, "percentage": 49.74, "elapsed_time": "2:22:56", "remaining_time": "2:24:27", "throughput": 1317.44, "total_tokens": 11299280} {"current_steps": 19900, "total_steps": 40000, "loss": 0.0, "lr": 2.5198310956459853e-05, "epoch": 349.12389380530976, "percentage": 49.75, "elapsed_time": "2:22:58", "remaining_time": "2:24:24", "throughput": 1317.49, "total_tokens": 11302400} {"current_steps": 19905, "total_steps": 40000, "loss": 0.0, "lr": 2.518849377325893e-05, "epoch": 349.21238938053096, "percentage": 49.76, "elapsed_time": "2:23:00", "remaining_time": "2:24:22", "throughput": 1317.48, "total_tokens": 11305104} {"current_steps": 19910, "total_steps": 40000, "loss": 0.0, "lr": 2.51786765609899e-05, "epoch": 349.3008849557522, "percentage": 49.78, "elapsed_time": "2:23:02", "remaining_time": "2:24:20", "throughput": 1317.54, "total_tokens": 11308352} {"current_steps": 19915, "total_steps": 40000, "loss": 0.0, "lr": 2.5168859321166694e-05, "epoch": 349.3893805309734, "percentage": 49.79, "elapsed_time": "2:23:04", "remaining_time": "2:24:18", "throughput": 1317.57, "total_tokens": 11311328} {"current_steps": 19920, "total_steps": 40000, "loss": 0.0, "lr": 2.515904205530326e-05, "epoch": 349.4778761061947, "percentage": 49.8, "elapsed_time": "2:23:07", "remaining_time": "2:24:16", "throughput": 1317.52, "total_tokens": 11313552} {"current_steps": 19925, "total_steps": 40000, "loss": 0.0, "lr": 2.514922476491355e-05, "epoch": 349.56637168141594, "percentage": 49.81, "elapsed_time": "2:23:09", "remaining_time": "2:24:13", "throughput": 1317.54, "total_tokens": 11316496} {"current_steps": 19930, "total_steps": 40000, "loss": 0.0, "lr": 2.51394074515115e-05, "epoch": 349.65486725663715, "percentage": 49.83, "elapsed_time": "2:23:11", "remaining_time": "2:24:11", "throughput": 1317.51, "total_tokens": 11318912} {"current_steps": 19935, "total_steps": 40000, "loss": 0.0, "lr": 2.5129590116611067e-05, "epoch": 349.7433628318584, "percentage": 49.84, "elapsed_time": "2:23:13", "remaining_time": "2:24:09", "throughput": 1317.6, "total_tokens": 11322416} {"current_steps": 19940, "total_steps": 40000, "loss": 0.0, "lr": 2.5119772761726212e-05, "epoch": 349.83185840707966, "percentage": 49.85, "elapsed_time": "2:23:15", "remaining_time": "2:24:07", "throughput": 1317.61, "total_tokens": 11325248} {"current_steps": 19945, "total_steps": 40000, "loss": 0.0, "lr": 2.5109955388370893e-05, "epoch": 349.92035398230087, "percentage": 49.86, "elapsed_time": "2:23:17", "remaining_time": "2:24:04", "throughput": 1317.6, "total_tokens": 11327872} {"current_steps": 19950, "total_steps": 40000, "loss": 0.0, "lr": 2.510013799805907e-05, "epoch": 350.0, "percentage": 49.88, "elapsed_time": "2:23:19", "remaining_time": "2:24:02", "throughput": 1317.6, "total_tokens": 11330576} {"current_steps": 19955, "total_steps": 40000, "loss": 0.0, "lr": 2.5090320592304706e-05, "epoch": 350.08849557522126, "percentage": 49.89, "elapsed_time": "2:23:21", "remaining_time": "2:24:00", "throughput": 1317.56, "total_tokens": 11333232} {"current_steps": 19960, "total_steps": 40000, "loss": 0.0, "lr": 2.5080503172621777e-05, "epoch": 350.17699115044246, "percentage": 49.9, "elapsed_time": "2:23:23", "remaining_time": "2:23:58", "throughput": 1317.56, "total_tokens": 11335952} {"current_steps": 19965, "total_steps": 40000, "loss": 0.0, "lr": 2.5070685740524246e-05, "epoch": 350.2654867256637, "percentage": 49.91, "elapsed_time": "2:23:25", "remaining_time": "2:23:56", "throughput": 1317.61, "total_tokens": 11339136} {"current_steps": 19970, "total_steps": 40000, "loss": 0.0, "lr": 2.5060868297526084e-05, "epoch": 350.353982300885, "percentage": 49.93, "elapsed_time": "2:23:27", "remaining_time": "2:23:53", "throughput": 1317.58, "total_tokens": 11341648} {"current_steps": 19975, "total_steps": 40000, "loss": 0.0, "lr": 2.5051050845141267e-05, "epoch": 350.4424778761062, "percentage": 49.94, "elapsed_time": "2:23:30", "remaining_time": "2:23:51", "throughput": 1317.57, "total_tokens": 11344272} {"current_steps": 19980, "total_steps": 40000, "loss": 0.0, "lr": 2.5041233384883765e-05, "epoch": 350.53097345132744, "percentage": 49.95, "elapsed_time": "2:23:32", "remaining_time": "2:23:49", "throughput": 1317.56, "total_tokens": 11346896} {"current_steps": 19985, "total_steps": 40000, "loss": 0.0, "lr": 2.5031415918267564e-05, "epoch": 350.6194690265487, "percentage": 49.96, "elapsed_time": "2:23:34", "remaining_time": "2:23:47", "throughput": 1317.59, "total_tokens": 11349904} {"current_steps": 19990, "total_steps": 40000, "loss": 0.0, "lr": 2.5021598446806626e-05, "epoch": 350.7079646017699, "percentage": 49.98, "elapsed_time": "2:23:36", "remaining_time": "2:23:44", "throughput": 1317.6, "total_tokens": 11352720} {"current_steps": 19995, "total_steps": 40000, "loss": 0.0, "lr": 2.5011780972014937e-05, "epoch": 350.79646017699116, "percentage": 49.99, "elapsed_time": "2:23:38", "remaining_time": "2:23:42", "throughput": 1317.7, "total_tokens": 11356320} {"current_steps": 20000, "total_steps": 40000, "loss": 0.0, "lr": 2.5001963495406478e-05, "epoch": 350.88495575221236, "percentage": 50.0, "elapsed_time": "2:23:40", "remaining_time": "2:23:40", "throughput": 1317.67, "total_tokens": 11358800} {"current_steps": 20000, "total_steps": 40000, "eval_loss": 0.538743257522583, "epoch": 350.88495575221236, "percentage": 50.0, "elapsed_time": "2:23:41", "remaining_time": "2:23:41", "throughput": 1317.51, "total_tokens": 11358800} {"current_steps": 20005, "total_steps": 40000, "loss": 0.0, "lr": 2.499214601849522e-05, "epoch": 350.9734513274336, "percentage": 50.01, "elapsed_time": "2:23:45", "remaining_time": "2:23:41", "throughput": 1317.28, "total_tokens": 11362048} {"current_steps": 20010, "total_steps": 40000, "loss": 0.0, "lr": 2.4982328542795148e-05, "epoch": 351.05309734513276, "percentage": 50.02, "elapsed_time": "2:23:47", "remaining_time": "2:23:39", "throughput": 1317.21, "total_tokens": 11364464} {"current_steps": 20015, "total_steps": 40000, "loss": 0.0, "lr": 2.497251106982024e-05, "epoch": 351.14159292035396, "percentage": 50.04, "elapsed_time": "2:23:49", "remaining_time": "2:23:36", "throughput": 1317.23, "total_tokens": 11367328} {"current_steps": 20020, "total_steps": 40000, "loss": 0.0, "lr": 2.4962693601084458e-05, "epoch": 351.2300884955752, "percentage": 50.05, "elapsed_time": "2:23:52", "remaining_time": "2:23:34", "throughput": 1317.22, "total_tokens": 11370336} {"current_steps": 20025, "total_steps": 40000, "loss": 0.0, "lr": 2.4952876138101794e-05, "epoch": 351.3185840707965, "percentage": 50.06, "elapsed_time": "2:23:54", "remaining_time": "2:23:32", "throughput": 1317.23, "total_tokens": 11373200} {"current_steps": 20030, "total_steps": 40000, "loss": 0.0, "lr": 2.4943058682386233e-05, "epoch": 351.4070796460177, "percentage": 50.08, "elapsed_time": "2:23:56", "remaining_time": "2:23:30", "throughput": 1317.23, "total_tokens": 11375888} {"current_steps": 20035, "total_steps": 40000, "loss": 0.0, "lr": 2.493324123545173e-05, "epoch": 351.49557522123894, "percentage": 50.09, "elapsed_time": "2:23:58", "remaining_time": "2:23:28", "throughput": 1317.29, "total_tokens": 11379152} {"current_steps": 20040, "total_steps": 40000, "loss": 0.0, "lr": 2.4923423798812272e-05, "epoch": 351.5840707964602, "percentage": 50.1, "elapsed_time": "2:24:00", "remaining_time": "2:23:25", "throughput": 1317.34, "total_tokens": 11382288} {"current_steps": 20045, "total_steps": 40000, "loss": 0.0, "lr": 2.4913606373981825e-05, "epoch": 351.6725663716814, "percentage": 50.11, "elapsed_time": "2:24:02", "remaining_time": "2:23:23", "throughput": 1317.37, "total_tokens": 11385344} {"current_steps": 20050, "total_steps": 40000, "loss": 0.0, "lr": 2.4903788962474357e-05, "epoch": 351.76106194690266, "percentage": 50.12, "elapsed_time": "2:24:04", "remaining_time": "2:23:21", "throughput": 1317.36, "total_tokens": 11387920} {"current_steps": 20055, "total_steps": 40000, "loss": 0.0, "lr": 2.489397156580385e-05, "epoch": 351.8495575221239, "percentage": 50.14, "elapsed_time": "2:24:06", "remaining_time": "2:23:19", "throughput": 1317.37, "total_tokens": 11390768} {"current_steps": 20060, "total_steps": 40000, "loss": 0.0, "lr": 2.4884154185484246e-05, "epoch": 351.9380530973451, "percentage": 50.15, "elapsed_time": "2:24:08", "remaining_time": "2:23:16", "throughput": 1317.37, "total_tokens": 11393536} {"current_steps": 20065, "total_steps": 40000, "loss": 0.0, "lr": 2.4874336823029526e-05, "epoch": 352.01769911504425, "percentage": 50.16, "elapsed_time": "2:24:10", "remaining_time": "2:23:14", "throughput": 1317.35, "total_tokens": 11396296} {"current_steps": 20070, "total_steps": 40000, "loss": 0.0, "lr": 2.4864519479953656e-05, "epoch": 352.1061946902655, "percentage": 50.18, "elapsed_time": "2:24:13", "remaining_time": "2:23:12", "throughput": 1317.32, "total_tokens": 11398824} {"current_steps": 20075, "total_steps": 40000, "loss": 0.0, "lr": 2.485470215777058e-05, "epoch": 352.1946902654867, "percentage": 50.19, "elapsed_time": "2:24:15", "remaining_time": "2:23:10", "throughput": 1317.32, "total_tokens": 11401512} {"current_steps": 20080, "total_steps": 40000, "loss": 0.0, "lr": 2.4844884857994258e-05, "epoch": 352.283185840708, "percentage": 50.2, "elapsed_time": "2:24:17", "remaining_time": "2:23:08", "throughput": 1317.32, "total_tokens": 11404296} {"current_steps": 20085, "total_steps": 40000, "loss": 0.0, "lr": 2.4835067582138638e-05, "epoch": 352.37168141592923, "percentage": 50.21, "elapsed_time": "2:24:19", "remaining_time": "2:23:05", "throughput": 1317.39, "total_tokens": 11407624} {"current_steps": 20090, "total_steps": 40000, "loss": 0.0, "lr": 2.4825250331717666e-05, "epoch": 352.46017699115043, "percentage": 50.22, "elapsed_time": "2:24:21", "remaining_time": "2:23:03", "throughput": 1317.47, "total_tokens": 11410984} {"current_steps": 20095, "total_steps": 40000, "loss": 0.0, "lr": 2.4815433108245298e-05, "epoch": 352.5486725663717, "percentage": 50.24, "elapsed_time": "2:24:23", "remaining_time": "2:23:01", "throughput": 1317.43, "total_tokens": 11413432} {"current_steps": 20100, "total_steps": 40000, "loss": 0.0, "lr": 2.4805615913235456e-05, "epoch": 352.6371681415929, "percentage": 50.25, "elapsed_time": "2:24:25", "remaining_time": "2:22:59", "throughput": 1317.47, "total_tokens": 11416440} {"current_steps": 20105, "total_steps": 40000, "loss": 0.0, "lr": 2.479579874820208e-05, "epoch": 352.72566371681415, "percentage": 50.26, "elapsed_time": "2:24:27", "remaining_time": "2:22:56", "throughput": 1317.5, "total_tokens": 11419496} {"current_steps": 20110, "total_steps": 40000, "loss": 0.0, "lr": 2.4785981614659115e-05, "epoch": 352.8141592920354, "percentage": 50.28, "elapsed_time": "2:24:29", "remaining_time": "2:22:54", "throughput": 1317.52, "total_tokens": 11422424} {"current_steps": 20115, "total_steps": 40000, "loss": 0.0, "lr": 2.477616451412047e-05, "epoch": 352.9026548672566, "percentage": 50.29, "elapsed_time": "2:24:31", "remaining_time": "2:22:52", "throughput": 1317.56, "total_tokens": 11425432} {"current_steps": 20120, "total_steps": 40000, "loss": 0.0, "lr": 2.476634744810007e-05, "epoch": 352.9911504424779, "percentage": 50.3, "elapsed_time": "2:24:33", "remaining_time": "2:22:50", "throughput": 1317.54, "total_tokens": 11427976} {"current_steps": 20125, "total_steps": 40000, "loss": 0.0, "lr": 2.475653041811183e-05, "epoch": 353.070796460177, "percentage": 50.31, "elapsed_time": "2:24:35", "remaining_time": "2:22:48", "throughput": 1317.45, "total_tokens": 11430200} {"current_steps": 20130, "total_steps": 40000, "loss": 0.0, "lr": 2.4746713425669652e-05, "epoch": 353.1592920353982, "percentage": 50.32, "elapsed_time": "2:24:38", "remaining_time": "2:22:45", "throughput": 1317.45, "total_tokens": 11432936} {"current_steps": 20135, "total_steps": 40000, "loss": 0.0, "lr": 2.4736896472287458e-05, "epoch": 353.24778761061947, "percentage": 50.34, "elapsed_time": "2:24:40", "remaining_time": "2:22:43", "throughput": 1317.43, "total_tokens": 11435432} {"current_steps": 20140, "total_steps": 40000, "loss": 0.0, "lr": 2.4727079559479124e-05, "epoch": 353.3362831858407, "percentage": 50.35, "elapsed_time": "2:24:42", "remaining_time": "2:22:41", "throughput": 1317.42, "total_tokens": 11438088} {"current_steps": 20145, "total_steps": 40000, "loss": 0.0, "lr": 2.4717262688758557e-05, "epoch": 353.42477876106193, "percentage": 50.36, "elapsed_time": "2:24:44", "remaining_time": "2:22:39", "throughput": 1317.46, "total_tokens": 11441128} {"current_steps": 20150, "total_steps": 40000, "loss": 0.0, "lr": 2.4707445861639637e-05, "epoch": 353.5132743362832, "percentage": 50.38, "elapsed_time": "2:24:46", "remaining_time": "2:22:37", "throughput": 1317.5, "total_tokens": 11444248} {"current_steps": 20155, "total_steps": 40000, "loss": 0.0, "lr": 2.4697629079636244e-05, "epoch": 353.60176991150445, "percentage": 50.39, "elapsed_time": "2:24:48", "remaining_time": "2:22:34", "throughput": 1317.54, "total_tokens": 11447304} {"current_steps": 20160, "total_steps": 40000, "loss": 0.0, "lr": 2.4687812344262244e-05, "epoch": 353.69026548672565, "percentage": 50.4, "elapsed_time": "2:24:50", "remaining_time": "2:22:32", "throughput": 1317.61, "total_tokens": 11450680} {"current_steps": 20165, "total_steps": 40000, "loss": 0.0, "lr": 2.46779956570315e-05, "epoch": 353.7787610619469, "percentage": 50.41, "elapsed_time": "2:24:52", "remaining_time": "2:22:30", "throughput": 1317.57, "total_tokens": 11453080} {"current_steps": 20170, "total_steps": 40000, "loss": 0.0, "lr": 2.466817901945787e-05, "epoch": 353.86725663716817, "percentage": 50.42, "elapsed_time": "2:24:54", "remaining_time": "2:22:28", "throughput": 1317.63, "total_tokens": 11456312} {"current_steps": 20175, "total_steps": 40000, "loss": 0.0, "lr": 2.4658362433055217e-05, "epoch": 353.95575221238937, "percentage": 50.44, "elapsed_time": "2:24:56", "remaining_time": "2:22:25", "throughput": 1317.67, "total_tokens": 11459368} {"current_steps": 20180, "total_steps": 40000, "loss": 0.0, "lr": 2.4648545899337356e-05, "epoch": 354.0353982300885, "percentage": 50.45, "elapsed_time": "2:24:58", "remaining_time": "2:22:23", "throughput": 1317.58, "total_tokens": 11461496} {"current_steps": 20185, "total_steps": 40000, "loss": 0.0, "lr": 2.4638729419818143e-05, "epoch": 354.12389380530976, "percentage": 50.46, "elapsed_time": "2:25:01", "remaining_time": "2:22:21", "throughput": 1317.56, "total_tokens": 11464104} {"current_steps": 20190, "total_steps": 40000, "loss": 0.0, "lr": 2.46289129960114e-05, "epoch": 354.21238938053096, "percentage": 50.48, "elapsed_time": "2:25:03", "remaining_time": "2:22:19", "throughput": 1317.57, "total_tokens": 11466936} {"current_steps": 20195, "total_steps": 40000, "loss": 0.0, "lr": 2.4619096629430924e-05, "epoch": 354.3008849557522, "percentage": 50.49, "elapsed_time": "2:25:05", "remaining_time": "2:22:17", "throughput": 1317.53, "total_tokens": 11469336} {"current_steps": 20200, "total_steps": 40000, "loss": 0.0, "lr": 2.4609280321590543e-05, "epoch": 354.3893805309734, "percentage": 50.5, "elapsed_time": "2:25:07", "remaining_time": "2:22:14", "throughput": 1317.51, "total_tokens": 11471832} {"current_steps": 20200, "total_steps": 40000, "eval_loss": 0.5425193905830383, "epoch": 354.3893805309734, "percentage": 50.5, "elapsed_time": "2:25:08", "remaining_time": "2:22:15", "throughput": 1317.35, "total_tokens": 11471832} {"current_steps": 20205, "total_steps": 40000, "loss": 0.0, "lr": 2.4599464074004037e-05, "epoch": 354.4778761061947, "percentage": 50.51, "elapsed_time": "2:25:12", "remaining_time": "2:22:15", "throughput": 1317.15, "total_tokens": 11475144} {"current_steps": 20210, "total_steps": 40000, "loss": 0.0, "lr": 2.4589647888185204e-05, "epoch": 354.56637168141594, "percentage": 50.52, "elapsed_time": "2:25:14", "remaining_time": "2:22:13", "throughput": 1317.18, "total_tokens": 11478120} {"current_steps": 20215, "total_steps": 40000, "loss": 0.0, "lr": 2.4579831765647836e-05, "epoch": 354.65486725663715, "percentage": 50.54, "elapsed_time": "2:25:16", "remaining_time": "2:22:10", "throughput": 1317.24, "total_tokens": 11481352} {"current_steps": 20220, "total_steps": 40000, "loss": 0.0, "lr": 2.4570015707905676e-05, "epoch": 354.7433628318584, "percentage": 50.55, "elapsed_time": "2:25:18", "remaining_time": "2:22:08", "throughput": 1317.28, "total_tokens": 11484456} {"current_steps": 20225, "total_steps": 40000, "loss": 0.0, "lr": 2.4560199716472508e-05, "epoch": 354.83185840707966, "percentage": 50.56, "elapsed_time": "2:25:20", "remaining_time": "2:22:06", "throughput": 1317.35, "total_tokens": 11487720} {"current_steps": 20230, "total_steps": 40000, "loss": 0.0, "lr": 2.455038379286207e-05, "epoch": 354.92035398230087, "percentage": 50.58, "elapsed_time": "2:25:22", "remaining_time": "2:22:04", "throughput": 1317.36, "total_tokens": 11490536} {"current_steps": 20235, "total_steps": 40000, "loss": 0.0, "lr": 2.4540567938588095e-05, "epoch": 355.0, "percentage": 50.59, "elapsed_time": "2:25:24", "remaining_time": "2:22:01", "throughput": 1317.32, "total_tokens": 11492832} {"current_steps": 20240, "total_steps": 40000, "loss": 0.0, "lr": 2.4530752155164328e-05, "epoch": 355.08849557522126, "percentage": 50.6, "elapsed_time": "2:25:26", "remaining_time": "2:21:59", "throughput": 1317.36, "total_tokens": 11496256} {"current_steps": 20245, "total_steps": 40000, "loss": 0.0, "lr": 2.4520936444104463e-05, "epoch": 355.17699115044246, "percentage": 50.61, "elapsed_time": "2:25:28", "remaining_time": "2:21:57", "throughput": 1317.37, "total_tokens": 11499040} {"current_steps": 20250, "total_steps": 40000, "loss": 0.0, "lr": 2.4511120806922218e-05, "epoch": 355.2654867256637, "percentage": 50.62, "elapsed_time": "2:25:30", "remaining_time": "2:21:55", "throughput": 1317.33, "total_tokens": 11501456} {"current_steps": 20255, "total_steps": 40000, "loss": 0.0, "lr": 2.45013052451313e-05, "epoch": 355.353982300885, "percentage": 50.64, "elapsed_time": "2:25:32", "remaining_time": "2:21:53", "throughput": 1317.37, "total_tokens": 11504528} {"current_steps": 20260, "total_steps": 40000, "loss": 0.0, "lr": 2.4491489760245376e-05, "epoch": 355.4424778761062, "percentage": 50.65, "elapsed_time": "2:25:35", "remaining_time": "2:21:50", "throughput": 1317.36, "total_tokens": 11507200} {"current_steps": 20265, "total_steps": 40000, "loss": 0.0, "lr": 2.4481674353778115e-05, "epoch": 355.53097345132744, "percentage": 50.66, "elapsed_time": "2:25:37", "remaining_time": "2:21:48", "throughput": 1317.38, "total_tokens": 11510096} {"current_steps": 20270, "total_steps": 40000, "loss": 0.0, "lr": 2.447185902724319e-05, "epoch": 355.6194690265487, "percentage": 50.68, "elapsed_time": "2:25:39", "remaining_time": "2:21:46", "throughput": 1317.41, "total_tokens": 11513056} {"current_steps": 20275, "total_steps": 40000, "loss": 0.0, "lr": 2.4462043782154233e-05, "epoch": 355.7079646017699, "percentage": 50.69, "elapsed_time": "2:25:41", "remaining_time": "2:21:44", "throughput": 1317.41, "total_tokens": 11515824} {"current_steps": 20280, "total_steps": 40000, "loss": 0.0, "lr": 2.4452228620024895e-05, "epoch": 355.79646017699116, "percentage": 50.7, "elapsed_time": "2:25:43", "remaining_time": "2:21:41", "throughput": 1317.47, "total_tokens": 11519072} {"current_steps": 20285, "total_steps": 40000, "loss": 0.0, "lr": 2.4442413542368776e-05, "epoch": 355.88495575221236, "percentage": 50.71, "elapsed_time": "2:25:45", "remaining_time": "2:21:39", "throughput": 1317.42, "total_tokens": 11521392} {"current_steps": 20290, "total_steps": 40000, "loss": 0.0, "lr": 2.4432598550699502e-05, "epoch": 355.9734513274336, "percentage": 50.72, "elapsed_time": "2:25:47", "remaining_time": "2:21:37", "throughput": 1317.42, "total_tokens": 11524080} {"current_steps": 20295, "total_steps": 40000, "loss": 0.0, "lr": 2.4422783646530663e-05, "epoch": 356.05309734513276, "percentage": 50.74, "elapsed_time": "2:25:49", "remaining_time": "2:21:35", "throughput": 1317.42, "total_tokens": 11527064} {"current_steps": 20300, "total_steps": 40000, "loss": 0.0, "lr": 2.441296883137584e-05, "epoch": 356.14159292035396, "percentage": 50.75, "elapsed_time": "2:25:51", "remaining_time": "2:21:33", "throughput": 1317.41, "total_tokens": 11529688} {"current_steps": 20305, "total_steps": 40000, "loss": 0.0, "lr": 2.4403154106748592e-05, "epoch": 356.2300884955752, "percentage": 50.76, "elapsed_time": "2:25:53", "remaining_time": "2:21:30", "throughput": 1317.42, "total_tokens": 11532456} {"current_steps": 20310, "total_steps": 40000, "loss": 0.0, "lr": 2.4393339474162494e-05, "epoch": 356.3185840707965, "percentage": 50.78, "elapsed_time": "2:25:55", "remaining_time": "2:21:28", "throughput": 1317.42, "total_tokens": 11535272} {"current_steps": 20315, "total_steps": 40000, "loss": 0.0, "lr": 2.4383524935131062e-05, "epoch": 356.4070796460177, "percentage": 50.79, "elapsed_time": "2:25:57", "remaining_time": "2:21:26", "throughput": 1317.41, "total_tokens": 11537848} {"current_steps": 20320, "total_steps": 40000, "loss": 0.0, "lr": 2.437371049116784e-05, "epoch": 356.49557522123894, "percentage": 50.8, "elapsed_time": "2:26:00", "remaining_time": "2:21:24", "throughput": 1317.48, "total_tokens": 11541256} {"current_steps": 20325, "total_steps": 40000, "loss": 0.0, "lr": 2.436389614378632e-05, "epoch": 356.5840707964602, "percentage": 50.81, "elapsed_time": "2:26:02", "remaining_time": "2:21:21", "throughput": 1317.49, "total_tokens": 11544008} {"current_steps": 20330, "total_steps": 40000, "loss": 0.0, "lr": 2.435408189450002e-05, "epoch": 356.6725663716814, "percentage": 50.82, "elapsed_time": "2:26:04", "remaining_time": "2:21:19", "throughput": 1317.51, "total_tokens": 11546904} {"current_steps": 20335, "total_steps": 40000, "loss": 0.0, "lr": 2.4344267744822406e-05, "epoch": 356.76106194690266, "percentage": 50.84, "elapsed_time": "2:26:06", "remaining_time": "2:21:17", "throughput": 1317.56, "total_tokens": 11550104} {"current_steps": 20340, "total_steps": 40000, "loss": 0.0, "lr": 2.4334453696266944e-05, "epoch": 356.8495575221239, "percentage": 50.85, "elapsed_time": "2:26:08", "remaining_time": "2:21:15", "throughput": 1317.6, "total_tokens": 11553176} {"current_steps": 20345, "total_steps": 40000, "loss": 0.0, "lr": 2.432463975034708e-05, "epoch": 356.9380530973451, "percentage": 50.86, "elapsed_time": "2:26:10", "remaining_time": "2:21:12", "throughput": 1317.62, "total_tokens": 11556024} {"current_steps": 20350, "total_steps": 40000, "loss": 0.0, "lr": 2.4314825908576265e-05, "epoch": 357.01769911504425, "percentage": 50.88, "elapsed_time": "2:26:12", "remaining_time": "2:21:10", "throughput": 1317.53, "total_tokens": 11558240} {"current_steps": 20355, "total_steps": 40000, "loss": 0.0, "lr": 2.4305012172467897e-05, "epoch": 357.1061946902655, "percentage": 50.89, "elapsed_time": "2:26:14", "remaining_time": "2:21:08", "throughput": 1317.58, "total_tokens": 11561456} {"current_steps": 20360, "total_steps": 40000, "loss": 0.0, "lr": 2.4295198543535393e-05, "epoch": 357.1946902654867, "percentage": 50.9, "elapsed_time": "2:26:16", "remaining_time": "2:21:06", "throughput": 1317.56, "total_tokens": 11563968} {"current_steps": 20365, "total_steps": 40000, "loss": 0.0, "lr": 2.4285385023292124e-05, "epoch": 357.283185840708, "percentage": 50.91, "elapsed_time": "2:26:18", "remaining_time": "2:21:04", "throughput": 1317.51, "total_tokens": 11566320} {"current_steps": 20370, "total_steps": 40000, "loss": 0.0, "lr": 2.427557161325147e-05, "epoch": 357.37168141592923, "percentage": 50.92, "elapsed_time": "2:26:20", "remaining_time": "2:21:01", "throughput": 1317.55, "total_tokens": 11569376} {"current_steps": 20375, "total_steps": 40000, "loss": 0.0, "lr": 2.4265758314926778e-05, "epoch": 357.46017699115043, "percentage": 50.94, "elapsed_time": "2:26:23", "remaining_time": "2:20:59", "throughput": 1317.58, "total_tokens": 11572320} {"current_steps": 20380, "total_steps": 40000, "loss": 0.0, "lr": 2.4255945129831373e-05, "epoch": 357.5486725663717, "percentage": 50.95, "elapsed_time": "2:26:25", "remaining_time": "2:20:57", "throughput": 1317.59, "total_tokens": 11575168} {"current_steps": 20385, "total_steps": 40000, "loss": 0.0, "lr": 2.4246132059478578e-05, "epoch": 357.6371681415929, "percentage": 50.96, "elapsed_time": "2:26:27", "remaining_time": "2:20:55", "throughput": 1317.58, "total_tokens": 11577792} {"current_steps": 20390, "total_steps": 40000, "loss": 0.0, "lr": 2.4236319105381706e-05, "epoch": 357.72566371681415, "percentage": 50.98, "elapsed_time": "2:26:29", "remaining_time": "2:20:53", "throughput": 1317.55, "total_tokens": 11580224} {"current_steps": 20395, "total_steps": 40000, "loss": 0.0, "lr": 2.422650626905401e-05, "epoch": 357.8141592920354, "percentage": 50.99, "elapsed_time": "2:26:31", "remaining_time": "2:20:50", "throughput": 1317.55, "total_tokens": 11583024} {"current_steps": 20400, "total_steps": 40000, "loss": 0.0, "lr": 2.4216693552008785e-05, "epoch": 357.9026548672566, "percentage": 51.0, "elapsed_time": "2:26:33", "remaining_time": "2:20:48", "throughput": 1317.62, "total_tokens": 11586368} {"current_steps": 20400, "total_steps": 40000, "eval_loss": 0.5417349338531494, "epoch": 357.9026548672566, "percentage": 51.0, "elapsed_time": "2:26:34", "remaining_time": "2:20:49", "throughput": 1317.46, "total_tokens": 11586368} {"current_steps": 20405, "total_steps": 40000, "loss": 0.0, "lr": 2.4206880955759247e-05, "epoch": 357.9911504424779, "percentage": 51.01, "elapsed_time": "2:26:38", "remaining_time": "2:20:49", "throughput": 1317.14, "total_tokens": 11589504} {"current_steps": 20410, "total_steps": 40000, "loss": 0.0, "lr": 2.419706848181863e-05, "epoch": 358.070796460177, "percentage": 51.02, "elapsed_time": "2:26:41", "remaining_time": "2:20:47", "throughput": 1317.09, "total_tokens": 11592016} {"current_steps": 20415, "total_steps": 40000, "loss": 0.0, "lr": 2.4187256131700153e-05, "epoch": 358.1592920353982, "percentage": 51.04, "elapsed_time": "2:26:43", "remaining_time": "2:20:45", "throughput": 1317.14, "total_tokens": 11595216} {"current_steps": 20420, "total_steps": 40000, "loss": 0.0, "lr": 2.4177443906916985e-05, "epoch": 358.24778761061947, "percentage": 51.05, "elapsed_time": "2:26:45", "remaining_time": "2:20:43", "throughput": 1317.11, "total_tokens": 11597664} {"current_steps": 20425, "total_steps": 40000, "loss": 0.0, "lr": 2.4167631808982303e-05, "epoch": 358.3362831858407, "percentage": 51.06, "elapsed_time": "2:26:47", "remaining_time": "2:20:40", "throughput": 1317.17, "total_tokens": 11600880} {"current_steps": 20430, "total_steps": 40000, "loss": 0.0, "lr": 2.4157819839409264e-05, "epoch": 358.42477876106193, "percentage": 51.08, "elapsed_time": "2:26:49", "remaining_time": "2:20:38", "throughput": 1317.17, "total_tokens": 11603632} {"current_steps": 20435, "total_steps": 40000, "loss": 0.0, "lr": 2.414800799971098e-05, "epoch": 358.5132743362832, "percentage": 51.09, "elapsed_time": "2:26:51", "remaining_time": "2:20:36", "throughput": 1317.16, "total_tokens": 11606288} {"current_steps": 20440, "total_steps": 40000, "loss": 0.0, "lr": 2.4138196291400582e-05, "epoch": 358.60176991150445, "percentage": 51.1, "elapsed_time": "2:26:53", "remaining_time": "2:20:34", "throughput": 1317.21, "total_tokens": 11609392} {"current_steps": 20445, "total_steps": 40000, "loss": 0.0, "lr": 2.412838471599114e-05, "epoch": 358.69026548672565, "percentage": 51.11, "elapsed_time": "2:26:55", "remaining_time": "2:20:31", "throughput": 1317.26, "total_tokens": 11612576} {"current_steps": 20450, "total_steps": 40000, "loss": 0.0, "lr": 2.411857327499572e-05, "epoch": 358.7787610619469, "percentage": 51.12, "elapsed_time": "2:26:57", "remaining_time": "2:20:29", "throughput": 1317.23, "total_tokens": 11615040} {"current_steps": 20455, "total_steps": 40000, "loss": 0.0, "lr": 2.410876196992739e-05, "epoch": 358.86725663716817, "percentage": 51.14, "elapsed_time": "2:26:59", "remaining_time": "2:20:27", "throughput": 1317.29, "total_tokens": 11618288} {"current_steps": 20460, "total_steps": 40000, "loss": 0.0, "lr": 2.4098950802299156e-05, "epoch": 358.95575221238937, "percentage": 51.15, "elapsed_time": "2:27:01", "remaining_time": "2:20:25", "throughput": 1317.29, "total_tokens": 11621008} {"current_steps": 20465, "total_steps": 40000, "loss": 0.0, "lr": 2.4089139773624027e-05, "epoch": 359.0353982300885, "percentage": 51.16, "elapsed_time": "2:27:04", "remaining_time": "2:20:23", "throughput": 1317.23, "total_tokens": 11623472} {"current_steps": 20470, "total_steps": 40000, "loss": 0.0, "lr": 2.4079328885415007e-05, "epoch": 359.12389380530976, "percentage": 51.18, "elapsed_time": "2:27:06", "remaining_time": "2:20:20", "throughput": 1317.23, "total_tokens": 11626176} {"current_steps": 20475, "total_steps": 40000, "loss": 0.0, "lr": 2.4069518139185036e-05, "epoch": 359.21238938053096, "percentage": 51.19, "elapsed_time": "2:27:08", "remaining_time": "2:20:18", "throughput": 1317.26, "total_tokens": 11629216} {"current_steps": 20480, "total_steps": 40000, "loss": 0.0, "lr": 2.405970753644706e-05, "epoch": 359.3008849557522, "percentage": 51.2, "elapsed_time": "2:27:10", "remaining_time": "2:20:16", "throughput": 1317.31, "total_tokens": 11632352} {"current_steps": 20485, "total_steps": 40000, "loss": 0.0, "lr": 2.4049897078714e-05, "epoch": 359.3893805309734, "percentage": 51.21, "elapsed_time": "2:27:12", "remaining_time": "2:20:14", "throughput": 1317.3, "total_tokens": 11635024} {"current_steps": 20490, "total_steps": 40000, "loss": 0.0, "lr": 2.404008676749874e-05, "epoch": 359.4778761061947, "percentage": 51.23, "elapsed_time": "2:27:14", "remaining_time": "2:20:11", "throughput": 1317.26, "total_tokens": 11637376} {"current_steps": 20495, "total_steps": 40000, "loss": 0.0, "lr": 2.403027660431418e-05, "epoch": 359.56637168141594, "percentage": 51.24, "elapsed_time": "2:27:16", "remaining_time": "2:20:09", "throughput": 1317.33, "total_tokens": 11640704} {"current_steps": 20500, "total_steps": 40000, "loss": 0.0, "lr": 2.402046659067314e-05, "epoch": 359.65486725663715, "percentage": 51.25, "elapsed_time": "2:27:18", "remaining_time": "2:20:07", "throughput": 1317.37, "total_tokens": 11643760} {"current_steps": 20505, "total_steps": 40000, "loss": 0.0, "lr": 2.401065672808847e-05, "epoch": 359.7433628318584, "percentage": 51.26, "elapsed_time": "2:27:20", "remaining_time": "2:20:05", "throughput": 1317.39, "total_tokens": 11646656} {"current_steps": 20510, "total_steps": 40000, "loss": 0.0, "lr": 2.400084701807296e-05, "epoch": 359.83185840707966, "percentage": 51.28, "elapsed_time": "2:27:22", "remaining_time": "2:20:03", "throughput": 1317.41, "total_tokens": 11649552} {"current_steps": 20515, "total_steps": 40000, "loss": 0.0, "lr": 2.39910374621394e-05, "epoch": 359.92035398230087, "percentage": 51.29, "elapsed_time": "2:27:24", "remaining_time": "2:20:00", "throughput": 1317.43, "total_tokens": 11652464} {"current_steps": 20520, "total_steps": 40000, "loss": 0.0, "lr": 2.3981228061800544e-05, "epoch": 360.0, "percentage": 51.3, "elapsed_time": "2:27:26", "remaining_time": "2:19:58", "throughput": 1317.45, "total_tokens": 11655312} {"current_steps": 20525, "total_steps": 40000, "loss": 0.0, "lr": 2.3971418818569115e-05, "epoch": 360.08849557522126, "percentage": 51.31, "elapsed_time": "2:27:29", "remaining_time": "2:19:56", "throughput": 1317.39, "total_tokens": 11657760} {"current_steps": 20530, "total_steps": 40000, "loss": 0.0, "lr": 2.3961609733957832e-05, "epoch": 360.17699115044246, "percentage": 51.32, "elapsed_time": "2:27:31", "remaining_time": "2:19:54", "throughput": 1317.4, "total_tokens": 11660656} {"current_steps": 20535, "total_steps": 40000, "loss": 0.0, "lr": 2.395180080947939e-05, "epoch": 360.2654867256637, "percentage": 51.34, "elapsed_time": "2:27:33", "remaining_time": "2:19:52", "throughput": 1317.4, "total_tokens": 11663344} {"current_steps": 20540, "total_steps": 40000, "loss": 0.0, "lr": 2.394199204664642e-05, "epoch": 360.353982300885, "percentage": 51.35, "elapsed_time": "2:27:35", "remaining_time": "2:19:49", "throughput": 1317.44, "total_tokens": 11666432} {"current_steps": 20545, "total_steps": 40000, "loss": 0.0, "lr": 2.3932183446971583e-05, "epoch": 360.4424778761062, "percentage": 51.36, "elapsed_time": "2:27:37", "remaining_time": "2:19:47", "throughput": 1317.42, "total_tokens": 11669008} {"current_steps": 20550, "total_steps": 40000, "loss": 0.0, "lr": 2.3922375011967473e-05, "epoch": 360.53097345132744, "percentage": 51.38, "elapsed_time": "2:27:39", "remaining_time": "2:19:45", "throughput": 1317.47, "total_tokens": 11672096} {"current_steps": 20555, "total_steps": 40000, "loss": 0.0, "lr": 2.3912566743146676e-05, "epoch": 360.6194690265487, "percentage": 51.39, "elapsed_time": "2:27:41", "remaining_time": "2:19:43", "throughput": 1317.55, "total_tokens": 11675552} {"current_steps": 20560, "total_steps": 40000, "loss": 0.0, "lr": 2.390275864202176e-05, "epoch": 360.7079646017699, "percentage": 51.4, "elapsed_time": "2:27:43", "remaining_time": "2:19:40", "throughput": 1317.55, "total_tokens": 11678272} {"current_steps": 20565, "total_steps": 40000, "loss": 0.0, "lr": 2.3892950710105243e-05, "epoch": 360.79646017699116, "percentage": 51.41, "elapsed_time": "2:27:45", "remaining_time": "2:19:38", "throughput": 1317.6, "total_tokens": 11681472} {"current_steps": 20570, "total_steps": 40000, "loss": 0.0, "lr": 2.3883142948909635e-05, "epoch": 360.88495575221236, "percentage": 51.42, "elapsed_time": "2:27:47", "remaining_time": "2:19:36", "throughput": 1317.61, "total_tokens": 11684272} {"current_steps": 20575, "total_steps": 40000, "loss": 0.0, "lr": 2.3873335359947433e-05, "epoch": 360.9734513274336, "percentage": 51.44, "elapsed_time": "2:27:49", "remaining_time": "2:19:34", "throughput": 1317.61, "total_tokens": 11687008} {"current_steps": 20580, "total_steps": 40000, "loss": 0.0, "lr": 2.3863527944731066e-05, "epoch": 361.05309734513276, "percentage": 51.45, "elapsed_time": "2:27:52", "remaining_time": "2:19:32", "throughput": 1317.49, "total_tokens": 11688944} {"current_steps": 20585, "total_steps": 40000, "loss": 0.0, "lr": 2.385372070477298e-05, "epoch": 361.14159292035396, "percentage": 51.46, "elapsed_time": "2:27:54", "remaining_time": "2:19:29", "throughput": 1317.56, "total_tokens": 11692240} {"current_steps": 20590, "total_steps": 40000, "loss": 0.0, "lr": 2.384391364158556e-05, "epoch": 361.2300884955752, "percentage": 51.48, "elapsed_time": "2:27:56", "remaining_time": "2:19:27", "throughput": 1317.54, "total_tokens": 11694816} {"current_steps": 20595, "total_steps": 40000, "loss": 0.0, "lr": 2.3834106756681185e-05, "epoch": 361.3185840707965, "percentage": 51.49, "elapsed_time": "2:27:58", "remaining_time": "2:19:25", "throughput": 1317.55, "total_tokens": 11697648} {"current_steps": 20600, "total_steps": 40000, "loss": 0.0, "lr": 2.3824300051572206e-05, "epoch": 361.4070796460177, "percentage": 51.5, "elapsed_time": "2:28:00", "remaining_time": "2:19:23", "throughput": 1317.53, "total_tokens": 11700176} {"current_steps": 20600, "total_steps": 40000, "eval_loss": 0.56800377368927, "epoch": 361.4070796460177, "percentage": 51.5, "elapsed_time": "2:28:01", "remaining_time": "2:19:24", "throughput": 1317.37, "total_tokens": 11700176} {"current_steps": 20605, "total_steps": 40000, "loss": 0.0, "lr": 2.3814493527770923e-05, "epoch": 361.49557522123894, "percentage": 51.51, "elapsed_time": "2:28:05", "remaining_time": "2:19:23", "throughput": 1317.17, "total_tokens": 11703296} {"current_steps": 20610, "total_steps": 40000, "loss": 0.0, "lr": 2.3804687186789637e-05, "epoch": 361.5840707964602, "percentage": 51.52, "elapsed_time": "2:28:07", "remaining_time": "2:19:21", "throughput": 1317.15, "total_tokens": 11705904} {"current_steps": 20615, "total_steps": 40000, "loss": 0.0, "lr": 2.379488103014062e-05, "epoch": 361.6725663716814, "percentage": 51.54, "elapsed_time": "2:28:09", "remaining_time": "2:19:18", "throughput": 1317.14, "total_tokens": 11708496} {"current_steps": 20620, "total_steps": 40000, "loss": 0.0, "lr": 2.3785075059336086e-05, "epoch": 361.76106194690266, "percentage": 51.55, "elapsed_time": "2:28:11", "remaining_time": "2:19:16", "throughput": 1317.19, "total_tokens": 11711728} {"current_steps": 20625, "total_steps": 40000, "loss": 0.0, "lr": 2.3775269275888248e-05, "epoch": 361.8495575221239, "percentage": 51.56, "elapsed_time": "2:28:13", "remaining_time": "2:19:14", "throughput": 1317.24, "total_tokens": 11714848} {"current_steps": 20630, "total_steps": 40000, "loss": 0.0, "lr": 2.3765463681309274e-05, "epoch": 361.9380530973451, "percentage": 51.58, "elapsed_time": "2:28:15", "remaining_time": "2:19:12", "throughput": 1317.33, "total_tokens": 11718352} {"current_steps": 20635, "total_steps": 40000, "loss": 0.0, "lr": 2.3755658277111313e-05, "epoch": 362.01769911504425, "percentage": 51.59, "elapsed_time": "2:28:17", "remaining_time": "2:19:10", "throughput": 1317.25, "total_tokens": 11720688} {"current_steps": 20640, "total_steps": 40000, "loss": 0.0, "lr": 2.374585306480649e-05, "epoch": 362.1061946902655, "percentage": 51.6, "elapsed_time": "2:28:19", "remaining_time": "2:19:07", "throughput": 1317.21, "total_tokens": 11723040} {"current_steps": 20645, "total_steps": 40000, "loss": 0.0, "lr": 2.3736048045906877e-05, "epoch": 362.1946902654867, "percentage": 51.61, "elapsed_time": "2:28:21", "remaining_time": "2:19:05", "throughput": 1317.22, "total_tokens": 11725872} {"current_steps": 20650, "total_steps": 40000, "loss": 0.0, "lr": 2.372624322192454e-05, "epoch": 362.283185840708, "percentage": 51.62, "elapsed_time": "2:28:24", "remaining_time": "2:19:03", "throughput": 1317.26, "total_tokens": 11728960} {"current_steps": 20655, "total_steps": 40000, "loss": 0.0, "lr": 2.3716438594371516e-05, "epoch": 362.37168141592923, "percentage": 51.64, "elapsed_time": "2:28:26", "remaining_time": "2:19:01", "throughput": 1317.31, "total_tokens": 11732144} {"current_steps": 20660, "total_steps": 40000, "loss": 0.0, "lr": 2.3706634164759784e-05, "epoch": 362.46017699115043, "percentage": 51.65, "elapsed_time": "2:28:28", "remaining_time": "2:18:59", "throughput": 1317.37, "total_tokens": 11735424} {"current_steps": 20665, "total_steps": 40000, "loss": 0.0, "lr": 2.3696829934601323e-05, "epoch": 362.5486725663717, "percentage": 51.66, "elapsed_time": "2:28:30", "remaining_time": "2:18:56", "throughput": 1317.37, "total_tokens": 11738144} {"current_steps": 20670, "total_steps": 40000, "loss": 0.0, "lr": 2.3687025905408053e-05, "epoch": 362.6371681415929, "percentage": 51.68, "elapsed_time": "2:28:32", "remaining_time": "2:18:54", "throughput": 1317.33, "total_tokens": 11740528} {"current_steps": 20675, "total_steps": 40000, "loss": 0.0, "lr": 2.3677222078691886e-05, "epoch": 362.72566371681415, "percentage": 51.69, "elapsed_time": "2:28:34", "remaining_time": "2:18:52", "throughput": 1317.35, "total_tokens": 11743344} {"current_steps": 20680, "total_steps": 40000, "loss": 0.0, "lr": 2.366741845596471e-05, "epoch": 362.8141592920354, "percentage": 51.7, "elapsed_time": "2:28:36", "remaining_time": "2:18:50", "throughput": 1317.41, "total_tokens": 11746624} {"current_steps": 20685, "total_steps": 40000, "loss": 0.0, "lr": 2.3657615038738343e-05, "epoch": 362.9026548672566, "percentage": 51.71, "elapsed_time": "2:28:38", "remaining_time": "2:18:47", "throughput": 1317.47, "total_tokens": 11749920} {"current_steps": 20690, "total_steps": 40000, "loss": 0.0, "lr": 2.3647811828524614e-05, "epoch": 362.9911504424779, "percentage": 51.73, "elapsed_time": "2:28:40", "remaining_time": "2:18:45", "throughput": 1317.45, "total_tokens": 11752432} {"current_steps": 20695, "total_steps": 40000, "loss": 0.0, "lr": 2.363800882683529e-05, "epoch": 363.070796460177, "percentage": 51.74, "elapsed_time": "2:28:42", "remaining_time": "2:18:43", "throughput": 1317.33, "total_tokens": 11754384} {"current_steps": 20700, "total_steps": 40000, "loss": 0.0, "lr": 2.3628206035182125e-05, "epoch": 363.1592920353982, "percentage": 51.75, "elapsed_time": "2:28:44", "remaining_time": "2:18:41", "throughput": 1317.31, "total_tokens": 11756912} {"current_steps": 20705, "total_steps": 40000, "loss": 0.0, "lr": 2.361840345507683e-05, "epoch": 363.24778761061947, "percentage": 51.76, "elapsed_time": "2:28:46", "remaining_time": "2:18:39", "throughput": 1317.36, "total_tokens": 11760048} {"current_steps": 20710, "total_steps": 40000, "loss": 0.0, "lr": 2.3608601088031073e-05, "epoch": 363.3362831858407, "percentage": 51.78, "elapsed_time": "2:28:49", "remaining_time": "2:18:36", "throughput": 1317.38, "total_tokens": 11762960} {"current_steps": 20715, "total_steps": 40000, "loss": 0.0, "lr": 2.3598798935556516e-05, "epoch": 363.42477876106193, "percentage": 51.79, "elapsed_time": "2:28:51", "remaining_time": "2:18:34", "throughput": 1317.45, "total_tokens": 11766320} {"current_steps": 20720, "total_steps": 40000, "loss": 0.0, "lr": 2.3588996999164784e-05, "epoch": 363.5132743362832, "percentage": 51.8, "elapsed_time": "2:28:53", "remaining_time": "2:18:32", "throughput": 1317.47, "total_tokens": 11769264} {"current_steps": 20725, "total_steps": 40000, "loss": 0.0, "lr": 2.3579195280367434e-05, "epoch": 363.60176991150445, "percentage": 51.81, "elapsed_time": "2:28:55", "remaining_time": "2:18:30", "throughput": 1317.45, "total_tokens": 11771776} {"current_steps": 20730, "total_steps": 40000, "loss": 0.0, "lr": 2.356939378067603e-05, "epoch": 363.69026548672565, "percentage": 51.82, "elapsed_time": "2:28:57", "remaining_time": "2:18:27", "throughput": 1317.44, "total_tokens": 11774432} {"current_steps": 20735, "total_steps": 40000, "loss": 0.0, "lr": 2.3559592501602092e-05, "epoch": 363.7787610619469, "percentage": 51.84, "elapsed_time": "2:28:59", "remaining_time": "2:18:25", "throughput": 1317.54, "total_tokens": 11778000} {"current_steps": 20740, "total_steps": 40000, "loss": 0.0, "lr": 2.3549791444657076e-05, "epoch": 363.86725663716817, "percentage": 51.85, "elapsed_time": "2:29:01", "remaining_time": "2:18:23", "throughput": 1317.57, "total_tokens": 11781072} {"current_steps": 20745, "total_steps": 40000, "loss": 0.0, "lr": 2.353999061135246e-05, "epoch": 363.95575221238937, "percentage": 51.86, "elapsed_time": "2:29:03", "remaining_time": "2:18:21", "throughput": 1317.59, "total_tokens": 11783888} {"current_steps": 20750, "total_steps": 40000, "loss": 0.0, "lr": 2.3530190003199626e-05, "epoch": 364.0353982300885, "percentage": 51.88, "elapsed_time": "2:29:05", "remaining_time": "2:18:19", "throughput": 1317.5, "total_tokens": 11786048} {"current_steps": 20755, "total_steps": 40000, "loss": 0.0, "lr": 2.3520389621709965e-05, "epoch": 364.12389380530976, "percentage": 51.89, "elapsed_time": "2:29:07", "remaining_time": "2:18:16", "throughput": 1317.5, "total_tokens": 11788784} {"current_steps": 20760, "total_steps": 40000, "loss": 0.0, "lr": 2.351058946839483e-05, "epoch": 364.21238938053096, "percentage": 51.9, "elapsed_time": "2:29:09", "remaining_time": "2:18:14", "throughput": 1317.52, "total_tokens": 11791712} {"current_steps": 20765, "total_steps": 40000, "loss": 0.0, "lr": 2.350078954476551e-05, "epoch": 364.3008849557522, "percentage": 51.91, "elapsed_time": "2:29:12", "remaining_time": "2:18:12", "throughput": 1317.5, "total_tokens": 11794320} {"current_steps": 20770, "total_steps": 40000, "loss": 0.0, "lr": 2.3490989852333272e-05, "epoch": 364.3893805309734, "percentage": 51.92, "elapsed_time": "2:29:14", "remaining_time": "2:18:10", "throughput": 1317.47, "total_tokens": 11796768} {"current_steps": 20775, "total_steps": 40000, "loss": 0.0, "lr": 2.3481190392609377e-05, "epoch": 364.4778761061947, "percentage": 51.94, "elapsed_time": "2:29:16", "remaining_time": "2:18:07", "throughput": 1317.52, "total_tokens": 11799904} {"current_steps": 20780, "total_steps": 40000, "loss": 0.0, "lr": 2.3471391167105e-05, "epoch": 364.56637168141594, "percentage": 51.95, "elapsed_time": "2:29:18", "remaining_time": "2:18:05", "throughput": 1317.47, "total_tokens": 11802240} {"current_steps": 20785, "total_steps": 40000, "loss": 0.0, "lr": 2.3461592177331325e-05, "epoch": 364.65486725663715, "percentage": 51.96, "elapsed_time": "2:29:20", "remaining_time": "2:18:03", "throughput": 1317.53, "total_tokens": 11805440} {"current_steps": 20790, "total_steps": 40000, "loss": 0.0, "lr": 2.345179342479946e-05, "epoch": 364.7433628318584, "percentage": 51.98, "elapsed_time": "2:29:22", "remaining_time": "2:18:01", "throughput": 1317.55, "total_tokens": 11808352} {"current_steps": 20795, "total_steps": 40000, "loss": 0.0, "lr": 2.3441994911020503e-05, "epoch": 364.83185840707966, "percentage": 51.99, "elapsed_time": "2:29:24", "remaining_time": "2:17:58", "throughput": 1317.57, "total_tokens": 11811280} {"current_steps": 20800, "total_steps": 40000, "loss": 0.0, "lr": 2.3432196637505522e-05, "epoch": 364.92035398230087, "percentage": 52.0, "elapsed_time": "2:29:26", "remaining_time": "2:17:56", "throughput": 1317.6, "total_tokens": 11814304} {"current_steps": 20800, "total_steps": 40000, "eval_loss": 0.5215240716934204, "epoch": 364.92035398230087, "percentage": 52.0, "elapsed_time": "2:29:27", "remaining_time": "2:17:57", "throughput": 1317.45, "total_tokens": 11814304} {"current_steps": 20805, "total_steps": 40000, "loss": 0.0, "lr": 2.3422398605765515e-05, "epoch": 365.0, "percentage": 52.01, "elapsed_time": "2:29:31", "remaining_time": "2:17:57", "throughput": 1317.22, "total_tokens": 11817184} {"current_steps": 20810, "total_steps": 40000, "loss": 0.0, "lr": 2.3412600817311462e-05, "epoch": 365.08849557522126, "percentage": 52.02, "elapsed_time": "2:29:33", "remaining_time": "2:17:55", "throughput": 1317.18, "total_tokens": 11819888} {"current_steps": 20815, "total_steps": 40000, "loss": 0.0, "lr": 2.3402803273654326e-05, "epoch": 365.17699115044246, "percentage": 52.04, "elapsed_time": "2:29:35", "remaining_time": "2:17:52", "throughput": 1317.18, "total_tokens": 11822624} {"current_steps": 20820, "total_steps": 40000, "loss": 0.0, "lr": 2.3393005976304983e-05, "epoch": 365.2654867256637, "percentage": 52.05, "elapsed_time": "2:29:37", "remaining_time": "2:17:50", "throughput": 1317.18, "total_tokens": 11825344} {"current_steps": 20825, "total_steps": 40000, "loss": 0.0, "lr": 2.338320892677432e-05, "epoch": 365.353982300885, "percentage": 52.06, "elapsed_time": "2:29:39", "remaining_time": "2:17:48", "throughput": 1317.22, "total_tokens": 11828384} {"current_steps": 20830, "total_steps": 40000, "loss": 0.0, "lr": 2.3373412126573155e-05, "epoch": 365.4424778761062, "percentage": 52.08, "elapsed_time": "2:29:41", "remaining_time": "2:17:46", "throughput": 1317.23, "total_tokens": 11831248} {"current_steps": 20835, "total_steps": 40000, "loss": 0.0, "lr": 2.3363615577212285e-05, "epoch": 365.53097345132744, "percentage": 52.09, "elapsed_time": "2:29:43", "remaining_time": "2:17:43", "throughput": 1317.26, "total_tokens": 11834224} {"current_steps": 20840, "total_steps": 40000, "loss": 0.0, "lr": 2.3353819280202455e-05, "epoch": 365.6194690265487, "percentage": 52.1, "elapsed_time": "2:29:46", "remaining_time": "2:17:41", "throughput": 1317.32, "total_tokens": 11837504} {"current_steps": 20845, "total_steps": 40000, "loss": 0.0, "lr": 2.334402323705438e-05, "epoch": 365.7079646017699, "percentage": 52.11, "elapsed_time": "2:29:48", "remaining_time": "2:17:39", "throughput": 1317.32, "total_tokens": 11840288} {"current_steps": 20850, "total_steps": 40000, "loss": 0.0, "lr": 2.3334227449278725e-05, "epoch": 365.79646017699116, "percentage": 52.12, "elapsed_time": "2:29:50", "remaining_time": "2:17:37", "throughput": 1317.3, "total_tokens": 11842832} {"current_steps": 20855, "total_steps": 40000, "loss": 0.0, "lr": 2.3324431918386143e-05, "epoch": 365.88495575221236, "percentage": 52.14, "elapsed_time": "2:29:52", "remaining_time": "2:17:34", "throughput": 1317.37, "total_tokens": 11846192} {"current_steps": 20860, "total_steps": 40000, "loss": 0.0, "lr": 2.3314636645887207e-05, "epoch": 365.9734513274336, "percentage": 52.15, "elapsed_time": "2:29:54", "remaining_time": "2:17:32", "throughput": 1317.41, "total_tokens": 11849232} {"current_steps": 20865, "total_steps": 40000, "loss": 0.0, "lr": 2.3304841633292487e-05, "epoch": 366.05309734513276, "percentage": 52.16, "elapsed_time": "2:29:56", "remaining_time": "2:17:30", "throughput": 1317.34, "total_tokens": 11851592} {"current_steps": 20870, "total_steps": 40000, "loss": 0.0, "lr": 2.329504688211248e-05, "epoch": 366.14159292035396, "percentage": 52.18, "elapsed_time": "2:29:58", "remaining_time": "2:17:28", "throughput": 1317.38, "total_tokens": 11854664} {"current_steps": 20875, "total_steps": 40000, "loss": 0.0, "lr": 2.3285252393857677e-05, "epoch": 366.2300884955752, "percentage": 52.19, "elapsed_time": "2:30:00", "remaining_time": "2:17:26", "throughput": 1317.39, "total_tokens": 11857544} {"current_steps": 20880, "total_steps": 40000, "loss": 0.0, "lr": 2.327545817003851e-05, "epoch": 366.3185840707965, "percentage": 52.2, "elapsed_time": "2:30:02", "remaining_time": "2:17:23", "throughput": 1317.42, "total_tokens": 11860536} {"current_steps": 20885, "total_steps": 40000, "loss": 0.0, "lr": 2.326566421216535e-05, "epoch": 366.4070796460177, "percentage": 52.21, "elapsed_time": "2:30:04", "remaining_time": "2:17:21", "throughput": 1317.43, "total_tokens": 11863272} {"current_steps": 20890, "total_steps": 40000, "loss": 0.0, "lr": 2.3255870521748565e-05, "epoch": 366.49557522123894, "percentage": 52.23, "elapsed_time": "2:30:06", "remaining_time": "2:17:19", "throughput": 1317.42, "total_tokens": 11865944} {"current_steps": 20895, "total_steps": 40000, "loss": 0.0, "lr": 2.3246077100298474e-05, "epoch": 366.5840707964602, "percentage": 52.24, "elapsed_time": "2:30:09", "remaining_time": "2:17:17", "throughput": 1317.43, "total_tokens": 11868776} {"current_steps": 20900, "total_steps": 40000, "loss": 0.0, "lr": 2.3236283949325328e-05, "epoch": 366.6725663716814, "percentage": 52.25, "elapsed_time": "2:30:11", "remaining_time": "2:17:15", "throughput": 1317.47, "total_tokens": 11871816} {"current_steps": 20905, "total_steps": 40000, "loss": 0.0, "lr": 2.3226491070339368e-05, "epoch": 366.76106194690266, "percentage": 52.26, "elapsed_time": "2:30:13", "remaining_time": "2:17:12", "throughput": 1317.46, "total_tokens": 11874520} {"current_steps": 20910, "total_steps": 40000, "loss": 0.0, "lr": 2.3216698464850762e-05, "epoch": 366.8495575221239, "percentage": 52.28, "elapsed_time": "2:30:15", "remaining_time": "2:17:10", "throughput": 1317.47, "total_tokens": 11877288} {"current_steps": 20915, "total_steps": 40000, "loss": 0.0, "lr": 2.320690613436967e-05, "epoch": 366.9380530973451, "percentage": 52.29, "elapsed_time": "2:30:17", "remaining_time": "2:17:08", "throughput": 1317.5, "total_tokens": 11880328} {"current_steps": 20920, "total_steps": 40000, "loss": 0.0, "lr": 2.3197114080406192e-05, "epoch": 367.01769911504425, "percentage": 52.3, "elapsed_time": "2:30:19", "remaining_time": "2:17:06", "throughput": 1317.47, "total_tokens": 11882952} {"current_steps": 20925, "total_steps": 40000, "loss": 0.0, "lr": 2.3187322304470365e-05, "epoch": 367.1061946902655, "percentage": 52.31, "elapsed_time": "2:30:21", "remaining_time": "2:17:04", "throughput": 1317.48, "total_tokens": 11885848} {"current_steps": 20930, "total_steps": 40000, "loss": 0.0, "lr": 2.3177530808072222e-05, "epoch": 367.1946902654867, "percentage": 52.33, "elapsed_time": "2:30:23", "remaining_time": "2:17:01", "throughput": 1317.47, "total_tokens": 11888424} {"current_steps": 20935, "total_steps": 40000, "loss": 0.0, "lr": 2.316773959272174e-05, "epoch": 367.283185840708, "percentage": 52.34, "elapsed_time": "2:30:25", "remaining_time": "2:16:59", "throughput": 1317.47, "total_tokens": 11891224} {"current_steps": 20940, "total_steps": 40000, "loss": 0.0, "lr": 2.3157948659928823e-05, "epoch": 367.37168141592923, "percentage": 52.35, "elapsed_time": "2:30:27", "remaining_time": "2:16:57", "throughput": 1317.51, "total_tokens": 11894264} {"current_steps": 20945, "total_steps": 40000, "loss": 0.0, "lr": 2.3148158011203388e-05, "epoch": 367.46017699115043, "percentage": 52.36, "elapsed_time": "2:30:29", "remaining_time": "2:16:55", "throughput": 1317.51, "total_tokens": 11896984} {"current_steps": 20950, "total_steps": 40000, "loss": 0.0, "lr": 2.3138367648055253e-05, "epoch": 367.5486725663717, "percentage": 52.38, "elapsed_time": "2:30:32", "remaining_time": "2:16:52", "throughput": 1317.56, "total_tokens": 11900184} {"current_steps": 20955, "total_steps": 40000, "loss": 0.0, "lr": 2.312857757199422e-05, "epoch": 367.6371681415929, "percentage": 52.39, "elapsed_time": "2:30:34", "remaining_time": "2:16:50", "throughput": 1317.62, "total_tokens": 11903464} {"current_steps": 20960, "total_steps": 40000, "loss": 0.0, "lr": 2.3118787784530048e-05, "epoch": 367.72566371681415, "percentage": 52.4, "elapsed_time": "2:30:36", "remaining_time": "2:16:48", "throughput": 1317.6, "total_tokens": 11906056} {"current_steps": 20965, "total_steps": 40000, "loss": 0.0, "lr": 2.310899828717243e-05, "epoch": 367.8141592920354, "percentage": 52.41, "elapsed_time": "2:30:38", "remaining_time": "2:16:46", "throughput": 1317.62, "total_tokens": 11908888} {"current_steps": 20970, "total_steps": 40000, "loss": 0.0, "lr": 2.309920908143104e-05, "epoch": 367.9026548672566, "percentage": 52.42, "elapsed_time": "2:30:40", "remaining_time": "2:16:43", "throughput": 1317.63, "total_tokens": 11911704} {"current_steps": 20975, "total_steps": 40000, "loss": 0.0, "lr": 2.308942016881551e-05, "epoch": 367.9911504424779, "percentage": 52.44, "elapsed_time": "2:30:42", "remaining_time": "2:16:41", "throughput": 1317.61, "total_tokens": 11914248} {"current_steps": 20980, "total_steps": 40000, "loss": 0.0, "lr": 2.307963155083539e-05, "epoch": 368.070796460177, "percentage": 52.45, "elapsed_time": "2:30:44", "remaining_time": "2:16:39", "throughput": 1317.51, "total_tokens": 11916344} {"current_steps": 20985, "total_steps": 40000, "loss": 0.0, "lr": 2.306984322900022e-05, "epoch": 368.1592920353982, "percentage": 52.46, "elapsed_time": "2:30:46", "remaining_time": "2:16:37", "throughput": 1317.54, "total_tokens": 11919304} {"current_steps": 20990, "total_steps": 40000, "loss": 0.0, "lr": 2.3060055204819482e-05, "epoch": 368.24778761061947, "percentage": 52.48, "elapsed_time": "2:30:48", "remaining_time": "2:16:35", "throughput": 1317.58, "total_tokens": 11922376} {"current_steps": 20995, "total_steps": 40000, "loss": 0.0, "lr": 2.3050267479802604e-05, "epoch": 368.3362831858407, "percentage": 52.49, "elapsed_time": "2:30:50", "remaining_time": "2:16:32", "throughput": 1317.55, "total_tokens": 11924888} {"current_steps": 21000, "total_steps": 40000, "loss": 0.0, "lr": 2.304048005545899e-05, "epoch": 368.42477876106193, "percentage": 52.5, "elapsed_time": "2:30:52", "remaining_time": "2:16:30", "throughput": 1317.54, "total_tokens": 11927464} {"current_steps": 21000, "total_steps": 40000, "eval_loss": 0.5594981908798218, "epoch": 368.42477876106193, "percentage": 52.5, "elapsed_time": "2:30:53", "remaining_time": "2:16:31", "throughput": 1317.38, "total_tokens": 11927464} {"current_steps": 21005, "total_steps": 40000, "loss": 0.0, "lr": 2.3030692933297972e-05, "epoch": 368.5132743362832, "percentage": 52.51, "elapsed_time": "2:30:57", "remaining_time": "2:16:31", "throughput": 1317.2, "total_tokens": 11930888} {"current_steps": 21010, "total_steps": 40000, "loss": 0.0, "lr": 2.3020906114828843e-05, "epoch": 368.60176991150445, "percentage": 52.52, "elapsed_time": "2:30:59", "remaining_time": "2:16:28", "throughput": 1317.24, "total_tokens": 11933976} {"current_steps": 21015, "total_steps": 40000, "loss": 0.0, "lr": 2.301111960156088e-05, "epoch": 368.69026548672565, "percentage": 52.54, "elapsed_time": "2:31:01", "remaining_time": "2:16:26", "throughput": 1317.26, "total_tokens": 11936936} {"current_steps": 21020, "total_steps": 40000, "loss": 0.0, "lr": 2.300133339500326e-05, "epoch": 368.7787610619469, "percentage": 52.55, "elapsed_time": "2:31:03", "remaining_time": "2:16:24", "throughput": 1317.27, "total_tokens": 11939688} {"current_steps": 21025, "total_steps": 40000, "loss": 0.0, "lr": 2.2991547496665148e-05, "epoch": 368.86725663716817, "percentage": 52.56, "elapsed_time": "2:31:06", "remaining_time": "2:16:22", "throughput": 1317.29, "total_tokens": 11942616} {"current_steps": 21030, "total_steps": 40000, "loss": 0.0, "lr": 2.298176190805565e-05, "epoch": 368.95575221238937, "percentage": 52.58, "elapsed_time": "2:31:08", "remaining_time": "2:16:19", "throughput": 1317.29, "total_tokens": 11945304} {"current_steps": 21035, "total_steps": 40000, "loss": 0.0, "lr": 2.2971976630683826e-05, "epoch": 369.0353982300885, "percentage": 52.59, "elapsed_time": "2:31:10", "remaining_time": "2:16:17", "throughput": 1317.2, "total_tokens": 11947520} {"current_steps": 21040, "total_steps": 40000, "loss": 0.0, "lr": 2.29621916660587e-05, "epoch": 369.12389380530976, "percentage": 52.6, "elapsed_time": "2:31:12", "remaining_time": "2:16:15", "throughput": 1317.32, "total_tokens": 11951280} {"current_steps": 21045, "total_steps": 40000, "loss": 0.0, "lr": 2.295240701568922e-05, "epoch": 369.21238938053096, "percentage": 52.61, "elapsed_time": "2:31:14", "remaining_time": "2:16:13", "throughput": 1317.36, "total_tokens": 11954384} {"current_steps": 21050, "total_steps": 40000, "loss": 0.0, "lr": 2.2942622681084312e-05, "epoch": 369.3008849557522, "percentage": 52.62, "elapsed_time": "2:31:16", "remaining_time": "2:16:11", "throughput": 1317.33, "total_tokens": 11956880} {"current_steps": 21055, "total_steps": 40000, "loss": 0.0, "lr": 2.293283866375284e-05, "epoch": 369.3893805309734, "percentage": 52.64, "elapsed_time": "2:31:18", "remaining_time": "2:16:08", "throughput": 1317.35, "total_tokens": 11959744} {"current_steps": 21060, "total_steps": 40000, "loss": 0.0, "lr": 2.2923054965203627e-05, "epoch": 369.4778761061947, "percentage": 52.65, "elapsed_time": "2:31:20", "remaining_time": "2:16:06", "throughput": 1317.37, "total_tokens": 11962656} {"current_steps": 21065, "total_steps": 40000, "loss": 0.0, "lr": 2.2913271586945443e-05, "epoch": 369.56637168141594, "percentage": 52.66, "elapsed_time": "2:31:22", "remaining_time": "2:16:04", "throughput": 1317.39, "total_tokens": 11965648} {"current_steps": 21070, "total_steps": 40000, "loss": 0.0, "lr": 2.290348853048699e-05, "epoch": 369.65486725663715, "percentage": 52.68, "elapsed_time": "2:31:24", "remaining_time": "2:16:02", "throughput": 1317.43, "total_tokens": 11968752} {"current_steps": 21075, "total_steps": 40000, "loss": 0.0, "lr": 2.2893705797336956e-05, "epoch": 369.7433628318584, "percentage": 52.69, "elapsed_time": "2:31:26", "remaining_time": "2:15:59", "throughput": 1317.43, "total_tokens": 11971440} {"current_steps": 21080, "total_steps": 40000, "loss": 0.0, "lr": 2.288392338900397e-05, "epoch": 369.83185840707966, "percentage": 52.7, "elapsed_time": "2:31:29", "remaining_time": "2:15:57", "throughput": 1317.42, "total_tokens": 11974064} {"current_steps": 21085, "total_steps": 40000, "loss": 0.0, "lr": 2.2874141306996576e-05, "epoch": 369.92035398230087, "percentage": 52.71, "elapsed_time": "2:31:31", "remaining_time": "2:15:55", "throughput": 1317.42, "total_tokens": 11976816} {"current_steps": 21090, "total_steps": 40000, "loss": 0.0, "lr": 2.2864359552823312e-05, "epoch": 370.0, "percentage": 52.73, "elapsed_time": "2:31:33", "remaining_time": "2:15:53", "throughput": 1317.37, "total_tokens": 11978976} {"current_steps": 21095, "total_steps": 40000, "loss": 0.0, "lr": 2.2854578127992648e-05, "epoch": 370.08849557522126, "percentage": 52.74, "elapsed_time": "2:31:35", "remaining_time": "2:15:51", "throughput": 1317.3, "total_tokens": 11981376} {"current_steps": 21100, "total_steps": 40000, "loss": 0.0, "lr": 2.2844797034012988e-05, "epoch": 370.17699115044246, "percentage": 52.75, "elapsed_time": "2:31:37", "remaining_time": "2:15:48", "throughput": 1317.35, "total_tokens": 11984576} {"current_steps": 21105, "total_steps": 40000, "loss": 0.0, "lr": 2.2835016272392722e-05, "epoch": 370.2654867256637, "percentage": 52.76, "elapsed_time": "2:31:39", "remaining_time": "2:15:46", "throughput": 1317.35, "total_tokens": 11987328} {"current_steps": 21110, "total_steps": 40000, "loss": 0.0, "lr": 2.2825235844640142e-05, "epoch": 370.353982300885, "percentage": 52.78, "elapsed_time": "2:31:41", "remaining_time": "2:15:44", "throughput": 1317.42, "total_tokens": 11990720} {"current_steps": 21115, "total_steps": 40000, "loss": 0.0, "lr": 2.2815455752263522e-05, "epoch": 370.4424778761062, "percentage": 52.79, "elapsed_time": "2:31:43", "remaining_time": "2:15:42", "throughput": 1317.42, "total_tokens": 11993440} {"current_steps": 21120, "total_steps": 40000, "loss": 0.0, "lr": 2.2805675996771092e-05, "epoch": 370.53097345132744, "percentage": 52.8, "elapsed_time": "2:31:45", "remaining_time": "2:15:40", "throughput": 1317.41, "total_tokens": 11996112} {"current_steps": 21125, "total_steps": 40000, "loss": 0.0, "lr": 2.2795896579670987e-05, "epoch": 370.6194690265487, "percentage": 52.81, "elapsed_time": "2:31:47", "remaining_time": "2:15:37", "throughput": 1317.4, "total_tokens": 11998688} {"current_steps": 21130, "total_steps": 40000, "loss": 0.0, "lr": 2.2786117502471337e-05, "epoch": 370.7079646017699, "percentage": 52.83, "elapsed_time": "2:31:49", "remaining_time": "2:15:35", "throughput": 1317.41, "total_tokens": 12001520} {"current_steps": 21135, "total_steps": 40000, "loss": 0.0, "lr": 2.2776338766680185e-05, "epoch": 370.79646017699116, "percentage": 52.84, "elapsed_time": "2:31:52", "remaining_time": "2:15:33", "throughput": 1317.47, "total_tokens": 12004768} {"current_steps": 21140, "total_steps": 40000, "loss": 0.0, "lr": 2.2766560373805533e-05, "epoch": 370.88495575221236, "percentage": 52.85, "elapsed_time": "2:31:54", "remaining_time": "2:15:31", "throughput": 1317.47, "total_tokens": 12007552} {"current_steps": 21145, "total_steps": 40000, "loss": 0.0, "lr": 2.2756782325355353e-05, "epoch": 370.9734513274336, "percentage": 52.86, "elapsed_time": "2:31:56", "remaining_time": "2:15:28", "throughput": 1317.48, "total_tokens": 12010352} {"current_steps": 21150, "total_steps": 40000, "loss": 0.0, "lr": 2.2747004622837514e-05, "epoch": 371.05309734513276, "percentage": 52.88, "elapsed_time": "2:31:58", "remaining_time": "2:15:26", "throughput": 1317.4, "total_tokens": 12012648} {"current_steps": 21155, "total_steps": 40000, "loss": 0.0, "lr": 2.2737227267759878e-05, "epoch": 371.14159292035396, "percentage": 52.89, "elapsed_time": "2:32:00", "remaining_time": "2:15:24", "throughput": 1317.5, "total_tokens": 12016232} {"current_steps": 21160, "total_steps": 40000, "loss": 0.0, "lr": 2.272745026163024e-05, "epoch": 371.2300884955752, "percentage": 52.9, "elapsed_time": "2:32:02", "remaining_time": "2:15:22", "throughput": 1317.48, "total_tokens": 12018872} {"current_steps": 21165, "total_steps": 40000, "loss": 0.0, "lr": 2.271767360595633e-05, "epoch": 371.3185840707965, "percentage": 52.91, "elapsed_time": "2:32:04", "remaining_time": "2:15:20", "throughput": 1317.43, "total_tokens": 12021144} {"current_steps": 21170, "total_steps": 40000, "loss": 0.0, "lr": 2.270789730224583e-05, "epoch": 371.4070796460177, "percentage": 52.92, "elapsed_time": "2:32:06", "remaining_time": "2:15:17", "throughput": 1317.42, "total_tokens": 12023752} {"current_steps": 21175, "total_steps": 40000, "loss": 0.0, "lr": 2.2698121352006367e-05, "epoch": 371.49557522123894, "percentage": 52.94, "elapsed_time": "2:32:08", "remaining_time": "2:15:15", "throughput": 1317.44, "total_tokens": 12026648} {"current_steps": 21180, "total_steps": 40000, "loss": 0.0, "lr": 2.2688345756745517e-05, "epoch": 371.5840707964602, "percentage": 52.95, "elapsed_time": "2:32:10", "remaining_time": "2:15:13", "throughput": 1317.44, "total_tokens": 12029368} {"current_steps": 21185, "total_steps": 40000, "loss": 0.0, "lr": 2.267857051797081e-05, "epoch": 371.6725663716814, "percentage": 52.96, "elapsed_time": "2:32:12", "remaining_time": "2:15:11", "throughput": 1317.44, "total_tokens": 12032120} {"current_steps": 21190, "total_steps": 40000, "loss": 0.0, "lr": 2.2668795637189695e-05, "epoch": 371.76106194690266, "percentage": 52.98, "elapsed_time": "2:32:15", "remaining_time": "2:15:09", "throughput": 1317.46, "total_tokens": 12035000} {"current_steps": 21195, "total_steps": 40000, "loss": 0.0, "lr": 2.2659021115909586e-05, "epoch": 371.8495575221239, "percentage": 52.99, "elapsed_time": "2:32:17", "remaining_time": "2:15:06", "throughput": 1317.49, "total_tokens": 12038024} {"current_steps": 21200, "total_steps": 40000, "loss": 0.0, "lr": 2.2649246955637847e-05, "epoch": 371.9380530973451, "percentage": 53.0, "elapsed_time": "2:32:19", "remaining_time": "2:15:04", "throughput": 1317.56, "total_tokens": 12041416} {"current_steps": 21200, "total_steps": 40000, "eval_loss": 0.5175203680992126, "epoch": 371.9380530973451, "percentage": 53.0, "elapsed_time": "2:32:20", "remaining_time": "2:15:05", "throughput": 1317.41, "total_tokens": 12041416} {"current_steps": 21205, "total_steps": 40000, "loss": 0.0, "lr": 2.2639473157881766e-05, "epoch": 372.01769911504425, "percentage": 53.01, "elapsed_time": "2:32:24", "remaining_time": "2:15:04", "throughput": 1317.13, "total_tokens": 12044088} {"current_steps": 21210, "total_steps": 40000, "loss": 0.0, "lr": 2.2629699724148594e-05, "epoch": 372.1061946902655, "percentage": 53.02, "elapsed_time": "2:32:26", "remaining_time": "2:15:02", "throughput": 1317.12, "total_tokens": 12046792} {"current_steps": 21215, "total_steps": 40000, "loss": 0.0, "lr": 2.26199266559455e-05, "epoch": 372.1946902654867, "percentage": 53.04, "elapsed_time": "2:32:28", "remaining_time": "2:15:00", "throughput": 1317.12, "total_tokens": 12049480} {"current_steps": 21220, "total_steps": 40000, "loss": 0.0, "lr": 2.2610153954779625e-05, "epoch": 372.283185840708, "percentage": 53.05, "elapsed_time": "2:32:30", "remaining_time": "2:14:58", "throughput": 1317.15, "total_tokens": 12052552} {"current_steps": 21225, "total_steps": 40000, "loss": 0.0, "lr": 2.2600381622158056e-05, "epoch": 372.37168141592923, "percentage": 53.06, "elapsed_time": "2:32:32", "remaining_time": "2:14:56", "throughput": 1317.17, "total_tokens": 12055480} {"current_steps": 21230, "total_steps": 40000, "loss": 0.0, "lr": 2.2590609659587783e-05, "epoch": 372.46017699115043, "percentage": 53.08, "elapsed_time": "2:32:34", "remaining_time": "2:14:53", "throughput": 1317.18, "total_tokens": 12058232} {"current_steps": 21235, "total_steps": 40000, "loss": 0.0, "lr": 2.2580838068575787e-05, "epoch": 372.5486725663717, "percentage": 53.09, "elapsed_time": "2:32:36", "remaining_time": "2:14:51", "throughput": 1317.16, "total_tokens": 12060808} {"current_steps": 21240, "total_steps": 40000, "loss": 0.0, "lr": 2.257106685062896e-05, "epoch": 372.6371681415929, "percentage": 53.1, "elapsed_time": "2:32:38", "remaining_time": "2:14:49", "throughput": 1317.2, "total_tokens": 12063896} {"current_steps": 21245, "total_steps": 40000, "loss": 0.0, "lr": 2.256129600725415e-05, "epoch": 372.72566371681415, "percentage": 53.11, "elapsed_time": "2:32:40", "remaining_time": "2:14:47", "throughput": 1317.24, "total_tokens": 12066968} {"current_steps": 21250, "total_steps": 40000, "loss": 0.0, "lr": 2.2551525539958145e-05, "epoch": 372.8141592920354, "percentage": 53.12, "elapsed_time": "2:32:42", "remaining_time": "2:14:44", "throughput": 1317.29, "total_tokens": 12070200} {"current_steps": 21255, "total_steps": 40000, "loss": 0.0, "lr": 2.2541755450247663e-05, "epoch": 372.9026548672566, "percentage": 53.14, "elapsed_time": "2:32:44", "remaining_time": "2:14:42", "throughput": 1317.27, "total_tokens": 12072728} {"current_steps": 21260, "total_steps": 40000, "loss": 0.0, "lr": 2.2531985739629382e-05, "epoch": 372.9911504424779, "percentage": 53.15, "elapsed_time": "2:32:47", "remaining_time": "2:14:40", "throughput": 1317.27, "total_tokens": 12075480} {"current_steps": 21265, "total_steps": 40000, "loss": 0.0, "lr": 2.2522216409609924e-05, "epoch": 373.070796460177, "percentage": 53.16, "elapsed_time": "2:32:49", "remaining_time": "2:14:38", "throughput": 1317.19, "total_tokens": 12077736} {"current_steps": 21270, "total_steps": 40000, "loss": 0.0, "lr": 2.2512447461695826e-05, "epoch": 373.1592920353982, "percentage": 53.17, "elapsed_time": "2:32:51", "remaining_time": "2:14:36", "throughput": 1317.2, "total_tokens": 12080472} {"current_steps": 21275, "total_steps": 40000, "loss": 0.0, "lr": 2.2502678897393593e-05, "epoch": 373.24778761061947, "percentage": 53.19, "elapsed_time": "2:32:53", "remaining_time": "2:14:33", "throughput": 1317.2, "total_tokens": 12083224} {"current_steps": 21280, "total_steps": 40000, "loss": 0.0, "lr": 2.2492910718209665e-05, "epoch": 373.3362831858407, "percentage": 53.2, "elapsed_time": "2:32:55", "remaining_time": "2:14:31", "throughput": 1317.23, "total_tokens": 12086216} {"current_steps": 21285, "total_steps": 40000, "loss": 0.0, "lr": 2.2483142925650398e-05, "epoch": 373.42477876106193, "percentage": 53.21, "elapsed_time": "2:32:57", "remaining_time": "2:14:29", "throughput": 1317.2, "total_tokens": 12088696} {"current_steps": 21290, "total_steps": 40000, "loss": 0.0, "lr": 2.247337552122213e-05, "epoch": 373.5132743362832, "percentage": 53.23, "elapsed_time": "2:32:59", "remaining_time": "2:14:27", "throughput": 1317.19, "total_tokens": 12091384} {"current_steps": 21295, "total_steps": 40000, "loss": 0.0, "lr": 2.24636085064311e-05, "epoch": 373.60176991150445, "percentage": 53.24, "elapsed_time": "2:33:01", "remaining_time": "2:14:25", "throughput": 1317.22, "total_tokens": 12094376} {"current_steps": 21300, "total_steps": 40000, "loss": 0.0, "lr": 2.245384188278351e-05, "epoch": 373.69026548672565, "percentage": 53.25, "elapsed_time": "2:33:03", "remaining_time": "2:14:22", "throughput": 1317.23, "total_tokens": 12097176} {"current_steps": 21305, "total_steps": 40000, "loss": 0.0, "lr": 2.2444075651785513e-05, "epoch": 373.7787610619469, "percentage": 53.26, "elapsed_time": "2:33:05", "remaining_time": "2:14:20", "throughput": 1317.3, "total_tokens": 12100488} {"current_steps": 21310, "total_steps": 40000, "loss": 0.0, "lr": 2.243430981494316e-05, "epoch": 373.86725663716817, "percentage": 53.27, "elapsed_time": "2:33:07", "remaining_time": "2:14:18", "throughput": 1317.3, "total_tokens": 12103288} {"current_steps": 21315, "total_steps": 40000, "loss": 0.0, "lr": 2.2424544373762475e-05, "epoch": 373.95575221238937, "percentage": 53.29, "elapsed_time": "2:33:09", "remaining_time": "2:14:16", "throughput": 1317.32, "total_tokens": 12106168} {"current_steps": 21320, "total_steps": 40000, "loss": 0.0, "lr": 2.2414779329749418e-05, "epoch": 374.0353982300885, "percentage": 53.3, "elapsed_time": "2:33:12", "remaining_time": "2:14:13", "throughput": 1317.22, "total_tokens": 12108248} {"current_steps": 21325, "total_steps": 40000, "loss": 0.0, "lr": 2.2405014684409873e-05, "epoch": 374.12389380530976, "percentage": 53.31, "elapsed_time": "2:33:14", "remaining_time": "2:14:11", "throughput": 1317.31, "total_tokens": 12111720} {"current_steps": 21330, "total_steps": 40000, "loss": 0.0, "lr": 2.239525043924968e-05, "epoch": 374.21238938053096, "percentage": 53.33, "elapsed_time": "2:33:16", "remaining_time": "2:14:09", "throughput": 1317.36, "total_tokens": 12115000} {"current_steps": 21335, "total_steps": 40000, "loss": 0.0, "lr": 2.2385486595774592e-05, "epoch": 374.3008849557522, "percentage": 53.34, "elapsed_time": "2:33:18", "remaining_time": "2:14:07", "throughput": 1317.36, "total_tokens": 12117720} {"current_steps": 21340, "total_steps": 40000, "loss": 0.0, "lr": 2.237572315549033e-05, "epoch": 374.3893805309734, "percentage": 53.35, "elapsed_time": "2:33:20", "remaining_time": "2:14:05", "throughput": 1317.33, "total_tokens": 12120152} {"current_steps": 21345, "total_steps": 40000, "loss": 0.0, "lr": 2.2365960119902545e-05, "epoch": 374.4778761061947, "percentage": 53.36, "elapsed_time": "2:33:22", "remaining_time": "2:14:02", "throughput": 1317.3, "total_tokens": 12122616} {"current_steps": 21350, "total_steps": 40000, "loss": 0.0, "lr": 2.2356197490516806e-05, "epoch": 374.56637168141594, "percentage": 53.37, "elapsed_time": "2:33:24", "remaining_time": "2:14:00", "throughput": 1317.34, "total_tokens": 12125672} {"current_steps": 21355, "total_steps": 40000, "loss": 0.0, "lr": 2.234643526883863e-05, "epoch": 374.65486725663715, "percentage": 53.39, "elapsed_time": "2:33:26", "remaining_time": "2:13:58", "throughput": 1317.34, "total_tokens": 12128456} {"current_steps": 21360, "total_steps": 40000, "loss": 0.0, "lr": 2.2336673456373497e-05, "epoch": 374.7433628318584, "percentage": 53.4, "elapsed_time": "2:33:28", "remaining_time": "2:13:56", "throughput": 1317.35, "total_tokens": 12131288} {"current_steps": 21365, "total_steps": 40000, "loss": 0.0, "lr": 2.2326912054626772e-05, "epoch": 374.83185840707966, "percentage": 53.41, "elapsed_time": "2:33:30", "remaining_time": "2:13:53", "throughput": 1317.35, "total_tokens": 12133960} {"current_steps": 21370, "total_steps": 40000, "loss": 0.0, "lr": 2.2317151065103813e-05, "epoch": 374.92035398230087, "percentage": 53.42, "elapsed_time": "2:33:32", "remaining_time": "2:13:51", "throughput": 1317.37, "total_tokens": 12136904} {"current_steps": 21375, "total_steps": 40000, "loss": 0.0, "lr": 2.2307390489309865e-05, "epoch": 375.0, "percentage": 53.44, "elapsed_time": "2:33:34", "remaining_time": "2:13:49", "throughput": 1317.34, "total_tokens": 12139256} {"current_steps": 21380, "total_steps": 40000, "loss": 0.0, "lr": 2.2297630328750146e-05, "epoch": 375.08849557522126, "percentage": 53.45, "elapsed_time": "2:33:37", "remaining_time": "2:13:47", "throughput": 1317.37, "total_tokens": 12142568} {"current_steps": 21385, "total_steps": 40000, "loss": 0.0, "lr": 2.228787058492979e-05, "epoch": 375.17699115044246, "percentage": 53.46, "elapsed_time": "2:33:39", "remaining_time": "2:13:45", "throughput": 1317.38, "total_tokens": 12145368} {"current_steps": 21390, "total_steps": 40000, "loss": 0.0, "lr": 2.2278111259353875e-05, "epoch": 375.2654867256637, "percentage": 53.47, "elapsed_time": "2:33:41", "remaining_time": "2:13:42", "throughput": 1317.4, "total_tokens": 12148312} {"current_steps": 21395, "total_steps": 40000, "loss": 0.0, "lr": 2.2268352353527395e-05, "epoch": 375.353982300885, "percentage": 53.49, "elapsed_time": "2:33:43", "remaining_time": "2:13:40", "throughput": 1317.38, "total_tokens": 12150776} {"current_steps": 21400, "total_steps": 40000, "loss": 0.0, "lr": 2.225859386895533e-05, "epoch": 375.4424778761062, "percentage": 53.5, "elapsed_time": "2:33:45", "remaining_time": "2:13:38", "throughput": 1317.34, "total_tokens": 12153176} {"current_steps": 21400, "total_steps": 40000, "eval_loss": 0.5526835918426514, "epoch": 375.4424778761062, "percentage": 53.5, "elapsed_time": "2:33:46", "remaining_time": "2:13:39", "throughput": 1317.19, "total_tokens": 12153176} {"current_steps": 21405, "total_steps": 40000, "loss": 0.0, "lr": 2.2248835807142525e-05, "epoch": 375.53097345132744, "percentage": 53.51, "elapsed_time": "2:33:50", "remaining_time": "2:13:38", "throughput": 1316.91, "total_tokens": 12155576} {"current_steps": 21410, "total_steps": 40000, "loss": 0.0, "lr": 2.2239078169593826e-05, "epoch": 375.6194690265487, "percentage": 53.52, "elapsed_time": "2:33:52", "remaining_time": "2:13:36", "throughput": 1316.98, "total_tokens": 12158952} {"current_steps": 21415, "total_steps": 40000, "loss": 0.0, "lr": 2.222932095781396e-05, "epoch": 375.7079646017699, "percentage": 53.54, "elapsed_time": "2:33:54", "remaining_time": "2:13:34", "throughput": 1317.04, "total_tokens": 12162232} {"current_steps": 21420, "total_steps": 40000, "loss": 0.0, "lr": 2.221956417330762e-05, "epoch": 375.79646017699116, "percentage": 53.55, "elapsed_time": "2:33:56", "remaining_time": "2:13:31", "throughput": 1317.06, "total_tokens": 12165160} {"current_steps": 21425, "total_steps": 40000, "loss": 0.0, "lr": 2.2209807817579438e-05, "epoch": 375.88495575221236, "percentage": 53.56, "elapsed_time": "2:33:58", "remaining_time": "2:13:29", "throughput": 1317.04, "total_tokens": 12167704} {"current_steps": 21430, "total_steps": 40000, "loss": 0.0, "lr": 2.220005189213394e-05, "epoch": 375.9734513274336, "percentage": 53.57, "elapsed_time": "2:34:00", "remaining_time": "2:13:27", "throughput": 1317.08, "total_tokens": 12170808} {"current_steps": 21435, "total_steps": 40000, "loss": 0.0, "lr": 2.2190296398475624e-05, "epoch": 376.05309734513276, "percentage": 53.59, "elapsed_time": "2:34:03", "remaining_time": "2:13:25", "throughput": 1317.01, "total_tokens": 12173112} {"current_steps": 21440, "total_steps": 40000, "loss": 0.0, "lr": 2.2180541338108926e-05, "epoch": 376.14159292035396, "percentage": 53.6, "elapsed_time": "2:34:05", "remaining_time": "2:13:23", "throughput": 1316.99, "total_tokens": 12175672} {"current_steps": 21445, "total_steps": 40000, "loss": 0.0, "lr": 2.2170786712538176e-05, "epoch": 376.2300884955752, "percentage": 53.61, "elapsed_time": "2:34:07", "remaining_time": "2:13:20", "throughput": 1317.01, "total_tokens": 12178584} {"current_steps": 21450, "total_steps": 40000, "loss": 0.0, "lr": 2.216103252326768e-05, "epoch": 376.3185840707965, "percentage": 53.62, "elapsed_time": "2:34:09", "remaining_time": "2:13:18", "throughput": 1316.98, "total_tokens": 12181048} {"current_steps": 21455, "total_steps": 40000, "loss": 0.0, "lr": 2.2151278771801635e-05, "epoch": 376.4070796460177, "percentage": 53.64, "elapsed_time": "2:34:11", "remaining_time": "2:13:16", "throughput": 1316.96, "total_tokens": 12183640} {"current_steps": 21460, "total_steps": 40000, "loss": 0.0, "lr": 2.21415254596442e-05, "epoch": 376.49557522123894, "percentage": 53.65, "elapsed_time": "2:34:13", "remaining_time": "2:13:14", "throughput": 1317.05, "total_tokens": 12187160} {"current_steps": 21465, "total_steps": 40000, "loss": 0.0, "lr": 2.213177258829947e-05, "epoch": 376.5840707964602, "percentage": 53.66, "elapsed_time": "2:34:15", "remaining_time": "2:13:12", "throughput": 1317.08, "total_tokens": 12190152} {"current_steps": 21470, "total_steps": 40000, "loss": 0.0, "lr": 2.2122020159271445e-05, "epoch": 376.6725663716814, "percentage": 53.67, "elapsed_time": "2:34:17", "remaining_time": "2:13:09", "throughput": 1317.15, "total_tokens": 12193528} {"current_steps": 21475, "total_steps": 40000, "loss": 0.0, "lr": 2.2112268174064075e-05, "epoch": 376.76106194690266, "percentage": 53.69, "elapsed_time": "2:34:19", "remaining_time": "2:13:07", "throughput": 1317.16, "total_tokens": 12196360} {"current_steps": 21480, "total_steps": 40000, "loss": 0.0, "lr": 2.2102516634181253e-05, "epoch": 376.8495575221239, "percentage": 53.7, "elapsed_time": "2:34:21", "remaining_time": "2:13:05", "throughput": 1317.15, "total_tokens": 12199016} {"current_steps": 21485, "total_steps": 40000, "loss": 0.0, "lr": 2.209276554112677e-05, "epoch": 376.9380530973451, "percentage": 53.71, "elapsed_time": "2:34:23", "remaining_time": "2:13:03", "throughput": 1317.21, "total_tokens": 12202232} {"current_steps": 21490, "total_steps": 40000, "loss": 0.0, "lr": 2.2083014896404384e-05, "epoch": 377.01769911504425, "percentage": 53.73, "elapsed_time": "2:34:25", "remaining_time": "2:13:01", "throughput": 1317.14, "total_tokens": 12204616} {"current_steps": 21495, "total_steps": 40000, "loss": 0.0, "lr": 2.207326470151775e-05, "epoch": 377.1061946902655, "percentage": 53.74, "elapsed_time": "2:34:28", "remaining_time": "2:12:58", "throughput": 1317.18, "total_tokens": 12207736} {"current_steps": 21500, "total_steps": 40000, "loss": 0.0, "lr": 2.2063514957970477e-05, "epoch": 377.1946902654867, "percentage": 53.75, "elapsed_time": "2:34:30", "remaining_time": "2:12:56", "throughput": 1317.24, "total_tokens": 12210952} {"current_steps": 21505, "total_steps": 40000, "loss": 0.0, "lr": 2.205376566726611e-05, "epoch": 377.283185840708, "percentage": 53.76, "elapsed_time": "2:34:32", "remaining_time": "2:12:54", "throughput": 1317.29, "total_tokens": 12214168} {"current_steps": 21510, "total_steps": 40000, "loss": 0.0, "lr": 2.204401683090809e-05, "epoch": 377.37168141592923, "percentage": 53.77, "elapsed_time": "2:34:34", "remaining_time": "2:12:52", "throughput": 1317.29, "total_tokens": 12216920} {"current_steps": 21515, "total_steps": 40000, "loss": 0.0, "lr": 2.203426845039982e-05, "epoch": 377.46017699115043, "percentage": 53.79, "elapsed_time": "2:34:36", "remaining_time": "2:12:49", "throughput": 1317.32, "total_tokens": 12219864} {"current_steps": 21520, "total_steps": 40000, "loss": 0.0, "lr": 2.202452052724464e-05, "epoch": 377.5486725663717, "percentage": 53.8, "elapsed_time": "2:34:38", "remaining_time": "2:12:47", "throughput": 1317.36, "total_tokens": 12223000} {"current_steps": 21525, "total_steps": 40000, "loss": 0.0, "lr": 2.2014773062945777e-05, "epoch": 377.6371681415929, "percentage": 53.81, "elapsed_time": "2:34:40", "remaining_time": "2:12:45", "throughput": 1317.32, "total_tokens": 12225368} {"current_steps": 21530, "total_steps": 40000, "loss": 0.0, "lr": 2.2005026059006427e-05, "epoch": 377.72566371681415, "percentage": 53.83, "elapsed_time": "2:34:42", "remaining_time": "2:12:43", "throughput": 1317.32, "total_tokens": 12228056} {"current_steps": 21535, "total_steps": 40000, "loss": 0.0, "lr": 2.1995279516929695e-05, "epoch": 377.8141592920354, "percentage": 53.84, "elapsed_time": "2:34:44", "remaining_time": "2:12:41", "throughput": 1317.34, "total_tokens": 12230952} {"current_steps": 21540, "total_steps": 40000, "loss": 0.0, "lr": 2.1985533438218613e-05, "epoch": 377.9026548672566, "percentage": 53.85, "elapsed_time": "2:34:46", "remaining_time": "2:12:38", "throughput": 1317.37, "total_tokens": 12233944} {"current_steps": 21545, "total_steps": 40000, "loss": 0.0, "lr": 2.197578782437617e-05, "epoch": 377.9911504424779, "percentage": 53.86, "elapsed_time": "2:34:48", "remaining_time": "2:12:36", "throughput": 1317.36, "total_tokens": 12236552} {"current_steps": 21550, "total_steps": 40000, "loss": 0.0, "lr": 2.196604267690524e-05, "epoch": 378.070796460177, "percentage": 53.87, "elapsed_time": "2:34:51", "remaining_time": "2:12:34", "throughput": 1317.27, "total_tokens": 12238784} {"current_steps": 21555, "total_steps": 40000, "loss": 0.0, "lr": 2.195629799730865e-05, "epoch": 378.1592920353982, "percentage": 53.89, "elapsed_time": "2:34:53", "remaining_time": "2:12:32", "throughput": 1317.24, "total_tokens": 12241248} {"current_steps": 21560, "total_steps": 40000, "loss": 0.0, "lr": 2.1946553787089173e-05, "epoch": 378.24778761061947, "percentage": 53.9, "elapsed_time": "2:34:55", "remaining_time": "2:12:30", "throughput": 1317.32, "total_tokens": 12244688} {"current_steps": 21565, "total_steps": 40000, "loss": 0.0, "lr": 2.193681004774947e-05, "epoch": 378.3362831858407, "percentage": 53.91, "elapsed_time": "2:34:57", "remaining_time": "2:12:27", "throughput": 1317.33, "total_tokens": 12247472} {"current_steps": 21570, "total_steps": 40000, "loss": 0.0, "lr": 2.1927066780792154e-05, "epoch": 378.42477876106193, "percentage": 53.92, "elapsed_time": "2:34:59", "remaining_time": "2:12:25", "throughput": 1317.32, "total_tokens": 12250176} {"current_steps": 21575, "total_steps": 40000, "loss": 0.0, "lr": 2.191732398771975e-05, "epoch": 378.5132743362832, "percentage": 53.94, "elapsed_time": "2:35:01", "remaining_time": "2:12:23", "throughput": 1317.34, "total_tokens": 12253104} {"current_steps": 21580, "total_steps": 40000, "loss": 0.0, "lr": 2.1907581670034725e-05, "epoch": 378.60176991150445, "percentage": 53.95, "elapsed_time": "2:35:03", "remaining_time": "2:12:21", "throughput": 1317.36, "total_tokens": 12256016} {"current_steps": 21585, "total_steps": 40000, "loss": 0.0, "lr": 2.189783982923948e-05, "epoch": 378.69026548672565, "percentage": 53.96, "elapsed_time": "2:35:05", "remaining_time": "2:12:18", "throughput": 1317.4, "total_tokens": 12259088} {"current_steps": 21590, "total_steps": 40000, "loss": 0.0, "lr": 2.1888098466836303e-05, "epoch": 378.7787610619469, "percentage": 53.97, "elapsed_time": "2:35:07", "remaining_time": "2:12:16", "throughput": 1317.41, "total_tokens": 12261824} {"current_steps": 21595, "total_steps": 40000, "loss": 0.0, "lr": 2.1878357584327457e-05, "epoch": 378.86725663716817, "percentage": 53.99, "elapsed_time": "2:35:09", "remaining_time": "2:12:14", "throughput": 1317.46, "total_tokens": 12265008} {"current_steps": 21600, "total_steps": 40000, "loss": 0.0, "lr": 2.1868617183215103e-05, "epoch": 378.95575221238937, "percentage": 54.0, "elapsed_time": "2:35:11", "remaining_time": "2:12:12", "throughput": 1317.49, "total_tokens": 12267984} {"current_steps": 21600, "total_steps": 40000, "eval_loss": 0.534430742263794, "epoch": 378.95575221238937, "percentage": 54.0, "elapsed_time": "2:35:12", "remaining_time": "2:12:13", "throughput": 1317.33, "total_tokens": 12267984} {"current_steps": 21605, "total_steps": 40000, "loss": 0.0, "lr": 2.1858877265001327e-05, "epoch": 379.0353982300885, "percentage": 54.01, "elapsed_time": "2:35:16", "remaining_time": "2:12:12", "throughput": 1317.04, "total_tokens": 12270560} {"current_steps": 21610, "total_steps": 40000, "loss": 0.0, "lr": 2.184913783118816e-05, "epoch": 379.12389380530976, "percentage": 54.02, "elapsed_time": "2:35:18", "remaining_time": "2:12:10", "throughput": 1317.09, "total_tokens": 12273808} {"current_steps": 21615, "total_steps": 40000, "loss": 0.0, "lr": 2.1839398883277522e-05, "epoch": 379.21238938053096, "percentage": 54.04, "elapsed_time": "2:35:20", "remaining_time": "2:12:08", "throughput": 1317.12, "total_tokens": 12276736} {"current_steps": 21620, "total_steps": 40000, "loss": 0.0, "lr": 2.182966042277129e-05, "epoch": 379.3008849557522, "percentage": 54.05, "elapsed_time": "2:35:22", "remaining_time": "2:12:05", "throughput": 1317.13, "total_tokens": 12279600} {"current_steps": 21625, "total_steps": 40000, "loss": 0.0, "lr": 2.181992245117128e-05, "epoch": 379.3893805309734, "percentage": 54.06, "elapsed_time": "2:35:25", "remaining_time": "2:12:03", "throughput": 1317.13, "total_tokens": 12282304} {"current_steps": 21630, "total_steps": 40000, "loss": 0.0, "lr": 2.181018496997918e-05, "epoch": 379.4778761061947, "percentage": 54.07, "elapsed_time": "2:35:27", "remaining_time": "2:12:01", "throughput": 1317.13, "total_tokens": 12285040} {"current_steps": 21635, "total_steps": 40000, "loss": 0.0, "lr": 2.1800447980696648e-05, "epoch": 379.56637168141594, "percentage": 54.09, "elapsed_time": "2:35:29", "remaining_time": "2:11:59", "throughput": 1317.11, "total_tokens": 12287648} {"current_steps": 21640, "total_steps": 40000, "loss": 0.0, "lr": 2.1790711484825248e-05, "epoch": 379.65486725663715, "percentage": 54.1, "elapsed_time": "2:35:31", "remaining_time": "2:11:56", "throughput": 1317.1, "total_tokens": 12290288} {"current_steps": 21645, "total_steps": 40000, "loss": 0.0, "lr": 2.178097548386646e-05, "epoch": 379.7433628318584, "percentage": 54.11, "elapsed_time": "2:35:33", "remaining_time": "2:11:54", "throughput": 1317.14, "total_tokens": 12293376} {"current_steps": 21650, "total_steps": 40000, "loss": 0.0, "lr": 2.1771239979321712e-05, "epoch": 379.83185840707966, "percentage": 54.12, "elapsed_time": "2:35:35", "remaining_time": "2:11:52", "throughput": 1317.11, "total_tokens": 12295840} {"current_steps": 21655, "total_steps": 40000, "loss": 0.0, "lr": 2.1761504972692327e-05, "epoch": 379.92035398230087, "percentage": 54.14, "elapsed_time": "2:35:37", "remaining_time": "2:11:50", "throughput": 1317.11, "total_tokens": 12298528} {"current_steps": 21660, "total_steps": 40000, "loss": 0.0, "lr": 2.1751770465479572e-05, "epoch": 380.0, "percentage": 54.15, "elapsed_time": "2:35:39", "remaining_time": "2:11:48", "throughput": 1317.12, "total_tokens": 12301360} {"current_steps": 21665, "total_steps": 40000, "loss": 0.0, "lr": 2.174203645918464e-05, "epoch": 380.08849557522126, "percentage": 54.16, "elapsed_time": "2:35:41", "remaining_time": "2:11:45", "throughput": 1317.17, "total_tokens": 12304800} {"current_steps": 21670, "total_steps": 40000, "loss": 0.0, "lr": 2.1732302955308624e-05, "epoch": 380.17699115044246, "percentage": 54.17, "elapsed_time": "2:35:44", "remaining_time": "2:11:43", "throughput": 1317.14, "total_tokens": 12307664} {"current_steps": 21675, "total_steps": 40000, "loss": 0.0, "lr": 2.172256995535255e-05, "epoch": 380.2654867256637, "percentage": 54.19, "elapsed_time": "2:35:46", "remaining_time": "2:11:41", "throughput": 1317.17, "total_tokens": 12310624} {"current_steps": 21680, "total_steps": 40000, "loss": 0.0, "lr": 2.171283746081739e-05, "epoch": 380.353982300885, "percentage": 54.2, "elapsed_time": "2:35:48", "remaining_time": "2:11:39", "throughput": 1317.17, "total_tokens": 12313376} {"current_steps": 21685, "total_steps": 40000, "loss": 0.0, "lr": 2.1703105473203988e-05, "epoch": 380.4424778761062, "percentage": 54.21, "elapsed_time": "2:35:50", "remaining_time": "2:11:37", "throughput": 1317.17, "total_tokens": 12316112} {"current_steps": 21690, "total_steps": 40000, "loss": 0.0, "lr": 2.1693373994013168e-05, "epoch": 380.53097345132744, "percentage": 54.23, "elapsed_time": "2:35:52", "remaining_time": "2:11:35", "throughput": 1317.17, "total_tokens": 12318848} {"current_steps": 21695, "total_steps": 40000, "loss": 0.0, "lr": 2.168364302474562e-05, "epoch": 380.6194690265487, "percentage": 54.24, "elapsed_time": "2:35:54", "remaining_time": "2:11:32", "throughput": 1317.17, "total_tokens": 12321536} {"current_steps": 21700, "total_steps": 40000, "loss": 0.0, "lr": 2.167391256690199e-05, "epoch": 380.7079646017699, "percentage": 54.25, "elapsed_time": "2:35:56", "remaining_time": "2:11:30", "throughput": 1317.18, "total_tokens": 12324336} {"current_steps": 21705, "total_steps": 40000, "loss": 0.0, "lr": 2.1664182621982855e-05, "epoch": 380.79646017699116, "percentage": 54.26, "elapsed_time": "2:35:58", "remaining_time": "2:11:28", "throughput": 1317.2, "total_tokens": 12327280} {"current_steps": 21710, "total_steps": 40000, "loss": 0.0, "lr": 2.1654453191488673e-05, "epoch": 380.88495575221236, "percentage": 54.27, "elapsed_time": "2:36:00", "remaining_time": "2:11:26", "throughput": 1317.23, "total_tokens": 12330336} {"current_steps": 21715, "total_steps": 40000, "loss": 0.0, "lr": 2.1644724276919846e-05, "epoch": 380.9734513274336, "percentage": 54.29, "elapsed_time": "2:36:02", "remaining_time": "2:11:23", "throughput": 1317.25, "total_tokens": 12333232} {"current_steps": 21720, "total_steps": 40000, "loss": 0.0, "lr": 2.1634995879776715e-05, "epoch": 381.05309734513276, "percentage": 54.3, "elapsed_time": "2:36:05", "remaining_time": "2:11:21", "throughput": 1317.16, "total_tokens": 12335352} {"current_steps": 21725, "total_steps": 40000, "loss": 0.0, "lr": 2.162526800155949e-05, "epoch": 381.14159292035396, "percentage": 54.31, "elapsed_time": "2:36:07", "remaining_time": "2:11:19", "throughput": 1317.19, "total_tokens": 12338376} {"current_steps": 21730, "total_steps": 40000, "loss": 0.0, "lr": 2.1615540643768363e-05, "epoch": 381.2300884955752, "percentage": 54.33, "elapsed_time": "2:36:09", "remaining_time": "2:11:17", "throughput": 1317.23, "total_tokens": 12341416} {"current_steps": 21735, "total_steps": 40000, "loss": 0.0, "lr": 2.160581380790339e-05, "epoch": 381.3185840707965, "percentage": 54.34, "elapsed_time": "2:36:11", "remaining_time": "2:11:15", "throughput": 1317.27, "total_tokens": 12344568} {"current_steps": 21740, "total_steps": 40000, "loss": 0.0, "lr": 2.1596087495464586e-05, "epoch": 381.4070796460177, "percentage": 54.35, "elapsed_time": "2:36:13", "remaining_time": "2:11:12", "throughput": 1317.31, "total_tokens": 12347592} {"current_steps": 21745, "total_steps": 40000, "loss": 0.0, "lr": 2.1586361707951866e-05, "epoch": 381.49557522123894, "percentage": 54.36, "elapsed_time": "2:36:15", "remaining_time": "2:11:10", "throughput": 1317.36, "total_tokens": 12350808} {"current_steps": 21750, "total_steps": 40000, "loss": 0.0, "lr": 2.157663644686507e-05, "epoch": 381.5840707964602, "percentage": 54.37, "elapsed_time": "2:36:17", "remaining_time": "2:11:08", "throughput": 1317.33, "total_tokens": 12353304} {"current_steps": 21755, "total_steps": 40000, "loss": 0.0, "lr": 2.156691171370396e-05, "epoch": 381.6725663716814, "percentage": 54.39, "elapsed_time": "2:36:19", "remaining_time": "2:11:06", "throughput": 1317.35, "total_tokens": 12356184} {"current_steps": 21760, "total_steps": 40000, "loss": 0.0, "lr": 2.1557187509968195e-05, "epoch": 381.76106194690266, "percentage": 54.4, "elapsed_time": "2:36:21", "remaining_time": "2:11:04", "throughput": 1317.37, "total_tokens": 12359080} {"current_steps": 21765, "total_steps": 40000, "loss": 0.0, "lr": 2.1547463837157382e-05, "epoch": 381.8495575221239, "percentage": 54.41, "elapsed_time": "2:36:23", "remaining_time": "2:11:01", "throughput": 1317.37, "total_tokens": 12361832} {"current_steps": 21770, "total_steps": 40000, "loss": 0.0, "lr": 2.1537740696771045e-05, "epoch": 381.9380530973451, "percentage": 54.43, "elapsed_time": "2:36:25", "remaining_time": "2:10:59", "throughput": 1317.36, "total_tokens": 12364424} {"current_steps": 21775, "total_steps": 40000, "loss": 0.0, "lr": 2.1528018090308587e-05, "epoch": 382.01769911504425, "percentage": 54.44, "elapsed_time": "2:36:28", "remaining_time": "2:10:57", "throughput": 1317.31, "total_tokens": 12366928} {"current_steps": 21780, "total_steps": 40000, "loss": 0.0, "lr": 2.151829601926938e-05, "epoch": 382.1061946902655, "percentage": 54.45, "elapsed_time": "2:36:30", "remaining_time": "2:10:55", "throughput": 1317.3, "total_tokens": 12369616} {"current_steps": 21785, "total_steps": 40000, "loss": 0.0, "lr": 2.1508574485152684e-05, "epoch": 382.1946902654867, "percentage": 54.46, "elapsed_time": "2:36:32", "remaining_time": "2:10:53", "throughput": 1317.34, "total_tokens": 12372720} {"current_steps": 21790, "total_steps": 40000, "loss": 0.0, "lr": 2.1498853489457667e-05, "epoch": 382.283185840708, "percentage": 54.47, "elapsed_time": "2:36:34", "remaining_time": "2:10:50", "throughput": 1317.36, "total_tokens": 12375616} {"current_steps": 21795, "total_steps": 40000, "loss": 0.0, "lr": 2.1489133033683455e-05, "epoch": 382.37168141592923, "percentage": 54.49, "elapsed_time": "2:36:36", "remaining_time": "2:10:48", "throughput": 1317.38, "total_tokens": 12378528} {"current_steps": 21800, "total_steps": 40000, "loss": 0.0, "lr": 2.1479413119329038e-05, "epoch": 382.46017699115043, "percentage": 54.5, "elapsed_time": "2:36:38", "remaining_time": "2:10:46", "throughput": 1317.4, "total_tokens": 12381424} {"current_steps": 21800, "total_steps": 40000, "eval_loss": 0.5042070746421814, "epoch": 382.46017699115043, "percentage": 54.5, "elapsed_time": "2:36:39", "remaining_time": "2:10:47", "throughput": 1317.25, "total_tokens": 12381424} {"current_steps": 21805, "total_steps": 40000, "loss": 0.0, "lr": 2.1469693747893355e-05, "epoch": 382.5486725663717, "percentage": 54.51, "elapsed_time": "2:36:43", "remaining_time": "2:10:46", "throughput": 1317.02, "total_tokens": 12384224} {"current_steps": 21810, "total_steps": 40000, "loss": 0.0, "lr": 2.1459974920875274e-05, "epoch": 382.6371681415929, "percentage": 54.52, "elapsed_time": "2:36:45", "remaining_time": "2:10:44", "throughput": 1317.03, "total_tokens": 12387072} {"current_steps": 21815, "total_steps": 40000, "loss": 0.0, "lr": 2.145025663977354e-05, "epoch": 382.72566371681415, "percentage": 54.54, "elapsed_time": "2:36:47", "remaining_time": "2:10:42", "throughput": 1317.03, "total_tokens": 12389856} {"current_steps": 21820, "total_steps": 40000, "loss": 0.0, "lr": 2.1440538906086844e-05, "epoch": 382.8141592920354, "percentage": 54.55, "elapsed_time": "2:36:49", "remaining_time": "2:10:39", "throughput": 1317.02, "total_tokens": 12392464} {"current_steps": 21825, "total_steps": 40000, "loss": 0.0, "lr": 2.1430821721313782e-05, "epoch": 382.9026548672566, "percentage": 54.56, "elapsed_time": "2:36:51", "remaining_time": "2:10:37", "throughput": 1317.06, "total_tokens": 12395520} {"current_steps": 21830, "total_steps": 40000, "loss": 0.0, "lr": 2.142110508695286e-05, "epoch": 382.9911504424779, "percentage": 54.57, "elapsed_time": "2:36:53", "remaining_time": "2:10:35", "throughput": 1317.08, "total_tokens": 12398432} {"current_steps": 21835, "total_steps": 40000, "loss": 0.0, "lr": 2.1411389004502515e-05, "epoch": 383.070796460177, "percentage": 54.59, "elapsed_time": "2:36:55", "remaining_time": "2:10:33", "throughput": 1317.0, "total_tokens": 12400704} {"current_steps": 21840, "total_steps": 40000, "loss": 0.0, "lr": 2.140167347546107e-05, "epoch": 383.1592920353982, "percentage": 54.6, "elapsed_time": "2:36:57", "remaining_time": "2:10:31", "throughput": 1317.04, "total_tokens": 12403776} {"current_steps": 21845, "total_steps": 40000, "loss": 0.0, "lr": 2.1391958501326793e-05, "epoch": 383.24778761061947, "percentage": 54.61, "elapsed_time": "2:37:00", "remaining_time": "2:10:28", "throughput": 1317.04, "total_tokens": 12406576} {"current_steps": 21850, "total_steps": 40000, "loss": 0.0, "lr": 2.1382244083597873e-05, "epoch": 383.3362831858407, "percentage": 54.62, "elapsed_time": "2:37:02", "remaining_time": "2:10:26", "throughput": 1317.02, "total_tokens": 12409088} {"current_steps": 21855, "total_steps": 40000, "loss": 0.0, "lr": 2.137253022377237e-05, "epoch": 383.42477876106193, "percentage": 54.64, "elapsed_time": "2:37:04", "remaining_time": "2:10:24", "throughput": 1317.04, "total_tokens": 12411952} {"current_steps": 21860, "total_steps": 40000, "loss": 0.0, "lr": 2.136281692334829e-05, "epoch": 383.5132743362832, "percentage": 54.65, "elapsed_time": "2:37:06", "remaining_time": "2:10:22", "throughput": 1317.12, "total_tokens": 12415440} {"current_steps": 21865, "total_steps": 40000, "loss": 0.0, "lr": 2.135310418382356e-05, "epoch": 383.60176991150445, "percentage": 54.66, "elapsed_time": "2:37:08", "remaining_time": "2:10:19", "throughput": 1317.13, "total_tokens": 12418272} {"current_steps": 21870, "total_steps": 40000, "loss": 0.0, "lr": 2.134339200669598e-05, "epoch": 383.69026548672565, "percentage": 54.67, "elapsed_time": "2:37:10", "remaining_time": "2:10:17", "throughput": 1317.14, "total_tokens": 12421120} {"current_steps": 21875, "total_steps": 40000, "loss": 0.0, "lr": 2.133368039346331e-05, "epoch": 383.7787610619469, "percentage": 54.69, "elapsed_time": "2:37:12", "remaining_time": "2:10:15", "throughput": 1317.19, "total_tokens": 12424272} {"current_steps": 21880, "total_steps": 40000, "loss": 0.0, "lr": 2.1323969345623195e-05, "epoch": 383.86725663716817, "percentage": 54.7, "elapsed_time": "2:37:14", "remaining_time": "2:10:13", "throughput": 1317.17, "total_tokens": 12426848} {"current_steps": 21885, "total_steps": 40000, "loss": 0.0, "lr": 2.1314258864673207e-05, "epoch": 383.95575221238937, "percentage": 54.71, "elapsed_time": "2:37:16", "remaining_time": "2:10:10", "throughput": 1317.16, "total_tokens": 12429424} {"current_steps": 21890, "total_steps": 40000, "loss": 0.0, "lr": 2.130454895211082e-05, "epoch": 384.0353982300885, "percentage": 54.73, "elapsed_time": "2:37:18", "remaining_time": "2:10:08", "throughput": 1317.11, "total_tokens": 12431960} {"current_steps": 21895, "total_steps": 40000, "loss": 0.0, "lr": 2.129483960943342e-05, "epoch": 384.12389380530976, "percentage": 54.74, "elapsed_time": "2:37:20", "remaining_time": "2:10:06", "throughput": 1317.13, "total_tokens": 12434840} {"current_steps": 21900, "total_steps": 40000, "loss": 0.0, "lr": 2.128513083813831e-05, "epoch": 384.21238938053096, "percentage": 54.75, "elapsed_time": "2:37:22", "remaining_time": "2:10:04", "throughput": 1317.17, "total_tokens": 12437944} {"current_steps": 21905, "total_steps": 40000, "loss": 0.0, "lr": 2.1275422639722724e-05, "epoch": 384.3008849557522, "percentage": 54.76, "elapsed_time": "2:37:24", "remaining_time": "2:10:02", "throughput": 1317.16, "total_tokens": 12440568} {"current_steps": 21910, "total_steps": 40000, "loss": 0.0, "lr": 2.126571501568376e-05, "epoch": 384.3893805309734, "percentage": 54.77, "elapsed_time": "2:37:27", "remaining_time": "2:09:59", "throughput": 1317.22, "total_tokens": 12443912} {"current_steps": 21915, "total_steps": 40000, "loss": 0.0, "lr": 2.1256007967518478e-05, "epoch": 384.4778761061947, "percentage": 54.79, "elapsed_time": "2:37:29", "remaining_time": "2:09:57", "throughput": 1317.27, "total_tokens": 12447032} {"current_steps": 21920, "total_steps": 40000, "loss": 0.0, "lr": 2.124630149672381e-05, "epoch": 384.56637168141594, "percentage": 54.8, "elapsed_time": "2:37:31", "remaining_time": "2:09:55", "throughput": 1317.24, "total_tokens": 12449544} {"current_steps": 21925, "total_steps": 40000, "loss": 0.0, "lr": 2.1236595604796624e-05, "epoch": 384.65486725663715, "percentage": 54.81, "elapsed_time": "2:37:33", "remaining_time": "2:09:53", "throughput": 1317.27, "total_tokens": 12452504} {"current_steps": 21930, "total_steps": 40000, "loss": 0.0, "lr": 2.1226890293233693e-05, "epoch": 384.7433628318584, "percentage": 54.83, "elapsed_time": "2:37:35", "remaining_time": "2:09:51", "throughput": 1317.3, "total_tokens": 12455560} {"current_steps": 21935, "total_steps": 40000, "loss": 0.0, "lr": 2.1217185563531694e-05, "epoch": 384.83185840707966, "percentage": 54.84, "elapsed_time": "2:37:37", "remaining_time": "2:09:48", "throughput": 1317.29, "total_tokens": 12458104} {"current_steps": 21940, "total_steps": 40000, "loss": 0.0, "lr": 2.120748141718721e-05, "epoch": 384.92035398230087, "percentage": 54.85, "elapsed_time": "2:37:39", "remaining_time": "2:09:46", "throughput": 1317.27, "total_tokens": 12460680} {"current_steps": 21945, "total_steps": 40000, "loss": 0.0, "lr": 2.1197777855696765e-05, "epoch": 385.0, "percentage": 54.86, "elapsed_time": "2:37:41", "remaining_time": "2:09:44", "throughput": 1317.22, "total_tokens": 12462904} {"current_steps": 21950, "total_steps": 40000, "loss": 0.0, "lr": 2.1188074880556746e-05, "epoch": 385.08849557522126, "percentage": 54.87, "elapsed_time": "2:37:43", "remaining_time": "2:09:42", "throughput": 1317.25, "total_tokens": 12466184} {"current_steps": 21955, "total_steps": 40000, "loss": 0.0, "lr": 2.1178372493263495e-05, "epoch": 385.17699115044246, "percentage": 54.89, "elapsed_time": "2:37:45", "remaining_time": "2:09:40", "throughput": 1317.21, "total_tokens": 12468536} {"current_steps": 21960, "total_steps": 40000, "loss": 0.0, "lr": 2.116867069531322e-05, "epoch": 385.2654867256637, "percentage": 54.9, "elapsed_time": "2:37:47", "remaining_time": "2:09:37", "throughput": 1317.18, "total_tokens": 12471016} {"current_steps": 21965, "total_steps": 40000, "loss": 0.0, "lr": 2.1158969488202073e-05, "epoch": 385.353982300885, "percentage": 54.91, "elapsed_time": "2:37:50", "remaining_time": "2:09:35", "throughput": 1317.21, "total_tokens": 12474040} {"current_steps": 21970, "total_steps": 40000, "loss": 0.0, "lr": 2.114926887342611e-05, "epoch": 385.4424778761062, "percentage": 54.93, "elapsed_time": "2:37:52", "remaining_time": "2:09:33", "throughput": 1317.23, "total_tokens": 12476904} {"current_steps": 21975, "total_steps": 40000, "loss": 0.0, "lr": 2.113956885248127e-05, "epoch": 385.53097345132744, "percentage": 54.94, "elapsed_time": "2:37:54", "remaining_time": "2:09:31", "throughput": 1317.24, "total_tokens": 12479768} {"current_steps": 21980, "total_steps": 40000, "loss": 0.0, "lr": 2.112986942686342e-05, "epoch": 385.6194690265487, "percentage": 54.95, "elapsed_time": "2:37:56", "remaining_time": "2:09:28", "throughput": 1317.25, "total_tokens": 12482552} {"current_steps": 21985, "total_steps": 40000, "loss": 0.0, "lr": 2.112017059806835e-05, "epoch": 385.7079646017699, "percentage": 54.96, "elapsed_time": "2:37:58", "remaining_time": "2:09:26", "throughput": 1317.31, "total_tokens": 12485864} {"current_steps": 21990, "total_steps": 40000, "loss": 0.0, "lr": 2.1110472367591724e-05, "epoch": 385.79646017699116, "percentage": 54.97, "elapsed_time": "2:38:00", "remaining_time": "2:09:24", "throughput": 1317.31, "total_tokens": 12488568} {"current_steps": 21995, "total_steps": 40000, "loss": 0.0, "lr": 2.1100774736929145e-05, "epoch": 385.88495575221236, "percentage": 54.99, "elapsed_time": "2:38:02", "remaining_time": "2:09:22", "throughput": 1317.31, "total_tokens": 12491368} {"current_steps": 22000, "total_steps": 40000, "loss": 0.0, "lr": 2.10910777075761e-05, "epoch": 385.9734513274336, "percentage": 55.0, "elapsed_time": "2:38:04", "remaining_time": "2:09:20", "throughput": 1317.34, "total_tokens": 12494280} {"current_steps": 22000, "total_steps": 40000, "eval_loss": 0.5429548621177673, "epoch": 385.9734513274336, "percentage": 55.0, "elapsed_time": "2:38:05", "remaining_time": "2:09:20", "throughput": 1317.19, "total_tokens": 12494280} {"current_steps": 22005, "total_steps": 40000, "loss": 0.0, "lr": 2.108138128102799e-05, "epoch": 386.05309734513276, "percentage": 55.01, "elapsed_time": "2:38:09", "remaining_time": "2:09:20", "throughput": 1316.92, "total_tokens": 12496928} {"current_steps": 22010, "total_steps": 40000, "loss": 0.0, "lr": 2.107168545878014e-05, "epoch": 386.14159292035396, "percentage": 55.02, "elapsed_time": "2:38:11", "remaining_time": "2:09:18", "throughput": 1316.94, "total_tokens": 12499904} {"current_steps": 22015, "total_steps": 40000, "loss": 0.0, "lr": 2.106199024232775e-05, "epoch": 386.2300884955752, "percentage": 55.04, "elapsed_time": "2:38:13", "remaining_time": "2:09:15", "throughput": 1316.95, "total_tokens": 12502752} {"current_steps": 22020, "total_steps": 40000, "loss": 0.0, "lr": 2.105229563316595e-05, "epoch": 386.3185840707965, "percentage": 55.05, "elapsed_time": "2:38:15", "remaining_time": "2:09:13", "throughput": 1316.96, "total_tokens": 12505552} {"current_steps": 22025, "total_steps": 40000, "loss": 0.0, "lr": 2.1042601632789784e-05, "epoch": 386.4070796460177, "percentage": 55.06, "elapsed_time": "2:38:17", "remaining_time": "2:09:11", "throughput": 1316.93, "total_tokens": 12508000} {"current_steps": 22030, "total_steps": 40000, "loss": 0.0, "lr": 2.103290824269417e-05, "epoch": 386.49557522123894, "percentage": 55.07, "elapsed_time": "2:38:19", "remaining_time": "2:09:09", "throughput": 1316.94, "total_tokens": 12510784} {"current_steps": 22035, "total_steps": 40000, "loss": 0.0, "lr": 2.1023215464373965e-05, "epoch": 386.5840707964602, "percentage": 55.09, "elapsed_time": "2:38:21", "remaining_time": "2:09:06", "throughput": 1316.98, "total_tokens": 12513920} {"current_steps": 22040, "total_steps": 40000, "loss": 0.0, "lr": 2.1013523299323908e-05, "epoch": 386.6725663716814, "percentage": 55.1, "elapsed_time": "2:38:24", "remaining_time": "2:09:04", "throughput": 1316.96, "total_tokens": 12516448} {"current_steps": 22045, "total_steps": 40000, "loss": 0.0, "lr": 2.1003831749038654e-05, "epoch": 386.76106194690266, "percentage": 55.11, "elapsed_time": "2:38:26", "remaining_time": "2:09:02", "throughput": 1316.99, "total_tokens": 12519440} {"current_steps": 22050, "total_steps": 40000, "loss": 0.0, "lr": 2.099414081501277e-05, "epoch": 386.8495575221239, "percentage": 55.12, "elapsed_time": "2:38:28", "remaining_time": "2:09:00", "throughput": 1317.03, "total_tokens": 12522544} {"current_steps": 22055, "total_steps": 40000, "loss": 0.0, "lr": 2.09844504987407e-05, "epoch": 386.9380530973451, "percentage": 55.14, "elapsed_time": "2:38:30", "remaining_time": "2:08:58", "throughput": 1317.04, "total_tokens": 12525408} {"current_steps": 22060, "total_steps": 40000, "loss": 0.0, "lr": 2.097476080171683e-05, "epoch": 387.01769911504425, "percentage": 55.15, "elapsed_time": "2:38:32", "remaining_time": "2:08:55", "throughput": 1316.99, "total_tokens": 12527936} {"current_steps": 22065, "total_steps": 40000, "loss": 0.0, "lr": 2.0965071725435436e-05, "epoch": 387.1061946902655, "percentage": 55.16, "elapsed_time": "2:38:34", "remaining_time": "2:08:53", "throughput": 1317.03, "total_tokens": 12530976} {"current_steps": 22070, "total_steps": 40000, "loss": 0.0, "lr": 2.0955383271390684e-05, "epoch": 387.1946902654867, "percentage": 55.17, "elapsed_time": "2:38:36", "remaining_time": "2:08:51", "throughput": 1317.06, "total_tokens": 12533952} {"current_steps": 22075, "total_steps": 40000, "loss": 0.0, "lr": 2.094569544107666e-05, "epoch": 387.283185840708, "percentage": 55.19, "elapsed_time": "2:38:38", "remaining_time": "2:08:49", "throughput": 1317.05, "total_tokens": 12536656} {"current_steps": 22080, "total_steps": 40000, "loss": 0.0, "lr": 2.093600823598735e-05, "epoch": 387.37168141592923, "percentage": 55.2, "elapsed_time": "2:38:40", "remaining_time": "2:08:46", "throughput": 1317.03, "total_tokens": 12539104} {"current_steps": 22085, "total_steps": 40000, "loss": 0.0, "lr": 2.092632165761663e-05, "epoch": 387.46017699115043, "percentage": 55.21, "elapsed_time": "2:38:42", "remaining_time": "2:08:44", "throughput": 1317.04, "total_tokens": 12541920} {"current_steps": 22090, "total_steps": 40000, "loss": 0.0, "lr": 2.091663570745832e-05, "epoch": 387.5486725663717, "percentage": 55.23, "elapsed_time": "2:38:44", "remaining_time": "2:08:42", "throughput": 1317.08, "total_tokens": 12545024} {"current_steps": 22095, "total_steps": 40000, "loss": 0.0, "lr": 2.0906950387006086e-05, "epoch": 387.6371681415929, "percentage": 55.24, "elapsed_time": "2:38:46", "remaining_time": "2:08:40", "throughput": 1317.09, "total_tokens": 12547920} {"current_steps": 22100, "total_steps": 40000, "loss": 0.0, "lr": 2.0897265697753543e-05, "epoch": 387.72566371681415, "percentage": 55.25, "elapsed_time": "2:38:49", "remaining_time": "2:08:38", "throughput": 1317.12, "total_tokens": 12550848} {"current_steps": 22105, "total_steps": 40000, "loss": 0.0, "lr": 2.088758164119419e-05, "epoch": 387.8141592920354, "percentage": 55.26, "elapsed_time": "2:38:51", "remaining_time": "2:08:35", "throughput": 1317.16, "total_tokens": 12553952} {"current_steps": 22110, "total_steps": 40000, "loss": 0.0, "lr": 2.0877898218821428e-05, "epoch": 387.9026548672566, "percentage": 55.27, "elapsed_time": "2:38:53", "remaining_time": "2:08:33", "throughput": 1317.18, "total_tokens": 12556880} {"current_steps": 22115, "total_steps": 40000, "loss": 0.0, "lr": 2.0868215432128565e-05, "epoch": 387.9911504424779, "percentage": 55.29, "elapsed_time": "2:38:55", "remaining_time": "2:08:31", "throughput": 1317.22, "total_tokens": 12559952} {"current_steps": 22120, "total_steps": 40000, "loss": 0.0, "lr": 2.0858533282608796e-05, "epoch": 388.070796460177, "percentage": 55.3, "elapsed_time": "2:38:57", "remaining_time": "2:08:29", "throughput": 1317.21, "total_tokens": 12562832} {"current_steps": 22125, "total_steps": 40000, "loss": 0.0, "lr": 2.084885177175524e-05, "epoch": 388.1592920353982, "percentage": 55.31, "elapsed_time": "2:38:59", "remaining_time": "2:08:27", "throughput": 1317.26, "total_tokens": 12566016} {"current_steps": 22130, "total_steps": 40000, "loss": 0.0, "lr": 2.0839170901060917e-05, "epoch": 388.24778761061947, "percentage": 55.33, "elapsed_time": "2:39:01", "remaining_time": "2:08:24", "throughput": 1317.23, "total_tokens": 12568544} {"current_steps": 22135, "total_steps": 40000, "loss": 0.0, "lr": 2.082949067201872e-05, "epoch": 388.3362831858407, "percentage": 55.34, "elapsed_time": "2:39:03", "remaining_time": "2:08:22", "throughput": 1317.23, "total_tokens": 12571184} {"current_steps": 22140, "total_steps": 40000, "loss": 0.0, "lr": 2.0819811086121475e-05, "epoch": 388.42477876106193, "percentage": 55.35, "elapsed_time": "2:39:05", "remaining_time": "2:08:20", "throughput": 1317.22, "total_tokens": 12573904} {"current_steps": 22145, "total_steps": 40000, "loss": 0.0, "lr": 2.08101321448619e-05, "epoch": 388.5132743362832, "percentage": 55.36, "elapsed_time": "2:39:07", "remaining_time": "2:08:18", "throughput": 1317.24, "total_tokens": 12576800} {"current_steps": 22150, "total_steps": 40000, "loss": 0.0, "lr": 2.080045384973259e-05, "epoch": 388.60176991150445, "percentage": 55.38, "elapsed_time": "2:39:09", "remaining_time": "2:08:15", "throughput": 1317.26, "total_tokens": 12579664} {"current_steps": 22155, "total_steps": 40000, "loss": 0.0, "lr": 2.0790776202226082e-05, "epoch": 388.69026548672565, "percentage": 55.39, "elapsed_time": "2:39:11", "remaining_time": "2:08:13", "throughput": 1317.25, "total_tokens": 12582288} {"current_steps": 22160, "total_steps": 40000, "loss": 0.0, "lr": 2.078109920383477e-05, "epoch": 388.7787610619469, "percentage": 55.4, "elapsed_time": "2:39:14", "remaining_time": "2:08:11", "throughput": 1317.26, "total_tokens": 12585184} {"current_steps": 22165, "total_steps": 40000, "loss": 0.0, "lr": 2.0771422856050978e-05, "epoch": 388.86725663716817, "percentage": 55.41, "elapsed_time": "2:39:16", "remaining_time": "2:08:09", "throughput": 1317.27, "total_tokens": 12587952} {"current_steps": 22170, "total_steps": 40000, "loss": 0.0, "lr": 2.076174716036693e-05, "epoch": 388.95575221238937, "percentage": 55.43, "elapsed_time": "2:39:18", "remaining_time": "2:08:07", "throughput": 1317.3, "total_tokens": 12590960} {"current_steps": 22175, "total_steps": 40000, "loss": 0.0, "lr": 2.075207211827472e-05, "epoch": 389.0353982300885, "percentage": 55.44, "elapsed_time": "2:39:20", "remaining_time": "2:08:04", "throughput": 1317.23, "total_tokens": 12593288} {"current_steps": 22180, "total_steps": 40000, "loss": 0.0, "lr": 2.074239773126638e-05, "epoch": 389.12389380530976, "percentage": 55.45, "elapsed_time": "2:39:22", "remaining_time": "2:08:02", "throughput": 1317.25, "total_tokens": 12596200} {"current_steps": 22185, "total_steps": 40000, "loss": 0.0, "lr": 2.073272400083382e-05, "epoch": 389.21238938053096, "percentage": 55.46, "elapsed_time": "2:39:24", "remaining_time": "2:08:00", "throughput": 1317.29, "total_tokens": 12599256} {"current_steps": 22190, "total_steps": 40000, "loss": 0.0, "lr": 2.072305092846883e-05, "epoch": 389.3008849557522, "percentage": 55.47, "elapsed_time": "2:39:26", "remaining_time": "2:07:58", "throughput": 1317.27, "total_tokens": 12601800} {"current_steps": 22195, "total_steps": 40000, "loss": 0.0, "lr": 2.0713378515663152e-05, "epoch": 389.3893805309734, "percentage": 55.49, "elapsed_time": "2:39:28", "remaining_time": "2:07:56", "throughput": 1317.31, "total_tokens": 12604984} {"current_steps": 22200, "total_steps": 40000, "loss": 0.0, "lr": 2.070370676390836e-05, "epoch": 389.4778761061947, "percentage": 55.5, "elapsed_time": "2:39:30", "remaining_time": "2:07:53", "throughput": 1317.34, "total_tokens": 12608008} {"current_steps": 22200, "total_steps": 40000, "eval_loss": 0.5208003520965576, "epoch": 389.4778761061947, "percentage": 55.5, "elapsed_time": "2:39:31", "remaining_time": "2:07:54", "throughput": 1317.2, "total_tokens": 12608008} {"current_steps": 22205, "total_steps": 40000, "loss": 0.0, "lr": 2.0694035674695974e-05, "epoch": 389.56637168141594, "percentage": 55.51, "elapsed_time": "2:39:35", "remaining_time": "2:07:53", "throughput": 1316.98, "total_tokens": 12610984} {"current_steps": 22210, "total_steps": 40000, "loss": 0.0, "lr": 2.0684365249517416e-05, "epoch": 389.65486725663715, "percentage": 55.53, "elapsed_time": "2:39:37", "remaining_time": "2:07:51", "throughput": 1316.95, "total_tokens": 12613400} {"current_steps": 22215, "total_steps": 40000, "loss": 0.0, "lr": 2.067469548986396e-05, "epoch": 389.7433628318584, "percentage": 55.54, "elapsed_time": "2:39:39", "remaining_time": "2:07:49", "throughput": 1316.93, "total_tokens": 12615992} {"current_steps": 22220, "total_steps": 40000, "loss": 0.0, "lr": 2.066502639722681e-05, "epoch": 389.83185840707966, "percentage": 55.55, "elapsed_time": "2:39:41", "remaining_time": "2:07:47", "throughput": 1316.97, "total_tokens": 12619112} {"current_steps": 22225, "total_steps": 40000, "loss": 0.0, "lr": 2.065535797309708e-05, "epoch": 389.92035398230087, "percentage": 55.56, "elapsed_time": "2:39:43", "remaining_time": "2:07:45", "throughput": 1317.0, "total_tokens": 12622136} {"current_steps": 22230, "total_steps": 40000, "loss": 0.0, "lr": 2.0645690218965736e-05, "epoch": 390.0, "percentage": 55.57, "elapsed_time": "2:39:45", "remaining_time": "2:07:42", "throughput": 1316.98, "total_tokens": 12624536} {"current_steps": 22235, "total_steps": 40000, "loss": 0.0, "lr": 2.063602313632369e-05, "epoch": 390.08849557522126, "percentage": 55.59, "elapsed_time": "2:39:48", "remaining_time": "2:07:40", "throughput": 1317.01, "total_tokens": 12627944} {"current_steps": 22240, "total_steps": 40000, "loss": 0.0, "lr": 2.0626356726661704e-05, "epoch": 390.17699115044246, "percentage": 55.6, "elapsed_time": "2:39:50", "remaining_time": "2:07:38", "throughput": 1317.05, "total_tokens": 12631048} {"current_steps": 22245, "total_steps": 40000, "loss": 0.0, "lr": 2.0616690991470477e-05, "epoch": 390.2654867256637, "percentage": 55.61, "elapsed_time": "2:39:52", "remaining_time": "2:07:36", "throughput": 1317.03, "total_tokens": 12633560} {"current_steps": 22250, "total_steps": 40000, "loss": 0.0, "lr": 2.0607025932240595e-05, "epoch": 390.353982300885, "percentage": 55.62, "elapsed_time": "2:39:54", "remaining_time": "2:07:34", "throughput": 1317.06, "total_tokens": 12636600} {"current_steps": 22255, "total_steps": 40000, "loss": 0.0, "lr": 2.059736155046251e-05, "epoch": 390.4424778761062, "percentage": 55.64, "elapsed_time": "2:39:56", "remaining_time": "2:07:31", "throughput": 1317.06, "total_tokens": 12639320} {"current_steps": 22260, "total_steps": 40000, "loss": 0.0, "lr": 2.0587697847626603e-05, "epoch": 390.53097345132744, "percentage": 55.65, "elapsed_time": "2:39:58", "remaining_time": "2:07:29", "throughput": 1317.09, "total_tokens": 12642328} {"current_steps": 22265, "total_steps": 40000, "loss": 0.0, "lr": 2.057803482522314e-05, "epoch": 390.6194690265487, "percentage": 55.66, "elapsed_time": "2:40:00", "remaining_time": "2:07:27", "throughput": 1317.08, "total_tokens": 12644936} {"current_steps": 22270, "total_steps": 40000, "loss": 0.0, "lr": 2.056837248474227e-05, "epoch": 390.7079646017699, "percentage": 55.67, "elapsed_time": "2:40:02", "remaining_time": "2:07:25", "throughput": 1317.05, "total_tokens": 12647432} {"current_steps": 22275, "total_steps": 40000, "loss": 0.0, "lr": 2.0558710827674064e-05, "epoch": 390.79646017699116, "percentage": 55.69, "elapsed_time": "2:40:04", "remaining_time": "2:07:22", "throughput": 1317.05, "total_tokens": 12650072} {"current_steps": 22280, "total_steps": 40000, "loss": 0.0, "lr": 2.054904985550845e-05, "epoch": 390.88495575221236, "percentage": 55.7, "elapsed_time": "2:40:06", "remaining_time": "2:07:20", "throughput": 1317.04, "total_tokens": 12652728} {"current_steps": 22285, "total_steps": 40000, "loss": 0.0, "lr": 2.0539389569735287e-05, "epoch": 390.9734513274336, "percentage": 55.71, "elapsed_time": "2:40:09", "remaining_time": "2:07:18", "throughput": 1317.13, "total_tokens": 12656328} {"current_steps": 22290, "total_steps": 40000, "loss": 0.0, "lr": 2.052972997184431e-05, "epoch": 391.05309734513276, "percentage": 55.73, "elapsed_time": "2:40:11", "remaining_time": "2:07:16", "throughput": 1317.08, "total_tokens": 12658760} {"current_steps": 22295, "total_steps": 40000, "loss": 0.0, "lr": 2.0520071063325146e-05, "epoch": 391.14159292035396, "percentage": 55.74, "elapsed_time": "2:40:13", "remaining_time": "2:07:14", "throughput": 1317.07, "total_tokens": 12661448} {"current_steps": 22300, "total_steps": 40000, "loss": 0.0, "lr": 2.051041284566732e-05, "epoch": 391.2300884955752, "percentage": 55.75, "elapsed_time": "2:40:15", "remaining_time": "2:07:11", "throughput": 1317.15, "total_tokens": 12664920} {"current_steps": 22305, "total_steps": 40000, "loss": 0.0, "lr": 2.050075532036026e-05, "epoch": 391.3185840707965, "percentage": 55.76, "elapsed_time": "2:40:17", "remaining_time": "2:07:09", "throughput": 1317.17, "total_tokens": 12667864} {"current_steps": 22310, "total_steps": 40000, "loss": 0.0, "lr": 2.0491098488893264e-05, "epoch": 391.4070796460177, "percentage": 55.77, "elapsed_time": "2:40:19", "remaining_time": "2:07:07", "throughput": 1317.23, "total_tokens": 12671160} {"current_steps": 22315, "total_steps": 40000, "loss": 0.0, "lr": 2.0481442352755546e-05, "epoch": 391.49557522123894, "percentage": 55.79, "elapsed_time": "2:40:21", "remaining_time": "2:07:05", "throughput": 1317.21, "total_tokens": 12673672} {"current_steps": 22320, "total_steps": 40000, "loss": 0.0, "lr": 2.0471786913436198e-05, "epoch": 391.5840707964602, "percentage": 55.8, "elapsed_time": "2:40:23", "remaining_time": "2:07:03", "throughput": 1317.22, "total_tokens": 12676552} {"current_steps": 22325, "total_steps": 40000, "loss": 0.0, "lr": 2.0462132172424218e-05, "epoch": 391.6725663716814, "percentage": 55.81, "elapsed_time": "2:40:25", "remaining_time": "2:07:00", "throughput": 1317.21, "total_tokens": 12679160} {"current_steps": 22330, "total_steps": 40000, "loss": 0.0, "lr": 2.0452478131208484e-05, "epoch": 391.76106194690266, "percentage": 55.83, "elapsed_time": "2:40:27", "remaining_time": "2:06:58", "throughput": 1317.19, "total_tokens": 12681640} {"current_steps": 22335, "total_steps": 40000, "loss": 0.0, "lr": 2.0442824791277765e-05, "epoch": 391.8495575221239, "percentage": 55.84, "elapsed_time": "2:40:29", "remaining_time": "2:06:56", "throughput": 1317.18, "total_tokens": 12684328} {"current_steps": 22340, "total_steps": 40000, "loss": 0.0, "lr": 2.0433172154120727e-05, "epoch": 391.9380530973451, "percentage": 55.85, "elapsed_time": "2:40:31", "remaining_time": "2:06:54", "throughput": 1317.2, "total_tokens": 12687224} {"current_steps": 22345, "total_steps": 40000, "loss": 0.0, "lr": 2.0423520221225947e-05, "epoch": 392.01769911504425, "percentage": 55.86, "elapsed_time": "2:40:34", "remaining_time": "2:06:52", "throughput": 1317.14, "total_tokens": 12689680} {"current_steps": 22350, "total_steps": 40000, "loss": 0.0, "lr": 2.0413868994081848e-05, "epoch": 392.1061946902655, "percentage": 55.88, "elapsed_time": "2:40:36", "remaining_time": "2:06:49", "throughput": 1317.14, "total_tokens": 12692400} {"current_steps": 22355, "total_steps": 40000, "loss": 0.0, "lr": 2.0404218474176795e-05, "epoch": 392.1946902654867, "percentage": 55.89, "elapsed_time": "2:40:38", "remaining_time": "2:06:47", "throughput": 1317.2, "total_tokens": 12695712} {"current_steps": 22360, "total_steps": 40000, "loss": 0.0, "lr": 2.0394568662999002e-05, "epoch": 392.283185840708, "percentage": 55.9, "elapsed_time": "2:40:40", "remaining_time": "2:06:45", "throughput": 1317.2, "total_tokens": 12698448} {"current_steps": 22365, "total_steps": 40000, "loss": 0.0, "lr": 2.0384919562036593e-05, "epoch": 392.37168141592923, "percentage": 55.91, "elapsed_time": "2:40:42", "remaining_time": "2:06:43", "throughput": 1317.21, "total_tokens": 12701216} {"current_steps": 22370, "total_steps": 40000, "loss": 0.0, "lr": 2.0375271172777593e-05, "epoch": 392.46017699115043, "percentage": 55.93, "elapsed_time": "2:40:44", "remaining_time": "2:06:40", "throughput": 1317.21, "total_tokens": 12703984} {"current_steps": 22375, "total_steps": 40000, "loss": 0.0, "lr": 2.0365623496709885e-05, "epoch": 392.5486725663717, "percentage": 55.94, "elapsed_time": "2:40:46", "remaining_time": "2:06:38", "throughput": 1317.29, "total_tokens": 12707440} {"current_steps": 22380, "total_steps": 40000, "loss": 0.0, "lr": 2.0355976535321283e-05, "epoch": 392.6371681415929, "percentage": 55.95, "elapsed_time": "2:40:48", "remaining_time": "2:06:36", "throughput": 1317.31, "total_tokens": 12710336} {"current_steps": 22385, "total_steps": 40000, "loss": 0.0, "lr": 2.034633029009945e-05, "epoch": 392.72566371681415, "percentage": 55.96, "elapsed_time": "2:40:50", "remaining_time": "2:06:34", "throughput": 1317.3, "total_tokens": 12713024} {"current_steps": 22390, "total_steps": 40000, "loss": 0.0, "lr": 2.0336684762531972e-05, "epoch": 392.8141592920354, "percentage": 55.97, "elapsed_time": "2:40:52", "remaining_time": "2:06:32", "throughput": 1317.32, "total_tokens": 12715952} {"current_steps": 22395, "total_steps": 40000, "loss": 0.0, "lr": 2.032703995410631e-05, "epoch": 392.9026548672566, "percentage": 55.99, "elapsed_time": "2:40:54", "remaining_time": "2:06:29", "throughput": 1317.32, "total_tokens": 12718672} {"current_steps": 22400, "total_steps": 40000, "loss": 0.0, "lr": 2.031739586630981e-05, "epoch": 392.9911504424779, "percentage": 56.0, "elapsed_time": "2:40:56", "remaining_time": "2:06:27", "throughput": 1317.33, "total_tokens": 12721456} {"current_steps": 22400, "total_steps": 40000, "eval_loss": 0.5806827545166016, "epoch": 392.9911504424779, "percentage": 56.0, "elapsed_time": "2:40:58", "remaining_time": "2:06:28", "throughput": 1317.18, "total_tokens": 12721456} {"current_steps": 22405, "total_steps": 40000, "loss": 0.0, "lr": 2.0307752500629707e-05, "epoch": 393.070796460177, "percentage": 56.01, "elapsed_time": "2:41:02", "remaining_time": "2:06:27", "throughput": 1316.91, "total_tokens": 12724032} {"current_steps": 22410, "total_steps": 40000, "loss": 0.0, "lr": 2.0298109858553144e-05, "epoch": 393.1592920353982, "percentage": 56.03, "elapsed_time": "2:41:04", "remaining_time": "2:06:25", "throughput": 1316.93, "total_tokens": 12727008} {"current_steps": 22415, "total_steps": 40000, "loss": 0.0, "lr": 2.028846794156712e-05, "epoch": 393.24778761061947, "percentage": 56.04, "elapsed_time": "2:41:06", "remaining_time": "2:06:23", "throughput": 1316.96, "total_tokens": 12730048} {"current_steps": 22420, "total_steps": 40000, "loss": 0.0, "lr": 2.027882675115856e-05, "epoch": 393.3362831858407, "percentage": 56.05, "elapsed_time": "2:41:08", "remaining_time": "2:06:21", "throughput": 1316.98, "total_tokens": 12732960} {"current_steps": 22425, "total_steps": 40000, "loss": 0.0, "lr": 2.026918628881423e-05, "epoch": 393.42477876106193, "percentage": 56.06, "elapsed_time": "2:41:10", "remaining_time": "2:06:18", "throughput": 1316.98, "total_tokens": 12735632} {"current_steps": 22430, "total_steps": 40000, "loss": 0.0, "lr": 2.0259546556020833e-05, "epoch": 393.5132743362832, "percentage": 56.07, "elapsed_time": "2:41:12", "remaining_time": "2:06:16", "throughput": 1316.97, "total_tokens": 12738240} {"current_steps": 22435, "total_steps": 40000, "loss": 0.0, "lr": 2.024990755426493e-05, "epoch": 393.60176991150445, "percentage": 56.09, "elapsed_time": "2:41:14", "remaining_time": "2:06:14", "throughput": 1316.92, "total_tokens": 12740544} {"current_steps": 22440, "total_steps": 40000, "loss": 0.0, "lr": 2.0240269285032975e-05, "epoch": 393.69026548672565, "percentage": 56.1, "elapsed_time": "2:41:16", "remaining_time": "2:06:12", "throughput": 1316.98, "total_tokens": 12743872} {"current_steps": 22445, "total_steps": 40000, "loss": 0.0, "lr": 2.0230631749811306e-05, "epoch": 393.7787610619469, "percentage": 56.11, "elapsed_time": "2:41:18", "remaining_time": "2:06:09", "throughput": 1316.97, "total_tokens": 12746496} {"current_steps": 22450, "total_steps": 40000, "loss": 0.0, "lr": 2.0220994950086162e-05, "epoch": 393.86725663716817, "percentage": 56.12, "elapsed_time": "2:41:20", "remaining_time": "2:06:07", "throughput": 1317.01, "total_tokens": 12749568} {"current_steps": 22455, "total_steps": 40000, "loss": 0.0, "lr": 2.021135888734365e-05, "epoch": 393.95575221238937, "percentage": 56.14, "elapsed_time": "2:41:22", "remaining_time": "2:06:05", "throughput": 1317.09, "total_tokens": 12753008} {"current_steps": 22460, "total_steps": 40000, "loss": 0.0, "lr": 2.0201723563069783e-05, "epoch": 394.0353982300885, "percentage": 56.15, "elapsed_time": "2:41:25", "remaining_time": "2:06:03", "throughput": 1317.01, "total_tokens": 12755224} {"current_steps": 22465, "total_steps": 40000, "loss": 0.0, "lr": 2.0192088978750433e-05, "epoch": 394.12389380530976, "percentage": 56.16, "elapsed_time": "2:41:27", "remaining_time": "2:06:01", "throughput": 1317.0, "total_tokens": 12757896} {"current_steps": 22470, "total_steps": 40000, "loss": 0.0, "lr": 2.0182455135871385e-05, "epoch": 394.21238938053096, "percentage": 56.17, "elapsed_time": "2:41:29", "remaining_time": "2:05:59", "throughput": 1317.02, "total_tokens": 12760840} {"current_steps": 22475, "total_steps": 40000, "loss": 0.0, "lr": 2.0172822035918305e-05, "epoch": 394.3008849557522, "percentage": 56.19, "elapsed_time": "2:41:31", "remaining_time": "2:05:56", "throughput": 1317.03, "total_tokens": 12763656} {"current_steps": 22480, "total_steps": 40000, "loss": 0.0, "lr": 2.016318968037671e-05, "epoch": 394.3893805309734, "percentage": 56.2, "elapsed_time": "2:41:33", "remaining_time": "2:05:54", "throughput": 1317.07, "total_tokens": 12766712} {"current_steps": 22485, "total_steps": 40000, "loss": 0.0, "lr": 2.015355807073206e-05, "epoch": 394.4778761061947, "percentage": 56.21, "elapsed_time": "2:41:35", "remaining_time": "2:05:52", "throughput": 1317.06, "total_tokens": 12769368} {"current_steps": 22490, "total_steps": 40000, "loss": 0.0, "lr": 2.0143927208469664e-05, "epoch": 394.56637168141594, "percentage": 56.23, "elapsed_time": "2:41:37", "remaining_time": "2:05:50", "throughput": 1317.11, "total_tokens": 12772568} {"current_steps": 22495, "total_steps": 40000, "loss": 0.0, "lr": 2.0134297095074708e-05, "epoch": 394.65486725663715, "percentage": 56.24, "elapsed_time": "2:41:39", "remaining_time": "2:05:47", "throughput": 1317.11, "total_tokens": 12775304} {"current_steps": 22500, "total_steps": 40000, "loss": 0.0, "lr": 2.0124667732032297e-05, "epoch": 394.7433628318584, "percentage": 56.25, "elapsed_time": "2:41:41", "remaining_time": "2:05:45", "throughput": 1317.13, "total_tokens": 12778184} {"current_steps": 22505, "total_steps": 40000, "loss": 0.0, "lr": 2.011503912082738e-05, "epoch": 394.83185840707966, "percentage": 56.26, "elapsed_time": "2:41:43", "remaining_time": "2:05:43", "throughput": 1317.15, "total_tokens": 12781112} {"current_steps": 22510, "total_steps": 40000, "loss": 0.0, "lr": 2.0105411262944823e-05, "epoch": 394.92035398230087, "percentage": 56.27, "elapsed_time": "2:41:45", "remaining_time": "2:05:41", "throughput": 1317.15, "total_tokens": 12783848} {"current_steps": 22515, "total_steps": 40000, "loss": 0.0, "lr": 2.0095784159869366e-05, "epoch": 395.0, "percentage": 56.29, "elapsed_time": "2:41:47", "remaining_time": "2:05:38", "throughput": 1317.16, "total_tokens": 12786624} {"current_steps": 22520, "total_steps": 40000, "loss": 0.0, "lr": 2.0086157813085608e-05, "epoch": 395.08849557522126, "percentage": 56.3, "elapsed_time": "2:41:49", "remaining_time": "2:05:36", "throughput": 1317.12, "total_tokens": 12789248} {"current_steps": 22525, "total_steps": 40000, "loss": 0.0, "lr": 2.0076532224078068e-05, "epoch": 395.17699115044246, "percentage": 56.31, "elapsed_time": "2:41:52", "remaining_time": "2:05:34", "throughput": 1317.13, "total_tokens": 12792016} {"current_steps": 22530, "total_steps": 40000, "loss": 0.0, "lr": 2.0066907394331142e-05, "epoch": 395.2654867256637, "percentage": 56.33, "elapsed_time": "2:41:54", "remaining_time": "2:05:32", "throughput": 1317.21, "total_tokens": 12795568} {"current_steps": 22535, "total_steps": 40000, "loss": 0.0, "lr": 2.0057283325329077e-05, "epoch": 395.353982300885, "percentage": 56.34, "elapsed_time": "2:41:56", "remaining_time": "2:05:30", "throughput": 1317.24, "total_tokens": 12798624} {"current_steps": 22540, "total_steps": 40000, "loss": 0.0, "lr": 2.0047660018556047e-05, "epoch": 395.4424778761062, "percentage": 56.35, "elapsed_time": "2:41:58", "remaining_time": "2:05:28", "throughput": 1317.22, "total_tokens": 12801184} {"current_steps": 22545, "total_steps": 40000, "loss": 0.0, "lr": 2.0038037475496075e-05, "epoch": 395.53097345132744, "percentage": 56.36, "elapsed_time": "2:42:00", "remaining_time": "2:05:25", "throughput": 1317.22, "total_tokens": 12803872} {"current_steps": 22550, "total_steps": 40000, "loss": 0.0, "lr": 2.0028415697633073e-05, "epoch": 395.6194690265487, "percentage": 56.38, "elapsed_time": "2:42:02", "remaining_time": "2:05:23", "throughput": 1317.21, "total_tokens": 12806544} {"current_steps": 22555, "total_steps": 40000, "loss": 0.0, "lr": 2.0018794686450858e-05, "epoch": 395.7079646017699, "percentage": 56.39, "elapsed_time": "2:42:04", "remaining_time": "2:05:21", "throughput": 1317.23, "total_tokens": 12809376} {"current_steps": 22560, "total_steps": 40000, "loss": 0.0, "lr": 2.0009174443433088e-05, "epoch": 395.79646017699116, "percentage": 56.4, "elapsed_time": "2:42:06", "remaining_time": "2:05:19", "throughput": 1317.25, "total_tokens": 12812368} {"current_steps": 22565, "total_steps": 40000, "loss": 0.0, "lr": 1.999955497006334e-05, "epoch": 395.88495575221236, "percentage": 56.41, "elapsed_time": "2:42:08", "remaining_time": "2:05:16", "throughput": 1317.29, "total_tokens": 12815424} {"current_steps": 22570, "total_steps": 40000, "loss": 0.0, "lr": 1.9989936267825067e-05, "epoch": 395.9734513274336, "percentage": 56.43, "elapsed_time": "2:42:10", "remaining_time": "2:05:14", "throughput": 1317.3, "total_tokens": 12818208} {"current_steps": 22575, "total_steps": 40000, "loss": 0.0, "lr": 1.9980318338201572e-05, "epoch": 396.05309734513276, "percentage": 56.44, "elapsed_time": "2:42:12", "remaining_time": "2:05:12", "throughput": 1317.23, "total_tokens": 12820568} {"current_steps": 22580, "total_steps": 40000, "loss": 0.0, "lr": 1.997070118267607e-05, "epoch": 396.14159292035396, "percentage": 56.45, "elapsed_time": "2:42:15", "remaining_time": "2:05:10", "throughput": 1317.25, "total_tokens": 12823480} {"current_steps": 22585, "total_steps": 40000, "loss": 0.0, "lr": 1.9961084802731654e-05, "epoch": 396.2300884955752, "percentage": 56.46, "elapsed_time": "2:42:17", "remaining_time": "2:05:08", "throughput": 1317.24, "total_tokens": 12826072} {"current_steps": 22590, "total_steps": 40000, "loss": 0.0, "lr": 1.9951469199851273e-05, "epoch": 396.3185840707965, "percentage": 56.47, "elapsed_time": "2:42:19", "remaining_time": "2:05:05", "throughput": 1317.27, "total_tokens": 12829112} {"current_steps": 22595, "total_steps": 40000, "loss": 0.0, "lr": 1.99418543755178e-05, "epoch": 396.4070796460177, "percentage": 56.49, "elapsed_time": "2:42:21", "remaining_time": "2:05:03", "throughput": 1317.27, "total_tokens": 12831832} {"current_steps": 22600, "total_steps": 40000, "loss": 0.0, "lr": 1.9932240331213936e-05, "epoch": 396.49557522123894, "percentage": 56.5, "elapsed_time": "2:42:23", "remaining_time": "2:05:01", "throughput": 1317.34, "total_tokens": 12835240} {"current_steps": 22600, "total_steps": 40000, "eval_loss": 0.5170691013336182, "epoch": 396.49557522123894, "percentage": 56.5, "elapsed_time": "2:42:24", "remaining_time": "2:05:02", "throughput": 1317.2, "total_tokens": 12835240} {"current_steps": 22605, "total_steps": 40000, "loss": 0.0, "lr": 1.9922627068422297e-05, "epoch": 396.5840707964602, "percentage": 56.51, "elapsed_time": "2:42:28", "remaining_time": "2:05:01", "throughput": 1317.05, "total_tokens": 12838904} {"current_steps": 22610, "total_steps": 40000, "loss": 0.0, "lr": 1.991301458862538e-05, "epoch": 396.6725663716814, "percentage": 56.53, "elapsed_time": "2:42:30", "remaining_time": "2:04:59", "throughput": 1317.07, "total_tokens": 12841800} {"current_steps": 22615, "total_steps": 40000, "loss": 0.0, "lr": 1.9903402893305536e-05, "epoch": 396.76106194690266, "percentage": 56.54, "elapsed_time": "2:42:32", "remaining_time": "2:04:56", "throughput": 1317.07, "total_tokens": 12844472} {"current_steps": 22620, "total_steps": 40000, "loss": 0.0, "lr": 1.9893791983945016e-05, "epoch": 396.8495575221239, "percentage": 56.55, "elapsed_time": "2:42:34", "remaining_time": "2:04:54", "throughput": 1317.06, "total_tokens": 12847128} {"current_steps": 22625, "total_steps": 40000, "loss": 0.0, "lr": 1.988418186202594e-05, "epoch": 396.9380530973451, "percentage": 56.56, "elapsed_time": "2:42:36", "remaining_time": "2:04:52", "throughput": 1317.04, "total_tokens": 12849640} {"current_steps": 22630, "total_steps": 40000, "loss": 0.0, "lr": 1.98745725290303e-05, "epoch": 397.01769911504425, "percentage": 56.57, "elapsed_time": "2:42:38", "remaining_time": "2:04:50", "throughput": 1316.95, "total_tokens": 12851704} {"current_steps": 22635, "total_steps": 40000, "loss": 0.0, "lr": 1.986496398644e-05, "epoch": 397.1061946902655, "percentage": 56.59, "elapsed_time": "2:42:40", "remaining_time": "2:04:48", "throughput": 1316.94, "total_tokens": 12854392} {"current_steps": 22640, "total_steps": 40000, "loss": 0.0, "lr": 1.9855356235736777e-05, "epoch": 397.1946902654867, "percentage": 56.6, "elapsed_time": "2:42:42", "remaining_time": "2:04:46", "throughput": 1316.93, "total_tokens": 12857016} {"current_steps": 22645, "total_steps": 40000, "loss": 0.0, "lr": 1.9845749278402277e-05, "epoch": 397.283185840708, "percentage": 56.61, "elapsed_time": "2:42:44", "remaining_time": "2:04:43", "throughput": 1316.95, "total_tokens": 12859896} {"current_steps": 22650, "total_steps": 40000, "loss": 0.0, "lr": 1.9836143115918006e-05, "epoch": 397.37168141592923, "percentage": 56.62, "elapsed_time": "2:42:47", "remaining_time": "2:04:41", "throughput": 1316.96, "total_tokens": 12862744} {"current_steps": 22655, "total_steps": 40000, "loss": 0.0, "lr": 1.9826537749765367e-05, "epoch": 397.46017699115043, "percentage": 56.64, "elapsed_time": "2:42:49", "remaining_time": "2:04:39", "throughput": 1316.96, "total_tokens": 12865464} {"current_steps": 22660, "total_steps": 40000, "loss": 0.0, "lr": 1.9816933181425625e-05, "epoch": 397.5486725663717, "percentage": 56.65, "elapsed_time": "2:42:51", "remaining_time": "2:04:37", "throughput": 1316.95, "total_tokens": 12868120} {"current_steps": 22665, "total_steps": 40000, "loss": 0.0, "lr": 1.9807329412379903e-05, "epoch": 397.6371681415929, "percentage": 56.66, "elapsed_time": "2:42:53", "remaining_time": "2:04:34", "throughput": 1316.98, "total_tokens": 12871112} {"current_steps": 22670, "total_steps": 40000, "loss": 0.0, "lr": 1.9797726444109247e-05, "epoch": 397.72566371681415, "percentage": 56.67, "elapsed_time": "2:42:55", "remaining_time": "2:04:32", "throughput": 1317.0, "total_tokens": 12874008} {"current_steps": 22675, "total_steps": 40000, "loss": 0.0, "lr": 1.9788124278094557e-05, "epoch": 397.8141592920354, "percentage": 56.69, "elapsed_time": "2:42:57", "remaining_time": "2:04:30", "throughput": 1317.04, "total_tokens": 12877112} {"current_steps": 22680, "total_steps": 40000, "loss": 0.0, "lr": 1.9778522915816594e-05, "epoch": 397.9026548672566, "percentage": 56.7, "elapsed_time": "2:42:59", "remaining_time": "2:04:28", "throughput": 1317.05, "total_tokens": 12879944} {"current_steps": 22685, "total_steps": 40000, "loss": 0.0, "lr": 1.9768922358756014e-05, "epoch": 397.9911504424779, "percentage": 56.71, "elapsed_time": "2:43:01", "remaining_time": "2:04:25", "throughput": 1317.15, "total_tokens": 12883672} {"current_steps": 22690, "total_steps": 40000, "loss": 0.0, "lr": 1.9759322608393353e-05, "epoch": 398.070796460177, "percentage": 56.73, "elapsed_time": "2:43:03", "remaining_time": "2:04:23", "throughput": 1317.12, "total_tokens": 12886360} {"current_steps": 22695, "total_steps": 40000, "loss": 0.0, "lr": 1.9749723666208992e-05, "epoch": 398.1592920353982, "percentage": 56.74, "elapsed_time": "2:43:05", "remaining_time": "2:04:21", "throughput": 1317.1, "total_tokens": 12888904} {"current_steps": 22700, "total_steps": 40000, "loss": 0.0, "lr": 1.9740125533683235e-05, "epoch": 398.24778761061947, "percentage": 56.75, "elapsed_time": "2:43:07", "remaining_time": "2:04:19", "throughput": 1317.13, "total_tokens": 12891864} {"current_steps": 22705, "total_steps": 40000, "loss": 0.0, "lr": 1.9730528212296208e-05, "epoch": 398.3362831858407, "percentage": 56.76, "elapsed_time": "2:43:09", "remaining_time": "2:04:17", "throughput": 1317.16, "total_tokens": 12894888} {"current_steps": 22710, "total_steps": 40000, "loss": 0.0, "lr": 1.9720931703527945e-05, "epoch": 398.42477876106193, "percentage": 56.77, "elapsed_time": "2:43:12", "remaining_time": "2:04:15", "throughput": 1317.17, "total_tokens": 12897768} {"current_steps": 22715, "total_steps": 40000, "loss": 0.0, "lr": 1.9711336008858373e-05, "epoch": 398.5132743362832, "percentage": 56.79, "elapsed_time": "2:43:14", "remaining_time": "2:04:12", "throughput": 1317.16, "total_tokens": 12900392} {"current_steps": 22720, "total_steps": 40000, "loss": 0.0, "lr": 1.9701741129767233e-05, "epoch": 398.60176991150445, "percentage": 56.8, "elapsed_time": "2:43:16", "remaining_time": "2:04:10", "throughput": 1317.18, "total_tokens": 12903304} {"current_steps": 22725, "total_steps": 40000, "loss": 0.0, "lr": 1.9692147067734202e-05, "epoch": 398.69026548672565, "percentage": 56.81, "elapsed_time": "2:43:18", "remaining_time": "2:04:08", "throughput": 1317.22, "total_tokens": 12906360} {"current_steps": 22730, "total_steps": 40000, "loss": 0.0, "lr": 1.96825538242388e-05, "epoch": 398.7787610619469, "percentage": 56.83, "elapsed_time": "2:43:20", "remaining_time": "2:04:06", "throughput": 1317.25, "total_tokens": 12909448} {"current_steps": 22735, "total_steps": 40000, "loss": 0.0, "lr": 1.967296140076041e-05, "epoch": 398.86725663716817, "percentage": 56.84, "elapsed_time": "2:43:22", "remaining_time": "2:04:03", "throughput": 1317.27, "total_tokens": 12912376} {"current_steps": 22740, "total_steps": 40000, "loss": 0.0, "lr": 1.966336979877833e-05, "epoch": 398.95575221238937, "percentage": 56.85, "elapsed_time": "2:43:24", "remaining_time": "2:04:01", "throughput": 1317.25, "total_tokens": 12914872} {"current_steps": 22745, "total_steps": 40000, "loss": 0.0, "lr": 1.9653779019771678e-05, "epoch": 399.0353982300885, "percentage": 56.86, "elapsed_time": "2:43:26", "remaining_time": "2:03:59", "throughput": 1317.18, "total_tokens": 12917160} {"current_steps": 22750, "total_steps": 40000, "loss": 0.0, "lr": 1.9644189065219488e-05, "epoch": 399.12389380530976, "percentage": 56.88, "elapsed_time": "2:43:28", "remaining_time": "2:03:57", "throughput": 1317.17, "total_tokens": 12919800} {"current_steps": 22755, "total_steps": 40000, "loss": 0.0, "lr": 1.9634599936600655e-05, "epoch": 399.21238938053096, "percentage": 56.89, "elapsed_time": "2:43:30", "remaining_time": "2:03:55", "throughput": 1317.21, "total_tokens": 12922920} {"current_steps": 22760, "total_steps": 40000, "loss": 0.0, "lr": 1.9625011635393935e-05, "epoch": 399.3008849557522, "percentage": 56.9, "elapsed_time": "2:43:32", "remaining_time": "2:03:52", "throughput": 1317.21, "total_tokens": 12925656} {"current_steps": 22765, "total_steps": 40000, "loss": 0.0, "lr": 1.9615424163077963e-05, "epoch": 399.3893805309734, "percentage": 56.91, "elapsed_time": "2:43:34", "remaining_time": "2:03:50", "throughput": 1317.23, "total_tokens": 12928568} {"current_steps": 22770, "total_steps": 40000, "loss": 0.0, "lr": 1.9605837521131263e-05, "epoch": 399.4778761061947, "percentage": 56.93, "elapsed_time": "2:43:37", "remaining_time": "2:03:48", "throughput": 1317.27, "total_tokens": 12931720} {"current_steps": 22775, "total_steps": 40000, "loss": 0.0, "lr": 1.9596251711032192e-05, "epoch": 399.56637168141594, "percentage": 56.94, "elapsed_time": "2:43:39", "remaining_time": "2:03:46", "throughput": 1317.25, "total_tokens": 12934264} {"current_steps": 22780, "total_steps": 40000, "loss": 0.0, "lr": 1.958666673425903e-05, "epoch": 399.65486725663715, "percentage": 56.95, "elapsed_time": "2:43:41", "remaining_time": "2:03:44", "throughput": 1317.34, "total_tokens": 12937848} {"current_steps": 22785, "total_steps": 40000, "loss": 0.0, "lr": 1.957708259228987e-05, "epoch": 399.7433628318584, "percentage": 56.96, "elapsed_time": "2:43:43", "remaining_time": "2:03:41", "throughput": 1317.35, "total_tokens": 12940632} {"current_steps": 22790, "total_steps": 40000, "loss": 0.0, "lr": 1.956749928660273e-05, "epoch": 399.83185840707966, "percentage": 56.97, "elapsed_time": "2:43:45", "remaining_time": "2:03:39", "throughput": 1317.36, "total_tokens": 12943512} {"current_steps": 22795, "total_steps": 40000, "loss": 0.0, "lr": 1.955791681867547e-05, "epoch": 399.92035398230087, "percentage": 56.99, "elapsed_time": "2:43:47", "remaining_time": "2:03:37", "throughput": 1317.39, "total_tokens": 12946456} {"current_steps": 22800, "total_steps": 40000, "loss": 0.0, "lr": 1.9548335189985824e-05, "epoch": 400.0, "percentage": 57.0, "elapsed_time": "2:43:49", "remaining_time": "2:03:35", "throughput": 1317.32, "total_tokens": 12948416} {"current_steps": 22800, "total_steps": 40000, "eval_loss": 0.5288233160972595, "epoch": 400.0, "percentage": 57.0, "elapsed_time": "2:43:50", "remaining_time": "2:03:35", "throughput": 1317.17, "total_tokens": 12948416} {"current_steps": 22805, "total_steps": 40000, "loss": 0.0, "lr": 1.9538754402011396e-05, "epoch": 400.08849557522126, "percentage": 57.01, "elapsed_time": "2:43:54", "remaining_time": "2:03:35", "throughput": 1316.95, "total_tokens": 12951568} {"current_steps": 22810, "total_steps": 40000, "loss": 0.0, "lr": 1.952917445622968e-05, "epoch": 400.17699115044246, "percentage": 57.03, "elapsed_time": "2:43:56", "remaining_time": "2:03:33", "throughput": 1316.93, "total_tokens": 12954160} {"current_steps": 22815, "total_steps": 40000, "loss": 0.0, "lr": 1.9519595354118005e-05, "epoch": 400.2654867256637, "percentage": 57.04, "elapsed_time": "2:43:58", "remaining_time": "2:03:30", "throughput": 1316.96, "total_tokens": 12957136} {"current_steps": 22820, "total_steps": 40000, "loss": 0.0, "lr": 1.951001709715361e-05, "epoch": 400.353982300885, "percentage": 57.05, "elapsed_time": "2:44:00", "remaining_time": "2:03:28", "throughput": 1316.94, "total_tokens": 12959712} {"current_steps": 22825, "total_steps": 40000, "loss": 0.0, "lr": 1.9500439686813556e-05, "epoch": 400.4424778761062, "percentage": 57.06, "elapsed_time": "2:44:02", "remaining_time": "2:03:26", "throughput": 1316.94, "total_tokens": 12962416} {"current_steps": 22830, "total_steps": 40000, "loss": 0.0, "lr": 1.949086312457482e-05, "epoch": 400.53097345132744, "percentage": 57.07, "elapsed_time": "2:44:04", "remaining_time": "2:03:24", "throughput": 1316.97, "total_tokens": 12965456} {"current_steps": 22835, "total_steps": 40000, "loss": 0.0, "lr": 1.9481287411914223e-05, "epoch": 400.6194690265487, "percentage": 57.09, "elapsed_time": "2:44:07", "remaining_time": "2:03:21", "throughput": 1317.0, "total_tokens": 12968480} {"current_steps": 22840, "total_steps": 40000, "loss": 0.0, "lr": 1.9471712550308457e-05, "epoch": 400.7079646017699, "percentage": 57.1, "elapsed_time": "2:44:09", "remaining_time": "2:03:19", "throughput": 1317.01, "total_tokens": 12971376} {"current_steps": 22845, "total_steps": 40000, "loss": 0.0, "lr": 1.946213854123409e-05, "epoch": 400.79646017699116, "percentage": 57.11, "elapsed_time": "2:44:11", "remaining_time": "2:03:17", "throughput": 1317.03, "total_tokens": 12974288} {"current_steps": 22850, "total_steps": 40000, "loss": 0.0, "lr": 1.9452565386167554e-05, "epoch": 400.88495575221236, "percentage": 57.12, "elapsed_time": "2:44:13", "remaining_time": "2:03:15", "throughput": 1317.03, "total_tokens": 12976928} {"current_steps": 22855, "total_steps": 40000, "loss": 0.0, "lr": 1.9442993086585142e-05, "epoch": 400.9734513274336, "percentage": 57.14, "elapsed_time": "2:44:15", "remaining_time": "2:03:13", "throughput": 1317.03, "total_tokens": 12979712} {"current_steps": 22860, "total_steps": 40000, "loss": 0.0, "lr": 1.9433421643963043e-05, "epoch": 401.05309734513276, "percentage": 57.15, "elapsed_time": "2:44:17", "remaining_time": "2:03:11", "throughput": 1316.98, "total_tokens": 12982208} {"current_steps": 22865, "total_steps": 40000, "loss": 0.0, "lr": 1.942385105977727e-05, "epoch": 401.14159292035396, "percentage": 57.16, "elapsed_time": "2:44:19", "remaining_time": "2:03:08", "throughput": 1317.01, "total_tokens": 12985184} {"current_steps": 22870, "total_steps": 40000, "loss": 0.0, "lr": 1.9414281335503743e-05, "epoch": 401.2300884955752, "percentage": 57.17, "elapsed_time": "2:44:21", "remaining_time": "2:03:06", "throughput": 1317.01, "total_tokens": 12987984} {"current_steps": 22875, "total_steps": 40000, "loss": 0.0, "lr": 1.9404712472618232e-05, "epoch": 401.3185840707965, "percentage": 57.19, "elapsed_time": "2:44:23", "remaining_time": "2:03:04", "throughput": 1316.98, "total_tokens": 12990400} {"current_steps": 22880, "total_steps": 40000, "loss": 0.0, "lr": 1.939514447259636e-05, "epoch": 401.4070796460177, "percentage": 57.2, "elapsed_time": "2:44:25", "remaining_time": "2:03:02", "throughput": 1317.0, "total_tokens": 12993296} {"current_steps": 22885, "total_steps": 40000, "loss": 0.0, "lr": 1.938557733691365e-05, "epoch": 401.49557522123894, "percentage": 57.21, "elapsed_time": "2:44:27", "remaining_time": "2:02:59", "throughput": 1317.02, "total_tokens": 12996224} {"current_steps": 22890, "total_steps": 40000, "loss": 0.0, "lr": 1.9376011067045476e-05, "epoch": 401.5840707964602, "percentage": 57.23, "elapsed_time": "2:44:29", "remaining_time": "2:02:57", "throughput": 1317.05, "total_tokens": 12999248} {"current_steps": 22895, "total_steps": 40000, "loss": 0.0, "lr": 1.9366445664467065e-05, "epoch": 401.6725663716814, "percentage": 57.24, "elapsed_time": "2:44:32", "remaining_time": "2:02:55", "throughput": 1317.12, "total_tokens": 13002672} {"current_steps": 22900, "total_steps": 40000, "loss": 0.0, "lr": 1.9356881130653533e-05, "epoch": 401.76106194690266, "percentage": 57.25, "elapsed_time": "2:44:34", "remaining_time": "2:02:53", "throughput": 1317.18, "total_tokens": 13005984} {"current_steps": 22905, "total_steps": 40000, "loss": 0.0, "lr": 1.9347317467079846e-05, "epoch": 401.8495575221239, "percentage": 57.26, "elapsed_time": "2:44:36", "remaining_time": "2:02:51", "throughput": 1317.15, "total_tokens": 13008480} {"current_steps": 22910, "total_steps": 40000, "loss": 0.0, "lr": 1.9337754675220836e-05, "epoch": 401.9380530973451, "percentage": 57.27, "elapsed_time": "2:44:38", "remaining_time": "2:02:48", "throughput": 1317.14, "total_tokens": 13011088} {"current_steps": 22915, "total_steps": 40000, "loss": 0.0, "lr": 1.9328192756551218e-05, "epoch": 402.01769911504425, "percentage": 57.29, "elapsed_time": "2:44:40", "remaining_time": "2:02:46", "throughput": 1317.09, "total_tokens": 13013504} {"current_steps": 22920, "total_steps": 40000, "loss": 0.0, "lr": 1.931863171254555e-05, "epoch": 402.1061946902655, "percentage": 57.3, "elapsed_time": "2:44:42", "remaining_time": "2:02:44", "throughput": 1317.1, "total_tokens": 13016416} {"current_steps": 22925, "total_steps": 40000, "loss": 0.0, "lr": 1.930907154467826e-05, "epoch": 402.1946902654867, "percentage": 57.31, "elapsed_time": "2:44:44", "remaining_time": "2:02:42", "throughput": 1317.09, "total_tokens": 13018992} {"current_steps": 22930, "total_steps": 40000, "loss": 0.0, "lr": 1.9299512254423673e-05, "epoch": 402.283185840708, "percentage": 57.33, "elapsed_time": "2:44:46", "remaining_time": "2:02:40", "throughput": 1317.13, "total_tokens": 13022208} {"current_steps": 22935, "total_steps": 40000, "loss": 0.0, "lr": 1.9289953843255914e-05, "epoch": 402.37168141592923, "percentage": 57.34, "elapsed_time": "2:44:48", "remaining_time": "2:02:37", "throughput": 1317.13, "total_tokens": 13024912} {"current_steps": 22940, "total_steps": 40000, "loss": 0.0, "lr": 1.9280396312649048e-05, "epoch": 402.46017699115043, "percentage": 57.35, "elapsed_time": "2:44:50", "remaining_time": "2:02:35", "throughput": 1317.15, "total_tokens": 13027872} {"current_steps": 22945, "total_steps": 40000, "loss": 0.0, "lr": 1.9270839664076936e-05, "epoch": 402.5486725663717, "percentage": 57.36, "elapsed_time": "2:44:53", "remaining_time": "2:02:33", "throughput": 1317.16, "total_tokens": 13030640} {"current_steps": 22950, "total_steps": 40000, "loss": 0.0, "lr": 1.9261283899013345e-05, "epoch": 402.6371681415929, "percentage": 57.38, "elapsed_time": "2:44:55", "remaining_time": "2:02:31", "throughput": 1317.21, "total_tokens": 13033904} {"current_steps": 22955, "total_steps": 40000, "loss": 0.0, "lr": 1.92517290189319e-05, "epoch": 402.72566371681415, "percentage": 57.39, "elapsed_time": "2:44:57", "remaining_time": "2:02:29", "throughput": 1317.23, "total_tokens": 13036784} {"current_steps": 22960, "total_steps": 40000, "loss": 0.0, "lr": 1.924217502530607e-05, "epoch": 402.8141592920354, "percentage": 57.4, "elapsed_time": "2:44:59", "remaining_time": "2:02:26", "throughput": 1317.25, "total_tokens": 13039744} {"current_steps": 22965, "total_steps": 40000, "loss": 0.0, "lr": 1.9232621919609207e-05, "epoch": 402.9026548672566, "percentage": 57.41, "elapsed_time": "2:45:01", "remaining_time": "2:02:24", "throughput": 1317.24, "total_tokens": 13042384} {"current_steps": 22970, "total_steps": 40000, "loss": 0.0, "lr": 1.9223069703314534e-05, "epoch": 402.9911504424779, "percentage": 57.43, "elapsed_time": "2:45:03", "remaining_time": "2:02:22", "throughput": 1317.25, "total_tokens": 13045216} {"current_steps": 22975, "total_steps": 40000, "loss": 0.0, "lr": 1.92135183778951e-05, "epoch": 403.070796460177, "percentage": 57.44, "elapsed_time": "2:45:05", "remaining_time": "2:02:20", "throughput": 1317.19, "total_tokens": 13047600} {"current_steps": 22980, "total_steps": 40000, "loss": 0.0, "lr": 1.9203967944823857e-05, "epoch": 403.1592920353982, "percentage": 57.45, "elapsed_time": "2:45:07", "remaining_time": "2:02:18", "throughput": 1317.15, "total_tokens": 13049888} {"current_steps": 22985, "total_steps": 40000, "loss": 0.0, "lr": 1.9194418405573588e-05, "epoch": 403.24778761061947, "percentage": 57.46, "elapsed_time": "2:45:09", "remaining_time": "2:02:15", "throughput": 1317.18, "total_tokens": 13052912} {"current_steps": 22990, "total_steps": 40000, "loss": 0.0, "lr": 1.9184869761616954e-05, "epoch": 403.3362831858407, "percentage": 57.48, "elapsed_time": "2:45:11", "remaining_time": "2:02:13", "throughput": 1317.17, "total_tokens": 13055584} {"current_steps": 22995, "total_steps": 40000, "loss": 0.0, "lr": 1.9175322014426495e-05, "epoch": 403.42477876106193, "percentage": 57.49, "elapsed_time": "2:45:13", "remaining_time": "2:02:11", "throughput": 1317.22, "total_tokens": 13058736} {"current_steps": 23000, "total_steps": 40000, "loss": 0.0, "lr": 1.9165775165474565e-05, "epoch": 403.5132743362832, "percentage": 57.5, "elapsed_time": "2:45:15", "remaining_time": "2:02:09", "throughput": 1317.22, "total_tokens": 13061472} {"current_steps": 23000, "total_steps": 40000, "eval_loss": 0.5603658556938171, "epoch": 403.5132743362832, "percentage": 57.5, "elapsed_time": "2:45:17", "remaining_time": "2:02:09", "throughput": 1317.07, "total_tokens": 13061472} {"current_steps": 23005, "total_steps": 40000, "loss": 0.0, "lr": 1.9156229216233434e-05, "epoch": 403.60176991150445, "percentage": 57.51, "elapsed_time": "2:45:20", "remaining_time": "2:02:09", "throughput": 1316.88, "total_tokens": 13064528} {"current_steps": 23010, "total_steps": 40000, "loss": 0.0, "lr": 1.9146684168175184e-05, "epoch": 403.69026548672565, "percentage": 57.53, "elapsed_time": "2:45:22", "remaining_time": "2:02:06", "throughput": 1316.93, "total_tokens": 13067712} {"current_steps": 23015, "total_steps": 40000, "loss": 0.0, "lr": 1.9137140022771796e-05, "epoch": 403.7787610619469, "percentage": 57.54, "elapsed_time": "2:45:24", "remaining_time": "2:02:04", "throughput": 1316.93, "total_tokens": 13070528} {"current_steps": 23020, "total_steps": 40000, "loss": 0.0, "lr": 1.9127596781495103e-05, "epoch": 403.86725663716817, "percentage": 57.55, "elapsed_time": "2:45:27", "remaining_time": "2:02:02", "throughput": 1316.94, "total_tokens": 13073328} {"current_steps": 23025, "total_steps": 40000, "loss": 0.0, "lr": 1.9118054445816767e-05, "epoch": 403.95575221238937, "percentage": 57.56, "elapsed_time": "2:45:29", "remaining_time": "2:02:00", "throughput": 1317.0, "total_tokens": 13076688} {"current_steps": 23030, "total_steps": 40000, "loss": 0.0, "lr": 1.9108513017208356e-05, "epoch": 404.0353982300885, "percentage": 57.57, "elapsed_time": "2:45:31", "remaining_time": "2:01:58", "throughput": 1316.96, "total_tokens": 13079304} {"current_steps": 23035, "total_steps": 40000, "loss": 0.0, "lr": 1.9098972497141287e-05, "epoch": 404.12389380530976, "percentage": 57.59, "elapsed_time": "2:45:33", "remaining_time": "2:01:55", "throughput": 1316.96, "total_tokens": 13082024} {"current_steps": 23040, "total_steps": 40000, "loss": 0.0, "lr": 1.9089432887086806e-05, "epoch": 404.21238938053096, "percentage": 57.6, "elapsed_time": "2:45:35", "remaining_time": "2:01:53", "throughput": 1316.96, "total_tokens": 13084680} {"current_steps": 23045, "total_steps": 40000, "loss": 0.0, "lr": 1.9079894188516056e-05, "epoch": 404.3008849557522, "percentage": 57.61, "elapsed_time": "2:45:37", "remaining_time": "2:01:51", "throughput": 1317.0, "total_tokens": 13087848} {"current_steps": 23050, "total_steps": 40000, "loss": 0.0, "lr": 1.907035640290002e-05, "epoch": 404.3893805309734, "percentage": 57.63, "elapsed_time": "2:45:39", "remaining_time": "2:01:49", "throughput": 1317.03, "total_tokens": 13090840} {"current_steps": 23055, "total_steps": 40000, "loss": 0.0, "lr": 1.9060819531709534e-05, "epoch": 404.4778761061947, "percentage": 57.64, "elapsed_time": "2:45:41", "remaining_time": "2:01:46", "throughput": 1317.04, "total_tokens": 13093688} {"current_steps": 23060, "total_steps": 40000, "loss": 0.0, "lr": 1.9051283576415325e-05, "epoch": 404.56637168141594, "percentage": 57.65, "elapsed_time": "2:45:43", "remaining_time": "2:01:44", "throughput": 1317.06, "total_tokens": 13096616} {"current_steps": 23065, "total_steps": 40000, "loss": 0.0, "lr": 1.904174853848793e-05, "epoch": 404.65486725663715, "percentage": 57.66, "elapsed_time": "2:45:45", "remaining_time": "2:01:42", "throughput": 1317.11, "total_tokens": 13099816} {"current_steps": 23070, "total_steps": 40000, "loss": 0.0, "lr": 1.903221441939779e-05, "epoch": 404.7433628318584, "percentage": 57.67, "elapsed_time": "2:45:47", "remaining_time": "2:01:40", "throughput": 1317.12, "total_tokens": 13102680} {"current_steps": 23075, "total_steps": 40000, "loss": 0.0, "lr": 1.9022681220615194e-05, "epoch": 404.83185840707966, "percentage": 57.69, "elapsed_time": "2:45:50", "remaining_time": "2:01:38", "throughput": 1317.11, "total_tokens": 13105320} {"current_steps": 23080, "total_steps": 40000, "loss": 0.0, "lr": 1.9013148943610255e-05, "epoch": 404.92035398230087, "percentage": 57.7, "elapsed_time": "2:45:52", "remaining_time": "2:01:35", "throughput": 1317.1, "total_tokens": 13107912} {"current_steps": 23085, "total_steps": 40000, "loss": 0.0, "lr": 1.9003617589852998e-05, "epoch": 405.0, "percentage": 57.71, "elapsed_time": "2:45:54", "remaining_time": "2:01:33", "throughput": 1317.06, "total_tokens": 13110120} {"current_steps": 23090, "total_steps": 40000, "loss": 0.0, "lr": 1.899408716081326e-05, "epoch": 405.08849557522126, "percentage": 57.73, "elapsed_time": "2:45:56", "remaining_time": "2:01:31", "throughput": 1317.03, "total_tokens": 13112888} {"current_steps": 23095, "total_steps": 40000, "loss": 0.0, "lr": 1.898455765796075e-05, "epoch": 405.17699115044246, "percentage": 57.74, "elapsed_time": "2:45:58", "remaining_time": "2:01:29", "throughput": 1317.04, "total_tokens": 13115752} {"current_steps": 23100, "total_steps": 40000, "loss": 0.0, "lr": 1.8975029082765053e-05, "epoch": 405.2654867256637, "percentage": 57.75, "elapsed_time": "2:46:00", "remaining_time": "2:01:27", "throughput": 1317.04, "total_tokens": 13118424} {"current_steps": 23105, "total_steps": 40000, "loss": 0.0, "lr": 1.8965501436695577e-05, "epoch": 405.353982300885, "percentage": 57.76, "elapsed_time": "2:46:02", "remaining_time": "2:01:24", "throughput": 1317.06, "total_tokens": 13121432} {"current_steps": 23110, "total_steps": 40000, "loss": 0.0, "lr": 1.895597472122161e-05, "epoch": 405.4424778761062, "percentage": 57.77, "elapsed_time": "2:46:04", "remaining_time": "2:01:22", "throughput": 1317.05, "total_tokens": 13124024} {"current_steps": 23115, "total_steps": 40000, "loss": 0.0, "lr": 1.894644893781231e-05, "epoch": 405.53097345132744, "percentage": 57.79, "elapsed_time": "2:46:06", "remaining_time": "2:01:20", "throughput": 1317.09, "total_tokens": 13127096} {"current_steps": 23120, "total_steps": 40000, "loss": 0.0, "lr": 1.893692408793665e-05, "epoch": 405.6194690265487, "percentage": 57.8, "elapsed_time": "2:46:08", "remaining_time": "2:01:18", "throughput": 1317.12, "total_tokens": 13130136} {"current_steps": 23125, "total_steps": 40000, "loss": 0.0, "lr": 1.8927400173063493e-05, "epoch": 405.7079646017699, "percentage": 57.81, "elapsed_time": "2:46:10", "remaining_time": "2:01:16", "throughput": 1317.19, "total_tokens": 13133576} {"current_steps": 23130, "total_steps": 40000, "loss": 0.0, "lr": 1.891787719466154e-05, "epoch": 405.79646017699116, "percentage": 57.83, "elapsed_time": "2:46:13", "remaining_time": "2:01:13", "throughput": 1317.2, "total_tokens": 13136472} {"current_steps": 23135, "total_steps": 40000, "loss": 0.0, "lr": 1.8908355154199346e-05, "epoch": 405.88495575221236, "percentage": 57.84, "elapsed_time": "2:46:15", "remaining_time": "2:01:11", "throughput": 1317.22, "total_tokens": 13139368} {"current_steps": 23140, "total_steps": 40000, "loss": 0.0, "lr": 1.8898834053145357e-05, "epoch": 405.9734513274336, "percentage": 57.85, "elapsed_time": "2:46:17", "remaining_time": "2:01:09", "throughput": 1317.22, "total_tokens": 13142104} {"current_steps": 23145, "total_steps": 40000, "loss": 0.0, "lr": 1.8889313892967813e-05, "epoch": 406.05309734513276, "percentage": 57.86, "elapsed_time": "2:46:19", "remaining_time": "2:01:07", "throughput": 1317.2, "total_tokens": 13144904} {"current_steps": 23150, "total_steps": 40000, "loss": 0.0, "lr": 1.8879794675134863e-05, "epoch": 406.14159292035396, "percentage": 57.88, "elapsed_time": "2:46:21", "remaining_time": "2:01:05", "throughput": 1317.24, "total_tokens": 13148008} {"current_steps": 23155, "total_steps": 40000, "loss": 0.0, "lr": 1.8870276401114494e-05, "epoch": 406.2300884955752, "percentage": 57.89, "elapsed_time": "2:46:23", "remaining_time": "2:01:02", "throughput": 1317.27, "total_tokens": 13151032} {"current_steps": 23160, "total_steps": 40000, "loss": 0.0, "lr": 1.886075907237453e-05, "epoch": 406.3185840707965, "percentage": 57.9, "elapsed_time": "2:46:25", "remaining_time": "2:01:00", "throughput": 1317.31, "total_tokens": 13154152} {"current_steps": 23165, "total_steps": 40000, "loss": 0.0, "lr": 1.8851242690382672e-05, "epoch": 406.4070796460177, "percentage": 57.91, "elapsed_time": "2:46:27", "remaining_time": "2:00:58", "throughput": 1317.3, "total_tokens": 13156744} {"current_steps": 23170, "total_steps": 40000, "loss": 0.0, "lr": 1.884172725660645e-05, "epoch": 406.49557522123894, "percentage": 57.93, "elapsed_time": "2:46:29", "remaining_time": "2:00:56", "throughput": 1317.3, "total_tokens": 13159512} {"current_steps": 23175, "total_steps": 40000, "loss": 0.0, "lr": 1.8832212772513277e-05, "epoch": 406.5840707964602, "percentage": 57.94, "elapsed_time": "2:46:31", "remaining_time": "2:00:54", "throughput": 1317.3, "total_tokens": 13162248} {"current_steps": 23180, "total_steps": 40000, "loss": 0.0, "lr": 1.8822699239570414e-05, "epoch": 406.6725663716814, "percentage": 57.95, "elapsed_time": "2:46:33", "remaining_time": "2:00:51", "throughput": 1317.35, "total_tokens": 13165464} {"current_steps": 23185, "total_steps": 40000, "loss": 0.0, "lr": 1.8813186659244943e-05, "epoch": 406.76106194690266, "percentage": 57.96, "elapsed_time": "2:46:35", "remaining_time": "2:00:49", "throughput": 1317.32, "total_tokens": 13167848} {"current_steps": 23190, "total_steps": 40000, "loss": 0.0, "lr": 1.880367503300385e-05, "epoch": 406.8495575221239, "percentage": 57.98, "elapsed_time": "2:46:38", "remaining_time": "2:00:47", "throughput": 1317.32, "total_tokens": 13170648} {"current_steps": 23195, "total_steps": 40000, "loss": 0.0, "lr": 1.8794164362313927e-05, "epoch": 406.9380530973451, "percentage": 57.99, "elapsed_time": "2:46:40", "remaining_time": "2:00:45", "throughput": 1317.34, "total_tokens": 13173528} {"current_steps": 23200, "total_steps": 40000, "loss": 0.0, "lr": 1.878465464864185e-05, "epoch": 407.01769911504425, "percentage": 58.0, "elapsed_time": "2:46:42", "remaining_time": "2:00:43", "throughput": 1317.28, "total_tokens": 13175888} {"current_steps": 23200, "total_steps": 40000, "eval_loss": 0.5697670578956604, "epoch": 407.01769911504425, "percentage": 58.0, "elapsed_time": "2:46:43", "remaining_time": "2:00:43", "throughput": 1317.14, "total_tokens": 13175888} {"current_steps": 23205, "total_steps": 40000, "loss": 0.0, "lr": 1.877514589345414e-05, "epoch": 407.1061946902655, "percentage": 58.01, "elapsed_time": "2:46:47", "remaining_time": "2:00:43", "throughput": 1316.9, "total_tokens": 13178864} {"current_steps": 23210, "total_steps": 40000, "loss": 0.0, "lr": 1.876563809821715e-05, "epoch": 407.1946902654867, "percentage": 58.03, "elapsed_time": "2:46:49", "remaining_time": "2:00:40", "throughput": 1316.9, "total_tokens": 13181568} {"current_steps": 23215, "total_steps": 40000, "loss": 0.0, "lr": 1.8756131264397106e-05, "epoch": 407.283185840708, "percentage": 58.04, "elapsed_time": "2:46:51", "remaining_time": "2:00:38", "throughput": 1316.93, "total_tokens": 13184592} {"current_steps": 23220, "total_steps": 40000, "loss": 0.0, "lr": 1.87466253934601e-05, "epoch": 407.37168141592923, "percentage": 58.05, "elapsed_time": "2:46:53", "remaining_time": "2:00:36", "throughput": 1316.96, "total_tokens": 13187648} {"current_steps": 23225, "total_steps": 40000, "loss": 0.0, "lr": 1.8737120486872033e-05, "epoch": 407.46017699115043, "percentage": 58.06, "elapsed_time": "2:46:55", "remaining_time": "2:00:34", "throughput": 1316.98, "total_tokens": 13190576} {"current_steps": 23230, "total_steps": 40000, "loss": 0.0, "lr": 1.8727616546098696e-05, "epoch": 407.5486725663717, "percentage": 58.07, "elapsed_time": "2:46:57", "remaining_time": "2:00:32", "throughput": 1317.01, "total_tokens": 13193664} {"current_steps": 23235, "total_steps": 40000, "loss": 0.0, "lr": 1.8718113572605716e-05, "epoch": 407.6371681415929, "percentage": 58.09, "elapsed_time": "2:46:59", "remaining_time": "2:00:29", "throughput": 1317.03, "total_tokens": 13196592} {"current_steps": 23240, "total_steps": 40000, "loss": 0.0, "lr": 1.8708611567858554e-05, "epoch": 407.72566371681415, "percentage": 58.1, "elapsed_time": "2:47:02", "remaining_time": "2:00:27", "throughput": 1317.03, "total_tokens": 13199264} {"current_steps": 23245, "total_steps": 40000, "loss": 0.0, "lr": 1.8699110533322565e-05, "epoch": 407.8141592920354, "percentage": 58.11, "elapsed_time": "2:47:04", "remaining_time": "2:00:25", "throughput": 1317.04, "total_tokens": 13202096} {"current_steps": 23250, "total_steps": 40000, "loss": 0.0, "lr": 1.8689610470462897e-05, "epoch": 407.9026548672566, "percentage": 58.13, "elapsed_time": "2:47:06", "remaining_time": "2:00:23", "throughput": 1317.07, "total_tokens": 13205088} {"current_steps": 23255, "total_steps": 40000, "loss": 0.0, "lr": 1.8680111380744604e-05, "epoch": 407.9911504424779, "percentage": 58.14, "elapsed_time": "2:47:08", "remaining_time": "2:00:20", "throughput": 1317.07, "total_tokens": 13207872} {"current_steps": 23260, "total_steps": 40000, "loss": 0.0, "lr": 1.8670613265632564e-05, "epoch": 408.070796460177, "percentage": 58.15, "elapsed_time": "2:47:10", "remaining_time": "2:00:18", "throughput": 1317.0, "total_tokens": 13210088} {"current_steps": 23265, "total_steps": 40000, "loss": 0.0, "lr": 1.866111612659149e-05, "epoch": 408.1592920353982, "percentage": 58.16, "elapsed_time": "2:47:12", "remaining_time": "2:00:16", "throughput": 1317.03, "total_tokens": 13213192} {"current_steps": 23270, "total_steps": 40000, "loss": 0.0, "lr": 1.8651619965085967e-05, "epoch": 408.24778761061947, "percentage": 58.17, "elapsed_time": "2:47:14", "remaining_time": "2:00:14", "throughput": 1317.02, "total_tokens": 13215784} {"current_steps": 23275, "total_steps": 40000, "loss": 0.0, "lr": 1.8642124782580433e-05, "epoch": 408.3362831858407, "percentage": 58.19, "elapsed_time": "2:47:16", "remaining_time": "2:00:12", "throughput": 1317.07, "total_tokens": 13219048} {"current_steps": 23280, "total_steps": 40000, "loss": 0.0, "lr": 1.8632630580539144e-05, "epoch": 408.42477876106193, "percentage": 58.2, "elapsed_time": "2:47:18", "remaining_time": "2:00:09", "throughput": 1317.09, "total_tokens": 13221960} {"current_steps": 23285, "total_steps": 40000, "loss": 0.0, "lr": 1.862313736042625e-05, "epoch": 408.5132743362832, "percentage": 58.21, "elapsed_time": "2:47:20", "remaining_time": "2:00:07", "throughput": 1317.1, "total_tokens": 13224824} {"current_steps": 23290, "total_steps": 40000, "loss": 0.0, "lr": 1.8613645123705703e-05, "epoch": 408.60176991150445, "percentage": 58.23, "elapsed_time": "2:47:22", "remaining_time": "2:00:05", "throughput": 1317.12, "total_tokens": 13227688} {"current_steps": 23295, "total_steps": 40000, "loss": 0.0, "lr": 1.8604153871841328e-05, "epoch": 408.69026548672565, "percentage": 58.24, "elapsed_time": "2:47:24", "remaining_time": "2:00:03", "throughput": 1317.13, "total_tokens": 13230552} {"current_steps": 23300, "total_steps": 40000, "loss": 0.0, "lr": 1.859466360629682e-05, "epoch": 408.7787610619469, "percentage": 58.25, "elapsed_time": "2:47:27", "remaining_time": "2:00:01", "throughput": 1317.11, "total_tokens": 13233128} {"current_steps": 23305, "total_steps": 40000, "loss": 0.0, "lr": 1.8585174328535666e-05, "epoch": 408.86725663716817, "percentage": 58.26, "elapsed_time": "2:47:29", "remaining_time": "1:59:58", "throughput": 1317.15, "total_tokens": 13236200} {"current_steps": 23310, "total_steps": 40000, "loss": 0.0, "lr": 1.857568604002124e-05, "epoch": 408.95575221238937, "percentage": 58.27, "elapsed_time": "2:47:31", "remaining_time": "1:59:56", "throughput": 1317.16, "total_tokens": 13239048} {"current_steps": 23315, "total_steps": 40000, "loss": 0.0, "lr": 1.8566198742216774e-05, "epoch": 409.0353982300885, "percentage": 58.29, "elapsed_time": "2:47:33", "remaining_time": "1:59:54", "throughput": 1317.09, "total_tokens": 13241352} {"current_steps": 23320, "total_steps": 40000, "loss": 0.0, "lr": 1.85567124365853e-05, "epoch": 409.12389380530976, "percentage": 58.3, "elapsed_time": "2:47:35", "remaining_time": "1:59:52", "throughput": 1317.11, "total_tokens": 13244296} {"current_steps": 23325, "total_steps": 40000, "loss": 0.0, "lr": 1.854722712458975e-05, "epoch": 409.21238938053096, "percentage": 58.31, "elapsed_time": "2:47:37", "remaining_time": "1:59:50", "throughput": 1317.14, "total_tokens": 13247288} {"current_steps": 23330, "total_steps": 40000, "loss": 0.0, "lr": 1.853774280769286e-05, "epoch": 409.3008849557522, "percentage": 58.33, "elapsed_time": "2:47:39", "remaining_time": "1:59:47", "throughput": 1317.14, "total_tokens": 13250040} {"current_steps": 23335, "total_steps": 40000, "loss": 0.0, "lr": 1.852825948735724e-05, "epoch": 409.3893805309734, "percentage": 58.34, "elapsed_time": "2:47:41", "remaining_time": "1:59:45", "throughput": 1317.13, "total_tokens": 13252664} {"current_steps": 23340, "total_steps": 40000, "loss": 0.0, "lr": 1.851877716504534e-05, "epoch": 409.4778761061947, "percentage": 58.35, "elapsed_time": "2:47:43", "remaining_time": "1:59:43", "throughput": 1317.14, "total_tokens": 13255512} {"current_steps": 23345, "total_steps": 40000, "loss": 0.0, "lr": 1.8509295842219448e-05, "epoch": 409.56637168141594, "percentage": 58.36, "elapsed_time": "2:47:45", "remaining_time": "1:59:41", "throughput": 1317.21, "total_tokens": 13258952} {"current_steps": 23350, "total_steps": 40000, "loss": 0.0, "lr": 1.8499815520341697e-05, "epoch": 409.65486725663715, "percentage": 58.38, "elapsed_time": "2:47:48", "remaining_time": "1:59:39", "throughput": 1317.27, "total_tokens": 13262264} {"current_steps": 23355, "total_steps": 40000, "loss": 0.0, "lr": 1.8490336200874094e-05, "epoch": 409.7433628318584, "percentage": 58.39, "elapsed_time": "2:47:50", "remaining_time": "1:59:36", "throughput": 1317.26, "total_tokens": 13264920} {"current_steps": 23360, "total_steps": 40000, "loss": 0.0, "lr": 1.848085788527844e-05, "epoch": 409.83185840707966, "percentage": 58.4, "elapsed_time": "2:47:52", "remaining_time": "1:59:34", "throughput": 1317.23, "total_tokens": 13267336} {"current_steps": 23365, "total_steps": 40000, "loss": 0.0, "lr": 1.847138057501644e-05, "epoch": 409.92035398230087, "percentage": 58.41, "elapsed_time": "2:47:54", "remaining_time": "1:59:32", "throughput": 1317.25, "total_tokens": 13270216} {"current_steps": 23370, "total_steps": 40000, "loss": 0.0, "lr": 1.8461904271549582e-05, "epoch": 410.0, "percentage": 58.43, "elapsed_time": "2:47:56", "remaining_time": "1:59:30", "throughput": 1317.24, "total_tokens": 13272776} {"current_steps": 23375, "total_steps": 40000, "loss": 0.0, "lr": 1.845242897633926e-05, "epoch": 410.08849557522126, "percentage": 58.44, "elapsed_time": "2:47:58", "remaining_time": "1:59:28", "throughput": 1317.23, "total_tokens": 13275736} {"current_steps": 23380, "total_steps": 40000, "loss": 0.0, "lr": 1.844295469084667e-05, "epoch": 410.17699115044246, "percentage": 58.45, "elapsed_time": "2:48:00", "remaining_time": "1:59:25", "throughput": 1317.25, "total_tokens": 13278712} {"current_steps": 23385, "total_steps": 40000, "loss": 0.0, "lr": 1.843348141653286e-05, "epoch": 410.2654867256637, "percentage": 58.46, "elapsed_time": "2:48:02", "remaining_time": "1:59:23", "throughput": 1317.24, "total_tokens": 13281368} {"current_steps": 23390, "total_steps": 40000, "loss": 0.0, "lr": 1.842400915485874e-05, "epoch": 410.353982300885, "percentage": 58.48, "elapsed_time": "2:48:04", "remaining_time": "1:59:21", "throughput": 1317.24, "total_tokens": 13284088} {"current_steps": 23395, "total_steps": 40000, "loss": 0.0, "lr": 1.8414537907285053e-05, "epoch": 410.4424778761062, "percentage": 58.49, "elapsed_time": "2:48:06", "remaining_time": "1:59:19", "throughput": 1317.26, "total_tokens": 13287048} {"current_steps": 23400, "total_steps": 40000, "loss": 0.0, "lr": 1.840506767527237e-05, "epoch": 410.53097345132744, "percentage": 58.5, "elapsed_time": "2:48:08", "remaining_time": "1:59:17", "throughput": 1317.26, "total_tokens": 13289752} {"current_steps": 23400, "total_steps": 40000, "eval_loss": 0.5085816979408264, "epoch": 410.53097345132744, "percentage": 58.5, "elapsed_time": "2:48:09", "remaining_time": "1:59:17", "throughput": 1317.12, "total_tokens": 13289752} {"current_steps": 23405, "total_steps": 40000, "loss": 0.0, "lr": 1.8395598460281137e-05, "epoch": 410.6194690265487, "percentage": 58.51, "elapsed_time": "2:48:14", "remaining_time": "1:59:17", "throughput": 1316.82, "total_tokens": 13292584} {"current_steps": 23410, "total_steps": 40000, "loss": 0.0, "lr": 1.838613026377161e-05, "epoch": 410.7079646017699, "percentage": 58.53, "elapsed_time": "2:48:16", "remaining_time": "1:59:15", "throughput": 1316.85, "total_tokens": 13295704} {"current_steps": 23415, "total_steps": 40000, "loss": 0.0, "lr": 1.8376663087203917e-05, "epoch": 410.79646017699116, "percentage": 58.54, "elapsed_time": "2:48:18", "remaining_time": "1:59:12", "throughput": 1316.86, "total_tokens": 13298600} {"current_steps": 23420, "total_steps": 40000, "loss": 0.0, "lr": 1.8367196932038014e-05, "epoch": 410.88495575221236, "percentage": 58.55, "elapsed_time": "2:48:20", "remaining_time": "1:59:10", "throughput": 1316.92, "total_tokens": 13301912} {"current_steps": 23425, "total_steps": 40000, "loss": 0.0, "lr": 1.8357731799733686e-05, "epoch": 410.9734513274336, "percentage": 58.56, "elapsed_time": "2:48:22", "remaining_time": "1:59:08", "throughput": 1316.91, "total_tokens": 13304472} {"current_steps": 23430, "total_steps": 40000, "loss": 0.0, "lr": 1.8348267691750586e-05, "epoch": 411.05309734513276, "percentage": 58.58, "elapsed_time": "2:48:25", "remaining_time": "1:59:06", "throughput": 1316.87, "total_tokens": 13307080} {"current_steps": 23435, "total_steps": 40000, "loss": 0.0, "lr": 1.833880460954821e-05, "epoch": 411.14159292035396, "percentage": 58.59, "elapsed_time": "2:48:27", "remaining_time": "1:59:04", "throughput": 1316.9, "total_tokens": 13310152} {"current_steps": 23440, "total_steps": 40000, "loss": 0.0, "lr": 1.8329342554585866e-05, "epoch": 411.2300884955752, "percentage": 58.6, "elapsed_time": "2:48:29", "remaining_time": "1:59:02", "throughput": 1316.9, "total_tokens": 13312840} {"current_steps": 23445, "total_steps": 40000, "loss": 0.0, "lr": 1.8319881528322735e-05, "epoch": 411.3185840707965, "percentage": 58.61, "elapsed_time": "2:48:31", "remaining_time": "1:58:59", "throughput": 1316.96, "total_tokens": 13316168} {"current_steps": 23450, "total_steps": 40000, "loss": 0.0, "lr": 1.8310421532217815e-05, "epoch": 411.4070796460177, "percentage": 58.63, "elapsed_time": "2:48:33", "remaining_time": "1:58:57", "throughput": 1317.0, "total_tokens": 13319304} {"current_steps": 23455, "total_steps": 40000, "loss": 0.0, "lr": 1.8300962567729958e-05, "epoch": 411.49557522123894, "percentage": 58.64, "elapsed_time": "2:48:35", "remaining_time": "1:58:55", "throughput": 1316.99, "total_tokens": 13321912} {"current_steps": 23460, "total_steps": 40000, "loss": 0.0, "lr": 1.8291504636317866e-05, "epoch": 411.5840707964602, "percentage": 58.65, "elapsed_time": "2:48:37", "remaining_time": "1:58:53", "throughput": 1316.95, "total_tokens": 13324232} {"current_steps": 23465, "total_steps": 40000, "loss": 0.0, "lr": 1.8282047739440055e-05, "epoch": 411.6725663716814, "percentage": 58.66, "elapsed_time": "2:48:39", "remaining_time": "1:58:50", "throughput": 1316.95, "total_tokens": 13327016} {"current_steps": 23470, "total_steps": 40000, "loss": 0.0, "lr": 1.8272591878554903e-05, "epoch": 411.76106194690266, "percentage": 58.67, "elapsed_time": "2:48:41", "remaining_time": "1:58:48", "throughput": 1316.96, "total_tokens": 13329784} {"current_steps": 23475, "total_steps": 40000, "loss": 0.0, "lr": 1.8263137055120638e-05, "epoch": 411.8495575221239, "percentage": 58.69, "elapsed_time": "2:48:43", "remaining_time": "1:58:46", "throughput": 1316.97, "total_tokens": 13332616} {"current_steps": 23480, "total_steps": 40000, "loss": 0.0, "lr": 1.8253683270595295e-05, "epoch": 411.9380530973451, "percentage": 58.7, "elapsed_time": "2:48:45", "remaining_time": "1:58:44", "throughput": 1317.0, "total_tokens": 13335736} {"current_steps": 23485, "total_steps": 40000, "loss": 0.0, "lr": 1.824423052643677e-05, "epoch": 412.01769911504425, "percentage": 58.71, "elapsed_time": "2:48:48", "remaining_time": "1:58:42", "throughput": 1316.96, "total_tokens": 13338224} {"current_steps": 23490, "total_steps": 40000, "loss": 0.0, "lr": 1.82347788241028e-05, "epoch": 412.1061946902655, "percentage": 58.73, "elapsed_time": "2:48:50", "remaining_time": "1:58:39", "throughput": 1316.99, "total_tokens": 13341264} {"current_steps": 23495, "total_steps": 40000, "loss": 0.0, "lr": 1.8225328165050942e-05, "epoch": 412.1946902654867, "percentage": 58.74, "elapsed_time": "2:48:52", "remaining_time": "1:58:37", "throughput": 1316.99, "total_tokens": 13344048} {"current_steps": 23500, "total_steps": 40000, "loss": 0.0, "lr": 1.821587855073863e-05, "epoch": 412.283185840708, "percentage": 58.75, "elapsed_time": "2:48:54", "remaining_time": "1:58:35", "throughput": 1316.96, "total_tokens": 13346416} {"current_steps": 23505, "total_steps": 40000, "loss": 0.0, "lr": 1.8206429982623086e-05, "epoch": 412.37168141592923, "percentage": 58.76, "elapsed_time": "2:48:56", "remaining_time": "1:58:33", "throughput": 1317.04, "total_tokens": 13349984} {"current_steps": 23510, "total_steps": 40000, "loss": 0.0, "lr": 1.8196982462161416e-05, "epoch": 412.46017699115043, "percentage": 58.77, "elapsed_time": "2:48:58", "remaining_time": "1:58:31", "throughput": 1317.04, "total_tokens": 13352736} {"current_steps": 23515, "total_steps": 40000, "loss": 0.0, "lr": 1.818753599081055e-05, "epoch": 412.5486725663717, "percentage": 58.79, "elapsed_time": "2:49:00", "remaining_time": "1:58:28", "throughput": 1317.01, "total_tokens": 13355136} {"current_steps": 23520, "total_steps": 40000, "loss": 0.0, "lr": 1.817809057002724e-05, "epoch": 412.6371681415929, "percentage": 58.8, "elapsed_time": "2:49:02", "remaining_time": "1:58:26", "throughput": 1317.02, "total_tokens": 13358032} {"current_steps": 23525, "total_steps": 40000, "loss": 0.0, "lr": 1.8168646201268096e-05, "epoch": 412.72566371681415, "percentage": 58.81, "elapsed_time": "2:49:04", "remaining_time": "1:58:24", "throughput": 1317.0, "total_tokens": 13360528} {"current_steps": 23530, "total_steps": 40000, "loss": 0.0, "lr": 1.8159202885989557e-05, "epoch": 412.8141592920354, "percentage": 58.83, "elapsed_time": "2:49:06", "remaining_time": "1:58:22", "throughput": 1317.07, "total_tokens": 13363904} {"current_steps": 23535, "total_steps": 40000, "loss": 0.0, "lr": 1.814976062564789e-05, "epoch": 412.9026548672566, "percentage": 58.84, "elapsed_time": "2:49:08", "remaining_time": "1:58:20", "throughput": 1317.06, "total_tokens": 13366576} {"current_steps": 23540, "total_steps": 40000, "loss": 0.0, "lr": 1.8140319421699234e-05, "epoch": 412.9911504424779, "percentage": 58.85, "elapsed_time": "2:49:10", "remaining_time": "1:58:17", "throughput": 1317.09, "total_tokens": 13369584} {"current_steps": 23545, "total_steps": 40000, "loss": 0.0, "lr": 1.8130879275599515e-05, "epoch": 413.070796460177, "percentage": 58.86, "elapsed_time": "2:49:13", "remaining_time": "1:58:15", "throughput": 1317.03, "total_tokens": 13371928} {"current_steps": 23550, "total_steps": 40000, "loss": 0.0, "lr": 1.8121440188804544e-05, "epoch": 413.1592920353982, "percentage": 58.88, "elapsed_time": "2:49:15", "remaining_time": "1:58:13", "throughput": 1317.05, "total_tokens": 13374888} {"current_steps": 23555, "total_steps": 40000, "loss": 0.0, "lr": 1.811200216276993e-05, "epoch": 413.24778761061947, "percentage": 58.89, "elapsed_time": "2:49:17", "remaining_time": "1:58:11", "throughput": 1317.07, "total_tokens": 13377848} {"current_steps": 23560, "total_steps": 40000, "loss": 0.0, "lr": 1.810256519895115e-05, "epoch": 413.3362831858407, "percentage": 58.9, "elapsed_time": "2:49:19", "remaining_time": "1:58:09", "throughput": 1317.05, "total_tokens": 13380408} {"current_steps": 23565, "total_steps": 40000, "loss": 0.0, "lr": 1.8093129298803494e-05, "epoch": 413.42477876106193, "percentage": 58.91, "elapsed_time": "2:49:21", "remaining_time": "1:58:06", "throughput": 1317.05, "total_tokens": 13383128} {"current_steps": 23570, "total_steps": 40000, "loss": 0.0, "lr": 1.808369446378209e-05, "epoch": 413.5132743362832, "percentage": 58.93, "elapsed_time": "2:49:23", "remaining_time": "1:58:04", "throughput": 1317.08, "total_tokens": 13386104} {"current_steps": 23575, "total_steps": 40000, "loss": 0.0, "lr": 1.8074260695341914e-05, "epoch": 413.60176991150445, "percentage": 58.94, "elapsed_time": "2:49:25", "remaining_time": "1:58:02", "throughput": 1317.11, "total_tokens": 13389144} {"current_steps": 23580, "total_steps": 40000, "loss": 0.0, "lr": 1.8064827994937782e-05, "epoch": 413.69026548672565, "percentage": 58.95, "elapsed_time": "2:49:27", "remaining_time": "1:58:00", "throughput": 1317.15, "total_tokens": 13392312} {"current_steps": 23585, "total_steps": 40000, "loss": 0.0, "lr": 1.8055396364024317e-05, "epoch": 413.7787610619469, "percentage": 58.96, "elapsed_time": "2:49:29", "remaining_time": "1:57:58", "throughput": 1317.15, "total_tokens": 13395096} {"current_steps": 23590, "total_steps": 40000, "loss": 0.0, "lr": 1.804596580405601e-05, "epoch": 413.86725663716817, "percentage": 58.98, "elapsed_time": "2:49:31", "remaining_time": "1:57:55", "throughput": 1317.17, "total_tokens": 13398008} {"current_steps": 23595, "total_steps": 40000, "loss": 0.0, "lr": 1.8036536316487174e-05, "epoch": 413.95575221238937, "percentage": 58.99, "elapsed_time": "2:49:33", "remaining_time": "1:57:53", "throughput": 1317.21, "total_tokens": 13401112} {"current_steps": 23600, "total_steps": 40000, "loss": 0.0, "lr": 1.802710790277193e-05, "epoch": 414.0353982300885, "percentage": 59.0, "elapsed_time": "2:49:36", "remaining_time": "1:57:51", "throughput": 1317.19, "total_tokens": 13403848} {"current_steps": 23600, "total_steps": 40000, "eval_loss": 0.4857552647590637, "epoch": 414.0353982300885, "percentage": 59.0, "elapsed_time": "2:49:37", "remaining_time": "1:57:52", "throughput": 1317.05, "total_tokens": 13403848} {"current_steps": 23605, "total_steps": 40000, "loss": 0.0, "lr": 1.801768056436429e-05, "epoch": 414.12389380530976, "percentage": 59.01, "elapsed_time": "2:49:40", "remaining_time": "1:57:51", "throughput": 1316.84, "total_tokens": 13406680} {"current_steps": 23610, "total_steps": 40000, "loss": 0.0, "lr": 1.8008254302718035e-05, "epoch": 414.21238938053096, "percentage": 59.03, "elapsed_time": "2:49:43", "remaining_time": "1:57:49", "throughput": 1316.81, "total_tokens": 13409160} {"current_steps": 23615, "total_steps": 40000, "loss": 0.0, "lr": 1.7998829119286837e-05, "epoch": 414.3008849557522, "percentage": 59.04, "elapsed_time": "2:49:45", "remaining_time": "1:57:46", "throughput": 1316.8, "total_tokens": 13411752} {"current_steps": 23620, "total_steps": 40000, "loss": 0.0, "lr": 1.798940501552418e-05, "epoch": 414.3893805309734, "percentage": 59.05, "elapsed_time": "2:49:47", "remaining_time": "1:57:44", "throughput": 1316.74, "total_tokens": 13413896} {"current_steps": 23625, "total_steps": 40000, "loss": 0.0, "lr": 1.797998199288336e-05, "epoch": 414.4778761061947, "percentage": 59.06, "elapsed_time": "2:49:49", "remaining_time": "1:57:42", "throughput": 1316.78, "total_tokens": 13417048} {"current_steps": 23630, "total_steps": 40000, "loss": 0.0, "lr": 1.7970560052817543e-05, "epoch": 414.56637168141594, "percentage": 59.08, "elapsed_time": "2:49:51", "remaining_time": "1:57:40", "throughput": 1316.79, "total_tokens": 13419896} {"current_steps": 23635, "total_steps": 40000, "loss": 0.0, "lr": 1.7961139196779702e-05, "epoch": 414.65486725663715, "percentage": 59.09, "elapsed_time": "2:49:53", "remaining_time": "1:57:37", "throughput": 1316.82, "total_tokens": 13422920} {"current_steps": 23640, "total_steps": 40000, "loss": 0.0, "lr": 1.7951719426222647e-05, "epoch": 414.7433628318584, "percentage": 59.1, "elapsed_time": "2:49:55", "remaining_time": "1:57:35", "throughput": 1316.9, "total_tokens": 13426424} {"current_steps": 23645, "total_steps": 40000, "loss": 0.0, "lr": 1.794230074259904e-05, "epoch": 414.83185840707966, "percentage": 59.11, "elapsed_time": "2:49:57", "remaining_time": "1:57:33", "throughput": 1316.91, "total_tokens": 13429304} {"current_steps": 23650, "total_steps": 40000, "loss": 0.0, "lr": 1.7932883147361336e-05, "epoch": 414.92035398230087, "percentage": 59.13, "elapsed_time": "2:49:59", "remaining_time": "1:57:31", "throughput": 1316.96, "total_tokens": 13432536} {"current_steps": 23655, "total_steps": 40000, "loss": 0.0, "lr": 1.7923466641961865e-05, "epoch": 415.0, "percentage": 59.14, "elapsed_time": "2:50:01", "remaining_time": "1:57:29", "throughput": 1316.95, "total_tokens": 13435104} {"current_steps": 23660, "total_steps": 40000, "loss": 0.0, "lr": 1.791405122785278e-05, "epoch": 415.08849557522126, "percentage": 59.15, "elapsed_time": "2:50:03", "remaining_time": "1:57:27", "throughput": 1316.92, "total_tokens": 13437776} {"current_steps": 23665, "total_steps": 40000, "loss": 0.0, "lr": 1.7904636906486037e-05, "epoch": 415.17699115044246, "percentage": 59.16, "elapsed_time": "2:50:06", "remaining_time": "1:57:24", "throughput": 1316.92, "total_tokens": 13440528} {"current_steps": 23670, "total_steps": 40000, "loss": 0.0, "lr": 1.7895223679313448e-05, "epoch": 415.2654867256637, "percentage": 59.17, "elapsed_time": "2:50:08", "remaining_time": "1:57:22", "throughput": 1316.89, "total_tokens": 13442944} {"current_steps": 23675, "total_steps": 40000, "loss": 0.0, "lr": 1.7885811547786653e-05, "epoch": 415.353982300885, "percentage": 59.19, "elapsed_time": "2:50:10", "remaining_time": "1:57:20", "throughput": 1316.91, "total_tokens": 13445856} {"current_steps": 23680, "total_steps": 40000, "loss": 0.0, "lr": 1.7876400513357115e-05, "epoch": 415.4424778761062, "percentage": 59.2, "elapsed_time": "2:50:12", "remaining_time": "1:57:18", "throughput": 1316.99, "total_tokens": 13449424} {"current_steps": 23685, "total_steps": 40000, "loss": 0.0, "lr": 1.7866990577476146e-05, "epoch": 415.53097345132744, "percentage": 59.21, "elapsed_time": "2:50:14", "remaining_time": "1:57:15", "throughput": 1317.04, "total_tokens": 13452608} {"current_steps": 23690, "total_steps": 40000, "loss": 0.0, "lr": 1.7857581741594863e-05, "epoch": 415.6194690265487, "percentage": 59.23, "elapsed_time": "2:50:16", "remaining_time": "1:57:13", "throughput": 1317.08, "total_tokens": 13455776} {"current_steps": 23695, "total_steps": 40000, "loss": 0.0, "lr": 1.7848174007164237e-05, "epoch": 415.7079646017699, "percentage": 59.24, "elapsed_time": "2:50:18", "remaining_time": "1:57:11", "throughput": 1317.13, "total_tokens": 13459024} {"current_steps": 23700, "total_steps": 40000, "loss": 0.0, "lr": 1.7838767375635052e-05, "epoch": 415.79646017699116, "percentage": 59.25, "elapsed_time": "2:50:20", "remaining_time": "1:57:09", "throughput": 1317.13, "total_tokens": 13461776} {"current_steps": 23705, "total_steps": 40000, "loss": 0.0, "lr": 1.782936184845793e-05, "epoch": 415.88495575221236, "percentage": 59.26, "elapsed_time": "2:50:22", "remaining_time": "1:57:07", "throughput": 1317.12, "total_tokens": 13464416} {"current_steps": 23710, "total_steps": 40000, "loss": 0.0, "lr": 1.7819957427083334e-05, "epoch": 415.9734513274336, "percentage": 59.27, "elapsed_time": "2:50:24", "remaining_time": "1:57:04", "throughput": 1317.12, "total_tokens": 13467072} {"current_steps": 23715, "total_steps": 40000, "loss": 0.0, "lr": 1.7810554112961516e-05, "epoch": 416.05309734513276, "percentage": 59.29, "elapsed_time": "2:50:26", "remaining_time": "1:57:02", "throughput": 1317.1, "total_tokens": 13469936} {"current_steps": 23720, "total_steps": 40000, "loss": 0.0, "lr": 1.7801151907542607e-05, "epoch": 416.14159292035396, "percentage": 59.3, "elapsed_time": "2:50:29", "remaining_time": "1:57:00", "throughput": 1317.09, "total_tokens": 13472528} {"current_steps": 23725, "total_steps": 40000, "loss": 0.0, "lr": 1.7791750812276547e-05, "epoch": 416.2300884955752, "percentage": 59.31, "elapsed_time": "2:50:31", "remaining_time": "1:56:58", "throughput": 1317.09, "total_tokens": 13475264} {"current_steps": 23730, "total_steps": 40000, "loss": 0.0, "lr": 1.778235082861309e-05, "epoch": 416.3185840707965, "percentage": 59.33, "elapsed_time": "2:50:33", "remaining_time": "1:56:56", "throughput": 1317.12, "total_tokens": 13478288} {"current_steps": 23735, "total_steps": 40000, "loss": 0.0, "lr": 1.777295195800184e-05, "epoch": 416.4070796460177, "percentage": 59.34, "elapsed_time": "2:50:35", "remaining_time": "1:56:53", "throughput": 1317.15, "total_tokens": 13481312} {"current_steps": 23740, "total_steps": 40000, "loss": 0.0, "lr": 1.7763554201892215e-05, "epoch": 416.49557522123894, "percentage": 59.35, "elapsed_time": "2:50:37", "remaining_time": "1:56:51", "throughput": 1317.18, "total_tokens": 13484352} {"current_steps": 23745, "total_steps": 40000, "loss": 0.0, "lr": 1.7754157561733476e-05, "epoch": 416.5840707964602, "percentage": 59.36, "elapsed_time": "2:50:39", "remaining_time": "1:56:49", "throughput": 1317.24, "total_tokens": 13487712} {"current_steps": 23750, "total_steps": 40000, "loss": 0.0, "lr": 1.7744762038974702e-05, "epoch": 416.6725663716814, "percentage": 59.38, "elapsed_time": "2:50:41", "remaining_time": "1:56:47", "throughput": 1317.26, "total_tokens": 13490576} {"current_steps": 23755, "total_steps": 40000, "loss": 0.0, "lr": 1.7735367635064788e-05, "epoch": 416.76106194690266, "percentage": 59.39, "elapsed_time": "2:50:43", "remaining_time": "1:56:45", "throughput": 1317.24, "total_tokens": 13493104} {"current_steps": 23760, "total_steps": 40000, "loss": 0.0, "lr": 1.7725974351452474e-05, "epoch": 416.8495575221239, "percentage": 59.4, "elapsed_time": "2:50:45", "remaining_time": "1:56:42", "throughput": 1317.23, "total_tokens": 13495792} {"current_steps": 23765, "total_steps": 40000, "loss": 0.0, "lr": 1.771658218958634e-05, "epoch": 416.9380530973451, "percentage": 59.41, "elapsed_time": "2:50:47", "remaining_time": "1:56:40", "throughput": 1317.25, "total_tokens": 13498688} {"current_steps": 23770, "total_steps": 40000, "loss": 0.0, "lr": 1.770719115091475e-05, "epoch": 417.01769911504425, "percentage": 59.42, "elapsed_time": "2:50:49", "remaining_time": "1:56:38", "throughput": 1317.15, "total_tokens": 13500624} {"current_steps": 23775, "total_steps": 40000, "loss": 0.0, "lr": 1.7697801236885935e-05, "epoch": 417.1061946902655, "percentage": 59.44, "elapsed_time": "2:50:51", "remaining_time": "1:56:36", "throughput": 1317.19, "total_tokens": 13503808} {"current_steps": 23780, "total_steps": 40000, "loss": 0.0, "lr": 1.7688412448947944e-05, "epoch": 417.1946902654867, "percentage": 59.45, "elapsed_time": "2:50:54", "remaining_time": "1:56:34", "throughput": 1317.25, "total_tokens": 13507136} {"current_steps": 23785, "total_steps": 40000, "loss": 0.0, "lr": 1.767902478854862e-05, "epoch": 417.283185840708, "percentage": 59.46, "elapsed_time": "2:50:56", "remaining_time": "1:56:31", "throughput": 1317.24, "total_tokens": 13509728} {"current_steps": 23790, "total_steps": 40000, "loss": 0.0, "lr": 1.766963825713569e-05, "epoch": 417.37168141592923, "percentage": 59.48, "elapsed_time": "2:50:58", "remaining_time": "1:56:29", "throughput": 1317.23, "total_tokens": 13512400} {"current_steps": 23795, "total_steps": 40000, "loss": 0.0, "lr": 1.766025285615665e-05, "epoch": 417.46017699115043, "percentage": 59.49, "elapsed_time": "2:51:00", "remaining_time": "1:56:27", "throughput": 1317.31, "total_tokens": 13515904} {"current_steps": 23800, "total_steps": 40000, "loss": 0.0, "lr": 1.7650868587058854e-05, "epoch": 417.5486725663717, "percentage": 59.5, "elapsed_time": "2:51:02", "remaining_time": "1:56:25", "throughput": 1317.29, "total_tokens": 13518496} {"current_steps": 23800, "total_steps": 40000, "eval_loss": 0.5352886915206909, "epoch": 417.5486725663717, "percentage": 59.5, "elapsed_time": "2:51:03", "remaining_time": "1:56:26", "throughput": 1317.16, "total_tokens": 13518496} {"current_steps": 23805, "total_steps": 40000, "loss": 0.0, "lr": 1.7641485451289484e-05, "epoch": 417.6371681415929, "percentage": 59.51, "elapsed_time": "2:51:07", "remaining_time": "1:56:24", "throughput": 1316.95, "total_tokens": 13521296} {"current_steps": 23810, "total_steps": 40000, "loss": 0.0, "lr": 1.7632103450295534e-05, "epoch": 417.72566371681415, "percentage": 59.52, "elapsed_time": "2:51:09", "remaining_time": "1:56:22", "throughput": 1316.91, "total_tokens": 13523728} {"current_steps": 23815, "total_steps": 40000, "loss": 0.0, "lr": 1.762272258552381e-05, "epoch": 417.8141592920354, "percentage": 59.54, "elapsed_time": "2:51:11", "remaining_time": "1:56:20", "throughput": 1316.93, "total_tokens": 13526624} {"current_steps": 23820, "total_steps": 40000, "loss": 0.0, "lr": 1.7613342858420988e-05, "epoch": 417.9026548672566, "percentage": 59.55, "elapsed_time": "2:51:13", "remaining_time": "1:56:18", "throughput": 1316.98, "total_tokens": 13529888} {"current_steps": 23825, "total_steps": 40000, "loss": 0.0, "lr": 1.760396427043351e-05, "epoch": 417.9911504424779, "percentage": 59.56, "elapsed_time": "2:51:15", "remaining_time": "1:56:16", "throughput": 1316.95, "total_tokens": 13532272} {"current_steps": 23830, "total_steps": 40000, "loss": 0.0, "lr": 1.7594586823007696e-05, "epoch": 418.070796460177, "percentage": 59.58, "elapsed_time": "2:51:17", "remaining_time": "1:56:14", "throughput": 1316.93, "total_tokens": 13535136} {"current_steps": 23835, "total_steps": 40000, "loss": 0.0, "lr": 1.7585210517589646e-05, "epoch": 418.1592920353982, "percentage": 59.59, "elapsed_time": "2:51:19", "remaining_time": "1:56:11", "throughput": 1316.95, "total_tokens": 13538032} {"current_steps": 23840, "total_steps": 40000, "loss": 0.0, "lr": 1.7575835355625314e-05, "epoch": 418.24778761061947, "percentage": 59.6, "elapsed_time": "2:51:21", "remaining_time": "1:56:09", "throughput": 1316.96, "total_tokens": 13540816} {"current_steps": 23845, "total_steps": 40000, "loss": 0.0, "lr": 1.756646133856048e-05, "epoch": 418.3362831858407, "percentage": 59.61, "elapsed_time": "2:51:23", "remaining_time": "1:56:07", "throughput": 1316.98, "total_tokens": 13543776} {"current_steps": 23850, "total_steps": 40000, "loss": 0.0, "lr": 1.7557088467840714e-05, "epoch": 418.42477876106193, "percentage": 59.62, "elapsed_time": "2:51:26", "remaining_time": "1:56:05", "throughput": 1316.97, "total_tokens": 13546464} {"current_steps": 23855, "total_steps": 40000, "loss": 0.0, "lr": 1.7547716744911438e-05, "epoch": 418.5132743362832, "percentage": 59.64, "elapsed_time": "2:51:28", "remaining_time": "1:56:02", "throughput": 1316.97, "total_tokens": 13549136} {"current_steps": 23860, "total_steps": 40000, "loss": 0.0, "lr": 1.7538346171217902e-05, "epoch": 418.60176991150445, "percentage": 59.65, "elapsed_time": "2:51:30", "remaining_time": "1:56:00", "throughput": 1316.94, "total_tokens": 13551552} {"current_steps": 23865, "total_steps": 40000, "loss": 0.0, "lr": 1.7528976748205146e-05, "epoch": 418.69026548672565, "percentage": 59.66, "elapsed_time": "2:51:32", "remaining_time": "1:55:58", "throughput": 1316.93, "total_tokens": 13554240} {"current_steps": 23870, "total_steps": 40000, "loss": 0.0, "lr": 1.751960847731807e-05, "epoch": 418.7787610619469, "percentage": 59.67, "elapsed_time": "2:51:34", "remaining_time": "1:55:56", "throughput": 1316.94, "total_tokens": 13557056} {"current_steps": 23875, "total_steps": 40000, "loss": 0.0, "lr": 1.7510241360001362e-05, "epoch": 418.86725663716817, "percentage": 59.69, "elapsed_time": "2:51:36", "remaining_time": "1:55:54", "throughput": 1317.05, "total_tokens": 13560880} {"current_steps": 23880, "total_steps": 40000, "loss": 0.0, "lr": 1.7500875397699562e-05, "epoch": 418.95575221238937, "percentage": 59.7, "elapsed_time": "2:51:38", "remaining_time": "1:55:51", "throughput": 1317.07, "total_tokens": 13563792} {"current_steps": 23885, "total_steps": 40000, "loss": 0.0, "lr": 1.7491510591857015e-05, "epoch": 419.0353982300885, "percentage": 59.71, "elapsed_time": "2:51:40", "remaining_time": "1:55:49", "throughput": 1317.05, "total_tokens": 13566536} {"current_steps": 23890, "total_steps": 40000, "loss": 0.0, "lr": 1.7482146943917896e-05, "epoch": 419.12389380530976, "percentage": 59.72, "elapsed_time": "2:51:42", "remaining_time": "1:55:47", "throughput": 1317.05, "total_tokens": 13569256} {"current_steps": 23895, "total_steps": 40000, "loss": 0.0, "lr": 1.7472784455326185e-05, "epoch": 419.21238938053096, "percentage": 59.74, "elapsed_time": "2:51:44", "remaining_time": "1:55:45", "throughput": 1317.07, "total_tokens": 13572216} {"current_steps": 23900, "total_steps": 40000, "loss": 0.0, "lr": 1.746342312752572e-05, "epoch": 419.3008849557522, "percentage": 59.75, "elapsed_time": "2:51:46", "remaining_time": "1:55:43", "throughput": 1317.07, "total_tokens": 13574984} {"current_steps": 23905, "total_steps": 40000, "loss": 0.0, "lr": 1.74540629619601e-05, "epoch": 419.3893805309734, "percentage": 59.76, "elapsed_time": "2:51:48", "remaining_time": "1:55:40", "throughput": 1317.11, "total_tokens": 13578040} {"current_steps": 23910, "total_steps": 40000, "loss": 0.0, "lr": 1.7444703960072815e-05, "epoch": 419.4778761061947, "percentage": 59.77, "elapsed_time": "2:51:51", "remaining_time": "1:55:38", "throughput": 1317.14, "total_tokens": 13581080} {"current_steps": 23915, "total_steps": 40000, "loss": 0.0, "lr": 1.7435346123307118e-05, "epoch": 419.56637168141594, "percentage": 59.79, "elapsed_time": "2:51:53", "remaining_time": "1:55:36", "throughput": 1317.16, "total_tokens": 13584104} {"current_steps": 23920, "total_steps": 40000, "loss": 0.0, "lr": 1.742598945310611e-05, "epoch": 419.65486725663715, "percentage": 59.8, "elapsed_time": "2:51:55", "remaining_time": "1:55:34", "throughput": 1317.16, "total_tokens": 13586840} {"current_steps": 23925, "total_steps": 40000, "loss": 0.0, "lr": 1.741663395091272e-05, "epoch": 419.7433628318584, "percentage": 59.81, "elapsed_time": "2:51:57", "remaining_time": "1:55:32", "throughput": 1317.15, "total_tokens": 13589448} {"current_steps": 23930, "total_steps": 40000, "loss": 0.0, "lr": 1.7407279618169657e-05, "epoch": 419.83185840707966, "percentage": 59.82, "elapsed_time": "2:51:59", "remaining_time": "1:55:29", "throughput": 1317.16, "total_tokens": 13592264} {"current_steps": 23935, "total_steps": 40000, "loss": 0.0, "lr": 1.73979264563195e-05, "epoch": 419.92035398230087, "percentage": 59.84, "elapsed_time": "2:52:01", "remaining_time": "1:55:27", "throughput": 1317.17, "total_tokens": 13595080} {"current_steps": 23940, "total_steps": 40000, "loss": 0.0, "lr": 1.7388574466804625e-05, "epoch": 420.0, "percentage": 59.85, "elapsed_time": "2:52:03", "remaining_time": "1:55:25", "throughput": 1317.16, "total_tokens": 13597592} {"current_steps": 23945, "total_steps": 40000, "loss": 0.0, "lr": 1.7379223651067207e-05, "epoch": 420.08849557522126, "percentage": 59.86, "elapsed_time": "2:52:05", "remaining_time": "1:55:23", "throughput": 1317.12, "total_tokens": 13600248} {"current_steps": 23950, "total_steps": 40000, "loss": 0.0, "lr": 1.736987401054928e-05, "epoch": 420.17699115044246, "percentage": 59.88, "elapsed_time": "2:52:07", "remaining_time": "1:55:21", "throughput": 1317.14, "total_tokens": 13603144} {"current_steps": 23955, "total_steps": 40000, "loss": 0.0, "lr": 1.736052554669266e-05, "epoch": 420.2654867256637, "percentage": 59.89, "elapsed_time": "2:52:09", "remaining_time": "1:55:18", "throughput": 1317.18, "total_tokens": 13606296} {"current_steps": 23960, "total_steps": 40000, "loss": 0.0, "lr": 1.7351178260939007e-05, "epoch": 420.353982300885, "percentage": 59.9, "elapsed_time": "2:52:11", "remaining_time": "1:55:16", "throughput": 1317.23, "total_tokens": 13609592} {"current_steps": 23965, "total_steps": 40000, "loss": 0.0, "lr": 1.7341832154729794e-05, "epoch": 420.4424778761062, "percentage": 59.91, "elapsed_time": "2:52:14", "remaining_time": "1:55:14", "throughput": 1317.21, "total_tokens": 13612024} {"current_steps": 23970, "total_steps": 40000, "loss": 0.0, "lr": 1.7332487229506286e-05, "epoch": 420.53097345132744, "percentage": 59.92, "elapsed_time": "2:52:16", "remaining_time": "1:55:12", "throughput": 1317.24, "total_tokens": 13615128} {"current_steps": 23975, "total_steps": 40000, "loss": 0.0, "lr": 1.732314348670961e-05, "epoch": 420.6194690265487, "percentage": 59.94, "elapsed_time": "2:52:18", "remaining_time": "1:55:10", "throughput": 1317.26, "total_tokens": 13618024} {"current_steps": 23980, "total_steps": 40000, "loss": 0.0, "lr": 1.7313800927780686e-05, "epoch": 420.7079646017699, "percentage": 59.95, "elapsed_time": "2:52:20", "remaining_time": "1:55:07", "throughput": 1317.3, "total_tokens": 13621128} {"current_steps": 23985, "total_steps": 40000, "loss": 0.0, "lr": 1.7304459554160245e-05, "epoch": 420.79646017699116, "percentage": 59.96, "elapsed_time": "2:52:22", "remaining_time": "1:55:05", "throughput": 1317.33, "total_tokens": 13624168} {"current_steps": 23990, "total_steps": 40000, "loss": 0.0, "lr": 1.7295119367288853e-05, "epoch": 420.88495575221236, "percentage": 59.98, "elapsed_time": "2:52:24", "remaining_time": "1:55:03", "throughput": 1317.3, "total_tokens": 13626616} {"current_steps": 23995, "total_steps": 40000, "loss": 0.0, "lr": 1.728578036860688e-05, "epoch": 420.9734513274336, "percentage": 59.99, "elapsed_time": "2:52:26", "remaining_time": "1:55:01", "throughput": 1317.29, "total_tokens": 13629272} {"current_steps": 24000, "total_steps": 40000, "loss": 0.0, "lr": 1.7276442559554513e-05, "epoch": 421.05309734513276, "percentage": 60.0, "elapsed_time": "2:52:28", "remaining_time": "1:54:59", "throughput": 1317.24, "total_tokens": 13631704} {"current_steps": 24000, "total_steps": 40000, "eval_loss": 0.49583497643470764, "epoch": 421.05309734513276, "percentage": 60.0, "elapsed_time": "2:52:29", "remaining_time": "1:54:59", "throughput": 1317.1, "total_tokens": 13631704} {"current_steps": 24005, "total_steps": 40000, "loss": 0.0, "lr": 1.726710594157177e-05, "epoch": 421.14159292035396, "percentage": 60.01, "elapsed_time": "2:52:33", "remaining_time": "1:54:58", "throughput": 1316.91, "total_tokens": 13634808} {"current_steps": 24010, "total_steps": 40000, "loss": 0.0, "lr": 1.725777051609846e-05, "epoch": 421.2300884955752, "percentage": 60.02, "elapsed_time": "2:52:35", "remaining_time": "1:54:56", "throughput": 1316.91, "total_tokens": 13637448} {"current_steps": 24015, "total_steps": 40000, "loss": 0.0, "lr": 1.7248436284574228e-05, "epoch": 421.3185840707965, "percentage": 60.04, "elapsed_time": "2:52:37", "remaining_time": "1:54:54", "throughput": 1316.94, "total_tokens": 13640520} {"current_steps": 24020, "total_steps": 40000, "loss": 0.0, "lr": 1.723910324843855e-05, "epoch": 421.4070796460177, "percentage": 60.05, "elapsed_time": "2:52:39", "remaining_time": "1:54:52", "throughput": 1316.92, "total_tokens": 13643064} {"current_steps": 24025, "total_steps": 40000, "loss": 0.0, "lr": 1.722977140913067e-05, "epoch": 421.49557522123894, "percentage": 60.06, "elapsed_time": "2:52:41", "remaining_time": "1:54:49", "throughput": 1316.97, "total_tokens": 13646296} {"current_steps": 24030, "total_steps": 40000, "loss": 0.0, "lr": 1.7220440768089688e-05, "epoch": 421.5840707964602, "percentage": 60.08, "elapsed_time": "2:52:43", "remaining_time": "1:54:47", "throughput": 1316.98, "total_tokens": 13649128} {"current_steps": 24035, "total_steps": 40000, "loss": 0.0, "lr": 1.7211111326754505e-05, "epoch": 421.6725663716814, "percentage": 60.09, "elapsed_time": "2:52:46", "remaining_time": "1:54:45", "throughput": 1316.96, "total_tokens": 13651688} {"current_steps": 24040, "total_steps": 40000, "loss": 0.0, "lr": 1.720178308656383e-05, "epoch": 421.76106194690266, "percentage": 60.1, "elapsed_time": "2:52:48", "remaining_time": "1:54:43", "throughput": 1316.99, "total_tokens": 13654744} {"current_steps": 24045, "total_steps": 40000, "loss": 0.0, "lr": 1.719245604895621e-05, "epoch": 421.8495575221239, "percentage": 60.11, "elapsed_time": "2:52:50", "remaining_time": "1:54:41", "throughput": 1317.0, "total_tokens": 13657544} {"current_steps": 24050, "total_steps": 40000, "loss": 0.0, "lr": 1.7183130215369972e-05, "epoch": 421.9380530973451, "percentage": 60.12, "elapsed_time": "2:52:52", "remaining_time": "1:54:38", "throughput": 1317.03, "total_tokens": 13660504} {"current_steps": 24055, "total_steps": 40000, "loss": 0.0, "lr": 1.7173805587243292e-05, "epoch": 422.01769911504425, "percentage": 60.14, "elapsed_time": "2:52:54", "remaining_time": "1:54:36", "throughput": 1316.95, "total_tokens": 13662744} {"current_steps": 24060, "total_steps": 40000, "loss": 0.0, "lr": 1.7164482166014147e-05, "epoch": 422.1061946902655, "percentage": 60.15, "elapsed_time": "2:52:56", "remaining_time": "1:54:34", "throughput": 1316.96, "total_tokens": 13665576} {"current_steps": 24065, "total_steps": 40000, "loss": 0.0, "lr": 1.7155159953120313e-05, "epoch": 422.1946902654867, "percentage": 60.16, "elapsed_time": "2:52:58", "remaining_time": "1:54:32", "throughput": 1316.94, "total_tokens": 13668056} {"current_steps": 24070, "total_steps": 40000, "loss": 0.0, "lr": 1.714583894999941e-05, "epoch": 422.283185840708, "percentage": 60.17, "elapsed_time": "2:53:00", "remaining_time": "1:54:30", "throughput": 1316.95, "total_tokens": 13670872} {"current_steps": 24075, "total_steps": 40000, "loss": 0.0, "lr": 1.7136519158088826e-05, "epoch": 422.37168141592923, "percentage": 60.19, "elapsed_time": "2:53:02", "remaining_time": "1:54:27", "throughput": 1317.05, "total_tokens": 13674632} {"current_steps": 24080, "total_steps": 40000, "loss": 0.0, "lr": 1.712720057882581e-05, "epoch": 422.46017699115043, "percentage": 60.2, "elapsed_time": "2:53:04", "remaining_time": "1:54:25", "throughput": 1317.04, "total_tokens": 13677272} {"current_steps": 24085, "total_steps": 40000, "loss": 0.0, "lr": 1.7117883213647413e-05, "epoch": 422.5486725663717, "percentage": 60.21, "elapsed_time": "2:53:06", "remaining_time": "1:54:23", "throughput": 1317.06, "total_tokens": 13680264} {"current_steps": 24090, "total_steps": 40000, "loss": 0.0, "lr": 1.710856706399046e-05, "epoch": 422.6371681415929, "percentage": 60.22, "elapsed_time": "2:53:09", "remaining_time": "1:54:21", "throughput": 1317.11, "total_tokens": 13683432} {"current_steps": 24095, "total_steps": 40000, "loss": 0.0, "lr": 1.7099252131291648e-05, "epoch": 422.72566371681415, "percentage": 60.24, "elapsed_time": "2:53:11", "remaining_time": "1:54:19", "throughput": 1317.11, "total_tokens": 13686168} {"current_steps": 24100, "total_steps": 40000, "loss": 0.0, "lr": 1.708993841698744e-05, "epoch": 422.8141592920354, "percentage": 60.25, "elapsed_time": "2:53:13", "remaining_time": "1:54:16", "throughput": 1317.12, "total_tokens": 13688984} {"current_steps": 24105, "total_steps": 40000, "loss": 0.0, "lr": 1.7080625922514132e-05, "epoch": 422.9026548672566, "percentage": 60.26, "elapsed_time": "2:53:15", "remaining_time": "1:54:14", "throughput": 1317.13, "total_tokens": 13691880} {"current_steps": 24110, "total_steps": 40000, "loss": 0.0, "lr": 1.7071314649307836e-05, "epoch": 422.9911504424779, "percentage": 60.27, "elapsed_time": "2:53:17", "remaining_time": "1:54:12", "throughput": 1317.12, "total_tokens": 13694440} {"current_steps": 24115, "total_steps": 40000, "loss": 0.0, "lr": 1.7062004598804448e-05, "epoch": 423.070796460177, "percentage": 60.29, "elapsed_time": "2:53:19", "remaining_time": "1:54:10", "throughput": 1317.04, "total_tokens": 13696576} {"current_steps": 24120, "total_steps": 40000, "loss": 0.0, "lr": 1.7052695772439702e-05, "epoch": 423.1592920353982, "percentage": 60.3, "elapsed_time": "2:53:21", "remaining_time": "1:54:08", "throughput": 1317.04, "total_tokens": 13699392} {"current_steps": 24125, "total_steps": 40000, "loss": 0.0, "lr": 1.7043388171649154e-05, "epoch": 423.24778761061947, "percentage": 60.31, "elapsed_time": "2:53:23", "remaining_time": "1:54:05", "throughput": 1317.05, "total_tokens": 13702160} {"current_steps": 24130, "total_steps": 40000, "loss": 0.0, "lr": 1.7034081797868127e-05, "epoch": 423.3362831858407, "percentage": 60.32, "elapsed_time": "2:53:25", "remaining_time": "1:54:03", "throughput": 1317.08, "total_tokens": 13705200} {"current_steps": 24135, "total_steps": 40000, "loss": 0.0, "lr": 1.70247766525318e-05, "epoch": 423.42477876106193, "percentage": 60.34, "elapsed_time": "2:53:27", "remaining_time": "1:54:01", "throughput": 1317.07, "total_tokens": 13707872} {"current_steps": 24140, "total_steps": 40000, "loss": 0.0, "lr": 1.701547273707514e-05, "epoch": 423.5132743362832, "percentage": 60.35, "elapsed_time": "2:53:29", "remaining_time": "1:53:59", "throughput": 1317.1, "total_tokens": 13710896} {"current_steps": 24145, "total_steps": 40000, "loss": 0.0, "lr": 1.7006170052932916e-05, "epoch": 423.60176991150445, "percentage": 60.36, "elapsed_time": "2:53:31", "remaining_time": "1:53:57", "throughput": 1317.1, "total_tokens": 13713632} {"current_steps": 24150, "total_steps": 40000, "loss": 0.0, "lr": 1.6996868601539735e-05, "epoch": 423.69026548672565, "percentage": 60.38, "elapsed_time": "2:53:34", "remaining_time": "1:53:54", "throughput": 1317.15, "total_tokens": 13716848} {"current_steps": 24155, "total_steps": 40000, "loss": 0.0, "lr": 1.6987568384329977e-05, "epoch": 423.7787610619469, "percentage": 60.39, "elapsed_time": "2:53:36", "remaining_time": "1:53:52", "throughput": 1317.15, "total_tokens": 13719632} {"current_steps": 24160, "total_steps": 40000, "loss": 0.0, "lr": 1.6978269402737866e-05, "epoch": 423.86725663716817, "percentage": 60.4, "elapsed_time": "2:53:38", "remaining_time": "1:53:50", "throughput": 1317.17, "total_tokens": 13722576} {"current_steps": 24165, "total_steps": 40000, "loss": 0.0, "lr": 1.696897165819743e-05, "epoch": 423.95575221238937, "percentage": 60.41, "elapsed_time": "2:53:40", "remaining_time": "1:53:48", "throughput": 1317.19, "total_tokens": 13725440} {"current_steps": 24170, "total_steps": 40000, "loss": 0.0, "lr": 1.6959675152142487e-05, "epoch": 424.0353982300885, "percentage": 60.42, "elapsed_time": "2:53:42", "remaining_time": "1:53:46", "throughput": 1317.17, "total_tokens": 13728208} {"current_steps": 24175, "total_steps": 40000, "loss": 0.0, "lr": 1.6950379886006667e-05, "epoch": 424.12389380530976, "percentage": 60.44, "elapsed_time": "2:53:44", "remaining_time": "1:53:43", "throughput": 1317.22, "total_tokens": 13731456} {"current_steps": 24180, "total_steps": 40000, "loss": 0.0, "lr": 1.6941085861223438e-05, "epoch": 424.21238938053096, "percentage": 60.45, "elapsed_time": "2:53:46", "remaining_time": "1:53:41", "throughput": 1317.22, "total_tokens": 13734144} {"current_steps": 24185, "total_steps": 40000, "loss": 0.0, "lr": 1.6931793079226034e-05, "epoch": 424.3008849557522, "percentage": 60.46, "elapsed_time": "2:53:48", "remaining_time": "1:53:39", "throughput": 1317.21, "total_tokens": 13736816} {"current_steps": 24190, "total_steps": 40000, "loss": 0.0, "lr": 1.692250154144754e-05, "epoch": 424.3893805309734, "percentage": 60.48, "elapsed_time": "2:53:50", "remaining_time": "1:53:37", "throughput": 1317.18, "total_tokens": 13739264} {"current_steps": 24195, "total_steps": 40000, "loss": 0.0, "lr": 1.6913211249320807e-05, "epoch": 424.4778761061947, "percentage": 60.49, "elapsed_time": "2:53:52", "remaining_time": "1:53:35", "throughput": 1317.2, "total_tokens": 13742176} {"current_steps": 24200, "total_steps": 40000, "loss": 0.0, "lr": 1.6903922204278522e-05, "epoch": 424.56637168141594, "percentage": 60.5, "elapsed_time": "2:53:54", "remaining_time": "1:53:32", "throughput": 1317.23, "total_tokens": 13745200} {"current_steps": 24200, "total_steps": 40000, "eval_loss": 0.49358347058296204, "epoch": 424.56637168141594, "percentage": 60.5, "elapsed_time": "2:53:56", "remaining_time": "1:53:33", "throughput": 1317.09, "total_tokens": 13745200} {"current_steps": 24205, "total_steps": 40000, "loss": 0.0, "lr": 1.6894634407753186e-05, "epoch": 424.65486725663715, "percentage": 60.51, "elapsed_time": "2:53:59", "remaining_time": "1:53:32", "throughput": 1316.89, "total_tokens": 13748144} {"current_steps": 24210, "total_steps": 40000, "loss": 0.0, "lr": 1.6885347861177077e-05, "epoch": 424.7433628318584, "percentage": 60.52, "elapsed_time": "2:54:01", "remaining_time": "1:53:30", "throughput": 1316.95, "total_tokens": 13751504} {"current_steps": 24215, "total_steps": 40000, "loss": 0.0, "lr": 1.6876062565982298e-05, "epoch": 424.83185840707966, "percentage": 60.54, "elapsed_time": "2:54:04", "remaining_time": "1:53:28", "throughput": 1316.96, "total_tokens": 13754336} {"current_steps": 24220, "total_steps": 40000, "loss": 0.0, "lr": 1.6866778523600774e-05, "epoch": 424.92035398230087, "percentage": 60.55, "elapsed_time": "2:54:06", "remaining_time": "1:53:25", "throughput": 1316.97, "total_tokens": 13757184} {"current_steps": 24225, "total_steps": 40000, "loss": 0.0, "lr": 1.6857495735464195e-05, "epoch": 425.0, "percentage": 60.56, "elapsed_time": "2:54:08", "remaining_time": "1:53:23", "throughput": 1316.92, "total_tokens": 13759352} {"current_steps": 24230, "total_steps": 40000, "loss": 0.0, "lr": 1.6848214203004115e-05, "epoch": 425.08849557522126, "percentage": 60.58, "elapsed_time": "2:54:10", "remaining_time": "1:53:21", "throughput": 1316.91, "total_tokens": 13762296} {"current_steps": 24235, "total_steps": 40000, "loss": 0.0, "lr": 1.6838933927651835e-05, "epoch": 425.17699115044246, "percentage": 60.59, "elapsed_time": "2:54:12", "remaining_time": "1:53:19", "throughput": 1316.94, "total_tokens": 13765320} {"current_steps": 24240, "total_steps": 40000, "loss": 0.0, "lr": 1.6829654910838506e-05, "epoch": 425.2654867256637, "percentage": 60.6, "elapsed_time": "2:54:14", "remaining_time": "1:53:17", "throughput": 1316.96, "total_tokens": 13768184} {"current_steps": 24245, "total_steps": 40000, "loss": 0.0, "lr": 1.6820377153995065e-05, "epoch": 425.353982300885, "percentage": 60.61, "elapsed_time": "2:54:16", "remaining_time": "1:53:14", "throughput": 1316.95, "total_tokens": 13770888} {"current_steps": 24250, "total_steps": 40000, "loss": 0.0, "lr": 1.681110065855226e-05, "epoch": 425.4424778761062, "percentage": 60.62, "elapsed_time": "2:54:18", "remaining_time": "1:53:12", "throughput": 1316.94, "total_tokens": 13773432} {"current_steps": 24255, "total_steps": 40000, "loss": 0.0, "lr": 1.6801825425940642e-05, "epoch": 425.53097345132744, "percentage": 60.64, "elapsed_time": "2:54:20", "remaining_time": "1:53:10", "throughput": 1316.96, "total_tokens": 13776440} {"current_steps": 24260, "total_steps": 40000, "loss": 0.0, "lr": 1.679255145759056e-05, "epoch": 425.6194690265487, "percentage": 60.65, "elapsed_time": "2:54:22", "remaining_time": "1:53:08", "throughput": 1316.98, "total_tokens": 13779320} {"current_steps": 24265, "total_steps": 40000, "loss": 0.0, "lr": 1.6783278754932187e-05, "epoch": 425.7079646017699, "percentage": 60.66, "elapsed_time": "2:54:24", "remaining_time": "1:53:06", "throughput": 1316.99, "total_tokens": 13782168} {"current_steps": 24270, "total_steps": 40000, "loss": 0.0, "lr": 1.6774007319395496e-05, "epoch": 425.79646017699116, "percentage": 60.68, "elapsed_time": "2:54:26", "remaining_time": "1:53:03", "throughput": 1317.03, "total_tokens": 13785288} {"current_steps": 24275, "total_steps": 40000, "loss": 0.0, "lr": 1.6764737152410243e-05, "epoch": 425.88495575221236, "percentage": 60.69, "elapsed_time": "2:54:29", "remaining_time": "1:53:01", "throughput": 1317.03, "total_tokens": 13788056} {"current_steps": 24280, "total_steps": 40000, "loss": 0.0, "lr": 1.6755468255406016e-05, "epoch": 425.9734513274336, "percentage": 60.7, "elapsed_time": "2:54:31", "remaining_time": "1:52:59", "throughput": 1317.04, "total_tokens": 13790920} {"current_steps": 24285, "total_steps": 40000, "loss": 0.0, "lr": 1.674620062981219e-05, "epoch": 426.05309734513276, "percentage": 60.71, "elapsed_time": "2:54:33", "remaining_time": "1:52:57", "throughput": 1317.0, "total_tokens": 13793464} {"current_steps": 24290, "total_steps": 40000, "loss": 0.0, "lr": 1.6736934277057947e-05, "epoch": 426.14159292035396, "percentage": 60.72, "elapsed_time": "2:54:35", "remaining_time": "1:52:55", "throughput": 1317.02, "total_tokens": 13796424} {"current_steps": 24295, "total_steps": 40000, "loss": 0.0, "lr": 1.6727669198572286e-05, "epoch": 426.2300884955752, "percentage": 60.74, "elapsed_time": "2:54:37", "remaining_time": "1:52:52", "throughput": 1317.02, "total_tokens": 13799064} {"current_steps": 24300, "total_steps": 40000, "loss": 0.0, "lr": 1.6718405395783984e-05, "epoch": 426.3185840707965, "percentage": 60.75, "elapsed_time": "2:54:39", "remaining_time": "1:52:50", "throughput": 1317.07, "total_tokens": 13802408} {"current_steps": 24305, "total_steps": 40000, "loss": 0.0, "lr": 1.6709142870121643e-05, "epoch": 426.4070796460177, "percentage": 60.76, "elapsed_time": "2:54:41", "remaining_time": "1:52:48", "throughput": 1317.05, "total_tokens": 13804920} {"current_steps": 24310, "total_steps": 40000, "loss": 0.0, "lr": 1.669988162301367e-05, "epoch": 426.49557522123894, "percentage": 60.77, "elapsed_time": "2:54:43", "remaining_time": "1:52:46", "throughput": 1317.09, "total_tokens": 13808008} {"current_steps": 24315, "total_steps": 40000, "loss": 0.0, "lr": 1.6690621655888243e-05, "epoch": 426.5840707964602, "percentage": 60.79, "elapsed_time": "2:54:45", "remaining_time": "1:52:44", "throughput": 1317.13, "total_tokens": 13811160} {"current_steps": 24320, "total_steps": 40000, "loss": 0.0, "lr": 1.6681362970173386e-05, "epoch": 426.6725663716814, "percentage": 60.8, "elapsed_time": "2:54:47", "remaining_time": "1:52:41", "throughput": 1317.18, "total_tokens": 13814472} {"current_steps": 24325, "total_steps": 40000, "loss": 0.0, "lr": 1.6672105567296904e-05, "epoch": 426.76106194690266, "percentage": 60.81, "elapsed_time": "2:54:49", "remaining_time": "1:52:39", "throughput": 1317.21, "total_tokens": 13817528} {"current_steps": 24330, "total_steps": 40000, "loss": 0.0, "lr": 1.666284944868639e-05, "epoch": 426.8495575221239, "percentage": 60.82, "elapsed_time": "2:54:52", "remaining_time": "1:52:37", "throughput": 1317.18, "total_tokens": 13819960} {"current_steps": 24335, "total_steps": 40000, "loss": 0.0, "lr": 1.665359461576927e-05, "epoch": 426.9380530973451, "percentage": 60.84, "elapsed_time": "2:54:54", "remaining_time": "1:52:35", "throughput": 1317.19, "total_tokens": 13822712} {"current_steps": 24340, "total_steps": 40000, "loss": 0.0, "lr": 1.6644341069972736e-05, "epoch": 427.01769911504425, "percentage": 60.85, "elapsed_time": "2:54:56", "remaining_time": "1:52:33", "throughput": 1317.14, "total_tokens": 13825240} {"current_steps": 24345, "total_steps": 40000, "loss": 0.0, "lr": 1.6635088812723813e-05, "epoch": 427.1061946902655, "percentage": 60.86, "elapsed_time": "2:54:58", "remaining_time": "1:52:31", "throughput": 1317.12, "total_tokens": 13827688} {"current_steps": 24350, "total_steps": 40000, "loss": 0.0, "lr": 1.6625837845449328e-05, "epoch": 427.1946902654867, "percentage": 60.88, "elapsed_time": "2:55:00", "remaining_time": "1:52:28", "throughput": 1317.16, "total_tokens": 13830840} {"current_steps": 24355, "total_steps": 40000, "loss": 0.0, "lr": 1.6616588169575874e-05, "epoch": 427.283185840708, "percentage": 60.89, "elapsed_time": "2:55:02", "remaining_time": "1:52:26", "throughput": 1317.22, "total_tokens": 13834264} {"current_steps": 24360, "total_steps": 40000, "loss": 0.0, "lr": 1.6607339786529878e-05, "epoch": 427.37168141592923, "percentage": 60.9, "elapsed_time": "2:55:04", "remaining_time": "1:52:24", "throughput": 1317.26, "total_tokens": 13837336} {"current_steps": 24365, "total_steps": 40000, "loss": 0.0, "lr": 1.659809269773756e-05, "epoch": 427.46017699115043, "percentage": 60.91, "elapsed_time": "2:55:06", "remaining_time": "1:52:22", "throughput": 1317.27, "total_tokens": 13840168} {"current_steps": 24370, "total_steps": 40000, "loss": 0.0, "lr": 1.658884690462493e-05, "epoch": 427.5486725663717, "percentage": 60.92, "elapsed_time": "2:55:08", "remaining_time": "1:52:19", "throughput": 1317.25, "total_tokens": 13842760} {"current_steps": 24375, "total_steps": 40000, "loss": 0.0, "lr": 1.6579602408617813e-05, "epoch": 427.6371681415929, "percentage": 60.94, "elapsed_time": "2:55:10", "remaining_time": "1:52:17", "throughput": 1317.26, "total_tokens": 13845592} {"current_steps": 24380, "total_steps": 40000, "loss": 0.0, "lr": 1.657035921114181e-05, "epoch": 427.72566371681415, "percentage": 60.95, "elapsed_time": "2:55:12", "remaining_time": "1:52:15", "throughput": 1317.29, "total_tokens": 13848568} {"current_steps": 24385, "total_steps": 40000, "loss": 0.0, "lr": 1.656111731362236e-05, "epoch": 427.8141592920354, "percentage": 60.96, "elapsed_time": "2:55:15", "remaining_time": "1:52:13", "throughput": 1317.3, "total_tokens": 13851464} {"current_steps": 24390, "total_steps": 40000, "loss": 0.0, "lr": 1.6551876717484666e-05, "epoch": 427.9026548672566, "percentage": 60.98, "elapsed_time": "2:55:17", "remaining_time": "1:52:11", "throughput": 1317.36, "total_tokens": 13854744} {"current_steps": 24395, "total_steps": 40000, "loss": 0.0, "lr": 1.6542637424153752e-05, "epoch": 427.9911504424779, "percentage": 60.99, "elapsed_time": "2:55:19", "remaining_time": "1:52:08", "throughput": 1317.34, "total_tokens": 13857256} {"current_steps": 24400, "total_steps": 40000, "loss": 0.0, "lr": 1.6533399435054418e-05, "epoch": 428.070796460177, "percentage": 61.0, "elapsed_time": "2:55:21", "remaining_time": "1:52:06", "throughput": 1317.29, "total_tokens": 13859752} {"current_steps": 24400, "total_steps": 40000, "eval_loss": 0.5260993242263794, "epoch": 428.070796460177, "percentage": 61.0, "elapsed_time": "2:55:22", "remaining_time": "1:52:07", "throughput": 1317.16, "total_tokens": 13859752} {"current_steps": 24405, "total_steps": 40000, "loss": 0.0, "lr": 1.6524162751611304e-05, "epoch": 428.1592920353982, "percentage": 61.01, "elapsed_time": "2:55:26", "remaining_time": "1:52:06", "throughput": 1317.05, "total_tokens": 13863672} {"current_steps": 24410, "total_steps": 40000, "loss": 0.0, "lr": 1.6514927375248796e-05, "epoch": 428.24778761061947, "percentage": 61.02, "elapsed_time": "2:55:28", "remaining_time": "1:52:04", "throughput": 1317.07, "total_tokens": 13866632} {"current_steps": 24415, "total_steps": 40000, "loss": 0.0, "lr": 1.6505693307391127e-05, "epoch": 428.3362831858407, "percentage": 61.04, "elapsed_time": "2:55:30", "remaining_time": "1:52:01", "throughput": 1317.09, "total_tokens": 13869592} {"current_steps": 24420, "total_steps": 40000, "loss": 0.0, "lr": 1.6496460549462288e-05, "epoch": 428.42477876106193, "percentage": 61.05, "elapsed_time": "2:55:32", "remaining_time": "1:51:59", "throughput": 1317.11, "total_tokens": 13872472} {"current_steps": 24425, "total_steps": 40000, "loss": 0.0, "lr": 1.6487229102886097e-05, "epoch": 428.5132743362832, "percentage": 61.06, "elapsed_time": "2:55:34", "remaining_time": "1:51:57", "throughput": 1317.09, "total_tokens": 13875032} {"current_steps": 24430, "total_steps": 40000, "loss": 0.0, "lr": 1.6477998969086155e-05, "epoch": 428.60176991150445, "percentage": 61.08, "elapsed_time": "2:55:36", "remaining_time": "1:51:55", "throughput": 1317.08, "total_tokens": 13877624} {"current_steps": 24435, "total_steps": 40000, "loss": 0.0, "lr": 1.646877014948587e-05, "epoch": 428.69026548672565, "percentage": 61.09, "elapsed_time": "2:55:38", "remaining_time": "1:51:53", "throughput": 1317.05, "total_tokens": 13880056} {"current_steps": 24440, "total_steps": 40000, "loss": 0.0, "lr": 1.6459542645508433e-05, "epoch": 428.7787610619469, "percentage": 61.1, "elapsed_time": "2:55:40", "remaining_time": "1:51:50", "throughput": 1317.09, "total_tokens": 13883192} {"current_steps": 24445, "total_steps": 40000, "loss": 0.0, "lr": 1.6450316458576852e-05, "epoch": 428.86725663716817, "percentage": 61.11, "elapsed_time": "2:55:42", "remaining_time": "1:51:48", "throughput": 1317.07, "total_tokens": 13885720} {"current_steps": 24450, "total_steps": 40000, "loss": 0.0, "lr": 1.6441091590113912e-05, "epoch": 428.95575221238937, "percentage": 61.12, "elapsed_time": "2:55:44", "remaining_time": "1:51:46", "throughput": 1317.1, "total_tokens": 13888776} {"current_steps": 24455, "total_steps": 40000, "loss": 0.0, "lr": 1.6431868041542213e-05, "epoch": 429.0353982300885, "percentage": 61.14, "elapsed_time": "2:55:47", "remaining_time": "1:51:44", "throughput": 1317.05, "total_tokens": 13891224} {"current_steps": 24460, "total_steps": 40000, "loss": 0.0, "lr": 1.6422645814284123e-05, "epoch": 429.12389380530976, "percentage": 61.15, "elapsed_time": "2:55:49", "remaining_time": "1:51:42", "throughput": 1317.07, "total_tokens": 13894136} {"current_steps": 24465, "total_steps": 40000, "loss": 0.0, "lr": 1.6413424909761846e-05, "epoch": 429.21238938053096, "percentage": 61.16, "elapsed_time": "2:55:51", "remaining_time": "1:51:39", "throughput": 1317.06, "total_tokens": 13896744} {"current_steps": 24470, "total_steps": 40000, "loss": 0.0, "lr": 1.640420532939736e-05, "epoch": 429.3008849557522, "percentage": 61.18, "elapsed_time": "2:55:53", "remaining_time": "1:51:37", "throughput": 1317.06, "total_tokens": 13899512} {"current_steps": 24475, "total_steps": 40000, "loss": 0.0, "lr": 1.639498707461242e-05, "epoch": 429.3893805309734, "percentage": 61.19, "elapsed_time": "2:55:55", "remaining_time": "1:51:35", "throughput": 1317.1, "total_tokens": 13902616} {"current_steps": 24480, "total_steps": 40000, "loss": 0.0, "lr": 1.6385770146828614e-05, "epoch": 429.4778761061947, "percentage": 61.2, "elapsed_time": "2:55:57", "remaining_time": "1:51:33", "throughput": 1317.09, "total_tokens": 13905256} {"current_steps": 24485, "total_steps": 40000, "loss": 0.0, "lr": 1.637655454746731e-05, "epoch": 429.56637168141594, "percentage": 61.21, "elapsed_time": "2:55:59", "remaining_time": "1:51:31", "throughput": 1317.14, "total_tokens": 13908536} {"current_steps": 24490, "total_steps": 40000, "loss": 0.0, "lr": 1.6367340277949658e-05, "epoch": 429.65486725663715, "percentage": 61.22, "elapsed_time": "2:56:01", "remaining_time": "1:51:28", "throughput": 1317.15, "total_tokens": 13911384} {"current_steps": 24495, "total_steps": 40000, "loss": 0.0, "lr": 1.635812733969663e-05, "epoch": 429.7433628318584, "percentage": 61.24, "elapsed_time": "2:56:03", "remaining_time": "1:51:26", "throughput": 1317.19, "total_tokens": 13914520} {"current_steps": 24500, "total_steps": 40000, "loss": 0.0, "lr": 1.634891573412896e-05, "epoch": 429.83185840707966, "percentage": 61.25, "elapsed_time": "2:56:05", "remaining_time": "1:51:24", "throughput": 1317.21, "total_tokens": 13917448} {"current_steps": 24505, "total_steps": 40000, "loss": 0.0, "lr": 1.6339705462667196e-05, "epoch": 429.92035398230087, "percentage": 61.26, "elapsed_time": "2:56:07", "remaining_time": "1:51:22", "throughput": 1317.2, "total_tokens": 13920136} {"current_steps": 24510, "total_steps": 40000, "loss": 0.0, "lr": 1.633049652673169e-05, "epoch": 430.0, "percentage": 61.27, "elapsed_time": "2:56:09", "remaining_time": "1:51:20", "throughput": 1317.16, "total_tokens": 13922320} {"current_steps": 24515, "total_steps": 40000, "loss": 0.0, "lr": 1.632128892774256e-05, "epoch": 430.08849557522126, "percentage": 61.29, "elapsed_time": "2:56:12", "remaining_time": "1:51:18", "throughput": 1317.14, "total_tokens": 13925120} {"current_steps": 24520, "total_steps": 40000, "loss": 0.0, "lr": 1.6312082667119737e-05, "epoch": 430.17699115044246, "percentage": 61.3, "elapsed_time": "2:56:14", "remaining_time": "1:51:15", "throughput": 1317.19, "total_tokens": 13928400} {"current_steps": 24525, "total_steps": 40000, "loss": 0.0, "lr": 1.630287774628296e-05, "epoch": 430.2654867256637, "percentage": 61.31, "elapsed_time": "2:56:16", "remaining_time": "1:51:13", "throughput": 1317.16, "total_tokens": 13930816} {"current_steps": 24530, "total_steps": 40000, "loss": 0.0, "lr": 1.6293674166651718e-05, "epoch": 430.353982300885, "percentage": 61.32, "elapsed_time": "2:56:18", "remaining_time": "1:51:11", "throughput": 1317.17, "total_tokens": 13933712} {"current_steps": 24535, "total_steps": 40000, "loss": 0.0, "lr": 1.6284471929645338e-05, "epoch": 430.4424778761062, "percentage": 61.34, "elapsed_time": "2:56:20", "remaining_time": "1:51:09", "throughput": 1317.18, "total_tokens": 13936576} {"current_steps": 24540, "total_steps": 40000, "loss": 0.0, "lr": 1.627527103668291e-05, "epoch": 430.53097345132744, "percentage": 61.35, "elapsed_time": "2:56:22", "remaining_time": "1:51:06", "throughput": 1317.23, "total_tokens": 13939824} {"current_steps": 24545, "total_steps": 40000, "loss": 0.0, "lr": 1.6266071489183327e-05, "epoch": 430.6194690265487, "percentage": 61.36, "elapsed_time": "2:56:24", "remaining_time": "1:51:04", "throughput": 1317.25, "total_tokens": 13942752} {"current_steps": 24550, "total_steps": 40000, "loss": 0.0, "lr": 1.6256873288565283e-05, "epoch": 430.7079646017699, "percentage": 61.38, "elapsed_time": "2:56:26", "remaining_time": "1:51:02", "throughput": 1317.25, "total_tokens": 13945504} {"current_steps": 24555, "total_steps": 40000, "loss": 0.0, "lr": 1.6247676436247245e-05, "epoch": 430.79646017699116, "percentage": 61.39, "elapsed_time": "2:56:28", "remaining_time": "1:51:00", "throughput": 1317.25, "total_tokens": 13948240} {"current_steps": 24560, "total_steps": 40000, "loss": 0.0, "lr": 1.6238480933647486e-05, "epoch": 430.88495575221236, "percentage": 61.4, "elapsed_time": "2:56:30", "remaining_time": "1:50:58", "throughput": 1317.26, "total_tokens": 13951040} {"current_steps": 24565, "total_steps": 40000, "loss": 0.0, "lr": 1.6229286782184083e-05, "epoch": 430.9734513274336, "percentage": 61.41, "elapsed_time": "2:56:33", "remaining_time": "1:50:55", "throughput": 1317.26, "total_tokens": 13953808} {"current_steps": 24570, "total_steps": 40000, "loss": 0.0, "lr": 1.622009398327487e-05, "epoch": 431.05309734513276, "percentage": 61.42, "elapsed_time": "2:56:35", "remaining_time": "1:50:53", "throughput": 1317.21, "total_tokens": 13956216} {"current_steps": 24575, "total_steps": 40000, "loss": 0.0, "lr": 1.6210902538337502e-05, "epoch": 431.14159292035396, "percentage": 61.44, "elapsed_time": "2:56:37", "remaining_time": "1:50:51", "throughput": 1317.2, "total_tokens": 13958872} {"current_steps": 24580, "total_steps": 40000, "loss": 0.0, "lr": 1.6201712448789413e-05, "epoch": 431.2300884955752, "percentage": 61.45, "elapsed_time": "2:56:39", "remaining_time": "1:50:49", "throughput": 1317.23, "total_tokens": 13961848} {"current_steps": 24585, "total_steps": 40000, "loss": 0.0, "lr": 1.6192523716047827e-05, "epoch": 431.3185840707965, "percentage": 61.46, "elapsed_time": "2:56:41", "remaining_time": "1:50:47", "throughput": 1317.23, "total_tokens": 13964632} {"current_steps": 24590, "total_steps": 40000, "loss": 0.0, "lr": 1.6183336341529776e-05, "epoch": 431.4070796460177, "percentage": 61.48, "elapsed_time": "2:56:43", "remaining_time": "1:50:45", "throughput": 1317.2, "total_tokens": 13967048} {"current_steps": 24595, "total_steps": 40000, "loss": 0.0, "lr": 1.6174150326652047e-05, "epoch": 431.49557522123894, "percentage": 61.49, "elapsed_time": "2:56:45", "remaining_time": "1:50:42", "throughput": 1317.17, "total_tokens": 13969480} {"current_steps": 24600, "total_steps": 40000, "loss": 0.0, "lr": 1.6164965672831256e-05, "epoch": 431.5840707964602, "percentage": 61.5, "elapsed_time": "2:56:47", "remaining_time": "1:50:40", "throughput": 1317.21, "total_tokens": 13972648} {"current_steps": 24600, "total_steps": 40000, "eval_loss": 0.5022317171096802, "epoch": 431.5840707964602, "percentage": 61.5, "elapsed_time": "2:56:48", "remaining_time": "1:50:41", "throughput": 1317.08, "total_tokens": 13972648} {"current_steps": 24605, "total_steps": 40000, "loss": 0.0, "lr": 1.6155782381483784e-05, "epoch": 431.6725663716814, "percentage": 61.51, "elapsed_time": "2:56:52", "remaining_time": "1:50:40", "throughput": 1316.91, "total_tokens": 13975832} {"current_steps": 24610, "total_steps": 40000, "loss": 0.0, "lr": 1.6146600454025813e-05, "epoch": 431.76106194690266, "percentage": 61.52, "elapsed_time": "2:56:54", "remaining_time": "1:50:37", "throughput": 1316.96, "total_tokens": 13979112} {"current_steps": 24615, "total_steps": 40000, "loss": 0.0, "lr": 1.6137419891873317e-05, "epoch": 431.8495575221239, "percentage": 61.54, "elapsed_time": "2:56:56", "remaining_time": "1:50:35", "throughput": 1316.97, "total_tokens": 13981960} {"current_steps": 24620, "total_steps": 40000, "loss": 0.0, "lr": 1.6128240696442038e-05, "epoch": 431.9380530973451, "percentage": 61.55, "elapsed_time": "2:56:58", "remaining_time": "1:50:33", "throughput": 1316.96, "total_tokens": 13984536} {"current_steps": 24625, "total_steps": 40000, "loss": 0.0, "lr": 1.611906286914753e-05, "epoch": 432.01769911504425, "percentage": 61.56, "elapsed_time": "2:57:01", "remaining_time": "1:50:31", "throughput": 1316.9, "total_tokens": 13986872} {"current_steps": 24630, "total_steps": 40000, "loss": 0.0, "lr": 1.6109886411405144e-05, "epoch": 432.1061946902655, "percentage": 61.58, "elapsed_time": "2:57:03", "remaining_time": "1:50:29", "throughput": 1316.87, "total_tokens": 13989352} {"current_steps": 24635, "total_steps": 40000, "loss": 0.0, "lr": 1.6100711324629985e-05, "epoch": 432.1946902654867, "percentage": 61.59, "elapsed_time": "2:57:05", "remaining_time": "1:50:27", "throughput": 1316.89, "total_tokens": 13992280} {"current_steps": 24640, "total_steps": 40000, "loss": 0.0, "lr": 1.609153761023698e-05, "epoch": 432.283185840708, "percentage": 61.6, "elapsed_time": "2:57:07", "remaining_time": "1:50:24", "throughput": 1316.92, "total_tokens": 13995256} {"current_steps": 24645, "total_steps": 40000, "loss": 0.0, "lr": 1.608236526964083e-05, "epoch": 432.37168141592923, "percentage": 61.61, "elapsed_time": "2:57:09", "remaining_time": "1:50:22", "throughput": 1316.92, "total_tokens": 13997992} {"current_steps": 24650, "total_steps": 40000, "loss": 0.0, "lr": 1.607319430425601e-05, "epoch": 432.46017699115043, "percentage": 61.62, "elapsed_time": "2:57:11", "remaining_time": "1:50:20", "throughput": 1316.93, "total_tokens": 14000792} {"current_steps": 24655, "total_steps": 40000, "loss": 0.0, "lr": 1.606402471549682e-05, "epoch": 432.5486725663717, "percentage": 61.64, "elapsed_time": "2:57:13", "remaining_time": "1:50:18", "throughput": 1316.91, "total_tokens": 14003352} {"current_steps": 24660, "total_steps": 40000, "loss": 0.0, "lr": 1.6054856504777312e-05, "epoch": 432.6371681415929, "percentage": 61.65, "elapsed_time": "2:57:15", "remaining_time": "1:50:15", "throughput": 1317.0, "total_tokens": 14007016} {"current_steps": 24665, "total_steps": 40000, "loss": 0.0, "lr": 1.6045689673511334e-05, "epoch": 432.72566371681415, "percentage": 61.66, "elapsed_time": "2:57:17", "remaining_time": "1:50:13", "throughput": 1317.02, "total_tokens": 14009928} {"current_steps": 24670, "total_steps": 40000, "loss": 0.0, "lr": 1.6036524223112548e-05, "epoch": 432.8141592920354, "percentage": 61.68, "elapsed_time": "2:57:19", "remaining_time": "1:50:11", "throughput": 1317.03, "total_tokens": 14012792} {"current_steps": 24675, "total_steps": 40000, "loss": 0.0, "lr": 1.602736015499436e-05, "epoch": 432.9026548672566, "percentage": 61.69, "elapsed_time": "2:57:21", "remaining_time": "1:50:09", "throughput": 1317.02, "total_tokens": 14015400} {"current_steps": 24680, "total_steps": 40000, "loss": 0.0, "lr": 1.601819747057e-05, "epoch": 432.9911504424779, "percentage": 61.7, "elapsed_time": "2:57:23", "remaining_time": "1:50:07", "throughput": 1317.1, "total_tokens": 14018920} {"current_steps": 24685, "total_steps": 40000, "loss": 0.0, "lr": 1.6009036171252465e-05, "epoch": 433.070796460177, "percentage": 61.71, "elapsed_time": "2:57:26", "remaining_time": "1:50:05", "throughput": 1317.08, "total_tokens": 14021720} {"current_steps": 24690, "total_steps": 40000, "loss": 0.0, "lr": 1.599987625845453e-05, "epoch": 433.1592920353982, "percentage": 61.72, "elapsed_time": "2:57:28", "remaining_time": "1:50:02", "throughput": 1317.13, "total_tokens": 14025016} {"current_steps": 24695, "total_steps": 40000, "loss": 0.0, "lr": 1.599071773358879e-05, "epoch": 433.24778761061947, "percentage": 61.74, "elapsed_time": "2:57:30", "remaining_time": "1:50:00", "throughput": 1317.16, "total_tokens": 14028056} {"current_steps": 24700, "total_steps": 40000, "loss": 0.0, "lr": 1.598156059806758e-05, "epoch": 433.3362831858407, "percentage": 61.75, "elapsed_time": "2:57:32", "remaining_time": "1:49:58", "throughput": 1317.17, "total_tokens": 14030888} {"current_steps": 24705, "total_steps": 40000, "loss": 0.0, "lr": 1.5972404853303062e-05, "epoch": 433.42477876106193, "percentage": 61.76, "elapsed_time": "2:57:34", "remaining_time": "1:49:56", "throughput": 1317.16, "total_tokens": 14033480} {"current_steps": 24710, "total_steps": 40000, "loss": 0.0, "lr": 1.5963250500707172e-05, "epoch": 433.5132743362832, "percentage": 61.78, "elapsed_time": "2:57:36", "remaining_time": "1:49:53", "throughput": 1317.2, "total_tokens": 14036648} {"current_steps": 24715, "total_steps": 40000, "loss": 0.0, "lr": 1.5954097541691612e-05, "epoch": 433.60176991150445, "percentage": 61.79, "elapsed_time": "2:57:38", "remaining_time": "1:49:51", "throughput": 1317.17, "total_tokens": 14039096} {"current_steps": 24720, "total_steps": 40000, "loss": 0.0, "lr": 1.5944945977667884e-05, "epoch": 433.69026548672565, "percentage": 61.8, "elapsed_time": "2:57:40", "remaining_time": "1:49:49", "throughput": 1317.19, "total_tokens": 14042024} {"current_steps": 24725, "total_steps": 40000, "loss": 0.0, "lr": 1.593579581004729e-05, "epoch": 433.7787610619469, "percentage": 61.81, "elapsed_time": "2:57:42", "remaining_time": "1:49:47", "throughput": 1317.21, "total_tokens": 14045032} {"current_steps": 24730, "total_steps": 40000, "loss": 0.0, "lr": 1.592664704024088e-05, "epoch": 433.86725663716817, "percentage": 61.82, "elapsed_time": "2:57:44", "remaining_time": "1:49:45", "throughput": 1317.18, "total_tokens": 14047384} {"current_steps": 24735, "total_steps": 40000, "loss": 0.0, "lr": 1.591749966965953e-05, "epoch": 433.95575221238937, "percentage": 61.84, "elapsed_time": "2:57:46", "remaining_time": "1:49:42", "throughput": 1317.18, "total_tokens": 14050136} {"current_steps": 24740, "total_steps": 40000, "loss": 0.0, "lr": 1.5908353699713856e-05, "epoch": 434.0353982300885, "percentage": 61.85, "elapsed_time": "2:57:49", "remaining_time": "1:49:40", "throughput": 1317.15, "total_tokens": 14052824} {"current_steps": 24745, "total_steps": 40000, "loss": 0.0, "lr": 1.5899209131814298e-05, "epoch": 434.12389380530976, "percentage": 61.86, "elapsed_time": "2:57:51", "remaining_time": "1:49:38", "throughput": 1317.18, "total_tokens": 14055816} {"current_steps": 24750, "total_steps": 40000, "loss": 0.0, "lr": 1.5890065967371067e-05, "epoch": 434.21238938053096, "percentage": 61.88, "elapsed_time": "2:57:53", "remaining_time": "1:49:36", "throughput": 1317.19, "total_tokens": 14058712} {"current_steps": 24755, "total_steps": 40000, "loss": 0.0, "lr": 1.5880924207794144e-05, "epoch": 434.3008849557522, "percentage": 61.89, "elapsed_time": "2:57:55", "remaining_time": "1:49:34", "throughput": 1317.16, "total_tokens": 14061176} {"current_steps": 24760, "total_steps": 40000, "loss": 0.0, "lr": 1.5871783854493298e-05, "epoch": 434.3893805309734, "percentage": 61.9, "elapsed_time": "2:57:57", "remaining_time": "1:49:32", "throughput": 1317.14, "total_tokens": 14064056} {"current_steps": 24765, "total_steps": 40000, "loss": 0.0, "lr": 1.5862644908878106e-05, "epoch": 434.4778761061947, "percentage": 61.91, "elapsed_time": "2:57:59", "remaining_time": "1:49:30", "throughput": 1317.17, "total_tokens": 14067096} {"current_steps": 24770, "total_steps": 40000, "loss": 0.0, "lr": 1.5853507372357885e-05, "epoch": 434.56637168141594, "percentage": 61.92, "elapsed_time": "2:58:01", "remaining_time": "1:49:27", "throughput": 1317.21, "total_tokens": 14070264} {"current_steps": 24775, "total_steps": 40000, "loss": 0.0, "lr": 1.5844371246341776e-05, "epoch": 434.65486725663715, "percentage": 61.94, "elapsed_time": "2:58:03", "remaining_time": "1:49:25", "throughput": 1317.19, "total_tokens": 14072728} {"current_steps": 24780, "total_steps": 40000, "loss": 0.0, "lr": 1.5835236532238674e-05, "epoch": 434.7433628318584, "percentage": 61.95, "elapsed_time": "2:58:05", "remaining_time": "1:49:23", "throughput": 1317.19, "total_tokens": 14075464} {"current_steps": 24785, "total_steps": 40000, "loss": 0.0, "lr": 1.582610323145727e-05, "epoch": 434.83185840707966, "percentage": 61.96, "elapsed_time": "2:58:08", "remaining_time": "1:49:21", "throughput": 1317.24, "total_tokens": 14078776} {"current_steps": 24790, "total_steps": 40000, "loss": 0.0, "lr": 1.5816971345406035e-05, "epoch": 434.92035398230087, "percentage": 61.98, "elapsed_time": "2:58:10", "remaining_time": "1:49:18", "throughput": 1317.25, "total_tokens": 14081576} {"current_steps": 24795, "total_steps": 40000, "loss": 0.0, "lr": 1.5807840875493225e-05, "epoch": 435.0, "percentage": 61.99, "elapsed_time": "2:58:12", "remaining_time": "1:49:16", "throughput": 1317.22, "total_tokens": 14083896} {"current_steps": 24800, "total_steps": 40000, "loss": 0.0, "lr": 1.5798711823126854e-05, "epoch": 435.08849557522126, "percentage": 62.0, "elapsed_time": "2:58:14", "remaining_time": "1:49:14", "throughput": 1317.17, "total_tokens": 14086360} {"current_steps": 24800, "total_steps": 40000, "eval_loss": 0.5776745080947876, "epoch": 435.08849557522126, "percentage": 62.0, "elapsed_time": "2:58:15", "remaining_time": "1:49:15", "throughput": 1317.03, "total_tokens": 14086360} {"current_steps": 24805, "total_steps": 40000, "loss": 0.0, "lr": 1.578958418971477e-05, "epoch": 435.17699115044246, "percentage": 62.01, "elapsed_time": "2:58:19", "remaining_time": "1:49:14", "throughput": 1316.84, "total_tokens": 14089400} {"current_steps": 24810, "total_steps": 40000, "loss": 0.0, "lr": 1.578045797666453e-05, "epoch": 435.2654867256637, "percentage": 62.02, "elapsed_time": "2:58:21", "remaining_time": "1:49:12", "throughput": 1316.89, "total_tokens": 14092600} {"current_steps": 24815, "total_steps": 40000, "loss": 0.0, "lr": 1.5771333185383548e-05, "epoch": 435.353982300885, "percentage": 62.04, "elapsed_time": "2:58:23", "remaining_time": "1:49:09", "throughput": 1316.88, "total_tokens": 14095240} {"current_steps": 24820, "total_steps": 40000, "loss": 0.0, "lr": 1.576220981727895e-05, "epoch": 435.4424778761062, "percentage": 62.05, "elapsed_time": "2:58:25", "remaining_time": "1:49:07", "throughput": 1316.9, "total_tokens": 14098200} {"current_steps": 24825, "total_steps": 40000, "loss": 0.0, "lr": 1.575308787375769e-05, "epoch": 435.53097345132744, "percentage": 62.06, "elapsed_time": "2:58:27", "remaining_time": "1:49:05", "throughput": 1316.95, "total_tokens": 14101480} {"current_steps": 24830, "total_steps": 40000, "loss": 0.0, "lr": 1.5743967356226492e-05, "epoch": 435.6194690265487, "percentage": 62.08, "elapsed_time": "2:58:29", "remaining_time": "1:49:03", "throughput": 1316.93, "total_tokens": 14103960} {"current_steps": 24835, "total_steps": 40000, "loss": 0.0, "lr": 1.5734848266091835e-05, "epoch": 435.7079646017699, "percentage": 62.09, "elapsed_time": "2:58:31", "remaining_time": "1:49:00", "throughput": 1316.96, "total_tokens": 14107048} {"current_steps": 24840, "total_steps": 40000, "loss": 0.0, "lr": 1.572573060476001e-05, "epoch": 435.79646017699116, "percentage": 62.1, "elapsed_time": "2:58:33", "remaining_time": "1:48:58", "throughput": 1316.98, "total_tokens": 14110008} {"current_steps": 24845, "total_steps": 40000, "loss": 0.0, "lr": 1.5716614373637085e-05, "epoch": 435.88495575221236, "percentage": 62.11, "elapsed_time": "2:58:35", "remaining_time": "1:48:56", "throughput": 1317.01, "total_tokens": 14113000} {"current_steps": 24850, "total_steps": 40000, "loss": 0.0, "lr": 1.570749957412887e-05, "epoch": 435.9734513274336, "percentage": 62.12, "elapsed_time": "2:58:37", "remaining_time": "1:48:54", "throughput": 1317.01, "total_tokens": 14115752} {"current_steps": 24855, "total_steps": 40000, "loss": 0.0, "lr": 1.5698386207641013e-05, "epoch": 436.05309734513276, "percentage": 62.14, "elapsed_time": "2:58:40", "remaining_time": "1:48:52", "throughput": 1316.96, "total_tokens": 14118128} {"current_steps": 24860, "total_steps": 40000, "loss": 0.0, "lr": 1.5689274275578884e-05, "epoch": 436.14159292035396, "percentage": 62.15, "elapsed_time": "2:58:42", "remaining_time": "1:48:50", "throughput": 1316.98, "total_tokens": 14121072} {"current_steps": 24865, "total_steps": 40000, "loss": 0.0, "lr": 1.5680163779347667e-05, "epoch": 436.2300884955752, "percentage": 62.16, "elapsed_time": "2:58:44", "remaining_time": "1:48:47", "throughput": 1317.03, "total_tokens": 14124304} {"current_steps": 24870, "total_steps": 40000, "loss": 0.0, "lr": 1.5671054720352327e-05, "epoch": 436.3185840707965, "percentage": 62.18, "elapsed_time": "2:58:46", "remaining_time": "1:48:45", "throughput": 1317.03, "total_tokens": 14127056} {"current_steps": 24875, "total_steps": 40000, "loss": 0.0, "lr": 1.566194709999757e-05, "epoch": 436.4070796460177, "percentage": 62.19, "elapsed_time": "2:58:48", "remaining_time": "1:48:43", "throughput": 1317.03, "total_tokens": 14129776} {"current_steps": 24880, "total_steps": 40000, "loss": 0.0, "lr": 1.5652840919687933e-05, "epoch": 436.49557522123894, "percentage": 62.2, "elapsed_time": "2:58:50", "remaining_time": "1:48:41", "throughput": 1317.02, "total_tokens": 14132400} {"current_steps": 24885, "total_steps": 40000, "loss": 0.0, "lr": 1.5643736180827676e-05, "epoch": 436.5840707964602, "percentage": 62.21, "elapsed_time": "2:58:52", "remaining_time": "1:48:38", "throughput": 1317.03, "total_tokens": 14135280} {"current_steps": 24890, "total_steps": 40000, "loss": 0.0, "lr": 1.5634632884820878e-05, "epoch": 436.6725663716814, "percentage": 62.22, "elapsed_time": "2:58:54", "remaining_time": "1:48:36", "throughput": 1317.01, "total_tokens": 14137776} {"current_steps": 24895, "total_steps": 40000, "loss": 0.0, "lr": 1.5625531033071395e-05, "epoch": 436.76106194690266, "percentage": 62.24, "elapsed_time": "2:58:56", "remaining_time": "1:48:34", "throughput": 1317.03, "total_tokens": 14140768} {"current_steps": 24900, "total_steps": 40000, "loss": 0.0, "lr": 1.5616430626982828e-05, "epoch": 436.8495575221239, "percentage": 62.25, "elapsed_time": "2:58:58", "remaining_time": "1:48:32", "throughput": 1317.05, "total_tokens": 14143744} {"current_steps": 24905, "total_steps": 40000, "loss": 0.0, "lr": 1.5607331667958575e-05, "epoch": 436.9380530973451, "percentage": 62.26, "elapsed_time": "2:59:01", "remaining_time": "1:48:30", "throughput": 1317.05, "total_tokens": 14146448} {"current_steps": 24910, "total_steps": 40000, "loss": 0.0, "lr": 1.5598234157401824e-05, "epoch": 437.01769911504425, "percentage": 62.28, "elapsed_time": "2:59:03", "remaining_time": "1:48:28", "throughput": 1317.03, "total_tokens": 14149152} {"current_steps": 24915, "total_steps": 40000, "loss": 0.0, "lr": 1.5589138096715503e-05, "epoch": 437.1061946902655, "percentage": 62.29, "elapsed_time": "2:59:05", "remaining_time": "1:48:25", "throughput": 1317.03, "total_tokens": 14151952} {"current_steps": 24920, "total_steps": 40000, "loss": 0.0, "lr": 1.5580043487302365e-05, "epoch": 437.1946902654867, "percentage": 62.3, "elapsed_time": "2:59:07", "remaining_time": "1:48:23", "throughput": 1317.04, "total_tokens": 14154784} {"current_steps": 24925, "total_steps": 40000, "loss": 0.0, "lr": 1.5570950330564888e-05, "epoch": 437.283185840708, "percentage": 62.31, "elapsed_time": "2:59:09", "remaining_time": "1:48:21", "throughput": 1317.07, "total_tokens": 14157872} {"current_steps": 24930, "total_steps": 40000, "loss": 0.0, "lr": 1.5561858627905367e-05, "epoch": 437.37168141592923, "percentage": 62.32, "elapsed_time": "2:59:11", "remaining_time": "1:48:19", "throughput": 1317.11, "total_tokens": 14161040} {"current_steps": 24935, "total_steps": 40000, "loss": 0.0, "lr": 1.5552768380725857e-05, "epoch": 437.46017699115043, "percentage": 62.34, "elapsed_time": "2:59:13", "remaining_time": "1:48:17", "throughput": 1317.12, "total_tokens": 14163872} {"current_steps": 24940, "total_steps": 40000, "loss": 0.0, "lr": 1.5543679590428183e-05, "epoch": 437.5486725663717, "percentage": 62.35, "elapsed_time": "2:59:15", "remaining_time": "1:48:14", "throughput": 1317.17, "total_tokens": 14167152} {"current_steps": 24945, "total_steps": 40000, "loss": 0.0, "lr": 1.5534592258413943e-05, "epoch": 437.6371681415929, "percentage": 62.36, "elapsed_time": "2:59:17", "remaining_time": "1:48:12", "throughput": 1317.17, "total_tokens": 14169888} {"current_steps": 24950, "total_steps": 40000, "loss": 0.0, "lr": 1.5525506386084538e-05, "epoch": 437.72566371681415, "percentage": 62.38, "elapsed_time": "2:59:19", "remaining_time": "1:48:10", "throughput": 1317.21, "total_tokens": 14172992} {"current_steps": 24955, "total_steps": 40000, "loss": 0.0, "lr": 1.55164219748411e-05, "epoch": 437.8141592920354, "percentage": 62.39, "elapsed_time": "2:59:21", "remaining_time": "1:48:08", "throughput": 1317.2, "total_tokens": 14175568} {"current_steps": 24960, "total_steps": 40000, "loss": 0.0, "lr": 1.550733902608459e-05, "epoch": 437.9026548672566, "percentage": 62.4, "elapsed_time": "2:59:24", "remaining_time": "1:48:06", "throughput": 1317.18, "total_tokens": 14178144} {"current_steps": 24965, "total_steps": 40000, "loss": 0.0, "lr": 1.549825754121568e-05, "epoch": 437.9911504424779, "percentage": 62.41, "elapsed_time": "2:59:26", "remaining_time": "1:48:03", "throughput": 1317.2, "total_tokens": 14181104} {"current_steps": 24970, "total_steps": 40000, "loss": 0.0, "lr": 1.5489177521634864e-05, "epoch": 438.070796460177, "percentage": 62.42, "elapsed_time": "2:59:28", "remaining_time": "1:48:01", "throughput": 1317.12, "total_tokens": 14183192} {"current_steps": 24975, "total_steps": 40000, "loss": 0.0, "lr": 1.5480098968742402e-05, "epoch": 438.1592920353982, "percentage": 62.44, "elapsed_time": "2:59:30", "remaining_time": "1:47:59", "throughput": 1317.12, "total_tokens": 14185976} {"current_steps": 24980, "total_steps": 40000, "loss": 0.0, "lr": 1.5471021883938304e-05, "epoch": 438.24778761061947, "percentage": 62.45, "elapsed_time": "2:59:32", "remaining_time": "1:47:57", "throughput": 1317.16, "total_tokens": 14189144} {"current_steps": 24985, "total_steps": 40000, "loss": 0.0, "lr": 1.546194626862238e-05, "epoch": 438.3362831858407, "percentage": 62.46, "elapsed_time": "2:59:34", "remaining_time": "1:47:55", "throughput": 1317.22, "total_tokens": 14192472} {"current_steps": 24990, "total_steps": 40000, "loss": 0.0, "lr": 1.5452872124194216e-05, "epoch": 438.42477876106193, "percentage": 62.48, "elapsed_time": "2:59:36", "remaining_time": "1:47:52", "throughput": 1317.25, "total_tokens": 14195560} {"current_steps": 24995, "total_steps": 40000, "loss": 0.0, "lr": 1.5443799452053136e-05, "epoch": 438.5132743362832, "percentage": 62.49, "elapsed_time": "2:59:38", "remaining_time": "1:47:50", "throughput": 1317.3, "total_tokens": 14198760} {"current_steps": 25000, "total_steps": 40000, "loss": 0.0, "lr": 1.543472825359828e-05, "epoch": 438.60176991150445, "percentage": 62.5, "elapsed_time": "2:59:40", "remaining_time": "1:47:48", "throughput": 1317.31, "total_tokens": 14201656} {"current_steps": 25000, "total_steps": 40000, "eval_loss": 0.5152356624603271, "epoch": 438.60176991150445, "percentage": 62.5, "elapsed_time": "2:59:41", "remaining_time": "1:47:49", "throughput": 1317.18, "total_tokens": 14201656} {"current_steps": 25005, "total_steps": 40000, "loss": 0.0, "lr": 1.5425658530228522e-05, "epoch": 438.69026548672565, "percentage": 62.51, "elapsed_time": "2:59:47", "remaining_time": "1:47:48", "throughput": 1316.79, "total_tokens": 14204424} {"current_steps": 25010, "total_steps": 40000, "loss": 0.0, "lr": 1.5416590283342546e-05, "epoch": 438.7787610619469, "percentage": 62.52, "elapsed_time": "2:59:49", "remaining_time": "1:47:46", "throughput": 1316.78, "total_tokens": 14207144} {"current_steps": 25015, "total_steps": 40000, "loss": 0.0, "lr": 1.5407523514338783e-05, "epoch": 438.86725663716817, "percentage": 62.54, "elapsed_time": "2:59:51", "remaining_time": "1:47:44", "throughput": 1316.76, "total_tokens": 14209656} {"current_steps": 25020, "total_steps": 40000, "loss": 0.0, "lr": 1.539845822461543e-05, "epoch": 438.95575221238937, "percentage": 62.55, "elapsed_time": "2:59:53", "remaining_time": "1:47:42", "throughput": 1316.77, "total_tokens": 14212424} {"current_steps": 25025, "total_steps": 40000, "loss": 0.0, "lr": 1.538939441557048e-05, "epoch": 439.0353982300885, "percentage": 62.56, "elapsed_time": "2:59:55", "remaining_time": "1:47:40", "throughput": 1316.72, "total_tokens": 14214888} {"current_steps": 25030, "total_steps": 40000, "loss": 0.0, "lr": 1.5380332088601696e-05, "epoch": 439.12389380530976, "percentage": 62.58, "elapsed_time": "2:59:57", "remaining_time": "1:47:37", "throughput": 1316.73, "total_tokens": 14217768} {"current_steps": 25035, "total_steps": 40000, "loss": 0.0, "lr": 1.537127124510658e-05, "epoch": 439.21238938053096, "percentage": 62.59, "elapsed_time": "2:59:59", "remaining_time": "1:47:35", "throughput": 1316.72, "total_tokens": 14220328} {"current_steps": 25040, "total_steps": 40000, "loss": 0.0, "lr": 1.5362211886482457e-05, "epoch": 439.3008849557522, "percentage": 62.6, "elapsed_time": "3:00:01", "remaining_time": "1:47:33", "throughput": 1316.7, "total_tokens": 14222840} {"current_steps": 25045, "total_steps": 40000, "loss": 0.0, "lr": 1.5353154014126363e-05, "epoch": 439.3893805309734, "percentage": 62.61, "elapsed_time": "3:00:03", "remaining_time": "1:47:31", "throughput": 1316.68, "total_tokens": 14225352} {"current_steps": 25050, "total_steps": 40000, "loss": 0.0, "lr": 1.534409762943515e-05, "epoch": 439.4778761061947, "percentage": 62.62, "elapsed_time": "3:00:06", "remaining_time": "1:47:29", "throughput": 1316.68, "total_tokens": 14228072} {"current_steps": 25055, "total_steps": 40000, "loss": 0.0, "lr": 1.5335042733805438e-05, "epoch": 439.56637168141594, "percentage": 62.64, "elapsed_time": "3:00:08", "remaining_time": "1:47:26", "throughput": 1316.71, "total_tokens": 14231080} {"current_steps": 25060, "total_steps": 40000, "loss": 0.0, "lr": 1.532598932863358e-05, "epoch": 439.65486725663715, "percentage": 62.65, "elapsed_time": "3:00:10", "remaining_time": "1:47:24", "throughput": 1316.74, "total_tokens": 14234200} {"current_steps": 25065, "total_steps": 40000, "loss": 0.0, "lr": 1.531693741531574e-05, "epoch": 439.7433628318584, "percentage": 62.66, "elapsed_time": "3:00:12", "remaining_time": "1:47:22", "throughput": 1316.75, "total_tokens": 14237048} {"current_steps": 25070, "total_steps": 40000, "loss": 0.0, "lr": 1.5307886995247844e-05, "epoch": 439.83185840707966, "percentage": 62.68, "elapsed_time": "3:00:14", "remaining_time": "1:47:20", "throughput": 1316.77, "total_tokens": 14239992} {"current_steps": 25075, "total_steps": 40000, "loss": 0.0, "lr": 1.529883806982557e-05, "epoch": 439.92035398230087, "percentage": 62.69, "elapsed_time": "3:00:16", "remaining_time": "1:47:18", "throughput": 1316.84, "total_tokens": 14243480} {"current_steps": 25080, "total_steps": 40000, "loss": 0.0, "lr": 1.5289790640444376e-05, "epoch": 440.0, "percentage": 62.7, "elapsed_time": "3:00:18", "remaining_time": "1:47:15", "throughput": 1316.84, "total_tokens": 14246096} {"current_steps": 25085, "total_steps": 40000, "loss": 0.0, "lr": 1.5280744708499494e-05, "epoch": 440.08849557522126, "percentage": 62.71, "elapsed_time": "3:00:20", "remaining_time": "1:47:13", "throughput": 1316.85, "total_tokens": 14249216} {"current_steps": 25090, "total_steps": 40000, "loss": 0.0, "lr": 1.527170027538591e-05, "epoch": 440.17699115044246, "percentage": 62.72, "elapsed_time": "3:00:22", "remaining_time": "1:47:11", "throughput": 1316.85, "total_tokens": 14252000} {"current_steps": 25095, "total_steps": 40000, "loss": 0.0, "lr": 1.5262657342498407e-05, "epoch": 440.2654867256637, "percentage": 62.74, "elapsed_time": "3:00:24", "remaining_time": "1:47:09", "throughput": 1316.9, "total_tokens": 14255216} {"current_steps": 25100, "total_steps": 40000, "loss": 0.0, "lr": 1.52536159112315e-05, "epoch": 440.353982300885, "percentage": 62.75, "elapsed_time": "3:00:26", "remaining_time": "1:47:07", "throughput": 1316.89, "total_tokens": 14257904} {"current_steps": 25105, "total_steps": 40000, "loss": 0.0, "lr": 1.5244575982979497e-05, "epoch": 440.4424778761062, "percentage": 62.76, "elapsed_time": "3:00:29", "remaining_time": "1:47:04", "throughput": 1316.88, "total_tokens": 14260496} {"current_steps": 25110, "total_steps": 40000, "loss": 0.0, "lr": 1.5235537559136487e-05, "epoch": 440.53097345132744, "percentage": 62.78, "elapsed_time": "3:00:31", "remaining_time": "1:47:02", "throughput": 1316.92, "total_tokens": 14263680} {"current_steps": 25115, "total_steps": 40000, "loss": 0.0, "lr": 1.5226500641096286e-05, "epoch": 440.6194690265487, "percentage": 62.79, "elapsed_time": "3:00:33", "remaining_time": "1:47:00", "throughput": 1316.91, "total_tokens": 14266272} {"current_steps": 25120, "total_steps": 40000, "loss": 0.0, "lr": 1.5217465230252509e-05, "epoch": 440.7079646017699, "percentage": 62.8, "elapsed_time": "3:00:35", "remaining_time": "1:46:58", "throughput": 1316.89, "total_tokens": 14268784} {"current_steps": 25125, "total_steps": 40000, "loss": 0.0, "lr": 1.5208431327998523e-05, "epoch": 440.79646017699116, "percentage": 62.81, "elapsed_time": "3:00:37", "remaining_time": "1:46:56", "throughput": 1316.93, "total_tokens": 14271952} {"current_steps": 25130, "total_steps": 40000, "loss": 0.0, "lr": 1.5199398935727477e-05, "epoch": 440.88495575221236, "percentage": 62.82, "elapsed_time": "3:00:39", "remaining_time": "1:46:53", "throughput": 1316.92, "total_tokens": 14274608} {"current_steps": 25135, "total_steps": 40000, "loss": 0.0, "lr": 1.5190368054832282e-05, "epoch": 440.9734513274336, "percentage": 62.84, "elapsed_time": "3:00:41", "remaining_time": "1:46:51", "throughput": 1316.94, "total_tokens": 14277520} {"current_steps": 25140, "total_steps": 40000, "loss": 0.0, "lr": 1.5181338686705601e-05, "epoch": 441.05309734513276, "percentage": 62.85, "elapsed_time": "3:00:43", "remaining_time": "1:46:49", "throughput": 1316.91, "total_tokens": 14280120} {"current_steps": 25145, "total_steps": 40000, "loss": 0.0, "lr": 1.5172310832739889e-05, "epoch": 441.14159292035396, "percentage": 62.86, "elapsed_time": "3:00:45", "remaining_time": "1:46:47", "throughput": 1316.94, "total_tokens": 14283176} {"current_steps": 25150, "total_steps": 40000, "loss": 0.0, "lr": 1.5163284494327346e-05, "epoch": 441.2300884955752, "percentage": 62.88, "elapsed_time": "3:00:47", "remaining_time": "1:46:45", "throughput": 1316.93, "total_tokens": 14285800} {"current_steps": 25155, "total_steps": 40000, "loss": 0.0, "lr": 1.5154259672859952e-05, "epoch": 441.3185840707965, "percentage": 62.89, "elapsed_time": "3:00:49", "remaining_time": "1:46:42", "throughput": 1316.94, "total_tokens": 14288680} {"current_steps": 25160, "total_steps": 40000, "loss": 0.0, "lr": 1.5145236369729452e-05, "epoch": 441.4070796460177, "percentage": 62.9, "elapsed_time": "3:00:51", "remaining_time": "1:46:40", "throughput": 1316.94, "total_tokens": 14291416} {"current_steps": 25165, "total_steps": 40000, "loss": 0.0, "lr": 1.5136214586327335e-05, "epoch": 441.49557522123894, "percentage": 62.91, "elapsed_time": "3:00:54", "remaining_time": "1:46:38", "throughput": 1316.97, "total_tokens": 14294424} {"current_steps": 25170, "total_steps": 40000, "loss": 0.0, "lr": 1.5127194324044885e-05, "epoch": 441.5840707964602, "percentage": 62.92, "elapsed_time": "3:00:56", "remaining_time": "1:46:36", "throughput": 1316.96, "total_tokens": 14297048} {"current_steps": 25175, "total_steps": 40000, "loss": 0.0, "lr": 1.5118175584273148e-05, "epoch": 441.6725663716814, "percentage": 62.94, "elapsed_time": "3:00:58", "remaining_time": "1:46:34", "throughput": 1316.95, "total_tokens": 14299672} {"current_steps": 25180, "total_steps": 40000, "loss": 0.0, "lr": 1.5109158368402909e-05, "epoch": 441.76106194690266, "percentage": 62.95, "elapsed_time": "3:01:00", "remaining_time": "1:46:31", "throughput": 1316.96, "total_tokens": 14302568} {"current_steps": 25185, "total_steps": 40000, "loss": 0.0, "lr": 1.5100142677824753e-05, "epoch": 441.8495575221239, "percentage": 62.96, "elapsed_time": "3:01:02", "remaining_time": "1:46:29", "throughput": 1316.98, "total_tokens": 14305448} {"current_steps": 25190, "total_steps": 40000, "loss": 0.0, "lr": 1.509112851392901e-05, "epoch": 441.9380530973451, "percentage": 62.98, "elapsed_time": "3:01:04", "remaining_time": "1:46:27", "throughput": 1317.02, "total_tokens": 14308680} {"current_steps": 25195, "total_steps": 40000, "loss": 0.0, "lr": 1.5082115878105763e-05, "epoch": 442.01769911504425, "percentage": 62.99, "elapsed_time": "3:01:06", "remaining_time": "1:46:25", "throughput": 1317.04, "total_tokens": 14311808} {"current_steps": 25200, "total_steps": 40000, "loss": 0.0, "lr": 1.5073104771744892e-05, "epoch": 442.1061946902655, "percentage": 63.0, "elapsed_time": "3:01:08", "remaining_time": "1:46:23", "throughput": 1317.06, "total_tokens": 14314736} {"current_steps": 25200, "total_steps": 40000, "eval_loss": 0.5149388313293457, "epoch": 442.1061946902655, "percentage": 63.0, "elapsed_time": "3:01:09", "remaining_time": "1:46:23", "throughput": 1316.93, "total_tokens": 14314736} {"current_steps": 25205, "total_steps": 40000, "loss": 0.0, "lr": 1.5064095196236006e-05, "epoch": 442.1946902654867, "percentage": 63.01, "elapsed_time": "3:01:13", "remaining_time": "1:46:22", "throughput": 1316.69, "total_tokens": 14317232} {"current_steps": 25210, "total_steps": 40000, "loss": 0.0, "lr": 1.50550871529685e-05, "epoch": 442.283185840708, "percentage": 63.02, "elapsed_time": "3:01:15", "remaining_time": "1:46:20", "throughput": 1316.68, "total_tokens": 14319824} {"current_steps": 25215, "total_steps": 40000, "loss": 0.0, "lr": 1.5046080643331546e-05, "epoch": 442.37168141592923, "percentage": 63.04, "elapsed_time": "3:01:17", "remaining_time": "1:46:18", "throughput": 1316.77, "total_tokens": 14323552} {"current_steps": 25220, "total_steps": 40000, "loss": 0.0, "lr": 1.5037075668714028e-05, "epoch": 442.46017699115043, "percentage": 63.05, "elapsed_time": "3:01:19", "remaining_time": "1:46:16", "throughput": 1316.77, "total_tokens": 14326240} {"current_steps": 25225, "total_steps": 40000, "loss": 0.0, "lr": 1.5028072230504656e-05, "epoch": 442.5486725663717, "percentage": 63.06, "elapsed_time": "3:01:21", "remaining_time": "1:46:13", "throughput": 1316.85, "total_tokens": 14329824} {"current_steps": 25230, "total_steps": 40000, "loss": 0.0, "lr": 1.5019070330091861e-05, "epoch": 442.6371681415929, "percentage": 63.08, "elapsed_time": "3:01:23", "remaining_time": "1:46:11", "throughput": 1316.87, "total_tokens": 14332720} {"current_steps": 25235, "total_steps": 40000, "loss": 0.0, "lr": 1.5010069968863843e-05, "epoch": 442.72566371681415, "percentage": 63.09, "elapsed_time": "3:01:26", "remaining_time": "1:46:09", "throughput": 1316.84, "total_tokens": 14335168} {"current_steps": 25240, "total_steps": 40000, "loss": 0.0, "lr": 1.5001071148208584e-05, "epoch": 442.8141592920354, "percentage": 63.1, "elapsed_time": "3:01:28", "remaining_time": "1:46:07", "throughput": 1316.84, "total_tokens": 14337936} {"current_steps": 25245, "total_steps": 40000, "loss": 0.0, "lr": 1.49920738695138e-05, "epoch": 442.9026548672566, "percentage": 63.11, "elapsed_time": "3:01:30", "remaining_time": "1:46:05", "throughput": 1316.81, "total_tokens": 14340288} {"current_steps": 25250, "total_steps": 40000, "loss": 0.0, "lr": 1.4983078134166995e-05, "epoch": 442.9911504424779, "percentage": 63.12, "elapsed_time": "3:01:32", "remaining_time": "1:46:02", "throughput": 1316.83, "total_tokens": 14343200} {"current_steps": 25255, "total_steps": 40000, "loss": 0.0, "lr": 1.4974083943555428e-05, "epoch": 443.070796460177, "percentage": 63.14, "elapsed_time": "3:01:34", "remaining_time": "1:46:00", "throughput": 1316.76, "total_tokens": 14345424} {"current_steps": 25260, "total_steps": 40000, "loss": 0.0, "lr": 1.496509129906611e-05, "epoch": 443.1592920353982, "percentage": 63.15, "elapsed_time": "3:01:36", "remaining_time": "1:45:58", "throughput": 1316.75, "total_tokens": 14348080} {"current_steps": 25265, "total_steps": 40000, "loss": 0.0, "lr": 1.4956100202085809e-05, "epoch": 443.24778761061947, "percentage": 63.16, "elapsed_time": "3:01:38", "remaining_time": "1:45:56", "throughput": 1316.78, "total_tokens": 14351088} {"current_steps": 25270, "total_steps": 40000, "loss": 0.0, "lr": 1.4947110654001093e-05, "epoch": 443.3362831858407, "percentage": 63.18, "elapsed_time": "3:01:40", "remaining_time": "1:45:54", "throughput": 1316.82, "total_tokens": 14354304} {"current_steps": 25275, "total_steps": 40000, "loss": 0.0, "lr": 1.4938122656198234e-05, "epoch": 443.42477876106193, "percentage": 63.19, "elapsed_time": "3:01:42", "remaining_time": "1:45:51", "throughput": 1316.82, "total_tokens": 14356976} {"current_steps": 25280, "total_steps": 40000, "loss": 0.0, "lr": 1.4929136210063316e-05, "epoch": 443.5132743362832, "percentage": 63.2, "elapsed_time": "3:01:44", "remaining_time": "1:45:49", "throughput": 1316.84, "total_tokens": 14359952} {"current_steps": 25285, "total_steps": 40000, "loss": 0.0, "lr": 1.4920151316982146e-05, "epoch": 443.60176991150445, "percentage": 63.21, "elapsed_time": "3:01:46", "remaining_time": "1:45:47", "throughput": 1316.87, "total_tokens": 14362992} {"current_steps": 25290, "total_steps": 40000, "loss": 0.0, "lr": 1.4911167978340312e-05, "epoch": 443.69026548672565, "percentage": 63.22, "elapsed_time": "3:01:49", "remaining_time": "1:45:45", "throughput": 1316.86, "total_tokens": 14365696} {"current_steps": 25295, "total_steps": 40000, "loss": 0.0, "lr": 1.4902186195523166e-05, "epoch": 443.7787610619469, "percentage": 63.24, "elapsed_time": "3:01:51", "remaining_time": "1:45:43", "throughput": 1316.9, "total_tokens": 14368800} {"current_steps": 25300, "total_steps": 40000, "loss": 0.0, "lr": 1.4893205969915805e-05, "epoch": 443.86725663716817, "percentage": 63.25, "elapsed_time": "3:01:53", "remaining_time": "1:45:40", "throughput": 1316.89, "total_tokens": 14371440} {"current_steps": 25305, "total_steps": 40000, "loss": 0.0, "lr": 1.4884227302903086e-05, "epoch": 443.95575221238937, "percentage": 63.26, "elapsed_time": "3:01:55", "remaining_time": "1:45:38", "throughput": 1316.96, "total_tokens": 14374960} {"current_steps": 25310, "total_steps": 40000, "loss": 0.0, "lr": 1.4875250195869653e-05, "epoch": 444.0353982300885, "percentage": 63.28, "elapsed_time": "3:01:57", "remaining_time": "1:45:36", "throughput": 1316.89, "total_tokens": 14377168} {"current_steps": 25315, "total_steps": 40000, "loss": 0.0, "lr": 1.4866274650199862e-05, "epoch": 444.12389380530976, "percentage": 63.29, "elapsed_time": "3:01:59", "remaining_time": "1:45:34", "throughput": 1316.92, "total_tokens": 14380288} {"current_steps": 25320, "total_steps": 40000, "loss": 0.0, "lr": 1.485730066727788e-05, "epoch": 444.21238938053096, "percentage": 63.3, "elapsed_time": "3:02:01", "remaining_time": "1:45:32", "throughput": 1316.89, "total_tokens": 14382640} {"current_steps": 25325, "total_steps": 40000, "loss": 0.0, "lr": 1.4848328248487586e-05, "epoch": 444.3008849557522, "percentage": 63.31, "elapsed_time": "3:02:03", "remaining_time": "1:45:29", "throughput": 1316.9, "total_tokens": 14385440} {"current_steps": 25330, "total_steps": 40000, "loss": 0.0, "lr": 1.4839357395212656e-05, "epoch": 444.3893805309734, "percentage": 63.32, "elapsed_time": "3:02:05", "remaining_time": "1:45:27", "throughput": 1316.91, "total_tokens": 14388304} {"current_steps": 25335, "total_steps": 40000, "loss": 0.0, "lr": 1.4830388108836502e-05, "epoch": 444.4778761061947, "percentage": 63.34, "elapsed_time": "3:02:07", "remaining_time": "1:45:25", "throughput": 1316.94, "total_tokens": 14391376} {"current_steps": 25340, "total_steps": 40000, "loss": 0.0, "lr": 1.4821420390742299e-05, "epoch": 444.56637168141594, "percentage": 63.35, "elapsed_time": "3:02:09", "remaining_time": "1:45:23", "throughput": 1316.96, "total_tokens": 14394336} {"current_steps": 25345, "total_steps": 40000, "loss": 0.0, "lr": 1.4812454242312979e-05, "epoch": 444.65486725663715, "percentage": 63.36, "elapsed_time": "3:02:12", "remaining_time": "1:45:21", "throughput": 1316.95, "total_tokens": 14396880} {"current_steps": 25350, "total_steps": 40000, "loss": 0.0, "lr": 1.4803489664931253e-05, "epoch": 444.7433628318584, "percentage": 63.38, "elapsed_time": "3:02:14", "remaining_time": "1:45:18", "throughput": 1316.94, "total_tokens": 14399520} {"current_steps": 25355, "total_steps": 40000, "loss": 0.0, "lr": 1.4794526659979544e-05, "epoch": 444.83185840707966, "percentage": 63.39, "elapsed_time": "3:02:16", "remaining_time": "1:45:16", "throughput": 1316.94, "total_tokens": 14402304} {"current_steps": 25360, "total_steps": 40000, "loss": 0.0, "lr": 1.4785565228840086e-05, "epoch": 444.92035398230087, "percentage": 63.4, "elapsed_time": "3:02:18", "remaining_time": "1:45:14", "throughput": 1316.96, "total_tokens": 14405232} {"current_steps": 25365, "total_steps": 40000, "loss": 0.0, "lr": 1.4776605372894819e-05, "epoch": 445.0, "percentage": 63.41, "elapsed_time": "3:02:20", "remaining_time": "1:45:12", "throughput": 1316.93, "total_tokens": 14407480} {"current_steps": 25370, "total_steps": 40000, "loss": 0.0, "lr": 1.4767647093525488e-05, "epoch": 445.08849557522126, "percentage": 63.42, "elapsed_time": "3:02:22", "remaining_time": "1:45:10", "throughput": 1316.93, "total_tokens": 14410616} {"current_steps": 25375, "total_steps": 40000, "loss": 0.0, "lr": 1.4758690392113566e-05, "epoch": 445.17699115044246, "percentage": 63.44, "elapsed_time": "3:02:24", "remaining_time": "1:45:07", "throughput": 1316.92, "total_tokens": 14413176} {"current_steps": 25380, "total_steps": 40000, "loss": 0.0, "lr": 1.4749735270040276e-05, "epoch": 445.2654867256637, "percentage": 63.45, "elapsed_time": "3:02:26", "remaining_time": "1:45:05", "throughput": 1316.94, "total_tokens": 14416200} {"current_steps": 25385, "total_steps": 40000, "loss": 0.0, "lr": 1.4740781728686623e-05, "epoch": 445.353982300885, "percentage": 63.46, "elapsed_time": "3:02:28", "remaining_time": "1:45:03", "throughput": 1316.99, "total_tokens": 14419464} {"current_steps": 25390, "total_steps": 40000, "loss": 0.0, "lr": 1.4731829769433358e-05, "epoch": 445.4424778761062, "percentage": 63.48, "elapsed_time": "3:02:30", "remaining_time": "1:45:01", "throughput": 1316.97, "total_tokens": 14421992} {"current_steps": 25395, "total_steps": 40000, "loss": 0.0, "lr": 1.4722879393660976e-05, "epoch": 445.53097345132744, "percentage": 63.49, "elapsed_time": "3:02:32", "remaining_time": "1:44:59", "throughput": 1317.02, "total_tokens": 14425256} {"current_steps": 25400, "total_steps": 40000, "loss": 0.0, "lr": 1.4713930602749748e-05, "epoch": 445.6194690265487, "percentage": 63.5, "elapsed_time": "3:02:35", "remaining_time": "1:44:56", "throughput": 1317.03, "total_tokens": 14428104} {"current_steps": 25400, "total_steps": 40000, "eval_loss": 0.5317846536636353, "epoch": 445.6194690265487, "percentage": 63.5, "elapsed_time": "3:02:36", "remaining_time": "1:44:57", "throughput": 1316.9, "total_tokens": 14428104} {"current_steps": 25405, "total_steps": 40000, "loss": 0.0, "lr": 1.470498339807968e-05, "epoch": 445.7079646017699, "percentage": 63.51, "elapsed_time": "3:02:39", "remaining_time": "1:44:56", "throughput": 1316.67, "total_tokens": 14430552} {"current_steps": 25410, "total_steps": 40000, "loss": 0.0, "lr": 1.4696037781030542e-05, "epoch": 445.79646017699116, "percentage": 63.52, "elapsed_time": "3:02:41", "remaining_time": "1:44:54", "throughput": 1316.69, "total_tokens": 14433528} {"current_steps": 25415, "total_steps": 40000, "loss": 0.0, "lr": 1.4687093752981876e-05, "epoch": 445.88495575221236, "percentage": 63.54, "elapsed_time": "3:02:44", "remaining_time": "1:44:51", "throughput": 1316.68, "total_tokens": 14436056} {"current_steps": 25420, "total_steps": 40000, "loss": 0.0, "lr": 1.4678151315312943e-05, "epoch": 445.9734513274336, "percentage": 63.55, "elapsed_time": "3:02:46", "remaining_time": "1:44:49", "throughput": 1316.71, "total_tokens": 14439160} {"current_steps": 25425, "total_steps": 40000, "loss": 0.0, "lr": 1.4669210469402789e-05, "epoch": 446.05309734513276, "percentage": 63.56, "elapsed_time": "3:02:48", "remaining_time": "1:44:47", "throughput": 1316.67, "total_tokens": 14441688} {"current_steps": 25430, "total_steps": 40000, "loss": 0.0, "lr": 1.4660271216630218e-05, "epoch": 446.14159292035396, "percentage": 63.58, "elapsed_time": "3:02:50", "remaining_time": "1:44:45", "throughput": 1316.68, "total_tokens": 14444552} {"current_steps": 25435, "total_steps": 40000, "loss": 0.0, "lr": 1.4651333558373748e-05, "epoch": 446.2300884955752, "percentage": 63.59, "elapsed_time": "3:02:52", "remaining_time": "1:44:43", "throughput": 1316.67, "total_tokens": 14447160} {"current_steps": 25440, "total_steps": 40000, "loss": 0.0, "lr": 1.4642397496011707e-05, "epoch": 446.3185840707965, "percentage": 63.6, "elapsed_time": "3:02:54", "remaining_time": "1:44:41", "throughput": 1316.69, "total_tokens": 14450104} {"current_steps": 25445, "total_steps": 40000, "loss": 0.0, "lr": 1.4633463030922129e-05, "epoch": 446.4070796460177, "percentage": 63.61, "elapsed_time": "3:02:56", "remaining_time": "1:44:38", "throughput": 1316.72, "total_tokens": 14453128} {"current_steps": 25450, "total_steps": 40000, "loss": 0.0, "lr": 1.462453016448282e-05, "epoch": 446.49557522123894, "percentage": 63.62, "elapsed_time": "3:02:58", "remaining_time": "1:44:36", "throughput": 1316.73, "total_tokens": 14456008} {"current_steps": 25455, "total_steps": 40000, "loss": 0.0, "lr": 1.4615598898071354e-05, "epoch": 446.5840707964602, "percentage": 63.64, "elapsed_time": "3:03:00", "remaining_time": "1:44:34", "throughput": 1316.77, "total_tokens": 14459208} {"current_steps": 25460, "total_steps": 40000, "loss": 0.0, "lr": 1.4606669233065026e-05, "epoch": 446.6725663716814, "percentage": 63.65, "elapsed_time": "3:03:02", "remaining_time": "1:44:32", "throughput": 1316.76, "total_tokens": 14461800} {"current_steps": 25465, "total_steps": 40000, "loss": 0.0, "lr": 1.4597741170840914e-05, "epoch": 446.76106194690266, "percentage": 63.66, "elapsed_time": "3:03:04", "remaining_time": "1:44:30", "throughput": 1316.78, "total_tokens": 14464744} {"current_steps": 25470, "total_steps": 40000, "loss": 0.0, "lr": 1.4588814712775853e-05, "epoch": 446.8495575221239, "percentage": 63.68, "elapsed_time": "3:03:07", "remaining_time": "1:44:27", "throughput": 1316.8, "total_tokens": 14467672} {"current_steps": 25475, "total_steps": 40000, "loss": 0.0, "lr": 1.4579889860246382e-05, "epoch": 446.9380530973451, "percentage": 63.69, "elapsed_time": "3:03:09", "remaining_time": "1:44:25", "throughput": 1316.8, "total_tokens": 14470456} {"current_steps": 25480, "total_steps": 40000, "loss": 0.0, "lr": 1.457096661462885e-05, "epoch": 447.01769911504425, "percentage": 63.7, "elapsed_time": "3:03:11", "remaining_time": "1:44:23", "throughput": 1316.75, "total_tokens": 14472848} {"current_steps": 25485, "total_steps": 40000, "loss": 0.0, "lr": 1.4562044977299322e-05, "epoch": 447.1061946902655, "percentage": 63.71, "elapsed_time": "3:03:13", "remaining_time": "1:44:21", "throughput": 1316.75, "total_tokens": 14475520} {"current_steps": 25490, "total_steps": 40000, "loss": 0.0, "lr": 1.4553124949633623e-05, "epoch": 447.1946902654867, "percentage": 63.73, "elapsed_time": "3:03:15", "remaining_time": "1:44:19", "throughput": 1316.74, "total_tokens": 14478144} {"current_steps": 25495, "total_steps": 40000, "loss": 0.0, "lr": 1.4544206533007354e-05, "epoch": 447.283185840708, "percentage": 63.74, "elapsed_time": "3:03:17", "remaining_time": "1:44:16", "throughput": 1316.77, "total_tokens": 14481280} {"current_steps": 25500, "total_steps": 40000, "loss": 0.0, "lr": 1.4535289728795821e-05, "epoch": 447.37168141592923, "percentage": 63.75, "elapsed_time": "3:03:19", "remaining_time": "1:44:14", "throughput": 1316.82, "total_tokens": 14484608} {"current_steps": 25505, "total_steps": 40000, "loss": 0.0, "lr": 1.4526374538374132e-05, "epoch": 447.46017699115043, "percentage": 63.76, "elapsed_time": "3:03:21", "remaining_time": "1:44:12", "throughput": 1316.82, "total_tokens": 14487248} {"current_steps": 25510, "total_steps": 40000, "loss": 0.0, "lr": 1.4517460963117097e-05, "epoch": 447.5486725663717, "percentage": 63.78, "elapsed_time": "3:03:23", "remaining_time": "1:44:10", "throughput": 1316.8, "total_tokens": 14489776} {"current_steps": 25515, "total_steps": 40000, "loss": 0.0, "lr": 1.4508549004399314e-05, "epoch": 447.6371681415929, "percentage": 63.79, "elapsed_time": "3:03:25", "remaining_time": "1:44:08", "throughput": 1316.82, "total_tokens": 14492768} {"current_steps": 25520, "total_steps": 40000, "loss": 0.0, "lr": 1.449963866359513e-05, "epoch": 447.72566371681415, "percentage": 63.8, "elapsed_time": "3:03:27", "remaining_time": "1:44:05", "throughput": 1316.84, "total_tokens": 14495664} {"current_steps": 25525, "total_steps": 40000, "loss": 0.0, "lr": 1.4490729942078607e-05, "epoch": 447.8141592920354, "percentage": 63.81, "elapsed_time": "3:03:30", "remaining_time": "1:44:03", "throughput": 1316.85, "total_tokens": 14498544} {"current_steps": 25530, "total_steps": 40000, "loss": 0.0, "lr": 1.4481822841223608e-05, "epoch": 447.9026548672566, "percentage": 63.82, "elapsed_time": "3:03:32", "remaining_time": "1:44:01", "throughput": 1316.87, "total_tokens": 14501520} {"current_steps": 25535, "total_steps": 40000, "loss": 0.0, "lr": 1.4472917362403704e-05, "epoch": 447.9911504424779, "percentage": 63.84, "elapsed_time": "3:03:34", "remaining_time": "1:43:59", "throughput": 1316.91, "total_tokens": 14504656} {"current_steps": 25540, "total_steps": 40000, "loss": 0.0, "lr": 1.4464013506992224e-05, "epoch": 448.070796460177, "percentage": 63.85, "elapsed_time": "3:03:36", "remaining_time": "1:43:57", "throughput": 1316.85, "total_tokens": 14506960} {"current_steps": 25545, "total_steps": 40000, "loss": 0.0, "lr": 1.4455111276362277e-05, "epoch": 448.1592920353982, "percentage": 63.86, "elapsed_time": "3:03:38", "remaining_time": "1:43:54", "throughput": 1316.94, "total_tokens": 14510720} {"current_steps": 25550, "total_steps": 40000, "loss": 0.0, "lr": 1.4446210671886676e-05, "epoch": 448.24778761061947, "percentage": 63.88, "elapsed_time": "3:03:40", "remaining_time": "1:43:52", "throughput": 1316.95, "total_tokens": 14513552} {"current_steps": 25555, "total_steps": 40000, "loss": 0.0, "lr": 1.4437311694938015e-05, "epoch": 448.3362831858407, "percentage": 63.89, "elapsed_time": "3:03:42", "remaining_time": "1:43:50", "throughput": 1316.98, "total_tokens": 14516592} {"current_steps": 25560, "total_steps": 40000, "loss": 0.0, "lr": 1.442841434688864e-05, "epoch": 448.42477876106193, "percentage": 63.9, "elapsed_time": "3:03:44", "remaining_time": "1:43:48", "throughput": 1316.97, "total_tokens": 14519216} {"current_steps": 25565, "total_steps": 40000, "loss": 0.0, "lr": 1.4419518629110615e-05, "epoch": 448.5132743362832, "percentage": 63.91, "elapsed_time": "3:03:46", "remaining_time": "1:43:46", "throughput": 1317.03, "total_tokens": 14522608} {"current_steps": 25570, "total_steps": 40000, "loss": 0.0, "lr": 1.4410624542975778e-05, "epoch": 448.60176991150445, "percentage": 63.92, "elapsed_time": "3:03:48", "remaining_time": "1:43:43", "throughput": 1316.99, "total_tokens": 14524928} {"current_steps": 25575, "total_steps": 40000, "loss": 0.0, "lr": 1.4401732089855724e-05, "epoch": 448.69026548672565, "percentage": 63.94, "elapsed_time": "3:03:50", "remaining_time": "1:43:41", "throughput": 1316.99, "total_tokens": 14527616} {"current_steps": 25580, "total_steps": 40000, "loss": 0.0, "lr": 1.4392841271121754e-05, "epoch": 448.7787610619469, "percentage": 63.95, "elapsed_time": "3:03:52", "remaining_time": "1:43:39", "throughput": 1317.02, "total_tokens": 14530688} {"current_steps": 25585, "total_steps": 40000, "loss": 0.0, "lr": 1.438395208814497e-05, "epoch": 448.86725663716817, "percentage": 63.96, "elapsed_time": "3:03:55", "remaining_time": "1:43:37", "throughput": 1317.0, "total_tokens": 14533152} {"current_steps": 25590, "total_steps": 40000, "loss": 0.0, "lr": 1.4375064542296174e-05, "epoch": 448.95575221238937, "percentage": 63.98, "elapsed_time": "3:03:57", "remaining_time": "1:43:35", "throughput": 1317.01, "total_tokens": 14535984} {"current_steps": 25595, "total_steps": 40000, "loss": 0.0, "lr": 1.4366178634945946e-05, "epoch": 449.0353982300885, "percentage": 63.99, "elapsed_time": "3:03:59", "remaining_time": "1:43:33", "throughput": 1316.92, "total_tokens": 14537984} {"current_steps": 25600, "total_steps": 40000, "loss": 0.0, "lr": 1.4357294367464616e-05, "epoch": 449.12389380530976, "percentage": 64.0, "elapsed_time": "3:04:01", "remaining_time": "1:43:30", "throughput": 1316.96, "total_tokens": 14541136} {"current_steps": 25600, "total_steps": 40000, "eval_loss": 0.48938480019569397, "epoch": 449.12389380530976, "percentage": 64.0, "elapsed_time": "3:04:02", "remaining_time": "1:43:31", "throughput": 1316.83, "total_tokens": 14541136} {"current_steps": 25605, "total_steps": 40000, "loss": 0.0, "lr": 1.434841174122224e-05, "epoch": 449.21238938053096, "percentage": 64.01, "elapsed_time": "3:04:06", "remaining_time": "1:43:30", "throughput": 1316.6, "total_tokens": 14543632} {"current_steps": 25610, "total_steps": 40000, "loss": 0.0, "lr": 1.4339530757588615e-05, "epoch": 449.3008849557522, "percentage": 64.03, "elapsed_time": "3:04:08", "remaining_time": "1:43:28", "throughput": 1316.58, "total_tokens": 14546160} {"current_steps": 25615, "total_steps": 40000, "loss": 0.0, "lr": 1.433065141793333e-05, "epoch": 449.3893805309734, "percentage": 64.04, "elapsed_time": "3:04:10", "remaining_time": "1:43:25", "throughput": 1316.58, "total_tokens": 14548832} {"current_steps": 25620, "total_steps": 40000, "loss": 0.0, "lr": 1.4321773723625665e-05, "epoch": 449.4778761061947, "percentage": 64.05, "elapsed_time": "3:04:12", "remaining_time": "1:43:23", "throughput": 1316.6, "total_tokens": 14551792} {"current_steps": 25625, "total_steps": 40000, "loss": 0.0, "lr": 1.4312897676034693e-05, "epoch": 449.56637168141594, "percentage": 64.06, "elapsed_time": "3:04:14", "remaining_time": "1:43:21", "throughput": 1316.61, "total_tokens": 14554608} {"current_steps": 25630, "total_steps": 40000, "loss": 0.0, "lr": 1.4304023276529188e-05, "epoch": 449.65486725663715, "percentage": 64.08, "elapsed_time": "3:04:16", "remaining_time": "1:43:19", "throughput": 1316.68, "total_tokens": 14558080} {"current_steps": 25635, "total_steps": 40000, "loss": 0.0, "lr": 1.4295150526477712e-05, "epoch": 449.7433628318584, "percentage": 64.09, "elapsed_time": "3:04:18", "remaining_time": "1:43:16", "throughput": 1316.7, "total_tokens": 14561024} {"current_steps": 25640, "total_steps": 40000, "loss": 0.0, "lr": 1.4286279427248562e-05, "epoch": 449.83185840707966, "percentage": 64.1, "elapsed_time": "3:04:20", "remaining_time": "1:43:14", "throughput": 1316.74, "total_tokens": 14564240} {"current_steps": 25645, "total_steps": 40000, "loss": 0.0, "lr": 1.4277409980209747e-05, "epoch": 449.92035398230087, "percentage": 64.11, "elapsed_time": "3:04:22", "remaining_time": "1:43:12", "throughput": 1316.75, "total_tokens": 14567040} {"current_steps": 25650, "total_steps": 40000, "loss": 0.0, "lr": 1.4268542186729061e-05, "epoch": 450.0, "percentage": 64.12, "elapsed_time": "3:04:24", "remaining_time": "1:43:10", "throughput": 1316.74, "total_tokens": 14569608} {"current_steps": 25655, "total_steps": 40000, "loss": 0.0, "lr": 1.4259676048174043e-05, "epoch": 450.08849557522126, "percentage": 64.14, "elapsed_time": "3:04:27", "remaining_time": "1:43:08", "throughput": 1316.74, "total_tokens": 14572744} {"current_steps": 25660, "total_steps": 40000, "loss": 0.0, "lr": 1.4250811565911937e-05, "epoch": 450.17699115044246, "percentage": 64.15, "elapsed_time": "3:04:29", "remaining_time": "1:43:06", "throughput": 1316.79, "total_tokens": 14575960} {"current_steps": 25665, "total_steps": 40000, "loss": 0.0, "lr": 1.4241948741309782e-05, "epoch": 450.2654867256637, "percentage": 64.16, "elapsed_time": "3:04:31", "remaining_time": "1:43:03", "throughput": 1316.8, "total_tokens": 14578824} {"current_steps": 25670, "total_steps": 40000, "loss": 0.0, "lr": 1.4233087575734317e-05, "epoch": 450.353982300885, "percentage": 64.18, "elapsed_time": "3:04:33", "remaining_time": "1:43:01", "throughput": 1316.82, "total_tokens": 14581752} {"current_steps": 25675, "total_steps": 40000, "loss": 0.0, "lr": 1.422422807055206e-05, "epoch": 450.4424778761062, "percentage": 64.19, "elapsed_time": "3:04:35", "remaining_time": "1:42:59", "throughput": 1316.82, "total_tokens": 14584520} {"current_steps": 25680, "total_steps": 40000, "loss": 0.0, "lr": 1.4215370227129243e-05, "epoch": 450.53097345132744, "percentage": 64.2, "elapsed_time": "3:04:37", "remaining_time": "1:42:57", "throughput": 1316.83, "total_tokens": 14587320} {"current_steps": 25685, "total_steps": 40000, "loss": 0.0, "lr": 1.4206514046831876e-05, "epoch": 450.6194690265487, "percentage": 64.21, "elapsed_time": "3:04:39", "remaining_time": "1:42:55", "throughput": 1316.84, "total_tokens": 14590216} {"current_steps": 25690, "total_steps": 40000, "loss": 0.0, "lr": 1.419765953102567e-05, "epoch": 450.7079646017699, "percentage": 64.22, "elapsed_time": "3:04:41", "remaining_time": "1:42:52", "throughput": 1316.83, "total_tokens": 14592824} {"current_steps": 25695, "total_steps": 40000, "loss": 0.0, "lr": 1.4188806681076125e-05, "epoch": 450.79646017699116, "percentage": 64.24, "elapsed_time": "3:04:43", "remaining_time": "1:42:50", "throughput": 1316.82, "total_tokens": 14595464} {"current_steps": 25700, "total_steps": 40000, "loss": 0.0, "lr": 1.4179955498348443e-05, "epoch": 450.88495575221236, "percentage": 64.25, "elapsed_time": "3:04:45", "remaining_time": "1:42:48", "throughput": 1316.87, "total_tokens": 14598680} {"current_steps": 25705, "total_steps": 40000, "loss": 0.0, "lr": 1.4171105984207605e-05, "epoch": 450.9734513274336, "percentage": 64.26, "elapsed_time": "3:04:47", "remaining_time": "1:42:46", "throughput": 1316.87, "total_tokens": 14601352} {"current_steps": 25710, "total_steps": 40000, "loss": 0.0, "lr": 1.4162258140018304e-05, "epoch": 451.05309734513276, "percentage": 64.28, "elapsed_time": "3:04:50", "remaining_time": "1:42:44", "throughput": 1316.8, "total_tokens": 14603616} {"current_steps": 25715, "total_steps": 40000, "loss": 0.0, "lr": 1.4153411967144986e-05, "epoch": 451.14159292035396, "percentage": 64.29, "elapsed_time": "3:04:52", "remaining_time": "1:42:41", "throughput": 1316.79, "total_tokens": 14606192} {"current_steps": 25720, "total_steps": 40000, "loss": 0.0, "lr": 1.4144567466951864e-05, "epoch": 451.2300884955752, "percentage": 64.3, "elapsed_time": "3:04:54", "remaining_time": "1:42:39", "throughput": 1316.76, "total_tokens": 14608576} {"current_steps": 25725, "total_steps": 40000, "loss": 0.0, "lr": 1.4135724640802844e-05, "epoch": 451.3185840707965, "percentage": 64.31, "elapsed_time": "3:04:56", "remaining_time": "1:42:37", "throughput": 1316.8, "total_tokens": 14611856} {"current_steps": 25730, "total_steps": 40000, "loss": 0.0, "lr": 1.4126883490061615e-05, "epoch": 451.4070796460177, "percentage": 64.33, "elapsed_time": "3:04:58", "remaining_time": "1:42:35", "throughput": 1316.8, "total_tokens": 14614592} {"current_steps": 25735, "total_steps": 40000, "loss": 0.0, "lr": 1.4118044016091603e-05, "epoch": 451.49557522123894, "percentage": 64.34, "elapsed_time": "3:05:00", "remaining_time": "1:42:33", "throughput": 1316.87, "total_tokens": 14618064} {"current_steps": 25740, "total_steps": 40000, "loss": 0.0, "lr": 1.410920622025594e-05, "epoch": 451.5840707964602, "percentage": 64.35, "elapsed_time": "3:05:02", "remaining_time": "1:42:30", "throughput": 1316.87, "total_tokens": 14620832} {"current_steps": 25745, "total_steps": 40000, "loss": 0.0, "lr": 1.4100370103917554e-05, "epoch": 451.6725663716814, "percentage": 64.36, "elapsed_time": "3:05:04", "remaining_time": "1:42:28", "throughput": 1316.9, "total_tokens": 14623856} {"current_steps": 25750, "total_steps": 40000, "loss": 0.0, "lr": 1.409153566843907e-05, "epoch": 451.76106194690266, "percentage": 64.38, "elapsed_time": "3:05:06", "remaining_time": "1:42:26", "throughput": 1316.9, "total_tokens": 14626592} {"current_steps": 25755, "total_steps": 40000, "loss": 0.0, "lr": 1.408270291518286e-05, "epoch": 451.8495575221239, "percentage": 64.39, "elapsed_time": "3:05:08", "remaining_time": "1:42:24", "throughput": 1316.93, "total_tokens": 14629616} {"current_steps": 25760, "total_steps": 40000, "loss": 0.0, "lr": 1.407387184551107e-05, "epoch": 451.9380530973451, "percentage": 64.4, "elapsed_time": "3:05:10", "remaining_time": "1:42:22", "throughput": 1316.92, "total_tokens": 14632288} {"current_steps": 25765, "total_steps": 40000, "loss": 0.0, "lr": 1.4065042460785532e-05, "epoch": 452.01769911504425, "percentage": 64.41, "elapsed_time": "3:05:13", "remaining_time": "1:42:19", "throughput": 1316.91, "total_tokens": 14635040} {"current_steps": 25770, "total_steps": 40000, "loss": 0.0, "lr": 1.405621476236787e-05, "epoch": 452.1061946902655, "percentage": 64.42, "elapsed_time": "3:05:15", "remaining_time": "1:42:17", "throughput": 1316.93, "total_tokens": 14638080} {"current_steps": 25775, "total_steps": 40000, "loss": 0.0, "lr": 1.4047388751619423e-05, "epoch": 452.1946902654867, "percentage": 64.44, "elapsed_time": "3:05:17", "remaining_time": "1:42:15", "throughput": 1316.93, "total_tokens": 14640768} {"current_steps": 25780, "total_steps": 40000, "loss": 0.0, "lr": 1.4038564429901264e-05, "epoch": 452.283185840708, "percentage": 64.45, "elapsed_time": "3:05:19", "remaining_time": "1:42:13", "throughput": 1316.96, "total_tokens": 14643808} {"current_steps": 25785, "total_steps": 40000, "loss": 0.0, "lr": 1.4029741798574227e-05, "epoch": 452.37168141592923, "percentage": 64.46, "elapsed_time": "3:05:21", "remaining_time": "1:42:11", "throughput": 1316.97, "total_tokens": 14646704} {"current_steps": 25790, "total_steps": 40000, "loss": 0.0, "lr": 1.402092085899886e-05, "epoch": 452.46017699115043, "percentage": 64.48, "elapsed_time": "3:05:23", "remaining_time": "1:42:08", "throughput": 1317.01, "total_tokens": 14649808} {"current_steps": 25795, "total_steps": 40000, "loss": 0.0, "lr": 1.4012101612535464e-05, "epoch": 452.5486725663717, "percentage": 64.49, "elapsed_time": "3:05:25", "remaining_time": "1:42:06", "throughput": 1316.99, "total_tokens": 14652400} {"current_steps": 25800, "total_steps": 40000, "loss": 0.0, "lr": 1.4003284060544092e-05, "epoch": 452.6371681415929, "percentage": 64.5, "elapsed_time": "3:05:27", "remaining_time": "1:42:04", "throughput": 1317.04, "total_tokens": 14655696} {"current_steps": 25800, "total_steps": 40000, "eval_loss": 0.516354501247406, "epoch": 452.6371681415929, "percentage": 64.5, "elapsed_time": "3:05:28", "remaining_time": "1:42:05", "throughput": 1316.92, "total_tokens": 14655696} {"current_steps": 25805, "total_steps": 40000, "loss": 0.0, "lr": 1.3994468204384504e-05, "epoch": 452.72566371681415, "percentage": 64.51, "elapsed_time": "3:05:32", "remaining_time": "1:42:03", "throughput": 1316.72, "total_tokens": 14658528} {"current_steps": 25810, "total_steps": 40000, "loss": 0.0, "lr": 1.398565404541622e-05, "epoch": 452.8141592920354, "percentage": 64.53, "elapsed_time": "3:05:34", "remaining_time": "1:42:01", "throughput": 1316.77, "total_tokens": 14661792} {"current_steps": 25815, "total_steps": 40000, "loss": 0.0, "lr": 1.3976841584998513e-05, "epoch": 452.9026548672566, "percentage": 64.54, "elapsed_time": "3:05:36", "remaining_time": "1:41:59", "throughput": 1316.74, "total_tokens": 14664272} {"current_steps": 25820, "total_steps": 40000, "loss": 0.0, "lr": 1.3968030824490352e-05, "epoch": 452.9911504424779, "percentage": 64.55, "elapsed_time": "3:05:38", "remaining_time": "1:41:57", "throughput": 1316.73, "total_tokens": 14666800} {"current_steps": 25825, "total_steps": 40000, "loss": 0.0, "lr": 1.3959221765250469e-05, "epoch": 453.070796460177, "percentage": 64.56, "elapsed_time": "3:05:41", "remaining_time": "1:41:55", "throughput": 1316.66, "total_tokens": 14669096} {"current_steps": 25830, "total_steps": 40000, "loss": 0.0, "lr": 1.3950414408637343e-05, "epoch": 453.1592920353982, "percentage": 64.58, "elapsed_time": "3:05:43", "remaining_time": "1:41:52", "throughput": 1316.68, "total_tokens": 14672008} {"current_steps": 25835, "total_steps": 40000, "loss": 0.0, "lr": 1.3941608756009166e-05, "epoch": 453.24778761061947, "percentage": 64.59, "elapsed_time": "3:05:45", "remaining_time": "1:41:50", "throughput": 1316.7, "total_tokens": 14674920} {"current_steps": 25840, "total_steps": 40000, "loss": 0.0, "lr": 1.3932804808723898e-05, "epoch": 453.3362831858407, "percentage": 64.6, "elapsed_time": "3:05:47", "remaining_time": "1:41:48", "throughput": 1316.75, "total_tokens": 14678232} {"current_steps": 25845, "total_steps": 40000, "loss": 0.0, "lr": 1.3924002568139194e-05, "epoch": 453.42477876106193, "percentage": 64.61, "elapsed_time": "3:05:49", "remaining_time": "1:41:46", "throughput": 1316.73, "total_tokens": 14680744} {"current_steps": 25850, "total_steps": 40000, "loss": 0.0, "lr": 1.3915202035612485e-05, "epoch": 453.5132743362832, "percentage": 64.62, "elapsed_time": "3:05:51", "remaining_time": "1:41:44", "throughput": 1316.74, "total_tokens": 14683560} {"current_steps": 25855, "total_steps": 40000, "loss": 0.0, "lr": 1.3906403212500935e-05, "epoch": 453.60176991150445, "percentage": 64.64, "elapsed_time": "3:05:53", "remaining_time": "1:41:41", "throughput": 1316.79, "total_tokens": 14686808} {"current_steps": 25860, "total_steps": 40000, "loss": 0.0, "lr": 1.3897606100161409e-05, "epoch": 453.69026548672565, "percentage": 64.65, "elapsed_time": "3:05:55", "remaining_time": "1:41:39", "throughput": 1316.79, "total_tokens": 14689640} {"current_steps": 25865, "total_steps": 40000, "loss": 0.0, "lr": 1.388881069995055e-05, "epoch": 453.7787610619469, "percentage": 64.66, "elapsed_time": "3:05:57", "remaining_time": "1:41:37", "throughput": 1316.78, "total_tokens": 14692248} {"current_steps": 25870, "total_steps": 40000, "loss": 0.0, "lr": 1.3880017013224708e-05, "epoch": 453.86725663716817, "percentage": 64.68, "elapsed_time": "3:05:59", "remaining_time": "1:41:35", "throughput": 1316.79, "total_tokens": 14695032} {"current_steps": 25875, "total_steps": 40000, "loss": 0.0, "lr": 1.3871225041339984e-05, "epoch": 453.95575221238937, "percentage": 64.69, "elapsed_time": "3:06:01", "remaining_time": "1:41:33", "throughput": 1316.81, "total_tokens": 14697960} {"current_steps": 25880, "total_steps": 40000, "loss": 0.0, "lr": 1.386243478565222e-05, "epoch": 454.0353982300885, "percentage": 64.7, "elapsed_time": "3:06:04", "remaining_time": "1:41:31", "throughput": 1316.78, "total_tokens": 14700632} {"current_steps": 25885, "total_steps": 40000, "loss": 0.0, "lr": 1.3853646247516966e-05, "epoch": 454.12389380530976, "percentage": 64.71, "elapsed_time": "3:06:06", "remaining_time": "1:41:28", "throughput": 1316.76, "total_tokens": 14703112} {"current_steps": 25890, "total_steps": 40000, "loss": 0.0, "lr": 1.3844859428289545e-05, "epoch": 454.21238938053096, "percentage": 64.72, "elapsed_time": "3:06:08", "remaining_time": "1:41:26", "throughput": 1316.75, "total_tokens": 14705736} {"current_steps": 25895, "total_steps": 40000, "loss": 0.0, "lr": 1.3836074329324984e-05, "epoch": 454.3008849557522, "percentage": 64.74, "elapsed_time": "3:06:10", "remaining_time": "1:41:24", "throughput": 1316.78, "total_tokens": 14708888} {"current_steps": 25900, "total_steps": 40000, "loss": 0.0, "lr": 1.3827290951978044e-05, "epoch": 454.3893805309734, "percentage": 64.75, "elapsed_time": "3:06:12", "remaining_time": "1:41:22", "throughput": 1316.77, "total_tokens": 14711496} {"current_steps": 25905, "total_steps": 40000, "loss": 0.0, "lr": 1.381850929760326e-05, "epoch": 454.4778761061947, "percentage": 64.76, "elapsed_time": "3:06:14", "remaining_time": "1:41:20", "throughput": 1316.75, "total_tokens": 14713992} {"current_steps": 25910, "total_steps": 40000, "loss": 0.0, "lr": 1.3809729367554842e-05, "epoch": 454.56637168141594, "percentage": 64.78, "elapsed_time": "3:06:16", "remaining_time": "1:41:17", "throughput": 1316.76, "total_tokens": 14716824} {"current_steps": 25915, "total_steps": 40000, "loss": 0.0, "lr": 1.3800951163186784e-05, "epoch": 454.65486725663715, "percentage": 64.79, "elapsed_time": "3:06:18", "remaining_time": "1:41:15", "throughput": 1316.78, "total_tokens": 14719784} {"current_steps": 25920, "total_steps": 40000, "loss": 0.0, "lr": 1.3792174685852801e-05, "epoch": 454.7433628318584, "percentage": 64.8, "elapsed_time": "3:06:20", "remaining_time": "1:41:13", "throughput": 1316.78, "total_tokens": 14722456} {"current_steps": 25925, "total_steps": 40000, "loss": 0.0, "lr": 1.378339993690632e-05, "epoch": 454.83185840707966, "percentage": 64.81, "elapsed_time": "3:06:22", "remaining_time": "1:41:11", "throughput": 1316.84, "total_tokens": 14725944} {"current_steps": 25930, "total_steps": 40000, "loss": 0.0, "lr": 1.3774626917700523e-05, "epoch": 454.92035398230087, "percentage": 64.83, "elapsed_time": "3:06:24", "remaining_time": "1:41:09", "throughput": 1316.87, "total_tokens": 14728984} {"current_steps": 25935, "total_steps": 40000, "loss": 0.0, "lr": 1.3765855629588334e-05, "epoch": 455.0, "percentage": 64.84, "elapsed_time": "3:06:26", "remaining_time": "1:41:06", "throughput": 1316.86, "total_tokens": 14731520} {"current_steps": 25940, "total_steps": 40000, "loss": 0.0, "lr": 1.3757086073922374e-05, "epoch": 455.08849557522126, "percentage": 64.85, "elapsed_time": "3:06:29", "remaining_time": "1:41:04", "throughput": 1316.8, "total_tokens": 14733952} {"current_steps": 25945, "total_steps": 40000, "loss": 0.0, "lr": 1.3748318252055038e-05, "epoch": 455.17699115044246, "percentage": 64.86, "elapsed_time": "3:06:31", "remaining_time": "1:41:02", "throughput": 1316.85, "total_tokens": 14737200} {"current_steps": 25950, "total_steps": 40000, "loss": 0.0, "lr": 1.3739552165338416e-05, "epoch": 455.2654867256637, "percentage": 64.88, "elapsed_time": "3:06:33", "remaining_time": "1:41:00", "throughput": 1316.88, "total_tokens": 14740208} {"current_steps": 25955, "total_steps": 40000, "loss": 0.0, "lr": 1.3730787815124354e-05, "epoch": 455.353982300885, "percentage": 64.89, "elapsed_time": "3:06:35", "remaining_time": "1:40:58", "throughput": 1316.88, "total_tokens": 14742944} {"current_steps": 25960, "total_steps": 40000, "loss": 0.0, "lr": 1.3722025202764443e-05, "epoch": 455.4424778761062, "percentage": 64.9, "elapsed_time": "3:06:37", "remaining_time": "1:40:55", "throughput": 1316.89, "total_tokens": 14745824} {"current_steps": 25965, "total_steps": 40000, "loss": 0.0, "lr": 1.371326432960997e-05, "epoch": 455.53097345132744, "percentage": 64.91, "elapsed_time": "3:06:39", "remaining_time": "1:40:53", "throughput": 1316.89, "total_tokens": 14748576} {"current_steps": 25970, "total_steps": 40000, "loss": 0.0, "lr": 1.3704505197011969e-05, "epoch": 455.6194690265487, "percentage": 64.92, "elapsed_time": "3:06:41", "remaining_time": "1:40:51", "throughput": 1316.87, "total_tokens": 14750992} {"current_steps": 25975, "total_steps": 40000, "loss": 0.0, "lr": 1.3695747806321224e-05, "epoch": 455.7079646017699, "percentage": 64.94, "elapsed_time": "3:06:43", "remaining_time": "1:40:49", "throughput": 1316.89, "total_tokens": 14753936} {"current_steps": 25980, "total_steps": 40000, "loss": 0.0, "lr": 1.3686992158888212e-05, "epoch": 455.79646017699116, "percentage": 64.95, "elapsed_time": "3:06:45", "remaining_time": "1:40:47", "throughput": 1316.91, "total_tokens": 14756976} {"current_steps": 25985, "total_steps": 40000, "loss": 0.0, "lr": 1.367823825606319e-05, "epoch": 455.88495575221236, "percentage": 64.96, "elapsed_time": "3:06:47", "remaining_time": "1:40:44", "throughput": 1316.96, "total_tokens": 14760288} {"current_steps": 25990, "total_steps": 40000, "loss": 0.0, "lr": 1.36694860991961e-05, "epoch": 455.9734513274336, "percentage": 64.98, "elapsed_time": "3:06:49", "remaining_time": "1:40:42", "throughput": 1316.98, "total_tokens": 14763120} {"current_steps": 25995, "total_steps": 40000, "loss": 0.0, "lr": 1.3660735689636636e-05, "epoch": 456.05309734513276, "percentage": 64.99, "elapsed_time": "3:06:52", "remaining_time": "1:40:40", "throughput": 1316.92, "total_tokens": 14765480} {"current_steps": 26000, "total_steps": 40000, "loss": 0.0, "lr": 1.365198702873424e-05, "epoch": 456.14159292035396, "percentage": 65.0, "elapsed_time": "3:06:54", "remaining_time": "1:40:38", "throughput": 1316.92, "total_tokens": 14768168} {"current_steps": 26000, "total_steps": 40000, "eval_loss": 0.5152615904808044, "epoch": 456.14159292035396, "percentage": 65.0, "elapsed_time": "3:06:55", "remaining_time": "1:40:39", "throughput": 1316.79, "total_tokens": 14768168} {"current_steps": 26005, "total_steps": 40000, "loss": 0.0, "lr": 1.364324011783804e-05, "epoch": 456.2300884955752, "percentage": 65.01, "elapsed_time": "3:06:59", "remaining_time": "1:40:37", "throughput": 1316.56, "total_tokens": 14770904} {"current_steps": 26010, "total_steps": 40000, "loss": 0.0, "lr": 1.3634494958296934e-05, "epoch": 456.3185840707965, "percentage": 65.03, "elapsed_time": "3:07:01", "remaining_time": "1:40:35", "throughput": 1316.59, "total_tokens": 14774024} {"current_steps": 26015, "total_steps": 40000, "loss": 0.0, "lr": 1.3625751551459542e-05, "epoch": 456.4070796460177, "percentage": 65.04, "elapsed_time": "3:07:03", "remaining_time": "1:40:33", "throughput": 1316.63, "total_tokens": 14777208} {"current_steps": 26020, "total_steps": 40000, "loss": 0.0, "lr": 1.3617009898674188e-05, "epoch": 456.49557522123894, "percentage": 65.05, "elapsed_time": "3:07:05", "remaining_time": "1:40:31", "throughput": 1316.63, "total_tokens": 14779928} {"current_steps": 26025, "total_steps": 40000, "loss": 0.0, "lr": 1.3608270001288967e-05, "epoch": 456.5840707964602, "percentage": 65.06, "elapsed_time": "3:07:07", "remaining_time": "1:40:29", "throughput": 1316.67, "total_tokens": 14783064} {"current_steps": 26030, "total_steps": 40000, "loss": 0.0, "lr": 1.359953186065166e-05, "epoch": 456.6725663716814, "percentage": 65.08, "elapsed_time": "3:07:09", "remaining_time": "1:40:26", "throughput": 1316.69, "total_tokens": 14786072} {"current_steps": 26035, "total_steps": 40000, "loss": 0.0, "lr": 1.3590795478109814e-05, "epoch": 456.76106194690266, "percentage": 65.09, "elapsed_time": "3:07:11", "remaining_time": "1:40:24", "throughput": 1316.68, "total_tokens": 14788584} {"current_steps": 26040, "total_steps": 40000, "loss": 0.0, "lr": 1.3582060855010675e-05, "epoch": 456.8495575221239, "percentage": 65.1, "elapsed_time": "3:07:13", "remaining_time": "1:40:22", "throughput": 1316.69, "total_tokens": 14791480} {"current_steps": 26045, "total_steps": 40000, "loss": 0.0, "lr": 1.3573327992701245e-05, "epoch": 456.9380530973451, "percentage": 65.11, "elapsed_time": "3:07:15", "remaining_time": "1:40:20", "throughput": 1316.73, "total_tokens": 14794696} {"current_steps": 26050, "total_steps": 40000, "loss": 0.0, "lr": 1.356459689252823e-05, "epoch": 457.01769911504425, "percentage": 65.12, "elapsed_time": "3:07:18", "remaining_time": "1:40:18", "throughput": 1316.67, "total_tokens": 14796992} {"current_steps": 26055, "total_steps": 40000, "loss": 0.0, "lr": 1.3555867555838087e-05, "epoch": 457.1061946902655, "percentage": 65.14, "elapsed_time": "3:07:20", "remaining_time": "1:40:15", "throughput": 1316.7, "total_tokens": 14800080} {"current_steps": 26060, "total_steps": 40000, "loss": 0.0, "lr": 1.3547139983976975e-05, "epoch": 457.1946902654867, "percentage": 65.15, "elapsed_time": "3:07:22", "remaining_time": "1:40:13", "throughput": 1316.69, "total_tokens": 14802624} {"current_steps": 26065, "total_steps": 40000, "loss": 0.0, "lr": 1.3538414178290815e-05, "epoch": 457.283185840708, "percentage": 65.16, "elapsed_time": "3:07:24", "remaining_time": "1:40:11", "throughput": 1316.69, "total_tokens": 14805408} {"current_steps": 26070, "total_steps": 40000, "loss": 0.0, "lr": 1.3529690140125209e-05, "epoch": 457.37168141592923, "percentage": 65.18, "elapsed_time": "3:07:26", "remaining_time": "1:40:09", "throughput": 1316.71, "total_tokens": 14808416} {"current_steps": 26075, "total_steps": 40000, "loss": 0.0, "lr": 1.352096787082553e-05, "epoch": 457.46017699115043, "percentage": 65.19, "elapsed_time": "3:07:28", "remaining_time": "1:40:07", "throughput": 1316.7, "total_tokens": 14810992} {"current_steps": 26080, "total_steps": 40000, "loss": 0.0, "lr": 1.3512247371736871e-05, "epoch": 457.5486725663717, "percentage": 65.2, "elapsed_time": "3:07:30", "remaining_time": "1:40:04", "throughput": 1316.7, "total_tokens": 14813776} {"current_steps": 26085, "total_steps": 40000, "loss": 0.0, "lr": 1.3503528644204022e-05, "epoch": 457.6371681415929, "percentage": 65.21, "elapsed_time": "3:07:32", "remaining_time": "1:40:02", "throughput": 1316.76, "total_tokens": 14817152} {"current_steps": 26090, "total_steps": 40000, "loss": 0.0, "lr": 1.349481168957153e-05, "epoch": 457.72566371681415, "percentage": 65.22, "elapsed_time": "3:07:34", "remaining_time": "1:40:00", "throughput": 1316.77, "total_tokens": 14819984} {"current_steps": 26095, "total_steps": 40000, "loss": 0.0, "lr": 1.3486096509183665e-05, "epoch": 457.8141592920354, "percentage": 65.24, "elapsed_time": "3:07:36", "remaining_time": "1:39:58", "throughput": 1316.82, "total_tokens": 14823344} {"current_steps": 26100, "total_steps": 40000, "loss": 0.0, "lr": 1.3477383104384406e-05, "epoch": 457.9026548672566, "percentage": 65.25, "elapsed_time": "3:07:38", "remaining_time": "1:39:56", "throughput": 1316.82, "total_tokens": 14826016} {"current_steps": 26105, "total_steps": 40000, "loss": 0.0, "lr": 1.3468671476517481e-05, "epoch": 457.9911504424779, "percentage": 65.26, "elapsed_time": "3:07:41", "remaining_time": "1:39:53", "throughput": 1316.84, "total_tokens": 14828992} {"current_steps": 26110, "total_steps": 40000, "loss": 0.0, "lr": 1.3459961626926326e-05, "epoch": 458.070796460177, "percentage": 65.28, "elapsed_time": "3:07:43", "remaining_time": "1:39:51", "throughput": 1316.78, "total_tokens": 14831296} {"current_steps": 26115, "total_steps": 40000, "loss": 0.0, "lr": 1.3451253556954101e-05, "epoch": 458.1592920353982, "percentage": 65.29, "elapsed_time": "3:07:45", "remaining_time": "1:39:49", "throughput": 1316.82, "total_tokens": 14834464} {"current_steps": 26120, "total_steps": 40000, "loss": 0.0, "lr": 1.3442547267943717e-05, "epoch": 458.24778761061947, "percentage": 65.3, "elapsed_time": "3:07:47", "remaining_time": "1:39:47", "throughput": 1316.86, "total_tokens": 14837632} {"current_steps": 26125, "total_steps": 40000, "loss": 0.0, "lr": 1.3433842761237774e-05, "epoch": 458.3362831858407, "percentage": 65.31, "elapsed_time": "3:07:49", "remaining_time": "1:39:45", "throughput": 1316.86, "total_tokens": 14840336} {"current_steps": 26130, "total_steps": 40000, "loss": 0.0, "lr": 1.3425140038178639e-05, "epoch": 458.42477876106193, "percentage": 65.33, "elapsed_time": "3:07:51", "remaining_time": "1:39:43", "throughput": 1316.81, "total_tokens": 14842496} {"current_steps": 26135, "total_steps": 40000, "loss": 0.0, "lr": 1.3416439100108358e-05, "epoch": 458.5132743362832, "percentage": 65.34, "elapsed_time": "3:07:53", "remaining_time": "1:39:40", "throughput": 1316.82, "total_tokens": 14845360} {"current_steps": 26140, "total_steps": 40000, "loss": 0.0, "lr": 1.3407739948368734e-05, "epoch": 458.60176991150445, "percentage": 65.35, "elapsed_time": "3:07:55", "remaining_time": "1:39:38", "throughput": 1316.82, "total_tokens": 14848080} {"current_steps": 26145, "total_steps": 40000, "loss": 0.0, "lr": 1.3399042584301298e-05, "epoch": 458.69026548672565, "percentage": 65.36, "elapsed_time": "3:07:57", "remaining_time": "1:39:36", "throughput": 1316.82, "total_tokens": 14850864} {"current_steps": 26150, "total_steps": 40000, "loss": 0.0, "lr": 1.3390347009247272e-05, "epoch": 458.7787610619469, "percentage": 65.38, "elapsed_time": "3:07:59", "remaining_time": "1:39:34", "throughput": 1316.87, "total_tokens": 14854176} {"current_steps": 26155, "total_steps": 40000, "loss": 0.0, "lr": 1.3381653224547635e-05, "epoch": 458.86725663716817, "percentage": 65.39, "elapsed_time": "3:08:01", "remaining_time": "1:39:32", "throughput": 1316.95, "total_tokens": 14857696} {"current_steps": 26160, "total_steps": 40000, "loss": 0.0, "lr": 1.3372961231543086e-05, "epoch": 458.95575221238937, "percentage": 65.4, "elapsed_time": "3:08:03", "remaining_time": "1:39:29", "throughput": 1316.93, "total_tokens": 14860256} {"current_steps": 26165, "total_steps": 40000, "loss": 0.0, "lr": 1.3364271031574016e-05, "epoch": 459.0353982300885, "percentage": 65.41, "elapsed_time": "3:08:06", "remaining_time": "1:39:27", "throughput": 1316.87, "total_tokens": 14862496} {"current_steps": 26170, "total_steps": 40000, "loss": 0.0, "lr": 1.335558262598059e-05, "epoch": 459.12389380530976, "percentage": 65.42, "elapsed_time": "3:08:08", "remaining_time": "1:39:25", "throughput": 1316.9, "total_tokens": 14865568} {"current_steps": 26175, "total_steps": 40000, "loss": 0.0, "lr": 1.3346896016102645e-05, "epoch": 459.21238938053096, "percentage": 65.44, "elapsed_time": "3:08:10", "remaining_time": "1:39:23", "throughput": 1316.91, "total_tokens": 14868448} {"current_steps": 26180, "total_steps": 40000, "loss": 0.0, "lr": 1.3338211203279788e-05, "epoch": 459.3008849557522, "percentage": 65.45, "elapsed_time": "3:08:12", "remaining_time": "1:39:21", "throughput": 1316.92, "total_tokens": 14871296} {"current_steps": 26185, "total_steps": 40000, "loss": 0.0, "lr": 1.3329528188851303e-05, "epoch": 459.3893805309734, "percentage": 65.46, "elapsed_time": "3:08:14", "remaining_time": "1:39:18", "throughput": 1316.9, "total_tokens": 14873776} {"current_steps": 26190, "total_steps": 40000, "loss": 0.0, "lr": 1.3320846974156242e-05, "epoch": 459.4778761061947, "percentage": 65.48, "elapsed_time": "3:08:16", "remaining_time": "1:39:16", "throughput": 1316.9, "total_tokens": 14876544} {"current_steps": 26195, "total_steps": 40000, "loss": 0.0, "lr": 1.3312167560533337e-05, "epoch": 459.56637168141594, "percentage": 65.49, "elapsed_time": "3:08:18", "remaining_time": "1:39:14", "throughput": 1316.9, "total_tokens": 14879248} {"current_steps": 26200, "total_steps": 40000, "loss": 0.0, "lr": 1.3303489949321082e-05, "epoch": 459.65486725663715, "percentage": 65.5, "elapsed_time": "3:08:20", "remaining_time": "1:39:12", "throughput": 1316.9, "total_tokens": 14882048} {"current_steps": 26200, "total_steps": 40000, "eval_loss": 0.5005371570587158, "epoch": 459.65486725663715, "percentage": 65.5, "elapsed_time": "3:08:21", "remaining_time": "1:39:12", "throughput": 1316.78, "total_tokens": 14882048} {"current_steps": 26205, "total_steps": 40000, "loss": 0.0, "lr": 1.3294814141857653e-05, "epoch": 459.7433628318584, "percentage": 65.51, "elapsed_time": "3:08:25", "remaining_time": "1:39:11", "throughput": 1316.66, "total_tokens": 14885712} {"current_steps": 26210, "total_steps": 40000, "loss": 0.0, "lr": 1.3286140139480992e-05, "epoch": 459.83185840707966, "percentage": 65.53, "elapsed_time": "3:08:27", "remaining_time": "1:39:09", "throughput": 1316.7, "total_tokens": 14888896} {"current_steps": 26215, "total_steps": 40000, "loss": 0.0, "lr": 1.3277467943528719e-05, "epoch": 459.92035398230087, "percentage": 65.54, "elapsed_time": "3:08:29", "remaining_time": "1:39:07", "throughput": 1316.71, "total_tokens": 14891792} {"current_steps": 26220, "total_steps": 40000, "loss": 0.0, "lr": 1.3268797555338203e-05, "epoch": 460.0, "percentage": 65.55, "elapsed_time": "3:08:31", "remaining_time": "1:39:04", "throughput": 1316.67, "total_tokens": 14893968} {"current_steps": 26225, "total_steps": 40000, "loss": 0.0, "lr": 1.3260128976246533e-05, "epoch": 460.08849557522126, "percentage": 65.56, "elapsed_time": "3:08:34", "remaining_time": "1:39:02", "throughput": 1316.67, "total_tokens": 14897008} {"current_steps": 26230, "total_steps": 40000, "loss": 0.0, "lr": 1.32514622075905e-05, "epoch": 460.17699115044246, "percentage": 65.58, "elapsed_time": "3:08:36", "remaining_time": "1:39:00", "throughput": 1316.66, "total_tokens": 14899680} {"current_steps": 26235, "total_steps": 40000, "loss": 0.0, "lr": 1.3242797250706638e-05, "epoch": 460.2654867256637, "percentage": 65.59, "elapsed_time": "3:08:38", "remaining_time": "1:38:58", "throughput": 1316.7, "total_tokens": 14902800} {"current_steps": 26240, "total_steps": 40000, "loss": 0.0, "lr": 1.3234134106931195e-05, "epoch": 460.353982300885, "percentage": 65.6, "elapsed_time": "3:08:40", "remaining_time": "1:38:56", "throughput": 1316.69, "total_tokens": 14905440} {"current_steps": 26245, "total_steps": 40000, "loss": 0.0, "lr": 1.322547277760013e-05, "epoch": 460.4424778761062, "percentage": 65.61, "elapsed_time": "3:08:42", "remaining_time": "1:38:54", "throughput": 1316.7, "total_tokens": 14908336} {"current_steps": 26250, "total_steps": 40000, "loss": 0.0, "lr": 1.3216813264049132e-05, "epoch": 460.53097345132744, "percentage": 65.62, "elapsed_time": "3:08:44", "remaining_time": "1:38:51", "throughput": 1316.7, "total_tokens": 14910976} {"current_steps": 26255, "total_steps": 40000, "loss": 0.0, "lr": 1.32081555676136e-05, "epoch": 460.6194690265487, "percentage": 65.64, "elapsed_time": "3:08:46", "remaining_time": "1:38:49", "throughput": 1316.72, "total_tokens": 14913952} {"current_steps": 26260, "total_steps": 40000, "loss": 0.0, "lr": 1.3199499689628674e-05, "epoch": 460.7079646017699, "percentage": 65.65, "elapsed_time": "3:08:48", "remaining_time": "1:38:47", "throughput": 1316.75, "total_tokens": 14917056} {"current_steps": 26265, "total_steps": 40000, "loss": 0.0, "lr": 1.3190845631429192e-05, "epoch": 460.79646017699116, "percentage": 65.66, "elapsed_time": "3:08:50", "remaining_time": "1:38:45", "throughput": 1316.76, "total_tokens": 14919856} {"current_steps": 26270, "total_steps": 40000, "loss": 0.0, "lr": 1.3182193394349704e-05, "epoch": 460.88495575221236, "percentage": 65.67, "elapsed_time": "3:08:52", "remaining_time": "1:38:43", "throughput": 1316.71, "total_tokens": 14922096} {"current_steps": 26275, "total_steps": 40000, "loss": 0.0, "lr": 1.3173542979724507e-05, "epoch": 460.9734513274336, "percentage": 65.69, "elapsed_time": "3:08:54", "remaining_time": "1:38:40", "throughput": 1316.79, "total_tokens": 14925632} {"current_steps": 26280, "total_steps": 40000, "loss": 0.0, "lr": 1.3164894388887617e-05, "epoch": 461.05309734513276, "percentage": 65.7, "elapsed_time": "3:08:57", "remaining_time": "1:38:38", "throughput": 1316.72, "total_tokens": 14927848} {"current_steps": 26285, "total_steps": 40000, "loss": 0.0, "lr": 1.3156247623172727e-05, "epoch": 461.14159292035396, "percentage": 65.71, "elapsed_time": "3:08:59", "remaining_time": "1:38:36", "throughput": 1316.72, "total_tokens": 14930584} {"current_steps": 26290, "total_steps": 40000, "loss": 0.0, "lr": 1.3147602683913302e-05, "epoch": 461.2300884955752, "percentage": 65.72, "elapsed_time": "3:09:01", "remaining_time": "1:38:34", "throughput": 1316.76, "total_tokens": 14933784} {"current_steps": 26295, "total_steps": 40000, "loss": 0.0, "lr": 1.3138959572442481e-05, "epoch": 461.3185840707965, "percentage": 65.74, "elapsed_time": "3:09:03", "remaining_time": "1:38:32", "throughput": 1316.73, "total_tokens": 14936216} {"current_steps": 26300, "total_steps": 40000, "loss": 0.0, "lr": 1.3130318290093146e-05, "epoch": 461.4070796460177, "percentage": 65.75, "elapsed_time": "3:09:05", "remaining_time": "1:38:30", "throughput": 1316.76, "total_tokens": 14939304} {"current_steps": 26305, "total_steps": 40000, "loss": 0.0, "lr": 1.3121678838197909e-05, "epoch": 461.49557522123894, "percentage": 65.76, "elapsed_time": "3:09:07", "remaining_time": "1:38:27", "throughput": 1316.76, "total_tokens": 14942392} {"current_steps": 26310, "total_steps": 40000, "loss": 0.0, "lr": 1.3113041218089056e-05, "epoch": 461.5840707964602, "percentage": 65.77, "elapsed_time": "3:09:09", "remaining_time": "1:38:25", "throughput": 1316.78, "total_tokens": 14945288} {"current_steps": 26315, "total_steps": 40000, "loss": 0.0, "lr": 1.3104405431098626e-05, "epoch": 461.6725663716814, "percentage": 65.79, "elapsed_time": "3:09:11", "remaining_time": "1:38:23", "throughput": 1316.81, "total_tokens": 14948376} {"current_steps": 26320, "total_steps": 40000, "loss": 0.0, "lr": 1.3095771478558377e-05, "epoch": 461.76106194690266, "percentage": 65.8, "elapsed_time": "3:09:14", "remaining_time": "1:38:21", "throughput": 1316.83, "total_tokens": 14951320} {"current_steps": 26325, "total_steps": 40000, "loss": 0.0, "lr": 1.3087139361799766e-05, "epoch": 461.8495575221239, "percentage": 65.81, "elapsed_time": "3:09:16", "remaining_time": "1:38:19", "throughput": 1316.86, "total_tokens": 14954360} {"current_steps": 26330, "total_steps": 40000, "loss": 0.0, "lr": 1.3078509082153964e-05, "epoch": 461.9380530973451, "percentage": 65.83, "elapsed_time": "3:09:18", "remaining_time": "1:38:16", "throughput": 1316.85, "total_tokens": 14956952} {"current_steps": 26335, "total_steps": 40000, "loss": 0.0, "lr": 1.3069880640951885e-05, "epoch": 462.01769911504425, "percentage": 65.84, "elapsed_time": "3:09:20", "remaining_time": "1:38:14", "throughput": 1316.77, "total_tokens": 14959064} {"current_steps": 26340, "total_steps": 40000, "loss": 0.0, "lr": 1.3061254039524123e-05, "epoch": 462.1061946902655, "percentage": 65.85, "elapsed_time": "3:09:22", "remaining_time": "1:38:12", "throughput": 1316.74, "total_tokens": 14961480} {"current_steps": 26345, "total_steps": 40000, "loss": 0.0, "lr": 1.3052629279201028e-05, "epoch": 462.1946902654867, "percentage": 65.86, "elapsed_time": "3:09:24", "remaining_time": "1:38:10", "throughput": 1316.75, "total_tokens": 14964344} {"current_steps": 26350, "total_steps": 40000, "loss": 0.0, "lr": 1.3044006361312633e-05, "epoch": 462.283185840708, "percentage": 65.88, "elapsed_time": "3:09:26", "remaining_time": "1:38:08", "throughput": 1316.72, "total_tokens": 14966744} {"current_steps": 26355, "total_steps": 40000, "loss": 0.0, "lr": 1.30353852871887e-05, "epoch": 462.37168141592923, "percentage": 65.89, "elapsed_time": "3:09:28", "remaining_time": "1:38:06", "throughput": 1316.8, "total_tokens": 14970328} {"current_steps": 26360, "total_steps": 40000, "loss": 0.0, "lr": 1.302676605815873e-05, "epoch": 462.46017699115043, "percentage": 65.9, "elapsed_time": "3:09:30", "remaining_time": "1:38:03", "throughput": 1316.8, "total_tokens": 14973160} {"current_steps": 26365, "total_steps": 40000, "loss": 0.0, "lr": 1.3018148675551884e-05, "epoch": 462.5486725663717, "percentage": 65.91, "elapsed_time": "3:09:32", "remaining_time": "1:38:01", "throughput": 1316.83, "total_tokens": 14976136} {"current_steps": 26370, "total_steps": 40000, "loss": 0.0, "lr": 1.3009533140697094e-05, "epoch": 462.6371681415929, "percentage": 65.92, "elapsed_time": "3:09:34", "remaining_time": "1:37:59", "throughput": 1316.81, "total_tokens": 14978712} {"current_steps": 26375, "total_steps": 40000, "loss": 0.0, "lr": 1.3000919454922966e-05, "epoch": 462.72566371681415, "percentage": 65.94, "elapsed_time": "3:09:37", "remaining_time": "1:37:57", "throughput": 1316.82, "total_tokens": 14981528} {"current_steps": 26380, "total_steps": 40000, "loss": 0.0, "lr": 1.299230761955785e-05, "epoch": 462.8141592920354, "percentage": 65.95, "elapsed_time": "3:09:39", "remaining_time": "1:37:55", "throughput": 1316.84, "total_tokens": 14984488} {"current_steps": 26385, "total_steps": 40000, "loss": 0.0, "lr": 1.2983697635929807e-05, "epoch": 462.9026548672566, "percentage": 65.96, "elapsed_time": "3:09:41", "remaining_time": "1:37:52", "throughput": 1316.84, "total_tokens": 14987208} {"current_steps": 26390, "total_steps": 40000, "loss": 0.0, "lr": 1.2975089505366584e-05, "epoch": 462.9911504424779, "percentage": 65.97, "elapsed_time": "3:09:43", "remaining_time": "1:37:50", "throughput": 1316.89, "total_tokens": 14990504} {"current_steps": 26395, "total_steps": 40000, "loss": 0.0, "lr": 1.2966483229195683e-05, "epoch": 463.070796460177, "percentage": 65.99, "elapsed_time": "3:09:45", "remaining_time": "1:37:48", "throughput": 1316.84, "total_tokens": 14992888} {"current_steps": 26400, "total_steps": 40000, "loss": 0.0, "lr": 1.2957878808744283e-05, "epoch": 463.1592920353982, "percentage": 66.0, "elapsed_time": "3:09:47", "remaining_time": "1:37:46", "throughput": 1316.87, "total_tokens": 14996008} {"current_steps": 26400, "total_steps": 40000, "eval_loss": 0.5167677402496338, "epoch": 463.1592920353982, "percentage": 66.0, "elapsed_time": "3:09:48", "remaining_time": "1:37:46", "throughput": 1316.75, "total_tokens": 14996008} {"current_steps": 26405, "total_steps": 40000, "loss": 0.0, "lr": 1.294927624533931e-05, "epoch": 463.24778761061947, "percentage": 66.01, "elapsed_time": "3:09:52", "remaining_time": "1:37:45", "throughput": 1316.56, "total_tokens": 14998904} {"current_steps": 26410, "total_steps": 40000, "loss": 0.0, "lr": 1.2940675540307378e-05, "epoch": 463.3362831858407, "percentage": 66.03, "elapsed_time": "3:09:54", "remaining_time": "1:37:43", "throughput": 1316.57, "total_tokens": 15001768} {"current_steps": 26415, "total_steps": 40000, "loss": 0.0, "lr": 1.2932076694974814e-05, "epoch": 463.42477876106193, "percentage": 66.04, "elapsed_time": "3:09:56", "remaining_time": "1:37:41", "throughput": 1316.59, "total_tokens": 15004696} {"current_steps": 26420, "total_steps": 40000, "loss": 0.0, "lr": 1.2923479710667682e-05, "epoch": 463.5132743362832, "percentage": 66.05, "elapsed_time": "3:09:58", "remaining_time": "1:37:38", "throughput": 1316.59, "total_tokens": 15007400} {"current_steps": 26425, "total_steps": 40000, "loss": 0.0068, "lr": 1.2914884588711751e-05, "epoch": 463.60176991150445, "percentage": 66.06, "elapsed_time": "3:10:00", "remaining_time": "1:37:36", "throughput": 1316.58, "total_tokens": 15010040} {"current_steps": 26430, "total_steps": 40000, "loss": 0.2589, "lr": 1.2906291330432475e-05, "epoch": 463.69026548672565, "percentage": 66.07, "elapsed_time": "3:10:02", "remaining_time": "1:37:34", "throughput": 1316.58, "total_tokens": 15012792} {"current_steps": 26435, "total_steps": 40000, "loss": 0.0, "lr": 1.2897699937155055e-05, "epoch": 463.7787610619469, "percentage": 66.09, "elapsed_time": "3:10:04", "remaining_time": "1:37:32", "throughput": 1316.62, "total_tokens": 15015944} {"current_steps": 26440, "total_steps": 40000, "loss": 0.0084, "lr": 1.2889110410204403e-05, "epoch": 463.86725663716817, "percentage": 66.1, "elapsed_time": "3:10:06", "remaining_time": "1:37:30", "throughput": 1316.64, "total_tokens": 15018952} {"current_steps": 26445, "total_steps": 40000, "loss": 0.0, "lr": 1.2880522750905111e-05, "epoch": 463.95575221238937, "percentage": 66.11, "elapsed_time": "3:10:09", "remaining_time": "1:37:27", "throughput": 1316.64, "total_tokens": 15021608} {"current_steps": 26450, "total_steps": 40000, "loss": 0.0, "lr": 1.2871936960581523e-05, "epoch": 464.0353982300885, "percentage": 66.12, "elapsed_time": "3:10:11", "remaining_time": "1:37:25", "throughput": 1316.61, "total_tokens": 15024248} {"current_steps": 26455, "total_steps": 40000, "loss": 0.0, "lr": 1.2863353040557658e-05, "epoch": 464.12389380530976, "percentage": 66.14, "elapsed_time": "3:10:13", "remaining_time": "1:37:23", "throughput": 1316.65, "total_tokens": 15027448} {"current_steps": 26460, "total_steps": 40000, "loss": 0.0, "lr": 1.2854770992157273e-05, "epoch": 464.21238938053096, "percentage": 66.15, "elapsed_time": "3:10:15", "remaining_time": "1:37:21", "throughput": 1316.69, "total_tokens": 15030568} {"current_steps": 26465, "total_steps": 40000, "loss": 0.0, "lr": 1.2846190816703835e-05, "epoch": 464.3008849557522, "percentage": 66.16, "elapsed_time": "3:10:17", "remaining_time": "1:37:19", "throughput": 1316.66, "total_tokens": 15032920} {"current_steps": 26470, "total_steps": 40000, "loss": 0.0, "lr": 1.2837612515520498e-05, "epoch": 464.3893805309734, "percentage": 66.17, "elapsed_time": "3:10:19", "remaining_time": "1:37:17", "throughput": 1316.7, "total_tokens": 15036120} {"current_steps": 26475, "total_steps": 40000, "loss": 0.0, "lr": 1.2829036089930163e-05, "epoch": 464.4778761061947, "percentage": 66.19, "elapsed_time": "3:10:21", "remaining_time": "1:37:14", "throughput": 1316.72, "total_tokens": 15039080} {"current_steps": 26480, "total_steps": 40000, "loss": 0.0, "lr": 1.2820461541255412e-05, "epoch": 464.56637168141594, "percentage": 66.2, "elapsed_time": "3:10:23", "remaining_time": "1:37:12", "throughput": 1316.69, "total_tokens": 15041496} {"current_steps": 26485, "total_steps": 40000, "loss": 0.0, "lr": 1.2811888870818543e-05, "epoch": 464.65486725663715, "percentage": 66.21, "elapsed_time": "3:10:25", "remaining_time": "1:37:10", "throughput": 1316.67, "total_tokens": 15044024} {"current_steps": 26490, "total_steps": 40000, "loss": 0.0904, "lr": 1.2803318079941581e-05, "epoch": 464.7433628318584, "percentage": 66.22, "elapsed_time": "3:10:27", "remaining_time": "1:37:08", "throughput": 1316.65, "total_tokens": 15046536} {"current_steps": 26495, "total_steps": 40000, "loss": 0.0, "lr": 1.2794749169946235e-05, "epoch": 464.83185840707966, "percentage": 66.24, "elapsed_time": "3:10:29", "remaining_time": "1:37:06", "throughput": 1316.71, "total_tokens": 15050024} {"current_steps": 26500, "total_steps": 40000, "loss": 0.1704, "lr": 1.2786182142153952e-05, "epoch": 464.92035398230087, "percentage": 66.25, "elapsed_time": "3:10:32", "remaining_time": "1:37:03", "throughput": 1316.77, "total_tokens": 15053384} {"current_steps": 26505, "total_steps": 40000, "loss": 0.0, "lr": 1.2777616997885878e-05, "epoch": 465.0, "percentage": 66.26, "elapsed_time": "3:10:34", "remaining_time": "1:37:01", "throughput": 1316.73, "total_tokens": 15055576} {"current_steps": 26510, "total_steps": 40000, "loss": 0.2264, "lr": 1.2769053738462847e-05, "epoch": 465.08849557522126, "percentage": 66.27, "elapsed_time": "3:10:36", "remaining_time": "1:36:59", "throughput": 1316.7, "total_tokens": 15058232} {"current_steps": 26515, "total_steps": 40000, "loss": 0.1045, "lr": 1.2760492365205434e-05, "epoch": 465.17699115044246, "percentage": 66.29, "elapsed_time": "3:10:38", "remaining_time": "1:36:57", "throughput": 1316.74, "total_tokens": 15061512} {"current_steps": 26520, "total_steps": 40000, "loss": 0.0, "lr": 1.2751932879433919e-05, "epoch": 465.2654867256637, "percentage": 66.3, "elapsed_time": "3:10:40", "remaining_time": "1:36:55", "throughput": 1316.77, "total_tokens": 15064536} {"current_steps": 26525, "total_steps": 40000, "loss": 0.2155, "lr": 1.2743375282468267e-05, "epoch": 465.353982300885, "percentage": 66.31, "elapsed_time": "3:10:42", "remaining_time": "1:36:52", "throughput": 1316.78, "total_tokens": 15067416} {"current_steps": 26530, "total_steps": 40000, "loss": 0.0, "lr": 1.2734819575628182e-05, "epoch": 465.4424778761062, "percentage": 66.33, "elapsed_time": "3:10:44", "remaining_time": "1:36:50", "throughput": 1316.79, "total_tokens": 15070200} {"current_steps": 26535, "total_steps": 40000, "loss": 0.0, "lr": 1.2726265760233039e-05, "epoch": 465.53097345132744, "percentage": 66.34, "elapsed_time": "3:10:46", "remaining_time": "1:36:48", "throughput": 1316.78, "total_tokens": 15072808} {"current_steps": 26540, "total_steps": 40000, "loss": 0.0, "lr": 1.271771383760197e-05, "epoch": 465.6194690265487, "percentage": 66.35, "elapsed_time": "3:10:48", "remaining_time": "1:36:46", "throughput": 1316.8, "total_tokens": 15075800} {"current_steps": 26545, "total_steps": 40000, "loss": 0.0001, "lr": 1.2709163809053764e-05, "epoch": 465.7079646017699, "percentage": 66.36, "elapsed_time": "3:10:50", "remaining_time": "1:36:44", "throughput": 1316.77, "total_tokens": 15078232} {"current_steps": 26550, "total_steps": 40000, "loss": 0.0, "lr": 1.2700615675906963e-05, "epoch": 465.79646017699116, "percentage": 66.38, "elapsed_time": "3:10:52", "remaining_time": "1:36:41", "throughput": 1316.79, "total_tokens": 15081096} {"current_steps": 26555, "total_steps": 40000, "loss": 0.0, "lr": 1.269206943947978e-05, "epoch": 465.88495575221236, "percentage": 66.39, "elapsed_time": "3:10:55", "remaining_time": "1:36:39", "throughput": 1316.86, "total_tokens": 15084616} {"current_steps": 26560, "total_steps": 40000, "loss": 0.0, "lr": 1.2683525101090177e-05, "epoch": 465.9734513274336, "percentage": 66.4, "elapsed_time": "3:10:57", "remaining_time": "1:36:37", "throughput": 1316.84, "total_tokens": 15087160} {"current_steps": 26565, "total_steps": 40000, "loss": 0.0, "lr": 1.2674982662055765e-05, "epoch": 466.05309734513276, "percentage": 66.41, "elapsed_time": "3:10:59", "remaining_time": "1:36:35", "throughput": 1316.76, "total_tokens": 15089240} {"current_steps": 26570, "total_steps": 40000, "loss": 0.0, "lr": 1.2666442123693922e-05, "epoch": 466.14159292035396, "percentage": 66.42, "elapsed_time": "3:11:01", "remaining_time": "1:36:33", "throughput": 1316.78, "total_tokens": 15092200} {"current_steps": 26575, "total_steps": 40000, "loss": 0.0, "lr": 1.265790348732169e-05, "epoch": 466.2300884955752, "percentage": 66.44, "elapsed_time": "3:11:03", "remaining_time": "1:36:31", "throughput": 1316.77, "total_tokens": 15094808} {"current_steps": 26580, "total_steps": 40000, "loss": 0.0, "lr": 1.264936675425584e-05, "epoch": 466.3185840707965, "percentage": 66.45, "elapsed_time": "3:11:05", "remaining_time": "1:36:28", "throughput": 1316.77, "total_tokens": 15097560} {"current_steps": 26585, "total_steps": 40000, "loss": 0.0, "lr": 1.2640831925812852e-05, "epoch": 466.4070796460177, "percentage": 66.46, "elapsed_time": "3:11:07", "remaining_time": "1:36:26", "throughput": 1316.82, "total_tokens": 15100824} {"current_steps": 26590, "total_steps": 40000, "loss": 0.0, "lr": 1.263229900330889e-05, "epoch": 466.49557522123894, "percentage": 66.47, "elapsed_time": "3:11:09", "remaining_time": "1:36:24", "throughput": 1316.8, "total_tokens": 15103368} {"current_steps": 26595, "total_steps": 40000, "loss": 0.0, "lr": 1.2623767988059843e-05, "epoch": 466.5840707964602, "percentage": 66.49, "elapsed_time": "3:11:11", "remaining_time": "1:36:22", "throughput": 1316.84, "total_tokens": 15106504} {"current_steps": 26600, "total_steps": 40000, "loss": 0.139, "lr": 1.2615238881381309e-05, "epoch": 466.6725663716814, "percentage": 66.5, "elapsed_time": "3:11:13", "remaining_time": "1:36:20", "throughput": 1316.85, "total_tokens": 15109352} {"current_steps": 26600, "total_steps": 40000, "eval_loss": 0.8271105885505676, "epoch": 466.6725663716814, "percentage": 66.5, "elapsed_time": "3:11:14", "remaining_time": "1:36:20", "throughput": 1316.72, "total_tokens": 15109352} {"current_steps": 26605, "total_steps": 40000, "loss": 0.0005, "lr": 1.2606711684588568e-05, "epoch": 466.76106194690266, "percentage": 66.51, "elapsed_time": "3:11:19", "remaining_time": "1:36:19", "throughput": 1316.49, "total_tokens": 15112392} {"current_steps": 26610, "total_steps": 40000, "loss": 0.1392, "lr": 1.2598186398996636e-05, "epoch": 466.8495575221239, "percentage": 66.53, "elapsed_time": "3:11:21", "remaining_time": "1:36:17", "throughput": 1316.54, "total_tokens": 15115688} {"current_steps": 26615, "total_steps": 40000, "loss": 0.0, "lr": 1.2589663025920207e-05, "epoch": 466.9380530973451, "percentage": 66.54, "elapsed_time": "3:11:23", "remaining_time": "1:36:15", "throughput": 1316.51, "total_tokens": 15118104} {"current_steps": 26620, "total_steps": 40000, "loss": 0.0, "lr": 1.2581141566673705e-05, "epoch": 467.01769911504425, "percentage": 66.55, "elapsed_time": "3:11:25", "remaining_time": "1:36:13", "throughput": 1316.46, "total_tokens": 15120496} {"current_steps": 26625, "total_steps": 40000, "loss": 0.0, "lr": 1.257262202257124e-05, "epoch": 467.1061946902655, "percentage": 66.56, "elapsed_time": "3:11:27", "remaining_time": "1:36:10", "throughput": 1316.47, "total_tokens": 15123328} {"current_steps": 26630, "total_steps": 40000, "loss": 0.0, "lr": 1.2564104394926618e-05, "epoch": 467.1946902654867, "percentage": 66.57, "elapsed_time": "3:11:29", "remaining_time": "1:36:08", "throughput": 1316.45, "total_tokens": 15125856} {"current_steps": 26635, "total_steps": 40000, "loss": 0.0, "lr": 1.2555588685053383e-05, "epoch": 467.283185840708, "percentage": 66.59, "elapsed_time": "3:11:31", "remaining_time": "1:36:06", "throughput": 1316.45, "total_tokens": 15128512} {"current_steps": 26640, "total_steps": 40000, "loss": 0.0034, "lr": 1.2547074894264762e-05, "epoch": 467.37168141592923, "percentage": 66.6, "elapsed_time": "3:11:34", "remaining_time": "1:36:04", "throughput": 1316.47, "total_tokens": 15131520} {"current_steps": 26645, "total_steps": 40000, "loss": 0.0, "lr": 1.2538563023873679e-05, "epoch": 467.46017699115043, "percentage": 66.61, "elapsed_time": "3:11:36", "remaining_time": "1:36:02", "throughput": 1316.46, "total_tokens": 15134128} {"current_steps": 26650, "total_steps": 40000, "loss": 0.0, "lr": 1.2530053075192789e-05, "epoch": 467.5486725663717, "percentage": 66.62, "elapsed_time": "3:11:38", "remaining_time": "1:35:59", "throughput": 1316.46, "total_tokens": 15136816} {"current_steps": 26655, "total_steps": 40000, "loss": 0.0, "lr": 1.252154504953441e-05, "epoch": 467.6371681415929, "percentage": 66.64, "elapsed_time": "3:11:40", "remaining_time": "1:35:57", "throughput": 1316.52, "total_tokens": 15140256} {"current_steps": 26660, "total_steps": 40000, "loss": 0.0, "lr": 1.25130389482106e-05, "epoch": 467.72566371681415, "percentage": 66.65, "elapsed_time": "3:11:42", "remaining_time": "1:35:55", "throughput": 1316.54, "total_tokens": 15143248} {"current_steps": 26665, "total_steps": 40000, "loss": 0.0, "lr": 1.2504534772533116e-05, "epoch": 467.8141592920354, "percentage": 66.66, "elapsed_time": "3:11:44", "remaining_time": "1:35:53", "throughput": 1316.57, "total_tokens": 15146240} {"current_steps": 26670, "total_steps": 40000, "loss": 0.0, "lr": 1.2496032523813387e-05, "epoch": 467.9026548672566, "percentage": 66.67, "elapsed_time": "3:11:46", "remaining_time": "1:35:51", "throughput": 1316.62, "total_tokens": 15149520} {"current_steps": 26675, "total_steps": 40000, "loss": 0.0, "lr": 1.2487532203362576e-05, "epoch": 467.9911504424779, "percentage": 66.69, "elapsed_time": "3:11:48", "remaining_time": "1:35:48", "throughput": 1316.62, "total_tokens": 15152272} {"current_steps": 26680, "total_steps": 40000, "loss": 0.0, "lr": 1.247903381249155e-05, "epoch": 468.070796460177, "percentage": 66.7, "elapsed_time": "3:11:50", "remaining_time": "1:35:46", "throughput": 1316.61, "total_tokens": 15155144} {"current_steps": 26685, "total_steps": 40000, "loss": 0.0, "lr": 1.2470537352510853e-05, "epoch": 468.1592920353982, "percentage": 66.71, "elapsed_time": "3:11:52", "remaining_time": "1:35:44", "throughput": 1316.64, "total_tokens": 15158280} {"current_steps": 26690, "total_steps": 40000, "loss": 0.0, "lr": 1.2462042824730758e-05, "epoch": 468.24778761061947, "percentage": 66.72, "elapsed_time": "3:11:54", "remaining_time": "1:35:42", "throughput": 1316.71, "total_tokens": 15161736} {"current_steps": 26695, "total_steps": 40000, "loss": 0.0, "lr": 1.245355023046122e-05, "epoch": 468.3362831858407, "percentage": 66.74, "elapsed_time": "3:11:56", "remaining_time": "1:35:40", "throughput": 1316.67, "total_tokens": 15164072} {"current_steps": 26700, "total_steps": 40000, "loss": 0.0, "lr": 1.2445059571011896e-05, "epoch": 468.42477876106193, "percentage": 66.75, "elapsed_time": "3:11:59", "remaining_time": "1:35:37", "throughput": 1316.71, "total_tokens": 15167192} {"current_steps": 26705, "total_steps": 40000, "loss": 0.0, "lr": 1.2436570847692173e-05, "epoch": 468.5132743362832, "percentage": 66.76, "elapsed_time": "3:12:01", "remaining_time": "1:35:35", "throughput": 1316.74, "total_tokens": 15170264} {"current_steps": 26710, "total_steps": 40000, "loss": 0.0, "lr": 1.2428084061811096e-05, "epoch": 468.60176991150445, "percentage": 66.77, "elapsed_time": "3:12:03", "remaining_time": "1:35:33", "throughput": 1316.8, "total_tokens": 15173768} {"current_steps": 26715, "total_steps": 40000, "loss": 0.0, "lr": 1.2419599214677447e-05, "epoch": 468.69026548672565, "percentage": 66.79, "elapsed_time": "3:12:05", "remaining_time": "1:35:31", "throughput": 1316.81, "total_tokens": 15176584} {"current_steps": 26720, "total_steps": 40000, "loss": 0.0, "lr": 1.2411116307599702e-05, "epoch": 468.7787610619469, "percentage": 66.8, "elapsed_time": "3:12:07", "remaining_time": "1:35:29", "throughput": 1316.79, "total_tokens": 15179032} {"current_steps": 26725, "total_steps": 40000, "loss": 0.0, "lr": 1.2402635341886016e-05, "epoch": 468.86725663716817, "percentage": 66.81, "elapsed_time": "3:12:09", "remaining_time": "1:35:26", "throughput": 1316.78, "total_tokens": 15181624} {"current_steps": 26730, "total_steps": 40000, "loss": 0.0, "lr": 1.2394156318844278e-05, "epoch": 468.95575221238937, "percentage": 66.83, "elapsed_time": "3:12:11", "remaining_time": "1:35:24", "throughput": 1316.76, "total_tokens": 15184088} {"current_steps": 26735, "total_steps": 40000, "loss": 0.0, "lr": 1.2385679239782039e-05, "epoch": 469.0353982300885, "percentage": 66.84, "elapsed_time": "3:12:13", "remaining_time": "1:35:22", "throughput": 1316.66, "total_tokens": 15186016} {"current_steps": 26740, "total_steps": 40000, "loss": 0.0, "lr": 1.2377204106006585e-05, "epoch": 469.12389380530976, "percentage": 66.85, "elapsed_time": "3:12:15", "remaining_time": "1:35:20", "throughput": 1316.67, "total_tokens": 15188768} {"current_steps": 26745, "total_steps": 40000, "loss": 0.0, "lr": 1.2368730918824891e-05, "epoch": 469.21238938053096, "percentage": 66.86, "elapsed_time": "3:12:17", "remaining_time": "1:35:18", "throughput": 1316.7, "total_tokens": 15191872} {"current_steps": 26750, "total_steps": 40000, "loss": 0.0, "lr": 1.236025967954362e-05, "epoch": 469.3008849557522, "percentage": 66.88, "elapsed_time": "3:12:19", "remaining_time": "1:35:16", "throughput": 1316.7, "total_tokens": 15194592} {"current_steps": 26755, "total_steps": 40000, "loss": 0.0, "lr": 1.2351790389469153e-05, "epoch": 469.3893805309734, "percentage": 66.89, "elapsed_time": "3:12:21", "remaining_time": "1:35:13", "throughput": 1316.73, "total_tokens": 15197680} {"current_steps": 26760, "total_steps": 40000, "loss": 0.0, "lr": 1.234332304990755e-05, "epoch": 469.4778761061947, "percentage": 66.9, "elapsed_time": "3:12:24", "remaining_time": "1:35:11", "throughput": 1316.74, "total_tokens": 15200560} {"current_steps": 26765, "total_steps": 40000, "loss": 0.0, "lr": 1.2334857662164593e-05, "epoch": 469.56637168141594, "percentage": 66.91, "elapsed_time": "3:12:26", "remaining_time": "1:35:09", "throughput": 1316.73, "total_tokens": 15203216} {"current_steps": 26770, "total_steps": 40000, "loss": 0.0, "lr": 1.2326394227545743e-05, "epoch": 469.65486725663715, "percentage": 66.92, "elapsed_time": "3:12:28", "remaining_time": "1:35:07", "throughput": 1316.73, "total_tokens": 15205920} {"current_steps": 26775, "total_steps": 40000, "loss": 0.0, "lr": 1.2317932747356162e-05, "epoch": 469.7433628318584, "percentage": 66.94, "elapsed_time": "3:12:30", "remaining_time": "1:35:05", "throughput": 1316.75, "total_tokens": 15208880} {"current_steps": 26780, "total_steps": 40000, "loss": 0.0, "lr": 1.2309473222900726e-05, "epoch": 469.83185840707966, "percentage": 66.95, "elapsed_time": "3:12:32", "remaining_time": "1:35:02", "throughput": 1316.78, "total_tokens": 15211968} {"current_steps": 26785, "total_steps": 40000, "loss": 0.0, "lr": 1.2301015655484006e-05, "epoch": 469.92035398230087, "percentage": 66.96, "elapsed_time": "3:12:34", "remaining_time": "1:35:00", "throughput": 1316.82, "total_tokens": 15215120} {"current_steps": 26790, "total_steps": 40000, "loss": 0.0, "lr": 1.2292560046410245e-05, "epoch": 470.0, "percentage": 66.97, "elapsed_time": "3:12:36", "remaining_time": "1:34:58", "throughput": 1316.81, "total_tokens": 15217640} {"current_steps": 26795, "total_steps": 40000, "loss": 0.0, "lr": 1.228410639698343e-05, "epoch": 470.08849557522126, "percentage": 66.99, "elapsed_time": "3:12:38", "remaining_time": "1:34:56", "throughput": 1316.8, "total_tokens": 15220568} {"current_steps": 26800, "total_steps": 40000, "loss": 0.0, "lr": 1.2275654708507195e-05, "epoch": 470.17699115044246, "percentage": 67.0, "elapsed_time": "3:12:40", "remaining_time": "1:34:54", "throughput": 1316.82, "total_tokens": 15223592} {"current_steps": 26800, "total_steps": 40000, "eval_loss": 0.9104436039924622, "epoch": 470.17699115044246, "percentage": 67.0, "elapsed_time": "3:12:41", "remaining_time": "1:34:54", "throughput": 1316.7, "total_tokens": 15223592} {"current_steps": 26805, "total_steps": 40000, "loss": 0.0, "lr": 1.2267204982284908e-05, "epoch": 470.2654867256637, "percentage": 67.01, "elapsed_time": "3:12:45", "remaining_time": "1:34:53", "throughput": 1316.55, "total_tokens": 15226888} {"current_steps": 26810, "total_steps": 40000, "loss": 0.0, "lr": 1.2258757219619635e-05, "epoch": 470.353982300885, "percentage": 67.03, "elapsed_time": "3:12:47", "remaining_time": "1:34:51", "throughput": 1316.54, "total_tokens": 15229496} {"current_steps": 26815, "total_steps": 40000, "loss": 0.0, "lr": 1.2250311421814104e-05, "epoch": 470.4424778761062, "percentage": 67.04, "elapsed_time": "3:12:49", "remaining_time": "1:34:48", "throughput": 1316.53, "total_tokens": 15232088} {"current_steps": 26820, "total_steps": 40000, "loss": 0.0, "lr": 1.2241867590170772e-05, "epoch": 470.53097345132744, "percentage": 67.05, "elapsed_time": "3:12:51", "remaining_time": "1:34:46", "throughput": 1316.59, "total_tokens": 15235576} {"current_steps": 26825, "total_steps": 40000, "loss": 0.0, "lr": 1.2233425725991799e-05, "epoch": 470.6194690265487, "percentage": 67.06, "elapsed_time": "3:12:54", "remaining_time": "1:34:44", "throughput": 1316.58, "total_tokens": 15238120} {"current_steps": 26830, "total_steps": 40000, "loss": 0.0, "lr": 1.2224985830579003e-05, "epoch": 470.7079646017699, "percentage": 67.07, "elapsed_time": "3:12:56", "remaining_time": "1:34:42", "throughput": 1316.6, "total_tokens": 15241112} {"current_steps": 26835, "total_steps": 40000, "loss": 0.0, "lr": 1.2216547905233944e-05, "epoch": 470.79646017699116, "percentage": 67.09, "elapsed_time": "3:12:58", "remaining_time": "1:34:40", "throughput": 1316.59, "total_tokens": 15243688} {"current_steps": 26840, "total_steps": 40000, "loss": 0.0, "lr": 1.2208111951257842e-05, "epoch": 470.88495575221236, "percentage": 67.1, "elapsed_time": "3:13:00", "remaining_time": "1:34:37", "throughput": 1316.59, "total_tokens": 15246424} {"current_steps": 26845, "total_steps": 40000, "loss": 0.0, "lr": 1.2199677969951622e-05, "epoch": 470.9734513274336, "percentage": 67.11, "elapsed_time": "3:13:02", "remaining_time": "1:34:35", "throughput": 1316.6, "total_tokens": 15249320} {"current_steps": 26850, "total_steps": 40000, "loss": 0.0, "lr": 1.2191245962615927e-05, "epoch": 471.05309734513276, "percentage": 67.12, "elapsed_time": "3:13:04", "remaining_time": "1:34:33", "throughput": 1316.52, "total_tokens": 15251360} {"current_steps": 26855, "total_steps": 40000, "loss": 0.0, "lr": 1.218281593055106e-05, "epoch": 471.14159292035396, "percentage": 67.14, "elapsed_time": "3:13:06", "remaining_time": "1:34:31", "throughput": 1316.53, "total_tokens": 15254256} {"current_steps": 26860, "total_steps": 40000, "loss": 0.0, "lr": 1.217438787505705e-05, "epoch": 471.2300884955752, "percentage": 67.15, "elapsed_time": "3:13:08", "remaining_time": "1:34:29", "throughput": 1316.57, "total_tokens": 15257424} {"current_steps": 26865, "total_steps": 40000, "loss": 0.0, "lr": 1.2165961797433615e-05, "epoch": 471.3185840707965, "percentage": 67.16, "elapsed_time": "3:13:10", "remaining_time": "1:34:27", "throughput": 1316.6, "total_tokens": 15260464} {"current_steps": 26870, "total_steps": 40000, "loss": 0.0, "lr": 1.215753769898014e-05, "epoch": 471.4070796460177, "percentage": 67.17, "elapsed_time": "3:13:12", "remaining_time": "1:34:24", "throughput": 1316.65, "total_tokens": 15263712} {"current_steps": 26875, "total_steps": 40000, "loss": 0.0, "lr": 1.2149115580995755e-05, "epoch": 471.49557522123894, "percentage": 67.19, "elapsed_time": "3:13:14", "remaining_time": "1:34:22", "throughput": 1316.63, "total_tokens": 15266256} {"current_steps": 26880, "total_steps": 40000, "loss": 0.0, "lr": 1.2140695444779227e-05, "epoch": 471.5840707964602, "percentage": 67.2, "elapsed_time": "3:13:17", "remaining_time": "1:34:20", "throughput": 1316.66, "total_tokens": 15269312} {"current_steps": 26885, "total_steps": 40000, "loss": 0.0, "lr": 1.2132277291629066e-05, "epoch": 471.6725663716814, "percentage": 67.21, "elapsed_time": "3:13:19", "remaining_time": "1:34:18", "throughput": 1316.66, "total_tokens": 15272032} {"current_steps": 26890, "total_steps": 40000, "loss": 0.0, "lr": 1.2123861122843458e-05, "epoch": 471.76106194690266, "percentage": 67.22, "elapsed_time": "3:13:21", "remaining_time": "1:34:16", "throughput": 1316.67, "total_tokens": 15274912} {"current_steps": 26895, "total_steps": 40000, "loss": 0.0, "lr": 1.2115446939720271e-05, "epoch": 471.8495575221239, "percentage": 67.24, "elapsed_time": "3:13:23", "remaining_time": "1:34:13", "throughput": 1316.7, "total_tokens": 15277952} {"current_steps": 26900, "total_steps": 40000, "loss": 0.0, "lr": 1.210703474355708e-05, "epoch": 471.9380530973451, "percentage": 67.25, "elapsed_time": "3:13:25", "remaining_time": "1:34:11", "throughput": 1316.68, "total_tokens": 15280512} {"current_steps": 26905, "total_steps": 40000, "loss": 0.0, "lr": 1.2098624535651164e-05, "epoch": 472.01769911504425, "percentage": 67.26, "elapsed_time": "3:13:27", "remaining_time": "1:34:09", "throughput": 1316.63, "total_tokens": 15282872} {"current_steps": 26910, "total_steps": 40000, "loss": 0.0, "lr": 1.2090216317299477e-05, "epoch": 472.1061946902655, "percentage": 67.27, "elapsed_time": "3:13:29", "remaining_time": "1:34:07", "throughput": 1316.7, "total_tokens": 15286456} {"current_steps": 26915, "total_steps": 40000, "loss": 0.0, "lr": 1.2081810089798668e-05, "epoch": 472.1946902654867, "percentage": 67.29, "elapsed_time": "3:13:31", "remaining_time": "1:34:05", "throughput": 1316.72, "total_tokens": 15289368} {"current_steps": 26920, "total_steps": 40000, "loss": 0.0, "lr": 1.2073405854445072e-05, "epoch": 472.283185840708, "percentage": 67.3, "elapsed_time": "3:13:33", "remaining_time": "1:34:02", "throughput": 1316.75, "total_tokens": 15292488} {"current_steps": 26925, "total_steps": 40000, "loss": 0.0, "lr": 1.206500361253474e-05, "epoch": 472.37168141592923, "percentage": 67.31, "elapsed_time": "3:13:35", "remaining_time": "1:34:00", "throughput": 1316.73, "total_tokens": 15294952} {"current_steps": 26930, "total_steps": 40000, "loss": 0.0, "lr": 1.2056603365363409e-05, "epoch": 472.46017699115043, "percentage": 67.33, "elapsed_time": "3:13:37", "remaining_time": "1:33:58", "throughput": 1316.75, "total_tokens": 15297928} {"current_steps": 26935, "total_steps": 40000, "loss": 0.0, "lr": 1.2048205114226487e-05, "epoch": 472.5486725663717, "percentage": 67.34, "elapsed_time": "3:13:40", "remaining_time": "1:33:56", "throughput": 1316.76, "total_tokens": 15300760} {"current_steps": 26940, "total_steps": 40000, "loss": 0.0, "lr": 1.2039808860419102e-05, "epoch": 472.6371681415929, "percentage": 67.35, "elapsed_time": "3:13:42", "remaining_time": "1:33:54", "throughput": 1316.77, "total_tokens": 15303640} {"current_steps": 26945, "total_steps": 40000, "loss": 0.0, "lr": 1.2031414605236066e-05, "epoch": 472.72566371681415, "percentage": 67.36, "elapsed_time": "3:13:44", "remaining_time": "1:33:51", "throughput": 1316.78, "total_tokens": 15306424} {"current_steps": 26950, "total_steps": 40000, "loss": 0.0, "lr": 1.2023022349971862e-05, "epoch": 472.8141592920354, "percentage": 67.38, "elapsed_time": "3:13:46", "remaining_time": "1:33:49", "throughput": 1316.81, "total_tokens": 15309560} {"current_steps": 26955, "total_steps": 40000, "loss": 0.0, "lr": 1.20146320959207e-05, "epoch": 472.9026548672566, "percentage": 67.39, "elapsed_time": "3:13:48", "remaining_time": "1:33:47", "throughput": 1316.82, "total_tokens": 15312440} {"current_steps": 26960, "total_steps": 40000, "loss": 0.0, "lr": 1.2006243844376445e-05, "epoch": 472.9911504424779, "percentage": 67.4, "elapsed_time": "3:13:50", "remaining_time": "1:33:45", "throughput": 1316.8, "total_tokens": 15314872} {"current_steps": 26965, "total_steps": 40000, "loss": 0.0, "lr": 1.1997857596632678e-05, "epoch": 473.070796460177, "percentage": 67.41, "elapsed_time": "3:13:52", "remaining_time": "1:33:43", "throughput": 1316.79, "total_tokens": 15317736} {"current_steps": 26970, "total_steps": 40000, "loss": 0.0, "lr": 1.1989473353982672e-05, "epoch": 473.1592920353982, "percentage": 67.42, "elapsed_time": "3:13:54", "remaining_time": "1:33:41", "throughput": 1316.83, "total_tokens": 15320888} {"current_steps": 26975, "total_steps": 40000, "loss": 0.0, "lr": 1.198109111771937e-05, "epoch": 473.24778761061947, "percentage": 67.44, "elapsed_time": "3:13:56", "remaining_time": "1:33:38", "throughput": 1316.85, "total_tokens": 15323944} {"current_steps": 26980, "total_steps": 40000, "loss": 0.0, "lr": 1.197271088913543e-05, "epoch": 473.3362831858407, "percentage": 67.45, "elapsed_time": "3:13:58", "remaining_time": "1:33:36", "throughput": 1316.88, "total_tokens": 15327048} {"current_steps": 26985, "total_steps": 40000, "loss": 0.0, "lr": 1.1964332669523182e-05, "epoch": 473.42477876106193, "percentage": 67.46, "elapsed_time": "3:14:00", "remaining_time": "1:33:34", "throughput": 1316.88, "total_tokens": 15329816} {"current_steps": 26990, "total_steps": 40000, "loss": 0.0, "lr": 1.1955956460174645e-05, "epoch": 473.5132743362832, "percentage": 67.47, "elapsed_time": "3:14:03", "remaining_time": "1:33:32", "throughput": 1316.9, "total_tokens": 15332728} {"current_steps": 26995, "total_steps": 40000, "loss": 0.0, "lr": 1.1947582262381552e-05, "epoch": 473.60176991150445, "percentage": 67.49, "elapsed_time": "3:14:05", "remaining_time": "1:33:30", "throughput": 1316.88, "total_tokens": 15335192} {"current_steps": 27000, "total_steps": 40000, "loss": 0.0, "lr": 1.1939210077435293e-05, "epoch": 473.69026548672565, "percentage": 67.5, "elapsed_time": "3:14:07", "remaining_time": "1:33:27", "throughput": 1316.89, "total_tokens": 15338072} {"current_steps": 27000, "total_steps": 40000, "eval_loss": 0.9008995890617371, "epoch": 473.69026548672565, "percentage": 67.5, "elapsed_time": "3:14:08", "remaining_time": "1:33:28", "throughput": 1316.77, "total_tokens": 15338072} {"current_steps": 27005, "total_steps": 40000, "loss": 0.0, "lr": 1.193083990662697e-05, "epoch": 473.7787610619469, "percentage": 67.51, "elapsed_time": "3:14:12", "remaining_time": "1:33:27", "throughput": 1316.6, "total_tokens": 15341128} {"current_steps": 27010, "total_steps": 40000, "loss": 0.0, "lr": 1.192247175124738e-05, "epoch": 473.86725663716817, "percentage": 67.53, "elapsed_time": "3:14:14", "remaining_time": "1:33:24", "throughput": 1316.58, "total_tokens": 15343592} {"current_steps": 27015, "total_steps": 40000, "loss": 0.0, "lr": 1.191410561258698e-05, "epoch": 473.95575221238937, "percentage": 67.54, "elapsed_time": "3:14:16", "remaining_time": "1:33:22", "throughput": 1316.58, "total_tokens": 15346248} {"current_steps": 27020, "total_steps": 40000, "loss": 0.0, "lr": 1.1905741491935944e-05, "epoch": 474.0353982300885, "percentage": 67.55, "elapsed_time": "3:14:18", "remaining_time": "1:33:20", "throughput": 1316.51, "total_tokens": 15348456} {"current_steps": 27025, "total_steps": 40000, "loss": 0.0, "lr": 1.1897379390584129e-05, "epoch": 474.12389380530976, "percentage": 67.56, "elapsed_time": "3:14:20", "remaining_time": "1:33:18", "throughput": 1316.56, "total_tokens": 15351736} {"current_steps": 27030, "total_steps": 40000, "loss": 0.0, "lr": 1.1889019309821062e-05, "epoch": 474.21238938053096, "percentage": 67.58, "elapsed_time": "3:14:22", "remaining_time": "1:33:16", "throughput": 1316.59, "total_tokens": 15354824} {"current_steps": 27035, "total_steps": 40000, "loss": 0.0, "lr": 1.188066125093599e-05, "epoch": 474.3008849557522, "percentage": 67.59, "elapsed_time": "3:14:24", "remaining_time": "1:33:13", "throughput": 1316.58, "total_tokens": 15357480} {"current_steps": 27040, "total_steps": 40000, "loss": 0.0, "lr": 1.1872305215217811e-05, "epoch": 474.3893805309734, "percentage": 67.6, "elapsed_time": "3:14:26", "remaining_time": "1:33:11", "throughput": 1316.62, "total_tokens": 15360664} {"current_steps": 27045, "total_steps": 40000, "loss": 0.0, "lr": 1.186395120395514e-05, "epoch": 474.4778761061947, "percentage": 67.61, "elapsed_time": "3:14:28", "remaining_time": "1:33:09", "throughput": 1316.62, "total_tokens": 15363368} {"current_steps": 27050, "total_steps": 40000, "loss": 0.0, "lr": 1.1855599218436283e-05, "epoch": 474.56637168141594, "percentage": 67.62, "elapsed_time": "3:14:30", "remaining_time": "1:33:07", "throughput": 1316.61, "total_tokens": 15366024} {"current_steps": 27055, "total_steps": 40000, "loss": 0.0, "lr": 1.1847249259949209e-05, "epoch": 474.65486725663715, "percentage": 67.64, "elapsed_time": "3:14:32", "remaining_time": "1:33:05", "throughput": 1316.63, "total_tokens": 15368904} {"current_steps": 27060, "total_steps": 40000, "loss": 0.0, "lr": 1.1838901329781574e-05, "epoch": 474.7433628318584, "percentage": 67.65, "elapsed_time": "3:14:35", "remaining_time": "1:33:02", "throughput": 1316.63, "total_tokens": 15371720} {"current_steps": 27065, "total_steps": 40000, "loss": 0.0, "lr": 1.1830555429220758e-05, "epoch": 474.83185840707966, "percentage": 67.66, "elapsed_time": "3:14:37", "remaining_time": "1:33:00", "throughput": 1316.68, "total_tokens": 15375016} {"current_steps": 27070, "total_steps": 40000, "loss": 0.0, "lr": 1.1822211559553784e-05, "epoch": 474.92035398230087, "percentage": 67.67, "elapsed_time": "3:14:39", "remaining_time": "1:32:58", "throughput": 1316.69, "total_tokens": 15377832} {"current_steps": 27075, "total_steps": 40000, "loss": 0.0, "lr": 1.18138697220674e-05, "epoch": 475.0, "percentage": 67.69, "elapsed_time": "3:14:41", "remaining_time": "1:32:56", "throughput": 1316.64, "total_tokens": 15379912} {"current_steps": 27080, "total_steps": 40000, "loss": 0.0, "lr": 1.1805529918048e-05, "epoch": 475.08849557522126, "percentage": 67.7, "elapsed_time": "3:14:43", "remaining_time": "1:32:54", "throughput": 1316.6, "total_tokens": 15382568} {"current_steps": 27085, "total_steps": 40000, "loss": 0.0, "lr": 1.1797192148781702e-05, "epoch": 475.17699115044246, "percentage": 67.71, "elapsed_time": "3:14:45", "remaining_time": "1:32:52", "throughput": 1316.61, "total_tokens": 15385384} {"current_steps": 27090, "total_steps": 40000, "loss": 0.0, "lr": 1.1788856415554297e-05, "epoch": 475.2654867256637, "percentage": 67.73, "elapsed_time": "3:14:47", "remaining_time": "1:32:49", "throughput": 1316.64, "total_tokens": 15388488} {"current_steps": 27095, "total_steps": 40000, "loss": 0.0, "lr": 1.1780522719651249e-05, "epoch": 475.353982300885, "percentage": 67.74, "elapsed_time": "3:14:49", "remaining_time": "1:32:47", "throughput": 1316.67, "total_tokens": 15391576} {"current_steps": 27100, "total_steps": 40000, "loss": 0.0, "lr": 1.1772191062357721e-05, "epoch": 475.4424778761062, "percentage": 67.75, "elapsed_time": "3:14:51", "remaining_time": "1:32:45", "throughput": 1316.65, "total_tokens": 15394008} {"current_steps": 27105, "total_steps": 40000, "loss": 0.0, "lr": 1.1763861444958573e-05, "epoch": 475.53097345132744, "percentage": 67.76, "elapsed_time": "3:14:53", "remaining_time": "1:32:43", "throughput": 1316.64, "total_tokens": 15396680} {"current_steps": 27110, "total_steps": 40000, "loss": 0.0, "lr": 1.1755533868738317e-05, "epoch": 475.6194690265487, "percentage": 67.77, "elapsed_time": "3:14:56", "remaining_time": "1:32:41", "throughput": 1316.65, "total_tokens": 15399592} {"current_steps": 27115, "total_steps": 40000, "loss": 0.0, "lr": 1.1747208334981185e-05, "epoch": 475.7079646017699, "percentage": 67.79, "elapsed_time": "3:14:58", "remaining_time": "1:32:38", "throughput": 1316.71, "total_tokens": 15402920} {"current_steps": 27120, "total_steps": 40000, "loss": 0.0, "lr": 1.1738884844971067e-05, "epoch": 475.79646017699116, "percentage": 67.8, "elapsed_time": "3:15:00", "remaining_time": "1:32:36", "throughput": 1316.73, "total_tokens": 15405896} {"current_steps": 27125, "total_steps": 40000, "loss": 0.0, "lr": 1.1730563399991563e-05, "epoch": 475.88495575221236, "percentage": 67.81, "elapsed_time": "3:15:02", "remaining_time": "1:32:34", "throughput": 1316.75, "total_tokens": 15408936} {"current_steps": 27130, "total_steps": 40000, "loss": 0.0, "lr": 1.1722244001325938e-05, "epoch": 475.9734513274336, "percentage": 67.83, "elapsed_time": "3:15:04", "remaining_time": "1:32:32", "throughput": 1316.76, "total_tokens": 15411768} {"current_steps": 27135, "total_steps": 40000, "loss": 0.0, "lr": 1.1713926650257137e-05, "epoch": 476.05309734513276, "percentage": 67.84, "elapsed_time": "3:15:06", "remaining_time": "1:32:30", "throughput": 1316.72, "total_tokens": 15414264} {"current_steps": 27140, "total_steps": 40000, "loss": 0.0, "lr": 1.170561134806781e-05, "epoch": 476.14159292035396, "percentage": 67.85, "elapsed_time": "3:15:08", "remaining_time": "1:32:28", "throughput": 1316.74, "total_tokens": 15417240} {"current_steps": 27145, "total_steps": 40000, "loss": 0.0, "lr": 1.1697298096040287e-05, "epoch": 476.2300884955752, "percentage": 67.86, "elapsed_time": "3:15:10", "remaining_time": "1:32:25", "throughput": 1316.78, "total_tokens": 15420360} {"current_steps": 27150, "total_steps": 40000, "loss": 0.0, "lr": 1.1688986895456567e-05, "epoch": 476.3185840707965, "percentage": 67.88, "elapsed_time": "3:15:12", "remaining_time": "1:32:23", "throughput": 1316.84, "total_tokens": 15423784} {"current_steps": 27155, "total_steps": 40000, "loss": 0.0, "lr": 1.1680677747598349e-05, "epoch": 476.4070796460177, "percentage": 67.89, "elapsed_time": "3:15:14", "remaining_time": "1:32:21", "throughput": 1316.87, "total_tokens": 15426936} {"current_steps": 27160, "total_steps": 40000, "loss": 0.0, "lr": 1.1672370653746995e-05, "epoch": 476.49557522123894, "percentage": 67.9, "elapsed_time": "3:15:16", "remaining_time": "1:32:19", "throughput": 1316.89, "total_tokens": 15429864} {"current_steps": 27165, "total_steps": 40000, "loss": 0.0, "lr": 1.166406561518357e-05, "epoch": 476.5840707964602, "percentage": 67.91, "elapsed_time": "3:15:18", "remaining_time": "1:32:17", "throughput": 1316.9, "total_tokens": 15432792} {"current_steps": 27170, "total_steps": 40000, "loss": 0.0, "lr": 1.1655762633188826e-05, "epoch": 476.6725663716814, "percentage": 67.92, "elapsed_time": "3:15:21", "remaining_time": "1:32:14", "throughput": 1316.95, "total_tokens": 15436024} {"current_steps": 27175, "total_steps": 40000, "loss": 0.0, "lr": 1.1647461709043172e-05, "epoch": 476.76106194690266, "percentage": 67.94, "elapsed_time": "3:15:23", "remaining_time": "1:32:12", "throughput": 1316.94, "total_tokens": 15438648} {"current_steps": 27180, "total_steps": 40000, "loss": 0.0, "lr": 1.1639162844026722e-05, "epoch": 476.8495575221239, "percentage": 67.95, "elapsed_time": "3:15:25", "remaining_time": "1:32:10", "throughput": 1316.92, "total_tokens": 15441224} {"current_steps": 27185, "total_steps": 40000, "loss": 0.0, "lr": 1.163086603941927e-05, "epoch": 476.9380530973451, "percentage": 67.96, "elapsed_time": "3:15:27", "remaining_time": "1:32:08", "throughput": 1316.9, "total_tokens": 15443704} {"current_steps": 27190, "total_steps": 40000, "loss": 0.0, "lr": 1.1622571296500273e-05, "epoch": 477.01769911504425, "percentage": 67.97, "elapsed_time": "3:15:29", "remaining_time": "1:32:06", "throughput": 1316.82, "total_tokens": 15445760} {"current_steps": 27195, "total_steps": 40000, "loss": 0.0, "lr": 1.1614278616548904e-05, "epoch": 477.1061946902655, "percentage": 67.99, "elapsed_time": "3:15:31", "remaining_time": "1:32:03", "throughput": 1316.84, "total_tokens": 15448704} {"current_steps": 27200, "total_steps": 40000, "loss": 0.0, "lr": 1.1605988000843986e-05, "epoch": 477.1946902654867, "percentage": 68.0, "elapsed_time": "3:15:33", "remaining_time": "1:32:01", "throughput": 1316.83, "total_tokens": 15451312} {"current_steps": 27200, "total_steps": 40000, "eval_loss": 0.9213019013404846, "epoch": 477.1946902654867, "percentage": 68.0, "elapsed_time": "3:15:34", "remaining_time": "1:32:02", "throughput": 1316.71, "total_tokens": 15451312} {"current_steps": 27205, "total_steps": 40000, "loss": 0.0, "lr": 1.1597699450664028e-05, "epoch": 477.283185840708, "percentage": 68.01, "elapsed_time": "3:15:38", "remaining_time": "1:32:00", "throughput": 1316.53, "total_tokens": 15454432} {"current_steps": 27210, "total_steps": 40000, "loss": 0.0, "lr": 1.1589412967287252e-05, "epoch": 477.37168141592923, "percentage": 68.03, "elapsed_time": "3:15:40", "remaining_time": "1:31:58", "throughput": 1316.51, "total_tokens": 15456992} {"current_steps": 27215, "total_steps": 40000, "loss": 0.0, "lr": 1.1581128551991514e-05, "epoch": 477.46017699115043, "percentage": 68.04, "elapsed_time": "3:15:42", "remaining_time": "1:31:56", "throughput": 1316.53, "total_tokens": 15460000} {"current_steps": 27220, "total_steps": 40000, "loss": 0.0, "lr": 1.1572846206054383e-05, "epoch": 477.5486725663717, "percentage": 68.05, "elapsed_time": "3:15:45", "remaining_time": "1:31:54", "throughput": 1316.53, "total_tokens": 15462736} {"current_steps": 27225, "total_steps": 40000, "loss": 0.0, "lr": 1.1564565930753113e-05, "epoch": 477.6371681415929, "percentage": 68.06, "elapsed_time": "3:15:47", "remaining_time": "1:31:52", "throughput": 1316.51, "total_tokens": 15465216} {"current_steps": 27230, "total_steps": 40000, "loss": 0.0, "lr": 1.1556287727364606e-05, "epoch": 477.72566371681415, "percentage": 68.08, "elapsed_time": "3:15:49", "remaining_time": "1:31:49", "throughput": 1316.55, "total_tokens": 15468384} {"current_steps": 27235, "total_steps": 40000, "loss": 0.0, "lr": 1.1548011597165489e-05, "epoch": 477.8141592920354, "percentage": 68.09, "elapsed_time": "3:15:51", "remaining_time": "1:31:47", "throughput": 1316.6, "total_tokens": 15471680} {"current_steps": 27240, "total_steps": 40000, "loss": 0.0, "lr": 1.1539737541432019e-05, "epoch": 477.9026548672566, "percentage": 68.1, "elapsed_time": "3:15:53", "remaining_time": "1:31:45", "throughput": 1316.59, "total_tokens": 15474256} {"current_steps": 27245, "total_steps": 40000, "loss": 0.0, "lr": 1.1531465561440174e-05, "epoch": 477.9911504424779, "percentage": 68.11, "elapsed_time": "3:15:55", "remaining_time": "1:31:43", "throughput": 1316.61, "total_tokens": 15477216} {"current_steps": 27250, "total_steps": 40000, "loss": 0.0, "lr": 1.1523195658465605e-05, "epoch": 478.070796460177, "percentage": 68.12, "elapsed_time": "3:15:57", "remaining_time": "1:31:41", "throughput": 1316.56, "total_tokens": 15479632} {"current_steps": 27255, "total_steps": 40000, "loss": 0.0, "lr": 1.1514927833783618e-05, "epoch": 478.1592920353982, "percentage": 68.14, "elapsed_time": "3:15:59", "remaining_time": "1:31:39", "throughput": 1316.56, "total_tokens": 15482416} {"current_steps": 27260, "total_steps": 40000, "loss": 0.0, "lr": 1.150666208866922e-05, "epoch": 478.24778761061947, "percentage": 68.15, "elapsed_time": "3:16:01", "remaining_time": "1:31:36", "throughput": 1316.57, "total_tokens": 15485280} {"current_steps": 27265, "total_steps": 40000, "loss": 0.0, "lr": 1.1498398424397106e-05, "epoch": 478.3362831858407, "percentage": 68.16, "elapsed_time": "3:16:03", "remaining_time": "1:31:34", "throughput": 1316.55, "total_tokens": 15487776} {"current_steps": 27270, "total_steps": 40000, "loss": 0.0, "lr": 1.1490136842241628e-05, "epoch": 478.42477876106193, "percentage": 68.17, "elapsed_time": "3:16:05", "remaining_time": "1:31:32", "throughput": 1316.59, "total_tokens": 15490944} {"current_steps": 27275, "total_steps": 40000, "loss": 0.0, "lr": 1.1481877343476813e-05, "epoch": 478.5132743362832, "percentage": 68.19, "elapsed_time": "3:16:08", "remaining_time": "1:31:30", "throughput": 1316.58, "total_tokens": 15493584} {"current_steps": 27280, "total_steps": 40000, "loss": 0.0, "lr": 1.14736199293764e-05, "epoch": 478.60176991150445, "percentage": 68.2, "elapsed_time": "3:16:10", "remaining_time": "1:31:28", "throughput": 1316.61, "total_tokens": 15496672} {"current_steps": 27285, "total_steps": 40000, "loss": 0.0, "lr": 1.1465364601213771e-05, "epoch": 478.69026548672565, "percentage": 68.21, "elapsed_time": "3:16:12", "remaining_time": "1:31:25", "throughput": 1316.64, "total_tokens": 15499664} {"current_steps": 27290, "total_steps": 40000, "loss": 0.0, "lr": 1.1457111360262012e-05, "epoch": 478.7787610619469, "percentage": 68.23, "elapsed_time": "3:16:14", "remaining_time": "1:31:23", "throughput": 1316.67, "total_tokens": 15502736} {"current_steps": 27295, "total_steps": 40000, "loss": 0.0, "lr": 1.1448860207793869e-05, "epoch": 478.86725663716817, "percentage": 68.24, "elapsed_time": "3:16:16", "remaining_time": "1:31:21", "throughput": 1316.65, "total_tokens": 15505280} {"current_steps": 27300, "total_steps": 40000, "loss": 0.0, "lr": 1.144061114508177e-05, "epoch": 478.95575221238937, "percentage": 68.25, "elapsed_time": "3:16:18", "remaining_time": "1:31:19", "throughput": 1316.67, "total_tokens": 15508256} {"current_steps": 27305, "total_steps": 40000, "loss": 0.0, "lr": 1.1432364173397842e-05, "epoch": 479.0353982300885, "percentage": 68.26, "elapsed_time": "3:16:20", "remaining_time": "1:31:17", "throughput": 1316.65, "total_tokens": 15510952} {"current_steps": 27310, "total_steps": 40000, "loss": 0.0, "lr": 1.1424119294013852e-05, "epoch": 479.12389380530976, "percentage": 68.27, "elapsed_time": "3:16:22", "remaining_time": "1:31:15", "throughput": 1316.65, "total_tokens": 15513672} {"current_steps": 27315, "total_steps": 40000, "loss": 0.0, "lr": 1.1415876508201279e-05, "epoch": 479.21238938053096, "percentage": 68.29, "elapsed_time": "3:16:24", "remaining_time": "1:31:12", "throughput": 1316.65, "total_tokens": 15516376} {"current_steps": 27320, "total_steps": 40000, "loss": 0.0, "lr": 1.140763581723125e-05, "epoch": 479.3008849557522, "percentage": 68.3, "elapsed_time": "3:16:26", "remaining_time": "1:31:10", "throughput": 1316.65, "total_tokens": 15519176} {"current_steps": 27325, "total_steps": 40000, "loss": 0.0, "lr": 1.1399397222374588e-05, "epoch": 479.3893805309734, "percentage": 68.31, "elapsed_time": "3:16:28", "remaining_time": "1:31:08", "throughput": 1316.71, "total_tokens": 15522648} {"current_steps": 27330, "total_steps": 40000, "loss": 0.0, "lr": 1.1391160724901804e-05, "epoch": 479.4778761061947, "percentage": 68.33, "elapsed_time": "3:16:31", "remaining_time": "1:31:06", "throughput": 1316.74, "total_tokens": 15525672} {"current_steps": 27335, "total_steps": 40000, "loss": 0.0, "lr": 1.138292632608304e-05, "epoch": 479.56637168141594, "percentage": 68.34, "elapsed_time": "3:16:33", "remaining_time": "1:31:04", "throughput": 1316.76, "total_tokens": 15528648} {"current_steps": 27340, "total_steps": 40000, "loss": 0.0, "lr": 1.1374694027188174e-05, "epoch": 479.65486725663715, "percentage": 68.35, "elapsed_time": "3:16:35", "remaining_time": "1:31:01", "throughput": 1316.76, "total_tokens": 15531416} {"current_steps": 27345, "total_steps": 40000, "loss": 0.0, "lr": 1.1366463829486711e-05, "epoch": 479.7433628318584, "percentage": 68.36, "elapsed_time": "3:16:37", "remaining_time": "1:30:59", "throughput": 1316.75, "total_tokens": 15533992} {"current_steps": 27350, "total_steps": 40000, "loss": 0.0, "lr": 1.1358235734247849e-05, "epoch": 479.83185840707966, "percentage": 68.38, "elapsed_time": "3:16:39", "remaining_time": "1:30:57", "throughput": 1316.74, "total_tokens": 15536600} {"current_steps": 27355, "total_steps": 40000, "loss": 0.0, "lr": 1.1350009742740478e-05, "epoch": 479.92035398230087, "percentage": 68.39, "elapsed_time": "3:16:41", "remaining_time": "1:30:55", "throughput": 1316.8, "total_tokens": 15539992} {"current_steps": 27360, "total_steps": 40000, "loss": 0.0, "lr": 1.134178585623313e-05, "epoch": 480.0, "percentage": 68.4, "elapsed_time": "3:16:43", "remaining_time": "1:30:53", "throughput": 1316.77, "total_tokens": 15542312} {"current_steps": 27365, "total_steps": 40000, "loss": 0.0, "lr": 1.1333564075994047e-05, "epoch": 480.08849557522126, "percentage": 68.41, "elapsed_time": "3:16:45", "remaining_time": "1:30:50", "throughput": 1316.74, "total_tokens": 15545032} {"current_steps": 27370, "total_steps": 40000, "loss": 0.0, "lr": 1.1325344403291133e-05, "epoch": 480.17699115044246, "percentage": 68.42, "elapsed_time": "3:16:47", "remaining_time": "1:30:48", "throughput": 1316.81, "total_tokens": 15548616} {"current_steps": 27375, "total_steps": 40000, "loss": 0.0, "lr": 1.1317126839391951e-05, "epoch": 480.2654867256637, "percentage": 68.44, "elapsed_time": "3:16:49", "remaining_time": "1:30:46", "throughput": 1316.84, "total_tokens": 15551624} {"current_steps": 27380, "total_steps": 40000, "loss": 0.0, "lr": 1.1308911385563766e-05, "epoch": 480.353982300885, "percentage": 68.45, "elapsed_time": "3:16:51", "remaining_time": "1:30:44", "throughput": 1316.89, "total_tokens": 15555016} {"current_steps": 27385, "total_steps": 40000, "loss": 0.0, "lr": 1.1300698043073494e-05, "epoch": 480.4424778761062, "percentage": 68.46, "elapsed_time": "3:16:53", "remaining_time": "1:30:42", "throughput": 1316.88, "total_tokens": 15557608} {"current_steps": 27390, "total_steps": 40000, "loss": 0.0, "lr": 1.1292486813187736e-05, "epoch": 480.53097345132744, "percentage": 68.47, "elapsed_time": "3:16:56", "remaining_time": "1:30:39", "throughput": 1316.88, "total_tokens": 15560360} {"current_steps": 27395, "total_steps": 40000, "loss": 0.0, "lr": 1.1284277697172782e-05, "epoch": 480.6194690265487, "percentage": 68.49, "elapsed_time": "3:16:58", "remaining_time": "1:30:37", "throughput": 1316.87, "total_tokens": 15562952} {"current_steps": 27400, "total_steps": 40000, "loss": 0.0, "lr": 1.127607069629456e-05, "epoch": 480.7079646017699, "percentage": 68.5, "elapsed_time": "3:17:00", "remaining_time": "1:30:35", "throughput": 1316.88, "total_tokens": 15565784} {"current_steps": 27400, "total_steps": 40000, "eval_loss": 0.9219540953636169, "epoch": 480.7079646017699, "percentage": 68.5, "elapsed_time": "3:17:01", "remaining_time": "1:30:36", "throughput": 1316.76, "total_tokens": 15565784} {"current_steps": 27405, "total_steps": 40000, "loss": 0.0, "lr": 1.1267865811818701e-05, "epoch": 480.79646017699116, "percentage": 68.51, "elapsed_time": "3:17:05", "remaining_time": "1:30:34", "throughput": 1316.48, "total_tokens": 15568328} {"current_steps": 27410, "total_steps": 40000, "loss": 0.0, "lr": 1.1259663045010513e-05, "epoch": 480.88495575221236, "percentage": 68.53, "elapsed_time": "3:17:07", "remaining_time": "1:30:32", "throughput": 1316.5, "total_tokens": 15571400} {"current_steps": 27415, "total_steps": 40000, "loss": 0.0, "lr": 1.1251462397134957e-05, "epoch": 480.9734513274336, "percentage": 68.54, "elapsed_time": "3:17:09", "remaining_time": "1:30:30", "throughput": 1316.5, "total_tokens": 15574088} {"current_steps": 27420, "total_steps": 40000, "loss": 0.0, "lr": 1.1243263869456664e-05, "epoch": 481.05309734513276, "percentage": 68.55, "elapsed_time": "3:17:12", "remaining_time": "1:30:28", "throughput": 1316.5, "total_tokens": 15576984} {"current_steps": 27425, "total_steps": 40000, "loss": 0.0, "lr": 1.1235067463239967e-05, "epoch": 481.14159292035396, "percentage": 68.56, "elapsed_time": "3:17:14", "remaining_time": "1:30:26", "throughput": 1316.48, "total_tokens": 15579496} {"current_steps": 27430, "total_steps": 40000, "loss": 0.0, "lr": 1.122687317974884e-05, "epoch": 481.2300884955752, "percentage": 68.58, "elapsed_time": "3:17:16", "remaining_time": "1:30:24", "throughput": 1316.49, "total_tokens": 15582376} {"current_steps": 27435, "total_steps": 40000, "loss": 0.0, "lr": 1.1218681020246963e-05, "epoch": 481.3185840707965, "percentage": 68.59, "elapsed_time": "3:17:18", "remaining_time": "1:30:21", "throughput": 1316.52, "total_tokens": 15585416} {"current_steps": 27440, "total_steps": 40000, "loss": 0.0, "lr": 1.1210490985997652e-05, "epoch": 481.4070796460177, "percentage": 68.6, "elapsed_time": "3:17:20", "remaining_time": "1:30:19", "throughput": 1316.52, "total_tokens": 15588184} {"current_steps": 27445, "total_steps": 40000, "loss": 0.0, "lr": 1.1202303078263917e-05, "epoch": 481.49557522123894, "percentage": 68.61, "elapsed_time": "3:17:22", "remaining_time": "1:30:17", "throughput": 1316.53, "total_tokens": 15590984} {"current_steps": 27450, "total_steps": 40000, "loss": 0.0, "lr": 1.1194117298308451e-05, "epoch": 481.5840707964602, "percentage": 68.62, "elapsed_time": "3:17:24", "remaining_time": "1:30:15", "throughput": 1316.52, "total_tokens": 15593608} {"current_steps": 27455, "total_steps": 40000, "loss": 0.0, "lr": 1.1185933647393585e-05, "epoch": 481.6725663716814, "percentage": 68.64, "elapsed_time": "3:17:26", "remaining_time": "1:30:13", "throughput": 1316.55, "total_tokens": 15596728} {"current_steps": 27460, "total_steps": 40000, "loss": 0.0, "lr": 1.1177752126781354e-05, "epoch": 481.76106194690266, "percentage": 68.65, "elapsed_time": "3:17:28", "remaining_time": "1:30:10", "throughput": 1316.57, "total_tokens": 15599736} {"current_steps": 27465, "total_steps": 40000, "loss": 0.0, "lr": 1.1169572737733441e-05, "epoch": 481.8495575221239, "percentage": 68.66, "elapsed_time": "3:17:30", "remaining_time": "1:30:08", "throughput": 1316.58, "total_tokens": 15602520} {"current_steps": 27470, "total_steps": 40000, "loss": 0.0, "lr": 1.1161395481511216e-05, "epoch": 481.9380530973451, "percentage": 68.67, "elapsed_time": "3:17:32", "remaining_time": "1:30:06", "throughput": 1316.58, "total_tokens": 15605320} {"current_steps": 27475, "total_steps": 40000, "loss": 0.0, "lr": 1.1153220359375722e-05, "epoch": 482.01769911504425, "percentage": 68.69, "elapsed_time": "3:17:35", "remaining_time": "1:30:04", "throughput": 1316.54, "total_tokens": 15607816} {"current_steps": 27480, "total_steps": 40000, "loss": 0.0, "lr": 1.114504737258765e-05, "epoch": 482.1061946902655, "percentage": 68.7, "elapsed_time": "3:17:37", "remaining_time": "1:30:02", "throughput": 1316.54, "total_tokens": 15610568} {"current_steps": 27485, "total_steps": 40000, "loss": 0.0, "lr": 1.1136876522407393e-05, "epoch": 482.1946902654867, "percentage": 68.71, "elapsed_time": "3:17:39", "remaining_time": "1:30:00", "throughput": 1316.56, "total_tokens": 15613480} {"current_steps": 27490, "total_steps": 40000, "loss": 0.0, "lr": 1.1128707810094985e-05, "epoch": 482.283185840708, "percentage": 68.73, "elapsed_time": "3:17:41", "remaining_time": "1:29:57", "throughput": 1316.57, "total_tokens": 15616344} {"current_steps": 27495, "total_steps": 40000, "loss": 0.0, "lr": 1.1120541236910157e-05, "epoch": 482.37168141592923, "percentage": 68.74, "elapsed_time": "3:17:43", "remaining_time": "1:29:55", "throughput": 1316.57, "total_tokens": 15618984} {"current_steps": 27500, "total_steps": 40000, "loss": 0.0, "lr": 1.111237680411229e-05, "epoch": 482.46017699115043, "percentage": 68.75, "elapsed_time": "3:17:45", "remaining_time": "1:29:53", "throughput": 1316.55, "total_tokens": 15621560} {"current_steps": 27505, "total_steps": 40000, "loss": 0.0, "lr": 1.1104214512960433e-05, "epoch": 482.5486725663717, "percentage": 68.76, "elapsed_time": "3:17:47", "remaining_time": "1:29:51", "throughput": 1316.58, "total_tokens": 15624664} {"current_steps": 27510, "total_steps": 40000, "loss": 0.0, "lr": 1.1096054364713327e-05, "epoch": 482.6371681415929, "percentage": 68.77, "elapsed_time": "3:17:49", "remaining_time": "1:29:49", "throughput": 1316.6, "total_tokens": 15627640} {"current_steps": 27515, "total_steps": 40000, "loss": 0.0, "lr": 1.1087896360629371e-05, "epoch": 482.72566371681415, "percentage": 68.79, "elapsed_time": "3:17:51", "remaining_time": "1:29:46", "throughput": 1316.67, "total_tokens": 15631112} {"current_steps": 27520, "total_steps": 40000, "loss": 0.0, "lr": 1.107974050196662e-05, "epoch": 482.8141592920354, "percentage": 68.8, "elapsed_time": "3:17:53", "remaining_time": "1:29:44", "throughput": 1316.67, "total_tokens": 15633832} {"current_steps": 27525, "total_steps": 40000, "loss": 0.0, "lr": 1.1071586789982816e-05, "epoch": 482.9026548672566, "percentage": 68.81, "elapsed_time": "3:17:55", "remaining_time": "1:29:42", "throughput": 1316.68, "total_tokens": 15636792} {"current_steps": 27530, "total_steps": 40000, "loss": 0.0, "lr": 1.1063435225935373e-05, "epoch": 482.9911504424779, "percentage": 68.83, "elapsed_time": "3:17:57", "remaining_time": "1:29:40", "throughput": 1316.69, "total_tokens": 15639560} {"current_steps": 27535, "total_steps": 40000, "loss": 0.0, "lr": 1.1055285811081348e-05, "epoch": 483.070796460177, "percentage": 68.84, "elapsed_time": "3:18:00", "remaining_time": "1:29:38", "throughput": 1316.64, "total_tokens": 15642000} {"current_steps": 27540, "total_steps": 40000, "loss": 0.0, "lr": 1.1047138546677499e-05, "epoch": 483.1592920353982, "percentage": 68.85, "elapsed_time": "3:18:02", "remaining_time": "1:29:35", "throughput": 1316.67, "total_tokens": 15645056} {"current_steps": 27545, "total_steps": 40000, "loss": 0.0, "lr": 1.1038993433980219e-05, "epoch": 483.24778761061947, "percentage": 68.86, "elapsed_time": "3:18:04", "remaining_time": "1:29:33", "throughput": 1316.69, "total_tokens": 15648016} {"current_steps": 27550, "total_steps": 40000, "loss": 0.0, "lr": 1.1030850474245597e-05, "epoch": 483.3362831858407, "percentage": 68.88, "elapsed_time": "3:18:06", "remaining_time": "1:29:31", "throughput": 1316.67, "total_tokens": 15650528} {"current_steps": 27555, "total_steps": 40000, "loss": 0.0, "lr": 1.102270966872939e-05, "epoch": 483.42477876106193, "percentage": 68.89, "elapsed_time": "3:18:08", "remaining_time": "1:29:29", "throughput": 1316.72, "total_tokens": 15653824} {"current_steps": 27560, "total_steps": 40000, "loss": 0.0, "lr": 1.1014571018687e-05, "epoch": 483.5132743362832, "percentage": 68.9, "elapsed_time": "3:18:10", "remaining_time": "1:29:27", "throughput": 1316.72, "total_tokens": 15656496} {"current_steps": 27565, "total_steps": 40000, "loss": 0.0, "lr": 1.1006434525373502e-05, "epoch": 483.60176991150445, "percentage": 68.91, "elapsed_time": "3:18:12", "remaining_time": "1:29:24", "throughput": 1316.71, "total_tokens": 15659120} {"current_steps": 27570, "total_steps": 40000, "loss": 0.0, "lr": 1.0998300190043664e-05, "epoch": 483.69026548672565, "percentage": 68.92, "elapsed_time": "3:18:14", "remaining_time": "1:29:22", "throughput": 1316.72, "total_tokens": 15662032} {"current_steps": 27575, "total_steps": 40000, "loss": 0.0, "lr": 1.0990168013951882e-05, "epoch": 483.7787610619469, "percentage": 68.94, "elapsed_time": "3:18:16", "remaining_time": "1:29:20", "throughput": 1316.7, "total_tokens": 15664544} {"current_steps": 27580, "total_steps": 40000, "loss": 0.0, "lr": 1.0982037998352263e-05, "epoch": 483.86725663716817, "percentage": 68.95, "elapsed_time": "3:18:18", "remaining_time": "1:29:18", "throughput": 1316.7, "total_tokens": 15667200} {"current_steps": 27585, "total_steps": 40000, "loss": 0.0, "lr": 1.0973910144498534e-05, "epoch": 483.95575221238937, "percentage": 68.96, "elapsed_time": "3:18:20", "remaining_time": "1:29:16", "throughput": 1316.7, "total_tokens": 15670000} {"current_steps": 27590, "total_steps": 40000, "loss": 0.0, "lr": 1.0965784453644123e-05, "epoch": 484.0353982300885, "percentage": 68.97, "elapsed_time": "3:18:23", "remaining_time": "1:29:14", "throughput": 1316.69, "total_tokens": 15672776} {"current_steps": 27595, "total_steps": 40000, "loss": 0.0, "lr": 1.0957660927042127e-05, "epoch": 484.12389380530976, "percentage": 68.99, "elapsed_time": "3:18:25", "remaining_time": "1:29:11", "throughput": 1316.76, "total_tokens": 15676328} {"current_steps": 27600, "total_steps": 40000, "loss": 0.0, "lr": 1.094953956594527e-05, "epoch": 484.21238938053096, "percentage": 69.0, "elapsed_time": "3:18:27", "remaining_time": "1:29:09", "throughput": 1316.81, "total_tokens": 15679720} {"current_steps": 27600, "total_steps": 40000, "eval_loss": 0.9056763052940369, "epoch": 484.21238938053096, "percentage": 69.0, "elapsed_time": "3:18:28", "remaining_time": "1:29:10", "throughput": 1316.69, "total_tokens": 15679720} {"current_steps": 27605, "total_steps": 40000, "loss": 0.0, "lr": 1.0941420371605981e-05, "epoch": 484.3008849557522, "percentage": 69.01, "elapsed_time": "3:18:32", "remaining_time": "1:29:08", "throughput": 1316.52, "total_tokens": 15682680} {"current_steps": 27610, "total_steps": 40000, "loss": 0.0, "lr": 1.0933303345276354e-05, "epoch": 484.3893805309734, "percentage": 69.03, "elapsed_time": "3:18:34", "remaining_time": "1:29:06", "throughput": 1316.51, "total_tokens": 15685336} {"current_steps": 27615, "total_steps": 40000, "loss": 0.0, "lr": 1.0925188488208112e-05, "epoch": 484.4778761061947, "percentage": 69.04, "elapsed_time": "3:18:36", "remaining_time": "1:29:04", "throughput": 1316.5, "total_tokens": 15687944} {"current_steps": 27620, "total_steps": 40000, "loss": 0.0, "lr": 1.0917075801652694e-05, "epoch": 484.56637168141594, "percentage": 69.05, "elapsed_time": "3:18:38", "remaining_time": "1:29:02", "throughput": 1316.51, "total_tokens": 15690776} {"current_steps": 27625, "total_steps": 40000, "loss": 0.0, "lr": 1.0908965286861151e-05, "epoch": 484.65486725663715, "percentage": 69.06, "elapsed_time": "3:18:40", "remaining_time": "1:28:59", "throughput": 1316.53, "total_tokens": 15693704} {"current_steps": 27630, "total_steps": 40000, "loss": 0.0, "lr": 1.090085694508425e-05, "epoch": 484.7433628318584, "percentage": 69.08, "elapsed_time": "3:18:42", "remaining_time": "1:28:57", "throughput": 1316.53, "total_tokens": 15696456} {"current_steps": 27635, "total_steps": 40000, "loss": 0.0, "lr": 1.089275077757238e-05, "epoch": 484.83185840707966, "percentage": 69.09, "elapsed_time": "3:18:44", "remaining_time": "1:28:55", "throughput": 1316.54, "total_tokens": 15699304} {"current_steps": 27640, "total_steps": 40000, "loss": 0.0, "lr": 1.0884646785575633e-05, "epoch": 484.92035398230087, "percentage": 69.1, "elapsed_time": "3:18:46", "remaining_time": "1:28:53", "throughput": 1316.53, "total_tokens": 15701880} {"current_steps": 27645, "total_steps": 40000, "loss": 0.0, "lr": 1.0876544970343728e-05, "epoch": 485.0, "percentage": 69.11, "elapsed_time": "3:18:48", "remaining_time": "1:28:51", "throughput": 1316.51, "total_tokens": 15704328} {"current_steps": 27650, "total_steps": 40000, "loss": 0.0, "lr": 1.0868445333126082e-05, "epoch": 485.08849557522126, "percentage": 69.12, "elapsed_time": "3:18:51", "remaining_time": "1:28:49", "throughput": 1316.51, "total_tokens": 15707336} {"current_steps": 27655, "total_steps": 40000, "loss": 0.0, "lr": 1.0860347875171745e-05, "epoch": 485.17699115044246, "percentage": 69.14, "elapsed_time": "3:18:53", "remaining_time": "1:28:46", "throughput": 1316.5, "total_tokens": 15709944} {"current_steps": 27660, "total_steps": 40000, "loss": 0.0, "lr": 1.0852252597729465e-05, "epoch": 485.2654867256637, "percentage": 69.15, "elapsed_time": "3:18:55", "remaining_time": "1:28:44", "throughput": 1316.48, "total_tokens": 15712472} {"current_steps": 27665, "total_steps": 40000, "loss": 0.0, "lr": 1.0844159502047615e-05, "epoch": 485.353982300885, "percentage": 69.16, "elapsed_time": "3:18:57", "remaining_time": "1:28:42", "throughput": 1316.47, "total_tokens": 15715112} {"current_steps": 27670, "total_steps": 40000, "loss": 0.0, "lr": 1.0836068589374265e-05, "epoch": 485.4424778761062, "percentage": 69.17, "elapsed_time": "3:18:59", "remaining_time": "1:28:40", "throughput": 1316.46, "total_tokens": 15717704} {"current_steps": 27675, "total_steps": 40000, "loss": 0.0, "lr": 1.0827979860957144e-05, "epoch": 485.53097345132744, "percentage": 69.19, "elapsed_time": "3:19:01", "remaining_time": "1:28:38", "throughput": 1316.45, "total_tokens": 15720360} {"current_steps": 27680, "total_steps": 40000, "loss": 0.0, "lr": 1.0819893318043615e-05, "epoch": 485.6194690265487, "percentage": 69.2, "elapsed_time": "3:19:03", "remaining_time": "1:28:35", "throughput": 1316.47, "total_tokens": 15723352} {"current_steps": 27685, "total_steps": 40000, "loss": 0.0, "lr": 1.0811808961880734e-05, "epoch": 485.7079646017699, "percentage": 69.21, "elapsed_time": "3:19:05", "remaining_time": "1:28:33", "throughput": 1316.52, "total_tokens": 15726600} {"current_steps": 27690, "total_steps": 40000, "loss": 0.0, "lr": 1.080372679371522e-05, "epoch": 485.79646017699116, "percentage": 69.23, "elapsed_time": "3:19:07", "remaining_time": "1:28:31", "throughput": 1316.55, "total_tokens": 15729752} {"current_steps": 27695, "total_steps": 40000, "loss": 0.0, "lr": 1.0795646814793428e-05, "epoch": 485.88495575221236, "percentage": 69.24, "elapsed_time": "3:19:09", "remaining_time": "1:28:29", "throughput": 1316.56, "total_tokens": 15732568} {"current_steps": 27700, "total_steps": 40000, "loss": 0.0, "lr": 1.078756902636141e-05, "epoch": 485.9734513274336, "percentage": 69.25, "elapsed_time": "3:19:11", "remaining_time": "1:28:27", "throughput": 1316.58, "total_tokens": 15735464} {"current_steps": 27705, "total_steps": 40000, "loss": 0.0, "lr": 1.077949342966485e-05, "epoch": 486.05309734513276, "percentage": 69.26, "elapsed_time": "3:19:14", "remaining_time": "1:28:25", "throughput": 1316.54, "total_tokens": 15737976} {"current_steps": 27710, "total_steps": 40000, "loss": 0.0, "lr": 1.0771420025949103e-05, "epoch": 486.14159292035396, "percentage": 69.27, "elapsed_time": "3:19:16", "remaining_time": "1:28:22", "throughput": 1316.54, "total_tokens": 15740776} {"current_steps": 27715, "total_steps": 40000, "loss": 0.0, "lr": 1.0763348816459204e-05, "epoch": 486.2300884955752, "percentage": 69.29, "elapsed_time": "3:19:18", "remaining_time": "1:28:20", "throughput": 1316.59, "total_tokens": 15744008} {"current_steps": 27720, "total_steps": 40000, "loss": 0.0, "lr": 1.0755279802439816e-05, "epoch": 486.3185840707965, "percentage": 69.3, "elapsed_time": "3:19:20", "remaining_time": "1:28:18", "throughput": 1316.59, "total_tokens": 15746824} {"current_steps": 27725, "total_steps": 40000, "loss": 0.0, "lr": 1.0747212985135293e-05, "epoch": 486.4070796460177, "percentage": 69.31, "elapsed_time": "3:19:22", "remaining_time": "1:28:16", "throughput": 1316.59, "total_tokens": 15749496} {"current_steps": 27730, "total_steps": 40000, "loss": 0.0, "lr": 1.073914836578965e-05, "epoch": 486.49557522123894, "percentage": 69.33, "elapsed_time": "3:19:24", "remaining_time": "1:28:14", "throughput": 1316.56, "total_tokens": 15751848} {"current_steps": 27735, "total_steps": 40000, "loss": 0.0, "lr": 1.0731085945646529e-05, "epoch": 486.5840707964602, "percentage": 69.34, "elapsed_time": "3:19:26", "remaining_time": "1:28:11", "throughput": 1316.59, "total_tokens": 15755016} {"current_steps": 27740, "total_steps": 40000, "loss": 0.0, "lr": 1.0723025725949285e-05, "epoch": 486.6725663716814, "percentage": 69.35, "elapsed_time": "3:19:28", "remaining_time": "1:28:09", "throughput": 1316.62, "total_tokens": 15758056} {"current_steps": 27745, "total_steps": 40000, "loss": 0.0, "lr": 1.0714967707940875e-05, "epoch": 486.76106194690266, "percentage": 69.36, "elapsed_time": "3:19:30", "remaining_time": "1:28:07", "throughput": 1316.61, "total_tokens": 15760712} {"current_steps": 27750, "total_steps": 40000, "loss": 0.0, "lr": 1.0706911892863963e-05, "epoch": 486.8495575221239, "percentage": 69.38, "elapsed_time": "3:19:32", "remaining_time": "1:28:05", "throughput": 1316.62, "total_tokens": 15763544} {"current_steps": 27755, "total_steps": 40000, "loss": 0.0, "lr": 1.0698858281960866e-05, "epoch": 486.9380530973451, "percentage": 69.39, "elapsed_time": "3:19:34", "remaining_time": "1:28:03", "throughput": 1316.65, "total_tokens": 15766648} {"current_steps": 27760, "total_steps": 40000, "loss": 0.0, "lr": 1.069080687647353e-05, "epoch": 487.01769911504425, "percentage": 69.4, "elapsed_time": "3:19:37", "remaining_time": "1:28:00", "throughput": 1316.63, "total_tokens": 15769352} {"current_steps": 27765, "total_steps": 40000, "loss": 0.0, "lr": 1.0682757677643596e-05, "epoch": 487.1061946902655, "percentage": 69.41, "elapsed_time": "3:19:39", "remaining_time": "1:27:58", "throughput": 1316.62, "total_tokens": 15771960} {"current_steps": 27770, "total_steps": 40000, "loss": 0.0, "lr": 1.0674710686712359e-05, "epoch": 487.1946902654867, "percentage": 69.42, "elapsed_time": "3:19:41", "remaining_time": "1:27:56", "throughput": 1316.64, "total_tokens": 15774872} {"current_steps": 27775, "total_steps": 40000, "loss": 0.0, "lr": 1.0666665904920756e-05, "epoch": 487.283185840708, "percentage": 69.44, "elapsed_time": "3:19:43", "remaining_time": "1:27:54", "throughput": 1316.64, "total_tokens": 15777672} {"current_steps": 27780, "total_steps": 40000, "loss": 0.0, "lr": 1.0658623333509385e-05, "epoch": 487.37168141592923, "percentage": 69.45, "elapsed_time": "3:19:45", "remaining_time": "1:27:52", "throughput": 1316.68, "total_tokens": 15780872} {"current_steps": 27785, "total_steps": 40000, "loss": 0.0, "lr": 1.0650582973718532e-05, "epoch": 487.46017699115043, "percentage": 69.46, "elapsed_time": "3:19:47", "remaining_time": "1:27:49", "throughput": 1316.72, "total_tokens": 15784040} {"current_steps": 27790, "total_steps": 40000, "loss": 0.0, "lr": 1.0642544826788098e-05, "epoch": 487.5486725663717, "percentage": 69.47, "elapsed_time": "3:19:49", "remaining_time": "1:27:47", "throughput": 1316.71, "total_tokens": 15786696} {"current_steps": 27795, "total_steps": 40000, "loss": 0.0, "lr": 1.063450889395769e-05, "epoch": 487.6371681415929, "percentage": 69.49, "elapsed_time": "3:19:51", "remaining_time": "1:27:45", "throughput": 1316.7, "total_tokens": 15789272} {"current_steps": 27800, "total_steps": 40000, "loss": 0.0, "lr": 1.062647517646653e-05, "epoch": 487.72566371681415, "percentage": 69.5, "elapsed_time": "3:19:53", "remaining_time": "1:27:43", "throughput": 1316.75, "total_tokens": 15792680} {"current_steps": 27800, "total_steps": 40000, "eval_loss": 0.9154664278030396, "epoch": 487.72566371681415, "percentage": 69.5, "elapsed_time": "3:19:54", "remaining_time": "1:27:43", "throughput": 1316.64, "total_tokens": 15792680} {"current_steps": 27805, "total_steps": 40000, "loss": 0.0, "lr": 1.0618443675553527e-05, "epoch": 487.8141592920354, "percentage": 69.51, "elapsed_time": "3:19:59", "remaining_time": "1:27:42", "throughput": 1316.36, "total_tokens": 15795880} {"current_steps": 27810, "total_steps": 40000, "loss": 0.0, "lr": 1.0610414392457247e-05, "epoch": 487.9026548672566, "percentage": 69.53, "elapsed_time": "3:20:01", "remaining_time": "1:27:40", "throughput": 1316.34, "total_tokens": 15798424} {"current_steps": 27815, "total_steps": 40000, "loss": 0.0, "lr": 1.0602387328415888e-05, "epoch": 487.9911504424779, "percentage": 69.54, "elapsed_time": "3:20:03", "remaining_time": "1:27:38", "throughput": 1316.39, "total_tokens": 15801624} {"current_steps": 27820, "total_steps": 40000, "loss": 0.0, "lr": 1.0594362484667347e-05, "epoch": 488.070796460177, "percentage": 69.55, "elapsed_time": "3:20:06", "remaining_time": "1:27:36", "throughput": 1316.31, "total_tokens": 15803736} {"current_steps": 27825, "total_steps": 40000, "loss": 0.0, "lr": 1.0586339862449132e-05, "epoch": 488.1592920353982, "percentage": 69.56, "elapsed_time": "3:20:08", "remaining_time": "1:27:34", "throughput": 1316.31, "total_tokens": 15806408} {"current_steps": 27830, "total_steps": 40000, "loss": 0.0, "lr": 1.0578319462998445e-05, "epoch": 488.24778761061947, "percentage": 69.58, "elapsed_time": "3:20:10", "remaining_time": "1:27:32", "throughput": 1316.33, "total_tokens": 15809416} {"current_steps": 27835, "total_steps": 40000, "loss": 0.0, "lr": 1.057030128755214e-05, "epoch": 488.3362831858407, "percentage": 69.59, "elapsed_time": "3:20:12", "remaining_time": "1:27:29", "throughput": 1316.35, "total_tokens": 15812392} {"current_steps": 27840, "total_steps": 40000, "loss": 0.0, "lr": 1.0562285337346703e-05, "epoch": 488.42477876106193, "percentage": 69.6, "elapsed_time": "3:20:14", "remaining_time": "1:27:27", "throughput": 1316.42, "total_tokens": 15815896} {"current_steps": 27845, "total_steps": 40000, "loss": 0.0, "lr": 1.0554271613618308e-05, "epoch": 488.5132743362832, "percentage": 69.61, "elapsed_time": "3:20:16", "remaining_time": "1:27:25", "throughput": 1316.48, "total_tokens": 15819336} {"current_steps": 27850, "total_steps": 40000, "loss": 0.0, "lr": 1.054626011760276e-05, "epoch": 488.60176991150445, "percentage": 69.62, "elapsed_time": "3:20:18", "remaining_time": "1:27:23", "throughput": 1316.46, "total_tokens": 15822296} {"current_steps": 27855, "total_steps": 40000, "loss": 0.0, "lr": 1.0538250850535549e-05, "epoch": 488.69026548672565, "percentage": 69.64, "elapsed_time": "3:20:20", "remaining_time": "1:27:21", "throughput": 1316.49, "total_tokens": 15825352} {"current_steps": 27860, "total_steps": 40000, "loss": 0.0, "lr": 1.0530243813651794e-05, "epoch": 488.7787610619469, "percentage": 69.65, "elapsed_time": "3:20:22", "remaining_time": "1:27:19", "throughput": 1316.45, "total_tokens": 15827672} {"current_steps": 27865, "total_steps": 40000, "loss": 0.0, "lr": 1.0522239008186271e-05, "epoch": 488.86725663716817, "percentage": 69.66, "elapsed_time": "3:20:25", "remaining_time": "1:27:16", "throughput": 1316.43, "total_tokens": 15830072} {"current_steps": 27870, "total_steps": 40000, "loss": 0.0, "lr": 1.0514236435373434e-05, "epoch": 488.95575221238937, "percentage": 69.67, "elapsed_time": "3:20:27", "remaining_time": "1:27:14", "throughput": 1316.44, "total_tokens": 15832920} {"current_steps": 27875, "total_steps": 40000, "loss": 0.0, "lr": 1.0506236096447386e-05, "epoch": 489.0353982300885, "percentage": 69.69, "elapsed_time": "3:20:29", "remaining_time": "1:27:12", "throughput": 1316.39, "total_tokens": 15835384} {"current_steps": 27880, "total_steps": 40000, "loss": 0.0, "lr": 1.049823799264186e-05, "epoch": 489.12389380530976, "percentage": 69.7, "elapsed_time": "3:20:31", "remaining_time": "1:27:10", "throughput": 1316.4, "total_tokens": 15838136} {"current_steps": 27885, "total_steps": 40000, "loss": 0.0, "lr": 1.049024212519028e-05, "epoch": 489.21238938053096, "percentage": 69.71, "elapsed_time": "3:20:33", "remaining_time": "1:27:08", "throughput": 1316.43, "total_tokens": 15841240} {"current_steps": 27890, "total_steps": 40000, "loss": 0.0, "lr": 1.0482248495325713e-05, "epoch": 489.3008849557522, "percentage": 69.73, "elapsed_time": "3:20:35", "remaining_time": "1:27:05", "throughput": 1316.41, "total_tokens": 15843800} {"current_steps": 27895, "total_steps": 40000, "loss": 0.0, "lr": 1.047425710428086e-05, "epoch": 489.3893805309734, "percentage": 69.74, "elapsed_time": "3:20:37", "remaining_time": "1:27:03", "throughput": 1316.42, "total_tokens": 15846568} {"current_steps": 27900, "total_steps": 40000, "loss": 0.0, "lr": 1.0466267953288114e-05, "epoch": 489.4778761061947, "percentage": 69.75, "elapsed_time": "3:20:39", "remaining_time": "1:27:01", "throughput": 1316.41, "total_tokens": 15849160} {"current_steps": 27905, "total_steps": 40000, "loss": 0.0, "lr": 1.0458281043579482e-05, "epoch": 489.56637168141594, "percentage": 69.76, "elapsed_time": "3:20:41", "remaining_time": "1:26:59", "throughput": 1316.44, "total_tokens": 15852296} {"current_steps": 27910, "total_steps": 40000, "loss": 0.0, "lr": 1.0450296376386657e-05, "epoch": 489.65486725663715, "percentage": 69.77, "elapsed_time": "3:20:43", "remaining_time": "1:26:57", "throughput": 1316.48, "total_tokens": 15855480} {"current_steps": 27915, "total_steps": 40000, "loss": 0.0, "lr": 1.044231395294098e-05, "epoch": 489.7433628318584, "percentage": 69.79, "elapsed_time": "3:20:45", "remaining_time": "1:26:54", "throughput": 1316.45, "total_tokens": 15857880} {"current_steps": 27920, "total_steps": 40000, "loss": 0.0, "lr": 1.0434333774473435e-05, "epoch": 489.83185840707966, "percentage": 69.8, "elapsed_time": "3:20:47", "remaining_time": "1:26:52", "throughput": 1316.52, "total_tokens": 15861416} {"current_steps": 27925, "total_steps": 40000, "loss": 0.0, "lr": 1.0426355842214657e-05, "epoch": 489.92035398230087, "percentage": 69.81, "elapsed_time": "3:20:50", "remaining_time": "1:26:50", "throughput": 1316.5, "total_tokens": 15863928} {"current_steps": 27930, "total_steps": 40000, "loss": 0.0, "lr": 1.0418380157394963e-05, "epoch": 490.0, "percentage": 69.83, "elapsed_time": "3:20:52", "remaining_time": "1:26:48", "throughput": 1316.48, "total_tokens": 15866288} {"current_steps": 27935, "total_steps": 40000, "loss": 0.0, "lr": 1.0410406721244281e-05, "epoch": 490.08849557522126, "percentage": 69.84, "elapsed_time": "3:20:54", "remaining_time": "1:26:46", "throughput": 1316.42, "total_tokens": 15868624} {"current_steps": 27940, "total_steps": 40000, "loss": 0.0, "lr": 1.0402435534992238e-05, "epoch": 490.17699115044246, "percentage": 69.85, "elapsed_time": "3:20:56", "remaining_time": "1:26:44", "throughput": 1316.4, "total_tokens": 15871104} {"current_steps": 27945, "total_steps": 40000, "loss": 0.0, "lr": 1.0394466599868071e-05, "epoch": 490.2654867256637, "percentage": 69.86, "elapsed_time": "3:20:58", "remaining_time": "1:26:41", "throughput": 1316.42, "total_tokens": 15874144} {"current_steps": 27950, "total_steps": 40000, "loss": 0.0, "lr": 1.0386499917100697e-05, "epoch": 490.353982300885, "percentage": 69.88, "elapsed_time": "3:21:00", "remaining_time": "1:26:39", "throughput": 1316.44, "total_tokens": 15877168} {"current_steps": 27955, "total_steps": 40000, "loss": 0.0, "lr": 1.0378535487918692e-05, "epoch": 490.4424778761062, "percentage": 69.89, "elapsed_time": "3:21:02", "remaining_time": "1:26:37", "throughput": 1316.45, "total_tokens": 15879920} {"current_steps": 27960, "total_steps": 40000, "loss": 0.0, "lr": 1.037057331355025e-05, "epoch": 490.53097345132744, "percentage": 69.9, "elapsed_time": "3:21:04", "remaining_time": "1:26:35", "throughput": 1316.46, "total_tokens": 15882768} {"current_steps": 27965, "total_steps": 40000, "loss": 0.0, "lr": 1.0362613395223247e-05, "epoch": 490.6194690265487, "percentage": 69.91, "elapsed_time": "3:21:06", "remaining_time": "1:26:33", "throughput": 1316.49, "total_tokens": 15885952} {"current_steps": 27970, "total_steps": 40000, "loss": 0.0, "lr": 1.0354655734165212e-05, "epoch": 490.7079646017699, "percentage": 69.92, "elapsed_time": "3:21:08", "remaining_time": "1:26:30", "throughput": 1316.54, "total_tokens": 15889264} {"current_steps": 27975, "total_steps": 40000, "loss": 0.0, "lr": 1.03467003316033e-05, "epoch": 490.79646017699116, "percentage": 69.94, "elapsed_time": "3:21:10", "remaining_time": "1:26:28", "throughput": 1316.54, "total_tokens": 15891904} {"current_steps": 27980, "total_steps": 40000, "loss": 0.0, "lr": 1.033874718876435e-05, "epoch": 490.88495575221236, "percentage": 69.95, "elapsed_time": "3:21:13", "remaining_time": "1:26:26", "throughput": 1316.59, "total_tokens": 15895296} {"current_steps": 27985, "total_steps": 40000, "loss": 0.0, "lr": 1.0330796306874818e-05, "epoch": 490.9734513274336, "percentage": 69.96, "elapsed_time": "3:21:15", "remaining_time": "1:26:24", "throughput": 1316.59, "total_tokens": 15897952} {"current_steps": 27990, "total_steps": 40000, "loss": 0.0, "lr": 1.032284768716085e-05, "epoch": 491.05309734513276, "percentage": 69.97, "elapsed_time": "3:21:17", "remaining_time": "1:26:22", "throughput": 1316.53, "total_tokens": 15900272} {"current_steps": 27995, "total_steps": 40000, "loss": 0.0, "lr": 1.0314901330848206e-05, "epoch": 491.14159292035396, "percentage": 69.99, "elapsed_time": "3:21:19", "remaining_time": "1:26:19", "throughput": 1316.59, "total_tokens": 15903680} {"current_steps": 28000, "total_steps": 40000, "loss": 0.0, "lr": 1.030695723916233e-05, "epoch": 491.2300884955752, "percentage": 70.0, "elapsed_time": "3:21:21", "remaining_time": "1:26:17", "throughput": 1316.61, "total_tokens": 15906624} {"current_steps": 28000, "total_steps": 40000, "eval_loss": 0.925339937210083, "epoch": 491.2300884955752, "percentage": 70.0, "elapsed_time": "3:21:22", "remaining_time": "1:26:18", "throughput": 1316.49, "total_tokens": 15906624} {"current_steps": 28005, "total_steps": 40000, "loss": 0.0, "lr": 1.0299015413328289e-05, "epoch": 491.3185840707965, "percentage": 70.01, "elapsed_time": "3:21:26", "remaining_time": "1:26:16", "throughput": 1316.35, "total_tokens": 15909952} {"current_steps": 28010, "total_steps": 40000, "loss": 0.0, "lr": 1.0291075854570809e-05, "epoch": 491.4070796460177, "percentage": 70.03, "elapsed_time": "3:21:28", "remaining_time": "1:26:14", "throughput": 1316.36, "total_tokens": 15912832} {"current_steps": 28015, "total_steps": 40000, "loss": 0.0, "lr": 1.0283138564114275e-05, "epoch": 491.49557522123894, "percentage": 70.04, "elapsed_time": "3:21:30", "remaining_time": "1:26:12", "throughput": 1316.36, "total_tokens": 15915616} {"current_steps": 28020, "total_steps": 40000, "loss": 0.0, "lr": 1.027520354318273e-05, "epoch": 491.5840707964602, "percentage": 70.05, "elapsed_time": "3:21:32", "remaining_time": "1:26:10", "throughput": 1316.36, "total_tokens": 15918304} {"current_steps": 28025, "total_steps": 40000, "loss": 0.0, "lr": 1.0267270792999828e-05, "epoch": 491.6725663716814, "percentage": 70.06, "elapsed_time": "3:21:34", "remaining_time": "1:26:08", "throughput": 1316.36, "total_tokens": 15921024} {"current_steps": 28030, "total_steps": 40000, "loss": 0.0, "lr": 1.0259340314788919e-05, "epoch": 491.76106194690266, "percentage": 70.08, "elapsed_time": "3:21:36", "remaining_time": "1:26:05", "throughput": 1316.39, "total_tokens": 15924064} {"current_steps": 28035, "total_steps": 40000, "loss": 0.0, "lr": 1.0251412109772979e-05, "epoch": 491.8495575221239, "percentage": 70.09, "elapsed_time": "3:21:38", "remaining_time": "1:26:03", "throughput": 1316.39, "total_tokens": 15926880} {"current_steps": 28040, "total_steps": 40000, "loss": 0.0, "lr": 1.0243486179174627e-05, "epoch": 491.9380530973451, "percentage": 70.1, "elapsed_time": "3:21:40", "remaining_time": "1:26:01", "throughput": 1316.36, "total_tokens": 15929184} {"current_steps": 28045, "total_steps": 40000, "loss": 0.0, "lr": 1.0235562524216158e-05, "epoch": 492.01769911504425, "percentage": 70.11, "elapsed_time": "3:21:43", "remaining_time": "1:25:59", "throughput": 1316.31, "total_tokens": 15931552} {"current_steps": 28050, "total_steps": 40000, "loss": 0.0, "lr": 1.022764114611948e-05, "epoch": 492.1061946902655, "percentage": 70.12, "elapsed_time": "3:21:45", "remaining_time": "1:25:57", "throughput": 1316.3, "total_tokens": 15934192} {"current_steps": 28055, "total_steps": 40000, "loss": 0.0, "lr": 1.0219722046106178e-05, "epoch": 492.1946902654867, "percentage": 70.14, "elapsed_time": "3:21:47", "remaining_time": "1:25:54", "throughput": 1316.32, "total_tokens": 15937104} {"current_steps": 28060, "total_steps": 40000, "loss": 0.0, "lr": 1.0211805225397486e-05, "epoch": 492.283185840708, "percentage": 70.15, "elapsed_time": "3:21:49", "remaining_time": "1:25:52", "throughput": 1316.31, "total_tokens": 15939728} {"current_steps": 28065, "total_steps": 40000, "loss": 0.0, "lr": 1.020389068521426e-05, "epoch": 492.37168141592923, "percentage": 70.16, "elapsed_time": "3:21:51", "remaining_time": "1:25:50", "throughput": 1316.37, "total_tokens": 15943264} {"current_steps": 28070, "total_steps": 40000, "loss": 0.0, "lr": 1.0195978426777039e-05, "epoch": 492.46017699115043, "percentage": 70.17, "elapsed_time": "3:21:53", "remaining_time": "1:25:48", "throughput": 1316.37, "total_tokens": 15945904} {"current_steps": 28075, "total_steps": 40000, "loss": 0.0, "lr": 1.0188068451305982e-05, "epoch": 492.5486725663717, "percentage": 70.19, "elapsed_time": "3:21:55", "remaining_time": "1:25:46", "throughput": 1316.41, "total_tokens": 15949104} {"current_steps": 28080, "total_steps": 40000, "loss": 0.0, "lr": 1.0180160760020902e-05, "epoch": 492.6371681415929, "percentage": 70.2, "elapsed_time": "3:21:57", "remaining_time": "1:25:43", "throughput": 1316.42, "total_tokens": 15952032} {"current_steps": 28085, "total_steps": 40000, "loss": 0.0, "lr": 1.0172255354141278e-05, "epoch": 492.72566371681415, "percentage": 70.21, "elapsed_time": "3:21:59", "remaining_time": "1:25:41", "throughput": 1316.44, "total_tokens": 15954944} {"current_steps": 28090, "total_steps": 40000, "loss": 0.0, "lr": 1.0164352234886205e-05, "epoch": 492.8141592920354, "percentage": 70.23, "elapsed_time": "3:22:01", "remaining_time": "1:25:39", "throughput": 1316.43, "total_tokens": 15957568} {"current_steps": 28095, "total_steps": 40000, "loss": 0.0, "lr": 1.0156451403474454e-05, "epoch": 492.9026548672566, "percentage": 70.24, "elapsed_time": "3:22:03", "remaining_time": "1:25:37", "throughput": 1316.43, "total_tokens": 15960352} {"current_steps": 28100, "total_steps": 40000, "loss": 0.0, "lr": 1.0148552861124443e-05, "epoch": 492.9911504424779, "percentage": 70.25, "elapsed_time": "3:22:05", "remaining_time": "1:25:35", "throughput": 1316.46, "total_tokens": 15963360} {"current_steps": 28105, "total_steps": 40000, "loss": 0.0, "lr": 1.0140656609054205e-05, "epoch": 493.070796460177, "percentage": 70.26, "elapsed_time": "3:22:08", "remaining_time": "1:25:33", "throughput": 1316.44, "total_tokens": 15966096} {"current_steps": 28110, "total_steps": 40000, "loss": 0.0, "lr": 1.0132762648481455e-05, "epoch": 493.1592920353982, "percentage": 70.28, "elapsed_time": "3:22:10", "remaining_time": "1:25:30", "throughput": 1316.44, "total_tokens": 15968816} {"current_steps": 28115, "total_steps": 40000, "loss": 0.0, "lr": 1.0124870980623543e-05, "epoch": 493.24778761061947, "percentage": 70.29, "elapsed_time": "3:22:12", "remaining_time": "1:25:28", "throughput": 1316.49, "total_tokens": 15972160} {"current_steps": 28120, "total_steps": 40000, "loss": 0.0, "lr": 1.0116981606697453e-05, "epoch": 493.3362831858407, "percentage": 70.3, "elapsed_time": "3:22:14", "remaining_time": "1:25:26", "throughput": 1316.5, "total_tokens": 15974976} {"current_steps": 28125, "total_steps": 40000, "loss": 0.0, "lr": 1.0109094527919838e-05, "epoch": 493.42477876106193, "percentage": 70.31, "elapsed_time": "3:22:16", "remaining_time": "1:25:24", "throughput": 1316.52, "total_tokens": 15977984} {"current_steps": 28130, "total_steps": 40000, "loss": 0.0, "lr": 1.010120974550697e-05, "epoch": 493.5132743362832, "percentage": 70.33, "elapsed_time": "3:22:18", "remaining_time": "1:25:22", "throughput": 1316.58, "total_tokens": 15981376} {"current_steps": 28135, "total_steps": 40000, "loss": 0.0, "lr": 1.0093327260674795e-05, "epoch": 493.60176991150445, "percentage": 70.34, "elapsed_time": "3:22:20", "remaining_time": "1:25:19", "throughput": 1316.56, "total_tokens": 15983952} {"current_steps": 28140, "total_steps": 40000, "loss": 0.0, "lr": 1.0085447074638878e-05, "epoch": 493.69026548672565, "percentage": 70.35, "elapsed_time": "3:22:22", "remaining_time": "1:25:17", "throughput": 1316.59, "total_tokens": 15987056} {"current_steps": 28145, "total_steps": 40000, "loss": 0.0, "lr": 1.0077569188614461e-05, "epoch": 493.7787610619469, "percentage": 70.36, "elapsed_time": "3:22:24", "remaining_time": "1:25:15", "throughput": 1316.59, "total_tokens": 15989728} {"current_steps": 28150, "total_steps": 40000, "loss": 0.0, "lr": 1.0069693603816393e-05, "epoch": 493.86725663716817, "percentage": 70.38, "elapsed_time": "3:22:26", "remaining_time": "1:25:13", "throughput": 1316.6, "total_tokens": 15992624} {"current_steps": 28155, "total_steps": 40000, "loss": 0.0, "lr": 1.0061820321459204e-05, "epoch": 493.95575221238937, "percentage": 70.39, "elapsed_time": "3:22:28", "remaining_time": "1:25:11", "throughput": 1316.59, "total_tokens": 15995184} {"current_steps": 28160, "total_steps": 40000, "loss": 0.0, "lr": 1.0053949342757038e-05, "epoch": 494.0353982300885, "percentage": 70.4, "elapsed_time": "3:22:31", "remaining_time": "1:25:09", "throughput": 1316.54, "total_tokens": 15997584} {"current_steps": 28165, "total_steps": 40000, "loss": 0.0, "lr": 1.0046080668923717e-05, "epoch": 494.12389380530976, "percentage": 70.41, "elapsed_time": "3:22:33", "remaining_time": "1:25:06", "throughput": 1316.54, "total_tokens": 16000352} {"current_steps": 28170, "total_steps": 40000, "loss": 0.0, "lr": 1.003821430117267e-05, "epoch": 494.21238938053096, "percentage": 70.43, "elapsed_time": "3:22:35", "remaining_time": "1:25:04", "throughput": 1316.55, "total_tokens": 16003136} {"current_steps": 28175, "total_steps": 40000, "loss": 0.0, "lr": 1.0030350240716999e-05, "epoch": 494.3008849557522, "percentage": 70.44, "elapsed_time": "3:22:37", "remaining_time": "1:25:02", "throughput": 1316.54, "total_tokens": 16005744} {"current_steps": 28180, "total_steps": 40000, "loss": 0.0, "lr": 1.0022488488769449e-05, "epoch": 494.3893805309734, "percentage": 70.45, "elapsed_time": "3:22:39", "remaining_time": "1:25:00", "throughput": 1316.51, "total_tokens": 16008176} {"current_steps": 28185, "total_steps": 40000, "loss": 0.0, "lr": 1.0014629046542387e-05, "epoch": 494.4778761061947, "percentage": 70.46, "elapsed_time": "3:22:41", "remaining_time": "1:24:58", "throughput": 1316.52, "total_tokens": 16010960} {"current_steps": 28190, "total_steps": 40000, "loss": 0.0, "lr": 1.0006771915247842e-05, "epoch": 494.56637168141594, "percentage": 70.47, "elapsed_time": "3:22:43", "remaining_time": "1:24:55", "throughput": 1316.51, "total_tokens": 16013568} {"current_steps": 28195, "total_steps": 40000, "loss": 0.0, "lr": 9.998917096097495e-06, "epoch": 494.65486725663715, "percentage": 70.49, "elapsed_time": "3:22:45", "remaining_time": "1:24:53", "throughput": 1316.56, "total_tokens": 16016880} {"current_steps": 28200, "total_steps": 40000, "loss": 0.0, "lr": 9.991064590302638e-06, "epoch": 494.7433628318584, "percentage": 70.5, "elapsed_time": "3:22:47", "remaining_time": "1:24:51", "throughput": 1316.58, "total_tokens": 16019936} {"current_steps": 28200, "total_steps": 40000, "eval_loss": 0.9103339910507202, "epoch": 494.7433628318584, "percentage": 70.5, "elapsed_time": "3:22:48", "remaining_time": "1:24:51", "throughput": 1316.47, "total_tokens": 16019936} {"current_steps": 28205, "total_steps": 40000, "loss": 0.0, "lr": 9.983214399074241e-06, "epoch": 494.83185840707966, "percentage": 70.51, "elapsed_time": "3:22:52", "remaining_time": "1:24:50", "throughput": 1316.28, "total_tokens": 16022880} {"current_steps": 28210, "total_steps": 40000, "loss": 0.0, "lr": 9.975366523622893e-06, "epoch": 494.92035398230087, "percentage": 70.53, "elapsed_time": "3:22:54", "remaining_time": "1:24:48", "throughput": 1316.27, "total_tokens": 16025536} {"current_steps": 28215, "total_steps": 40000, "loss": 0.0, "lr": 9.967520965158841e-06, "epoch": 495.0, "percentage": 70.54, "elapsed_time": "3:22:56", "remaining_time": "1:24:46", "throughput": 1316.29, "total_tokens": 16028400} {"current_steps": 28220, "total_steps": 40000, "loss": 0.0, "lr": 9.95967772489197e-06, "epoch": 495.08849557522126, "percentage": 70.55, "elapsed_time": "3:22:59", "remaining_time": "1:24:44", "throughput": 1316.29, "total_tokens": 16031440} {"current_steps": 28225, "total_steps": 40000, "loss": 0.0, "lr": 9.951836804031794e-06, "epoch": 495.17699115044246, "percentage": 70.56, "elapsed_time": "3:23:01", "remaining_time": "1:24:41", "throughput": 1316.29, "total_tokens": 16034208} {"current_steps": 28230, "total_steps": 40000, "loss": 0.0, "lr": 9.943998203787489e-06, "epoch": 495.2654867256637, "percentage": 70.58, "elapsed_time": "3:23:03", "remaining_time": "1:24:39", "throughput": 1316.3, "total_tokens": 16037008} {"current_steps": 28235, "total_steps": 40000, "loss": 0.0, "lr": 9.936161925367874e-06, "epoch": 495.353982300885, "percentage": 70.59, "elapsed_time": "3:23:05", "remaining_time": "1:24:37", "throughput": 1316.29, "total_tokens": 16039616} {"current_steps": 28240, "total_steps": 40000, "loss": 0.0, "lr": 9.928327969981386e-06, "epoch": 495.4424778761062, "percentage": 70.6, "elapsed_time": "3:23:07", "remaining_time": "1:24:35", "throughput": 1316.32, "total_tokens": 16042784} {"current_steps": 28245, "total_steps": 40000, "loss": 0.0, "lr": 9.920496338836135e-06, "epoch": 495.53097345132744, "percentage": 70.61, "elapsed_time": "3:23:09", "remaining_time": "1:24:33", "throughput": 1316.32, "total_tokens": 16045504} {"current_steps": 28250, "total_steps": 40000, "loss": 0.0, "lr": 9.912667033139844e-06, "epoch": 495.6194690265487, "percentage": 70.62, "elapsed_time": "3:23:11", "remaining_time": "1:24:30", "throughput": 1316.35, "total_tokens": 16048560} {"current_steps": 28255, "total_steps": 40000, "loss": 0.0, "lr": 9.904840054099893e-06, "epoch": 495.7079646017699, "percentage": 70.64, "elapsed_time": "3:23:13", "remaining_time": "1:24:28", "throughput": 1316.36, "total_tokens": 16051424} {"current_steps": 28260, "total_steps": 40000, "loss": 0.0, "lr": 9.897015402923312e-06, "epoch": 495.79646017699116, "percentage": 70.65, "elapsed_time": "3:23:15", "remaining_time": "1:24:26", "throughput": 1316.37, "total_tokens": 16054320} {"current_steps": 28265, "total_steps": 40000, "loss": 0.0, "lr": 9.889193080816744e-06, "epoch": 495.88495575221236, "percentage": 70.66, "elapsed_time": "3:23:17", "remaining_time": "1:24:24", "throughput": 1316.42, "total_tokens": 16057616} {"current_steps": 28270, "total_steps": 40000, "loss": 0.0, "lr": 9.881373088986498e-06, "epoch": 495.9734513274336, "percentage": 70.67, "elapsed_time": "3:23:20", "remaining_time": "1:24:22", "throughput": 1316.41, "total_tokens": 16060192} {"current_steps": 28275, "total_steps": 40000, "loss": 0.0, "lr": 9.873555428638523e-06, "epoch": 496.05309734513276, "percentage": 70.69, "elapsed_time": "3:23:22", "remaining_time": "1:24:20", "throughput": 1316.37, "total_tokens": 16062768} {"current_steps": 28280, "total_steps": 40000, "loss": 0.0, "lr": 9.865740100978383e-06, "epoch": 496.14159292035396, "percentage": 70.7, "elapsed_time": "3:23:24", "remaining_time": "1:24:17", "throughput": 1316.36, "total_tokens": 16065344} {"current_steps": 28285, "total_steps": 40000, "loss": 0.0, "lr": 9.857927107211315e-06, "epoch": 496.2300884955752, "percentage": 70.71, "elapsed_time": "3:23:26", "remaining_time": "1:24:15", "throughput": 1316.39, "total_tokens": 16068416} {"current_steps": 28290, "total_steps": 40000, "loss": 0.0, "lr": 9.850116448542177e-06, "epoch": 496.3185840707965, "percentage": 70.73, "elapsed_time": "3:23:28", "remaining_time": "1:24:13", "throughput": 1316.38, "total_tokens": 16071088} {"current_steps": 28295, "total_steps": 40000, "loss": 0.0, "lr": 9.842308126175457e-06, "epoch": 496.4070796460177, "percentage": 70.74, "elapsed_time": "3:23:30", "remaining_time": "1:24:11", "throughput": 1316.37, "total_tokens": 16073616} {"current_steps": 28300, "total_steps": 40000, "loss": 0.0, "lr": 9.834502141315315e-06, "epoch": 496.49557522123894, "percentage": 70.75, "elapsed_time": "3:23:32", "remaining_time": "1:24:09", "throughput": 1316.34, "total_tokens": 16076064} {"current_steps": 28305, "total_steps": 40000, "loss": 0.0, "lr": 9.82669849516552e-06, "epoch": 496.5840707964602, "percentage": 70.76, "elapsed_time": "3:23:34", "remaining_time": "1:24:06", "throughput": 1316.37, "total_tokens": 16079136} {"current_steps": 28310, "total_steps": 40000, "loss": 0.0, "lr": 9.818897188929493e-06, "epoch": 496.6725663716814, "percentage": 70.78, "elapsed_time": "3:23:36", "remaining_time": "1:24:04", "throughput": 1316.38, "total_tokens": 16081920} {"current_steps": 28315, "total_steps": 40000, "loss": 0.0, "lr": 9.811098223810309e-06, "epoch": 496.76106194690266, "percentage": 70.79, "elapsed_time": "3:23:38", "remaining_time": "1:24:02", "throughput": 1316.41, "total_tokens": 16085072} {"current_steps": 28320, "total_steps": 40000, "loss": 0.0, "lr": 9.803301601010641e-06, "epoch": 496.8495575221239, "percentage": 70.8, "elapsed_time": "3:23:40", "remaining_time": "1:24:00", "throughput": 1316.45, "total_tokens": 16088336} {"current_steps": 28325, "total_steps": 40000, "loss": 0.0, "lr": 9.795507321732853e-06, "epoch": 496.9380530973451, "percentage": 70.81, "elapsed_time": "3:23:43", "remaining_time": "1:23:58", "throughput": 1316.48, "total_tokens": 16091408} {"current_steps": 28330, "total_steps": 40000, "loss": 0.0, "lr": 9.787715387178898e-06, "epoch": 497.01769911504425, "percentage": 70.83, "elapsed_time": "3:23:45", "remaining_time": "1:23:55", "throughput": 1316.46, "total_tokens": 16094072} {"current_steps": 28335, "total_steps": 40000, "loss": 0.0, "lr": 9.779925798550399e-06, "epoch": 497.1061946902655, "percentage": 70.84, "elapsed_time": "3:23:47", "remaining_time": "1:23:53", "throughput": 1316.47, "total_tokens": 16096984} {"current_steps": 28340, "total_steps": 40000, "loss": 0.0, "lr": 9.772138557048619e-06, "epoch": 497.1946902654867, "percentage": 70.85, "elapsed_time": "3:23:49", "remaining_time": "1:23:51", "throughput": 1316.45, "total_tokens": 16099432} {"current_steps": 28345, "total_steps": 40000, "loss": 0.0, "lr": 9.764353663874426e-06, "epoch": 497.283185840708, "percentage": 70.86, "elapsed_time": "3:23:51", "remaining_time": "1:23:49", "throughput": 1316.48, "total_tokens": 16102472} {"current_steps": 28350, "total_steps": 40000, "loss": 0.0, "lr": 9.756571120228375e-06, "epoch": 497.37168141592923, "percentage": 70.88, "elapsed_time": "3:23:53", "remaining_time": "1:23:47", "throughput": 1316.48, "total_tokens": 16105208} {"current_steps": 28355, "total_steps": 40000, "loss": 0.0, "lr": 9.748790927310605e-06, "epoch": 497.46017699115043, "percentage": 70.89, "elapsed_time": "3:23:55", "remaining_time": "1:23:45", "throughput": 1316.5, "total_tokens": 16108248} {"current_steps": 28360, "total_steps": 40000, "loss": 0.0, "lr": 9.741013086320946e-06, "epoch": 497.5486725663717, "percentage": 70.9, "elapsed_time": "3:23:57", "remaining_time": "1:23:42", "throughput": 1316.57, "total_tokens": 16111864} {"current_steps": 28365, "total_steps": 40000, "loss": 0.0, "lr": 9.733237598458821e-06, "epoch": 497.6371681415929, "percentage": 70.91, "elapsed_time": "3:23:59", "remaining_time": "1:23:40", "throughput": 1316.56, "total_tokens": 16114456} {"current_steps": 28370, "total_steps": 40000, "loss": 0.0, "lr": 9.725464464923308e-06, "epoch": 497.72566371681415, "percentage": 70.93, "elapsed_time": "3:24:01", "remaining_time": "1:23:38", "throughput": 1316.56, "total_tokens": 16117240} {"current_steps": 28375, "total_steps": 40000, "loss": 0.0, "lr": 9.717693686913123e-06, "epoch": 497.8141592920354, "percentage": 70.94, "elapsed_time": "3:24:03", "remaining_time": "1:23:36", "throughput": 1316.57, "total_tokens": 16119992} {"current_steps": 28380, "total_steps": 40000, "loss": 0.0, "lr": 9.709925265626632e-06, "epoch": 497.9026548672566, "percentage": 70.95, "elapsed_time": "3:24:06", "remaining_time": "1:23:34", "throughput": 1316.57, "total_tokens": 16122744} {"current_steps": 28385, "total_steps": 40000, "loss": 0.0, "lr": 9.702159202261801e-06, "epoch": 497.9911504424779, "percentage": 70.96, "elapsed_time": "3:24:08", "remaining_time": "1:23:31", "throughput": 1316.58, "total_tokens": 16125528} {"current_steps": 28390, "total_steps": 40000, "loss": 0.0, "lr": 9.694395498016268e-06, "epoch": 498.070796460177, "percentage": 70.97, "elapsed_time": "3:24:10", "remaining_time": "1:23:29", "throughput": 1316.52, "total_tokens": 16127848} {"current_steps": 28395, "total_steps": 40000, "loss": 0.0, "lr": 9.686634154087298e-06, "epoch": 498.1592920353982, "percentage": 70.99, "elapsed_time": "3:24:12", "remaining_time": "1:23:27", "throughput": 1316.51, "total_tokens": 16130488} {"current_steps": 28400, "total_steps": 40000, "loss": 0.0, "lr": 9.678875171671776e-06, "epoch": 498.24778761061947, "percentage": 71.0, "elapsed_time": "3:24:14", "remaining_time": "1:23:25", "throughput": 1316.56, "total_tokens": 16133784} {"current_steps": 28400, "total_steps": 40000, "eval_loss": 0.9244890809059143, "epoch": 498.24778761061947, "percentage": 71.0, "elapsed_time": "3:24:15", "remaining_time": "1:23:25", "throughput": 1316.44, "total_tokens": 16133784} {"current_steps": 28405, "total_steps": 40000, "loss": 0.0, "lr": 9.671118551966246e-06, "epoch": 498.3362831858407, "percentage": 71.01, "elapsed_time": "3:24:19", "remaining_time": "1:23:24", "throughput": 1316.3, "total_tokens": 16137032} {"current_steps": 28410, "total_steps": 40000, "loss": 0.0, "lr": 9.66336429616686e-06, "epoch": 498.42477876106193, "percentage": 71.03, "elapsed_time": "3:24:21", "remaining_time": "1:23:22", "throughput": 1316.31, "total_tokens": 16139944} {"current_steps": 28415, "total_steps": 40000, "loss": 0.0, "lr": 9.655612405469436e-06, "epoch": 498.5132743362832, "percentage": 71.04, "elapsed_time": "3:24:23", "remaining_time": "1:23:19", "throughput": 1316.33, "total_tokens": 16142856} {"current_steps": 28420, "total_steps": 40000, "loss": 0.0, "lr": 9.647862881069413e-06, "epoch": 498.60176991150445, "percentage": 71.05, "elapsed_time": "3:24:25", "remaining_time": "1:23:17", "throughput": 1316.35, "total_tokens": 16145848} {"current_steps": 28425, "total_steps": 40000, "loss": 0.0, "lr": 9.640115724161855e-06, "epoch": 498.69026548672565, "percentage": 71.06, "elapsed_time": "3:24:27", "remaining_time": "1:23:15", "throughput": 1316.34, "total_tokens": 16148488} {"current_steps": 28430, "total_steps": 40000, "loss": 0.0, "lr": 9.632370935941483e-06, "epoch": 498.7787610619469, "percentage": 71.08, "elapsed_time": "3:24:29", "remaining_time": "1:23:13", "throughput": 1316.35, "total_tokens": 16151384} {"current_steps": 28435, "total_steps": 40000, "loss": 0.0, "lr": 9.624628517602634e-06, "epoch": 498.86725663716817, "percentage": 71.09, "elapsed_time": "3:24:31", "remaining_time": "1:23:11", "throughput": 1316.36, "total_tokens": 16154248} {"current_steps": 28440, "total_steps": 40000, "loss": 0.0, "lr": 9.61688847033928e-06, "epoch": 498.95575221238937, "percentage": 71.1, "elapsed_time": "3:24:33", "remaining_time": "1:23:08", "throughput": 1316.38, "total_tokens": 16157208} {"current_steps": 28445, "total_steps": 40000, "loss": 0.0, "lr": 9.609150795345051e-06, "epoch": 499.0353982300885, "percentage": 71.11, "elapsed_time": "3:24:36", "remaining_time": "1:23:06", "throughput": 1316.3, "total_tokens": 16159192} {"current_steps": 28450, "total_steps": 40000, "loss": 0.0, "lr": 9.601415493813171e-06, "epoch": 499.12389380530976, "percentage": 71.12, "elapsed_time": "3:24:38", "remaining_time": "1:23:04", "throughput": 1316.28, "total_tokens": 16161672} {"current_steps": 28455, "total_steps": 40000, "loss": 0.0, "lr": 9.593682566936533e-06, "epoch": 499.21238938053096, "percentage": 71.14, "elapsed_time": "3:24:40", "remaining_time": "1:23:02", "throughput": 1316.3, "total_tokens": 16164632} {"current_steps": 28460, "total_steps": 40000, "loss": 0.0, "lr": 9.58595201590766e-06, "epoch": 499.3008849557522, "percentage": 71.15, "elapsed_time": "3:24:42", "remaining_time": "1:23:00", "throughput": 1316.31, "total_tokens": 16167432} {"current_steps": 28465, "total_steps": 40000, "loss": 0.0, "lr": 9.578223841918681e-06, "epoch": 499.3893805309734, "percentage": 71.16, "elapsed_time": "3:24:44", "remaining_time": "1:22:58", "throughput": 1316.29, "total_tokens": 16170008} {"current_steps": 28470, "total_steps": 40000, "loss": 0.0, "lr": 9.570498046161389e-06, "epoch": 499.4778761061947, "percentage": 71.17, "elapsed_time": "3:24:46", "remaining_time": "1:22:55", "throughput": 1316.3, "total_tokens": 16172872} {"current_steps": 28475, "total_steps": 40000, "loss": 0.0, "lr": 9.562774629827206e-06, "epoch": 499.56637168141594, "percentage": 71.19, "elapsed_time": "3:24:48", "remaining_time": "1:22:53", "throughput": 1316.37, "total_tokens": 16176408} {"current_steps": 28480, "total_steps": 40000, "loss": 0.0, "lr": 9.555053594107163e-06, "epoch": 499.65486725663715, "percentage": 71.2, "elapsed_time": "3:24:50", "remaining_time": "1:22:51", "throughput": 1316.38, "total_tokens": 16179272} {"current_steps": 28485, "total_steps": 40000, "loss": 0.0, "lr": 9.547334940191957e-06, "epoch": 499.7433628318584, "percentage": 71.21, "elapsed_time": "3:24:52", "remaining_time": "1:22:49", "throughput": 1316.42, "total_tokens": 16182472} {"current_steps": 28490, "total_steps": 40000, "loss": 0.0, "lr": 9.539618669271886e-06, "epoch": 499.83185840707966, "percentage": 71.23, "elapsed_time": "3:24:54", "remaining_time": "1:22:47", "throughput": 1316.45, "total_tokens": 16185496} {"current_steps": 28495, "total_steps": 40000, "loss": 0.0, "lr": 9.531904782536904e-06, "epoch": 499.92035398230087, "percentage": 71.24, "elapsed_time": "3:24:56", "remaining_time": "1:22:44", "throughput": 1316.48, "total_tokens": 16188728} {"current_steps": 28500, "total_steps": 40000, "loss": 0.0, "lr": 9.524193281176597e-06, "epoch": 500.0, "percentage": 71.25, "elapsed_time": "3:24:58", "remaining_time": "1:22:42", "throughput": 1316.44, "total_tokens": 16190856} {"current_steps": 28505, "total_steps": 40000, "loss": 0.0, "lr": 9.516484166380165e-06, "epoch": 500.08849557522126, "percentage": 71.26, "elapsed_time": "3:25:01", "remaining_time": "1:22:40", "throughput": 1316.46, "total_tokens": 16194104} {"current_steps": 28510, "total_steps": 40000, "loss": 0.0, "lr": 9.508777439336447e-06, "epoch": 500.17699115044246, "percentage": 71.28, "elapsed_time": "3:25:03", "remaining_time": "1:22:38", "throughput": 1316.45, "total_tokens": 16196776} {"current_steps": 28515, "total_steps": 40000, "loss": 0.0, "lr": 9.50107310123393e-06, "epoch": 500.2654867256637, "percentage": 71.29, "elapsed_time": "3:25:05", "remaining_time": "1:22:36", "throughput": 1316.48, "total_tokens": 16199848} {"current_steps": 28520, "total_steps": 40000, "loss": 0.0, "lr": 9.493371153260702e-06, "epoch": 500.353982300885, "percentage": 71.3, "elapsed_time": "3:25:07", "remaining_time": "1:22:34", "throughput": 1316.48, "total_tokens": 16202504} {"current_steps": 28525, "total_steps": 40000, "loss": 0.0, "lr": 9.485671596604523e-06, "epoch": 500.4424778761062, "percentage": 71.31, "elapsed_time": "3:25:09", "remaining_time": "1:22:31", "throughput": 1316.49, "total_tokens": 16205448} {"current_steps": 28530, "total_steps": 40000, "loss": 0.0, "lr": 9.477974432452738e-06, "epoch": 500.53097345132744, "percentage": 71.33, "elapsed_time": "3:25:11", "remaining_time": "1:22:29", "throughput": 1316.52, "total_tokens": 16208456} {"current_steps": 28535, "total_steps": 40000, "loss": 0.0, "lr": 9.470279661992356e-06, "epoch": 500.6194690265487, "percentage": 71.34, "elapsed_time": "3:25:13", "remaining_time": "1:22:27", "throughput": 1316.5, "total_tokens": 16211032} {"current_steps": 28540, "total_steps": 40000, "loss": 0.0, "lr": 9.462587286410021e-06, "epoch": 500.7079646017699, "percentage": 71.35, "elapsed_time": "3:25:15", "remaining_time": "1:22:25", "throughput": 1316.53, "total_tokens": 16214136} {"current_steps": 28545, "total_steps": 40000, "loss": 0.0, "lr": 9.454897306891972e-06, "epoch": 500.79646017699116, "percentage": 71.36, "elapsed_time": "3:25:17", "remaining_time": "1:22:23", "throughput": 1316.54, "total_tokens": 16216984} {"current_steps": 28550, "total_steps": 40000, "loss": 0.0, "lr": 9.44720972462411e-06, "epoch": 500.88495575221236, "percentage": 71.38, "elapsed_time": "3:25:19", "remaining_time": "1:22:20", "throughput": 1316.57, "total_tokens": 16220072} {"current_steps": 28555, "total_steps": 40000, "loss": 0.0, "lr": 9.439524540791964e-06, "epoch": 500.9734513274336, "percentage": 71.39, "elapsed_time": "3:25:21", "remaining_time": "1:22:18", "throughput": 1316.56, "total_tokens": 16222648} {"current_steps": 28560, "total_steps": 40000, "loss": 0.0, "lr": 9.431841756580673e-06, "epoch": 501.05309734513276, "percentage": 71.4, "elapsed_time": "3:25:24", "remaining_time": "1:22:16", "throughput": 1316.52, "total_tokens": 16225112} {"current_steps": 28565, "total_steps": 40000, "loss": 0.0, "lr": 9.42416137317503e-06, "epoch": 501.14159292035396, "percentage": 71.41, "elapsed_time": "3:25:26", "remaining_time": "1:22:14", "throughput": 1316.55, "total_tokens": 16228200} {"current_steps": 28570, "total_steps": 40000, "loss": 0.0, "lr": 9.416483391759437e-06, "epoch": 501.2300884955752, "percentage": 71.43, "elapsed_time": "3:25:28", "remaining_time": "1:22:12", "throughput": 1316.56, "total_tokens": 16231048} {"current_steps": 28575, "total_steps": 40000, "loss": 0.0, "lr": 9.408807813517945e-06, "epoch": 501.3185840707965, "percentage": 71.44, "elapsed_time": "3:25:30", "remaining_time": "1:22:10", "throughput": 1316.56, "total_tokens": 16233848} {"current_steps": 28580, "total_steps": 40000, "loss": 0.0, "lr": 9.401134639634221e-06, "epoch": 501.4070796460177, "percentage": 71.45, "elapsed_time": "3:25:32", "remaining_time": "1:22:07", "throughput": 1316.57, "total_tokens": 16236648} {"current_steps": 28585, "total_steps": 40000, "loss": 0.0, "lr": 9.393463871291555e-06, "epoch": 501.49557522123894, "percentage": 71.46, "elapsed_time": "3:25:34", "remaining_time": "1:22:05", "throughput": 1316.58, "total_tokens": 16239512} {"current_steps": 28590, "total_steps": 40000, "loss": 0.0, "lr": 9.385795509672881e-06, "epoch": 501.5840707964602, "percentage": 71.47, "elapsed_time": "3:25:36", "remaining_time": "1:22:03", "throughput": 1316.59, "total_tokens": 16242424} {"current_steps": 28595, "total_steps": 40000, "loss": 0.0, "lr": 9.378129555960771e-06, "epoch": 501.6725663716814, "percentage": 71.49, "elapsed_time": "3:25:38", "remaining_time": "1:22:01", "throughput": 1316.61, "total_tokens": 16245352} {"current_steps": 28600, "total_steps": 40000, "loss": 0.0, "lr": 9.370466011337392e-06, "epoch": 501.76106194690266, "percentage": 71.5, "elapsed_time": "3:25:40", "remaining_time": "1:21:59", "throughput": 1316.62, "total_tokens": 16248200} {"current_steps": 28600, "total_steps": 40000, "eval_loss": 0.8963096141815186, "epoch": 501.76106194690266, "percentage": 71.5, "elapsed_time": "3:25:41", "remaining_time": "1:21:59", "throughput": 1316.51, "total_tokens": 16248200} {"current_steps": 28605, "total_steps": 40000, "loss": 0.0, "lr": 9.362804876984573e-06, "epoch": 501.8495575221239, "percentage": 71.51, "elapsed_time": "3:25:47", "remaining_time": "1:21:58", "throughput": 1316.19, "total_tokens": 16251432} {"current_steps": 28610, "total_steps": 40000, "loss": 0.0, "lr": 9.355146154083747e-06, "epoch": 501.9380530973451, "percentage": 71.53, "elapsed_time": "3:25:49", "remaining_time": "1:21:56", "throughput": 1316.18, "total_tokens": 16254008} {"current_steps": 28615, "total_steps": 40000, "loss": 0.0, "lr": 9.347489843815987e-06, "epoch": 502.01769911504425, "percentage": 71.54, "elapsed_time": "3:25:51", "remaining_time": "1:21:54", "throughput": 1316.13, "total_tokens": 16256376} {"current_steps": 28620, "total_steps": 40000, "loss": 0.0, "lr": 9.339835947362002e-06, "epoch": 502.1061946902655, "percentage": 71.55, "elapsed_time": "3:25:53", "remaining_time": "1:21:52", "throughput": 1316.12, "total_tokens": 16258984} {"current_steps": 28625, "total_steps": 40000, "loss": 0.0, "lr": 9.332184465902105e-06, "epoch": 502.1946902654867, "percentage": 71.56, "elapsed_time": "3:25:55", "remaining_time": "1:21:49", "throughput": 1316.12, "total_tokens": 16261784} {"current_steps": 28630, "total_steps": 40000, "loss": 0.0, "lr": 9.324535400616266e-06, "epoch": 502.283185840708, "percentage": 71.58, "elapsed_time": "3:25:57", "remaining_time": "1:21:47", "throughput": 1316.15, "total_tokens": 16264840} {"current_steps": 28635, "total_steps": 40000, "loss": 0.0, "lr": 9.31688875268405e-06, "epoch": 502.37168141592923, "percentage": 71.59, "elapsed_time": "3:25:59", "remaining_time": "1:21:45", "throughput": 1316.17, "total_tokens": 16267768} {"current_steps": 28640, "total_steps": 40000, "loss": 0.0, "lr": 9.309244523284674e-06, "epoch": 502.46017699115043, "percentage": 71.6, "elapsed_time": "3:26:02", "remaining_time": "1:21:43", "throughput": 1316.16, "total_tokens": 16270488} {"current_steps": 28645, "total_steps": 40000, "loss": 0.0, "lr": 9.301602713596982e-06, "epoch": 502.5486725663717, "percentage": 71.61, "elapsed_time": "3:26:04", "remaining_time": "1:21:41", "throughput": 1316.16, "total_tokens": 16273240} {"current_steps": 28650, "total_steps": 40000, "loss": 0.0, "lr": 9.293963324799432e-06, "epoch": 502.6371681415929, "percentage": 71.62, "elapsed_time": "3:26:06", "remaining_time": "1:21:39", "throughput": 1316.17, "total_tokens": 16276024} {"current_steps": 28655, "total_steps": 40000, "loss": 0.0, "lr": 9.286326358070104e-06, "epoch": 502.72566371681415, "percentage": 71.64, "elapsed_time": "3:26:08", "remaining_time": "1:21:36", "throughput": 1316.19, "total_tokens": 16278952} {"current_steps": 28660, "total_steps": 40000, "loss": 0.0, "lr": 9.278691814586729e-06, "epoch": 502.8141592920354, "percentage": 71.65, "elapsed_time": "3:26:10", "remaining_time": "1:21:34", "throughput": 1316.23, "total_tokens": 16282248} {"current_steps": 28665, "total_steps": 40000, "loss": 0.0, "lr": 9.271059695526635e-06, "epoch": 502.9026548672566, "percentage": 71.66, "elapsed_time": "3:26:12", "remaining_time": "1:21:32", "throughput": 1316.24, "total_tokens": 16285032} {"current_steps": 28670, "total_steps": 40000, "loss": 0.0, "lr": 9.263430002066805e-06, "epoch": 502.9911504424779, "percentage": 71.67, "elapsed_time": "3:26:14", "remaining_time": "1:21:30", "throughput": 1316.25, "total_tokens": 16287864} {"current_steps": 28675, "total_steps": 40000, "loss": 0.0, "lr": 9.25580273538382e-06, "epoch": 503.070796460177, "percentage": 71.69, "elapsed_time": "3:26:16", "remaining_time": "1:21:28", "throughput": 1316.2, "total_tokens": 16290344} {"current_steps": 28680, "total_steps": 40000, "loss": 0.0, "lr": 9.248177896653907e-06, "epoch": 503.1592920353982, "percentage": 71.7, "elapsed_time": "3:26:18", "remaining_time": "1:21:25", "throughput": 1316.19, "total_tokens": 16292936} {"current_steps": 28685, "total_steps": 40000, "loss": 0.0, "lr": 9.240555487052918e-06, "epoch": 503.24778761061947, "percentage": 71.71, "elapsed_time": "3:26:20", "remaining_time": "1:21:23", "throughput": 1316.24, "total_tokens": 16296264} {"current_steps": 28690, "total_steps": 40000, "loss": 0.0, "lr": 9.232935507756313e-06, "epoch": 503.3362831858407, "percentage": 71.73, "elapsed_time": "3:26:22", "remaining_time": "1:21:21", "throughput": 1316.21, "total_tokens": 16298648} {"current_steps": 28695, "total_steps": 40000, "loss": 0.0, "lr": 9.225317959939193e-06, "epoch": 503.42477876106193, "percentage": 71.74, "elapsed_time": "3:26:25", "remaining_time": "1:21:19", "throughput": 1316.22, "total_tokens": 16301512} {"current_steps": 28700, "total_steps": 40000, "loss": 0.0, "lr": 9.217702844776287e-06, "epoch": 503.5132743362832, "percentage": 71.75, "elapsed_time": "3:26:27", "remaining_time": "1:21:17", "throughput": 1316.24, "total_tokens": 16304440} {"current_steps": 28705, "total_steps": 40000, "loss": 0.0, "lr": 9.210090163441929e-06, "epoch": 503.60176991150445, "percentage": 71.76, "elapsed_time": "3:26:29", "remaining_time": "1:21:14", "throughput": 1316.23, "total_tokens": 16307096} {"current_steps": 28710, "total_steps": 40000, "loss": 0.0, "lr": 9.202479917110105e-06, "epoch": 503.69026548672565, "percentage": 71.78, "elapsed_time": "3:26:31", "remaining_time": "1:21:12", "throughput": 1316.26, "total_tokens": 16310216} {"current_steps": 28715, "total_steps": 40000, "loss": 0.0, "lr": 9.194872106954392e-06, "epoch": 503.7787610619469, "percentage": 71.79, "elapsed_time": "3:26:33", "remaining_time": "1:21:10", "throughput": 1316.26, "total_tokens": 16312904} {"current_steps": 28720, "total_steps": 40000, "loss": 0.0, "lr": 9.187266734148029e-06, "epoch": 503.86725663716817, "percentage": 71.8, "elapsed_time": "3:26:35", "remaining_time": "1:21:08", "throughput": 1316.29, "total_tokens": 16316040} {"current_steps": 28725, "total_steps": 40000, "loss": 0.0, "lr": 9.179663799863849e-06, "epoch": 503.95575221238937, "percentage": 71.81, "elapsed_time": "3:26:37", "remaining_time": "1:21:06", "throughput": 1316.33, "total_tokens": 16319224} {"current_steps": 28730, "total_steps": 40000, "loss": 0.0, "lr": 9.172063305274317e-06, "epoch": 504.0353982300885, "percentage": 71.83, "elapsed_time": "3:26:39", "remaining_time": "1:21:04", "throughput": 1316.31, "total_tokens": 16321928} {"current_steps": 28735, "total_steps": 40000, "loss": 0.0, "lr": 9.164465251551527e-06, "epoch": 504.12389380530976, "percentage": 71.84, "elapsed_time": "3:26:41", "remaining_time": "1:21:01", "throughput": 1316.29, "total_tokens": 16324424} {"current_steps": 28740, "total_steps": 40000, "loss": 0.0, "lr": 9.156869639867205e-06, "epoch": 504.21238938053096, "percentage": 71.85, "elapsed_time": "3:26:43", "remaining_time": "1:20:59", "throughput": 1316.29, "total_tokens": 16327096} {"current_steps": 28745, "total_steps": 40000, "loss": 0.0, "lr": 9.149276471392677e-06, "epoch": 504.3008849557522, "percentage": 71.86, "elapsed_time": "3:26:45", "remaining_time": "1:20:57", "throughput": 1316.29, "total_tokens": 16329848} {"current_steps": 28750, "total_steps": 40000, "loss": 0.0, "lr": 9.141685747298914e-06, "epoch": 504.3893805309734, "percentage": 71.88, "elapsed_time": "3:26:48", "remaining_time": "1:20:55", "throughput": 1316.32, "total_tokens": 16332984} {"current_steps": 28755, "total_steps": 40000, "loss": 0.0, "lr": 9.13409746875649e-06, "epoch": 504.4778761061947, "percentage": 71.89, "elapsed_time": "3:26:50", "remaining_time": "1:20:53", "throughput": 1316.3, "total_tokens": 16335496} {"current_steps": 28760, "total_steps": 40000, "loss": 0.0, "lr": 9.12651163693562e-06, "epoch": 504.56637168141594, "percentage": 71.9, "elapsed_time": "3:26:52", "remaining_time": "1:20:50", "throughput": 1316.32, "total_tokens": 16338520} {"current_steps": 28765, "total_steps": 40000, "loss": 0.0, "lr": 9.11892825300614e-06, "epoch": 504.65486725663715, "percentage": 71.91, "elapsed_time": "3:26:54", "remaining_time": "1:20:48", "throughput": 1316.36, "total_tokens": 16341640} {"current_steps": 28770, "total_steps": 40000, "loss": 0.0, "lr": 9.111347318137491e-06, "epoch": 504.7433628318584, "percentage": 71.92, "elapsed_time": "3:26:56", "remaining_time": "1:20:46", "throughput": 1316.39, "total_tokens": 16344840} {"current_steps": 28775, "total_steps": 40000, "loss": 0.0, "lr": 9.103768833498755e-06, "epoch": 504.83185840707966, "percentage": 71.94, "elapsed_time": "3:26:58", "remaining_time": "1:20:44", "throughput": 1316.42, "total_tokens": 16347896} {"current_steps": 28780, "total_steps": 40000, "loss": 0.0, "lr": 9.096192800258639e-06, "epoch": 504.92035398230087, "percentage": 71.95, "elapsed_time": "3:27:00", "remaining_time": "1:20:42", "throughput": 1316.44, "total_tokens": 16350840} {"current_steps": 28785, "total_steps": 40000, "loss": 0.0, "lr": 9.088619219585443e-06, "epoch": 505.0, "percentage": 71.96, "elapsed_time": "3:27:02", "remaining_time": "1:20:39", "throughput": 1316.43, "total_tokens": 16353448} {"current_steps": 28790, "total_steps": 40000, "loss": 0.0, "lr": 9.081048092647127e-06, "epoch": 505.08849557522126, "percentage": 71.97, "elapsed_time": "3:27:04", "remaining_time": "1:20:37", "throughput": 1316.4, "total_tokens": 16356024} {"current_steps": 28795, "total_steps": 40000, "loss": 0.0, "lr": 9.073479420611245e-06, "epoch": 505.17699115044246, "percentage": 71.99, "elapsed_time": "3:27:06", "remaining_time": "1:20:35", "throughput": 1316.42, "total_tokens": 16359016} {"current_steps": 28800, "total_steps": 40000, "loss": 0.0, "lr": 9.065913204644974e-06, "epoch": 505.2654867256637, "percentage": 72.0, "elapsed_time": "3:27:08", "remaining_time": "1:20:33", "throughput": 1316.4, "total_tokens": 16361560} {"current_steps": 28800, "total_steps": 40000, "eval_loss": 0.9023752808570862, "epoch": 505.2654867256637, "percentage": 72.0, "elapsed_time": "3:27:10", "remaining_time": "1:20:33", "throughput": 1316.29, "total_tokens": 16361560} {"current_steps": 28805, "total_steps": 40000, "loss": 0.0, "lr": 9.058349445915135e-06, "epoch": 505.353982300885, "percentage": 72.01, "elapsed_time": "3:27:13", "remaining_time": "1:20:32", "throughput": 1316.1, "total_tokens": 16364184} {"current_steps": 28810, "total_steps": 40000, "loss": 0.0, "lr": 9.050788145588138e-06, "epoch": 505.4424778761062, "percentage": 72.02, "elapsed_time": "3:27:15", "remaining_time": "1:20:30", "throughput": 1316.11, "total_tokens": 16367160} {"current_steps": 28815, "total_steps": 40000, "loss": 0.0, "lr": 9.043229304830039e-06, "epoch": 505.53097345132744, "percentage": 72.04, "elapsed_time": "3:27:18", "remaining_time": "1:20:28", "throughput": 1316.14, "total_tokens": 16370264} {"current_steps": 28820, "total_steps": 40000, "loss": 0.0, "lr": 9.035672924806515e-06, "epoch": 505.6194690265487, "percentage": 72.05, "elapsed_time": "3:27:20", "remaining_time": "1:20:25", "throughput": 1316.16, "total_tokens": 16373224} {"current_steps": 28825, "total_steps": 40000, "loss": 0.0, "lr": 9.028119006682839e-06, "epoch": 505.7079646017699, "percentage": 72.06, "elapsed_time": "3:27:22", "remaining_time": "1:20:23", "throughput": 1316.16, "total_tokens": 16375992} {"current_steps": 28830, "total_steps": 40000, "loss": 0.0, "lr": 9.020567551623935e-06, "epoch": 505.79646017699116, "percentage": 72.08, "elapsed_time": "3:27:24", "remaining_time": "1:20:21", "throughput": 1316.19, "total_tokens": 16379000} {"current_steps": 28835, "total_steps": 40000, "loss": 0.0, "lr": 9.013018560794318e-06, "epoch": 505.88495575221236, "percentage": 72.09, "elapsed_time": "3:27:26", "remaining_time": "1:20:19", "throughput": 1316.18, "total_tokens": 16381640} {"current_steps": 28840, "total_steps": 40000, "loss": 0.0, "lr": 9.005472035358139e-06, "epoch": 505.9734513274336, "percentage": 72.1, "elapsed_time": "3:27:28", "remaining_time": "1:20:17", "throughput": 1316.21, "total_tokens": 16384680} {"current_steps": 28845, "total_steps": 40000, "loss": 0.0, "lr": 8.997927976479185e-06, "epoch": 506.05309734513276, "percentage": 72.11, "elapsed_time": "3:27:30", "remaining_time": "1:20:14", "throughput": 1316.2, "total_tokens": 16387568} {"current_steps": 28850, "total_steps": 40000, "loss": 0.0, "lr": 8.99038638532082e-06, "epoch": 506.14159292035396, "percentage": 72.12, "elapsed_time": "3:27:32", "remaining_time": "1:20:12", "throughput": 1316.23, "total_tokens": 16390688} {"current_steps": 28855, "total_steps": 40000, "loss": 0.0, "lr": 8.982847263046065e-06, "epoch": 506.2300884955752, "percentage": 72.14, "elapsed_time": "3:27:34", "remaining_time": "1:20:10", "throughput": 1316.21, "total_tokens": 16393184} {"current_steps": 28860, "total_steps": 40000, "loss": 0.0, "lr": 8.975310610817555e-06, "epoch": 506.3185840707965, "percentage": 72.15, "elapsed_time": "3:27:36", "remaining_time": "1:20:08", "throughput": 1316.24, "total_tokens": 16396352} {"current_steps": 28865, "total_steps": 40000, "loss": 0.0, "lr": 8.967776429797528e-06, "epoch": 506.4070796460177, "percentage": 72.16, "elapsed_time": "3:27:38", "remaining_time": "1:20:06", "throughput": 1316.27, "total_tokens": 16399376} {"current_steps": 28870, "total_steps": 40000, "loss": 0.0, "lr": 8.960244721147842e-06, "epoch": 506.49557522123894, "percentage": 72.17, "elapsed_time": "3:27:41", "remaining_time": "1:20:04", "throughput": 1316.26, "total_tokens": 16402032} {"current_steps": 28875, "total_steps": 40000, "loss": 0.0, "lr": 8.952715486029995e-06, "epoch": 506.5840707964602, "percentage": 72.19, "elapsed_time": "3:27:43", "remaining_time": "1:20:01", "throughput": 1316.3, "total_tokens": 16405216} {"current_steps": 28880, "total_steps": 40000, "loss": 0.0, "lr": 8.945188725605075e-06, "epoch": 506.6725663716814, "percentage": 72.2, "elapsed_time": "3:27:45", "remaining_time": "1:19:59", "throughput": 1316.32, "total_tokens": 16408240} {"current_steps": 28885, "total_steps": 40000, "loss": 0.0, "lr": 8.937664441033817e-06, "epoch": 506.76106194690266, "percentage": 72.21, "elapsed_time": "3:27:47", "remaining_time": "1:19:57", "throughput": 1316.29, "total_tokens": 16410608} {"current_steps": 28890, "total_steps": 40000, "loss": 0.0, "lr": 8.930142633476549e-06, "epoch": 506.8495575221239, "percentage": 72.22, "elapsed_time": "3:27:49", "remaining_time": "1:19:55", "throughput": 1316.31, "total_tokens": 16413552} {"current_steps": 28895, "total_steps": 40000, "loss": 0.0, "lr": 8.92262330409323e-06, "epoch": 506.9380530973451, "percentage": 72.24, "elapsed_time": "3:27:51", "remaining_time": "1:19:53", "throughput": 1316.33, "total_tokens": 16416544} {"current_steps": 28900, "total_steps": 40000, "loss": 0.0, "lr": 8.915106454043448e-06, "epoch": 507.01769911504425, "percentage": 72.25, "elapsed_time": "3:27:53", "remaining_time": "1:19:50", "throughput": 1316.29, "total_tokens": 16419008} {"current_steps": 28905, "total_steps": 40000, "loss": 0.0, "lr": 8.90759208448638e-06, "epoch": 507.1061946902655, "percentage": 72.26, "elapsed_time": "3:27:55", "remaining_time": "1:19:48", "throughput": 1316.32, "total_tokens": 16422096} {"current_steps": 28910, "total_steps": 40000, "loss": 0.0, "lr": 8.900080196580848e-06, "epoch": 507.1946902654867, "percentage": 72.28, "elapsed_time": "3:27:57", "remaining_time": "1:19:46", "throughput": 1316.29, "total_tokens": 16424464} {"current_steps": 28915, "total_steps": 40000, "loss": 0.0, "lr": 8.892570791485267e-06, "epoch": 507.283185840708, "percentage": 72.29, "elapsed_time": "3:27:59", "remaining_time": "1:19:44", "throughput": 1316.31, "total_tokens": 16427456} {"current_steps": 28920, "total_steps": 40000, "loss": 0.0, "lr": 8.885063870357688e-06, "epoch": 507.37168141592923, "percentage": 72.3, "elapsed_time": "3:28:01", "remaining_time": "1:19:42", "throughput": 1316.29, "total_tokens": 16429840} {"current_steps": 28925, "total_steps": 40000, "loss": 0.0, "lr": 8.87755943435578e-06, "epoch": 507.46017699115043, "percentage": 72.31, "elapsed_time": "3:28:04", "remaining_time": "1:19:39", "throughput": 1316.32, "total_tokens": 16432976} {"current_steps": 28930, "total_steps": 40000, "loss": 0.0, "lr": 8.87005748463681e-06, "epoch": 507.5486725663717, "percentage": 72.32, "elapsed_time": "3:28:06", "remaining_time": "1:19:37", "throughput": 1316.31, "total_tokens": 16435584} {"current_steps": 28935, "total_steps": 40000, "loss": 0.0, "lr": 8.862558022357681e-06, "epoch": 507.6371681415929, "percentage": 72.34, "elapsed_time": "3:28:08", "remaining_time": "1:19:35", "throughput": 1316.33, "total_tokens": 16438512} {"current_steps": 28940, "total_steps": 40000, "loss": 0.0, "lr": 8.855061048674903e-06, "epoch": 507.72566371681415, "percentage": 72.35, "elapsed_time": "3:28:10", "remaining_time": "1:19:33", "throughput": 1316.32, "total_tokens": 16441184} {"current_steps": 28945, "total_steps": 40000, "loss": 0.0, "lr": 8.847566564744595e-06, "epoch": 507.8141592920354, "percentage": 72.36, "elapsed_time": "3:28:12", "remaining_time": "1:19:31", "throughput": 1316.31, "total_tokens": 16443776} {"current_steps": 28950, "total_steps": 40000, "loss": 0.0, "lr": 8.840074571722512e-06, "epoch": 507.9026548672566, "percentage": 72.38, "elapsed_time": "3:28:14", "remaining_time": "1:19:29", "throughput": 1316.31, "total_tokens": 16446544} {"current_steps": 28955, "total_steps": 40000, "loss": 0.0, "lr": 8.832585070764002e-06, "epoch": 507.9911504424779, "percentage": 72.39, "elapsed_time": "3:28:16", "remaining_time": "1:19:26", "throughput": 1316.38, "total_tokens": 16450080} {"current_steps": 28960, "total_steps": 40000, "loss": 0.0, "lr": 8.825098063024045e-06, "epoch": 508.070796460177, "percentage": 72.4, "elapsed_time": "3:28:18", "remaining_time": "1:19:24", "throughput": 1316.33, "total_tokens": 16452536} {"current_steps": 28965, "total_steps": 40000, "loss": 0.0, "lr": 8.817613549657244e-06, "epoch": 508.1592920353982, "percentage": 72.41, "elapsed_time": "3:28:20", "remaining_time": "1:19:22", "throughput": 1316.32, "total_tokens": 16455144} {"current_steps": 28970, "total_steps": 40000, "loss": 0.0, "lr": 8.810131531817783e-06, "epoch": 508.24778761061947, "percentage": 72.42, "elapsed_time": "3:28:22", "remaining_time": "1:19:20", "throughput": 1316.35, "total_tokens": 16458168} {"current_steps": 28975, "total_steps": 40000, "loss": 0.0, "lr": 8.802652010659496e-06, "epoch": 508.3362831858407, "percentage": 72.44, "elapsed_time": "3:28:24", "remaining_time": "1:19:18", "throughput": 1316.36, "total_tokens": 16461112} {"current_steps": 28980, "total_steps": 40000, "loss": 0.0, "lr": 8.795174987335827e-06, "epoch": 508.42477876106193, "percentage": 72.45, "elapsed_time": "3:28:27", "remaining_time": "1:19:15", "throughput": 1316.4, "total_tokens": 16464376} {"current_steps": 28985, "total_steps": 40000, "loss": 0.0, "lr": 8.787700462999807e-06, "epoch": 508.5132743362832, "percentage": 72.46, "elapsed_time": "3:28:29", "remaining_time": "1:19:13", "throughput": 1316.43, "total_tokens": 16467480} {"current_steps": 28990, "total_steps": 40000, "loss": 0.0, "lr": 8.780228438804122e-06, "epoch": 508.60176991150445, "percentage": 72.47, "elapsed_time": "3:28:31", "remaining_time": "1:19:11", "throughput": 1316.44, "total_tokens": 16470344} {"current_steps": 28995, "total_steps": 40000, "loss": 0.0, "lr": 8.772758915901032e-06, "epoch": 508.69026548672565, "percentage": 72.49, "elapsed_time": "3:28:33", "remaining_time": "1:19:09", "throughput": 1316.42, "total_tokens": 16472792} {"current_steps": 29000, "total_steps": 40000, "loss": 0.0, "lr": 8.765291895442443e-06, "epoch": 508.7787610619469, "percentage": 72.5, "elapsed_time": "3:28:35", "remaining_time": "1:19:07", "throughput": 1316.43, "total_tokens": 16475624} {"current_steps": 29000, "total_steps": 40000, "eval_loss": 0.9256235361099243, "epoch": 508.7787610619469, "percentage": 72.5, "elapsed_time": "3:28:36", "remaining_time": "1:19:07", "throughput": 1316.32, "total_tokens": 16475624} {"current_steps": 29005, "total_steps": 40000, "loss": 0.0, "lr": 8.75782737857987e-06, "epoch": 508.86725663716817, "percentage": 72.51, "elapsed_time": "3:28:40", "remaining_time": "1:19:06", "throughput": 1316.17, "total_tokens": 16478728} {"current_steps": 29010, "total_steps": 40000, "loss": 0.0, "lr": 8.750365366464425e-06, "epoch": 508.95575221238937, "percentage": 72.52, "elapsed_time": "3:28:42", "remaining_time": "1:19:03", "throughput": 1316.16, "total_tokens": 16481352} {"current_steps": 29015, "total_steps": 40000, "loss": 0.0, "lr": 8.742905860246838e-06, "epoch": 509.0353982300885, "percentage": 72.54, "elapsed_time": "3:28:44", "remaining_time": "1:19:01", "throughput": 1316.1, "total_tokens": 16483560} {"current_steps": 29020, "total_steps": 40000, "loss": 0.0, "lr": 8.735448861077478e-06, "epoch": 509.12389380530976, "percentage": 72.55, "elapsed_time": "3:28:46", "remaining_time": "1:18:59", "throughput": 1316.09, "total_tokens": 16486200} {"current_steps": 29025, "total_steps": 40000, "loss": 0.0, "lr": 8.727994370106288e-06, "epoch": 509.21238938053096, "percentage": 72.56, "elapsed_time": "3:28:48", "remaining_time": "1:18:57", "throughput": 1316.08, "total_tokens": 16488856} {"current_steps": 29030, "total_steps": 40000, "loss": 0.0, "lr": 8.720542388482861e-06, "epoch": 509.3008849557522, "percentage": 72.58, "elapsed_time": "3:28:50", "remaining_time": "1:18:55", "throughput": 1316.09, "total_tokens": 16491672} {"current_steps": 29035, "total_steps": 40000, "loss": 0.0, "lr": 8.71309291735637e-06, "epoch": 509.3893805309734, "percentage": 72.59, "elapsed_time": "3:28:52", "remaining_time": "1:18:53", "throughput": 1316.13, "total_tokens": 16494904} {"current_steps": 29040, "total_steps": 40000, "loss": 0.0, "lr": 8.705645957875621e-06, "epoch": 509.4778761061947, "percentage": 72.6, "elapsed_time": "3:28:54", "remaining_time": "1:18:50", "throughput": 1316.15, "total_tokens": 16497816} {"current_steps": 29045, "total_steps": 40000, "loss": 0.0, "lr": 8.698201511189048e-06, "epoch": 509.56637168141594, "percentage": 72.61, "elapsed_time": "3:28:57", "remaining_time": "1:18:48", "throughput": 1316.18, "total_tokens": 16500984} {"current_steps": 29050, "total_steps": 40000, "loss": 0.0, "lr": 8.690759578444649e-06, "epoch": 509.65486725663715, "percentage": 72.62, "elapsed_time": "3:28:59", "remaining_time": "1:18:46", "throughput": 1316.19, "total_tokens": 16503864} {"current_steps": 29055, "total_steps": 40000, "loss": 0.0, "lr": 8.68332016079008e-06, "epoch": 509.7433628318584, "percentage": 72.64, "elapsed_time": "3:29:01", "remaining_time": "1:18:44", "throughput": 1316.23, "total_tokens": 16507080} {"current_steps": 29060, "total_steps": 40000, "loss": 0.0, "lr": 8.6758832593726e-06, "epoch": 509.83185840707966, "percentage": 72.65, "elapsed_time": "3:29:03", "remaining_time": "1:18:42", "throughput": 1316.22, "total_tokens": 16509768} {"current_steps": 29065, "total_steps": 40000, "loss": 0.0, "lr": 8.668448875339053e-06, "epoch": 509.92035398230087, "percentage": 72.66, "elapsed_time": "3:29:05", "remaining_time": "1:18:39", "throughput": 1316.21, "total_tokens": 16512296} {"current_steps": 29070, "total_steps": 40000, "loss": 0.0, "lr": 8.661017009835933e-06, "epoch": 510.0, "percentage": 72.67, "elapsed_time": "3:29:07", "remaining_time": "1:18:37", "throughput": 1316.19, "total_tokens": 16514688} {"current_steps": 29075, "total_steps": 40000, "loss": 0.0, "lr": 8.653587664009311e-06, "epoch": 510.08849557522126, "percentage": 72.69, "elapsed_time": "3:29:09", "remaining_time": "1:18:35", "throughput": 1316.19, "total_tokens": 16517760} {"current_steps": 29080, "total_steps": 40000, "loss": 0.0, "lr": 8.646160839004902e-06, "epoch": 510.17699115044246, "percentage": 72.7, "elapsed_time": "3:29:11", "remaining_time": "1:18:33", "throughput": 1316.21, "total_tokens": 16520672} {"current_steps": 29085, "total_steps": 40000, "loss": 0.0, "lr": 8.638736535967998e-06, "epoch": 510.2654867256637, "percentage": 72.71, "elapsed_time": "3:29:13", "remaining_time": "1:18:31", "throughput": 1316.22, "total_tokens": 16523504} {"current_steps": 29090, "total_steps": 40000, "loss": 0.0, "lr": 8.631314756043535e-06, "epoch": 510.353982300885, "percentage": 72.72, "elapsed_time": "3:29:15", "remaining_time": "1:18:28", "throughput": 1316.24, "total_tokens": 16526496} {"current_steps": 29095, "total_steps": 40000, "loss": 0.0, "lr": 8.62389550037603e-06, "epoch": 510.4424778761062, "percentage": 72.74, "elapsed_time": "3:29:17", "remaining_time": "1:18:26", "throughput": 1316.25, "total_tokens": 16529376} {"current_steps": 29100, "total_steps": 40000, "loss": 0.0, "lr": 8.616478770109646e-06, "epoch": 510.53097345132744, "percentage": 72.75, "elapsed_time": "3:29:20", "remaining_time": "1:18:24", "throughput": 1316.28, "total_tokens": 16532480} {"current_steps": 29105, "total_steps": 40000, "loss": 0.0, "lr": 8.609064566388111e-06, "epoch": 510.6194690265487, "percentage": 72.76, "elapsed_time": "3:29:22", "remaining_time": "1:18:22", "throughput": 1316.27, "total_tokens": 16535088} {"current_steps": 29110, "total_steps": 40000, "loss": 0.0, "lr": 8.601652890354815e-06, "epoch": 510.7079646017699, "percentage": 72.78, "elapsed_time": "3:29:24", "remaining_time": "1:18:20", "throughput": 1316.31, "total_tokens": 16538384} {"current_steps": 29115, "total_steps": 40000, "loss": 0.0, "lr": 8.594243743152705e-06, "epoch": 510.79646017699116, "percentage": 72.79, "elapsed_time": "3:29:26", "remaining_time": "1:18:18", "throughput": 1316.32, "total_tokens": 16541168} {"current_steps": 29120, "total_steps": 40000, "loss": 0.0, "lr": 8.58683712592438e-06, "epoch": 510.88495575221236, "percentage": 72.8, "elapsed_time": "3:29:28", "remaining_time": "1:18:15", "throughput": 1316.31, "total_tokens": 16543808} {"current_steps": 29125, "total_steps": 40000, "loss": 0.0, "lr": 8.579433039812037e-06, "epoch": 510.9734513274336, "percentage": 72.81, "elapsed_time": "3:29:30", "remaining_time": "1:18:13", "throughput": 1316.32, "total_tokens": 16546624} {"current_steps": 29130, "total_steps": 40000, "loss": 0.0, "lr": 8.572031485957466e-06, "epoch": 511.05309734513276, "percentage": 72.82, "elapsed_time": "3:29:32", "remaining_time": "1:18:11", "throughput": 1316.26, "total_tokens": 16548824} {"current_steps": 29135, "total_steps": 40000, "loss": 0.0, "lr": 8.564632465502084e-06, "epoch": 511.14159292035396, "percentage": 72.84, "elapsed_time": "3:29:34", "remaining_time": "1:18:09", "throughput": 1316.24, "total_tokens": 16551416} {"current_steps": 29140, "total_steps": 40000, "loss": 0.0, "lr": 8.557235979586928e-06, "epoch": 511.2300884955752, "percentage": 72.85, "elapsed_time": "3:29:36", "remaining_time": "1:18:07", "throughput": 1316.28, "total_tokens": 16554536} {"current_steps": 29145, "total_steps": 40000, "loss": 0.0, "lr": 8.549842029352606e-06, "epoch": 511.3185840707965, "percentage": 72.86, "elapsed_time": "3:29:38", "remaining_time": "1:18:04", "throughput": 1316.26, "total_tokens": 16557032} {"current_steps": 29150, "total_steps": 40000, "loss": 0.0, "lr": 8.542450615939376e-06, "epoch": 511.4070796460177, "percentage": 72.88, "elapsed_time": "3:29:40", "remaining_time": "1:18:02", "throughput": 1316.26, "total_tokens": 16559880} {"current_steps": 29155, "total_steps": 40000, "loss": 0.0, "lr": 8.535061740487082e-06, "epoch": 511.49557522123894, "percentage": 72.89, "elapsed_time": "3:29:43", "remaining_time": "1:18:00", "throughput": 1316.28, "total_tokens": 16562824} {"current_steps": 29160, "total_steps": 40000, "loss": 0.0, "lr": 8.527675404135168e-06, "epoch": 511.5840707964602, "percentage": 72.9, "elapsed_time": "3:29:45", "remaining_time": "1:17:58", "throughput": 1316.3, "total_tokens": 16565800} {"current_steps": 29165, "total_steps": 40000, "loss": 0.0, "lr": 8.520291608022724e-06, "epoch": 511.6725663716814, "percentage": 72.91, "elapsed_time": "3:29:47", "remaining_time": "1:17:56", "throughput": 1316.29, "total_tokens": 16568408} {"current_steps": 29170, "total_steps": 40000, "loss": 0.0, "lr": 8.512910353288398e-06, "epoch": 511.76106194690266, "percentage": 72.92, "elapsed_time": "3:29:49", "remaining_time": "1:17:54", "throughput": 1316.32, "total_tokens": 16571496} {"current_steps": 29175, "total_steps": 40000, "loss": 0.0, "lr": 8.505531641070486e-06, "epoch": 511.8495575221239, "percentage": 72.94, "elapsed_time": "3:29:51", "remaining_time": "1:17:51", "throughput": 1316.39, "total_tokens": 16575064} {"current_steps": 29180, "total_steps": 40000, "loss": 0.0, "lr": 8.498155472506885e-06, "epoch": 511.9380530973451, "percentage": 72.95, "elapsed_time": "3:29:53", "remaining_time": "1:17:49", "throughput": 1316.39, "total_tokens": 16577848} {"current_steps": 29185, "total_steps": 40000, "loss": 0.0, "lr": 8.49078184873508e-06, "epoch": 512.0176991150443, "percentage": 72.96, "elapsed_time": "3:29:55", "remaining_time": "1:17:47", "throughput": 1316.35, "total_tokens": 16580344} {"current_steps": 29190, "total_steps": 40000, "loss": 0.0, "lr": 8.483410770892188e-06, "epoch": 512.1061946902655, "percentage": 72.97, "elapsed_time": "3:29:57", "remaining_time": "1:17:45", "throughput": 1316.36, "total_tokens": 16583176} {"current_steps": 29195, "total_steps": 40000, "loss": 0.0, "lr": 8.476042240114909e-06, "epoch": 512.1946902654868, "percentage": 72.99, "elapsed_time": "3:29:59", "remaining_time": "1:17:43", "throughput": 1316.39, "total_tokens": 16586280} {"current_steps": 29200, "total_steps": 40000, "loss": 0.0, "lr": 8.468676257539568e-06, "epoch": 512.2831858407079, "percentage": 73.0, "elapsed_time": "3:30:01", "remaining_time": "1:17:40", "throughput": 1316.39, "total_tokens": 16588984} {"current_steps": 29200, "total_steps": 40000, "eval_loss": 0.9239405989646912, "epoch": 512.2831858407079, "percentage": 73.0, "elapsed_time": "3:30:02", "remaining_time": "1:17:41", "throughput": 1316.28, "total_tokens": 16588984} {"current_steps": 29205, "total_steps": 40000, "loss": 0.0, "lr": 8.4613128243021e-06, "epoch": 512.3716814159292, "percentage": 73.01, "elapsed_time": "3:30:06", "remaining_time": "1:17:39", "throughput": 1316.11, "total_tokens": 16591880} {"current_steps": 29210, "total_steps": 40000, "loss": 0.0, "lr": 8.453951941538028e-06, "epoch": 512.4601769911504, "percentage": 73.02, "elapsed_time": "3:30:08", "remaining_time": "1:17:37", "throughput": 1316.17, "total_tokens": 16595352} {"current_steps": 29215, "total_steps": 40000, "loss": 0.0, "lr": 8.446593610382495e-06, "epoch": 512.5486725663717, "percentage": 73.04, "elapsed_time": "3:30:10", "remaining_time": "1:17:35", "throughput": 1316.13, "total_tokens": 16597560} {"current_steps": 29220, "total_steps": 40000, "loss": 0.0, "lr": 8.439237831970259e-06, "epoch": 512.637168141593, "percentage": 73.05, "elapsed_time": "3:30:12", "remaining_time": "1:17:33", "throughput": 1316.14, "total_tokens": 16600440} {"current_steps": 29225, "total_steps": 40000, "loss": 0.0, "lr": 8.431884607435667e-06, "epoch": 512.7256637168142, "percentage": 73.06, "elapsed_time": "3:30:15", "remaining_time": "1:17:31", "throughput": 1316.16, "total_tokens": 16603464} {"current_steps": 29230, "total_steps": 40000, "loss": 0.0, "lr": 8.424533937912665e-06, "epoch": 512.8141592920354, "percentage": 73.08, "elapsed_time": "3:30:17", "remaining_time": "1:17:28", "throughput": 1316.17, "total_tokens": 16606360} {"current_steps": 29235, "total_steps": 40000, "loss": 0.0, "lr": 8.41718582453484e-06, "epoch": 512.9026548672566, "percentage": 73.09, "elapsed_time": "3:30:19", "remaining_time": "1:17:26", "throughput": 1316.18, "total_tokens": 16609224} {"current_steps": 29240, "total_steps": 40000, "loss": 0.0, "lr": 8.409840268435346e-06, "epoch": 512.9911504424779, "percentage": 73.1, "elapsed_time": "3:30:21", "remaining_time": "1:17:24", "throughput": 1316.2, "total_tokens": 16612152} {"current_steps": 29245, "total_steps": 40000, "loss": 0.0, "lr": 8.402497270746976e-06, "epoch": 513.070796460177, "percentage": 73.11, "elapsed_time": "3:30:23", "remaining_time": "1:17:22", "throughput": 1316.18, "total_tokens": 16614920} {"current_steps": 29250, "total_steps": 40000, "loss": 0.0, "lr": 8.395156832602095e-06, "epoch": 513.1592920353983, "percentage": 73.12, "elapsed_time": "3:30:25", "remaining_time": "1:17:20", "throughput": 1316.18, "total_tokens": 16617624} {"current_steps": 29255, "total_steps": 40000, "loss": 0.0, "lr": 8.387818955132707e-06, "epoch": 513.2477876106195, "percentage": 73.14, "elapsed_time": "3:30:27", "remaining_time": "1:17:18", "throughput": 1316.18, "total_tokens": 16620296} {"current_steps": 29260, "total_steps": 40000, "loss": 0.0, "lr": 8.38048363947039e-06, "epoch": 513.3362831858407, "percentage": 73.15, "elapsed_time": "3:30:29", "remaining_time": "1:17:15", "throughput": 1316.2, "total_tokens": 16623352} {"current_steps": 29265, "total_steps": 40000, "loss": 0.0, "lr": 8.373150886746351e-06, "epoch": 513.4247787610619, "percentage": 73.16, "elapsed_time": "3:30:31", "remaining_time": "1:17:13", "throughput": 1316.21, "total_tokens": 16626120} {"current_steps": 29270, "total_steps": 40000, "loss": 0.0, "lr": 8.365820698091397e-06, "epoch": 513.5132743362832, "percentage": 73.17, "elapsed_time": "3:30:33", "remaining_time": "1:17:11", "throughput": 1316.23, "total_tokens": 16629112} {"current_steps": 29275, "total_steps": 40000, "loss": 0.0, "lr": 8.358493074635922e-06, "epoch": 513.6017699115044, "percentage": 73.19, "elapsed_time": "3:30:36", "remaining_time": "1:17:09", "throughput": 1316.22, "total_tokens": 16631800} {"current_steps": 29280, "total_steps": 40000, "loss": 0.0, "lr": 8.351168017509948e-06, "epoch": 513.6902654867257, "percentage": 73.2, "elapsed_time": "3:30:38", "remaining_time": "1:17:07", "throughput": 1316.24, "total_tokens": 16634680} {"current_steps": 29285, "total_steps": 40000, "loss": 0.0, "lr": 8.343845527843094e-06, "epoch": 513.7787610619469, "percentage": 73.21, "elapsed_time": "3:30:40", "remaining_time": "1:17:04", "throughput": 1316.26, "total_tokens": 16637736} {"current_steps": 29290, "total_steps": 40000, "loss": 0.0, "lr": 8.336525606764566e-06, "epoch": 513.8672566371681, "percentage": 73.22, "elapsed_time": "3:30:42", "remaining_time": "1:17:02", "throughput": 1316.24, "total_tokens": 16640120} {"current_steps": 29295, "total_steps": 40000, "loss": 0.0, "lr": 8.329208255403204e-06, "epoch": 513.9557522123894, "percentage": 73.24, "elapsed_time": "3:30:44", "remaining_time": "1:17:00", "throughput": 1316.28, "total_tokens": 16643400} {"current_steps": 29300, "total_steps": 40000, "loss": 0.0, "lr": 8.321893474887426e-06, "epoch": 514.0353982300885, "percentage": 73.25, "elapsed_time": "3:30:46", "remaining_time": "1:16:58", "throughput": 1316.22, "total_tokens": 16645576} {"current_steps": 29305, "total_steps": 40000, "loss": 0.0, "lr": 8.31458126634526e-06, "epoch": 514.1238938053098, "percentage": 73.26, "elapsed_time": "3:30:48", "remaining_time": "1:16:56", "throughput": 1316.21, "total_tokens": 16648184} {"current_steps": 29310, "total_steps": 40000, "loss": 0.0, "lr": 8.30727163090435e-06, "epoch": 514.212389380531, "percentage": 73.28, "elapsed_time": "3:30:50", "remaining_time": "1:16:53", "throughput": 1316.18, "total_tokens": 16650536} {"current_steps": 29315, "total_steps": 40000, "loss": 0.0, "lr": 8.29996456969192e-06, "epoch": 514.3008849557522, "percentage": 73.29, "elapsed_time": "3:30:52", "remaining_time": "1:16:51", "throughput": 1316.19, "total_tokens": 16653352} {"current_steps": 29320, "total_steps": 40000, "loss": 0.0, "lr": 8.292660083834818e-06, "epoch": 514.3893805309734, "percentage": 73.3, "elapsed_time": "3:30:54", "remaining_time": "1:16:49", "throughput": 1316.18, "total_tokens": 16656040} {"current_steps": 29325, "total_steps": 40000, "loss": 0.0, "lr": 8.2853581744595e-06, "epoch": 514.4778761061947, "percentage": 73.31, "elapsed_time": "3:30:56", "remaining_time": "1:16:47", "throughput": 1316.21, "total_tokens": 16659160} {"current_steps": 29330, "total_steps": 40000, "loss": 0.0, "lr": 8.278058842691991e-06, "epoch": 514.566371681416, "percentage": 73.32, "elapsed_time": "3:30:58", "remaining_time": "1:16:45", "throughput": 1316.25, "total_tokens": 16662312} {"current_steps": 29335, "total_steps": 40000, "loss": 0.0, "lr": 8.27076208965796e-06, "epoch": 514.6548672566372, "percentage": 73.34, "elapsed_time": "3:31:01", "remaining_time": "1:16:43", "throughput": 1316.28, "total_tokens": 16665432} {"current_steps": 29340, "total_steps": 40000, "loss": 0.0, "lr": 8.263467916482637e-06, "epoch": 514.7433628318585, "percentage": 73.35, "elapsed_time": "3:31:03", "remaining_time": "1:16:40", "throughput": 1316.3, "total_tokens": 16668440} {"current_steps": 29345, "total_steps": 40000, "loss": 0.0, "lr": 8.256176324290885e-06, "epoch": 514.8318584070796, "percentage": 73.36, "elapsed_time": "3:31:05", "remaining_time": "1:16:38", "throughput": 1316.32, "total_tokens": 16671416} {"current_steps": 29350, "total_steps": 40000, "loss": 0.0, "lr": 8.248887314207168e-06, "epoch": 514.9203539823009, "percentage": 73.38, "elapsed_time": "3:31:07", "remaining_time": "1:16:36", "throughput": 1316.35, "total_tokens": 16674584} {"current_steps": 29355, "total_steps": 40000, "loss": 0.0, "lr": 8.24160088735553e-06, "epoch": 515.0, "percentage": 73.39, "elapsed_time": "3:31:09", "remaining_time": "1:16:34", "throughput": 1316.32, "total_tokens": 16676800} {"current_steps": 29360, "total_steps": 40000, "loss": 0.0, "lr": 8.234317044859629e-06, "epoch": 515.0884955752213, "percentage": 73.4, "elapsed_time": "3:31:11", "remaining_time": "1:16:32", "throughput": 1316.27, "total_tokens": 16679280} {"current_steps": 29365, "total_steps": 40000, "loss": 0.0, "lr": 8.227035787842744e-06, "epoch": 515.1769911504425, "percentage": 73.41, "elapsed_time": "3:31:13", "remaining_time": "1:16:29", "throughput": 1316.27, "total_tokens": 16681936} {"current_steps": 29370, "total_steps": 40000, "loss": 0.0, "lr": 8.219757117427721e-06, "epoch": 515.2654867256637, "percentage": 73.42, "elapsed_time": "3:31:15", "remaining_time": "1:16:27", "throughput": 1316.26, "total_tokens": 16684608} {"current_steps": 29375, "total_steps": 40000, "loss": 0.0, "lr": 8.212481034737014e-06, "epoch": 515.3539823008849, "percentage": 73.44, "elapsed_time": "3:31:17", "remaining_time": "1:16:25", "throughput": 1316.32, "total_tokens": 16688048} {"current_steps": 29380, "total_steps": 40000, "loss": 0.0, "lr": 8.205207540892707e-06, "epoch": 515.4424778761062, "percentage": 73.45, "elapsed_time": "3:31:19", "remaining_time": "1:16:23", "throughput": 1316.35, "total_tokens": 16691232} {"current_steps": 29385, "total_steps": 40000, "loss": 0.0, "lr": 8.197936637016442e-06, "epoch": 515.5309734513274, "percentage": 73.46, "elapsed_time": "3:31:21", "remaining_time": "1:16:21", "throughput": 1316.35, "total_tokens": 16693840} {"current_steps": 29390, "total_steps": 40000, "loss": 0.0, "lr": 8.190668324229508e-06, "epoch": 515.6194690265487, "percentage": 73.47, "elapsed_time": "3:31:24", "remaining_time": "1:16:19", "throughput": 1316.36, "total_tokens": 16696720} {"current_steps": 29395, "total_steps": 40000, "loss": 0.0, "lr": 8.183402603652749e-06, "epoch": 515.70796460177, "percentage": 73.49, "elapsed_time": "3:31:26", "remaining_time": "1:16:16", "throughput": 1316.4, "total_tokens": 16699984} {"current_steps": 29400, "total_steps": 40000, "loss": 0.0, "lr": 8.176139476406635e-06, "epoch": 515.7964601769911, "percentage": 73.5, "elapsed_time": "3:31:28", "remaining_time": "1:16:14", "throughput": 1316.38, "total_tokens": 16702496} {"current_steps": 29400, "total_steps": 40000, "eval_loss": 0.9102046489715576, "epoch": 515.7964601769911, "percentage": 73.5, "elapsed_time": "3:31:29", "remaining_time": "1:16:15", "throughput": 1316.27, "total_tokens": 16702496} {"current_steps": 29405, "total_steps": 40000, "loss": 0.0, "lr": 8.16887894361125e-06, "epoch": 515.8849557522124, "percentage": 73.51, "elapsed_time": "3:31:33", "remaining_time": "1:16:13", "throughput": 1316.09, "total_tokens": 16705664} {"current_steps": 29410, "total_steps": 40000, "loss": 0.0, "lr": 8.161621006386233e-06, "epoch": 515.9734513274336, "percentage": 73.52, "elapsed_time": "3:31:35", "remaining_time": "1:16:11", "throughput": 1316.11, "total_tokens": 16708528} {"current_steps": 29415, "total_steps": 40000, "loss": 0.0, "lr": 8.154365665850869e-06, "epoch": 516.0530973451328, "percentage": 73.54, "elapsed_time": "3:31:37", "remaining_time": "1:16:09", "throughput": 1316.03, "total_tokens": 16710584} {"current_steps": 29420, "total_steps": 40000, "loss": 0.0, "lr": 8.147112923124005e-06, "epoch": 516.141592920354, "percentage": 73.55, "elapsed_time": "3:31:39", "remaining_time": "1:16:07", "throughput": 1316.03, "total_tokens": 16713224} {"current_steps": 29425, "total_steps": 40000, "loss": 0.0, "lr": 8.13986277932412e-06, "epoch": 516.2300884955753, "percentage": 73.56, "elapsed_time": "3:31:41", "remaining_time": "1:16:04", "throughput": 1316.08, "total_tokens": 16716648} {"current_steps": 29430, "total_steps": 40000, "loss": 0.0, "lr": 8.132615235569277e-06, "epoch": 516.3185840707964, "percentage": 73.58, "elapsed_time": "3:31:43", "remaining_time": "1:16:02", "throughput": 1316.1, "total_tokens": 16719608} {"current_steps": 29435, "total_steps": 40000, "loss": 0.0, "lr": 8.125370292977124e-06, "epoch": 516.4070796460177, "percentage": 73.59, "elapsed_time": "3:31:45", "remaining_time": "1:16:00", "throughput": 1316.09, "total_tokens": 16722216} {"current_steps": 29440, "total_steps": 40000, "loss": 0.0, "lr": 8.118127952664944e-06, "epoch": 516.4955752212389, "percentage": 73.6, "elapsed_time": "3:31:48", "remaining_time": "1:15:58", "throughput": 1316.11, "total_tokens": 16725176} {"current_steps": 29445, "total_steps": 40000, "loss": 0.0, "lr": 8.110888215749574e-06, "epoch": 516.5840707964602, "percentage": 73.61, "elapsed_time": "3:31:50", "remaining_time": "1:15:56", "throughput": 1316.1, "total_tokens": 16727832} {"current_steps": 29450, "total_steps": 40000, "loss": 0.0, "lr": 8.10365108334749e-06, "epoch": 516.6725663716815, "percentage": 73.62, "elapsed_time": "3:31:52", "remaining_time": "1:15:53", "throughput": 1316.12, "total_tokens": 16730760} {"current_steps": 29455, "total_steps": 40000, "loss": 0.0, "lr": 8.096416556574743e-06, "epoch": 516.7610619469026, "percentage": 73.64, "elapsed_time": "3:31:54", "remaining_time": "1:15:51", "throughput": 1316.11, "total_tokens": 16733416} {"current_steps": 29460, "total_steps": 40000, "loss": 0.0, "lr": 8.08918463654698e-06, "epoch": 516.8495575221239, "percentage": 73.65, "elapsed_time": "3:31:56", "remaining_time": "1:15:49", "throughput": 1316.15, "total_tokens": 16736632} {"current_steps": 29465, "total_steps": 40000, "loss": 0.0, "lr": 8.081955324379458e-06, "epoch": 516.9380530973451, "percentage": 73.66, "elapsed_time": "3:31:58", "remaining_time": "1:15:47", "throughput": 1316.17, "total_tokens": 16739592} {"current_steps": 29470, "total_steps": 40000, "loss": 0.0, "lr": 8.074728621187039e-06, "epoch": 517.0176991150443, "percentage": 73.67, "elapsed_time": "3:32:00", "remaining_time": "1:15:45", "throughput": 1316.1, "total_tokens": 16741720} {"current_steps": 29475, "total_steps": 40000, "loss": 0.0, "lr": 8.067504528084158e-06, "epoch": 517.1061946902655, "percentage": 73.69, "elapsed_time": "3:32:02", "remaining_time": "1:15:43", "throughput": 1316.14, "total_tokens": 16744920} {"current_steps": 29480, "total_steps": 40000, "loss": 0.0, "lr": 8.060283046184861e-06, "epoch": 517.1946902654868, "percentage": 73.7, "elapsed_time": "3:32:04", "remaining_time": "1:15:40", "throughput": 1316.15, "total_tokens": 16747704} {"current_steps": 29485, "total_steps": 40000, "loss": 0.0, "lr": 8.053064176602806e-06, "epoch": 517.2831858407079, "percentage": 73.71, "elapsed_time": "3:32:06", "remaining_time": "1:15:38", "throughput": 1316.17, "total_tokens": 16750760} {"current_steps": 29490, "total_steps": 40000, "loss": 0.0, "lr": 8.045847920451216e-06, "epoch": 517.3716814159292, "percentage": 73.72, "elapsed_time": "3:32:08", "remaining_time": "1:15:36", "throughput": 1316.19, "total_tokens": 16753672} {"current_steps": 29495, "total_steps": 40000, "loss": 0.0, "lr": 8.038634278842944e-06, "epoch": 517.4601769911504, "percentage": 73.74, "elapsed_time": "3:32:10", "remaining_time": "1:15:34", "throughput": 1316.18, "total_tokens": 16756328} {"current_steps": 29500, "total_steps": 40000, "loss": 0.0, "lr": 8.031423252890408e-06, "epoch": 517.5486725663717, "percentage": 73.75, "elapsed_time": "3:32:13", "remaining_time": "1:15:32", "throughput": 1316.16, "total_tokens": 16758728} {"current_steps": 29505, "total_steps": 40000, "loss": 0.0, "lr": 8.024214843705646e-06, "epoch": 517.637168141593, "percentage": 73.76, "elapsed_time": "3:32:15", "remaining_time": "1:15:29", "throughput": 1316.17, "total_tokens": 16761656} {"current_steps": 29510, "total_steps": 40000, "loss": 0.0, "lr": 8.017009052400295e-06, "epoch": 517.7256637168142, "percentage": 73.78, "elapsed_time": "3:32:17", "remaining_time": "1:15:27", "throughput": 1316.17, "total_tokens": 16764280} {"current_steps": 29515, "total_steps": 40000, "loss": 0.0, "lr": 8.00980588008557e-06, "epoch": 517.8141592920354, "percentage": 73.79, "elapsed_time": "3:32:19", "remaining_time": "1:15:25", "throughput": 1316.18, "total_tokens": 16767160} {"current_steps": 29520, "total_steps": 40000, "loss": 0.0, "lr": 8.002605327872282e-06, "epoch": 517.9026548672566, "percentage": 73.8, "elapsed_time": "3:32:21", "remaining_time": "1:15:23", "throughput": 1316.2, "total_tokens": 16770168} {"current_steps": 29525, "total_steps": 40000, "loss": 0.0, "lr": 7.995407396870862e-06, "epoch": 517.9911504424779, "percentage": 73.81, "elapsed_time": "3:32:23", "remaining_time": "1:15:21", "throughput": 1316.23, "total_tokens": 16773192} {"current_steps": 29530, "total_steps": 40000, "loss": 0.0, "lr": 7.988212088191307e-06, "epoch": 518.070796460177, "percentage": 73.83, "elapsed_time": "3:32:25", "remaining_time": "1:15:19", "throughput": 1316.2, "total_tokens": 16775816} {"current_steps": 29535, "total_steps": 40000, "loss": 0.0, "lr": 7.98101940294324e-06, "epoch": 518.1592920353983, "percentage": 73.84, "elapsed_time": "3:32:27", "remaining_time": "1:15:16", "throughput": 1316.21, "total_tokens": 16778696} {"current_steps": 29540, "total_steps": 40000, "loss": 0.0, "lr": 7.973829342235847e-06, "epoch": 518.2477876106195, "percentage": 73.85, "elapsed_time": "3:32:29", "remaining_time": "1:15:14", "throughput": 1316.23, "total_tokens": 16781720} {"current_steps": 29545, "total_steps": 40000, "loss": 0.0, "lr": 7.966641907177936e-06, "epoch": 518.3362831858407, "percentage": 73.86, "elapsed_time": "3:32:31", "remaining_time": "1:15:12", "throughput": 1316.3, "total_tokens": 16785320} {"current_steps": 29550, "total_steps": 40000, "loss": 0.0, "lr": 7.959457098877901e-06, "epoch": 518.4247787610619, "percentage": 73.88, "elapsed_time": "3:32:33", "remaining_time": "1:15:10", "throughput": 1316.31, "total_tokens": 16788184} {"current_steps": 29555, "total_steps": 40000, "loss": 0.0, "lr": 7.952274918443719e-06, "epoch": 518.5132743362832, "percentage": 73.89, "elapsed_time": "3:32:36", "remaining_time": "1:15:08", "throughput": 1316.28, "total_tokens": 16790488} {"current_steps": 29560, "total_steps": 40000, "loss": 0.0, "lr": 7.945095366982983e-06, "epoch": 518.6017699115044, "percentage": 73.9, "elapsed_time": "3:32:38", "remaining_time": "1:15:05", "throughput": 1316.27, "total_tokens": 16793080} {"current_steps": 29565, "total_steps": 40000, "loss": 0.0, "lr": 7.937918445602871e-06, "epoch": 518.6902654867257, "percentage": 73.91, "elapsed_time": "3:32:40", "remaining_time": "1:15:03", "throughput": 1316.28, "total_tokens": 16796024} {"current_steps": 29570, "total_steps": 40000, "loss": 0.0, "lr": 7.930744155410145e-06, "epoch": 518.7787610619469, "percentage": 73.92, "elapsed_time": "3:32:42", "remaining_time": "1:15:01", "throughput": 1316.31, "total_tokens": 16799032} {"current_steps": 29575, "total_steps": 40000, "loss": 0.0, "lr": 7.923572497511181e-06, "epoch": 518.8672566371681, "percentage": 73.94, "elapsed_time": "3:32:44", "remaining_time": "1:14:59", "throughput": 1316.34, "total_tokens": 16802152} {"current_steps": 29580, "total_steps": 40000, "loss": 0.0, "lr": 7.916403473011927e-06, "epoch": 518.9557522123894, "percentage": 73.95, "elapsed_time": "3:32:46", "remaining_time": "1:14:57", "throughput": 1316.33, "total_tokens": 16804712} {"current_steps": 29585, "total_steps": 40000, "loss": 0.0, "lr": 7.909237083017953e-06, "epoch": 519.0353982300885, "percentage": 73.96, "elapsed_time": "3:32:48", "remaining_time": "1:14:55", "throughput": 1316.27, "total_tokens": 16806992} {"current_steps": 29590, "total_steps": 40000, "loss": 0.0, "lr": 7.902073328634389e-06, "epoch": 519.1238938053098, "percentage": 73.98, "elapsed_time": "3:32:50", "remaining_time": "1:14:52", "throughput": 1316.33, "total_tokens": 16810432} {"current_steps": 29595, "total_steps": 40000, "loss": 0.0, "lr": 7.894912210965987e-06, "epoch": 519.212389380531, "percentage": 73.99, "elapsed_time": "3:32:52", "remaining_time": "1:14:50", "throughput": 1316.36, "total_tokens": 16813504} {"current_steps": 29600, "total_steps": 40000, "loss": 0.0, "lr": 7.887753731117075e-06, "epoch": 519.3008849557522, "percentage": 74.0, "elapsed_time": "3:32:54", "remaining_time": "1:14:48", "throughput": 1316.36, "total_tokens": 16816272} {"current_steps": 29600, "total_steps": 40000, "eval_loss": 0.9127913117408752, "epoch": 519.3008849557522, "percentage": 74.0, "elapsed_time": "3:32:55", "remaining_time": "1:14:48", "throughput": 1316.25, "total_tokens": 16816272} {"current_steps": 29605, "total_steps": 40000, "loss": 0.0, "lr": 7.880597890191587e-06, "epoch": 519.3893805309734, "percentage": 74.01, "elapsed_time": "3:33:00", "remaining_time": "1:14:47", "throughput": 1316.0, "total_tokens": 16818864} {"current_steps": 29610, "total_steps": 40000, "loss": 0.0, "lr": 7.873444689293036e-06, "epoch": 519.4778761061947, "percentage": 74.02, "elapsed_time": "3:33:02", "remaining_time": "1:14:45", "throughput": 1316.03, "total_tokens": 16821888} {"current_steps": 29615, "total_steps": 40000, "loss": 0.0, "lr": 7.866294129524548e-06, "epoch": 519.566371681416, "percentage": 74.04, "elapsed_time": "3:33:04", "remaining_time": "1:14:43", "throughput": 1316.01, "total_tokens": 16824464} {"current_steps": 29620, "total_steps": 40000, "loss": 0.0, "lr": 7.859146211988811e-06, "epoch": 519.6548672566372, "percentage": 74.05, "elapsed_time": "3:33:06", "remaining_time": "1:14:40", "throughput": 1316.04, "total_tokens": 16827456} {"current_steps": 29625, "total_steps": 40000, "loss": 0.0, "lr": 7.852000937788134e-06, "epoch": 519.7433628318585, "percentage": 74.06, "elapsed_time": "3:33:08", "remaining_time": "1:14:38", "throughput": 1316.03, "total_tokens": 16830080} {"current_steps": 29630, "total_steps": 40000, "loss": 0.0, "lr": 7.844858308024416e-06, "epoch": 519.8318584070796, "percentage": 74.08, "elapsed_time": "3:33:10", "remaining_time": "1:14:36", "throughput": 1316.04, "total_tokens": 16832912} {"current_steps": 29635, "total_steps": 40000, "loss": 0.0, "lr": 7.837718323799122e-06, "epoch": 519.9203539823009, "percentage": 74.09, "elapsed_time": "3:33:12", "remaining_time": "1:14:34", "throughput": 1316.06, "total_tokens": 16835984} {"current_steps": 29640, "total_steps": 40000, "loss": 0.0, "lr": 7.83058098621334e-06, "epoch": 520.0, "percentage": 74.1, "elapsed_time": "3:33:14", "remaining_time": "1:14:32", "throughput": 1316.05, "total_tokens": 16838416} {"current_steps": 29645, "total_steps": 40000, "loss": 0.0, "lr": 7.823446296367739e-06, "epoch": 520.0884955752213, "percentage": 74.11, "elapsed_time": "3:33:17", "remaining_time": "1:14:29", "throughput": 1316.06, "total_tokens": 16841680} {"current_steps": 29650, "total_steps": 40000, "loss": 0.0, "lr": 7.81631425536257e-06, "epoch": 520.1769911504425, "percentage": 74.12, "elapsed_time": "3:33:19", "remaining_time": "1:14:27", "throughput": 1316.08, "total_tokens": 16844688} {"current_steps": 29655, "total_steps": 40000, "loss": 0.0, "lr": 7.809184864297689e-06, "epoch": 520.2654867256637, "percentage": 74.14, "elapsed_time": "3:33:21", "remaining_time": "1:14:25", "throughput": 1316.09, "total_tokens": 16847440} {"current_steps": 29660, "total_steps": 40000, "loss": 0.0, "lr": 7.802058124272532e-06, "epoch": 520.3539823008849, "percentage": 74.15, "elapsed_time": "3:33:23", "remaining_time": "1:14:23", "throughput": 1316.08, "total_tokens": 16850000} {"current_steps": 29665, "total_steps": 40000, "loss": 0.0, "lr": 7.79493403638614e-06, "epoch": 520.4424778761062, "percentage": 74.16, "elapsed_time": "3:33:25", "remaining_time": "1:14:21", "throughput": 1316.09, "total_tokens": 16852880} {"current_steps": 29670, "total_steps": 40000, "loss": 0.0, "lr": 7.787812601737132e-06, "epoch": 520.5309734513274, "percentage": 74.17, "elapsed_time": "3:33:27", "remaining_time": "1:14:19", "throughput": 1316.05, "total_tokens": 16855152} {"current_steps": 29675, "total_steps": 40000, "loss": 0.0, "lr": 7.780693821423715e-06, "epoch": 520.6194690265487, "percentage": 74.19, "elapsed_time": "3:33:29", "remaining_time": "1:14:16", "throughput": 1316.05, "total_tokens": 16857888} {"current_steps": 29680, "total_steps": 40000, "loss": 0.0, "lr": 7.773577696543705e-06, "epoch": 520.70796460177, "percentage": 74.2, "elapsed_time": "3:33:31", "remaining_time": "1:14:14", "throughput": 1316.07, "total_tokens": 16860784} {"current_steps": 29685, "total_steps": 40000, "loss": 0.0, "lr": 7.7664642281945e-06, "epoch": 520.7964601769911, "percentage": 74.21, "elapsed_time": "3:33:33", "remaining_time": "1:14:12", "throughput": 1316.09, "total_tokens": 16863808} {"current_steps": 29690, "total_steps": 40000, "loss": 0.0, "lr": 7.759353417473072e-06, "epoch": 520.8849557522124, "percentage": 74.22, "elapsed_time": "3:33:35", "remaining_time": "1:14:10", "throughput": 1316.1, "total_tokens": 16866656} {"current_steps": 29695, "total_steps": 40000, "loss": 0.0, "lr": 7.752245265476016e-06, "epoch": 520.9734513274336, "percentage": 74.24, "elapsed_time": "3:33:37", "remaining_time": "1:14:08", "throughput": 1316.14, "total_tokens": 16869920} {"current_steps": 29700, "total_steps": 40000, "loss": 0.0, "lr": 7.745139773299481e-06, "epoch": 521.0530973451328, "percentage": 74.25, "elapsed_time": "3:33:39", "remaining_time": "1:14:05", "throughput": 1316.12, "total_tokens": 16872592} {"current_steps": 29705, "total_steps": 40000, "loss": 0.0, "lr": 7.738036942039232e-06, "epoch": 521.141592920354, "percentage": 74.26, "elapsed_time": "3:33:42", "remaining_time": "1:14:03", "throughput": 1316.11, "total_tokens": 16875248} {"current_steps": 29710, "total_steps": 40000, "loss": 0.0, "lr": 7.73093677279062e-06, "epoch": 521.2300884955753, "percentage": 74.28, "elapsed_time": "3:33:44", "remaining_time": "1:14:01", "throughput": 1316.11, "total_tokens": 16877952} {"current_steps": 29715, "total_steps": 40000, "loss": 0.0, "lr": 7.72383926664857e-06, "epoch": 521.3185840707964, "percentage": 74.29, "elapsed_time": "3:33:46", "remaining_time": "1:13:59", "throughput": 1316.13, "total_tokens": 16880848} {"current_steps": 29720, "total_steps": 40000, "loss": 0.0, "lr": 7.716744424707606e-06, "epoch": 521.4070796460177, "percentage": 74.3, "elapsed_time": "3:33:48", "remaining_time": "1:13:57", "throughput": 1316.13, "total_tokens": 16883664} {"current_steps": 29725, "total_steps": 40000, "loss": 0.0, "lr": 7.709652248061858e-06, "epoch": 521.4955752212389, "percentage": 74.31, "elapsed_time": "3:33:50", "remaining_time": "1:13:55", "throughput": 1316.15, "total_tokens": 16886560} {"current_steps": 29730, "total_steps": 40000, "loss": 0.0, "lr": 7.702562737805017e-06, "epoch": 521.5840707964602, "percentage": 74.33, "elapsed_time": "3:33:52", "remaining_time": "1:13:52", "throughput": 1316.16, "total_tokens": 16889408} {"current_steps": 29735, "total_steps": 40000, "loss": 0.0, "lr": 7.695475895030365e-06, "epoch": 521.6725663716815, "percentage": 74.34, "elapsed_time": "3:33:54", "remaining_time": "1:13:50", "throughput": 1316.16, "total_tokens": 16892192} {"current_steps": 29740, "total_steps": 40000, "loss": 0.0, "lr": 7.6883917208308e-06, "epoch": 521.7610619469026, "percentage": 74.35, "elapsed_time": "3:33:56", "remaining_time": "1:13:48", "throughput": 1316.14, "total_tokens": 16894688} {"current_steps": 29745, "total_steps": 40000, "loss": 0.0, "lr": 7.681310216298778e-06, "epoch": 521.8495575221239, "percentage": 74.36, "elapsed_time": "3:33:58", "remaining_time": "1:13:46", "throughput": 1316.18, "total_tokens": 16897888} {"current_steps": 29750, "total_steps": 40000, "loss": 0.0, "lr": 7.674231382526367e-06, "epoch": 521.9380530973451, "percentage": 74.38, "elapsed_time": "3:34:00", "remaining_time": "1:13:44", "throughput": 1316.22, "total_tokens": 16901152} {"current_steps": 29755, "total_steps": 40000, "loss": 0.0, "lr": 7.667155220605198e-06, "epoch": 522.0176991150443, "percentage": 74.39, "elapsed_time": "3:34:02", "remaining_time": "1:13:41", "throughput": 1316.17, "total_tokens": 16903504} {"current_steps": 29760, "total_steps": 40000, "loss": 0.0, "lr": 7.660081731626515e-06, "epoch": 522.1061946902655, "percentage": 74.4, "elapsed_time": "3:34:05", "remaining_time": "1:13:39", "throughput": 1316.15, "total_tokens": 16905968} {"current_steps": 29765, "total_steps": 40000, "loss": 0.0, "lr": 7.653010916681141e-06, "epoch": 522.1946902654868, "percentage": 74.41, "elapsed_time": "3:34:07", "remaining_time": "1:13:37", "throughput": 1316.15, "total_tokens": 16908688} {"current_steps": 29770, "total_steps": 40000, "loss": 0.0, "lr": 7.645942776859472e-06, "epoch": 522.2831858407079, "percentage": 74.42, "elapsed_time": "3:34:09", "remaining_time": "1:13:35", "throughput": 1316.18, "total_tokens": 16911840} {"current_steps": 29775, "total_steps": 40000, "loss": 0.0, "lr": 7.63887731325152e-06, "epoch": 522.3716814159292, "percentage": 74.44, "elapsed_time": "3:34:11", "remaining_time": "1:13:33", "throughput": 1316.22, "total_tokens": 16915072} {"current_steps": 29780, "total_steps": 40000, "loss": 0.0, "lr": 7.63181452694685e-06, "epoch": 522.4601769911504, "percentage": 74.45, "elapsed_time": "3:34:13", "remaining_time": "1:13:31", "throughput": 1316.21, "total_tokens": 16917680} {"current_steps": 29785, "total_steps": 40000, "loss": 0.0, "lr": 7.624754419034644e-06, "epoch": 522.5486725663717, "percentage": 74.46, "elapsed_time": "3:34:15", "remaining_time": "1:13:28", "throughput": 1316.2, "total_tokens": 16920240} {"current_steps": 29790, "total_steps": 40000, "loss": 0.0, "lr": 7.6176969906036645e-06, "epoch": 522.637168141593, "percentage": 74.48, "elapsed_time": "3:34:17", "remaining_time": "1:13:26", "throughput": 1316.2, "total_tokens": 16922992} {"current_steps": 29795, "total_steps": 40000, "loss": 0.0, "lr": 7.610642242742242e-06, "epoch": 522.7256637168142, "percentage": 74.49, "elapsed_time": "3:34:19", "remaining_time": "1:13:24", "throughput": 1316.21, "total_tokens": 16925824} {"current_steps": 29800, "total_steps": 40000, "loss": 0.0, "lr": 7.603590176538322e-06, "epoch": 522.8141592920354, "percentage": 74.5, "elapsed_time": "3:34:21", "remaining_time": "1:13:22", "throughput": 1316.25, "total_tokens": 16929072} {"current_steps": 29800, "total_steps": 40000, "eval_loss": 0.9138714671134949, "epoch": 522.8141592920354, "percentage": 74.5, "elapsed_time": "3:34:22", "remaining_time": "1:13:22", "throughput": 1316.14, "total_tokens": 16929072} {"current_steps": 29805, "total_steps": 40000, "loss": 0.0, "lr": 7.596540793079404e-06, "epoch": 522.9026548672566, "percentage": 74.51, "elapsed_time": "3:34:26", "remaining_time": "1:13:21", "throughput": 1315.99, "total_tokens": 16932176} {"current_steps": 29810, "total_steps": 40000, "loss": 0.0, "lr": 7.5894940934526125e-06, "epoch": 522.9911504424779, "percentage": 74.52, "elapsed_time": "3:34:28", "remaining_time": "1:13:18", "throughput": 1315.98, "total_tokens": 16934736} {"current_steps": 29815, "total_steps": 40000, "loss": 0.0, "lr": 7.582450078744621e-06, "epoch": 523.070796460177, "percentage": 74.54, "elapsed_time": "3:34:30", "remaining_time": "1:13:16", "throughput": 1315.94, "total_tokens": 16937232} {"current_steps": 29820, "total_steps": 40000, "loss": 0.0, "lr": 7.575408750041707e-06, "epoch": 523.1592920353983, "percentage": 74.55, "elapsed_time": "3:34:32", "remaining_time": "1:13:14", "throughput": 1315.98, "total_tokens": 16940544} {"current_steps": 29825, "total_steps": 40000, "loss": 0.0, "lr": 7.568370108429732e-06, "epoch": 523.2477876106195, "percentage": 74.56, "elapsed_time": "3:34:34", "remaining_time": "1:13:12", "throughput": 1315.99, "total_tokens": 16943328} {"current_steps": 29830, "total_steps": 40000, "loss": 0.0, "lr": 7.561334154994154e-06, "epoch": 523.3362831858407, "percentage": 74.58, "elapsed_time": "3:34:37", "remaining_time": "1:13:10", "throughput": 1315.99, "total_tokens": 16946032} {"current_steps": 29835, "total_steps": 40000, "loss": 0.0, "lr": 7.55430089081999e-06, "epoch": 523.4247787610619, "percentage": 74.59, "elapsed_time": "3:34:39", "remaining_time": "1:13:08", "throughput": 1316.02, "total_tokens": 16949232} {"current_steps": 29840, "total_steps": 40000, "loss": 0.0, "lr": 7.547270316991864e-06, "epoch": 523.5132743362832, "percentage": 74.6, "elapsed_time": "3:34:41", "remaining_time": "1:13:05", "throughput": 1316.03, "total_tokens": 16952080} {"current_steps": 29845, "total_steps": 40000, "loss": 0.0, "lr": 7.5402424345939884e-06, "epoch": 523.6017699115044, "percentage": 74.61, "elapsed_time": "3:34:43", "remaining_time": "1:13:03", "throughput": 1316.07, "total_tokens": 16955328} {"current_steps": 29850, "total_steps": 40000, "loss": 0.0, "lr": 7.533217244710133e-06, "epoch": 523.6902654867257, "percentage": 74.62, "elapsed_time": "3:34:45", "remaining_time": "1:13:01", "throughput": 1316.04, "total_tokens": 16957632} {"current_steps": 29855, "total_steps": 40000, "loss": 0.0, "lr": 7.52619474842369e-06, "epoch": 523.7787610619469, "percentage": 74.64, "elapsed_time": "3:34:47", "remaining_time": "1:12:59", "throughput": 1316.06, "total_tokens": 16960688} {"current_steps": 29860, "total_steps": 40000, "loss": 0.0, "lr": 7.519174946817597e-06, "epoch": 523.8672566371681, "percentage": 74.65, "elapsed_time": "3:34:49", "remaining_time": "1:12:57", "throughput": 1316.06, "total_tokens": 16963424} {"current_steps": 29865, "total_steps": 40000, "loss": 0.0, "lr": 7.512157840974407e-06, "epoch": 523.9557522123894, "percentage": 74.66, "elapsed_time": "3:34:51", "remaining_time": "1:12:54", "throughput": 1316.1, "total_tokens": 16966576} {"current_steps": 29870, "total_steps": 40000, "loss": 0.0, "lr": 7.5051434319762496e-06, "epoch": 524.0353982300885, "percentage": 74.67, "elapsed_time": "3:34:53", "remaining_time": "1:12:52", "throughput": 1316.02, "total_tokens": 16968544} {"current_steps": 29875, "total_steps": 40000, "loss": 0.0, "lr": 7.498131720904822e-06, "epoch": 524.1238938053098, "percentage": 74.69, "elapsed_time": "3:34:55", "remaining_time": "1:12:50", "throughput": 1316.01, "total_tokens": 16971152} {"current_steps": 29880, "total_steps": 40000, "loss": 0.0, "lr": 7.491122708841433e-06, "epoch": 524.212389380531, "percentage": 74.7, "elapsed_time": "3:34:57", "remaining_time": "1:12:48", "throughput": 1316.02, "total_tokens": 16973984} {"current_steps": 29885, "total_steps": 40000, "loss": 0.0, "lr": 7.4841163968669524e-06, "epoch": 524.3008849557522, "percentage": 74.71, "elapsed_time": "3:35:00", "remaining_time": "1:12:46", "throughput": 1316.07, "total_tokens": 16977440} {"current_steps": 29890, "total_steps": 40000, "loss": 0.0, "lr": 7.4771127860618355e-06, "epoch": 524.3893805309734, "percentage": 74.72, "elapsed_time": "3:35:02", "remaining_time": "1:12:44", "throughput": 1316.09, "total_tokens": 16980368} {"current_steps": 29895, "total_steps": 40000, "loss": 0.0, "lr": 7.470111877506139e-06, "epoch": 524.4778761061947, "percentage": 74.74, "elapsed_time": "3:35:04", "remaining_time": "1:12:41", "throughput": 1316.06, "total_tokens": 16982768} {"current_steps": 29900, "total_steps": 40000, "loss": 0.0, "lr": 7.463113672279479e-06, "epoch": 524.566371681416, "percentage": 74.75, "elapsed_time": "3:35:06", "remaining_time": "1:12:39", "throughput": 1316.06, "total_tokens": 16985440} {"current_steps": 29905, "total_steps": 40000, "loss": 0.0, "lr": 7.456118171461071e-06, "epoch": 524.6548672566372, "percentage": 74.76, "elapsed_time": "3:35:08", "remaining_time": "1:12:37", "throughput": 1316.09, "total_tokens": 16988608} {"current_steps": 29910, "total_steps": 40000, "loss": 0.0, "lr": 7.449125376129721e-06, "epoch": 524.7433628318585, "percentage": 74.78, "elapsed_time": "3:35:10", "remaining_time": "1:12:35", "throughput": 1316.11, "total_tokens": 16991488} {"current_steps": 29915, "total_steps": 40000, "loss": 0.0, "lr": 7.442135287363788e-06, "epoch": 524.8318584070796, "percentage": 74.79, "elapsed_time": "3:35:12", "remaining_time": "1:12:33", "throughput": 1316.14, "total_tokens": 16994688} {"current_steps": 29920, "total_steps": 40000, "loss": 0.0, "lr": 7.435147906241247e-06, "epoch": 524.9203539823009, "percentage": 74.8, "elapsed_time": "3:35:14", "remaining_time": "1:12:30", "throughput": 1316.16, "total_tokens": 16997584} {"current_steps": 29925, "total_steps": 40000, "loss": 0.0, "lr": 7.428163233839624e-06, "epoch": 525.0, "percentage": 74.81, "elapsed_time": "3:35:16", "remaining_time": "1:12:28", "throughput": 1316.13, "total_tokens": 16999896} {"current_steps": 29930, "total_steps": 40000, "loss": 0.0, "lr": 7.4211812712360525e-06, "epoch": 525.0884955752213, "percentage": 74.83, "elapsed_time": "3:35:18", "remaining_time": "1:12:26", "throughput": 1316.07, "total_tokens": 17002184} {"current_steps": 29935, "total_steps": 40000, "loss": 0.0, "lr": 7.4142020195072464e-06, "epoch": 525.1769911504425, "percentage": 74.84, "elapsed_time": "3:35:20", "remaining_time": "1:12:24", "throughput": 1316.04, "total_tokens": 17004472} {"current_steps": 29940, "total_steps": 40000, "loss": 0.0, "lr": 7.407225479729479e-06, "epoch": 525.2654867256637, "percentage": 74.85, "elapsed_time": "3:35:23", "remaining_time": "1:12:22", "throughput": 1316.06, "total_tokens": 17007528} {"current_steps": 29945, "total_steps": 40000, "loss": 0.0, "lr": 7.400251652978632e-06, "epoch": 525.3539823008849, "percentage": 74.86, "elapsed_time": "3:35:25", "remaining_time": "1:12:20", "throughput": 1316.11, "total_tokens": 17010824} {"current_steps": 29950, "total_steps": 40000, "loss": 0.0, "lr": 7.393280540330147e-06, "epoch": 525.4424778761062, "percentage": 74.88, "elapsed_time": "3:35:27", "remaining_time": "1:12:17", "throughput": 1316.11, "total_tokens": 17013688} {"current_steps": 29955, "total_steps": 40000, "loss": 0.0, "lr": 7.386312142859069e-06, "epoch": 525.5309734513274, "percentage": 74.89, "elapsed_time": "3:35:29", "remaining_time": "1:12:15", "throughput": 1316.1, "total_tokens": 17016264} {"current_steps": 29960, "total_steps": 40000, "loss": 0.0, "lr": 7.379346461640008e-06, "epoch": 525.6194690265487, "percentage": 74.9, "elapsed_time": "3:35:31", "remaining_time": "1:12:13", "throughput": 1316.15, "total_tokens": 17019576} {"current_steps": 29965, "total_steps": 40000, "loss": 0.0, "lr": 7.372383497747149e-06, "epoch": 525.70796460177, "percentage": 74.91, "elapsed_time": "3:35:33", "remaining_time": "1:12:11", "throughput": 1316.16, "total_tokens": 17022472} {"current_steps": 29970, "total_steps": 40000, "loss": 0.0, "lr": 7.3654232522542775e-06, "epoch": 525.7964601769911, "percentage": 74.92, "elapsed_time": "3:35:35", "remaining_time": "1:12:09", "throughput": 1316.21, "total_tokens": 17025880} {"current_steps": 29975, "total_steps": 40000, "loss": 0.0, "lr": 7.358465726234756e-06, "epoch": 525.8849557522124, "percentage": 74.94, "elapsed_time": "3:35:37", "remaining_time": "1:12:06", "throughput": 1316.24, "total_tokens": 17028856} {"current_steps": 29980, "total_steps": 40000, "loss": 0.0, "lr": 7.351510920761512e-06, "epoch": 525.9734513274336, "percentage": 74.95, "elapsed_time": "3:35:39", "remaining_time": "1:12:04", "throughput": 1316.26, "total_tokens": 17031848} {"current_steps": 29985, "total_steps": 40000, "loss": 0.0, "lr": 7.344558836907067e-06, "epoch": 526.0530973451328, "percentage": 74.96, "elapsed_time": "3:35:41", "remaining_time": "1:12:02", "throughput": 1316.22, "total_tokens": 17034336} {"current_steps": 29990, "total_steps": 40000, "loss": 0.0, "lr": 7.3376094757435285e-06, "epoch": 526.141592920354, "percentage": 74.98, "elapsed_time": "3:35:43", "remaining_time": "1:12:00", "throughput": 1316.21, "total_tokens": 17036992} {"current_steps": 29995, "total_steps": 40000, "loss": 0.0, "lr": 7.330662838342561e-06, "epoch": 526.2300884955753, "percentage": 74.99, "elapsed_time": "3:35:46", "remaining_time": "1:11:58", "throughput": 1316.23, "total_tokens": 17039888} {"current_steps": 30000, "total_steps": 40000, "loss": 0.0, "lr": 7.323718925775438e-06, "epoch": 526.3185840707964, "percentage": 75.0, "elapsed_time": "3:35:48", "remaining_time": "1:11:56", "throughput": 1316.27, "total_tokens": 17043120} {"current_steps": 30000, "total_steps": 40000, "eval_loss": 0.9153329133987427, "epoch": 526.3185840707964, "percentage": 75.0, "elapsed_time": "3:35:49", "remaining_time": "1:11:56", "throughput": 1316.16, "total_tokens": 17043120} {"current_steps": 30005, "total_steps": 40000, "loss": 0.0, "lr": 7.316777739112985e-06, "epoch": 526.4070796460177, "percentage": 75.01, "elapsed_time": "3:35:52", "remaining_time": "1:11:54", "throughput": 1316.01, "total_tokens": 17046224} {"current_steps": 30010, "total_steps": 40000, "loss": 0.0, "lr": 7.309839279425626e-06, "epoch": 526.4955752212389, "percentage": 75.02, "elapsed_time": "3:35:55", "remaining_time": "1:11:52", "throughput": 1316.04, "total_tokens": 17049360} {"current_steps": 30015, "total_steps": 40000, "loss": 0.0, "lr": 7.302903547783366e-06, "epoch": 526.5840707964602, "percentage": 75.04, "elapsed_time": "3:35:57", "remaining_time": "1:11:50", "throughput": 1316.06, "total_tokens": 17052352} {"current_steps": 30020, "total_steps": 40000, "loss": 0.0, "lr": 7.2959705452557644e-06, "epoch": 526.6725663716815, "percentage": 75.05, "elapsed_time": "3:35:59", "remaining_time": "1:11:48", "throughput": 1316.07, "total_tokens": 17055312} {"current_steps": 30025, "total_steps": 40000, "loss": 0.0, "lr": 7.289040272911996e-06, "epoch": 526.7610619469026, "percentage": 75.06, "elapsed_time": "3:36:01", "remaining_time": "1:11:46", "throughput": 1316.05, "total_tokens": 17057760} {"current_steps": 30030, "total_steps": 40000, "loss": 0.0, "lr": 7.282112731820789e-06, "epoch": 526.8495575221239, "percentage": 75.08, "elapsed_time": "3:36:03", "remaining_time": "1:11:43", "throughput": 1316.05, "total_tokens": 17060432} {"current_steps": 30035, "total_steps": 40000, "loss": 0.0, "lr": 7.275187923050447e-06, "epoch": 526.9380530973451, "percentage": 75.09, "elapsed_time": "3:36:05", "remaining_time": "1:11:41", "throughput": 1316.04, "total_tokens": 17063104} {"current_steps": 30040, "total_steps": 40000, "loss": 0.0, "lr": 7.268265847668879e-06, "epoch": 527.0176991150443, "percentage": 75.1, "elapsed_time": "3:36:07", "remaining_time": "1:11:39", "throughput": 1315.98, "total_tokens": 17065312} {"current_steps": 30045, "total_steps": 40000, "loss": 0.0, "lr": 7.261346506743538e-06, "epoch": 527.1061946902655, "percentage": 75.11, "elapsed_time": "3:36:09", "remaining_time": "1:11:37", "throughput": 1315.99, "total_tokens": 17068096} {"current_steps": 30050, "total_steps": 40000, "loss": 0.0, "lr": 7.254429901341486e-06, "epoch": 527.1946902654868, "percentage": 75.12, "elapsed_time": "3:36:11", "remaining_time": "1:11:35", "throughput": 1315.99, "total_tokens": 17070832} {"current_steps": 30055, "total_steps": 40000, "loss": 0.0, "lr": 7.247516032529356e-06, "epoch": 527.2831858407079, "percentage": 75.14, "elapsed_time": "3:36:13", "remaining_time": "1:11:32", "throughput": 1316.0, "total_tokens": 17073680} {"current_steps": 30060, "total_steps": 40000, "loss": 0.0, "lr": 7.240604901373338e-06, "epoch": 527.3716814159292, "percentage": 75.15, "elapsed_time": "3:36:16", "remaining_time": "1:11:30", "throughput": 1316.01, "total_tokens": 17076512} {"current_steps": 30065, "total_steps": 40000, "loss": 0.0, "lr": 7.233696508939223e-06, "epoch": 527.4601769911504, "percentage": 75.16, "elapsed_time": "3:36:18", "remaining_time": "1:11:28", "throughput": 1316.04, "total_tokens": 17079632} {"current_steps": 30070, "total_steps": 40000, "loss": 0.0, "lr": 7.226790856292376e-06, "epoch": 527.5486725663717, "percentage": 75.17, "elapsed_time": "3:36:20", "remaining_time": "1:11:26", "throughput": 1316.02, "total_tokens": 17082176} {"current_steps": 30075, "total_steps": 40000, "loss": 0.0, "lr": 7.219887944497727e-06, "epoch": 527.637168141593, "percentage": 75.19, "elapsed_time": "3:36:22", "remaining_time": "1:11:24", "throughput": 1316.1, "total_tokens": 17085872} {"current_steps": 30080, "total_steps": 40000, "loss": 0.0, "lr": 7.2129877746198e-06, "epoch": 527.7256637168142, "percentage": 75.2, "elapsed_time": "3:36:24", "remaining_time": "1:11:22", "throughput": 1316.15, "total_tokens": 17089216} {"current_steps": 30085, "total_steps": 40000, "loss": 0.0, "lr": 7.20609034772268e-06, "epoch": 527.8141592920354, "percentage": 75.21, "elapsed_time": "3:36:26", "remaining_time": "1:11:19", "throughput": 1316.15, "total_tokens": 17091968} {"current_steps": 30090, "total_steps": 40000, "loss": 0.0, "lr": 7.19919566487004e-06, "epoch": 527.9026548672566, "percentage": 75.22, "elapsed_time": "3:36:28", "remaining_time": "1:11:17", "throughput": 1316.11, "total_tokens": 17094224} {"current_steps": 30095, "total_steps": 40000, "loss": 0.0, "lr": 7.192303727125132e-06, "epoch": 527.9911504424779, "percentage": 75.24, "elapsed_time": "3:36:30", "remaining_time": "1:11:15", "throughput": 1316.14, "total_tokens": 17097264} {"current_steps": 30100, "total_steps": 40000, "loss": 0.0, "lr": 7.185414535550777e-06, "epoch": 528.070796460177, "percentage": 75.25, "elapsed_time": "3:36:32", "remaining_time": "1:11:13", "throughput": 1316.05, "total_tokens": 17099152} {"current_steps": 30105, "total_steps": 40000, "loss": 0.0, "lr": 7.178528091209363e-06, "epoch": 528.1592920353983, "percentage": 75.26, "elapsed_time": "3:36:34", "remaining_time": "1:11:11", "throughput": 1316.05, "total_tokens": 17101872} {"current_steps": 30110, "total_steps": 40000, "loss": 0.0, "lr": 7.171644395162888e-06, "epoch": 528.2477876106195, "percentage": 75.28, "elapsed_time": "3:36:36", "remaining_time": "1:11:09", "throughput": 1316.08, "total_tokens": 17105024} {"current_steps": 30115, "total_steps": 40000, "loss": 0.0, "lr": 7.164763448472881e-06, "epoch": 528.3362831858407, "percentage": 75.29, "elapsed_time": "3:36:39", "remaining_time": "1:11:06", "throughput": 1316.07, "total_tokens": 17107536} {"current_steps": 30120, "total_steps": 40000, "loss": 0.0, "lr": 7.157885252200491e-06, "epoch": 528.4247787610619, "percentage": 75.3, "elapsed_time": "3:36:41", "remaining_time": "1:11:04", "throughput": 1316.12, "total_tokens": 17111008} {"current_steps": 30125, "total_steps": 40000, "loss": 0.0, "lr": 7.151009807406403e-06, "epoch": 528.5132743362832, "percentage": 75.31, "elapsed_time": "3:36:43", "remaining_time": "1:11:02", "throughput": 1316.11, "total_tokens": 17113520} {"current_steps": 30130, "total_steps": 40000, "loss": 0.0, "lr": 7.144137115150909e-06, "epoch": 528.6017699115044, "percentage": 75.33, "elapsed_time": "3:36:45", "remaining_time": "1:11:00", "throughput": 1316.1, "total_tokens": 17116144} {"current_steps": 30135, "total_steps": 40000, "loss": 0.0, "lr": 7.1372671764938725e-06, "epoch": 528.6902654867257, "percentage": 75.34, "elapsed_time": "3:36:47", "remaining_time": "1:10:58", "throughput": 1316.1, "total_tokens": 17118912} {"current_steps": 30140, "total_steps": 40000, "loss": 0.0, "lr": 7.130399992494705e-06, "epoch": 528.7787610619469, "percentage": 75.35, "elapsed_time": "3:36:49", "remaining_time": "1:10:55", "throughput": 1316.09, "total_tokens": 17121584} {"current_steps": 30145, "total_steps": 40000, "loss": 0.0, "lr": 7.123535564212419e-06, "epoch": 528.8672566371681, "percentage": 75.36, "elapsed_time": "3:36:51", "remaining_time": "1:10:53", "throughput": 1316.13, "total_tokens": 17124800} {"current_steps": 30150, "total_steps": 40000, "loss": 0.0, "lr": 7.116673892705611e-06, "epoch": 528.9557522123894, "percentage": 75.38, "elapsed_time": "3:36:53", "remaining_time": "1:10:51", "throughput": 1316.14, "total_tokens": 17127600} {"current_steps": 30155, "total_steps": 40000, "loss": 0.0, "lr": 7.109814979032415e-06, "epoch": 529.0353982300885, "percentage": 75.39, "elapsed_time": "3:36:55", "remaining_time": "1:10:49", "throughput": 1316.13, "total_tokens": 17130488} {"current_steps": 30160, "total_steps": 40000, "loss": 0.0, "lr": 7.102958824250577e-06, "epoch": 529.1238938053098, "percentage": 75.4, "elapsed_time": "3:36:57", "remaining_time": "1:10:47", "throughput": 1316.15, "total_tokens": 17133512} {"current_steps": 30165, "total_steps": 40000, "loss": 0.0, "lr": 7.096105429417393e-06, "epoch": 529.212389380531, "percentage": 75.41, "elapsed_time": "3:36:59", "remaining_time": "1:10:45", "throughput": 1316.11, "total_tokens": 17135688} {"current_steps": 30170, "total_steps": 40000, "loss": 0.0, "lr": 7.0892547955897506e-06, "epoch": 529.3008849557522, "percentage": 75.42, "elapsed_time": "3:37:02", "remaining_time": "1:10:42", "throughput": 1316.15, "total_tokens": 17138888} {"current_steps": 30175, "total_steps": 40000, "loss": 0.0, "lr": 7.0824069238241e-06, "epoch": 529.3893805309734, "percentage": 75.44, "elapsed_time": "3:37:04", "remaining_time": "1:10:40", "throughput": 1316.15, "total_tokens": 17141656} {"current_steps": 30180, "total_steps": 40000, "loss": 0.0, "lr": 7.075561815176462e-06, "epoch": 529.4778761061947, "percentage": 75.45, "elapsed_time": "3:37:06", "remaining_time": "1:10:38", "throughput": 1316.14, "total_tokens": 17144344} {"current_steps": 30185, "total_steps": 40000, "loss": 0.0, "lr": 7.068719470702445e-06, "epoch": 529.566371681416, "percentage": 75.46, "elapsed_time": "3:37:08", "remaining_time": "1:10:36", "throughput": 1316.16, "total_tokens": 17147272} {"current_steps": 30190, "total_steps": 40000, "loss": 0.0, "lr": 7.061879891457229e-06, "epoch": 529.6548672566372, "percentage": 75.48, "elapsed_time": "3:37:10", "remaining_time": "1:10:34", "throughput": 1316.21, "total_tokens": 17150568} {"current_steps": 30195, "total_steps": 40000, "loss": 0.0, "lr": 7.0550430784955515e-06, "epoch": 529.7433628318585, "percentage": 75.49, "elapsed_time": "3:37:12", "remaining_time": "1:10:31", "throughput": 1316.24, "total_tokens": 17153800} {"current_steps": 30200, "total_steps": 40000, "loss": 0.0, "lr": 7.048209032871752e-06, "epoch": 529.8318584070796, "percentage": 75.5, "elapsed_time": "3:37:14", "remaining_time": "1:10:29", "throughput": 1316.23, "total_tokens": 17156344} {"current_steps": 30200, "total_steps": 40000, "eval_loss": 0.9343230724334717, "epoch": 529.8318584070796, "percentage": 75.5, "elapsed_time": "3:37:15", "remaining_time": "1:10:30", "throughput": 1316.12, "total_tokens": 17156344} {"current_steps": 30205, "total_steps": 40000, "loss": 0.0, "lr": 7.0413777556397055e-06, "epoch": 529.9203539823009, "percentage": 75.51, "elapsed_time": "3:37:19", "remaining_time": "1:10:28", "throughput": 1315.94, "total_tokens": 17159240} {"current_steps": 30210, "total_steps": 40000, "loss": 0.0, "lr": 7.0345492478528925e-06, "epoch": 530.0, "percentage": 75.52, "elapsed_time": "3:37:21", "remaining_time": "1:10:26", "throughput": 1315.89, "total_tokens": 17161240} {"current_steps": 30215, "total_steps": 40000, "loss": 0.0, "lr": 7.02772351056436e-06, "epoch": 530.0884955752213, "percentage": 75.54, "elapsed_time": "3:37:23", "remaining_time": "1:10:24", "throughput": 1315.87, "total_tokens": 17164104} {"current_steps": 30220, "total_steps": 40000, "loss": 0.0, "lr": 7.020900544826709e-06, "epoch": 530.1769911504425, "percentage": 75.55, "elapsed_time": "3:37:25", "remaining_time": "1:10:22", "throughput": 1315.91, "total_tokens": 17167256} {"current_steps": 30225, "total_steps": 40000, "loss": 0.0, "lr": 7.014080351692134e-06, "epoch": 530.2654867256637, "percentage": 75.56, "elapsed_time": "3:37:28", "remaining_time": "1:10:19", "throughput": 1315.93, "total_tokens": 17170360} {"current_steps": 30230, "total_steps": 40000, "loss": 0.0, "lr": 7.0072629322124024e-06, "epoch": 530.3539823008849, "percentage": 75.58, "elapsed_time": "3:37:30", "remaining_time": "1:10:17", "throughput": 1315.94, "total_tokens": 17173128} {"current_steps": 30235, "total_steps": 40000, "loss": 0.0, "lr": 7.000448287438827e-06, "epoch": 530.4424778761062, "percentage": 75.59, "elapsed_time": "3:37:32", "remaining_time": "1:10:15", "throughput": 1315.95, "total_tokens": 17176024} {"current_steps": 30240, "total_steps": 40000, "loss": 0.0, "lr": 6.993636418422331e-06, "epoch": 530.5309734513274, "percentage": 75.6, "elapsed_time": "3:37:34", "remaining_time": "1:10:13", "throughput": 1315.96, "total_tokens": 17178920} {"current_steps": 30245, "total_steps": 40000, "loss": 0.0, "lr": 6.986827326213383e-06, "epoch": 530.6194690265487, "percentage": 75.61, "elapsed_time": "3:37:36", "remaining_time": "1:10:11", "throughput": 1315.97, "total_tokens": 17181768} {"current_steps": 30250, "total_steps": 40000, "loss": 0.0, "lr": 6.9800210118620205e-06, "epoch": 530.70796460177, "percentage": 75.62, "elapsed_time": "3:37:38", "remaining_time": "1:10:08", "throughput": 1315.98, "total_tokens": 17184536} {"current_steps": 30255, "total_steps": 40000, "loss": 0.0, "lr": 6.973217476417876e-06, "epoch": 530.7964601769911, "percentage": 75.64, "elapsed_time": "3:37:40", "remaining_time": "1:10:06", "throughput": 1315.97, "total_tokens": 17187192} {"current_steps": 30260, "total_steps": 40000, "loss": 0.0, "lr": 6.96641672093013e-06, "epoch": 530.8849557522124, "percentage": 75.65, "elapsed_time": "3:37:42", "remaining_time": "1:10:04", "throughput": 1316.0, "total_tokens": 17190344} {"current_steps": 30265, "total_steps": 40000, "loss": 0.0, "lr": 6.95961874644755e-06, "epoch": 530.9734513274336, "percentage": 75.66, "elapsed_time": "3:37:44", "remaining_time": "1:10:02", "throughput": 1315.99, "total_tokens": 17192936} {"current_steps": 30270, "total_steps": 40000, "loss": 0.0, "lr": 6.952823554018476e-06, "epoch": 531.0530973451328, "percentage": 75.67, "elapsed_time": "3:37:46", "remaining_time": "1:10:00", "throughput": 1315.94, "total_tokens": 17195168} {"current_steps": 30275, "total_steps": 40000, "loss": 0.0, "lr": 6.946031144690798e-06, "epoch": 531.141592920354, "percentage": 75.69, "elapsed_time": "3:37:48", "remaining_time": "1:09:58", "throughput": 1315.95, "total_tokens": 17198016} {"current_steps": 30280, "total_steps": 40000, "loss": 0.0, "lr": 6.939241519512005e-06, "epoch": 531.2300884955753, "percentage": 75.7, "elapsed_time": "3:37:51", "remaining_time": "1:09:55", "throughput": 1315.95, "total_tokens": 17200832} {"current_steps": 30285, "total_steps": 40000, "loss": 0.0, "lr": 6.932454679529129e-06, "epoch": 531.3185840707964, "percentage": 75.71, "elapsed_time": "3:37:53", "remaining_time": "1:09:53", "throughput": 1316.07, "total_tokens": 17205024} {"current_steps": 30290, "total_steps": 40000, "loss": 0.0, "lr": 6.925670625788791e-06, "epoch": 531.4070796460177, "percentage": 75.72, "elapsed_time": "3:37:55", "remaining_time": "1:09:51", "throughput": 1316.04, "total_tokens": 17207392} {"current_steps": 30295, "total_steps": 40000, "loss": 0.0, "lr": 6.918889359337186e-06, "epoch": 531.4955752212389, "percentage": 75.74, "elapsed_time": "3:37:57", "remaining_time": "1:09:49", "throughput": 1316.04, "total_tokens": 17210176} {"current_steps": 30300, "total_steps": 40000, "loss": 0.0, "lr": 6.912110881220058e-06, "epoch": 531.5840707964602, "percentage": 75.75, "elapsed_time": "3:37:59", "remaining_time": "1:09:47", "throughput": 1316.04, "total_tokens": 17212864} {"current_steps": 30305, "total_steps": 40000, "loss": 0.0, "lr": 6.905335192482735e-06, "epoch": 531.6725663716815, "percentage": 75.76, "elapsed_time": "3:38:01", "remaining_time": "1:09:44", "throughput": 1316.02, "total_tokens": 17215360} {"current_steps": 30310, "total_steps": 40000, "loss": 0.0, "lr": 6.8985622941701275e-06, "epoch": 531.7610619469026, "percentage": 75.78, "elapsed_time": "3:38:03", "remaining_time": "1:09:42", "throughput": 1316.02, "total_tokens": 17218048} {"current_steps": 30315, "total_steps": 40000, "loss": 0.0, "lr": 6.89179218732669e-06, "epoch": 531.8495575221239, "percentage": 75.79, "elapsed_time": "3:38:05", "remaining_time": "1:09:40", "throughput": 1316.01, "total_tokens": 17220688} {"current_steps": 30320, "total_steps": 40000, "loss": 0.0, "lr": 6.8850248729964595e-06, "epoch": 531.9380530973451, "percentage": 75.8, "elapsed_time": "3:38:07", "remaining_time": "1:09:38", "throughput": 1316.06, "total_tokens": 17224112} {"current_steps": 30325, "total_steps": 40000, "loss": 0.0, "lr": 6.8782603522230314e-06, "epoch": 532.0176991150443, "percentage": 75.81, "elapsed_time": "3:38:09", "remaining_time": "1:09:36", "throughput": 1316.05, "total_tokens": 17226920} {"current_steps": 30330, "total_steps": 40000, "loss": 0.0, "lr": 6.871498626049591e-06, "epoch": 532.1061946902655, "percentage": 75.83, "elapsed_time": "3:38:11", "remaining_time": "1:09:34", "throughput": 1316.03, "total_tokens": 17229416} {"current_steps": 30335, "total_steps": 40000, "loss": 0.0, "lr": 6.8647396955188875e-06, "epoch": 532.1946902654868, "percentage": 75.84, "elapsed_time": "3:38:14", "remaining_time": "1:09:31", "throughput": 1316.05, "total_tokens": 17232344} {"current_steps": 30340, "total_steps": 40000, "loss": 0.0, "lr": 6.857983561673218e-06, "epoch": 532.2831858407079, "percentage": 75.85, "elapsed_time": "3:38:16", "remaining_time": "1:09:29", "throughput": 1316.08, "total_tokens": 17235544} {"current_steps": 30345, "total_steps": 40000, "loss": 0.0, "lr": 6.851230225554467e-06, "epoch": 532.3716814159292, "percentage": 75.86, "elapsed_time": "3:38:18", "remaining_time": "1:09:27", "throughput": 1316.1, "total_tokens": 17238456} {"current_steps": 30350, "total_steps": 40000, "loss": 0.0, "lr": 6.8444796882040946e-06, "epoch": 532.4601769911504, "percentage": 75.88, "elapsed_time": "3:38:20", "remaining_time": "1:09:25", "throughput": 1316.12, "total_tokens": 17241512} {"current_steps": 30355, "total_steps": 40000, "loss": 0.0, "lr": 6.837731950663106e-06, "epoch": 532.5486725663717, "percentage": 75.89, "elapsed_time": "3:38:22", "remaining_time": "1:09:23", "throughput": 1316.14, "total_tokens": 17244456} {"current_steps": 30360, "total_steps": 40000, "loss": 0.0, "lr": 6.830987013972098e-06, "epoch": 532.637168141593, "percentage": 75.9, "elapsed_time": "3:38:24", "remaining_time": "1:09:20", "throughput": 1316.12, "total_tokens": 17246920} {"current_steps": 30365, "total_steps": 40000, "loss": 0.0, "lr": 6.82424487917121e-06, "epoch": 532.7256637168142, "percentage": 75.91, "elapsed_time": "3:38:26", "remaining_time": "1:09:18", "throughput": 1316.14, "total_tokens": 17249880} {"current_steps": 30370, "total_steps": 40000, "loss": 0.0, "lr": 6.8175055473001735e-06, "epoch": 532.8141592920354, "percentage": 75.92, "elapsed_time": "3:38:28", "remaining_time": "1:09:16", "throughput": 1316.16, "total_tokens": 17252920} {"current_steps": 30375, "total_steps": 40000, "loss": 0.0, "lr": 6.8107690193982855e-06, "epoch": 532.9026548672566, "percentage": 75.94, "elapsed_time": "3:38:30", "remaining_time": "1:09:14", "throughput": 1316.14, "total_tokens": 17255336} {"current_steps": 30380, "total_steps": 40000, "loss": 0.0, "lr": 6.804035296504385e-06, "epoch": 532.9911504424779, "percentage": 75.95, "elapsed_time": "3:38:32", "remaining_time": "1:09:12", "throughput": 1316.14, "total_tokens": 17258136} {"current_steps": 30385, "total_steps": 40000, "loss": 0.0, "lr": 6.797304379656916e-06, "epoch": 533.070796460177, "percentage": 75.96, "elapsed_time": "3:38:34", "remaining_time": "1:09:10", "throughput": 1316.08, "total_tokens": 17260336} {"current_steps": 30390, "total_steps": 40000, "loss": 0.0, "lr": 6.790576269893861e-06, "epoch": 533.1592920353983, "percentage": 75.98, "elapsed_time": "3:38:36", "remaining_time": "1:09:07", "throughput": 1316.06, "total_tokens": 17262688} {"current_steps": 30395, "total_steps": 40000, "loss": 0.0, "lr": 6.783850968252772e-06, "epoch": 533.2477876106195, "percentage": 75.99, "elapsed_time": "3:38:39", "remaining_time": "1:09:05", "throughput": 1316.1, "total_tokens": 17266016} {"current_steps": 30400, "total_steps": 40000, "loss": 0.0, "lr": 6.777128475770789e-06, "epoch": 533.3362831858407, "percentage": 76.0, "elapsed_time": "3:38:41", "remaining_time": "1:09:03", "throughput": 1316.1, "total_tokens": 17268656} {"current_steps": 30400, "total_steps": 40000, "eval_loss": 0.9050721526145935, "epoch": 533.3362831858407, "percentage": 76.0, "elapsed_time": "3:38:42", "remaining_time": "1:09:03", "throughput": 1315.99, "total_tokens": 17268656} {"current_steps": 30405, "total_steps": 40000, "loss": 0.0, "lr": 6.77040879348459e-06, "epoch": 533.4247787610619, "percentage": 76.01, "elapsed_time": "3:38:46", "remaining_time": "1:09:02", "throughput": 1315.85, "total_tokens": 17271920} {"current_steps": 30410, "total_steps": 40000, "loss": 0.0, "lr": 6.763691922430443e-06, "epoch": 533.5132743362832, "percentage": 76.02, "elapsed_time": "3:38:48", "remaining_time": "1:09:00", "throughput": 1315.86, "total_tokens": 17274720} {"current_steps": 30415, "total_steps": 40000, "loss": 0.0, "lr": 6.756977863644178e-06, "epoch": 533.6017699115044, "percentage": 76.04, "elapsed_time": "3:38:50", "remaining_time": "1:08:57", "throughput": 1315.88, "total_tokens": 17277680} {"current_steps": 30420, "total_steps": 40000, "loss": 0.0, "lr": 6.7502666181611804e-06, "epoch": 533.6902654867257, "percentage": 76.05, "elapsed_time": "3:38:52", "remaining_time": "1:08:55", "throughput": 1315.86, "total_tokens": 17280192} {"current_steps": 30425, "total_steps": 40000, "loss": 0.0, "lr": 6.743558187016405e-06, "epoch": 533.7787610619469, "percentage": 76.06, "elapsed_time": "3:38:54", "remaining_time": "1:08:53", "throughput": 1315.89, "total_tokens": 17283296} {"current_steps": 30430, "total_steps": 40000, "loss": 0.0, "lr": 6.7368525712443925e-06, "epoch": 533.8672566371681, "percentage": 76.08, "elapsed_time": "3:38:56", "remaining_time": "1:08:51", "throughput": 1315.94, "total_tokens": 17286688} {"current_steps": 30435, "total_steps": 40000, "loss": 0.0, "lr": 6.7301497718792155e-06, "epoch": 533.9557522123894, "percentage": 76.09, "elapsed_time": "3:38:58", "remaining_time": "1:08:49", "throughput": 1315.98, "total_tokens": 17289952} {"current_steps": 30440, "total_steps": 40000, "loss": 0.0, "lr": 6.723449789954544e-06, "epoch": 534.0353982300885, "percentage": 76.1, "elapsed_time": "3:39:00", "remaining_time": "1:08:46", "throughput": 1315.93, "total_tokens": 17292320} {"current_steps": 30445, "total_steps": 40000, "loss": 0.0, "lr": 6.716752626503586e-06, "epoch": 534.1238938053098, "percentage": 76.11, "elapsed_time": "3:39:02", "remaining_time": "1:08:44", "throughput": 1315.91, "total_tokens": 17294800} {"current_steps": 30450, "total_steps": 40000, "loss": 0.0, "lr": 6.710058282559131e-06, "epoch": 534.212389380531, "percentage": 76.12, "elapsed_time": "3:39:04", "remaining_time": "1:08:42", "throughput": 1315.94, "total_tokens": 17297888} {"current_steps": 30455, "total_steps": 40000, "loss": 0.0, "lr": 6.703366759153545e-06, "epoch": 534.3008849557522, "percentage": 76.14, "elapsed_time": "3:39:06", "remaining_time": "1:08:40", "throughput": 1315.95, "total_tokens": 17300704} {"current_steps": 30460, "total_steps": 40000, "loss": 0.0, "lr": 6.6966780573187335e-06, "epoch": 534.3893805309734, "percentage": 76.15, "elapsed_time": "3:39:09", "remaining_time": "1:08:38", "throughput": 1315.92, "total_tokens": 17303120} {"current_steps": 30465, "total_steps": 40000, "loss": 0.0, "lr": 6.689992178086174e-06, "epoch": 534.4778761061947, "percentage": 76.16, "elapsed_time": "3:39:11", "remaining_time": "1:08:36", "throughput": 1315.93, "total_tokens": 17305888} {"current_steps": 30470, "total_steps": 40000, "loss": 0.0, "lr": 6.683309122486925e-06, "epoch": 534.566371681416, "percentage": 76.17, "elapsed_time": "3:39:13", "remaining_time": "1:08:33", "throughput": 1315.97, "total_tokens": 17309120} {"current_steps": 30475, "total_steps": 40000, "loss": 0.0, "lr": 6.676628891551584e-06, "epoch": 534.6548672566372, "percentage": 76.19, "elapsed_time": "3:39:15", "remaining_time": "1:08:31", "throughput": 1316.01, "total_tokens": 17312464} {"current_steps": 30480, "total_steps": 40000, "loss": 0.0, "lr": 6.6699514863103385e-06, "epoch": 534.7433628318585, "percentage": 76.2, "elapsed_time": "3:39:17", "remaining_time": "1:08:29", "throughput": 1316.03, "total_tokens": 17315360} {"current_steps": 30485, "total_steps": 40000, "loss": 0.0, "lr": 6.663276907792921e-06, "epoch": 534.8318584070796, "percentage": 76.21, "elapsed_time": "3:39:19", "remaining_time": "1:08:27", "throughput": 1316.02, "total_tokens": 17318048} {"current_steps": 30490, "total_steps": 40000, "loss": 0.0, "lr": 6.656605157028634e-06, "epoch": 534.9203539823009, "percentage": 76.22, "elapsed_time": "3:39:21", "remaining_time": "1:08:25", "throughput": 1316.04, "total_tokens": 17320976} {"current_steps": 30495, "total_steps": 40000, "loss": 0.0, "lr": 6.649936235046358e-06, "epoch": 535.0, "percentage": 76.24, "elapsed_time": "3:39:23", "remaining_time": "1:08:22", "throughput": 1316.03, "total_tokens": 17323544} {"current_steps": 30500, "total_steps": 40000, "loss": 0.0, "lr": 6.643270142874508e-06, "epoch": 535.0884955752213, "percentage": 76.25, "elapsed_time": "3:39:25", "remaining_time": "1:08:20", "throughput": 1316.03, "total_tokens": 17326568} {"current_steps": 30505, "total_steps": 40000, "loss": 0.0, "lr": 6.636606881541094e-06, "epoch": 535.1769911504425, "percentage": 76.26, "elapsed_time": "3:39:27", "remaining_time": "1:08:18", "throughput": 1316.02, "total_tokens": 17329160} {"current_steps": 30510, "total_steps": 40000, "loss": 0.0, "lr": 6.629946452073662e-06, "epoch": 535.2654867256637, "percentage": 76.28, "elapsed_time": "3:39:29", "remaining_time": "1:08:16", "throughput": 1316.01, "total_tokens": 17331704} {"current_steps": 30515, "total_steps": 40000, "loss": 0.0, "lr": 6.6232888554993375e-06, "epoch": 535.3539823008849, "percentage": 76.29, "elapsed_time": "3:39:31", "remaining_time": "1:08:14", "throughput": 1316.02, "total_tokens": 17334616} {"current_steps": 30520, "total_steps": 40000, "loss": 0.0, "lr": 6.616634092844817e-06, "epoch": 535.4424778761062, "percentage": 76.3, "elapsed_time": "3:39:34", "remaining_time": "1:08:12", "throughput": 1316.04, "total_tokens": 17337672} {"current_steps": 30525, "total_steps": 40000, "loss": 0.0, "lr": 6.609982165136331e-06, "epoch": 535.5309734513274, "percentage": 76.31, "elapsed_time": "3:39:36", "remaining_time": "1:08:09", "throughput": 1316.04, "total_tokens": 17340328} {"current_steps": 30530, "total_steps": 40000, "loss": 0.0, "lr": 6.603333073399706e-06, "epoch": 535.6194690265487, "percentage": 76.33, "elapsed_time": "3:39:38", "remaining_time": "1:08:07", "throughput": 1316.06, "total_tokens": 17343304} {"current_steps": 30535, "total_steps": 40000, "loss": 0.0, "lr": 6.596686818660308e-06, "epoch": 535.70796460177, "percentage": 76.34, "elapsed_time": "3:39:40", "remaining_time": "1:08:05", "throughput": 1316.09, "total_tokens": 17346472} {"current_steps": 30540, "total_steps": 40000, "loss": 0.0, "lr": 6.590043401943066e-06, "epoch": 535.7964601769911, "percentage": 76.35, "elapsed_time": "3:39:42", "remaining_time": "1:08:03", "throughput": 1316.11, "total_tokens": 17349448} {"current_steps": 30545, "total_steps": 40000, "loss": 0.0, "lr": 6.583402824272494e-06, "epoch": 535.8849557522124, "percentage": 76.36, "elapsed_time": "3:39:44", "remaining_time": "1:08:01", "throughput": 1316.12, "total_tokens": 17352248} {"current_steps": 30550, "total_steps": 40000, "loss": 0.0, "lr": 6.576765086672634e-06, "epoch": 535.9734513274336, "percentage": 76.38, "elapsed_time": "3:39:46", "remaining_time": "1:07:58", "throughput": 1316.12, "total_tokens": 17355080} {"current_steps": 30555, "total_steps": 40000, "loss": 0.0, "lr": 6.57013019016712e-06, "epoch": 536.0530973451328, "percentage": 76.39, "elapsed_time": "3:39:48", "remaining_time": "1:07:56", "throughput": 1316.09, "total_tokens": 17357600} {"current_steps": 30560, "total_steps": 40000, "loss": 0.0, "lr": 6.563498135779142e-06, "epoch": 536.141592920354, "percentage": 76.4, "elapsed_time": "3:39:50", "remaining_time": "1:07:54", "throughput": 1316.09, "total_tokens": 17360256} {"current_steps": 30565, "total_steps": 40000, "loss": 0.0, "lr": 6.556868924531431e-06, "epoch": 536.2300884955753, "percentage": 76.41, "elapsed_time": "3:39:52", "remaining_time": "1:07:52", "throughput": 1316.12, "total_tokens": 17363392} {"current_steps": 30570, "total_steps": 40000, "loss": 0.0, "lr": 6.550242557446304e-06, "epoch": 536.3185840707964, "percentage": 76.42, "elapsed_time": "3:39:54", "remaining_time": "1:07:50", "throughput": 1316.13, "total_tokens": 17366256} {"current_steps": 30575, "total_steps": 40000, "loss": 0.0, "lr": 6.543619035545634e-06, "epoch": 536.4070796460177, "percentage": 76.44, "elapsed_time": "3:39:57", "remaining_time": "1:07:48", "throughput": 1316.13, "total_tokens": 17369040} {"current_steps": 30580, "total_steps": 40000, "loss": 0.0, "lr": 6.53699835985084e-06, "epoch": 536.4955752212389, "percentage": 76.45, "elapsed_time": "3:39:59", "remaining_time": "1:07:45", "throughput": 1316.16, "total_tokens": 17372240} {"current_steps": 30585, "total_steps": 40000, "loss": 0.0, "lr": 6.530380531382927e-06, "epoch": 536.5840707964602, "percentage": 76.46, "elapsed_time": "3:40:01", "remaining_time": "1:07:43", "throughput": 1316.19, "total_tokens": 17375264} {"current_steps": 30590, "total_steps": 40000, "loss": 0.0, "lr": 6.523765551162433e-06, "epoch": 536.6725663716815, "percentage": 76.48, "elapsed_time": "3:40:03", "remaining_time": "1:07:41", "throughput": 1316.19, "total_tokens": 17378016} {"current_steps": 30595, "total_steps": 40000, "loss": 0.0, "lr": 6.517153420209476e-06, "epoch": 536.7610619469026, "percentage": 76.49, "elapsed_time": "3:40:05", "remaining_time": "1:07:39", "throughput": 1316.2, "total_tokens": 17380928} {"current_steps": 30600, "total_steps": 40000, "loss": 0.0, "lr": 6.510544139543739e-06, "epoch": 536.8495575221239, "percentage": 76.5, "elapsed_time": "3:40:07", "remaining_time": "1:07:37", "throughput": 1316.21, "total_tokens": 17383696} {"current_steps": 30600, "total_steps": 40000, "eval_loss": 0.9374831318855286, "epoch": 536.8495575221239, "percentage": 76.5, "elapsed_time": "3:40:08", "remaining_time": "1:07:37", "throughput": 1316.1, "total_tokens": 17383696} {"current_steps": 30605, "total_steps": 40000, "loss": 0.0, "lr": 6.503937710184452e-06, "epoch": 536.9380530973451, "percentage": 76.51, "elapsed_time": "3:40:12", "remaining_time": "1:07:35", "throughput": 1315.93, "total_tokens": 17386624} {"current_steps": 30610, "total_steps": 40000, "loss": 0.0, "lr": 6.4973341331503954e-06, "epoch": 537.0176991150443, "percentage": 76.53, "elapsed_time": "3:40:14", "remaining_time": "1:07:33", "throughput": 1315.9, "total_tokens": 17389112} {"current_steps": 30615, "total_steps": 40000, "loss": 0.0, "lr": 6.490733409459942e-06, "epoch": 537.1061946902655, "percentage": 76.54, "elapsed_time": "3:40:16", "remaining_time": "1:07:31", "throughput": 1315.91, "total_tokens": 17392024} {"current_steps": 30620, "total_steps": 40000, "loss": 0.0, "lr": 6.484135540130995e-06, "epoch": 537.1946902654868, "percentage": 76.55, "elapsed_time": "3:40:18", "remaining_time": "1:07:29", "throughput": 1315.88, "total_tokens": 17394344} {"current_steps": 30625, "total_steps": 40000, "loss": 0.0, "lr": 6.4775405261810364e-06, "epoch": 537.2831858407079, "percentage": 76.56, "elapsed_time": "3:40:20", "remaining_time": "1:07:27", "throughput": 1315.9, "total_tokens": 17397416} {"current_steps": 30630, "total_steps": 40000, "loss": 0.0, "lr": 6.470948368627092e-06, "epoch": 537.3716814159292, "percentage": 76.58, "elapsed_time": "3:40:22", "remaining_time": "1:07:25", "throughput": 1315.92, "total_tokens": 17400328} {"current_steps": 30635, "total_steps": 40000, "loss": 0.0, "lr": 6.464359068485756e-06, "epoch": 537.4601769911504, "percentage": 76.59, "elapsed_time": "3:40:25", "remaining_time": "1:07:22", "throughput": 1315.92, "total_tokens": 17403080} {"current_steps": 30640, "total_steps": 40000, "loss": 0.0, "lr": 6.457772626773195e-06, "epoch": 537.5486725663717, "percentage": 76.6, "elapsed_time": "3:40:27", "remaining_time": "1:07:20", "throughput": 1315.89, "total_tokens": 17405448} {"current_steps": 30645, "total_steps": 40000, "loss": 0.0, "lr": 6.451189044505104e-06, "epoch": 537.637168141593, "percentage": 76.61, "elapsed_time": "3:40:29", "remaining_time": "1:07:18", "throughput": 1315.9, "total_tokens": 17408312} {"current_steps": 30650, "total_steps": 40000, "loss": 0.0, "lr": 6.44460832269676e-06, "epoch": 537.7256637168142, "percentage": 76.62, "elapsed_time": "3:40:31", "remaining_time": "1:07:16", "throughput": 1315.9, "total_tokens": 17410936} {"current_steps": 30655, "total_steps": 40000, "loss": 0.0, "lr": 6.438030462363001e-06, "epoch": 537.8141592920354, "percentage": 76.64, "elapsed_time": "3:40:33", "remaining_time": "1:07:14", "throughput": 1315.9, "total_tokens": 17413768} {"current_steps": 30660, "total_steps": 40000, "loss": 0.0, "lr": 6.431455464518205e-06, "epoch": 537.9026548672566, "percentage": 76.65, "elapsed_time": "3:40:35", "remaining_time": "1:07:11", "throughput": 1315.94, "total_tokens": 17416952} {"current_steps": 30665, "total_steps": 40000, "loss": 0.0, "lr": 6.424883330176326e-06, "epoch": 537.9911504424779, "percentage": 76.66, "elapsed_time": "3:40:37", "remaining_time": "1:07:09", "throughput": 1315.95, "total_tokens": 17419864} {"current_steps": 30670, "total_steps": 40000, "loss": 0.0, "lr": 6.418314060350864e-06, "epoch": 538.070796460177, "percentage": 76.68, "elapsed_time": "3:40:39", "remaining_time": "1:07:07", "throughput": 1315.91, "total_tokens": 17422224} {"current_steps": 30675, "total_steps": 40000, "loss": 0.0, "lr": 6.4117476560548895e-06, "epoch": 538.1592920353983, "percentage": 76.69, "elapsed_time": "3:40:41", "remaining_time": "1:07:05", "throughput": 1315.9, "total_tokens": 17424848} {"current_steps": 30680, "total_steps": 40000, "loss": 0.0, "lr": 6.405184118301016e-06, "epoch": 538.2477876106195, "percentage": 76.7, "elapsed_time": "3:40:43", "remaining_time": "1:07:03", "throughput": 1315.9, "total_tokens": 17427600} {"current_steps": 30685, "total_steps": 40000, "loss": 0.0, "lr": 6.398623448101434e-06, "epoch": 538.3362831858407, "percentage": 76.71, "elapsed_time": "3:40:45", "remaining_time": "1:07:01", "throughput": 1315.86, "total_tokens": 17429824} {"current_steps": 30690, "total_steps": 40000, "loss": 0.0, "lr": 6.392065646467871e-06, "epoch": 538.4247787610619, "percentage": 76.72, "elapsed_time": "3:40:48", "remaining_time": "1:06:58", "throughput": 1315.82, "total_tokens": 17431984} {"current_steps": 30695, "total_steps": 40000, "loss": 0.0, "lr": 6.385510714411632e-06, "epoch": 538.5132743362832, "percentage": 76.74, "elapsed_time": "3:40:50", "remaining_time": "1:06:56", "throughput": 1315.85, "total_tokens": 17435168} {"current_steps": 30700, "total_steps": 40000, "loss": 0.0, "lr": 6.378958652943559e-06, "epoch": 538.6017699115044, "percentage": 76.75, "elapsed_time": "3:40:52", "remaining_time": "1:06:54", "throughput": 1315.89, "total_tokens": 17438368} {"current_steps": 30705, "total_steps": 40000, "loss": 0.0, "lr": 6.3724094630740776e-06, "epoch": 538.6902654867257, "percentage": 76.76, "elapsed_time": "3:40:54", "remaining_time": "1:06:52", "throughput": 1315.9, "total_tokens": 17441264} {"current_steps": 30710, "total_steps": 40000, "loss": 0.0, "lr": 6.365863145813136e-06, "epoch": 538.7787610619469, "percentage": 76.78, "elapsed_time": "3:40:56", "remaining_time": "1:06:50", "throughput": 1315.92, "total_tokens": 17444256} {"current_steps": 30715, "total_steps": 40000, "loss": 0.0, "lr": 6.359319702170269e-06, "epoch": 538.8672566371681, "percentage": 76.79, "elapsed_time": "3:40:58", "remaining_time": "1:06:47", "throughput": 1315.92, "total_tokens": 17446960} {"current_steps": 30720, "total_steps": 40000, "loss": 0.0, "lr": 6.352779133154566e-06, "epoch": 538.9557522123894, "percentage": 76.8, "elapsed_time": "3:41:00", "remaining_time": "1:06:45", "throughput": 1315.97, "total_tokens": 17450416} {"current_steps": 30725, "total_steps": 40000, "loss": 0.0, "lr": 6.346241439774648e-06, "epoch": 539.0353982300885, "percentage": 76.81, "elapsed_time": "3:41:02", "remaining_time": "1:06:43", "throughput": 1315.97, "total_tokens": 17453288} {"current_steps": 30730, "total_steps": 40000, "loss": 0.0, "lr": 6.339706623038716e-06, "epoch": 539.1238938053098, "percentage": 76.83, "elapsed_time": "3:41:04", "remaining_time": "1:06:41", "throughput": 1315.98, "total_tokens": 17456168} {"current_steps": 30735, "total_steps": 40000, "loss": 0.0, "lr": 6.333174683954532e-06, "epoch": 539.212389380531, "percentage": 76.84, "elapsed_time": "3:41:06", "remaining_time": "1:06:39", "throughput": 1315.99, "total_tokens": 17459080} {"current_steps": 30740, "total_steps": 40000, "loss": 0.0, "lr": 6.326645623529387e-06, "epoch": 539.3008849557522, "percentage": 76.85, "elapsed_time": "3:41:08", "remaining_time": "1:06:37", "throughput": 1316.01, "total_tokens": 17462104} {"current_steps": 30745, "total_steps": 40000, "loss": 0.0, "lr": 6.320119442770156e-06, "epoch": 539.3893805309734, "percentage": 76.86, "elapsed_time": "3:41:10", "remaining_time": "1:06:34", "throughput": 1316.01, "total_tokens": 17464792} {"current_steps": 30750, "total_steps": 40000, "loss": 0.0, "lr": 6.313596142683254e-06, "epoch": 539.4778761061947, "percentage": 76.88, "elapsed_time": "3:41:13", "remaining_time": "1:06:32", "throughput": 1316.05, "total_tokens": 17467960} {"current_steps": 30755, "total_steps": 40000, "loss": 0.0, "lr": 6.307075724274647e-06, "epoch": 539.566371681416, "percentage": 76.89, "elapsed_time": "3:41:15", "remaining_time": "1:06:30", "throughput": 1316.04, "total_tokens": 17470616} {"current_steps": 30760, "total_steps": 40000, "loss": 0.0, "lr": 6.300558188549882e-06, "epoch": 539.6548672566372, "percentage": 76.9, "elapsed_time": "3:41:17", "remaining_time": "1:06:28", "throughput": 1316.05, "total_tokens": 17473512} {"current_steps": 30765, "total_steps": 40000, "loss": 0.0, "lr": 6.29404353651403e-06, "epoch": 539.7433628318585, "percentage": 76.91, "elapsed_time": "3:41:19", "remaining_time": "1:06:26", "throughput": 1316.03, "total_tokens": 17475992} {"current_steps": 30770, "total_steps": 40000, "loss": 0.0, "lr": 6.287531769171737e-06, "epoch": 539.8318584070796, "percentage": 76.92, "elapsed_time": "3:41:21", "remaining_time": "1:06:23", "throughput": 1316.07, "total_tokens": 17479144} {"current_steps": 30775, "total_steps": 40000, "loss": 0.0, "lr": 6.2810228875272045e-06, "epoch": 539.9203539823009, "percentage": 76.94, "elapsed_time": "3:41:23", "remaining_time": "1:06:21", "throughput": 1316.04, "total_tokens": 17481544} {"current_steps": 30780, "total_steps": 40000, "loss": 0.0, "lr": 6.274516892584179e-06, "epoch": 540.0, "percentage": 76.95, "elapsed_time": "3:41:25", "remaining_time": "1:06:19", "throughput": 1316.02, "total_tokens": 17483856} {"current_steps": 30785, "total_steps": 40000, "loss": 0.0, "lr": 6.268013785345969e-06, "epoch": 540.0884955752213, "percentage": 76.96, "elapsed_time": "3:41:27", "remaining_time": "1:06:17", "throughput": 1316.01, "total_tokens": 17486816} {"current_steps": 30790, "total_steps": 40000, "loss": 0.0, "lr": 6.26151356681543e-06, "epoch": 540.1769911504425, "percentage": 76.98, "elapsed_time": "3:41:29", "remaining_time": "1:06:15", "throughput": 1316.04, "total_tokens": 17489920} {"current_steps": 30795, "total_steps": 40000, "loss": 0.0, "lr": 6.255016237994981e-06, "epoch": 540.2654867256637, "percentage": 76.99, "elapsed_time": "3:41:31", "remaining_time": "1:06:13", "throughput": 1316.07, "total_tokens": 17493120} {"current_steps": 30800, "total_steps": 40000, "loss": 0.0, "lr": 6.248521799886603e-06, "epoch": 540.3539823008849, "percentage": 77.0, "elapsed_time": "3:41:33", "remaining_time": "1:06:10", "throughput": 1316.06, "total_tokens": 17495648} {"current_steps": 30800, "total_steps": 40000, "eval_loss": 0.9451584219932556, "epoch": 540.3539823008849, "percentage": 77.0, "elapsed_time": "3:41:35", "remaining_time": "1:06:11", "throughput": 1315.95, "total_tokens": 17495648} {"current_steps": 30805, "total_steps": 40000, "loss": 0.0, "lr": 6.242030253491798e-06, "epoch": 540.4424778761062, "percentage": 77.01, "elapsed_time": "3:41:40", "remaining_time": "1:06:10", "throughput": 1315.62, "total_tokens": 17498352} {"current_steps": 30810, "total_steps": 40000, "loss": 0.0, "lr": 6.235541599811656e-06, "epoch": 540.5309734513274, "percentage": 77.03, "elapsed_time": "3:41:42", "remaining_time": "1:06:07", "throughput": 1315.62, "total_tokens": 17501120} {"current_steps": 30815, "total_steps": 40000, "loss": 0.0, "lr": 6.229055839846814e-06, "epoch": 540.6194690265487, "percentage": 77.04, "elapsed_time": "3:41:44", "remaining_time": "1:06:05", "throughput": 1315.65, "total_tokens": 17504240} {"current_steps": 30820, "total_steps": 40000, "loss": 0.0, "lr": 6.222572974597455e-06, "epoch": 540.70796460177, "percentage": 77.05, "elapsed_time": "3:41:46", "remaining_time": "1:06:03", "throughput": 1315.66, "total_tokens": 17507136} {"current_steps": 30825, "total_steps": 40000, "loss": 0.0, "lr": 6.216093005063306e-06, "epoch": 540.7964601769911, "percentage": 77.06, "elapsed_time": "3:41:48", "remaining_time": "1:06:01", "throughput": 1315.67, "total_tokens": 17509952} {"current_steps": 30830, "total_steps": 40000, "loss": 0.0, "lr": 6.209615932243678e-06, "epoch": 540.8849557522124, "percentage": 77.08, "elapsed_time": "3:41:50", "remaining_time": "1:05:59", "throughput": 1315.66, "total_tokens": 17512608} {"current_steps": 30835, "total_steps": 40000, "loss": 0.0, "lr": 6.203141757137399e-06, "epoch": 540.9734513274336, "percentage": 77.09, "elapsed_time": "3:41:52", "remaining_time": "1:05:56", "throughput": 1315.69, "total_tokens": 17515712} {"current_steps": 30840, "total_steps": 40000, "loss": 0.0, "lr": 6.196670480742886e-06, "epoch": 541.0530973451328, "percentage": 77.1, "elapsed_time": "3:41:55", "remaining_time": "1:05:54", "throughput": 1315.71, "total_tokens": 17518920} {"current_steps": 30845, "total_steps": 40000, "loss": 0.0, "lr": 6.190202104058074e-06, "epoch": 541.141592920354, "percentage": 77.11, "elapsed_time": "3:41:57", "remaining_time": "1:05:52", "throughput": 1315.71, "total_tokens": 17521688} {"current_steps": 30850, "total_steps": 40000, "loss": 0.0, "lr": 6.183736628080475e-06, "epoch": 541.2300884955753, "percentage": 77.12, "elapsed_time": "3:41:59", "remaining_time": "1:05:50", "throughput": 1315.72, "total_tokens": 17524584} {"current_steps": 30855, "total_steps": 40000, "loss": 0.0, "lr": 6.177274053807155e-06, "epoch": 541.3185840707964, "percentage": 77.14, "elapsed_time": "3:42:01", "remaining_time": "1:05:48", "throughput": 1315.71, "total_tokens": 17527096} {"current_steps": 30860, "total_steps": 40000, "loss": 0.0, "lr": 6.170814382234713e-06, "epoch": 541.4070796460177, "percentage": 77.15, "elapsed_time": "3:42:03", "remaining_time": "1:05:46", "throughput": 1315.73, "total_tokens": 17530072} {"current_steps": 30865, "total_steps": 40000, "loss": 0.0, "lr": 6.16435761435932e-06, "epoch": 541.4955752212389, "percentage": 77.16, "elapsed_time": "3:42:05", "remaining_time": "1:05:43", "throughput": 1315.73, "total_tokens": 17532920} {"current_steps": 30870, "total_steps": 40000, "loss": 0.0, "lr": 6.157903751176681e-06, "epoch": 541.5840707964602, "percentage": 77.18, "elapsed_time": "3:42:07", "remaining_time": "1:05:41", "throughput": 1315.71, "total_tokens": 17535288} {"current_steps": 30875, "total_steps": 40000, "loss": 0.0, "lr": 6.151452793682066e-06, "epoch": 541.6725663716815, "percentage": 77.19, "elapsed_time": "3:42:09", "remaining_time": "1:05:39", "throughput": 1315.71, "total_tokens": 17538088} {"current_steps": 30880, "total_steps": 40000, "loss": 0.0, "lr": 6.145004742870305e-06, "epoch": 541.7610619469026, "percentage": 77.2, "elapsed_time": "3:42:11", "remaining_time": "1:05:37", "throughput": 1315.74, "total_tokens": 17541112} {"current_steps": 30885, "total_steps": 40000, "loss": 0.0, "lr": 6.138559599735752e-06, "epoch": 541.8495575221239, "percentage": 77.21, "elapsed_time": "3:42:13", "remaining_time": "1:05:35", "throughput": 1315.73, "total_tokens": 17543800} {"current_steps": 30890, "total_steps": 40000, "loss": 0.0, "lr": 6.132117365272344e-06, "epoch": 541.9380530973451, "percentage": 77.22, "elapsed_time": "3:42:15", "remaining_time": "1:05:32", "throughput": 1315.76, "total_tokens": 17546808} {"current_steps": 30895, "total_steps": 40000, "loss": 0.0, "lr": 6.125678040473545e-06, "epoch": 542.0176991150443, "percentage": 77.24, "elapsed_time": "3:42:18", "remaining_time": "1:05:30", "throughput": 1315.71, "total_tokens": 17549200} {"current_steps": 30900, "total_steps": 40000, "loss": 0.0, "lr": 6.1192416263323755e-06, "epoch": 542.1061946902655, "percentage": 77.25, "elapsed_time": "3:42:20", "remaining_time": "1:05:28", "throughput": 1315.71, "total_tokens": 17551856} {"current_steps": 30905, "total_steps": 40000, "loss": 0.0, "lr": 6.112808123841424e-06, "epoch": 542.1946902654868, "percentage": 77.26, "elapsed_time": "3:42:22", "remaining_time": "1:05:26", "throughput": 1315.7, "total_tokens": 17554480} {"current_steps": 30910, "total_steps": 40000, "loss": 0.0, "lr": 6.106377533992805e-06, "epoch": 542.2831858407079, "percentage": 77.28, "elapsed_time": "3:42:24", "remaining_time": "1:05:24", "throughput": 1315.68, "total_tokens": 17556944} {"current_steps": 30915, "total_steps": 40000, "loss": 0.0, "lr": 6.099949857778204e-06, "epoch": 542.3716814159292, "percentage": 77.29, "elapsed_time": "3:42:26", "remaining_time": "1:05:22", "throughput": 1315.66, "total_tokens": 17559408} {"current_steps": 30920, "total_steps": 40000, "loss": 0.0, "lr": 6.093525096188852e-06, "epoch": 542.4601769911504, "percentage": 77.3, "elapsed_time": "3:42:28", "remaining_time": "1:05:19", "throughput": 1315.7, "total_tokens": 17562704} {"current_steps": 30925, "total_steps": 40000, "loss": 0.0, "lr": 6.087103250215518e-06, "epoch": 542.5486725663717, "percentage": 77.31, "elapsed_time": "3:42:30", "remaining_time": "1:05:17", "throughput": 1315.75, "total_tokens": 17566128} {"current_steps": 30930, "total_steps": 40000, "loss": 0.0, "lr": 6.080684320848537e-06, "epoch": 542.637168141593, "percentage": 77.33, "elapsed_time": "3:42:32", "remaining_time": "1:05:15", "throughput": 1315.77, "total_tokens": 17569056} {"current_steps": 30935, "total_steps": 40000, "loss": 0.0, "lr": 6.074268309077794e-06, "epoch": 542.7256637168142, "percentage": 77.34, "elapsed_time": "3:42:34", "remaining_time": "1:05:13", "throughput": 1315.78, "total_tokens": 17571920} {"current_steps": 30940, "total_steps": 40000, "loss": 0.0, "lr": 6.067855215892709e-06, "epoch": 542.8141592920354, "percentage": 77.35, "elapsed_time": "3:42:36", "remaining_time": "1:05:11", "throughput": 1315.78, "total_tokens": 17574656} {"current_steps": 30945, "total_steps": 40000, "loss": 0.0, "lr": 6.061445042282271e-06, "epoch": 542.9026548672566, "percentage": 77.36, "elapsed_time": "3:42:38", "remaining_time": "1:05:09", "throughput": 1315.82, "total_tokens": 17577936} {"current_steps": 30950, "total_steps": 40000, "loss": 0.0, "lr": 6.055037789234999e-06, "epoch": 542.9911504424779, "percentage": 77.38, "elapsed_time": "3:42:40", "remaining_time": "1:05:06", "throughput": 1315.85, "total_tokens": 17580992} {"current_steps": 30955, "total_steps": 40000, "loss": 0.0, "lr": 6.048633457738975e-06, "epoch": 543.070796460177, "percentage": 77.39, "elapsed_time": "3:42:43", "remaining_time": "1:05:04", "throughput": 1315.82, "total_tokens": 17583632} {"current_steps": 30960, "total_steps": 40000, "loss": 0.0, "lr": 6.042232048781837e-06, "epoch": 543.1592920353983, "percentage": 77.4, "elapsed_time": "3:42:45", "remaining_time": "1:05:02", "throughput": 1315.85, "total_tokens": 17586720} {"current_steps": 30965, "total_steps": 40000, "loss": 0.0, "lr": 6.035833563350757e-06, "epoch": 543.2477876106195, "percentage": 77.41, "elapsed_time": "3:42:47", "remaining_time": "1:05:00", "throughput": 1315.85, "total_tokens": 17589520} {"current_steps": 30970, "total_steps": 40000, "loss": 0.0, "lr": 6.0294380024324525e-06, "epoch": 543.3362831858407, "percentage": 77.42, "elapsed_time": "3:42:49", "remaining_time": "1:04:58", "throughput": 1315.85, "total_tokens": 17592240} {"current_steps": 30975, "total_steps": 40000, "loss": 0.0, "lr": 6.023045367013213e-06, "epoch": 543.4247787610619, "percentage": 77.44, "elapsed_time": "3:42:51", "remaining_time": "1:04:55", "throughput": 1315.89, "total_tokens": 17595472} {"current_steps": 30980, "total_steps": 40000, "loss": 0.0, "lr": 6.016655658078851e-06, "epoch": 543.5132743362832, "percentage": 77.45, "elapsed_time": "3:42:53", "remaining_time": "1:04:53", "throughput": 1315.92, "total_tokens": 17598656} {"current_steps": 30985, "total_steps": 40000, "loss": 0.0, "lr": 6.010268876614753e-06, "epoch": 543.6017699115044, "percentage": 77.46, "elapsed_time": "3:42:55", "remaining_time": "1:04:51", "throughput": 1315.94, "total_tokens": 17601600} {"current_steps": 30990, "total_steps": 40000, "loss": 0.0, "lr": 6.0038850236058266e-06, "epoch": 543.6902654867257, "percentage": 77.48, "elapsed_time": "3:42:57", "remaining_time": "1:04:49", "throughput": 1315.92, "total_tokens": 17604112} {"current_steps": 30995, "total_steps": 40000, "loss": 0.0, "lr": 5.997504100036549e-06, "epoch": 543.7787610619469, "percentage": 77.49, "elapsed_time": "3:42:59", "remaining_time": "1:04:47", "throughput": 1315.92, "total_tokens": 17606848} {"current_steps": 31000, "total_steps": 40000, "loss": 0.0, "lr": 5.991126106890949e-06, "epoch": 543.8672566371681, "percentage": 77.5, "elapsed_time": "3:43:01", "remaining_time": "1:04:45", "throughput": 1315.93, "total_tokens": 17609616} {"current_steps": 31000, "total_steps": 40000, "eval_loss": 0.9112905263900757, "epoch": 543.8672566371681, "percentage": 77.5, "elapsed_time": "3:43:02", "remaining_time": "1:04:45", "throughput": 1315.82, "total_tokens": 17609616} {"current_steps": 31005, "total_steps": 40000, "loss": 0.0, "lr": 5.984751045152576e-06, "epoch": 543.9557522123894, "percentage": 77.51, "elapsed_time": "3:43:07", "remaining_time": "1:04:43", "throughput": 1315.63, "total_tokens": 17612352} {"current_steps": 31010, "total_steps": 40000, "loss": 0.0, "lr": 5.978378915804553e-06, "epoch": 544.0353982300885, "percentage": 77.53, "elapsed_time": "3:43:09", "remaining_time": "1:04:41", "throughput": 1315.57, "total_tokens": 17614896} {"current_steps": 31015, "total_steps": 40000, "loss": 0.0, "lr": 5.972009719829547e-06, "epoch": 544.1238938053098, "percentage": 77.54, "elapsed_time": "3:43:11", "remaining_time": "1:04:39", "throughput": 1315.57, "total_tokens": 17617664} {"current_steps": 31020, "total_steps": 40000, "loss": 0.0, "lr": 5.965643458209755e-06, "epoch": 544.212389380531, "percentage": 77.55, "elapsed_time": "3:43:13", "remaining_time": "1:04:37", "throughput": 1315.6, "total_tokens": 17620752} {"current_steps": 31025, "total_steps": 40000, "loss": 0.0, "lr": 5.95928013192695e-06, "epoch": 544.3008849557522, "percentage": 77.56, "elapsed_time": "3:43:15", "remaining_time": "1:04:35", "throughput": 1315.57, "total_tokens": 17623200} {"current_steps": 31030, "total_steps": 40000, "loss": 0.0, "lr": 5.952919741962423e-06, "epoch": 544.3893805309734, "percentage": 77.58, "elapsed_time": "3:43:17", "remaining_time": "1:04:32", "throughput": 1315.56, "total_tokens": 17625744} {"current_steps": 31035, "total_steps": 40000, "loss": 0.0, "lr": 5.946562289297042e-06, "epoch": 544.4778761061947, "percentage": 77.59, "elapsed_time": "3:43:19", "remaining_time": "1:04:30", "throughput": 1315.58, "total_tokens": 17628736} {"current_steps": 31040, "total_steps": 40000, "loss": 0.0, "lr": 5.9402077749111855e-06, "epoch": 544.566371681416, "percentage": 77.6, "elapsed_time": "3:43:22", "remaining_time": "1:04:28", "throughput": 1315.54, "total_tokens": 17631328} {"current_steps": 31045, "total_steps": 40000, "loss": 0.0, "lr": 5.933856199784821e-06, "epoch": 544.6548672566372, "percentage": 77.61, "elapsed_time": "3:43:24", "remaining_time": "1:04:26", "throughput": 1315.61, "total_tokens": 17634928} {"current_steps": 31050, "total_steps": 40000, "loss": 0.0, "lr": 5.927507564897419e-06, "epoch": 544.7433628318585, "percentage": 77.62, "elapsed_time": "3:43:26", "remaining_time": "1:04:24", "throughput": 1315.62, "total_tokens": 17637808} {"current_steps": 31055, "total_steps": 40000, "loss": 0.0, "lr": 5.9211618712280395e-06, "epoch": 544.8318584070796, "percentage": 77.64, "elapsed_time": "3:43:28", "remaining_time": "1:04:22", "throughput": 1315.61, "total_tokens": 17640384} {"current_steps": 31060, "total_steps": 40000, "loss": 0.0, "lr": 5.914819119755255e-06, "epoch": 544.9203539823009, "percentage": 77.65, "elapsed_time": "3:43:30", "remaining_time": "1:04:19", "throughput": 1315.63, "total_tokens": 17643376} {"current_steps": 31065, "total_steps": 40000, "loss": 0.0, "lr": 5.908479311457205e-06, "epoch": 545.0, "percentage": 77.66, "elapsed_time": "3:43:32", "remaining_time": "1:04:17", "throughput": 1315.63, "total_tokens": 17646072} {"current_steps": 31070, "total_steps": 40000, "loss": 0.0, "lr": 5.902142447311559e-06, "epoch": 545.0884955752213, "percentage": 77.68, "elapsed_time": "3:43:34", "remaining_time": "1:04:15", "throughput": 1315.61, "total_tokens": 17648888} {"current_steps": 31075, "total_steps": 40000, "loss": 0.0, "lr": 5.895808528295546e-06, "epoch": 545.1769911504425, "percentage": 77.69, "elapsed_time": "3:43:37", "remaining_time": "1:04:13", "throughput": 1315.64, "total_tokens": 17651992} {"current_steps": 31080, "total_steps": 40000, "loss": 0.0, "lr": 5.889477555385941e-06, "epoch": 545.2654867256637, "percentage": 77.7, "elapsed_time": "3:43:39", "remaining_time": "1:04:11", "throughput": 1315.65, "total_tokens": 17654792} {"current_steps": 31085, "total_steps": 40000, "loss": 0.0, "lr": 5.883149529559051e-06, "epoch": 545.3539823008849, "percentage": 77.71, "elapsed_time": "3:43:41", "remaining_time": "1:04:09", "throughput": 1315.65, "total_tokens": 17657592} {"current_steps": 31090, "total_steps": 40000, "loss": 0.0, "lr": 5.876824451790738e-06, "epoch": 545.4424778761062, "percentage": 77.72, "elapsed_time": "3:43:43", "remaining_time": "1:04:06", "throughput": 1315.66, "total_tokens": 17660344} {"current_steps": 31095, "total_steps": 40000, "loss": 0.0, "lr": 5.87050232305642e-06, "epoch": 545.5309734513274, "percentage": 77.74, "elapsed_time": "3:43:45", "remaining_time": "1:04:04", "throughput": 1315.65, "total_tokens": 17663032} {"current_steps": 31100, "total_steps": 40000, "loss": 0.0, "lr": 5.864183144331034e-06, "epoch": 545.6194690265487, "percentage": 77.75, "elapsed_time": "3:43:47", "remaining_time": "1:04:02", "throughput": 1315.67, "total_tokens": 17666024} {"current_steps": 31105, "total_steps": 40000, "loss": 0.0, "lr": 5.857866916589089e-06, "epoch": 545.70796460177, "percentage": 77.76, "elapsed_time": "3:43:49", "remaining_time": "1:04:00", "throughput": 1315.7, "total_tokens": 17669080} {"current_steps": 31110, "total_steps": 40000, "loss": 0.0, "lr": 5.8515536408046216e-06, "epoch": 545.7964601769911, "percentage": 77.78, "elapsed_time": "3:43:51", "remaining_time": "1:03:58", "throughput": 1315.72, "total_tokens": 17672040} {"current_steps": 31115, "total_steps": 40000, "loss": 0.0, "lr": 5.845243317951208e-06, "epoch": 545.8849557522124, "percentage": 77.79, "elapsed_time": "3:43:53", "remaining_time": "1:03:56", "throughput": 1315.75, "total_tokens": 17675288} {"current_steps": 31120, "total_steps": 40000, "loss": 0.0, "lr": 5.838935949001997e-06, "epoch": 545.9734513274336, "percentage": 77.8, "elapsed_time": "3:43:55", "remaining_time": "1:03:53", "throughput": 1315.77, "total_tokens": 17678200} {"current_steps": 31125, "total_steps": 40000, "loss": 0.0, "lr": 5.8326315349296476e-06, "epoch": 546.0530973451328, "percentage": 77.81, "elapsed_time": "3:43:57", "remaining_time": "1:03:51", "throughput": 1315.71, "total_tokens": 17680416} {"current_steps": 31130, "total_steps": 40000, "loss": 0.0, "lr": 5.826330076706396e-06, "epoch": 546.141592920354, "percentage": 77.83, "elapsed_time": "3:43:59", "remaining_time": "1:03:49", "throughput": 1315.72, "total_tokens": 17683328} {"current_steps": 31135, "total_steps": 40000, "loss": 0.0, "lr": 5.820031575303988e-06, "epoch": 546.2300884955753, "percentage": 77.84, "elapsed_time": "3:44:02", "remaining_time": "1:03:47", "throughput": 1315.76, "total_tokens": 17686576} {"current_steps": 31140, "total_steps": 40000, "loss": 0.0, "lr": 5.813736031693745e-06, "epoch": 546.3185840707964, "percentage": 77.85, "elapsed_time": "3:44:04", "remaining_time": "1:03:45", "throughput": 1315.75, "total_tokens": 17689184} {"current_steps": 31145, "total_steps": 40000, "loss": 0.0, "lr": 5.807443446846522e-06, "epoch": 546.4070796460177, "percentage": 77.86, "elapsed_time": "3:44:06", "remaining_time": "1:03:42", "throughput": 1315.74, "total_tokens": 17691776} {"current_steps": 31150, "total_steps": 40000, "loss": 0.0, "lr": 5.801153821732699e-06, "epoch": 546.4955752212389, "percentage": 77.88, "elapsed_time": "3:44:08", "remaining_time": "1:03:40", "throughput": 1315.76, "total_tokens": 17694752} {"current_steps": 31155, "total_steps": 40000, "loss": 0.0, "lr": 5.794867157322229e-06, "epoch": 546.5840707964602, "percentage": 77.89, "elapsed_time": "3:44:10", "remaining_time": "1:03:38", "throughput": 1315.76, "total_tokens": 17697488} {"current_steps": 31160, "total_steps": 40000, "loss": 0.0, "lr": 5.788583454584593e-06, "epoch": 546.6725663716815, "percentage": 77.9, "elapsed_time": "3:44:12", "remaining_time": "1:03:36", "throughput": 1315.79, "total_tokens": 17700560} {"current_steps": 31165, "total_steps": 40000, "loss": 0.0, "lr": 5.7823027144888075e-06, "epoch": 546.7610619469026, "percentage": 77.91, "elapsed_time": "3:44:14", "remaining_time": "1:03:34", "throughput": 1315.81, "total_tokens": 17703584} {"current_steps": 31170, "total_steps": 40000, "loss": 0.0, "lr": 5.776024938003455e-06, "epoch": 546.8495575221239, "percentage": 77.92, "elapsed_time": "3:44:16", "remaining_time": "1:03:32", "throughput": 1315.81, "total_tokens": 17706320} {"current_steps": 31175, "total_steps": 40000, "loss": 0.0, "lr": 5.7697501260966345e-06, "epoch": 546.9380530973451, "percentage": 77.94, "elapsed_time": "3:44:18", "remaining_time": "1:03:29", "throughput": 1315.82, "total_tokens": 17709136} {"current_steps": 31180, "total_steps": 40000, "loss": 0.0, "lr": 5.7634782797360145e-06, "epoch": 547.0176991150443, "percentage": 77.95, "elapsed_time": "3:44:20", "remaining_time": "1:03:27", "throughput": 1315.84, "total_tokens": 17712368} {"current_steps": 31185, "total_steps": 40000, "loss": 0.0, "lr": 5.757209399888777e-06, "epoch": 547.1061946902655, "percentage": 77.96, "elapsed_time": "3:44:22", "remaining_time": "1:03:25", "throughput": 1315.86, "total_tokens": 17715392} {"current_steps": 31190, "total_steps": 40000, "loss": 0.0, "lr": 5.750943487521679e-06, "epoch": 547.1946902654868, "percentage": 77.98, "elapsed_time": "3:44:25", "remaining_time": "1:03:23", "throughput": 1315.9, "total_tokens": 17718640} {"current_steps": 31195, "total_steps": 40000, "loss": 0.0, "lr": 5.744680543600986e-06, "epoch": 547.2831858407079, "percentage": 77.99, "elapsed_time": "3:44:27", "remaining_time": "1:03:21", "throughput": 1315.89, "total_tokens": 17721200} {"current_steps": 31200, "total_steps": 40000, "loss": 0.0, "lr": 5.738420569092537e-06, "epoch": 547.3716814159292, "percentage": 78.0, "elapsed_time": "3:44:29", "remaining_time": "1:03:19", "throughput": 1315.86, "total_tokens": 17723600} {"current_steps": 31200, "total_steps": 40000, "eval_loss": 0.9103177785873413, "epoch": 547.3716814159292, "percentage": 78.0, "elapsed_time": "3:44:30", "remaining_time": "1:03:19", "throughput": 1315.76, "total_tokens": 17723600} {"current_steps": 31205, "total_steps": 40000, "loss": 0.0, "lr": 5.732163564961684e-06, "epoch": 547.4601769911504, "percentage": 78.01, "elapsed_time": "3:44:34", "remaining_time": "1:03:17", "throughput": 1315.58, "total_tokens": 17726800} {"current_steps": 31210, "total_steps": 40000, "loss": 0.0, "lr": 5.725909532173354e-06, "epoch": 547.5486725663717, "percentage": 78.03, "elapsed_time": "3:44:36", "remaining_time": "1:03:15", "throughput": 1315.59, "total_tokens": 17729728} {"current_steps": 31215, "total_steps": 40000, "loss": 0.0, "lr": 5.719658471691977e-06, "epoch": 547.637168141593, "percentage": 78.04, "elapsed_time": "3:44:38", "remaining_time": "1:03:13", "throughput": 1315.6, "total_tokens": 17732624} {"current_steps": 31220, "total_steps": 40000, "loss": 0.0, "lr": 5.71341038448156e-06, "epoch": 547.7256637168142, "percentage": 78.05, "elapsed_time": "3:44:40", "remaining_time": "1:03:11", "throughput": 1315.61, "total_tokens": 17735488} {"current_steps": 31225, "total_steps": 40000, "loss": 0.0, "lr": 5.707165271505635e-06, "epoch": 547.8141592920354, "percentage": 78.06, "elapsed_time": "3:44:42", "remaining_time": "1:03:09", "throughput": 1315.59, "total_tokens": 17737824} {"current_steps": 31230, "total_steps": 40000, "loss": 0.0, "lr": 5.700923133727271e-06, "epoch": 547.9026548672566, "percentage": 78.08, "elapsed_time": "3:44:44", "remaining_time": "1:03:06", "throughput": 1315.58, "total_tokens": 17740432} {"current_steps": 31235, "total_steps": 40000, "loss": 0.0, "lr": 5.694683972109083e-06, "epoch": 547.9911504424779, "percentage": 78.09, "elapsed_time": "3:44:46", "remaining_time": "1:03:04", "throughput": 1315.61, "total_tokens": 17743584} {"current_steps": 31240, "total_steps": 40000, "loss": 0.0, "lr": 5.688447787613241e-06, "epoch": 548.070796460177, "percentage": 78.1, "elapsed_time": "3:44:49", "remaining_time": "1:03:02", "throughput": 1315.59, "total_tokens": 17746264} {"current_steps": 31245, "total_steps": 40000, "loss": 0.0, "lr": 5.6822145812014285e-06, "epoch": 548.1592920353983, "percentage": 78.11, "elapsed_time": "3:44:51", "remaining_time": "1:03:00", "throughput": 1315.57, "total_tokens": 17748776} {"current_steps": 31250, "total_steps": 40000, "loss": 0.0, "lr": 5.675984353834896e-06, "epoch": 548.2477876106195, "percentage": 78.12, "elapsed_time": "3:44:53", "remaining_time": "1:02:58", "throughput": 1315.55, "total_tokens": 17751256} {"current_steps": 31255, "total_steps": 40000, "loss": 0.0, "lr": 5.66975710647441e-06, "epoch": 548.3362831858407, "percentage": 78.14, "elapsed_time": "3:44:55", "remaining_time": "1:02:55", "throughput": 1315.56, "total_tokens": 17754136} {"current_steps": 31260, "total_steps": 40000, "loss": 0.0, "lr": 5.663532840080304e-06, "epoch": 548.4247787610619, "percentage": 78.15, "elapsed_time": "3:44:57", "remaining_time": "1:02:53", "throughput": 1315.6, "total_tokens": 17757288} {"current_steps": 31265, "total_steps": 40000, "loss": 0.0, "lr": 5.6573115556124325e-06, "epoch": 548.5132743362832, "percentage": 78.16, "elapsed_time": "3:44:59", "remaining_time": "1:02:51", "throughput": 1315.62, "total_tokens": 17760312} {"current_steps": 31270, "total_steps": 40000, "loss": 0.0, "lr": 5.651093254030185e-06, "epoch": 548.6017699115044, "percentage": 78.17, "elapsed_time": "3:45:01", "remaining_time": "1:02:49", "throughput": 1315.61, "total_tokens": 17762920} {"current_steps": 31275, "total_steps": 40000, "loss": 0.0, "lr": 5.644877936292514e-06, "epoch": 548.6902654867257, "percentage": 78.19, "elapsed_time": "3:45:03", "remaining_time": "1:02:47", "throughput": 1315.61, "total_tokens": 17765608} {"current_steps": 31280, "total_steps": 40000, "loss": 0.0, "lr": 5.638665603357901e-06, "epoch": 548.7787610619469, "percentage": 78.2, "elapsed_time": "3:45:05", "remaining_time": "1:02:45", "throughput": 1315.58, "total_tokens": 17768024} {"current_steps": 31285, "total_steps": 40000, "loss": 0.0, "lr": 5.632456256184357e-06, "epoch": 548.8672566371681, "percentage": 78.21, "elapsed_time": "3:45:07", "remaining_time": "1:02:42", "throughput": 1315.63, "total_tokens": 17771368} {"current_steps": 31290, "total_steps": 40000, "loss": 0.0, "lr": 5.626249895729452e-06, "epoch": 548.9557522123894, "percentage": 78.22, "elapsed_time": "3:45:09", "remaining_time": "1:02:40", "throughput": 1315.67, "total_tokens": 17774648} {"current_steps": 31295, "total_steps": 40000, "loss": 0.0, "lr": 5.620046522950273e-06, "epoch": 549.0353982300885, "percentage": 78.24, "elapsed_time": "3:45:12", "remaining_time": "1:02:38", "throughput": 1315.61, "total_tokens": 17776816} {"current_steps": 31300, "total_steps": 40000, "loss": 0.0, "lr": 5.613846138803464e-06, "epoch": 549.1238938053098, "percentage": 78.25, "elapsed_time": "3:45:14", "remaining_time": "1:02:36", "throughput": 1315.61, "total_tokens": 17779472} {"current_steps": 31305, "total_steps": 40000, "loss": 0.0, "lr": 5.607648744245206e-06, "epoch": 549.212389380531, "percentage": 78.26, "elapsed_time": "3:45:16", "remaining_time": "1:02:34", "throughput": 1315.62, "total_tokens": 17782336} {"current_steps": 31310, "total_steps": 40000, "loss": 0.0, "lr": 5.601454340231207e-06, "epoch": 549.3008849557522, "percentage": 78.27, "elapsed_time": "3:45:18", "remaining_time": "1:02:31", "throughput": 1315.61, "total_tokens": 17784976} {"current_steps": 31315, "total_steps": 40000, "loss": 0.0, "lr": 5.595262927716724e-06, "epoch": 549.3893805309734, "percentage": 78.29, "elapsed_time": "3:45:20", "remaining_time": "1:02:29", "throughput": 1315.6, "total_tokens": 17787536} {"current_steps": 31320, "total_steps": 40000, "loss": 0.0, "lr": 5.589074507656561e-06, "epoch": 549.4778761061947, "percentage": 78.3, "elapsed_time": "3:45:22", "remaining_time": "1:02:27", "throughput": 1315.62, "total_tokens": 17790512} {"current_steps": 31325, "total_steps": 40000, "loss": 0.0, "lr": 5.582889081005044e-06, "epoch": 549.566371681416, "percentage": 78.31, "elapsed_time": "3:45:24", "remaining_time": "1:02:25", "throughput": 1315.61, "total_tokens": 17793200} {"current_steps": 31330, "total_steps": 40000, "loss": 0.0, "lr": 5.5767066487160316e-06, "epoch": 549.6548672566372, "percentage": 78.33, "elapsed_time": "3:45:26", "remaining_time": "1:02:23", "throughput": 1315.62, "total_tokens": 17796080} {"current_steps": 31335, "total_steps": 40000, "loss": 0.0, "lr": 5.570527211742949e-06, "epoch": 549.7433628318585, "percentage": 78.34, "elapsed_time": "3:45:28", "remaining_time": "1:02:21", "throughput": 1315.63, "total_tokens": 17798960} {"current_steps": 31340, "total_steps": 40000, "loss": 0.0, "lr": 5.564350771038731e-06, "epoch": 549.8318584070796, "percentage": 78.35, "elapsed_time": "3:45:30", "remaining_time": "1:02:18", "throughput": 1315.63, "total_tokens": 17801680} {"current_steps": 31345, "total_steps": 40000, "loss": 0.0, "lr": 5.558177327555875e-06, "epoch": 549.9203539823009, "percentage": 78.36, "elapsed_time": "3:45:32", "remaining_time": "1:02:16", "throughput": 1315.7, "total_tokens": 17805264} {"current_steps": 31350, "total_steps": 40000, "loss": 0.0, "lr": 5.552006882246388e-06, "epoch": 550.0, "percentage": 78.38, "elapsed_time": "3:45:34", "remaining_time": "1:02:14", "throughput": 1315.68, "total_tokens": 17807696} {"current_steps": 31355, "total_steps": 40000, "loss": 0.0, "lr": 5.545839436061839e-06, "epoch": 550.0884955752213, "percentage": 78.39, "elapsed_time": "3:45:37", "remaining_time": "1:02:12", "throughput": 1315.66, "total_tokens": 17810464} {"current_steps": 31360, "total_steps": 40000, "loss": 0.0, "lr": 5.539674989953331e-06, "epoch": 550.1769911504425, "percentage": 78.4, "elapsed_time": "3:45:39", "remaining_time": "1:02:10", "throughput": 1315.68, "total_tokens": 17813504} {"current_steps": 31365, "total_steps": 40000, "loss": 0.0, "lr": 5.533513544871488e-06, "epoch": 550.2654867256637, "percentage": 78.41, "elapsed_time": "3:45:41", "remaining_time": "1:02:08", "throughput": 1315.7, "total_tokens": 17816384} {"current_steps": 31370, "total_steps": 40000, "loss": 0.0, "lr": 5.527355101766493e-06, "epoch": 550.3539823008849, "percentage": 78.42, "elapsed_time": "3:45:43", "remaining_time": "1:02:05", "throughput": 1315.71, "total_tokens": 17819248} {"current_steps": 31375, "total_steps": 40000, "loss": 0.0, "lr": 5.521199661588044e-06, "epoch": 550.4424778761062, "percentage": 78.44, "elapsed_time": "3:45:45", "remaining_time": "1:02:03", "throughput": 1315.71, "total_tokens": 17822096} {"current_steps": 31380, "total_steps": 40000, "loss": 0.0, "lr": 5.5150472252853944e-06, "epoch": 550.5309734513274, "percentage": 78.45, "elapsed_time": "3:45:47", "remaining_time": "1:02:01", "throughput": 1315.74, "total_tokens": 17825216} {"current_steps": 31385, "total_steps": 40000, "loss": 0.0, "lr": 5.50889779380733e-06, "epoch": 550.6194690265487, "percentage": 78.46, "elapsed_time": "3:45:49", "remaining_time": "1:01:59", "throughput": 1315.74, "total_tokens": 17827856} {"current_steps": 31390, "total_steps": 40000, "loss": 0.0, "lr": 5.5027513681021605e-06, "epoch": 550.70796460177, "percentage": 78.47, "elapsed_time": "3:45:51", "remaining_time": "1:01:57", "throughput": 1315.75, "total_tokens": 17830752} {"current_steps": 31395, "total_steps": 40000, "loss": 0.0, "lr": 5.4966079491177545e-06, "epoch": 550.7964601769911, "percentage": 78.49, "elapsed_time": "3:45:53", "remaining_time": "1:01:54", "throughput": 1315.76, "total_tokens": 17833584} {"current_steps": 31400, "total_steps": 40000, "loss": 0.0, "lr": 5.490467537801491e-06, "epoch": 550.8849557522124, "percentage": 78.5, "elapsed_time": "3:45:55", "remaining_time": "1:01:52", "throughput": 1315.77, "total_tokens": 17836576} {"current_steps": 31400, "total_steps": 40000, "eval_loss": 0.8986397981643677, "epoch": 550.8849557522124, "percentage": 78.5, "elapsed_time": "3:45:57", "remaining_time": "1:01:53", "throughput": 1315.67, "total_tokens": 17836576} {"current_steps": 31405, "total_steps": 40000, "loss": 0.0, "lr": 5.484330135100313e-06, "epoch": 550.9734513274336, "percentage": 78.51, "elapsed_time": "3:46:01", "remaining_time": "1:01:51", "throughput": 1315.41, "total_tokens": 17839360} {"current_steps": 31410, "total_steps": 40000, "loss": 0.0, "lr": 5.4781957419606785e-06, "epoch": 551.0530973451328, "percentage": 78.53, "elapsed_time": "3:46:04", "remaining_time": "1:01:49", "throughput": 1315.35, "total_tokens": 17841592} {"current_steps": 31415, "total_steps": 40000, "loss": 0.0, "lr": 5.472064359328577e-06, "epoch": 551.141592920354, "percentage": 78.54, "elapsed_time": "3:46:06", "remaining_time": "1:01:47", "throughput": 1315.37, "total_tokens": 17844552} {"current_steps": 31420, "total_steps": 40000, "loss": 0.0, "lr": 5.4659359881495565e-06, "epoch": 551.2300884955753, "percentage": 78.55, "elapsed_time": "3:46:08", "remaining_time": "1:01:45", "throughput": 1315.38, "total_tokens": 17847512} {"current_steps": 31425, "total_steps": 40000, "loss": 0.0, "lr": 5.4598106293686916e-06, "epoch": 551.3185840707964, "percentage": 78.56, "elapsed_time": "3:46:10", "remaining_time": "1:01:42", "throughput": 1315.41, "total_tokens": 17850616} {"current_steps": 31430, "total_steps": 40000, "loss": 0.0, "lr": 5.45368828393058e-06, "epoch": 551.4070796460177, "percentage": 78.57, "elapsed_time": "3:46:12", "remaining_time": "1:01:40", "throughput": 1315.42, "total_tokens": 17853432} {"current_steps": 31435, "total_steps": 40000, "loss": 0.0, "lr": 5.44756895277937e-06, "epoch": 551.4955752212389, "percentage": 78.59, "elapsed_time": "3:46:14", "remaining_time": "1:01:38", "throughput": 1315.47, "total_tokens": 17856856} {"current_steps": 31440, "total_steps": 40000, "loss": 0.0, "lr": 5.441452636858746e-06, "epoch": 551.5840707964602, "percentage": 78.6, "elapsed_time": "3:46:16", "remaining_time": "1:01:36", "throughput": 1315.51, "total_tokens": 17860120} {"current_steps": 31445, "total_steps": 40000, "loss": 0.0, "lr": 5.435339337111905e-06, "epoch": 551.6725663716815, "percentage": 78.61, "elapsed_time": "3:46:18", "remaining_time": "1:01:34", "throughput": 1315.51, "total_tokens": 17862840} {"current_steps": 31450, "total_steps": 40000, "loss": 0.0, "lr": 5.42922905448161e-06, "epoch": 551.7610619469026, "percentage": 78.62, "elapsed_time": "3:46:20", "remaining_time": "1:01:32", "throughput": 1315.51, "total_tokens": 17865560} {"current_steps": 31455, "total_steps": 40000, "loss": 0.0, "lr": 5.423121789910129e-06, "epoch": 551.8495575221239, "percentage": 78.64, "elapsed_time": "3:46:22", "remaining_time": "1:01:29", "throughput": 1315.49, "total_tokens": 17868056} {"current_steps": 31460, "total_steps": 40000, "loss": 0.0, "lr": 5.417017544339287e-06, "epoch": 551.9380530973451, "percentage": 78.65, "elapsed_time": "3:46:24", "remaining_time": "1:01:27", "throughput": 1315.51, "total_tokens": 17870984} {"current_steps": 31465, "total_steps": 40000, "loss": 0.0, "lr": 5.410916318710443e-06, "epoch": 552.0176991150443, "percentage": 78.66, "elapsed_time": "3:46:27", "remaining_time": "1:01:25", "throughput": 1315.46, "total_tokens": 17873320} {"current_steps": 31470, "total_steps": 40000, "loss": 0.0, "lr": 5.404818113964466e-06, "epoch": 552.1061946902655, "percentage": 78.67, "elapsed_time": "3:46:29", "remaining_time": "1:01:23", "throughput": 1315.46, "total_tokens": 17876056} {"current_steps": 31475, "total_steps": 40000, "loss": 0.0, "lr": 5.398722931041792e-06, "epoch": 552.1946902654868, "percentage": 78.69, "elapsed_time": "3:46:31", "remaining_time": "1:01:21", "throughput": 1315.48, "total_tokens": 17879000} {"current_steps": 31480, "total_steps": 40000, "loss": 0.0, "lr": 5.392630770882367e-06, "epoch": 552.2831858407079, "percentage": 78.7, "elapsed_time": "3:46:33", "remaining_time": "1:01:19", "throughput": 1315.5, "total_tokens": 17881992} {"current_steps": 31485, "total_steps": 40000, "loss": 0.0, "lr": 5.3865416344256705e-06, "epoch": 552.3716814159292, "percentage": 78.71, "elapsed_time": "3:46:35", "remaining_time": "1:01:16", "throughput": 1315.48, "total_tokens": 17884488} {"current_steps": 31490, "total_steps": 40000, "loss": 0.0, "lr": 5.380455522610742e-06, "epoch": 552.4601769911504, "percentage": 78.72, "elapsed_time": "3:46:37", "remaining_time": "1:01:14", "throughput": 1315.48, "total_tokens": 17887144} {"current_steps": 31495, "total_steps": 40000, "loss": 0.0, "lr": 5.374372436376116e-06, "epoch": 552.5486725663717, "percentage": 78.74, "elapsed_time": "3:46:39", "remaining_time": "1:01:12", "throughput": 1315.46, "total_tokens": 17889704} {"current_steps": 31500, "total_steps": 40000, "loss": 0.0, "lr": 5.368292376659895e-06, "epoch": 552.637168141593, "percentage": 78.75, "elapsed_time": "3:46:41", "remaining_time": "1:01:10", "throughput": 1315.5, "total_tokens": 17892952} {"current_steps": 31505, "total_steps": 40000, "loss": 0.0, "lr": 5.362215344399701e-06, "epoch": 552.7256637168142, "percentage": 78.76, "elapsed_time": "3:46:43", "remaining_time": "1:01:08", "throughput": 1315.52, "total_tokens": 17895880} {"current_steps": 31510, "total_steps": 40000, "loss": 0.0, "lr": 5.356141340532678e-06, "epoch": 552.8141592920354, "percentage": 78.77, "elapsed_time": "3:46:45", "remaining_time": "1:01:05", "throughput": 1315.52, "total_tokens": 17898680} {"current_steps": 31515, "total_steps": 40000, "loss": 0.0, "lr": 5.350070365995522e-06, "epoch": 552.9026548672566, "percentage": 78.79, "elapsed_time": "3:46:47", "remaining_time": "1:01:03", "throughput": 1315.59, "total_tokens": 17902360} {"current_steps": 31520, "total_steps": 40000, "loss": 0.0, "lr": 5.344002421724459e-06, "epoch": 552.9911504424779, "percentage": 78.8, "elapsed_time": "3:46:49", "remaining_time": "1:01:01", "throughput": 1315.57, "total_tokens": 17904840} {"current_steps": 31525, "total_steps": 40000, "loss": 0.0, "lr": 5.337937508655228e-06, "epoch": 553.070796460177, "percentage": 78.81, "elapsed_time": "3:46:52", "remaining_time": "1:00:59", "throughput": 1315.54, "total_tokens": 17907416} {"current_steps": 31530, "total_steps": 40000, "loss": 0.0, "lr": 5.331875627723126e-06, "epoch": 553.1592920353983, "percentage": 78.83, "elapsed_time": "3:46:54", "remaining_time": "1:00:57", "throughput": 1315.53, "total_tokens": 17910024} {"current_steps": 31535, "total_steps": 40000, "loss": 0.0, "lr": 5.325816779862963e-06, "epoch": 553.2477876106195, "percentage": 78.84, "elapsed_time": "3:46:56", "remaining_time": "1:00:55", "throughput": 1315.57, "total_tokens": 17913384} {"current_steps": 31540, "total_steps": 40000, "loss": 0.0, "lr": 5.319760966009102e-06, "epoch": 553.3362831858407, "percentage": 78.85, "elapsed_time": "3:46:58", "remaining_time": "1:00:52", "throughput": 1315.59, "total_tokens": 17916520} {"current_steps": 31545, "total_steps": 40000, "loss": 0.0, "lr": 5.3137081870954096e-06, "epoch": 553.4247787610619, "percentage": 78.86, "elapsed_time": "3:47:00", "remaining_time": "1:00:50", "throughput": 1315.63, "total_tokens": 17919768} {"current_steps": 31550, "total_steps": 40000, "loss": 0.0, "lr": 5.307658444055313e-06, "epoch": 553.5132743362832, "percentage": 78.88, "elapsed_time": "3:47:02", "remaining_time": "1:00:48", "throughput": 1315.64, "total_tokens": 17922728} {"current_steps": 31555, "total_steps": 40000, "loss": 0.0, "lr": 5.301611737821749e-06, "epoch": 553.6017699115044, "percentage": 78.89, "elapsed_time": "3:47:04", "remaining_time": "1:00:46", "throughput": 1315.62, "total_tokens": 17925240} {"current_steps": 31560, "total_steps": 40000, "loss": 0.0, "lr": 5.295568069327206e-06, "epoch": 553.6902654867257, "percentage": 78.9, "elapsed_time": "3:47:07", "remaining_time": "1:00:44", "throughput": 1315.63, "total_tokens": 17928088} {"current_steps": 31565, "total_steps": 40000, "loss": 0.0, "lr": 5.289527439503683e-06, "epoch": 553.7787610619469, "percentage": 78.91, "elapsed_time": "3:47:09", "remaining_time": "1:00:42", "throughput": 1315.62, "total_tokens": 17930728} {"current_steps": 31570, "total_steps": 40000, "loss": 0.0, "lr": 5.28348984928273e-06, "epoch": 553.8672566371681, "percentage": 78.92, "elapsed_time": "3:47:11", "remaining_time": "1:00:39", "throughput": 1315.61, "total_tokens": 17933432} {"current_steps": 31575, "total_steps": 40000, "loss": 0.0, "lr": 5.27745529959541e-06, "epoch": 553.9557522123894, "percentage": 78.94, "elapsed_time": "3:47:13", "remaining_time": "1:00:37", "throughput": 1315.62, "total_tokens": 17936280} {"current_steps": 31580, "total_steps": 40000, "loss": 0.0, "lr": 5.271423791372335e-06, "epoch": 554.0353982300885, "percentage": 78.95, "elapsed_time": "3:47:15", "remaining_time": "1:00:35", "throughput": 1315.58, "total_tokens": 17938712} {"current_steps": 31585, "total_steps": 40000, "loss": 0.0, "lr": 5.26539532554364e-06, "epoch": 554.1238938053098, "percentage": 78.96, "elapsed_time": "3:47:17", "remaining_time": "1:00:33", "throughput": 1315.59, "total_tokens": 17941640} {"current_steps": 31590, "total_steps": 40000, "loss": 0.0, "lr": 5.25936990303898e-06, "epoch": 554.212389380531, "percentage": 78.97, "elapsed_time": "3:47:19", "remaining_time": "1:00:31", "throughput": 1315.59, "total_tokens": 17944392} {"current_steps": 31595, "total_steps": 40000, "loss": 0.0, "lr": 5.253347524787555e-06, "epoch": 554.3008849557522, "percentage": 78.99, "elapsed_time": "3:47:21", "remaining_time": "1:00:29", "throughput": 1315.6, "total_tokens": 17947416} {"current_steps": 31600, "total_steps": 40000, "loss": 0.0, "lr": 5.2473281917181035e-06, "epoch": 554.3893805309734, "percentage": 79.0, "elapsed_time": "3:47:24", "remaining_time": "1:00:26", "throughput": 1315.59, "total_tokens": 17949928} {"current_steps": 31600, "total_steps": 40000, "eval_loss": 0.8947702646255493, "epoch": 554.3893805309734, "percentage": 79.0, "elapsed_time": "3:47:25", "remaining_time": "1:00:27", "throughput": 1315.48, "total_tokens": 17949928} {"current_steps": 31605, "total_steps": 40000, "loss": 0.0, "lr": 5.241311904758864e-06, "epoch": 554.4778761061947, "percentage": 79.01, "elapsed_time": "3:47:29", "remaining_time": "1:00:25", "throughput": 1315.29, "total_tokens": 17952648} {"current_steps": 31610, "total_steps": 40000, "loss": 0.0, "lr": 5.23529866483764e-06, "epoch": 554.566371681416, "percentage": 79.03, "elapsed_time": "3:47:31", "remaining_time": "1:00:23", "throughput": 1315.31, "total_tokens": 17955656} {"current_steps": 31615, "total_steps": 40000, "loss": 0.0, "lr": 5.229288472881732e-06, "epoch": 554.6548672566372, "percentage": 79.04, "elapsed_time": "3:47:33", "remaining_time": "1:00:21", "throughput": 1315.32, "total_tokens": 17958504} {"current_steps": 31620, "total_steps": 40000, "loss": 0.0, "lr": 5.2232813298180025e-06, "epoch": 554.7433628318585, "percentage": 79.05, "elapsed_time": "3:47:35", "remaining_time": "1:00:19", "throughput": 1315.32, "total_tokens": 17961272} {"current_steps": 31625, "total_steps": 40000, "loss": 0.0, "lr": 5.217277236572824e-06, "epoch": 554.8318584070796, "percentage": 79.06, "elapsed_time": "3:47:37", "remaining_time": "1:00:16", "throughput": 1315.32, "total_tokens": 17964104} {"current_steps": 31630, "total_steps": 40000, "loss": 0.0, "lr": 5.211276194072093e-06, "epoch": 554.9203539823009, "percentage": 79.07, "elapsed_time": "3:47:39", "remaining_time": "1:00:14", "throughput": 1315.36, "total_tokens": 17967416} {"current_steps": 31635, "total_steps": 40000, "loss": 0.0, "lr": 5.205278203241254e-06, "epoch": 555.0, "percentage": 79.09, "elapsed_time": "3:47:41", "remaining_time": "1:00:12", "throughput": 1315.35, "total_tokens": 17969928} {"current_steps": 31640, "total_steps": 40000, "loss": 0.0, "lr": 5.199283265005278e-06, "epoch": 555.0884955752213, "percentage": 79.1, "elapsed_time": "3:47:44", "remaining_time": "1:00:10", "throughput": 1315.36, "total_tokens": 17973176} {"current_steps": 31645, "total_steps": 40000, "loss": 0.0, "lr": 5.193291380288648e-06, "epoch": 555.1769911504425, "percentage": 79.11, "elapsed_time": "3:47:46", "remaining_time": "1:00:08", "throughput": 1315.37, "total_tokens": 17976056} {"current_steps": 31650, "total_steps": 40000, "loss": 0.0, "lr": 5.1873025500153995e-06, "epoch": 555.2654867256637, "percentage": 79.12, "elapsed_time": "3:47:48", "remaining_time": "1:00:06", "throughput": 1315.41, "total_tokens": 17979336} {"current_steps": 31655, "total_steps": 40000, "loss": 0.0, "lr": 5.181316775109071e-06, "epoch": 555.3539823008849, "percentage": 79.14, "elapsed_time": "3:47:50", "remaining_time": "1:00:03", "throughput": 1315.41, "total_tokens": 17982168} {"current_steps": 31660, "total_steps": 40000, "loss": 0.0, "lr": 5.1753340564927564e-06, "epoch": 555.4424778761062, "percentage": 79.15, "elapsed_time": "3:47:52", "remaining_time": "1:00:01", "throughput": 1315.43, "total_tokens": 17985144} {"current_steps": 31665, "total_steps": 40000, "loss": 0.0, "lr": 5.169354395089068e-06, "epoch": 555.5309734513274, "percentage": 79.16, "elapsed_time": "3:47:54", "remaining_time": "0:59:59", "throughput": 1315.44, "total_tokens": 17988200} {"current_steps": 31670, "total_steps": 40000, "loss": 0.0, "lr": 5.1633777918201346e-06, "epoch": 555.6194690265487, "percentage": 79.17, "elapsed_time": "3:47:56", "remaining_time": "0:59:57", "throughput": 1315.43, "total_tokens": 17990808} {"current_steps": 31675, "total_steps": 40000, "loss": 0.0, "lr": 5.157404247607625e-06, "epoch": 555.70796460177, "percentage": 79.19, "elapsed_time": "3:47:58", "remaining_time": "0:59:55", "throughput": 1315.41, "total_tokens": 17993320} {"current_steps": 31680, "total_steps": 40000, "loss": 0.0, "lr": 5.1514337633727454e-06, "epoch": 555.7964601769911, "percentage": 79.2, "elapsed_time": "3:48:00", "remaining_time": "0:59:52", "throughput": 1315.4, "total_tokens": 17995992} {"current_steps": 31685, "total_steps": 40000, "loss": 0.0, "lr": 5.145466340036206e-06, "epoch": 555.8849557522124, "percentage": 79.21, "elapsed_time": "3:48:03", "remaining_time": "0:59:50", "throughput": 1315.41, "total_tokens": 17998856} {"current_steps": 31690, "total_steps": 40000, "loss": 0.0, "lr": 5.139501978518274e-06, "epoch": 555.9734513274336, "percentage": 79.22, "elapsed_time": "3:48:05", "remaining_time": "0:59:48", "throughput": 1315.43, "total_tokens": 18001784} {"current_steps": 31695, "total_steps": 40000, "loss": 0.0, "lr": 5.133540679738716e-06, "epoch": 556.0530973451328, "percentage": 79.24, "elapsed_time": "3:48:07", "remaining_time": "0:59:46", "throughput": 1315.35, "total_tokens": 18003784} {"current_steps": 31700, "total_steps": 40000, "loss": 0.0, "lr": 5.127582444616838e-06, "epoch": 556.141592920354, "percentage": 79.25, "elapsed_time": "3:48:09", "remaining_time": "0:59:44", "throughput": 1315.38, "total_tokens": 18007000} {"current_steps": 31705, "total_steps": 40000, "loss": 0.0, "lr": 5.121627274071486e-06, "epoch": 556.2300884955753, "percentage": 79.26, "elapsed_time": "3:48:11", "remaining_time": "0:59:42", "throughput": 1315.37, "total_tokens": 18009592} {"current_steps": 31710, "total_steps": 40000, "loss": 0.0, "lr": 5.115675169021009e-06, "epoch": 556.3185840707964, "percentage": 79.27, "elapsed_time": "3:48:13", "remaining_time": "0:59:39", "throughput": 1315.4, "total_tokens": 18012728} {"current_steps": 31715, "total_steps": 40000, "loss": 0.0, "lr": 5.1097261303832994e-06, "epoch": 556.4070796460177, "percentage": 79.29, "elapsed_time": "3:48:15", "remaining_time": "0:59:37", "throughput": 1315.37, "total_tokens": 18015144} {"current_steps": 31720, "total_steps": 40000, "loss": 0.0, "lr": 5.103780159075788e-06, "epoch": 556.4955752212389, "percentage": 79.3, "elapsed_time": "3:48:18", "remaining_time": "0:59:35", "throughput": 1315.39, "total_tokens": 18018264} {"current_steps": 31725, "total_steps": 40000, "loss": 0.0, "lr": 5.0978372560154e-06, "epoch": 556.5840707964602, "percentage": 79.31, "elapsed_time": "3:48:20", "remaining_time": "0:59:33", "throughput": 1315.38, "total_tokens": 18020776} {"current_steps": 31730, "total_steps": 40000, "loss": 0.0, "lr": 5.091897422118619e-06, "epoch": 556.6725663716815, "percentage": 79.33, "elapsed_time": "3:48:22", "remaining_time": "0:59:31", "throughput": 1315.42, "total_tokens": 18024152} {"current_steps": 31735, "total_steps": 40000, "loss": 0.0, "lr": 5.0859606583014305e-06, "epoch": 556.7610619469026, "percentage": 79.34, "elapsed_time": "3:48:24", "remaining_time": "0:59:29", "throughput": 1315.42, "total_tokens": 18026984} {"current_steps": 31740, "total_steps": 40000, "loss": 0.0, "lr": 5.080026965479365e-06, "epoch": 556.8495575221239, "percentage": 79.35, "elapsed_time": "3:48:26", "remaining_time": "0:59:26", "throughput": 1315.44, "total_tokens": 18029896} {"current_steps": 31745, "total_steps": 40000, "loss": 0.0, "lr": 5.074096344567475e-06, "epoch": 556.9380530973451, "percentage": 79.36, "elapsed_time": "3:48:28", "remaining_time": "0:59:24", "throughput": 1315.46, "total_tokens": 18033000} {"current_steps": 31750, "total_steps": 40000, "loss": 0.0, "lr": 5.0681687964803294e-06, "epoch": 557.0176991150443, "percentage": 79.38, "elapsed_time": "3:48:30", "remaining_time": "0:59:22", "throughput": 1315.4, "total_tokens": 18035296} {"current_steps": 31755, "total_steps": 40000, "loss": 0.0, "lr": 5.06224432213204e-06, "epoch": 557.1061946902655, "percentage": 79.39, "elapsed_time": "3:48:32", "remaining_time": "0:59:20", "throughput": 1315.43, "total_tokens": 18038320} {"current_steps": 31760, "total_steps": 40000, "loss": 0.0, "lr": 5.056322922436224e-06, "epoch": 557.1946902654868, "percentage": 79.4, "elapsed_time": "3:48:35", "remaining_time": "0:59:18", "throughput": 1315.42, "total_tokens": 18041040} {"current_steps": 31765, "total_steps": 40000, "loss": 0.0, "lr": 5.0504045983060465e-06, "epoch": 557.2831858407079, "percentage": 79.41, "elapsed_time": "3:48:37", "remaining_time": "0:59:16", "throughput": 1315.44, "total_tokens": 18044080} {"current_steps": 31770, "total_steps": 40000, "loss": 0.0, "lr": 5.044489350654183e-06, "epoch": 557.3716814159292, "percentage": 79.42, "elapsed_time": "3:48:39", "remaining_time": "0:59:13", "throughput": 1315.43, "total_tokens": 18046656} {"current_steps": 31775, "total_steps": 40000, "loss": 0.0, "lr": 5.038577180392831e-06, "epoch": 557.4601769911504, "percentage": 79.44, "elapsed_time": "3:48:41", "remaining_time": "0:59:11", "throughput": 1315.46, "total_tokens": 18049968} {"current_steps": 31780, "total_steps": 40000, "loss": 0.0, "lr": 5.032668088433729e-06, "epoch": 557.5486725663717, "percentage": 79.45, "elapsed_time": "3:48:43", "remaining_time": "0:59:09", "throughput": 1315.46, "total_tokens": 18052640} {"current_steps": 31785, "total_steps": 40000, "loss": 0.0, "lr": 5.02676207568814e-06, "epoch": 557.637168141593, "percentage": 79.46, "elapsed_time": "3:48:45", "remaining_time": "0:59:07", "throughput": 1315.48, "total_tokens": 18055680} {"current_steps": 31790, "total_steps": 40000, "loss": 0.0, "lr": 5.02085914306683e-06, "epoch": 557.7256637168142, "percentage": 79.47, "elapsed_time": "3:48:47", "remaining_time": "0:59:05", "throughput": 1315.51, "total_tokens": 18058944} {"current_steps": 31795, "total_steps": 40000, "loss": 0.0, "lr": 5.014959291480123e-06, "epoch": 557.8141592920354, "percentage": 79.49, "elapsed_time": "3:48:49", "remaining_time": "0:59:03", "throughput": 1315.54, "total_tokens": 18062080} {"current_steps": 31800, "total_steps": 40000, "loss": 0.0, "lr": 5.009062521837835e-06, "epoch": 557.9026548672566, "percentage": 79.5, "elapsed_time": "3:48:51", "remaining_time": "0:59:00", "throughput": 1315.52, "total_tokens": 18064576} {"current_steps": 31800, "total_steps": 40000, "eval_loss": 0.9036370515823364, "epoch": 557.9026548672566, "percentage": 79.5, "elapsed_time": "3:48:52", "remaining_time": "0:59:01", "throughput": 1315.42, "total_tokens": 18064576} {"current_steps": 31805, "total_steps": 40000, "loss": 0.0, "lr": 5.003168835049324e-06, "epoch": 557.9911504424779, "percentage": 79.51, "elapsed_time": "3:48:56", "remaining_time": "0:58:59", "throughput": 1315.24, "total_tokens": 18067184} {"current_steps": 31810, "total_steps": 40000, "loss": 0.0, "lr": 4.997278232023483e-06, "epoch": 558.070796460177, "percentage": 79.53, "elapsed_time": "3:48:59", "remaining_time": "0:58:57", "throughput": 1315.19, "total_tokens": 18069656} {"current_steps": 31815, "total_steps": 40000, "loss": 0.0, "lr": 4.9913907136687036e-06, "epoch": 558.1592920353983, "percentage": 79.54, "elapsed_time": "3:49:01", "remaining_time": "0:58:55", "throughput": 1315.19, "total_tokens": 18072440} {"current_steps": 31820, "total_steps": 40000, "loss": 0.0, "lr": 4.985506280892918e-06, "epoch": 558.2477876106195, "percentage": 79.55, "elapsed_time": "3:49:03", "remaining_time": "0:58:53", "throughput": 1315.24, "total_tokens": 18075960} {"current_steps": 31825, "total_steps": 40000, "loss": 0.0, "lr": 4.979624934603589e-06, "epoch": 558.3362831858407, "percentage": 79.56, "elapsed_time": "3:49:05", "remaining_time": "0:58:50", "throughput": 1315.28, "total_tokens": 18079208} {"current_steps": 31830, "total_steps": 40000, "loss": 0.0, "lr": 4.97374667570768e-06, "epoch": 558.4247787610619, "percentage": 79.57, "elapsed_time": "3:49:07", "remaining_time": "0:58:48", "throughput": 1315.28, "total_tokens": 18082024} {"current_steps": 31835, "total_steps": 40000, "loss": 0.0, "lr": 4.967871505111704e-06, "epoch": 558.5132743362832, "percentage": 79.59, "elapsed_time": "3:49:09", "remaining_time": "0:58:46", "throughput": 1315.26, "total_tokens": 18084456} {"current_steps": 31840, "total_steps": 40000, "loss": 0.0, "lr": 4.961999423721686e-06, "epoch": 558.6017699115044, "percentage": 79.6, "elapsed_time": "3:49:11", "remaining_time": "0:58:44", "throughput": 1315.27, "total_tokens": 18087352} {"current_steps": 31845, "total_steps": 40000, "loss": 0.0, "lr": 4.956130432443159e-06, "epoch": 558.6902654867257, "percentage": 79.61, "elapsed_time": "3:49:13", "remaining_time": "0:58:42", "throughput": 1315.26, "total_tokens": 18090072} {"current_steps": 31850, "total_steps": 40000, "loss": 0.0, "lr": 4.950264532181215e-06, "epoch": 558.7787610619469, "percentage": 79.62, "elapsed_time": "3:49:16", "remaining_time": "0:58:40", "throughput": 1315.28, "total_tokens": 18093160} {"current_steps": 31855, "total_steps": 40000, "loss": 0.0, "lr": 4.944401723840433e-06, "epoch": 558.8672566371681, "percentage": 79.64, "elapsed_time": "3:49:18", "remaining_time": "0:58:37", "throughput": 1315.29, "total_tokens": 18095976} {"current_steps": 31860, "total_steps": 40000, "loss": 0.0, "lr": 4.938542008324942e-06, "epoch": 558.9557522123894, "percentage": 79.65, "elapsed_time": "3:49:20", "remaining_time": "0:58:35", "throughput": 1315.3, "total_tokens": 18098824} {"current_steps": 31865, "total_steps": 40000, "loss": 0.0, "lr": 4.9326853865383855e-06, "epoch": 559.0353982300885, "percentage": 79.66, "elapsed_time": "3:49:22", "remaining_time": "0:58:33", "throughput": 1315.25, "total_tokens": 18101160} {"current_steps": 31870, "total_steps": 40000, "loss": 0.0, "lr": 4.926831859383918e-06, "epoch": 559.1238938053098, "percentage": 79.67, "elapsed_time": "3:49:24", "remaining_time": "0:58:31", "throughput": 1315.22, "total_tokens": 18103528} {"current_steps": 31875, "total_steps": 40000, "loss": 0.0, "lr": 4.92098142776424e-06, "epoch": 559.212389380531, "percentage": 79.69, "elapsed_time": "3:49:26", "remaining_time": "0:58:29", "throughput": 1315.21, "total_tokens": 18106248} {"current_steps": 31880, "total_steps": 40000, "loss": 0.0, "lr": 4.91513409258155e-06, "epoch": 559.3008849557522, "percentage": 79.7, "elapsed_time": "3:49:28", "remaining_time": "0:58:27", "throughput": 1315.21, "total_tokens": 18109000} {"current_steps": 31885, "total_steps": 40000, "loss": 0.0, "lr": 4.909289854737581e-06, "epoch": 559.3893805309734, "percentage": 79.71, "elapsed_time": "3:49:31", "remaining_time": "0:58:24", "throughput": 1315.23, "total_tokens": 18112120} {"current_steps": 31890, "total_steps": 40000, "loss": 0.0, "lr": 4.903448715133602e-06, "epoch": 559.4778761061947, "percentage": 79.72, "elapsed_time": "3:49:33", "remaining_time": "0:58:22", "throughput": 1315.28, "total_tokens": 18115448} {"current_steps": 31895, "total_steps": 40000, "loss": 0.0, "lr": 4.897610674670372e-06, "epoch": 559.566371681416, "percentage": 79.74, "elapsed_time": "3:49:35", "remaining_time": "0:58:20", "throughput": 1315.29, "total_tokens": 18118536} {"current_steps": 31900, "total_steps": 40000, "loss": 0.0, "lr": 4.8917757342482e-06, "epoch": 559.6548672566372, "percentage": 79.75, "elapsed_time": "3:49:37", "remaining_time": "0:58:18", "throughput": 1315.31, "total_tokens": 18121528} {"current_steps": 31905, "total_steps": 40000, "loss": 0.0, "lr": 4.885943894766909e-06, "epoch": 559.7433628318585, "percentage": 79.76, "elapsed_time": "3:49:39", "remaining_time": "0:58:16", "throughput": 1315.33, "total_tokens": 18124504} {"current_steps": 31910, "total_steps": 40000, "loss": 0.0, "lr": 4.880115157125842e-06, "epoch": 559.8318584070796, "percentage": 79.77, "elapsed_time": "3:49:41", "remaining_time": "0:58:13", "throughput": 1315.34, "total_tokens": 18127512} {"current_steps": 31915, "total_steps": 40000, "loss": 0.0, "lr": 4.874289522223857e-06, "epoch": 559.9203539823009, "percentage": 79.79, "elapsed_time": "3:49:43", "remaining_time": "0:58:11", "throughput": 1315.33, "total_tokens": 18130072} {"current_steps": 31920, "total_steps": 40000, "loss": 0.0, "lr": 4.868466990959339e-06, "epoch": 560.0, "percentage": 79.8, "elapsed_time": "3:49:45", "remaining_time": "0:58:09", "throughput": 1315.3, "total_tokens": 18132392} {"current_steps": 31925, "total_steps": 40000, "loss": 0.0, "lr": 4.8626475642301964e-06, "epoch": 560.0884955752213, "percentage": 79.81, "elapsed_time": "3:49:48", "remaining_time": "0:58:07", "throughput": 1315.26, "total_tokens": 18134904} {"current_steps": 31930, "total_steps": 40000, "loss": 0.0, "lr": 4.856831242933871e-06, "epoch": 560.1769911504425, "percentage": 79.83, "elapsed_time": "3:49:50", "remaining_time": "0:58:05", "throughput": 1315.32, "total_tokens": 18138536} {"current_steps": 31935, "total_steps": 40000, "loss": 0.0, "lr": 4.851018027967294e-06, "epoch": 560.2654867256637, "percentage": 79.84, "elapsed_time": "3:49:52", "remaining_time": "0:58:03", "throughput": 1315.3, "total_tokens": 18141096} {"current_steps": 31940, "total_steps": 40000, "loss": 0.0, "lr": 4.845207920226946e-06, "epoch": 560.3539823008849, "percentage": 79.85, "elapsed_time": "3:49:54", "remaining_time": "0:58:01", "throughput": 1315.3, "total_tokens": 18143880} {"current_steps": 31945, "total_steps": 40000, "loss": 0.0, "lr": 4.839400920608825e-06, "epoch": 560.4424778761062, "percentage": 79.86, "elapsed_time": "3:49:56", "remaining_time": "0:57:58", "throughput": 1315.33, "total_tokens": 18147144} {"current_steps": 31950, "total_steps": 40000, "loss": 0.0, "lr": 4.83359703000843e-06, "epoch": 560.5309734513274, "percentage": 79.88, "elapsed_time": "3:49:58", "remaining_time": "0:57:56", "throughput": 1315.34, "total_tokens": 18149880} {"current_steps": 31955, "total_steps": 40000, "loss": 0.0, "lr": 4.827796249320804e-06, "epoch": 560.6194690265487, "percentage": 79.89, "elapsed_time": "3:50:00", "remaining_time": "0:57:54", "throughput": 1315.37, "total_tokens": 18153160} {"current_steps": 31960, "total_steps": 40000, "loss": 0.0, "lr": 4.82199857944049e-06, "epoch": 560.70796460177, "percentage": 79.9, "elapsed_time": "3:50:02", "remaining_time": "0:57:52", "throughput": 1315.36, "total_tokens": 18155784} {"current_steps": 31965, "total_steps": 40000, "loss": 0.0, "lr": 4.8162040212615695e-06, "epoch": 560.7964601769911, "percentage": 79.91, "elapsed_time": "3:50:04", "remaining_time": "0:57:50", "throughput": 1315.35, "total_tokens": 18158344} {"current_steps": 31970, "total_steps": 40000, "loss": 0.0, "lr": 4.810412575677639e-06, "epoch": 560.8849557522124, "percentage": 79.92, "elapsed_time": "3:50:07", "remaining_time": "0:57:47", "throughput": 1315.34, "total_tokens": 18161032} {"current_steps": 31975, "total_steps": 40000, "loss": 0.0, "lr": 4.804624243581801e-06, "epoch": 560.9734513274336, "percentage": 79.94, "elapsed_time": "3:50:09", "remaining_time": "0:57:45", "throughput": 1315.36, "total_tokens": 18163976} {"current_steps": 31980, "total_steps": 40000, "loss": 0.0, "lr": 4.798839025866703e-06, "epoch": 561.0530973451328, "percentage": 79.95, "elapsed_time": "3:50:11", "remaining_time": "0:57:43", "throughput": 1315.29, "total_tokens": 18166088} {"current_steps": 31985, "total_steps": 40000, "loss": 0.0, "lr": 4.793056923424491e-06, "epoch": 561.141592920354, "percentage": 79.96, "elapsed_time": "3:50:13", "remaining_time": "0:57:41", "throughput": 1315.28, "total_tokens": 18168776} {"current_steps": 31990, "total_steps": 40000, "loss": 0.0, "lr": 4.78727793714683e-06, "epoch": 561.2300884955753, "percentage": 79.97, "elapsed_time": "3:50:15", "remaining_time": "0:57:39", "throughput": 1315.27, "total_tokens": 18171368} {"current_steps": 31995, "total_steps": 40000, "loss": 0.0, "lr": 4.7815020679249285e-06, "epoch": 561.3185840707964, "percentage": 79.99, "elapsed_time": "3:50:17", "remaining_time": "0:57:37", "throughput": 1315.28, "total_tokens": 18174280} {"current_steps": 32000, "total_steps": 40000, "loss": 0.0, "lr": 4.775729316649483e-06, "epoch": 561.4070796460177, "percentage": 80.0, "elapsed_time": "3:50:19", "remaining_time": "0:57:34", "throughput": 1315.28, "total_tokens": 18177096} {"current_steps": 32000, "total_steps": 40000, "eval_loss": 0.9058958888053894, "epoch": 561.4070796460177, "percentage": 80.0, "elapsed_time": "3:50:21", "remaining_time": "0:57:35", "throughput": 1315.18, "total_tokens": 18177096} {"current_steps": 32005, "total_steps": 40000, "loss": 0.0, "lr": 4.769959684210728e-06, "epoch": 561.4955752212389, "percentage": 80.01, "elapsed_time": "3:50:24", "remaining_time": "0:57:33", "throughput": 1315.02, "total_tokens": 18180024} {"current_steps": 32010, "total_steps": 40000, "loss": 0.0, "lr": 4.764193171498426e-06, "epoch": 561.5840707964602, "percentage": 80.03, "elapsed_time": "3:50:27", "remaining_time": "0:57:31", "throughput": 1315.01, "total_tokens": 18182696} {"current_steps": 32015, "total_steps": 40000, "loss": 0.0, "lr": 4.75842977940183e-06, "epoch": 561.6725663716815, "percentage": 80.04, "elapsed_time": "3:50:29", "remaining_time": "0:57:29", "throughput": 1315.03, "total_tokens": 18185784} {"current_steps": 32020, "total_steps": 40000, "loss": 0.0, "lr": 4.752669508809729e-06, "epoch": 561.7610619469026, "percentage": 80.05, "elapsed_time": "3:50:31", "remaining_time": "0:57:27", "throughput": 1315.01, "total_tokens": 18188264} {"current_steps": 32025, "total_steps": 40000, "loss": 0.0, "lr": 4.746912360610445e-06, "epoch": 561.8495575221239, "percentage": 80.06, "elapsed_time": "3:50:33", "remaining_time": "0:57:24", "throughput": 1315.05, "total_tokens": 18191592} {"current_steps": 32030, "total_steps": 40000, "loss": 0.0, "lr": 4.741158335691781e-06, "epoch": 561.9380530973451, "percentage": 80.08, "elapsed_time": "3:50:35", "remaining_time": "0:57:22", "throughput": 1315.07, "total_tokens": 18194616} {"current_steps": 32035, "total_steps": 40000, "loss": 0.0, "lr": 4.7354074349410994e-06, "epoch": 562.0176991150443, "percentage": 80.09, "elapsed_time": "3:50:37", "remaining_time": "0:57:20", "throughput": 1315.06, "total_tokens": 18197592} {"current_steps": 32040, "total_steps": 40000, "loss": 0.0, "lr": 4.729659659245245e-06, "epoch": 562.1061946902655, "percentage": 80.1, "elapsed_time": "3:50:39", "remaining_time": "0:57:18", "throughput": 1315.05, "total_tokens": 18200152} {"current_steps": 32045, "total_steps": 40000, "loss": 0.0, "lr": 4.723915009490601e-06, "epoch": 562.1946902654868, "percentage": 80.11, "elapsed_time": "3:50:41", "remaining_time": "0:57:16", "throughput": 1315.05, "total_tokens": 18202856} {"current_steps": 32050, "total_steps": 40000, "loss": 0.0, "lr": 4.718173486563077e-06, "epoch": 562.2831858407079, "percentage": 80.12, "elapsed_time": "3:50:44", "remaining_time": "0:57:14", "throughput": 1315.1, "total_tokens": 18206424} {"current_steps": 32055, "total_steps": 40000, "loss": 0.0, "lr": 4.71243509134808e-06, "epoch": 562.3716814159292, "percentage": 80.14, "elapsed_time": "3:50:46", "remaining_time": "0:57:11", "throughput": 1315.08, "total_tokens": 18208904} {"current_steps": 32060, "total_steps": 40000, "loss": 0.0, "lr": 4.706699824730532e-06, "epoch": 562.4601769911504, "percentage": 80.15, "elapsed_time": "3:50:48", "remaining_time": "0:57:09", "throughput": 1315.07, "total_tokens": 18211496} {"current_steps": 32065, "total_steps": 40000, "loss": 0.0, "lr": 4.700967687594901e-06, "epoch": 562.5486725663717, "percentage": 80.16, "elapsed_time": "3:50:50", "remaining_time": "0:57:07", "throughput": 1315.06, "total_tokens": 18214104} {"current_steps": 32070, "total_steps": 40000, "loss": 0.0, "lr": 4.69523868082514e-06, "epoch": 562.637168141593, "percentage": 80.17, "elapsed_time": "3:50:52", "remaining_time": "0:57:05", "throughput": 1315.07, "total_tokens": 18217016} {"current_steps": 32075, "total_steps": 40000, "loss": 0.0, "lr": 4.689512805304747e-06, "epoch": 562.7256637168142, "percentage": 80.19, "elapsed_time": "3:50:54", "remaining_time": "0:57:03", "throughput": 1315.06, "total_tokens": 18219688} {"current_steps": 32080, "total_steps": 40000, "loss": 0.0, "lr": 4.683790061916707e-06, "epoch": 562.8141592920354, "percentage": 80.2, "elapsed_time": "3:50:56", "remaining_time": "0:57:00", "throughput": 1315.08, "total_tokens": 18222680} {"current_steps": 32085, "total_steps": 40000, "loss": 0.0, "lr": 4.678070451543551e-06, "epoch": 562.9026548672566, "percentage": 80.21, "elapsed_time": "3:50:58", "remaining_time": "0:56:58", "throughput": 1315.12, "total_tokens": 18226072} {"current_steps": 32090, "total_steps": 40000, "loss": 0.0, "lr": 4.6723539750673204e-06, "epoch": 562.9911504424779, "percentage": 80.23, "elapsed_time": "3:51:00", "remaining_time": "0:56:56", "throughput": 1315.12, "total_tokens": 18228840} {"current_steps": 32095, "total_steps": 40000, "loss": 0.0, "lr": 4.666640633369551e-06, "epoch": 563.070796460177, "percentage": 80.24, "elapsed_time": "3:51:03", "remaining_time": "0:56:54", "throughput": 1315.08, "total_tokens": 18231328} {"current_steps": 32100, "total_steps": 40000, "loss": 0.0, "lr": 4.660930427331323e-06, "epoch": 563.1592920353983, "percentage": 80.25, "elapsed_time": "3:51:05", "remaining_time": "0:56:52", "throughput": 1315.08, "total_tokens": 18234000} {"current_steps": 32105, "total_steps": 40000, "loss": 0.0, "lr": 4.6552233578332244e-06, "epoch": 563.2477876106195, "percentage": 80.26, "elapsed_time": "3:51:07", "remaining_time": "0:56:50", "throughput": 1315.04, "total_tokens": 18236352} {"current_steps": 32110, "total_steps": 40000, "loss": 0.0, "lr": 4.649519425755347e-06, "epoch": 563.3362831858407, "percentage": 80.27, "elapsed_time": "3:51:09", "remaining_time": "0:56:48", "throughput": 1315.05, "total_tokens": 18239312} {"current_steps": 32115, "total_steps": 40000, "loss": 0.0, "lr": 4.64381863197732e-06, "epoch": 563.4247787610619, "percentage": 80.29, "elapsed_time": "3:51:11", "remaining_time": "0:56:45", "throughput": 1315.07, "total_tokens": 18242208} {"current_steps": 32120, "total_steps": 40000, "loss": 0.0, "lr": 4.638120977378269e-06, "epoch": 563.5132743362832, "percentage": 80.3, "elapsed_time": "3:51:13", "remaining_time": "0:56:43", "throughput": 1315.04, "total_tokens": 18244624} {"current_steps": 32125, "total_steps": 40000, "loss": 0.0, "lr": 4.632426462836848e-06, "epoch": 563.6017699115044, "percentage": 80.31, "elapsed_time": "3:51:15", "remaining_time": "0:56:41", "throughput": 1315.06, "total_tokens": 18247712} {"current_steps": 32130, "total_steps": 40000, "loss": 0.0, "lr": 4.626735089231224e-06, "epoch": 563.6902654867257, "percentage": 80.33, "elapsed_time": "3:51:18", "remaining_time": "0:56:39", "throughput": 1315.11, "total_tokens": 18251168} {"current_steps": 32135, "total_steps": 40000, "loss": 0.0, "lr": 4.621046857439068e-06, "epoch": 563.7787610619469, "percentage": 80.34, "elapsed_time": "3:51:20", "remaining_time": "0:56:37", "throughput": 1315.12, "total_tokens": 18254016} {"current_steps": 32140, "total_steps": 40000, "loss": 0.0, "lr": 4.615361768337587e-06, "epoch": 563.8672566371681, "percentage": 80.35, "elapsed_time": "3:51:22", "remaining_time": "0:56:34", "throughput": 1315.16, "total_tokens": 18257392} {"current_steps": 32145, "total_steps": 40000, "loss": 0.0, "lr": 4.6096798228034946e-06, "epoch": 563.9557522123894, "percentage": 80.36, "elapsed_time": "3:51:24", "remaining_time": "0:56:32", "throughput": 1315.19, "total_tokens": 18260528} {"current_steps": 32150, "total_steps": 40000, "loss": 0.0, "lr": 4.604001021713008e-06, "epoch": 564.0353982300885, "percentage": 80.38, "elapsed_time": "3:51:26", "remaining_time": "0:56:30", "throughput": 1315.15, "total_tokens": 18263056} {"current_steps": 32155, "total_steps": 40000, "loss": 0.0, "lr": 4.598325365941883e-06, "epoch": 564.1238938053098, "percentage": 80.39, "elapsed_time": "3:51:28", "remaining_time": "0:56:28", "throughput": 1315.15, "total_tokens": 18265872} {"current_steps": 32160, "total_steps": 40000, "loss": 0.0, "lr": 4.5926528563653645e-06, "epoch": 564.212389380531, "percentage": 80.4, "elapsed_time": "3:51:30", "remaining_time": "0:56:26", "throughput": 1315.15, "total_tokens": 18268544} {"current_steps": 32165, "total_steps": 40000, "loss": 0.0, "lr": 4.5869834938582295e-06, "epoch": 564.3008849557522, "percentage": 80.41, "elapsed_time": "3:51:33", "remaining_time": "0:56:24", "throughput": 1315.16, "total_tokens": 18271472} {"current_steps": 32170, "total_steps": 40000, "loss": 0.0, "lr": 4.581317279294772e-06, "epoch": 564.3893805309734, "percentage": 80.42, "elapsed_time": "3:51:35", "remaining_time": "0:56:22", "throughput": 1315.17, "total_tokens": 18274480} {"current_steps": 32175, "total_steps": 40000, "loss": 0.0, "lr": 4.57565421354878e-06, "epoch": 564.4778761061947, "percentage": 80.44, "elapsed_time": "3:51:37", "remaining_time": "0:56:19", "throughput": 1315.17, "total_tokens": 18277248} {"current_steps": 32180, "total_steps": 40000, "loss": 0.0, "lr": 4.569994297493579e-06, "epoch": 564.566371681416, "percentage": 80.45, "elapsed_time": "3:51:39", "remaining_time": "0:56:17", "throughput": 1315.16, "total_tokens": 18279808} {"current_steps": 32185, "total_steps": 40000, "loss": 0.0, "lr": 4.564337532002002e-06, "epoch": 564.6548672566372, "percentage": 80.46, "elapsed_time": "3:51:41", "remaining_time": "0:56:15", "throughput": 1315.15, "total_tokens": 18282448} {"current_steps": 32190, "total_steps": 40000, "loss": 0.0, "lr": 4.55868391794638e-06, "epoch": 564.7433628318585, "percentage": 80.47, "elapsed_time": "3:51:43", "remaining_time": "0:56:13", "throughput": 1315.16, "total_tokens": 18285472} {"current_steps": 32195, "total_steps": 40000, "loss": 0.0, "lr": 4.553033456198588e-06, "epoch": 564.8318584070796, "percentage": 80.49, "elapsed_time": "3:51:45", "remaining_time": "0:56:11", "throughput": 1315.12, "total_tokens": 18287728} {"current_steps": 32200, "total_steps": 40000, "loss": 0.0, "lr": 4.54738614762999e-06, "epoch": 564.9203539823009, "percentage": 80.5, "elapsed_time": "3:51:47", "remaining_time": "0:56:08", "throughput": 1315.13, "total_tokens": 18290608} {"current_steps": 32200, "total_steps": 40000, "eval_loss": 0.925896406173706, "epoch": 564.9203539823009, "percentage": 80.5, "elapsed_time": "3:51:48", "remaining_time": "0:56:09", "throughput": 1315.03, "total_tokens": 18290608} {"current_steps": 32205, "total_steps": 40000, "loss": 0.0, "lr": 4.541741993111465e-06, "epoch": 565.0, "percentage": 80.51, "elapsed_time": "3:51:52", "remaining_time": "0:56:07", "throughput": 1314.9, "total_tokens": 18293712} {"current_steps": 32210, "total_steps": 40000, "loss": 0.0, "lr": 4.536100993513423e-06, "epoch": 565.0884955752213, "percentage": 80.53, "elapsed_time": "3:51:55", "remaining_time": "0:56:05", "throughput": 1314.89, "total_tokens": 18296784} {"current_steps": 32215, "total_steps": 40000, "loss": 0.0, "lr": 4.530463149705768e-06, "epoch": 565.1769911504425, "percentage": 80.54, "elapsed_time": "3:51:57", "remaining_time": "0:56:03", "throughput": 1314.86, "total_tokens": 18299248} {"current_steps": 32220, "total_steps": 40000, "loss": 0.0, "lr": 4.524828462557934e-06, "epoch": 565.2654867256637, "percentage": 80.55, "elapsed_time": "3:51:59", "remaining_time": "0:56:01", "throughput": 1314.86, "total_tokens": 18302000} {"current_steps": 32225, "total_steps": 40000, "loss": 0.0, "lr": 4.5191969329388625e-06, "epoch": 565.3539823008849, "percentage": 80.56, "elapsed_time": "3:52:01", "remaining_time": "0:55:58", "throughput": 1314.86, "total_tokens": 18304720} {"current_steps": 32230, "total_steps": 40000, "loss": 0.0, "lr": 4.5135685617169965e-06, "epoch": 565.4424778761062, "percentage": 80.58, "elapsed_time": "3:52:03", "remaining_time": "0:55:56", "throughput": 1314.86, "total_tokens": 18307456} {"current_steps": 32235, "total_steps": 40000, "loss": 0.0, "lr": 4.507943349760313e-06, "epoch": 565.5309734513274, "percentage": 80.59, "elapsed_time": "3:52:05", "remaining_time": "0:55:54", "throughput": 1314.88, "total_tokens": 18310592} {"current_steps": 32240, "total_steps": 40000, "loss": 0.0, "lr": 4.502321297936277e-06, "epoch": 565.6194690265487, "percentage": 80.6, "elapsed_time": "3:52:07", "remaining_time": "0:55:52", "throughput": 1314.9, "total_tokens": 18313648} {"current_steps": 32245, "total_steps": 40000, "loss": 0.0, "lr": 4.496702407111888e-06, "epoch": 565.70796460177, "percentage": 80.61, "elapsed_time": "3:52:09", "remaining_time": "0:55:50", "throughput": 1314.92, "total_tokens": 18316544} {"current_steps": 32250, "total_steps": 40000, "loss": 0.0, "lr": 4.491086678153653e-06, "epoch": 565.7964601769911, "percentage": 80.62, "elapsed_time": "3:52:11", "remaining_time": "0:55:47", "throughput": 1314.91, "total_tokens": 18319248} {"current_steps": 32255, "total_steps": 40000, "loss": 0.0, "lr": 4.485474111927579e-06, "epoch": 565.8849557522124, "percentage": 80.64, "elapsed_time": "3:52:14", "remaining_time": "0:55:45", "throughput": 1314.92, "total_tokens": 18322176} {"current_steps": 32260, "total_steps": 40000, "loss": 0.0, "lr": 4.479864709299197e-06, "epoch": 565.9734513274336, "percentage": 80.65, "elapsed_time": "3:52:16", "remaining_time": "0:55:43", "throughput": 1314.94, "total_tokens": 18325200} {"current_steps": 32265, "total_steps": 40000, "loss": 0.0, "lr": 4.474258471133555e-06, "epoch": 566.0530973451328, "percentage": 80.66, "elapsed_time": "3:52:18", "remaining_time": "0:55:41", "throughput": 1314.9, "total_tokens": 18327664} {"current_steps": 32270, "total_steps": 40000, "loss": 0.0, "lr": 4.4686553982952014e-06, "epoch": 566.141592920354, "percentage": 80.67, "elapsed_time": "3:52:20", "remaining_time": "0:55:39", "throughput": 1314.93, "total_tokens": 18330784} {"current_steps": 32275, "total_steps": 40000, "loss": 0.0, "lr": 4.463055491648191e-06, "epoch": 566.2300884955753, "percentage": 80.69, "elapsed_time": "3:52:22", "remaining_time": "0:55:37", "throughput": 1314.92, "total_tokens": 18333424} {"current_steps": 32280, "total_steps": 40000, "loss": 0.0, "lr": 4.457458752056112e-06, "epoch": 566.3185840707964, "percentage": 80.7, "elapsed_time": "3:52:24", "remaining_time": "0:55:34", "throughput": 1314.94, "total_tokens": 18336512} {"current_steps": 32285, "total_steps": 40000, "loss": 0.0, "lr": 4.451865180382042e-06, "epoch": 566.4070796460177, "percentage": 80.71, "elapsed_time": "3:52:26", "remaining_time": "0:55:32", "throughput": 1314.96, "total_tokens": 18339616} {"current_steps": 32290, "total_steps": 40000, "loss": 0.0, "lr": 4.4462747774885936e-06, "epoch": 566.4955752212389, "percentage": 80.73, "elapsed_time": "3:52:29", "remaining_time": "0:55:30", "throughput": 1314.94, "total_tokens": 18342144} {"current_steps": 32295, "total_steps": 40000, "loss": 0.0, "lr": 4.440687544237859e-06, "epoch": 566.5840707964602, "percentage": 80.74, "elapsed_time": "3:52:31", "remaining_time": "0:55:28", "throughput": 1314.95, "total_tokens": 18344944} {"current_steps": 32300, "total_steps": 40000, "loss": 0.0, "lr": 4.435103481491471e-06, "epoch": 566.6725663716815, "percentage": 80.75, "elapsed_time": "3:52:33", "remaining_time": "0:55:26", "throughput": 1314.95, "total_tokens": 18347792} {"current_steps": 32305, "total_steps": 40000, "loss": 0.0, "lr": 4.429522590110569e-06, "epoch": 566.7610619469026, "percentage": 80.76, "elapsed_time": "3:52:35", "remaining_time": "0:55:24", "throughput": 1314.96, "total_tokens": 18350816} {"current_steps": 32310, "total_steps": 40000, "loss": 0.0, "lr": 4.423944870955779e-06, "epoch": 566.8495575221239, "percentage": 80.77, "elapsed_time": "3:52:37", "remaining_time": "0:55:21", "throughput": 1314.97, "total_tokens": 18353712} {"current_steps": 32315, "total_steps": 40000, "loss": 0.0, "lr": 4.418370324887272e-06, "epoch": 566.9380530973451, "percentage": 80.79, "elapsed_time": "3:52:39", "remaining_time": "0:55:19", "throughput": 1314.99, "total_tokens": 18356640} {"current_steps": 32320, "total_steps": 40000, "loss": 0.0, "lr": 4.412798952764699e-06, "epoch": 567.0176991150443, "percentage": 80.8, "elapsed_time": "3:52:41", "remaining_time": "0:55:17", "throughput": 1314.94, "total_tokens": 18358896} {"current_steps": 32325, "total_steps": 40000, "loss": 0.0, "lr": 4.407230755447245e-06, "epoch": 567.1061946902655, "percentage": 80.81, "elapsed_time": "3:52:43", "remaining_time": "0:55:15", "throughput": 1314.94, "total_tokens": 18361824} {"current_steps": 32330, "total_steps": 40000, "loss": 0.0, "lr": 4.401665733793598e-06, "epoch": 567.1946902654868, "percentage": 80.83, "elapsed_time": "3:52:46", "remaining_time": "0:55:13", "throughput": 1314.95, "total_tokens": 18364736} {"current_steps": 32335, "total_steps": 40000, "loss": 0.0, "lr": 4.3961038886619425e-06, "epoch": 567.2831858407079, "percentage": 80.84, "elapsed_time": "3:52:48", "remaining_time": "0:55:11", "throughput": 1314.95, "total_tokens": 18367536} {"current_steps": 32340, "total_steps": 40000, "loss": 0.0, "lr": 4.39054522091e-06, "epoch": 567.3716814159292, "percentage": 80.85, "elapsed_time": "3:52:50", "remaining_time": "0:55:08", "throughput": 1314.96, "total_tokens": 18370400} {"current_steps": 32345, "total_steps": 40000, "loss": 0.0, "lr": 4.384989731394979e-06, "epoch": 567.4601769911504, "percentage": 80.86, "elapsed_time": "3:52:52", "remaining_time": "0:55:06", "throughput": 1314.96, "total_tokens": 18373152} {"current_steps": 32350, "total_steps": 40000, "loss": 0.0, "lr": 4.379437420973598e-06, "epoch": 567.5486725663717, "percentage": 80.88, "elapsed_time": "3:52:54", "remaining_time": "0:55:04", "throughput": 1314.97, "total_tokens": 18376144} {"current_steps": 32355, "total_steps": 40000, "loss": 0.0, "lr": 4.373888290502107e-06, "epoch": 567.637168141593, "percentage": 80.89, "elapsed_time": "3:52:56", "remaining_time": "0:55:02", "throughput": 1314.94, "total_tokens": 18378544} {"current_steps": 32360, "total_steps": 40000, "loss": 0.0, "lr": 4.36834234083624e-06, "epoch": 567.7256637168142, "percentage": 80.9, "elapsed_time": "3:52:58", "remaining_time": "0:55:00", "throughput": 1314.95, "total_tokens": 18381360} {"current_steps": 32365, "total_steps": 40000, "loss": 0.0, "lr": 4.362799572831258e-06, "epoch": 567.8141592920354, "percentage": 80.91, "elapsed_time": "3:53:00", "remaining_time": "0:54:58", "throughput": 1314.94, "total_tokens": 18384032} {"current_steps": 32370, "total_steps": 40000, "loss": 0.0, "lr": 4.35725998734193e-06, "epoch": 567.9026548672566, "percentage": 80.92, "elapsed_time": "3:53:02", "remaining_time": "0:54:55", "throughput": 1315.02, "total_tokens": 18387872} {"current_steps": 32375, "total_steps": 40000, "loss": 0.0, "lr": 4.3517235852225195e-06, "epoch": 567.9911504424779, "percentage": 80.94, "elapsed_time": "3:53:05", "remaining_time": "0:54:53", "throughput": 1315.03, "total_tokens": 18390832} {"current_steps": 32380, "total_steps": 40000, "loss": 0.0, "lr": 4.346190367326822e-06, "epoch": 568.070796460177, "percentage": 80.95, "elapsed_time": "3:53:07", "remaining_time": "0:54:51", "throughput": 1315.0, "total_tokens": 18393512} {"current_steps": 32385, "total_steps": 40000, "loss": 0.0, "lr": 4.340660334508115e-06, "epoch": 568.1592920353983, "percentage": 80.96, "elapsed_time": "3:53:09", "remaining_time": "0:54:49", "throughput": 1315.0, "total_tokens": 18396328} {"current_steps": 32390, "total_steps": 40000, "loss": 0.0, "lr": 4.335133487619206e-06, "epoch": 568.2477876106195, "percentage": 80.97, "elapsed_time": "3:53:11", "remaining_time": "0:54:47", "throughput": 1315.03, "total_tokens": 18399416} {"current_steps": 32395, "total_steps": 40000, "loss": 0.0, "lr": 4.329609827512409e-06, "epoch": 568.3362831858407, "percentage": 80.99, "elapsed_time": "3:53:13", "remaining_time": "0:54:45", "throughput": 1315.03, "total_tokens": 18402056} {"current_steps": 32400, "total_steps": 40000, "loss": 0.0, "lr": 4.324089355039531e-06, "epoch": 568.4247787610619, "percentage": 81.0, "elapsed_time": "3:53:15", "remaining_time": "0:54:42", "throughput": 1315.01, "total_tokens": 18404648} {"current_steps": 32400, "total_steps": 40000, "eval_loss": 0.9181575179100037, "epoch": 568.4247787610619, "percentage": 81.0, "elapsed_time": "3:53:16", "remaining_time": "0:54:43", "throughput": 1314.91, "total_tokens": 18404648} {"current_steps": 32405, "total_steps": 40000, "loss": 0.0, "lr": 4.3185720710519075e-06, "epoch": 568.5132743362832, "percentage": 81.01, "elapsed_time": "3:53:20", "remaining_time": "0:54:41", "throughput": 1314.72, "total_tokens": 18407176} {"current_steps": 32410, "total_steps": 40000, "loss": 0.0, "lr": 4.3130579764003724e-06, "epoch": 568.6017699115044, "percentage": 81.03, "elapsed_time": "3:53:22", "remaining_time": "0:54:39", "throughput": 1314.75, "total_tokens": 18410408} {"current_steps": 32415, "total_steps": 40000, "loss": 0.0, "lr": 4.307547071935267e-06, "epoch": 568.6902654867257, "percentage": 81.04, "elapsed_time": "3:53:25", "remaining_time": "0:54:37", "throughput": 1314.74, "total_tokens": 18413048} {"current_steps": 32420, "total_steps": 40000, "loss": 0.0, "lr": 4.302039358506435e-06, "epoch": 568.7787610619469, "percentage": 81.05, "elapsed_time": "3:53:27", "remaining_time": "0:54:34", "throughput": 1314.76, "total_tokens": 18416088} {"current_steps": 32425, "total_steps": 40000, "loss": 0.0, "lr": 4.296534836963245e-06, "epoch": 568.8672566371681, "percentage": 81.06, "elapsed_time": "3:53:29", "remaining_time": "0:54:32", "throughput": 1314.77, "total_tokens": 18418936} {"current_steps": 32430, "total_steps": 40000, "loss": 0.0, "lr": 4.291033508154555e-06, "epoch": 568.9557522123894, "percentage": 81.08, "elapsed_time": "3:53:31", "remaining_time": "0:54:30", "throughput": 1314.78, "total_tokens": 18421816} {"current_steps": 32435, "total_steps": 40000, "loss": 0.0, "lr": 4.285535372928748e-06, "epoch": 569.0353982300885, "percentage": 81.09, "elapsed_time": "3:53:33", "remaining_time": "0:54:28", "throughput": 1314.71, "total_tokens": 18424008} {"current_steps": 32440, "total_steps": 40000, "loss": 0.0, "lr": 4.280040432133695e-06, "epoch": 569.1238938053098, "percentage": 81.1, "elapsed_time": "3:53:35", "remaining_time": "0:54:26", "throughput": 1314.75, "total_tokens": 18427272} {"current_steps": 32445, "total_steps": 40000, "loss": 0.0, "lr": 4.274548686616789e-06, "epoch": 569.212389380531, "percentage": 81.11, "elapsed_time": "3:53:37", "remaining_time": "0:54:24", "throughput": 1314.73, "total_tokens": 18429656} {"current_steps": 32450, "total_steps": 40000, "loss": 0.0, "lr": 4.2690601372249364e-06, "epoch": 569.3008849557522, "percentage": 81.12, "elapsed_time": "3:53:39", "remaining_time": "0:54:21", "throughput": 1314.75, "total_tokens": 18432760} {"current_steps": 32455, "total_steps": 40000, "loss": 0.0, "lr": 4.263574784804525e-06, "epoch": 569.3893805309734, "percentage": 81.14, "elapsed_time": "3:53:42", "remaining_time": "0:54:19", "throughput": 1314.74, "total_tokens": 18435352} {"current_steps": 32460, "total_steps": 40000, "loss": 0.0, "lr": 4.258092630201479e-06, "epoch": 569.4778761061947, "percentage": 81.15, "elapsed_time": "3:53:44", "remaining_time": "0:54:17", "throughput": 1314.74, "total_tokens": 18438264} {"current_steps": 32465, "total_steps": 40000, "loss": 0.0, "lr": 4.252613674261202e-06, "epoch": 569.566371681416, "percentage": 81.16, "elapsed_time": "3:53:46", "remaining_time": "0:54:15", "throughput": 1314.75, "total_tokens": 18441176} {"current_steps": 32470, "total_steps": 40000, "loss": 0.0, "lr": 4.2471379178286224e-06, "epoch": 569.6548672566372, "percentage": 81.17, "elapsed_time": "3:53:48", "remaining_time": "0:54:13", "throughput": 1314.76, "total_tokens": 18444120} {"current_steps": 32475, "total_steps": 40000, "loss": 0.0, "lr": 4.241665361748181e-06, "epoch": 569.7433628318585, "percentage": 81.19, "elapsed_time": "3:53:50", "remaining_time": "0:54:11", "throughput": 1314.81, "total_tokens": 18447480} {"current_steps": 32480, "total_steps": 40000, "loss": 0.0, "lr": 4.2361960068637994e-06, "epoch": 569.8318584070796, "percentage": 81.2, "elapsed_time": "3:53:52", "remaining_time": "0:54:08", "throughput": 1314.81, "total_tokens": 18450216} {"current_steps": 32485, "total_steps": 40000, "loss": 0.0, "lr": 4.230729854018933e-06, "epoch": 569.9203539823009, "percentage": 81.21, "elapsed_time": "3:53:54", "remaining_time": "0:54:06", "throughput": 1314.79, "total_tokens": 18452776} {"current_steps": 32490, "total_steps": 40000, "loss": 0.0, "lr": 4.225266904056521e-06, "epoch": 570.0, "percentage": 81.23, "elapsed_time": "3:53:56", "remaining_time": "0:54:04", "throughput": 1314.78, "total_tokens": 18455456} {"current_steps": 32495, "total_steps": 40000, "loss": 0.0, "lr": 4.21980715781903e-06, "epoch": 570.0884955752213, "percentage": 81.24, "elapsed_time": "3:53:59", "remaining_time": "0:54:02", "throughput": 1314.77, "total_tokens": 18458320} {"current_steps": 32500, "total_steps": 40000, "loss": 0.0, "lr": 4.214350616148416e-06, "epoch": 570.1769911504425, "percentage": 81.25, "elapsed_time": "3:54:01", "remaining_time": "0:54:00", "throughput": 1314.77, "total_tokens": 18461104} {"current_steps": 32505, "total_steps": 40000, "loss": 0.0, "lr": 4.20889727988614e-06, "epoch": 570.2654867256637, "percentage": 81.26, "elapsed_time": "3:54:03", "remaining_time": "0:53:58", "throughput": 1314.79, "total_tokens": 18464144} {"current_steps": 32510, "total_steps": 40000, "loss": 0.0, "lr": 4.20344714987318e-06, "epoch": 570.3539823008849, "percentage": 81.27, "elapsed_time": "3:54:05", "remaining_time": "0:53:55", "throughput": 1314.8, "total_tokens": 18466960} {"current_steps": 32515, "total_steps": 40000, "loss": 0.0, "lr": 4.198000226950022e-06, "epoch": 570.4424778761062, "percentage": 81.29, "elapsed_time": "3:54:07", "remaining_time": "0:53:53", "throughput": 1314.78, "total_tokens": 18469600} {"current_steps": 32520, "total_steps": 40000, "loss": 0.0, "lr": 4.192556511956635e-06, "epoch": 570.5309734513274, "percentage": 81.3, "elapsed_time": "3:54:09", "remaining_time": "0:53:51", "throughput": 1314.78, "total_tokens": 18472368} {"current_steps": 32525, "total_steps": 40000, "loss": 0.0, "lr": 4.18711600573252e-06, "epoch": 570.6194690265487, "percentage": 81.31, "elapsed_time": "3:54:11", "remaining_time": "0:53:49", "throughput": 1314.76, "total_tokens": 18474832} {"current_steps": 32530, "total_steps": 40000, "loss": 0.0, "lr": 4.181678709116671e-06, "epoch": 570.70796460177, "percentage": 81.33, "elapsed_time": "3:54:13", "remaining_time": "0:53:47", "throughput": 1314.79, "total_tokens": 18478032} {"current_steps": 32535, "total_steps": 40000, "loss": 0.0, "lr": 4.1762446229475785e-06, "epoch": 570.7964601769911, "percentage": 81.34, "elapsed_time": "3:54:16", "remaining_time": "0:53:45", "throughput": 1314.81, "total_tokens": 18481072} {"current_steps": 32540, "total_steps": 40000, "loss": 0.0, "lr": 4.17081374806326e-06, "epoch": 570.8849557522124, "percentage": 81.35, "elapsed_time": "3:54:18", "remaining_time": "0:53:42", "throughput": 1314.83, "total_tokens": 18484096} {"current_steps": 32545, "total_steps": 40000, "loss": 0.0, "lr": 4.165386085301212e-06, "epoch": 570.9734513274336, "percentage": 81.36, "elapsed_time": "3:54:20", "remaining_time": "0:53:40", "throughput": 1314.86, "total_tokens": 18487328} {"current_steps": 32550, "total_steps": 40000, "loss": 0.0, "lr": 4.1599616354984525e-06, "epoch": 571.0530973451328, "percentage": 81.38, "elapsed_time": "3:54:22", "remaining_time": "0:53:38", "throughput": 1314.84, "total_tokens": 18490064} {"current_steps": 32555, "total_steps": 40000, "loss": 0.0, "lr": 4.154540399491508e-06, "epoch": 571.141592920354, "percentage": 81.39, "elapsed_time": "3:54:24", "remaining_time": "0:53:36", "throughput": 1314.82, "total_tokens": 18492528} {"current_steps": 32560, "total_steps": 40000, "loss": 0.0, "lr": 4.149122378116394e-06, "epoch": 571.2300884955753, "percentage": 81.4, "elapsed_time": "3:54:26", "remaining_time": "0:53:34", "throughput": 1314.84, "total_tokens": 18495648} {"current_steps": 32565, "total_steps": 40000, "loss": 0.0, "lr": 4.14370757220863e-06, "epoch": 571.3185840707964, "percentage": 81.41, "elapsed_time": "3:54:28", "remaining_time": "0:53:32", "throughput": 1314.84, "total_tokens": 18498288} {"current_steps": 32570, "total_steps": 40000, "loss": 0.0, "lr": 4.138295982603263e-06, "epoch": 571.4070796460177, "percentage": 81.42, "elapsed_time": "3:54:30", "remaining_time": "0:53:29", "throughput": 1314.83, "total_tokens": 18500960} {"current_steps": 32575, "total_steps": 40000, "loss": 0.0, "lr": 4.132887610134814e-06, "epoch": 571.4955752212389, "percentage": 81.44, "elapsed_time": "3:54:33", "remaining_time": "0:53:27", "throughput": 1314.82, "total_tokens": 18503616} {"current_steps": 32580, "total_steps": 40000, "loss": 0.0, "lr": 4.127482455637335e-06, "epoch": 571.5840707964602, "percentage": 81.45, "elapsed_time": "3:54:35", "remaining_time": "0:53:25", "throughput": 1314.83, "total_tokens": 18506528} {"current_steps": 32585, "total_steps": 40000, "loss": 0.0, "lr": 4.1220805199443545e-06, "epoch": 571.6725663716815, "percentage": 81.46, "elapsed_time": "3:54:37", "remaining_time": "0:53:23", "throughput": 1314.85, "total_tokens": 18509696} {"current_steps": 32590, "total_steps": 40000, "loss": 0.0, "lr": 4.116681803888925e-06, "epoch": 571.7610619469026, "percentage": 81.47, "elapsed_time": "3:54:39", "remaining_time": "0:53:21", "throughput": 1314.84, "total_tokens": 18512336} {"current_steps": 32595, "total_steps": 40000, "loss": 0.0, "lr": 4.111286308303605e-06, "epoch": 571.8495575221239, "percentage": 81.49, "elapsed_time": "3:54:41", "remaining_time": "0:53:19", "throughput": 1314.83, "total_tokens": 18514880} {"current_steps": 32600, "total_steps": 40000, "loss": 0.0, "lr": 4.105894034020433e-06, "epoch": 571.9380530973451, "percentage": 81.5, "elapsed_time": "3:54:43", "remaining_time": "0:53:16", "throughput": 1314.8, "total_tokens": 18517216} {"current_steps": 32600, "total_steps": 40000, "eval_loss": 0.9213732481002808, "epoch": 571.9380530973451, "percentage": 81.5, "elapsed_time": "3:54:44", "remaining_time": "0:53:17", "throughput": 1314.7, "total_tokens": 18517216} {"current_steps": 32605, "total_steps": 40000, "loss": 0.0, "lr": 4.100504981870975e-06, "epoch": 572.0176991150443, "percentage": 81.51, "elapsed_time": "3:54:48", "remaining_time": "0:53:15", "throughput": 1314.54, "total_tokens": 18520328} {"current_steps": 32610, "total_steps": 40000, "loss": 0.0, "lr": 4.0951191526862915e-06, "epoch": 572.1061946902655, "percentage": 81.53, "elapsed_time": "3:54:50", "remaining_time": "0:53:13", "throughput": 1314.56, "total_tokens": 18523496} {"current_steps": 32615, "total_steps": 40000, "loss": 0.0, "lr": 4.089736547296938e-06, "epoch": 572.1946902654868, "percentage": 81.54, "elapsed_time": "3:54:53", "remaining_time": "0:53:11", "throughput": 1314.56, "total_tokens": 18526248} {"current_steps": 32620, "total_steps": 40000, "loss": 0.0, "lr": 4.08435716653299e-06, "epoch": 572.2831858407079, "percentage": 81.55, "elapsed_time": "3:54:55", "remaining_time": "0:53:08", "throughput": 1314.56, "total_tokens": 18528968} {"current_steps": 32625, "total_steps": 40000, "loss": 0.0, "lr": 4.0789810112240005e-06, "epoch": 572.3716814159292, "percentage": 81.56, "elapsed_time": "3:54:57", "remaining_time": "0:53:06", "throughput": 1314.58, "total_tokens": 18532024} {"current_steps": 32630, "total_steps": 40000, "loss": 0.0, "lr": 4.073608082199057e-06, "epoch": 572.4601769911504, "percentage": 81.58, "elapsed_time": "3:54:59", "remaining_time": "0:53:04", "throughput": 1314.59, "total_tokens": 18534840} {"current_steps": 32635, "total_steps": 40000, "loss": 0.0, "lr": 4.068238380286718e-06, "epoch": 572.5486725663717, "percentage": 81.59, "elapsed_time": "3:55:01", "remaining_time": "0:53:02", "throughput": 1314.6, "total_tokens": 18537848} {"current_steps": 32640, "total_steps": 40000, "loss": 0.0, "lr": 4.062871906315072e-06, "epoch": 572.637168141593, "percentage": 81.6, "elapsed_time": "3:55:03", "remaining_time": "0:53:00", "throughput": 1314.58, "total_tokens": 18540392} {"current_steps": 32645, "total_steps": 40000, "loss": 0.0, "lr": 4.057508661111686e-06, "epoch": 572.7256637168142, "percentage": 81.61, "elapsed_time": "3:55:05", "remaining_time": "0:52:58", "throughput": 1314.61, "total_tokens": 18543512} {"current_steps": 32650, "total_steps": 40000, "loss": 0.0, "lr": 4.052148645503648e-06, "epoch": 572.8141592920354, "percentage": 81.62, "elapsed_time": "3:55:07", "remaining_time": "0:52:55", "throughput": 1314.61, "total_tokens": 18546328} {"current_steps": 32655, "total_steps": 40000, "loss": 0.0, "lr": 4.046791860317531e-06, "epoch": 572.9026548672566, "percentage": 81.64, "elapsed_time": "3:55:09", "remaining_time": "0:52:53", "throughput": 1314.62, "total_tokens": 18549272} {"current_steps": 32660, "total_steps": 40000, "loss": 0.0, "lr": 4.041438306379431e-06, "epoch": 572.9911504424779, "percentage": 81.65, "elapsed_time": "3:55:12", "remaining_time": "0:52:51", "throughput": 1314.64, "total_tokens": 18552280} {"current_steps": 32665, "total_steps": 40000, "loss": 0.0, "lr": 4.036087984514916e-06, "epoch": 573.070796460177, "percentage": 81.66, "elapsed_time": "3:55:14", "remaining_time": "0:52:49", "throughput": 1314.6, "total_tokens": 18554696} {"current_steps": 32670, "total_steps": 40000, "loss": 0.0, "lr": 4.030740895549084e-06, "epoch": 573.1592920353983, "percentage": 81.67, "elapsed_time": "3:55:16", "remaining_time": "0:52:47", "throughput": 1314.6, "total_tokens": 18557464} {"current_steps": 32675, "total_steps": 40000, "loss": 0.0, "lr": 4.025397040306531e-06, "epoch": 573.2477876106195, "percentage": 81.69, "elapsed_time": "3:55:18", "remaining_time": "0:52:45", "throughput": 1314.63, "total_tokens": 18560728} {"current_steps": 32680, "total_steps": 40000, "loss": 0.0, "lr": 4.0200564196113285e-06, "epoch": 573.3362831858407, "percentage": 81.7, "elapsed_time": "3:55:20", "remaining_time": "0:52:42", "throughput": 1314.61, "total_tokens": 18563304} {"current_steps": 32685, "total_steps": 40000, "loss": 0.0, "lr": 4.014719034287079e-06, "epoch": 573.4247787610619, "percentage": 81.71, "elapsed_time": "3:55:22", "remaining_time": "0:52:40", "throughput": 1314.62, "total_tokens": 18566248} {"current_steps": 32690, "total_steps": 40000, "loss": 0.0, "lr": 4.0093848851568775e-06, "epoch": 573.5132743362832, "percentage": 81.73, "elapsed_time": "3:55:24", "remaining_time": "0:52:38", "throughput": 1314.66, "total_tokens": 18569528} {"current_steps": 32695, "total_steps": 40000, "loss": 0.0, "lr": 4.004053973043304e-06, "epoch": 573.6017699115044, "percentage": 81.74, "elapsed_time": "3:55:27", "remaining_time": "0:52:36", "throughput": 1314.64, "total_tokens": 18571992} {"current_steps": 32700, "total_steps": 40000, "loss": 0.0, "lr": 3.998726298768465e-06, "epoch": 573.6902654867257, "percentage": 81.75, "elapsed_time": "3:55:29", "remaining_time": "0:52:34", "throughput": 1314.61, "total_tokens": 18574296} {"current_steps": 32705, "total_steps": 40000, "loss": 0.0, "lr": 3.99340186315395e-06, "epoch": 573.7787610619469, "percentage": 81.76, "elapsed_time": "3:55:31", "remaining_time": "0:52:32", "throughput": 1314.65, "total_tokens": 18577624} {"current_steps": 32710, "total_steps": 40000, "loss": 0.0, "lr": 3.988080667020849e-06, "epoch": 573.8672566371681, "percentage": 81.77, "elapsed_time": "3:55:33", "remaining_time": "0:52:29", "throughput": 1314.69, "total_tokens": 18581016} {"current_steps": 32715, "total_steps": 40000, "loss": 0.0, "lr": 3.982762711189766e-06, "epoch": 573.9557522123894, "percentage": 81.79, "elapsed_time": "3:55:35", "remaining_time": "0:52:27", "throughput": 1314.68, "total_tokens": 18583576} {"current_steps": 32720, "total_steps": 40000, "loss": 0.0, "lr": 3.977447996480785e-06, "epoch": 574.0353982300885, "percentage": 81.8, "elapsed_time": "3:55:37", "remaining_time": "0:52:25", "throughput": 1314.61, "total_tokens": 18585736} {"current_steps": 32725, "total_steps": 40000, "loss": 0.0, "lr": 3.97213652371351e-06, "epoch": 574.1238938053098, "percentage": 81.81, "elapsed_time": "3:55:39", "remaining_time": "0:52:23", "throughput": 1314.64, "total_tokens": 18588888} {"current_steps": 32730, "total_steps": 40000, "loss": 0.0, "lr": 3.966828293707042e-06, "epoch": 574.212389380531, "percentage": 81.83, "elapsed_time": "3:55:41", "remaining_time": "0:52:21", "throughput": 1314.67, "total_tokens": 18592088} {"current_steps": 32735, "total_steps": 40000, "loss": 0.0, "lr": 3.961523307279963e-06, "epoch": 574.3008849557522, "percentage": 81.84, "elapsed_time": "3:55:44", "remaining_time": "0:52:19", "throughput": 1314.64, "total_tokens": 18594728} {"current_steps": 32740, "total_steps": 40000, "loss": 0.0, "lr": 3.956221565250382e-06, "epoch": 574.3893805309734, "percentage": 81.85, "elapsed_time": "3:55:46", "remaining_time": "0:52:16", "throughput": 1314.69, "total_tokens": 18598120} {"current_steps": 32745, "total_steps": 40000, "loss": 0.0, "lr": 3.950923068435883e-06, "epoch": 574.4778761061947, "percentage": 81.86, "elapsed_time": "3:55:48", "remaining_time": "0:52:14", "throughput": 1314.69, "total_tokens": 18600968} {"current_steps": 32750, "total_steps": 40000, "loss": 0.0, "lr": 3.945627817653566e-06, "epoch": 574.566371681416, "percentage": 81.88, "elapsed_time": "3:55:50", "remaining_time": "0:52:12", "throughput": 1314.7, "total_tokens": 18603944} {"current_steps": 32755, "total_steps": 40000, "loss": 0.0, "lr": 3.9403358137200335e-06, "epoch": 574.6548672566372, "percentage": 81.89, "elapsed_time": "3:55:52", "remaining_time": "0:52:10", "throughput": 1314.68, "total_tokens": 18606520} {"current_steps": 32760, "total_steps": 40000, "loss": 0.0, "lr": 3.9350470574513605e-06, "epoch": 574.7433628318585, "percentage": 81.9, "elapsed_time": "3:55:54", "remaining_time": "0:52:08", "throughput": 1314.7, "total_tokens": 18609512} {"current_steps": 32765, "total_steps": 40000, "loss": 0.0, "lr": 3.9297615496631525e-06, "epoch": 574.8318584070796, "percentage": 81.91, "elapsed_time": "3:55:57", "remaining_time": "0:52:06", "throughput": 1314.69, "total_tokens": 18612184} {"current_steps": 32770, "total_steps": 40000, "loss": 0.0, "lr": 3.924479291170505e-06, "epoch": 574.9203539823009, "percentage": 81.92, "elapsed_time": "3:55:59", "remaining_time": "0:52:03", "throughput": 1314.7, "total_tokens": 18614952} {"current_steps": 32775, "total_steps": 40000, "loss": 0.0, "lr": 3.919200282788002e-06, "epoch": 575.0, "percentage": 81.94, "elapsed_time": "3:56:01", "remaining_time": "0:52:01", "throughput": 1314.67, "total_tokens": 18617264} {"current_steps": 32780, "total_steps": 40000, "loss": 0.0, "lr": 3.913924525329726e-06, "epoch": 575.0884955752213, "percentage": 81.95, "elapsed_time": "3:56:03", "remaining_time": "0:51:59", "throughput": 1314.64, "total_tokens": 18619920} {"current_steps": 32785, "total_steps": 40000, "loss": 0.0, "lr": 3.908652019609279e-06, "epoch": 575.1769911504425, "percentage": 81.96, "elapsed_time": "3:56:05", "remaining_time": "0:51:57", "throughput": 1314.64, "total_tokens": 18622800} {"current_steps": 32790, "total_steps": 40000, "loss": 0.0, "lr": 3.9033827664397364e-06, "epoch": 575.2654867256637, "percentage": 81.97, "elapsed_time": "3:56:07", "remaining_time": "0:51:55", "throughput": 1314.66, "total_tokens": 18625872} {"current_steps": 32795, "total_steps": 40000, "loss": 0.0, "lr": 3.898116766633694e-06, "epoch": 575.3539823008849, "percentage": 81.99, "elapsed_time": "3:56:09", "remaining_time": "0:51:53", "throughput": 1314.65, "total_tokens": 18628464} {"current_steps": 32800, "total_steps": 40000, "loss": 0.0, "lr": 3.8928540210032225e-06, "epoch": 575.4424778761062, "percentage": 82.0, "elapsed_time": "3:56:12", "remaining_time": "0:51:50", "throughput": 1314.65, "total_tokens": 18631296} {"current_steps": 32800, "total_steps": 40000, "eval_loss": 0.9141509532928467, "epoch": 575.4424778761062, "percentage": 82.0, "elapsed_time": "3:56:13", "remaining_time": "0:51:51", "throughput": 1314.55, "total_tokens": 18631296} {"current_steps": 32805, "total_steps": 40000, "loss": 0.0, "lr": 3.887594530359909e-06, "epoch": 575.5309734513274, "percentage": 82.01, "elapsed_time": "3:56:16", "remaining_time": "0:51:49", "throughput": 1314.41, "total_tokens": 18634368} {"current_steps": 32810, "total_steps": 40000, "loss": 0.0, "lr": 3.88233829551484e-06, "epoch": 575.6194690265487, "percentage": 82.03, "elapsed_time": "3:56:19", "remaining_time": "0:51:47", "throughput": 1314.43, "total_tokens": 18637280} {"current_steps": 32815, "total_steps": 40000, "loss": 0.0, "lr": 3.877085317278581e-06, "epoch": 575.70796460177, "percentage": 82.04, "elapsed_time": "3:56:21", "remaining_time": "0:51:45", "throughput": 1314.43, "total_tokens": 18640048} {"current_steps": 32820, "total_steps": 40000, "loss": 0.0, "lr": 3.87183559646122e-06, "epoch": 575.7964601769911, "percentage": 82.05, "elapsed_time": "3:56:23", "remaining_time": "0:51:42", "throughput": 1314.4, "total_tokens": 18642432} {"current_steps": 32825, "total_steps": 40000, "loss": 0.0, "lr": 3.866589133872317e-06, "epoch": 575.8849557522124, "percentage": 82.06, "elapsed_time": "3:56:25", "remaining_time": "0:51:40", "throughput": 1314.43, "total_tokens": 18645696} {"current_steps": 32830, "total_steps": 40000, "loss": 0.0, "lr": 3.861345930320948e-06, "epoch": 575.9734513274336, "percentage": 82.08, "elapsed_time": "3:56:27", "remaining_time": "0:51:38", "throughput": 1314.48, "total_tokens": 18649200} {"current_steps": 32835, "total_steps": 40000, "loss": 0.0, "lr": 3.856105986615688e-06, "epoch": 576.0530973451328, "percentage": 82.09, "elapsed_time": "3:56:29", "remaining_time": "0:51:36", "throughput": 1314.41, "total_tokens": 18651216} {"current_steps": 32840, "total_steps": 40000, "loss": 0.0, "lr": 3.850869303564589e-06, "epoch": 576.141592920354, "percentage": 82.1, "elapsed_time": "3:56:31", "remaining_time": "0:51:34", "throughput": 1314.4, "total_tokens": 18653952} {"current_steps": 32845, "total_steps": 40000, "loss": 0.0, "lr": 3.845635881975226e-06, "epoch": 576.2300884955753, "percentage": 82.11, "elapsed_time": "3:56:34", "remaining_time": "0:51:32", "throughput": 1314.38, "total_tokens": 18656352} {"current_steps": 32850, "total_steps": 40000, "loss": 0.0, "lr": 3.840405722654647e-06, "epoch": 576.3185840707964, "percentage": 82.12, "elapsed_time": "3:56:36", "remaining_time": "0:51:29", "throughput": 1314.46, "total_tokens": 18660192} {"current_steps": 32855, "total_steps": 40000, "loss": 0.0, "lr": 3.835178826409419e-06, "epoch": 576.4070796460177, "percentage": 82.14, "elapsed_time": "3:56:38", "remaining_time": "0:51:27", "throughput": 1314.51, "total_tokens": 18663600} {"current_steps": 32860, "total_steps": 40000, "loss": 0.0, "lr": 3.8299551940455895e-06, "epoch": 576.4955752212389, "percentage": 82.15, "elapsed_time": "3:56:40", "remaining_time": "0:51:25", "throughput": 1314.49, "total_tokens": 18666096} {"current_steps": 32865, "total_steps": 40000, "loss": 0.0, "lr": 3.824734826368703e-06, "epoch": 576.5840707964602, "percentage": 82.16, "elapsed_time": "3:56:42", "remaining_time": "0:51:23", "throughput": 1314.47, "total_tokens": 18668576} {"current_steps": 32870, "total_steps": 40000, "loss": 0.0, "lr": 3.819517724183813e-06, "epoch": 576.6725663716815, "percentage": 82.17, "elapsed_time": "3:56:44", "remaining_time": "0:51:21", "throughput": 1314.48, "total_tokens": 18671504} {"current_steps": 32875, "total_steps": 40000, "loss": 0.0, "lr": 3.8143038882954648e-06, "epoch": 576.7610619469026, "percentage": 82.19, "elapsed_time": "3:56:46", "remaining_time": "0:51:19", "throughput": 1314.48, "total_tokens": 18674448} {"current_steps": 32880, "total_steps": 40000, "loss": 0.0, "lr": 3.8090933195076867e-06, "epoch": 576.8495575221239, "percentage": 82.2, "elapsed_time": "3:56:48", "remaining_time": "0:51:16", "throughput": 1314.51, "total_tokens": 18677680} {"current_steps": 32885, "total_steps": 40000, "loss": 0.0, "lr": 3.8038860186240198e-06, "epoch": 576.9380530973451, "percentage": 82.21, "elapsed_time": "3:56:50", "remaining_time": "0:51:14", "throughput": 1314.51, "total_tokens": 18680368} {"current_steps": 32890, "total_steps": 40000, "loss": 0.0, "lr": 3.7986819864475026e-06, "epoch": 577.0176991150443, "percentage": 82.23, "elapsed_time": "3:56:53", "remaining_time": "0:51:12", "throughput": 1314.46, "total_tokens": 18682512} {"current_steps": 32895, "total_steps": 40000, "loss": 0.0, "lr": 3.793481223780651e-06, "epoch": 577.1061946902655, "percentage": 82.24, "elapsed_time": "3:56:55", "remaining_time": "0:51:10", "throughput": 1314.44, "total_tokens": 18685056} {"current_steps": 32900, "total_steps": 40000, "loss": 0.0, "lr": 3.788283731425496e-06, "epoch": 577.1946902654868, "percentage": 82.25, "elapsed_time": "3:56:57", "remaining_time": "0:51:08", "throughput": 1314.48, "total_tokens": 18688352} {"current_steps": 32905, "total_steps": 40000, "loss": 0.0, "lr": 3.7830895101835488e-06, "epoch": 577.2831858407079, "percentage": 82.26, "elapsed_time": "3:56:59", "remaining_time": "0:51:05", "throughput": 1314.48, "total_tokens": 18691200} {"current_steps": 32910, "total_steps": 40000, "loss": 0.0, "lr": 3.7778985608558274e-06, "epoch": 577.3716814159292, "percentage": 82.27, "elapsed_time": "3:57:01", "remaining_time": "0:51:03", "throughput": 1314.45, "total_tokens": 18693472} {"current_steps": 32915, "total_steps": 40000, "loss": 0.0, "lr": 3.7727108842428443e-06, "epoch": 577.4601769911504, "percentage": 82.29, "elapsed_time": "3:57:03", "remaining_time": "0:51:01", "throughput": 1314.45, "total_tokens": 18696320} {"current_steps": 32920, "total_steps": 40000, "loss": 0.0, "lr": 3.7675264811446065e-06, "epoch": 577.5486725663717, "percentage": 82.3, "elapsed_time": "3:57:05", "remaining_time": "0:50:59", "throughput": 1314.47, "total_tokens": 18699424} {"current_steps": 32925, "total_steps": 40000, "loss": 0.0, "lr": 3.7623453523605994e-06, "epoch": 577.637168141593, "percentage": 82.31, "elapsed_time": "3:57:07", "remaining_time": "0:50:57", "throughput": 1314.48, "total_tokens": 18702352} {"current_steps": 32930, "total_steps": 40000, "loss": 0.0, "lr": 3.757167498689834e-06, "epoch": 577.7256637168142, "percentage": 82.33, "elapsed_time": "3:57:10", "remaining_time": "0:50:55", "throughput": 1314.53, "total_tokens": 18705824} {"current_steps": 32935, "total_steps": 40000, "loss": 0.0, "lr": 3.7519929209307914e-06, "epoch": 577.8141592920354, "percentage": 82.34, "elapsed_time": "3:57:12", "remaining_time": "0:50:52", "throughput": 1314.55, "total_tokens": 18708848} {"current_steps": 32940, "total_steps": 40000, "loss": 0.0, "lr": 3.746821619881463e-06, "epoch": 577.9026548672566, "percentage": 82.35, "elapsed_time": "3:57:14", "remaining_time": "0:50:50", "throughput": 1314.56, "total_tokens": 18711600} {"current_steps": 32945, "total_steps": 40000, "loss": 0.0, "lr": 3.74165359633932e-06, "epoch": 577.9911504424779, "percentage": 82.36, "elapsed_time": "3:57:16", "remaining_time": "0:50:48", "throughput": 1314.57, "total_tokens": 18714512} {"current_steps": 32950, "total_steps": 40000, "loss": 0.0, "lr": 3.736488851101341e-06, "epoch": 578.070796460177, "percentage": 82.38, "elapsed_time": "3:57:18", "remaining_time": "0:50:46", "throughput": 1314.53, "total_tokens": 18716952} {"current_steps": 32955, "total_steps": 40000, "loss": 0.0, "lr": 3.7313273849640035e-06, "epoch": 578.1592920353983, "percentage": 82.39, "elapsed_time": "3:57:20", "remaining_time": "0:50:44", "throughput": 1314.52, "total_tokens": 18719576} {"current_steps": 32960, "total_steps": 40000, "loss": 0.0, "lr": 3.7261691987232533e-06, "epoch": 578.2477876106195, "percentage": 82.4, "elapsed_time": "3:57:22", "remaining_time": "0:50:42", "throughput": 1314.52, "total_tokens": 18722424} {"current_steps": 32965, "total_steps": 40000, "loss": 0.0, "lr": 3.7210142931745575e-06, "epoch": 578.3362831858407, "percentage": 82.41, "elapsed_time": "3:57:24", "remaining_time": "0:50:39", "throughput": 1314.56, "total_tokens": 18725784} {"current_steps": 32970, "total_steps": 40000, "loss": 0.0, "lr": 3.7158626691128712e-06, "epoch": 578.4247787610619, "percentage": 82.42, "elapsed_time": "3:57:27", "remaining_time": "0:50:37", "throughput": 1314.56, "total_tokens": 18728648} {"current_steps": 32975, "total_steps": 40000, "loss": 0.0, "lr": 3.710714327332629e-06, "epoch": 578.5132743362832, "percentage": 82.44, "elapsed_time": "3:57:29", "remaining_time": "0:50:35", "throughput": 1314.54, "total_tokens": 18731080} {"current_steps": 32980, "total_steps": 40000, "loss": 0.0, "lr": 3.7055692686277815e-06, "epoch": 578.6017699115044, "percentage": 82.45, "elapsed_time": "3:57:31", "remaining_time": "0:50:33", "throughput": 1314.53, "total_tokens": 18733704} {"current_steps": 32985, "total_steps": 40000, "loss": 0.0, "lr": 3.70042749379175e-06, "epoch": 578.6902654867257, "percentage": 82.46, "elapsed_time": "3:57:33", "remaining_time": "0:50:31", "throughput": 1314.54, "total_tokens": 18736664} {"current_steps": 32990, "total_steps": 40000, "loss": 0.0, "lr": 3.6952890036174693e-06, "epoch": 578.7787610619469, "percentage": 82.47, "elapsed_time": "3:57:35", "remaining_time": "0:50:29", "throughput": 1314.58, "total_tokens": 18739928} {"current_steps": 32995, "total_steps": 40000, "loss": 0.0, "lr": 3.690153798897353e-06, "epoch": 578.8672566371681, "percentage": 82.49, "elapsed_time": "3:57:37", "remaining_time": "0:50:26", "throughput": 1314.57, "total_tokens": 18742552} {"current_steps": 33000, "total_steps": 40000, "loss": 0.0, "lr": 3.6850218804233225e-06, "epoch": 578.9557522123894, "percentage": 82.5, "elapsed_time": "3:57:39", "remaining_time": "0:50:24", "throughput": 1314.58, "total_tokens": 18745416} {"current_steps": 33000, "total_steps": 40000, "eval_loss": 0.9105704426765442, "epoch": 578.9557522123894, "percentage": 82.5, "elapsed_time": "3:57:40", "remaining_time": "0:50:24", "throughput": 1314.48, "total_tokens": 18745416} {"current_steps": 33005, "total_steps": 40000, "loss": 0.0, "lr": 3.679893248986779e-06, "epoch": 579.0353982300885, "percentage": 82.51, "elapsed_time": "3:57:45", "remaining_time": "0:50:23", "throughput": 1314.24, "total_tokens": 18747704} {"current_steps": 33010, "total_steps": 40000, "loss": 0.0, "lr": 3.6747679053786147e-06, "epoch": 579.1238938053098, "percentage": 82.53, "elapsed_time": "3:57:47", "remaining_time": "0:50:21", "throughput": 1314.25, "total_tokens": 18750712} {"current_steps": 33015, "total_steps": 40000, "loss": 0.0, "lr": 3.669645850389228e-06, "epoch": 579.212389380531, "percentage": 82.54, "elapsed_time": "3:57:49", "remaining_time": "0:50:18", "throughput": 1314.23, "total_tokens": 18753192} {"current_steps": 33020, "total_steps": 40000, "loss": 0.0, "lr": 3.664527084808514e-06, "epoch": 579.3008849557522, "percentage": 82.55, "elapsed_time": "3:57:51", "remaining_time": "0:50:16", "throughput": 1314.24, "total_tokens": 18756168} {"current_steps": 33025, "total_steps": 40000, "loss": 0.0, "lr": 3.6594116094258337e-06, "epoch": 579.3893805309734, "percentage": 82.56, "elapsed_time": "3:57:53", "remaining_time": "0:50:14", "throughput": 1314.26, "total_tokens": 18759176} {"current_steps": 33030, "total_steps": 40000, "loss": 0.0, "lr": 3.6542994250300665e-06, "epoch": 579.4778761061947, "percentage": 82.58, "elapsed_time": "3:57:55", "remaining_time": "0:50:12", "throughput": 1314.24, "total_tokens": 18761576} {"current_steps": 33035, "total_steps": 40000, "loss": 0.0, "lr": 3.6491905324095825e-06, "epoch": 579.566371681416, "percentage": 82.59, "elapsed_time": "3:57:57", "remaining_time": "0:50:10", "throughput": 1314.25, "total_tokens": 18764488} {"current_steps": 33040, "total_steps": 40000, "loss": 0.0, "lr": 3.644084932352221e-06, "epoch": 579.6548672566372, "percentage": 82.6, "elapsed_time": "3:57:59", "remaining_time": "0:50:08", "throughput": 1314.24, "total_tokens": 18767128} {"current_steps": 33045, "total_steps": 40000, "loss": 0.0, "lr": 3.6389826256453457e-06, "epoch": 579.7433628318585, "percentage": 82.61, "elapsed_time": "3:58:01", "remaining_time": "0:50:05", "throughput": 1314.28, "total_tokens": 18770376} {"current_steps": 33050, "total_steps": 40000, "loss": 0.0, "lr": 3.633883613075781e-06, "epoch": 579.8318584070796, "percentage": 82.62, "elapsed_time": "3:58:04", "remaining_time": "0:50:03", "throughput": 1314.27, "total_tokens": 18773064} {"current_steps": 33055, "total_steps": 40000, "loss": 0.0, "lr": 3.6287878954298693e-06, "epoch": 579.9203539823009, "percentage": 82.64, "elapsed_time": "3:58:06", "remaining_time": "0:50:01", "throughput": 1314.29, "total_tokens": 18776232} {"current_steps": 33060, "total_steps": 40000, "loss": 0.0, "lr": 3.6236954734934354e-06, "epoch": 580.0, "percentage": 82.65, "elapsed_time": "3:58:08", "remaining_time": "0:49:59", "throughput": 1314.28, "total_tokens": 18778768} {"current_steps": 33065, "total_steps": 40000, "loss": 0.0, "lr": 3.618606348051784e-06, "epoch": 580.0884955752213, "percentage": 82.66, "elapsed_time": "3:58:10", "remaining_time": "0:49:57", "throughput": 1314.23, "total_tokens": 18781232} {"current_steps": 33070, "total_steps": 40000, "loss": 0.0, "lr": 3.6135205198897376e-06, "epoch": 580.1769911504425, "percentage": 82.67, "elapsed_time": "3:58:12", "remaining_time": "0:49:55", "throughput": 1314.23, "total_tokens": 18784032} {"current_steps": 33075, "total_steps": 40000, "loss": 0.0, "lr": 3.6084379897915854e-06, "epoch": 580.2654867256637, "percentage": 82.69, "elapsed_time": "3:58:14", "remaining_time": "0:49:52", "throughput": 1314.21, "total_tokens": 18786496} {"current_steps": 33080, "total_steps": 40000, "loss": 0.0, "lr": 3.6033587585411115e-06, "epoch": 580.3539823008849, "percentage": 82.7, "elapsed_time": "3:58:16", "remaining_time": "0:49:50", "throughput": 1314.25, "total_tokens": 18789728} {"current_steps": 33085, "total_steps": 40000, "loss": 0.0, "lr": 3.5982828269216117e-06, "epoch": 580.4424778761062, "percentage": 82.71, "elapsed_time": "3:58:18", "remaining_time": "0:49:48", "throughput": 1314.25, "total_tokens": 18792496} {"current_steps": 33090, "total_steps": 40000, "loss": 0.0, "lr": 3.593210195715843e-06, "epoch": 580.5309734513274, "percentage": 82.73, "elapsed_time": "3:58:21", "remaining_time": "0:49:46", "throughput": 1314.24, "total_tokens": 18795040} {"current_steps": 33095, "total_steps": 40000, "loss": 0.0, "lr": 3.5881408657060773e-06, "epoch": 580.6194690265487, "percentage": 82.74, "elapsed_time": "3:58:23", "remaining_time": "0:49:44", "throughput": 1314.27, "total_tokens": 18798128} {"current_steps": 33100, "total_steps": 40000, "loss": 0.0, "lr": 3.583074837674075e-06, "epoch": 580.70796460177, "percentage": 82.75, "elapsed_time": "3:58:25", "remaining_time": "0:49:42", "throughput": 1314.27, "total_tokens": 18801024} {"current_steps": 33105, "total_steps": 40000, "loss": 0.0, "lr": 3.578012112401069e-06, "epoch": 580.7964601769911, "percentage": 82.76, "elapsed_time": "3:58:27", "remaining_time": "0:49:39", "throughput": 1314.28, "total_tokens": 18803984} {"current_steps": 33110, "total_steps": 40000, "loss": 0.0, "lr": 3.5729526906677996e-06, "epoch": 580.8849557522124, "percentage": 82.78, "elapsed_time": "3:58:29", "remaining_time": "0:49:37", "throughput": 1314.29, "total_tokens": 18806832} {"current_steps": 33115, "total_steps": 40000, "loss": 0.0, "lr": 3.5678965732545007e-06, "epoch": 580.9734513274336, "percentage": 82.79, "elapsed_time": "3:58:31", "remaining_time": "0:49:35", "throughput": 1314.3, "total_tokens": 18809840} {"current_steps": 33120, "total_steps": 40000, "loss": 0.0, "lr": 3.562843760940876e-06, "epoch": 581.0530973451328, "percentage": 82.8, "elapsed_time": "3:58:34", "remaining_time": "0:49:33", "throughput": 1314.24, "total_tokens": 18812080} {"current_steps": 33125, "total_steps": 40000, "loss": 0.0, "lr": 3.5577942545061473e-06, "epoch": 581.141592920354, "percentage": 82.81, "elapsed_time": "3:58:36", "remaining_time": "0:49:31", "throughput": 1314.25, "total_tokens": 18814976} {"current_steps": 33130, "total_steps": 40000, "loss": 0.0, "lr": 3.5527480547289967e-06, "epoch": 581.2300884955753, "percentage": 82.83, "elapsed_time": "3:58:38", "remaining_time": "0:49:29", "throughput": 1314.26, "total_tokens": 18817808} {"current_steps": 33135, "total_steps": 40000, "loss": 0.0, "lr": 3.547705162387624e-06, "epoch": 581.3185840707964, "percentage": 82.84, "elapsed_time": "3:58:40", "remaining_time": "0:49:26", "throughput": 1314.26, "total_tokens": 18820512} {"current_steps": 33140, "total_steps": 40000, "loss": 0.0, "lr": 3.542665578259699e-06, "epoch": 581.4070796460177, "percentage": 82.85, "elapsed_time": "3:58:42", "remaining_time": "0:49:24", "throughput": 1314.26, "total_tokens": 18823232} {"current_steps": 33145, "total_steps": 40000, "loss": 0.0, "lr": 3.5376293031223945e-06, "epoch": 581.4955752212389, "percentage": 82.86, "elapsed_time": "3:58:44", "remaining_time": "0:49:22", "throughput": 1314.25, "total_tokens": 18825856} {"current_steps": 33150, "total_steps": 40000, "loss": 0.0, "lr": 3.5325963377523614e-06, "epoch": 581.5840707964602, "percentage": 82.88, "elapsed_time": "3:58:46", "remaining_time": "0:49:20", "throughput": 1314.25, "total_tokens": 18828608} {"current_steps": 33155, "total_steps": 40000, "loss": 0.0, "lr": 3.5275666829257536e-06, "epoch": 581.6725663716815, "percentage": 82.89, "elapsed_time": "3:58:48", "remaining_time": "0:49:18", "throughput": 1314.28, "total_tokens": 18831824} {"current_steps": 33160, "total_steps": 40000, "loss": 0.0, "lr": 3.5225403394181955e-06, "epoch": 581.7610619469026, "percentage": 82.9, "elapsed_time": "3:58:50", "remaining_time": "0:49:16", "throughput": 1314.27, "total_tokens": 18834416} {"current_steps": 33165, "total_steps": 40000, "loss": 0.0, "lr": 3.517517308004828e-06, "epoch": 581.8495575221239, "percentage": 82.91, "elapsed_time": "3:58:52", "remaining_time": "0:49:13", "throughput": 1314.3, "total_tokens": 18837776} {"current_steps": 33170, "total_steps": 40000, "loss": 0.0, "lr": 3.512497589460251e-06, "epoch": 581.9380530973451, "percentage": 82.93, "elapsed_time": "3:58:55", "remaining_time": "0:49:11", "throughput": 1314.3, "total_tokens": 18840480} {"current_steps": 33175, "total_steps": 40000, "loss": 0.0, "lr": 3.5074811845585727e-06, "epoch": 582.0176991150443, "percentage": 82.94, "elapsed_time": "3:58:57", "remaining_time": "0:49:09", "throughput": 1314.28, "total_tokens": 18843368} {"current_steps": 33180, "total_steps": 40000, "loss": 0.0, "lr": 3.5024680940733937e-06, "epoch": 582.1061946902655, "percentage": 82.95, "elapsed_time": "3:58:59", "remaining_time": "0:49:07", "throughput": 1314.28, "total_tokens": 18846072} {"current_steps": 33185, "total_steps": 40000, "loss": 0.0, "lr": 3.4974583187777852e-06, "epoch": 582.1946902654868, "percentage": 82.96, "elapsed_time": "3:59:01", "remaining_time": "0:49:05", "throughput": 1314.31, "total_tokens": 18849240} {"current_steps": 33190, "total_steps": 40000, "loss": 0.0, "lr": 3.4924518594443204e-06, "epoch": 582.2831858407079, "percentage": 82.97, "elapsed_time": "3:59:03", "remaining_time": "0:49:03", "throughput": 1314.3, "total_tokens": 18851896} {"current_steps": 33195, "total_steps": 40000, "loss": 0.0, "lr": 3.4874487168450682e-06, "epoch": 582.3716814159292, "percentage": 82.99, "elapsed_time": "3:59:05", "remaining_time": "0:49:00", "throughput": 1314.33, "total_tokens": 18855000} {"current_steps": 33200, "total_steps": 40000, "loss": 0.0, "lr": 3.482448891751558e-06, "epoch": 582.4601769911504, "percentage": 83.0, "elapsed_time": "3:59:07", "remaining_time": "0:48:58", "throughput": 1314.34, "total_tokens": 18857896} {"current_steps": 33200, "total_steps": 40000, "eval_loss": 0.9186511635780334, "epoch": 582.4601769911504, "percentage": 83.0, "elapsed_time": "3:59:08", "remaining_time": "0:48:58", "throughput": 1314.25, "total_tokens": 18857896} {"current_steps": 33205, "total_steps": 40000, "loss": 0.0, "lr": 3.477452384934843e-06, "epoch": 582.5486725663717, "percentage": 83.01, "elapsed_time": "3:59:13", "remaining_time": "0:48:57", "throughput": 1314.04, "total_tokens": 18860696} {"current_steps": 33210, "total_steps": 40000, "loss": 0.0, "lr": 3.472459197165434e-06, "epoch": 582.637168141593, "percentage": 83.03, "elapsed_time": "3:59:15", "remaining_time": "0:48:55", "throughput": 1314.04, "total_tokens": 18863448} {"current_steps": 33215, "total_steps": 40000, "loss": 0.0, "lr": 3.4674693292133518e-06, "epoch": 582.7256637168142, "percentage": 83.04, "elapsed_time": "3:59:17", "remaining_time": "0:48:52", "throughput": 1314.05, "total_tokens": 18866344} {"current_steps": 33220, "total_steps": 40000, "loss": 0.0, "lr": 3.4624827818480977e-06, "epoch": 582.8141592920354, "percentage": 83.05, "elapsed_time": "3:59:19", "remaining_time": "0:48:50", "throughput": 1314.06, "total_tokens": 18869256} {"current_steps": 33225, "total_steps": 40000, "loss": 0.0, "lr": 3.4574995558386474e-06, "epoch": 582.9026548672566, "percentage": 83.06, "elapsed_time": "3:59:21", "remaining_time": "0:48:48", "throughput": 1314.04, "total_tokens": 18871912} {"current_steps": 33230, "total_steps": 40000, "loss": 0.0, "lr": 3.452519651953487e-06, "epoch": 582.9911504424779, "percentage": 83.08, "elapsed_time": "3:59:23", "remaining_time": "0:48:46", "throughput": 1314.05, "total_tokens": 18874824} {"current_steps": 33235, "total_steps": 40000, "loss": 0.0, "lr": 3.447543070960585e-06, "epoch": 583.070796460177, "percentage": 83.09, "elapsed_time": "3:59:26", "remaining_time": "0:48:44", "throughput": 1314.0, "total_tokens": 18877168} {"current_steps": 33240, "total_steps": 40000, "loss": 0.0, "lr": 3.4425698136273778e-06, "epoch": 583.1592920353983, "percentage": 83.1, "elapsed_time": "3:59:28", "remaining_time": "0:48:42", "throughput": 1313.98, "total_tokens": 18879680} {"current_steps": 33245, "total_steps": 40000, "loss": 0.0, "lr": 3.437599880720821e-06, "epoch": 583.2477876106195, "percentage": 83.11, "elapsed_time": "3:59:30", "remaining_time": "0:48:39", "throughput": 1314.0, "total_tokens": 18882672} {"current_steps": 33250, "total_steps": 40000, "loss": 0.0, "lr": 3.4326332730073267e-06, "epoch": 583.3362831858407, "percentage": 83.12, "elapsed_time": "3:59:32", "remaining_time": "0:48:37", "throughput": 1313.99, "total_tokens": 18885328} {"current_steps": 33255, "total_steps": 40000, "loss": 0.0, "lr": 3.427669991252813e-06, "epoch": 583.4247787610619, "percentage": 83.14, "elapsed_time": "3:59:34", "remaining_time": "0:48:35", "throughput": 1314.03, "total_tokens": 18888608} {"current_steps": 33260, "total_steps": 40000, "loss": 0.0, "lr": 3.42271003622269e-06, "epoch": 583.5132743362832, "percentage": 83.15, "elapsed_time": "3:59:36", "remaining_time": "0:48:33", "throughput": 1314.03, "total_tokens": 18891328} {"current_steps": 33265, "total_steps": 40000, "loss": 0.0, "lr": 3.4177534086818286e-06, "epoch": 583.6017699115044, "percentage": 83.16, "elapsed_time": "3:59:38", "remaining_time": "0:48:31", "throughput": 1314.0, "total_tokens": 18893664} {"current_steps": 33270, "total_steps": 40000, "loss": 0.0, "lr": 3.412800109394612e-06, "epoch": 583.6902654867257, "percentage": 83.17, "elapsed_time": "3:59:40", "remaining_time": "0:48:29", "throughput": 1314.03, "total_tokens": 18896768} {"current_steps": 33275, "total_steps": 40000, "loss": 0.0, "lr": 3.4078501391249044e-06, "epoch": 583.7787610619469, "percentage": 83.19, "elapsed_time": "3:59:42", "remaining_time": "0:48:26", "throughput": 1314.04, "total_tokens": 18899664} {"current_steps": 33280, "total_steps": 40000, "loss": 0.0, "lr": 3.4029034986360453e-06, "epoch": 583.8672566371681, "percentage": 83.2, "elapsed_time": "3:59:45", "remaining_time": "0:48:24", "throughput": 1314.07, "total_tokens": 18902896} {"current_steps": 33285, "total_steps": 40000, "loss": 0.0, "lr": 3.397960188690877e-06, "epoch": 583.9557522123894, "percentage": 83.21, "elapsed_time": "3:59:47", "remaining_time": "0:48:22", "throughput": 1314.09, "total_tokens": 18906096} {"current_steps": 33290, "total_steps": 40000, "loss": 0.0, "lr": 3.393020210051717e-06, "epoch": 584.0353982300885, "percentage": 83.23, "elapsed_time": "3:59:49", "remaining_time": "0:48:20", "throughput": 1314.05, "total_tokens": 18908552} {"current_steps": 33295, "total_steps": 40000, "loss": 0.0, "lr": 3.3880835634803655e-06, "epoch": 584.1238938053098, "percentage": 83.24, "elapsed_time": "3:59:51", "remaining_time": "0:48:18", "throughput": 1314.05, "total_tokens": 18911352} {"current_steps": 33300, "total_steps": 40000, "loss": 0.0, "lr": 3.383150249738126e-06, "epoch": 584.212389380531, "percentage": 83.25, "elapsed_time": "3:59:53", "remaining_time": "0:48:16", "throughput": 1314.06, "total_tokens": 18914264} {"current_steps": 33305, "total_steps": 40000, "loss": 0.0, "lr": 3.3782202695857663e-06, "epoch": 584.3008849557522, "percentage": 83.26, "elapsed_time": "3:59:55", "remaining_time": "0:48:13", "throughput": 1314.04, "total_tokens": 18916792} {"current_steps": 33310, "total_steps": 40000, "loss": 0.0, "lr": 3.373293623783558e-06, "epoch": 584.3893805309734, "percentage": 83.28, "elapsed_time": "3:59:57", "remaining_time": "0:48:11", "throughput": 1314.05, "total_tokens": 18919640} {"current_steps": 33315, "total_steps": 40000, "loss": 0.0, "lr": 3.368370313091257e-06, "epoch": 584.4778761061947, "percentage": 83.29, "elapsed_time": "4:00:00", "remaining_time": "0:48:09", "throughput": 1314.05, "total_tokens": 18922456} {"current_steps": 33320, "total_steps": 40000, "loss": 0.0, "lr": 3.363450338268087e-06, "epoch": 584.566371681416, "percentage": 83.3, "elapsed_time": "4:00:02", "remaining_time": "0:48:07", "throughput": 1314.08, "total_tokens": 18925608} {"current_steps": 33325, "total_steps": 40000, "loss": 0.0, "lr": 3.358533700072783e-06, "epoch": 584.6548672566372, "percentage": 83.31, "elapsed_time": "4:00:04", "remaining_time": "0:48:05", "throughput": 1314.1, "total_tokens": 18928568} {"current_steps": 33330, "total_steps": 40000, "loss": 0.0, "lr": 3.3536203992635377e-06, "epoch": 584.7433628318585, "percentage": 83.33, "elapsed_time": "4:00:06", "remaining_time": "0:48:02", "throughput": 1314.12, "total_tokens": 18931592} {"current_steps": 33335, "total_steps": 40000, "loss": 0.0, "lr": 3.348710436598057e-06, "epoch": 584.8318584070796, "percentage": 83.34, "elapsed_time": "4:00:08", "remaining_time": "0:48:00", "throughput": 1314.09, "total_tokens": 18933800} {"current_steps": 33340, "total_steps": 40000, "loss": 0.0, "lr": 3.3438038128335155e-06, "epoch": 584.9203539823009, "percentage": 83.35, "elapsed_time": "4:00:10", "remaining_time": "0:47:58", "throughput": 1314.11, "total_tokens": 18936952} {"current_steps": 33345, "total_steps": 40000, "loss": 0.0, "lr": 3.338900528726571e-06, "epoch": 585.0, "percentage": 83.36, "elapsed_time": "4:00:12", "remaining_time": "0:47:56", "throughput": 1314.1, "total_tokens": 18939504} {"current_steps": 33350, "total_steps": 40000, "loss": 0.0, "lr": 3.3340005850333812e-06, "epoch": 585.0884955752213, "percentage": 83.38, "elapsed_time": "4:00:14", "remaining_time": "0:47:54", "throughput": 1314.07, "total_tokens": 18942224} {"current_steps": 33355, "total_steps": 40000, "loss": 0.0, "lr": 3.329103982509568e-06, "epoch": 585.1769911504425, "percentage": 83.39, "elapsed_time": "4:00:17", "remaining_time": "0:47:52", "throughput": 1314.06, "total_tokens": 18944976} {"current_steps": 33360, "total_steps": 40000, "loss": 0.0, "lr": 3.324210721910259e-06, "epoch": 585.2654867256637, "percentage": 83.4, "elapsed_time": "4:00:19", "remaining_time": "0:47:50", "throughput": 1314.05, "total_tokens": 18947680} {"current_steps": 33365, "total_steps": 40000, "loss": 0.0, "lr": 3.319320803990053e-06, "epoch": 585.3539823008849, "percentage": 83.41, "elapsed_time": "4:00:21", "remaining_time": "0:47:47", "throughput": 1314.04, "total_tokens": 18950320} {"current_steps": 33370, "total_steps": 40000, "loss": 0.0, "lr": 3.3144342295030274e-06, "epoch": 585.4424778761062, "percentage": 83.43, "elapsed_time": "4:00:23", "remaining_time": "0:47:45", "throughput": 1314.05, "total_tokens": 18953200} {"current_steps": 33375, "total_steps": 40000, "loss": 0.0, "lr": 3.309550999202765e-06, "epoch": 585.5309734513274, "percentage": 83.44, "elapsed_time": "4:00:25", "remaining_time": "0:47:43", "throughput": 1314.03, "total_tokens": 18955760} {"current_steps": 33380, "total_steps": 40000, "loss": 0.0, "lr": 3.3046711138423197e-06, "epoch": 585.6194690265487, "percentage": 83.45, "elapsed_time": "4:00:27", "remaining_time": "0:47:41", "throughput": 1314.08, "total_tokens": 18959216} {"current_steps": 33385, "total_steps": 40000, "loss": 0.0, "lr": 3.2997945741742255e-06, "epoch": 585.70796460177, "percentage": 83.46, "elapsed_time": "4:00:29", "remaining_time": "0:47:39", "throughput": 1314.13, "total_tokens": 18962608} {"current_steps": 33390, "total_steps": 40000, "loss": 0.0, "lr": 3.2949213809505082e-06, "epoch": 585.7964601769911, "percentage": 83.47, "elapsed_time": "4:00:31", "remaining_time": "0:47:36", "throughput": 1314.18, "total_tokens": 18966064} {"current_steps": 33395, "total_steps": 40000, "loss": 0.0, "lr": 3.2900515349226834e-06, "epoch": 585.8849557522124, "percentage": 83.49, "elapsed_time": "4:00:33", "remaining_time": "0:47:34", "throughput": 1314.18, "total_tokens": 18968752} {"current_steps": 33400, "total_steps": 40000, "loss": 0.0, "lr": 3.285185036841731e-06, "epoch": 585.9734513274336, "percentage": 83.5, "elapsed_time": "4:00:35", "remaining_time": "0:47:32", "throughput": 1314.17, "total_tokens": 18971344} {"current_steps": 33400, "total_steps": 40000, "eval_loss": 0.9217712879180908, "epoch": 585.9734513274336, "percentage": 83.5, "elapsed_time": "4:00:37", "remaining_time": "0:47:32", "throughput": 1314.07, "total_tokens": 18971344} {"current_steps": 33405, "total_steps": 40000, "loss": 0.0, "lr": 3.2803218874581377e-06, "epoch": 586.0530973451328, "percentage": 83.51, "elapsed_time": "4:00:41", "remaining_time": "0:47:31", "throughput": 1313.87, "total_tokens": 18973736} {"current_steps": 33410, "total_steps": 40000, "loss": 0.0, "lr": 3.2754620875218494e-06, "epoch": 586.141592920354, "percentage": 83.53, "elapsed_time": "4:00:43", "remaining_time": "0:47:28", "throughput": 1313.86, "total_tokens": 18976392} {"current_steps": 33415, "total_steps": 40000, "loss": 0.0, "lr": 3.2706056377823146e-06, "epoch": 586.2300884955753, "percentage": 83.54, "elapsed_time": "4:00:45", "remaining_time": "0:47:26", "throughput": 1313.88, "total_tokens": 18979576} {"current_steps": 33420, "total_steps": 40000, "loss": 0.0, "lr": 3.2657525389884647e-06, "epoch": 586.3185840707964, "percentage": 83.55, "elapsed_time": "4:00:47", "remaining_time": "0:47:24", "throughput": 1313.87, "total_tokens": 18982136} {"current_steps": 33425, "total_steps": 40000, "loss": 0.0, "lr": 3.260902791888698e-06, "epoch": 586.4070796460177, "percentage": 83.56, "elapsed_time": "4:00:49", "remaining_time": "0:47:22", "throughput": 1313.89, "total_tokens": 18985288} {"current_steps": 33430, "total_steps": 40000, "loss": 0.0, "lr": 3.2560563972309166e-06, "epoch": 586.4955752212389, "percentage": 83.58, "elapsed_time": "4:00:51", "remaining_time": "0:47:20", "throughput": 1313.87, "total_tokens": 18987864} {"current_steps": 33435, "total_steps": 40000, "loss": 0.0, "lr": 3.251213355762489e-06, "epoch": 586.5840707964602, "percentage": 83.59, "elapsed_time": "4:00:53", "remaining_time": "0:47:18", "throughput": 1313.91, "total_tokens": 18991144} {"current_steps": 33440, "total_steps": 40000, "loss": 0.0, "lr": 3.2463736682302707e-06, "epoch": 586.6725663716815, "percentage": 83.6, "elapsed_time": "4:00:56", "remaining_time": "0:47:15", "throughput": 1313.91, "total_tokens": 18993976} {"current_steps": 33445, "total_steps": 40000, "loss": 0.0, "lr": 3.2415373353806124e-06, "epoch": 586.7610619469026, "percentage": 83.61, "elapsed_time": "4:00:58", "remaining_time": "0:47:13", "throughput": 1313.93, "total_tokens": 18997032} {"current_steps": 33450, "total_steps": 40000, "loss": 0.0, "lr": 3.236704357959322e-06, "epoch": 586.8495575221239, "percentage": 83.62, "elapsed_time": "4:01:00", "remaining_time": "0:47:11", "throughput": 1313.92, "total_tokens": 18999736} {"current_steps": 33455, "total_steps": 40000, "loss": 0.0, "lr": 3.2318747367117154e-06, "epoch": 586.9380530973451, "percentage": 83.64, "elapsed_time": "4:01:02", "remaining_time": "0:47:09", "throughput": 1313.96, "total_tokens": 19002936} {"current_steps": 33460, "total_steps": 40000, "loss": 0.0, "lr": 3.227048472382585e-06, "epoch": 587.0176991150443, "percentage": 83.65, "elapsed_time": "4:01:04", "remaining_time": "0:47:07", "throughput": 1313.92, "total_tokens": 19005400} {"current_steps": 33465, "total_steps": 40000, "loss": 0.0, "lr": 3.2222255657161915e-06, "epoch": 587.1061946902655, "percentage": 83.66, "elapsed_time": "4:01:06", "remaining_time": "0:47:05", "throughput": 1313.91, "total_tokens": 19007928} {"current_steps": 33470, "total_steps": 40000, "loss": 0.0, "lr": 3.2174060174562924e-06, "epoch": 587.1946902654868, "percentage": 83.67, "elapsed_time": "4:01:08", "remaining_time": "0:47:02", "throughput": 1313.91, "total_tokens": 19010600} {"current_steps": 33475, "total_steps": 40000, "loss": 0.0, "lr": 3.2125898283461298e-06, "epoch": 587.2831858407079, "percentage": 83.69, "elapsed_time": "4:01:10", "remaining_time": "0:47:00", "throughput": 1313.98, "total_tokens": 19014456} {"current_steps": 33480, "total_steps": 40000, "loss": 0.0, "lr": 3.207776999128406e-06, "epoch": 587.3716814159292, "percentage": 83.7, "elapsed_time": "4:01:12", "remaining_time": "0:46:58", "throughput": 1313.97, "total_tokens": 19016920} {"current_steps": 33485, "total_steps": 40000, "loss": 0.0, "lr": 3.202967530545331e-06, "epoch": 587.4601769911504, "percentage": 83.71, "elapsed_time": "4:01:15", "remaining_time": "0:46:56", "throughput": 1313.95, "total_tokens": 19019432} {"current_steps": 33490, "total_steps": 40000, "loss": 0.0, "lr": 3.1981614233385778e-06, "epoch": 587.5486725663717, "percentage": 83.73, "elapsed_time": "4:01:17", "remaining_time": "0:46:54", "throughput": 1313.96, "total_tokens": 19022376} {"current_steps": 33495, "total_steps": 40000, "loss": 0.0, "lr": 3.1933586782493115e-06, "epoch": 587.637168141593, "percentage": 83.74, "elapsed_time": "4:01:19", "remaining_time": "0:46:52", "throughput": 1313.97, "total_tokens": 19025416} {"current_steps": 33500, "total_steps": 40000, "loss": 0.0, "lr": 3.188559296018184e-06, "epoch": 587.7256637168142, "percentage": 83.75, "elapsed_time": "4:01:21", "remaining_time": "0:46:49", "throughput": 1313.98, "total_tokens": 19028360} {"current_steps": 33505, "total_steps": 40000, "loss": 0.0, "lr": 3.1837632773853098e-06, "epoch": 587.8141592920354, "percentage": 83.76, "elapsed_time": "4:01:23", "remaining_time": "0:46:47", "throughput": 1314.0, "total_tokens": 19031432} {"current_steps": 33510, "total_steps": 40000, "loss": 0.0, "lr": 3.178970623090294e-06, "epoch": 587.9026548672566, "percentage": 83.78, "elapsed_time": "4:01:25", "remaining_time": "0:46:45", "throughput": 1314.01, "total_tokens": 19034456} {"current_steps": 33515, "total_steps": 40000, "loss": 0.0, "lr": 3.174181333872234e-06, "epoch": 587.9911504424779, "percentage": 83.79, "elapsed_time": "4:01:27", "remaining_time": "0:46:43", "throughput": 1314.0, "total_tokens": 19037032} {"current_steps": 33520, "total_steps": 40000, "loss": 0.0, "lr": 3.169395410469686e-06, "epoch": 588.070796460177, "percentage": 83.8, "elapsed_time": "4:01:30", "remaining_time": "0:46:41", "throughput": 1313.93, "total_tokens": 19039232} {"current_steps": 33525, "total_steps": 40000, "loss": 0.0, "lr": 3.164612853620713e-06, "epoch": 588.1592920353983, "percentage": 83.81, "elapsed_time": "4:01:32", "remaining_time": "0:46:39", "throughput": 1313.94, "total_tokens": 19042032} {"current_steps": 33530, "total_steps": 40000, "loss": 0.0, "lr": 3.1598336640628333e-06, "epoch": 588.2477876106195, "percentage": 83.83, "elapsed_time": "4:01:34", "remaining_time": "0:46:36", "throughput": 1313.97, "total_tokens": 19045184} {"current_steps": 33535, "total_steps": 40000, "loss": 0.0, "lr": 3.155057842533063e-06, "epoch": 588.3362831858407, "percentage": 83.84, "elapsed_time": "4:01:36", "remaining_time": "0:46:34", "throughput": 1314.0, "total_tokens": 19048288} {"current_steps": 33540, "total_steps": 40000, "loss": 0.0, "lr": 3.1502853897678984e-06, "epoch": 588.4247787610619, "percentage": 83.85, "elapsed_time": "4:01:38", "remaining_time": "0:46:32", "throughput": 1314.03, "total_tokens": 19051520} {"current_steps": 33545, "total_steps": 40000, "loss": 0.0, "lr": 3.1455163065033017e-06, "epoch": 588.5132743362832, "percentage": 83.86, "elapsed_time": "4:01:40", "remaining_time": "0:46:30", "throughput": 1314.05, "total_tokens": 19054576} {"current_steps": 33550, "total_steps": 40000, "loss": 0.0, "lr": 3.140750593474734e-06, "epoch": 588.6017699115044, "percentage": 83.88, "elapsed_time": "4:01:42", "remaining_time": "0:46:28", "throughput": 1314.07, "total_tokens": 19057552} {"current_steps": 33555, "total_steps": 40000, "loss": 0.0, "lr": 3.1359882514171294e-06, "epoch": 588.6902654867257, "percentage": 83.89, "elapsed_time": "4:01:44", "remaining_time": "0:46:25", "throughput": 1314.08, "total_tokens": 19060400} {"current_steps": 33560, "total_steps": 40000, "loss": 0.0, "lr": 3.1312292810648903e-06, "epoch": 588.7787610619469, "percentage": 83.9, "elapsed_time": "4:01:46", "remaining_time": "0:46:23", "throughput": 1314.06, "total_tokens": 19062864} {"current_steps": 33565, "total_steps": 40000, "loss": 0.0, "lr": 3.1264736831519204e-06, "epoch": 588.8672566371681, "percentage": 83.91, "elapsed_time": "4:01:48", "remaining_time": "0:46:21", "throughput": 1314.08, "total_tokens": 19065840} {"current_steps": 33570, "total_steps": 40000, "loss": 0.0, "lr": 3.1217214584115863e-06, "epoch": 588.9557522123894, "percentage": 83.93, "elapsed_time": "4:01:51", "remaining_time": "0:46:19", "throughput": 1314.06, "total_tokens": 19068432} {"current_steps": 33575, "total_steps": 40000, "loss": 0.0, "lr": 3.116972607576746e-06, "epoch": 589.0353982300885, "percentage": 83.94, "elapsed_time": "4:01:53", "remaining_time": "0:46:17", "throughput": 1314.01, "total_tokens": 19070672} {"current_steps": 33580, "total_steps": 40000, "loss": 0.0, "lr": 3.1122271313797303e-06, "epoch": 589.1238938053098, "percentage": 83.95, "elapsed_time": "4:01:55", "remaining_time": "0:46:15", "throughput": 1314.01, "total_tokens": 19073664} {"current_steps": 33585, "total_steps": 40000, "loss": 0.0, "lr": 3.107485030552343e-06, "epoch": 589.212389380531, "percentage": 83.96, "elapsed_time": "4:01:57", "remaining_time": "0:46:12", "throughput": 1314.01, "total_tokens": 19076400} {"current_steps": 33590, "total_steps": 40000, "loss": 0.0, "lr": 3.1027463058258848e-06, "epoch": 589.3008849557522, "percentage": 83.97, "elapsed_time": "4:01:59", "remaining_time": "0:46:10", "throughput": 1314.01, "total_tokens": 19079264} {"current_steps": 33595, "total_steps": 40000, "loss": 0.0, "lr": 3.0980109579311273e-06, "epoch": 589.3893805309734, "percentage": 83.99, "elapsed_time": "4:02:02", "remaining_time": "0:46:08", "throughput": 1314.0, "total_tokens": 19081904} {"current_steps": 33600, "total_steps": 40000, "loss": 0.0, "lr": 3.093278987598314e-06, "epoch": 589.4778761061947, "percentage": 84.0, "elapsed_time": "4:02:04", "remaining_time": "0:46:06", "throughput": 1314.03, "total_tokens": 19085248} {"current_steps": 33600, "total_steps": 40000, "eval_loss": 0.923610270023346, "epoch": 589.4778761061947, "percentage": 84.0, "elapsed_time": "4:02:05", "remaining_time": "0:46:06", "throughput": 1313.94, "total_tokens": 19085248} {"current_steps": 33605, "total_steps": 40000, "loss": 0.0, "lr": 3.0885503955571826e-06, "epoch": 589.566371681416, "percentage": 84.01, "elapsed_time": "4:02:09", "remaining_time": "0:46:04", "throughput": 1313.77, "total_tokens": 19087968} {"current_steps": 33610, "total_steps": 40000, "loss": 0.0, "lr": 3.0838251825369313e-06, "epoch": 589.6548672566372, "percentage": 84.03, "elapsed_time": "4:02:11", "remaining_time": "0:46:02", "throughput": 1313.77, "total_tokens": 19090672} {"current_steps": 33615, "total_steps": 40000, "loss": 0.0, "lr": 3.0791033492662517e-06, "epoch": 589.7433628318585, "percentage": 84.04, "elapsed_time": "4:02:13", "remaining_time": "0:46:00", "throughput": 1313.77, "total_tokens": 19093360} {"current_steps": 33620, "total_steps": 40000, "loss": 0.0, "lr": 3.0743848964733203e-06, "epoch": 589.8318584070796, "percentage": 84.05, "elapsed_time": "4:02:15", "remaining_time": "0:45:58", "throughput": 1313.8, "total_tokens": 19096592} {"current_steps": 33625, "total_steps": 40000, "loss": 0.0, "lr": 3.0696698248857625e-06, "epoch": 589.9203539823009, "percentage": 84.06, "elapsed_time": "4:02:17", "remaining_time": "0:45:56", "throughput": 1313.84, "total_tokens": 19099872} {"current_steps": 33630, "total_steps": 40000, "loss": 0.0, "lr": 3.0649581352307192e-06, "epoch": 590.0, "percentage": 84.08, "elapsed_time": "4:02:19", "remaining_time": "0:45:53", "throughput": 1313.8, "total_tokens": 19101944} {"current_steps": 33635, "total_steps": 40000, "loss": 0.0, "lr": 3.060249828234776e-06, "epoch": 590.0884955752213, "percentage": 84.09, "elapsed_time": "4:02:21", "remaining_time": "0:45:51", "throughput": 1313.81, "total_tokens": 19105160} {"current_steps": 33640, "total_steps": 40000, "loss": 0.0, "lr": 3.055544904624025e-06, "epoch": 590.1769911504425, "percentage": 84.1, "elapsed_time": "4:02:23", "remaining_time": "0:45:49", "throughput": 1313.83, "total_tokens": 19108088} {"current_steps": 33645, "total_steps": 40000, "loss": 0.0, "lr": 3.050843365124026e-06, "epoch": 590.2654867256637, "percentage": 84.11, "elapsed_time": "4:02:25", "remaining_time": "0:45:47", "throughput": 1313.84, "total_tokens": 19111032} {"current_steps": 33650, "total_steps": 40000, "loss": 0.0, "lr": 3.0461452104598083e-06, "epoch": 590.3539823008849, "percentage": 84.12, "elapsed_time": "4:02:28", "remaining_time": "0:45:45", "throughput": 1313.83, "total_tokens": 19113704} {"current_steps": 33655, "total_steps": 40000, "loss": 0.0, "lr": 3.0414504413558836e-06, "epoch": 590.4424778761062, "percentage": 84.14, "elapsed_time": "4:02:30", "remaining_time": "0:45:43", "throughput": 1313.83, "total_tokens": 19116456} {"current_steps": 33660, "total_steps": 40000, "loss": 0.0, "lr": 3.0367590585362564e-06, "epoch": 590.5309734513274, "percentage": 84.15, "elapsed_time": "4:02:32", "remaining_time": "0:45:40", "throughput": 1313.84, "total_tokens": 19119416} {"current_steps": 33665, "total_steps": 40000, "loss": 0.0, "lr": 3.0320710627243813e-06, "epoch": 590.6194690265487, "percentage": 84.16, "elapsed_time": "4:02:34", "remaining_time": "0:45:38", "throughput": 1313.86, "total_tokens": 19122520} {"current_steps": 33670, "total_steps": 40000, "loss": 0.0, "lr": 3.027386454643222e-06, "epoch": 590.70796460177, "percentage": 84.17, "elapsed_time": "4:02:36", "remaining_time": "0:45:36", "throughput": 1313.85, "total_tokens": 19125240} {"current_steps": 33675, "total_steps": 40000, "loss": 0.0, "lr": 3.0227052350151914e-06, "epoch": 590.7964601769911, "percentage": 84.19, "elapsed_time": "4:02:38", "remaining_time": "0:45:34", "throughput": 1313.84, "total_tokens": 19127912} {"current_steps": 33680, "total_steps": 40000, "loss": 0.0, "lr": 3.0180274045621957e-06, "epoch": 590.8849557522124, "percentage": 84.2, "elapsed_time": "4:02:40", "remaining_time": "0:45:32", "throughput": 1313.84, "total_tokens": 19130696} {"current_steps": 33685, "total_steps": 40000, "loss": 0.0, "lr": 3.013352964005625e-06, "epoch": 590.9734513274336, "percentage": 84.21, "elapsed_time": "4:02:43", "remaining_time": "0:45:30", "throughput": 1313.86, "total_tokens": 19133816} {"current_steps": 33690, "total_steps": 40000, "loss": 0.0, "lr": 3.0086819140663218e-06, "epoch": 591.0530973451328, "percentage": 84.23, "elapsed_time": "4:02:45", "remaining_time": "0:45:28", "throughput": 1313.82, "total_tokens": 19136248} {"current_steps": 33695, "total_steps": 40000, "loss": 0.0, "lr": 3.0040142554646265e-06, "epoch": 591.141592920354, "percentage": 84.24, "elapsed_time": "4:02:47", "remaining_time": "0:45:25", "throughput": 1313.81, "total_tokens": 19138872} {"current_steps": 33700, "total_steps": 40000, "loss": 0.0, "lr": 2.999349988920361e-06, "epoch": 591.2300884955753, "percentage": 84.25, "elapsed_time": "4:02:49", "remaining_time": "0:45:23", "throughput": 1313.81, "total_tokens": 19141784} {"current_steps": 33705, "total_steps": 40000, "loss": 0.0, "lr": 2.994689115152796e-06, "epoch": 591.3185840707964, "percentage": 84.26, "elapsed_time": "4:02:51", "remaining_time": "0:45:21", "throughput": 1313.84, "total_tokens": 19144808} {"current_steps": 33710, "total_steps": 40000, "loss": 0.0, "lr": 2.9900316348807105e-06, "epoch": 591.4070796460177, "percentage": 84.28, "elapsed_time": "4:02:53", "remaining_time": "0:45:19", "throughput": 1313.82, "total_tokens": 19147336} {"current_steps": 33715, "total_steps": 40000, "loss": 0.0, "lr": 2.985377548822338e-06, "epoch": 591.4955752212389, "percentage": 84.29, "elapsed_time": "4:02:55", "remaining_time": "0:45:17", "throughput": 1313.82, "total_tokens": 19149992} {"current_steps": 33720, "total_steps": 40000, "loss": 0.0, "lr": 2.980726857695404e-06, "epoch": 591.5840707964602, "percentage": 84.3, "elapsed_time": "4:02:57", "remaining_time": "0:45:14", "throughput": 1313.84, "total_tokens": 19153048} {"current_steps": 33725, "total_steps": 40000, "loss": 0.0, "lr": 2.9760795622171017e-06, "epoch": 591.6725663716815, "percentage": 84.31, "elapsed_time": "4:02:59", "remaining_time": "0:45:12", "throughput": 1313.86, "total_tokens": 19156120} {"current_steps": 33730, "total_steps": 40000, "loss": 0.0, "lr": 2.971435663104094e-06, "epoch": 591.7610619469026, "percentage": 84.33, "elapsed_time": "4:03:02", "remaining_time": "0:45:10", "throughput": 1313.89, "total_tokens": 19159192} {"current_steps": 33735, "total_steps": 40000, "loss": 0.0, "lr": 2.9667951610725385e-06, "epoch": 591.8495575221239, "percentage": 84.34, "elapsed_time": "4:03:04", "remaining_time": "0:45:08", "throughput": 1313.9, "total_tokens": 19162104} {"current_steps": 33740, "total_steps": 40000, "loss": 0.0, "lr": 2.9621580568380575e-06, "epoch": 591.9380530973451, "percentage": 84.35, "elapsed_time": "4:03:06", "remaining_time": "0:45:06", "throughput": 1313.95, "total_tokens": 19165496} {"current_steps": 33745, "total_steps": 40000, "loss": 0.0, "lr": 2.9575243511157453e-06, "epoch": 592.0176991150443, "percentage": 84.36, "elapsed_time": "4:03:08", "remaining_time": "0:45:04", "throughput": 1313.92, "total_tokens": 19168032} {"current_steps": 33750, "total_steps": 40000, "loss": 0.0, "lr": 2.952894044620186e-06, "epoch": 592.1061946902655, "percentage": 84.38, "elapsed_time": "4:03:10", "remaining_time": "0:45:01", "throughput": 1313.92, "total_tokens": 19170752} {"current_steps": 33755, "total_steps": 40000, "loss": 0.0, "lr": 2.948267138065419e-06, "epoch": 592.1946902654868, "percentage": 84.39, "elapsed_time": "4:03:12", "remaining_time": "0:44:59", "throughput": 1313.93, "total_tokens": 19173712} {"current_steps": 33760, "total_steps": 40000, "loss": 0.0, "lr": 2.943643632164983e-06, "epoch": 592.2831858407079, "percentage": 84.4, "elapsed_time": "4:03:14", "remaining_time": "0:44:57", "throughput": 1313.93, "total_tokens": 19176624} {"current_steps": 33765, "total_steps": 40000, "loss": 0.0, "lr": 2.939023527631879e-06, "epoch": 592.3716814159292, "percentage": 84.41, "elapsed_time": "4:03:16", "remaining_time": "0:44:55", "throughput": 1313.92, "total_tokens": 19179296} {"current_steps": 33770, "total_steps": 40000, "loss": 0.0, "lr": 2.934406825178576e-06, "epoch": 592.4601769911504, "percentage": 84.42, "elapsed_time": "4:03:19", "remaining_time": "0:44:53", "throughput": 1313.92, "total_tokens": 19182064} {"current_steps": 33775, "total_steps": 40000, "loss": 0.0, "lr": 2.9297935255170357e-06, "epoch": 592.5486725663717, "percentage": 84.44, "elapsed_time": "4:03:21", "remaining_time": "0:44:51", "throughput": 1313.92, "total_tokens": 19184848} {"current_steps": 33780, "total_steps": 40000, "loss": 0.0, "lr": 2.925183629358691e-06, "epoch": 592.637168141593, "percentage": 84.45, "elapsed_time": "4:03:23", "remaining_time": "0:44:48", "throughput": 1313.91, "total_tokens": 19187488} {"current_steps": 33785, "total_steps": 40000, "loss": 0.0, "lr": 2.9205771374144346e-06, "epoch": 592.7256637168142, "percentage": 84.46, "elapsed_time": "4:03:25", "remaining_time": "0:44:46", "throughput": 1313.94, "total_tokens": 19190832} {"current_steps": 33790, "total_steps": 40000, "loss": 0.0, "lr": 2.915974050394657e-06, "epoch": 592.8141592920354, "percentage": 84.47, "elapsed_time": "4:03:27", "remaining_time": "0:44:44", "throughput": 1313.93, "total_tokens": 19193536} {"current_steps": 33795, "total_steps": 40000, "loss": 0.0, "lr": 2.9113743690092067e-06, "epoch": 592.9026548672566, "percentage": 84.49, "elapsed_time": "4:03:29", "remaining_time": "0:44:42", "throughput": 1313.92, "total_tokens": 19196176} {"current_steps": 33800, "total_steps": 40000, "loss": 0.0, "lr": 2.906778093967402e-06, "epoch": 592.9911504424779, "percentage": 84.5, "elapsed_time": "4:03:31", "remaining_time": "0:44:40", "throughput": 1313.93, "total_tokens": 19199136} {"current_steps": 33800, "total_steps": 40000, "eval_loss": 0.9060526490211487, "epoch": 592.9911504424779, "percentage": 84.5, "elapsed_time": "4:03:33", "remaining_time": "0:44:40", "throughput": 1313.84, "total_tokens": 19199136} {"current_steps": 33805, "total_steps": 40000, "loss": 0.0, "lr": 2.9021852259780656e-06, "epoch": 593.070796460177, "percentage": 84.51, "elapsed_time": "4:03:37", "remaining_time": "0:44:38", "throughput": 1313.62, "total_tokens": 19201480} {"current_steps": 33810, "total_steps": 40000, "loss": 0.0, "lr": 2.8975957657494583e-06, "epoch": 593.1592920353983, "percentage": 84.52, "elapsed_time": "4:03:39", "remaining_time": "0:44:36", "throughput": 1313.65, "total_tokens": 19204632} {"current_steps": 33815, "total_steps": 40000, "loss": 0.0, "lr": 2.8930097139893417e-06, "epoch": 593.2477876106195, "percentage": 84.54, "elapsed_time": "4:03:41", "remaining_time": "0:44:34", "throughput": 1313.65, "total_tokens": 19207288} {"current_steps": 33820, "total_steps": 40000, "loss": 0.0, "lr": 2.888427071404945e-06, "epoch": 593.3362831858407, "percentage": 84.55, "elapsed_time": "4:03:43", "remaining_time": "0:44:32", "throughput": 1313.65, "total_tokens": 19210072} {"current_steps": 33825, "total_steps": 40000, "loss": 0.0, "lr": 2.8838478387029606e-06, "epoch": 593.4247787610619, "percentage": 84.56, "elapsed_time": "4:03:45", "remaining_time": "0:44:29", "throughput": 1313.64, "total_tokens": 19212712} {"current_steps": 33830, "total_steps": 40000, "loss": 0.0, "lr": 2.8792720165895737e-06, "epoch": 593.5132743362832, "percentage": 84.58, "elapsed_time": "4:03:47", "remaining_time": "0:44:27", "throughput": 1313.67, "total_tokens": 19215864} {"current_steps": 33835, "total_steps": 40000, "loss": 0.0, "lr": 2.874699605770423e-06, "epoch": 593.6017699115044, "percentage": 84.59, "elapsed_time": "4:03:49", "remaining_time": "0:44:25", "throughput": 1313.69, "total_tokens": 19218776} {"current_steps": 33840, "total_steps": 40000, "loss": 0.0, "lr": 2.8701306069506383e-06, "epoch": 593.6902654867257, "percentage": 84.6, "elapsed_time": "4:03:51", "remaining_time": "0:44:23", "throughput": 1313.69, "total_tokens": 19221544} {"current_steps": 33845, "total_steps": 40000, "loss": 0.0, "lr": 2.8655650208348178e-06, "epoch": 593.7787610619469, "percentage": 84.61, "elapsed_time": "4:03:53", "remaining_time": "0:44:21", "throughput": 1313.73, "total_tokens": 19224920} {"current_steps": 33850, "total_steps": 40000, "loss": 0.0, "lr": 2.8610028481270257e-06, "epoch": 593.8672566371681, "percentage": 84.62, "elapsed_time": "4:03:55", "remaining_time": "0:44:19", "throughput": 1313.72, "total_tokens": 19227400} {"current_steps": 33855, "total_steps": 40000, "loss": 0.0, "lr": 2.856444089530813e-06, "epoch": 593.9557522123894, "percentage": 84.64, "elapsed_time": "4:03:57", "remaining_time": "0:44:16", "throughput": 1313.73, "total_tokens": 19230360} {"current_steps": 33860, "total_steps": 40000, "loss": 0.0, "lr": 2.8518887457491955e-06, "epoch": 594.0353982300885, "percentage": 84.65, "elapsed_time": "4:04:00", "remaining_time": "0:44:14", "throughput": 1313.68, "total_tokens": 19232576} {"current_steps": 33865, "total_steps": 40000, "loss": 0.0, "lr": 2.8473368174846666e-06, "epoch": 594.1238938053098, "percentage": 84.66, "elapsed_time": "4:04:02", "remaining_time": "0:44:12", "throughput": 1313.66, "total_tokens": 19235184} {"current_steps": 33870, "total_steps": 40000, "loss": 0.0, "lr": 2.842788305439184e-06, "epoch": 594.212389380531, "percentage": 84.67, "elapsed_time": "4:04:04", "remaining_time": "0:44:10", "throughput": 1313.63, "total_tokens": 19237568} {"current_steps": 33875, "total_steps": 40000, "loss": 0.0, "lr": 2.8382432103141925e-06, "epoch": 594.3008849557522, "percentage": 84.69, "elapsed_time": "4:04:06", "remaining_time": "0:44:08", "throughput": 1313.62, "total_tokens": 19240160} {"current_steps": 33880, "total_steps": 40000, "loss": 0.0, "lr": 2.833701532810598e-06, "epoch": 594.3893805309734, "percentage": 84.7, "elapsed_time": "4:04:08", "remaining_time": "0:44:06", "throughput": 1313.62, "total_tokens": 19242960} {"current_steps": 33885, "total_steps": 40000, "loss": 0.0, "lr": 2.8291632736287877e-06, "epoch": 594.4778761061947, "percentage": 84.71, "elapsed_time": "4:04:10", "remaining_time": "0:44:03", "throughput": 1313.62, "total_tokens": 19245824} {"current_steps": 33890, "total_steps": 40000, "loss": 0.0, "lr": 2.824628433468615e-06, "epoch": 594.566371681416, "percentage": 84.72, "elapsed_time": "4:04:13", "remaining_time": "0:44:01", "throughput": 1313.61, "total_tokens": 19248544} {"current_steps": 33895, "total_steps": 40000, "loss": 0.0, "lr": 2.8200970130294073e-06, "epoch": 594.6548672566372, "percentage": 84.74, "elapsed_time": "4:04:15", "remaining_time": "0:43:59", "throughput": 1313.67, "total_tokens": 19252112} {"current_steps": 33900, "total_steps": 40000, "loss": 0.0, "lr": 2.8155690130099775e-06, "epoch": 594.7433628318585, "percentage": 84.75, "elapsed_time": "4:04:17", "remaining_time": "0:43:57", "throughput": 1313.7, "total_tokens": 19255504} {"current_steps": 33905, "total_steps": 40000, "loss": 0.0, "lr": 2.8110444341085895e-06, "epoch": 594.8318584070796, "percentage": 84.76, "elapsed_time": "4:04:19", "remaining_time": "0:43:55", "throughput": 1313.71, "total_tokens": 19258432} {"current_steps": 33910, "total_steps": 40000, "loss": 0.0, "lr": 2.806523277022996e-06, "epoch": 594.9203539823009, "percentage": 84.78, "elapsed_time": "4:04:21", "remaining_time": "0:43:53", "throughput": 1313.76, "total_tokens": 19262000} {"current_steps": 33915, "total_steps": 40000, "loss": 0.0, "lr": 2.802005542450409e-06, "epoch": 595.0, "percentage": 84.79, "elapsed_time": "4:04:23", "remaining_time": "0:43:50", "throughput": 1313.73, "total_tokens": 19264208} {"current_steps": 33920, "total_steps": 40000, "loss": 0.0, "lr": 2.797491231087526e-06, "epoch": 595.0884955752213, "percentage": 84.8, "elapsed_time": "4:04:26", "remaining_time": "0:43:48", "throughput": 1313.69, "total_tokens": 19266768} {"current_steps": 33925, "total_steps": 40000, "loss": 0.0, "lr": 2.7929803436305137e-06, "epoch": 595.1769911504425, "percentage": 84.81, "elapsed_time": "4:04:28", "remaining_time": "0:43:46", "throughput": 1313.69, "total_tokens": 19269536} {"current_steps": 33930, "total_steps": 40000, "loss": 0.0, "lr": 2.788472880774998e-06, "epoch": 595.2654867256637, "percentage": 84.82, "elapsed_time": "4:04:30", "remaining_time": "0:43:44", "throughput": 1313.7, "total_tokens": 19272336} {"current_steps": 33935, "total_steps": 40000, "loss": 0.0, "lr": 2.7839688432160977e-06, "epoch": 595.3539823008849, "percentage": 84.84, "elapsed_time": "4:04:32", "remaining_time": "0:43:42", "throughput": 1313.71, "total_tokens": 19275168} {"current_steps": 33940, "total_steps": 40000, "loss": 0.0, "lr": 2.779468231648383e-06, "epoch": 595.4424778761062, "percentage": 84.85, "elapsed_time": "4:04:34", "remaining_time": "0:43:40", "throughput": 1313.72, "total_tokens": 19278048} {"current_steps": 33945, "total_steps": 40000, "loss": 0.0, "lr": 2.774971046765906e-06, "epoch": 595.5309734513274, "percentage": 84.86, "elapsed_time": "4:04:36", "remaining_time": "0:43:37", "throughput": 1313.72, "total_tokens": 19280864} {"current_steps": 33950, "total_steps": 40000, "loss": 0.0, "lr": 2.770477289262194e-06, "epoch": 595.6194690265487, "percentage": 84.88, "elapsed_time": "4:04:38", "remaining_time": "0:43:35", "throughput": 1313.74, "total_tokens": 19283920} {"current_steps": 33955, "total_steps": 40000, "loss": 0.0, "lr": 2.765986959830233e-06, "epoch": 595.70796460177, "percentage": 84.89, "elapsed_time": "4:04:40", "remaining_time": "0:43:33", "throughput": 1313.77, "total_tokens": 19287024} {"current_steps": 33960, "total_steps": 40000, "loss": 0.0, "lr": 2.761500059162492e-06, "epoch": 595.7964601769911, "percentage": 84.9, "elapsed_time": "4:04:42", "remaining_time": "0:43:31", "throughput": 1313.76, "total_tokens": 19289616} {"current_steps": 33965, "total_steps": 40000, "loss": 0.0, "lr": 2.757016587950914e-06, "epoch": 595.8849557522124, "percentage": 84.91, "elapsed_time": "4:04:44", "remaining_time": "0:43:29", "throughput": 1313.78, "total_tokens": 19292528} {"current_steps": 33970, "total_steps": 40000, "loss": 0.0, "lr": 2.752536546886897e-06, "epoch": 595.9734513274336, "percentage": 84.92, "elapsed_time": "4:04:46", "remaining_time": "0:43:27", "throughput": 1313.8, "total_tokens": 19295648} {"current_steps": 33975, "total_steps": 40000, "loss": 0.0, "lr": 2.7480599366613234e-06, "epoch": 596.0530973451328, "percentage": 84.94, "elapsed_time": "4:04:49", "remaining_time": "0:43:24", "throughput": 1313.76, "total_tokens": 19297952} {"current_steps": 33980, "total_steps": 40000, "loss": 0.0, "lr": 2.7435867579645473e-06, "epoch": 596.141592920354, "percentage": 84.95, "elapsed_time": "4:04:51", "remaining_time": "0:43:22", "throughput": 1313.76, "total_tokens": 19300784} {"current_steps": 33985, "total_steps": 40000, "loss": 0.0, "lr": 2.739117011486378e-06, "epoch": 596.2300884955753, "percentage": 84.96, "elapsed_time": "4:04:53", "remaining_time": "0:43:20", "throughput": 1313.75, "total_tokens": 19303312} {"current_steps": 33990, "total_steps": 40000, "loss": 0.0, "lr": 2.7346506979161216e-06, "epoch": 596.3185840707964, "percentage": 84.97, "elapsed_time": "4:04:55", "remaining_time": "0:43:18", "throughput": 1313.77, "total_tokens": 19306544} {"current_steps": 33995, "total_steps": 40000, "loss": 0.0, "lr": 2.7301878179425227e-06, "epoch": 596.4070796460177, "percentage": 84.99, "elapsed_time": "4:04:57", "remaining_time": "0:43:16", "throughput": 1313.74, "total_tokens": 19308912} {"current_steps": 34000, "total_steps": 40000, "loss": 0.0, "lr": 2.7257283722538244e-06, "epoch": 596.4955752212389, "percentage": 85.0, "elapsed_time": "4:04:59", "remaining_time": "0:43:14", "throughput": 1313.71, "total_tokens": 19311344} {"current_steps": 34000, "total_steps": 40000, "eval_loss": 0.8945153951644897, "epoch": 596.4955752212389, "percentage": 85.0, "elapsed_time": "4:05:00", "remaining_time": "0:43:14", "throughput": 1313.62, "total_tokens": 19311344} {"current_steps": 34005, "total_steps": 40000, "loss": 0.0, "lr": 2.7212723615377326e-06, "epoch": 596.5840707964602, "percentage": 85.01, "elapsed_time": "4:05:04", "remaining_time": "0:43:12", "throughput": 1313.44, "total_tokens": 19313920} {"current_steps": 34010, "total_steps": 40000, "loss": 0.0, "lr": 2.7168197864814145e-06, "epoch": 596.6725663716815, "percentage": 85.02, "elapsed_time": "4:05:06", "remaining_time": "0:43:10", "throughput": 1313.49, "total_tokens": 19317408} {"current_steps": 34015, "total_steps": 40000, "loss": 0.0, "lr": 2.712370647771509e-06, "epoch": 596.7610619469026, "percentage": 85.04, "elapsed_time": "4:05:09", "remaining_time": "0:43:08", "throughput": 1313.5, "total_tokens": 19320352} {"current_steps": 34020, "total_steps": 40000, "loss": 0.0, "lr": 2.707924946094137e-06, "epoch": 596.8495575221239, "percentage": 85.05, "elapsed_time": "4:05:11", "remaining_time": "0:43:05", "throughput": 1313.51, "total_tokens": 19323360} {"current_steps": 34025, "total_steps": 40000, "loss": 0.0, "lr": 2.7034826821348723e-06, "epoch": 596.9380530973451, "percentage": 85.06, "elapsed_time": "4:05:13", "remaining_time": "0:43:03", "throughput": 1313.54, "total_tokens": 19326640} {"current_steps": 34030, "total_steps": 40000, "loss": 0.0, "lr": 2.6990438565787786e-06, "epoch": 597.0176991150443, "percentage": 85.08, "elapsed_time": "4:05:15", "remaining_time": "0:43:01", "throughput": 1313.49, "total_tokens": 19328992} {"current_steps": 34035, "total_steps": 40000, "loss": 0.0, "lr": 2.6946084701103714e-06, "epoch": 597.1061946902655, "percentage": 85.09, "elapsed_time": "4:05:17", "remaining_time": "0:42:59", "throughput": 1313.48, "total_tokens": 19331680} {"current_steps": 34040, "total_steps": 40000, "loss": 0.0, "lr": 2.6901765234136428e-06, "epoch": 597.1946902654868, "percentage": 85.1, "elapsed_time": "4:05:20", "remaining_time": "0:42:57", "throughput": 1313.47, "total_tokens": 19334352} {"current_steps": 34045, "total_steps": 40000, "loss": 0.0, "lr": 2.685748017172063e-06, "epoch": 597.2831858407079, "percentage": 85.11, "elapsed_time": "4:05:22", "remaining_time": "0:42:55", "throughput": 1313.5, "total_tokens": 19337600} {"current_steps": 34050, "total_steps": 40000, "loss": 0.0, "lr": 2.681322952068549e-06, "epoch": 597.3716814159292, "percentage": 85.12, "elapsed_time": "4:05:24", "remaining_time": "0:42:52", "throughput": 1313.5, "total_tokens": 19340288} {"current_steps": 34055, "total_steps": 40000, "loss": 0.0, "lr": 2.6769013287855137e-06, "epoch": 597.4601769911504, "percentage": 85.14, "elapsed_time": "4:05:26", "remaining_time": "0:42:50", "throughput": 1313.54, "total_tokens": 19343552} {"current_steps": 34060, "total_steps": 40000, "loss": 0.0, "lr": 2.6724831480048286e-06, "epoch": 597.5486725663717, "percentage": 85.15, "elapsed_time": "4:05:28", "remaining_time": "0:42:48", "throughput": 1313.53, "total_tokens": 19346272} {"current_steps": 34065, "total_steps": 40000, "loss": 0.0, "lr": 2.66806841040782e-06, "epoch": 597.637168141593, "percentage": 85.16, "elapsed_time": "4:05:30", "remaining_time": "0:42:46", "throughput": 1313.54, "total_tokens": 19349104} {"current_steps": 34070, "total_steps": 40000, "loss": 0.0, "lr": 2.6636571166753083e-06, "epoch": 597.7256637168142, "percentage": 85.17, "elapsed_time": "4:05:32", "remaining_time": "0:42:44", "throughput": 1313.56, "total_tokens": 19352032} {"current_steps": 34075, "total_steps": 40000, "loss": 0.0, "lr": 2.6592492674875598e-06, "epoch": 597.8141592920354, "percentage": 85.19, "elapsed_time": "4:05:34", "remaining_time": "0:42:42", "throughput": 1313.55, "total_tokens": 19354688} {"current_steps": 34080, "total_steps": 40000, "loss": 0.0, "lr": 2.6548448635243305e-06, "epoch": 597.9026548672566, "percentage": 85.2, "elapsed_time": "4:05:36", "remaining_time": "0:42:39", "throughput": 1313.55, "total_tokens": 19357392} {"current_steps": 34085, "total_steps": 40000, "loss": 0.0, "lr": 2.650443905464828e-06, "epoch": 597.9911504424779, "percentage": 85.21, "elapsed_time": "4:05:38", "remaining_time": "0:42:37", "throughput": 1313.58, "total_tokens": 19360480} {"current_steps": 34090, "total_steps": 40000, "loss": 0.0, "lr": 2.646046393987739e-06, "epoch": 598.070796460177, "percentage": 85.22, "elapsed_time": "4:05:41", "remaining_time": "0:42:35", "throughput": 1313.52, "total_tokens": 19362624} {"current_steps": 34095, "total_steps": 40000, "loss": 0.0, "lr": 2.64165232977121e-06, "epoch": 598.1592920353983, "percentage": 85.24, "elapsed_time": "4:05:43", "remaining_time": "0:42:33", "throughput": 1313.51, "total_tokens": 19365200} {"current_steps": 34100, "total_steps": 40000, "loss": 0.0, "lr": 2.6372617134928695e-06, "epoch": 598.2477876106195, "percentage": 85.25, "elapsed_time": "4:05:45", "remaining_time": "0:42:31", "throughput": 1313.56, "total_tokens": 19368704} {"current_steps": 34105, "total_steps": 40000, "loss": 0.0, "lr": 2.6328745458297943e-06, "epoch": 598.3362831858407, "percentage": 85.26, "elapsed_time": "4:05:47", "remaining_time": "0:42:29", "throughput": 1313.57, "total_tokens": 19371456} {"current_steps": 34110, "total_steps": 40000, "loss": 0.0, "lr": 2.6284908274585546e-06, "epoch": 598.4247787610619, "percentage": 85.28, "elapsed_time": "4:05:49", "remaining_time": "0:42:26", "throughput": 1313.6, "total_tokens": 19374720} {"current_steps": 34115, "total_steps": 40000, "loss": 0.0, "lr": 2.6241105590551595e-06, "epoch": 598.5132743362832, "percentage": 85.29, "elapsed_time": "4:05:51", "remaining_time": "0:42:24", "throughput": 1313.62, "total_tokens": 19377728} {"current_steps": 34120, "total_steps": 40000, "loss": 0.0, "lr": 2.6197337412951105e-06, "epoch": 598.6017699115044, "percentage": 85.3, "elapsed_time": "4:05:53", "remaining_time": "0:42:22", "throughput": 1313.64, "total_tokens": 19380768} {"current_steps": 34125, "total_steps": 40000, "loss": 0.0, "lr": 2.6153603748533705e-06, "epoch": 598.6902654867257, "percentage": 85.31, "elapsed_time": "4:05:55", "remaining_time": "0:42:20", "throughput": 1313.62, "total_tokens": 19383360} {"current_steps": 34130, "total_steps": 40000, "loss": 0.0, "lr": 2.6109904604043585e-06, "epoch": 598.7787610619469, "percentage": 85.32, "elapsed_time": "4:05:57", "remaining_time": "0:42:18", "throughput": 1313.63, "total_tokens": 19386320} {"current_steps": 34135, "total_steps": 40000, "loss": 0.0, "lr": 2.6066239986219765e-06, "epoch": 598.8672566371681, "percentage": 85.34, "elapsed_time": "4:05:59", "remaining_time": "0:42:16", "throughput": 1313.64, "total_tokens": 19389280} {"current_steps": 34140, "total_steps": 40000, "loss": 0.0, "lr": 2.602260990179592e-06, "epoch": 598.9557522123894, "percentage": 85.35, "elapsed_time": "4:06:02", "remaining_time": "0:42:13", "throughput": 1313.64, "total_tokens": 19392048} {"current_steps": 34145, "total_steps": 40000, "loss": 0.0, "lr": 2.5979014357500248e-06, "epoch": 599.0353982300885, "percentage": 85.36, "elapsed_time": "4:06:04", "remaining_time": "0:42:11", "throughput": 1313.58, "total_tokens": 19394200} {"current_steps": 34150, "total_steps": 40000, "loss": 0.0, "lr": 2.5935453360055844e-06, "epoch": 599.1238938053098, "percentage": 85.38, "elapsed_time": "4:06:06", "remaining_time": "0:42:09", "throughput": 1313.57, "total_tokens": 19396904} {"current_steps": 34155, "total_steps": 40000, "loss": 0.0, "lr": 2.5891926916180283e-06, "epoch": 599.212389380531, "percentage": 85.39, "elapsed_time": "4:06:08", "remaining_time": "0:42:07", "throughput": 1313.57, "total_tokens": 19399688} {"current_steps": 34160, "total_steps": 40000, "loss": 0.0, "lr": 2.5848435032585883e-06, "epoch": 599.3008849557522, "percentage": 85.4, "elapsed_time": "4:06:10", "remaining_time": "0:42:05", "throughput": 1313.57, "total_tokens": 19402568} {"current_steps": 34165, "total_steps": 40000, "loss": 0.0, "lr": 2.58049777159797e-06, "epoch": 599.3893805309734, "percentage": 85.41, "elapsed_time": "4:06:12", "remaining_time": "0:42:03", "throughput": 1313.57, "total_tokens": 19405336} {"current_steps": 34170, "total_steps": 40000, "loss": 0.0, "lr": 2.576155497306332e-06, "epoch": 599.4778761061947, "percentage": 85.42, "elapsed_time": "4:06:15", "remaining_time": "0:42:00", "throughput": 1313.57, "total_tokens": 19408136} {"current_steps": 34175, "total_steps": 40000, "loss": 0.0, "lr": 2.57181668105331e-06, "epoch": 599.566371681416, "percentage": 85.44, "elapsed_time": "4:06:17", "remaining_time": "0:41:58", "throughput": 1313.56, "total_tokens": 19410840} {"current_steps": 34180, "total_steps": 40000, "loss": 0.0, "lr": 2.567481323508014e-06, "epoch": 599.6548672566372, "percentage": 85.45, "elapsed_time": "4:06:19", "remaining_time": "0:41:56", "throughput": 1313.56, "total_tokens": 19413720} {"current_steps": 34185, "total_steps": 40000, "loss": 0.0, "lr": 2.5631494253389954e-06, "epoch": 599.7433628318585, "percentage": 85.46, "elapsed_time": "4:06:21", "remaining_time": "0:41:54", "throughput": 1313.59, "total_tokens": 19416952} {"current_steps": 34190, "total_steps": 40000, "loss": 0.0, "lr": 2.5588209872142997e-06, "epoch": 599.8318584070796, "percentage": 85.47, "elapsed_time": "4:06:23", "remaining_time": "0:41:52", "throughput": 1313.6, "total_tokens": 19419912} {"current_steps": 34195, "total_steps": 40000, "loss": 0.0, "lr": 2.5544960098014186e-06, "epoch": 599.9203539823009, "percentage": 85.49, "elapsed_time": "4:06:25", "remaining_time": "0:41:50", "throughput": 1313.62, "total_tokens": 19423032} {"current_steps": 34200, "total_steps": 40000, "loss": 0.0, "lr": 2.550174493767318e-06, "epoch": 600.0, "percentage": 85.5, "elapsed_time": "4:06:27", "remaining_time": "0:41:47", "throughput": 1313.61, "total_tokens": 19425472} {"current_steps": 34200, "total_steps": 40000, "eval_loss": 0.897942304611206, "epoch": 600.0, "percentage": 85.5, "elapsed_time": "4:06:28", "remaining_time": "0:41:48", "throughput": 1313.52, "total_tokens": 19425472} {"current_steps": 34205, "total_steps": 40000, "loss": 0.0, "lr": 2.545856439778438e-06, "epoch": 600.0884955752213, "percentage": 85.51, "elapsed_time": "4:06:33", "remaining_time": "0:41:46", "throughput": 1313.38, "total_tokens": 19428848} {"current_steps": 34210, "total_steps": 40000, "loss": 0.0, "lr": 2.541541848500667e-06, "epoch": 600.1769911504425, "percentage": 85.52, "elapsed_time": "4:06:35", "remaining_time": "0:41:44", "throughput": 1313.41, "total_tokens": 19432096} {"current_steps": 34215, "total_steps": 40000, "loss": 0.0, "lr": 2.5372307205993733e-06, "epoch": 600.2654867256637, "percentage": 85.54, "elapsed_time": "4:06:37", "remaining_time": "0:41:41", "throughput": 1313.4, "total_tokens": 19434656} {"current_steps": 34220, "total_steps": 40000, "loss": 0.0, "lr": 2.5329230567393917e-06, "epoch": 600.3539823008849, "percentage": 85.55, "elapsed_time": "4:06:39", "remaining_time": "0:41:39", "throughput": 1313.37, "total_tokens": 19437280} {"current_steps": 34225, "total_steps": 40000, "loss": 0.0, "lr": 2.5286188575850164e-06, "epoch": 600.4424778761062, "percentage": 85.56, "elapsed_time": "4:06:41", "remaining_time": "0:41:37", "throughput": 1313.43, "total_tokens": 19440832} {"current_steps": 34230, "total_steps": 40000, "loss": 0.0, "lr": 2.5243181237999984e-06, "epoch": 600.5309734513274, "percentage": 85.58, "elapsed_time": "4:06:43", "remaining_time": "0:41:35", "throughput": 1313.44, "total_tokens": 19443712} {"current_steps": 34235, "total_steps": 40000, "loss": 0.0, "lr": 2.520020856047578e-06, "epoch": 600.6194690265487, "percentage": 85.59, "elapsed_time": "4:06:45", "remaining_time": "0:41:33", "throughput": 1313.45, "total_tokens": 19446624} {"current_steps": 34240, "total_steps": 40000, "loss": 0.0, "lr": 2.515727054990438e-06, "epoch": 600.70796460177, "percentage": 85.6, "elapsed_time": "4:06:47", "remaining_time": "0:41:31", "throughput": 1313.46, "total_tokens": 19449424} {"current_steps": 34245, "total_steps": 40000, "loss": 0.0, "lr": 2.511436721290747e-06, "epoch": 600.7964601769911, "percentage": 85.61, "elapsed_time": "4:06:49", "remaining_time": "0:41:28", "throughput": 1313.46, "total_tokens": 19452176} {"current_steps": 34250, "total_steps": 40000, "loss": 0.0, "lr": 2.5071498556101164e-06, "epoch": 600.8849557522124, "percentage": 85.62, "elapsed_time": "4:06:51", "remaining_time": "0:41:26", "throughput": 1313.43, "total_tokens": 19454512} {"current_steps": 34255, "total_steps": 40000, "loss": 0.0, "lr": 2.5028664586096485e-06, "epoch": 600.9734513274336, "percentage": 85.64, "elapsed_time": "4:06:53", "remaining_time": "0:41:24", "throughput": 1313.44, "total_tokens": 19457248} {"current_steps": 34260, "total_steps": 40000, "loss": 0.0, "lr": 2.498586530949881e-06, "epoch": 601.0530973451328, "percentage": 85.65, "elapsed_time": "4:06:56", "remaining_time": "0:41:22", "throughput": 1313.39, "total_tokens": 19459592} {"current_steps": 34265, "total_steps": 40000, "loss": 0.0, "lr": 2.4943100732908427e-06, "epoch": 601.141592920354, "percentage": 85.66, "elapsed_time": "4:06:58", "remaining_time": "0:41:20", "throughput": 1313.39, "total_tokens": 19462248} {"current_steps": 34270, "total_steps": 40000, "loss": 0.0, "lr": 2.4900370862920188e-06, "epoch": 601.2300884955753, "percentage": 85.67, "elapsed_time": "4:07:00", "remaining_time": "0:41:17", "throughput": 1313.41, "total_tokens": 19465224} {"current_steps": 34275, "total_steps": 40000, "loss": 0.0, "lr": 2.4857675706123518e-06, "epoch": 601.3185840707964, "percentage": 85.69, "elapsed_time": "4:07:02", "remaining_time": "0:41:15", "throughput": 1313.41, "total_tokens": 19468040} {"current_steps": 34280, "total_steps": 40000, "loss": 0.0, "lr": 2.4815015269102543e-06, "epoch": 601.4070796460177, "percentage": 85.7, "elapsed_time": "4:07:04", "remaining_time": "0:41:13", "throughput": 1313.42, "total_tokens": 19470920} {"current_steps": 34285, "total_steps": 40000, "loss": 0.0, "lr": 2.477238955843611e-06, "epoch": 601.4955752212389, "percentage": 85.71, "elapsed_time": "4:07:06", "remaining_time": "0:41:11", "throughput": 1313.43, "total_tokens": 19473928} {"current_steps": 34290, "total_steps": 40000, "loss": 0.0, "lr": 2.4729798580697573e-06, "epoch": 601.5840707964602, "percentage": 85.72, "elapsed_time": "4:07:08", "remaining_time": "0:41:09", "throughput": 1313.48, "total_tokens": 19477480} {"current_steps": 34295, "total_steps": 40000, "loss": 0.0, "lr": 2.4687242342455034e-06, "epoch": 601.6725663716815, "percentage": 85.74, "elapsed_time": "4:07:11", "remaining_time": "0:41:07", "throughput": 1313.45, "total_tokens": 19479848} {"current_steps": 34300, "total_steps": 40000, "loss": 0.0, "lr": 2.4644720850271196e-06, "epoch": 601.7610619469026, "percentage": 85.75, "elapsed_time": "4:07:13", "remaining_time": "0:41:04", "throughput": 1313.45, "total_tokens": 19482648} {"current_steps": 34305, "total_steps": 40000, "loss": 0.0, "lr": 2.4602234110703364e-06, "epoch": 601.8495575221239, "percentage": 85.76, "elapsed_time": "4:07:15", "remaining_time": "0:41:02", "throughput": 1313.45, "total_tokens": 19485432} {"current_steps": 34310, "total_steps": 40000, "loss": 0.0, "lr": 2.4559782130303576e-06, "epoch": 601.9380530973451, "percentage": 85.78, "elapsed_time": "4:07:17", "remaining_time": "0:41:00", "throughput": 1313.46, "total_tokens": 19488392} {"current_steps": 34315, "total_steps": 40000, "loss": 0.0, "lr": 2.451736491561843e-06, "epoch": 602.0176991150443, "percentage": 85.79, "elapsed_time": "4:07:19", "remaining_time": "0:40:58", "throughput": 1313.42, "total_tokens": 19490824} {"current_steps": 34320, "total_steps": 40000, "loss": 0.0, "lr": 2.4474982473189163e-06, "epoch": 602.1061946902655, "percentage": 85.8, "elapsed_time": "4:07:21", "remaining_time": "0:40:56", "throughput": 1313.4, "total_tokens": 19493352} {"current_steps": 34325, "total_steps": 40000, "loss": 0.0, "lr": 2.4432634809551796e-06, "epoch": 602.1946902654868, "percentage": 85.81, "elapsed_time": "4:07:24", "remaining_time": "0:40:54", "throughput": 1313.41, "total_tokens": 19496392} {"current_steps": 34330, "total_steps": 40000, "loss": 0.0, "lr": 2.439032193123675e-06, "epoch": 602.2831858407079, "percentage": 85.82, "elapsed_time": "4:07:26", "remaining_time": "0:40:52", "throughput": 1313.41, "total_tokens": 19499208} {"current_steps": 34335, "total_steps": 40000, "loss": 0.0, "lr": 2.4348043844769297e-06, "epoch": 602.3716814159292, "percentage": 85.84, "elapsed_time": "4:07:28", "remaining_time": "0:40:49", "throughput": 1313.41, "total_tokens": 19502056} {"current_steps": 34340, "total_steps": 40000, "loss": 0.0, "lr": 2.4305800556669146e-06, "epoch": 602.4601769911504, "percentage": 85.85, "elapsed_time": "4:07:30", "remaining_time": "0:40:47", "throughput": 1313.39, "total_tokens": 19504536} {"current_steps": 34345, "total_steps": 40000, "loss": 0.0, "lr": 2.426359207345083e-06, "epoch": 602.5486725663717, "percentage": 85.86, "elapsed_time": "4:07:32", "remaining_time": "0:40:45", "throughput": 1313.38, "total_tokens": 19507144} {"current_steps": 34350, "total_steps": 40000, "loss": 0.0, "lr": 2.4221418401623396e-06, "epoch": 602.637168141593, "percentage": 85.88, "elapsed_time": "4:07:34", "remaining_time": "0:40:43", "throughput": 1313.4, "total_tokens": 19510280} {"current_steps": 34355, "total_steps": 40000, "loss": 0.0, "lr": 2.4179279547690557e-06, "epoch": 602.7256637168142, "percentage": 85.89, "elapsed_time": "4:07:36", "remaining_time": "0:40:41", "throughput": 1313.41, "total_tokens": 19513240} {"current_steps": 34360, "total_steps": 40000, "loss": 0.0, "lr": 2.413717551815062e-06, "epoch": 602.8141592920354, "percentage": 85.9, "elapsed_time": "4:07:39", "remaining_time": "0:40:39", "throughput": 1313.42, "total_tokens": 19516184} {"current_steps": 34365, "total_steps": 40000, "loss": 0.0, "lr": 2.409510631949666e-06, "epoch": 602.9026548672566, "percentage": 85.91, "elapsed_time": "4:07:41", "remaining_time": "0:40:36", "throughput": 1313.46, "total_tokens": 19519640} {"current_steps": 34370, "total_steps": 40000, "loss": 0.0, "lr": 2.405307195821618e-06, "epoch": 602.9911504424779, "percentage": 85.92, "elapsed_time": "4:07:43", "remaining_time": "0:40:34", "throughput": 1313.44, "total_tokens": 19522104} {"current_steps": 34375, "total_steps": 40000, "loss": 0.0, "lr": 2.4011072440791372e-06, "epoch": 603.070796460177, "percentage": 85.94, "elapsed_time": "4:07:45", "remaining_time": "0:40:32", "throughput": 1313.38, "total_tokens": 19524120} {"current_steps": 34380, "total_steps": 40000, "loss": 0.0, "lr": 2.3969107773699233e-06, "epoch": 603.1592920353983, "percentage": 85.95, "elapsed_time": "4:07:47", "remaining_time": "0:40:30", "throughput": 1313.38, "total_tokens": 19526824} {"current_steps": 34385, "total_steps": 40000, "loss": 0.0, "lr": 2.3927177963411096e-06, "epoch": 603.2477876106195, "percentage": 85.96, "elapsed_time": "4:07:49", "remaining_time": "0:40:28", "throughput": 1313.4, "total_tokens": 19529816} {"current_steps": 34390, "total_steps": 40000, "loss": 0.0, "lr": 2.3885283016393144e-06, "epoch": 603.3362831858407, "percentage": 85.97, "elapsed_time": "4:07:51", "remaining_time": "0:40:26", "throughput": 1313.42, "total_tokens": 19532840} {"current_steps": 34395, "total_steps": 40000, "loss": 0.0, "lr": 2.3843422939106076e-06, "epoch": 603.4247787610619, "percentage": 85.99, "elapsed_time": "4:07:53", "remaining_time": "0:40:23", "throughput": 1313.45, "total_tokens": 19536040} {"current_steps": 34400, "total_steps": 40000, "loss": 0.0, "lr": 2.380159773800525e-06, "epoch": 603.5132743362832, "percentage": 86.0, "elapsed_time": "4:07:55", "remaining_time": "0:40:21", "throughput": 1313.47, "total_tokens": 19539112} {"current_steps": 34400, "total_steps": 40000, "eval_loss": 0.9249515533447266, "epoch": 603.5132743362832, "percentage": 86.0, "elapsed_time": "4:07:57", "remaining_time": "0:40:21", "throughput": 1313.38, "total_tokens": 19539112} {"current_steps": 34405, "total_steps": 40000, "loss": 0.0, "lr": 2.3759807419540675e-06, "epoch": 603.6017699115044, "percentage": 86.01, "elapsed_time": "4:08:00", "remaining_time": "0:40:19", "throughput": 1313.23, "total_tokens": 19541960} {"current_steps": 34410, "total_steps": 40000, "loss": 0.0, "lr": 2.3718051990156835e-06, "epoch": 603.6902654867257, "percentage": 86.02, "elapsed_time": "4:08:02", "remaining_time": "0:40:17", "throughput": 1313.22, "total_tokens": 19544568} {"current_steps": 34415, "total_steps": 40000, "loss": 0.0, "lr": 2.367633145629311e-06, "epoch": 603.7787610619469, "percentage": 86.04, "elapsed_time": "4:08:05", "remaining_time": "0:40:15", "throughput": 1313.22, "total_tokens": 19547272} {"current_steps": 34420, "total_steps": 40000, "loss": 0.0, "lr": 2.363464582438316e-06, "epoch": 603.8672566371681, "percentage": 86.05, "elapsed_time": "4:08:07", "remaining_time": "0:40:13", "throughput": 1313.24, "total_tokens": 19550296} {"current_steps": 34425, "total_steps": 40000, "loss": 0.0, "lr": 2.3592995100855526e-06, "epoch": 603.9557522123894, "percentage": 86.06, "elapsed_time": "4:08:09", "remaining_time": "0:40:11", "throughput": 1313.26, "total_tokens": 19553336} {"current_steps": 34430, "total_steps": 40000, "loss": 0.0, "lr": 2.3551379292133273e-06, "epoch": 604.0353982300885, "percentage": 86.08, "elapsed_time": "4:08:11", "remaining_time": "0:40:09", "throughput": 1313.24, "total_tokens": 19555984} {"current_steps": 34435, "total_steps": 40000, "loss": 0.0, "lr": 2.3509798404634047e-06, "epoch": 604.1238938053098, "percentage": 86.09, "elapsed_time": "4:08:13", "remaining_time": "0:40:06", "throughput": 1313.26, "total_tokens": 19559088} {"current_steps": 34440, "total_steps": 40000, "loss": 0.0, "lr": 2.346825244477019e-06, "epoch": 604.212389380531, "percentage": 86.1, "elapsed_time": "4:08:15", "remaining_time": "0:40:04", "throughput": 1313.3, "total_tokens": 19562400} {"current_steps": 34445, "total_steps": 40000, "loss": 0.0, "lr": 2.3426741418948545e-06, "epoch": 604.3008849557522, "percentage": 86.11, "elapsed_time": "4:08:17", "remaining_time": "0:40:02", "throughput": 1313.3, "total_tokens": 19565104} {"current_steps": 34450, "total_steps": 40000, "loss": 0.0, "lr": 2.3385265333570715e-06, "epoch": 604.3893805309734, "percentage": 86.12, "elapsed_time": "4:08:19", "remaining_time": "0:40:00", "throughput": 1313.28, "total_tokens": 19567440} {"current_steps": 34455, "total_steps": 40000, "loss": 0.0, "lr": 2.334382419503278e-06, "epoch": 604.4778761061947, "percentage": 86.14, "elapsed_time": "4:08:21", "remaining_time": "0:39:58", "throughput": 1313.28, "total_tokens": 19570256} {"current_steps": 34460, "total_steps": 40000, "loss": 0.0, "lr": 2.3302418009725465e-06, "epoch": 604.566371681416, "percentage": 86.15, "elapsed_time": "4:08:23", "remaining_time": "0:39:56", "throughput": 1313.28, "total_tokens": 19572928} {"current_steps": 34465, "total_steps": 40000, "loss": 0.0, "lr": 2.326104678403415e-06, "epoch": 604.6548672566372, "percentage": 86.16, "elapsed_time": "4:08:25", "remaining_time": "0:39:53", "throughput": 1313.3, "total_tokens": 19575920} {"current_steps": 34470, "total_steps": 40000, "loss": 0.0, "lr": 2.321971052433883e-06, "epoch": 604.7433628318585, "percentage": 86.17, "elapsed_time": "4:08:28", "remaining_time": "0:39:51", "throughput": 1313.35, "total_tokens": 19579440} {"current_steps": 34475, "total_steps": 40000, "loss": 0.0, "lr": 2.3178409237014004e-06, "epoch": 604.8318584070796, "percentage": 86.19, "elapsed_time": "4:08:30", "remaining_time": "0:39:49", "throughput": 1313.33, "total_tokens": 19581968} {"current_steps": 34480, "total_steps": 40000, "loss": 0.0, "lr": 2.313714292842889e-06, "epoch": 604.9203539823009, "percentage": 86.2, "elapsed_time": "4:08:32", "remaining_time": "0:39:47", "throughput": 1313.32, "total_tokens": 19584656} {"current_steps": 34485, "total_steps": 40000, "loss": 0.0, "lr": 2.309591160494734e-06, "epoch": 605.0, "percentage": 86.21, "elapsed_time": "4:08:34", "remaining_time": "0:39:45", "throughput": 1313.31, "total_tokens": 19587152} {"current_steps": 34490, "total_steps": 40000, "loss": 0.0, "lr": 2.305471527292763e-06, "epoch": 605.0884955752213, "percentage": 86.22, "elapsed_time": "4:08:36", "remaining_time": "0:39:43", "throughput": 1313.29, "total_tokens": 19589984} {"current_steps": 34495, "total_steps": 40000, "loss": 0.0, "lr": 2.3013553938722817e-06, "epoch": 605.1769911504425, "percentage": 86.24, "elapsed_time": "4:08:38", "remaining_time": "0:39:40", "throughput": 1313.29, "total_tokens": 19592784} {"current_steps": 34500, "total_steps": 40000, "loss": 0.0, "lr": 2.297242760868043e-06, "epoch": 605.2654867256637, "percentage": 86.25, "elapsed_time": "4:08:41", "remaining_time": "0:39:38", "throughput": 1313.28, "total_tokens": 19595488} {"current_steps": 34505, "total_steps": 40000, "loss": 0.0, "lr": 2.2931336289142735e-06, "epoch": 605.3539823008849, "percentage": 86.26, "elapsed_time": "4:08:43", "remaining_time": "0:39:36", "throughput": 1313.26, "total_tokens": 19597968} {"current_steps": 34510, "total_steps": 40000, "loss": 0.0, "lr": 2.289027998644655e-06, "epoch": 605.4424778761062, "percentage": 86.28, "elapsed_time": "4:08:45", "remaining_time": "0:39:34", "throughput": 1313.26, "total_tokens": 19600800} {"current_steps": 34515, "total_steps": 40000, "loss": 0.0, "lr": 2.2849258706923228e-06, "epoch": 605.5309734513274, "percentage": 86.29, "elapsed_time": "4:08:47", "remaining_time": "0:39:32", "throughput": 1313.29, "total_tokens": 19604080} {"current_steps": 34520, "total_steps": 40000, "loss": 0.0, "lr": 2.2808272456898705e-06, "epoch": 605.6194690265487, "percentage": 86.3, "elapsed_time": "4:08:49", "remaining_time": "0:39:30", "throughput": 1313.33, "total_tokens": 19607456} {"current_steps": 34525, "total_steps": 40000, "loss": 0.0, "lr": 2.2767321242693707e-06, "epoch": 605.70796460177, "percentage": 86.31, "elapsed_time": "4:08:51", "remaining_time": "0:39:27", "throughput": 1313.33, "total_tokens": 19610304} {"current_steps": 34530, "total_steps": 40000, "loss": 0.0, "lr": 2.272640507062329e-06, "epoch": 605.7964601769911, "percentage": 86.33, "elapsed_time": "4:08:53", "remaining_time": "0:39:25", "throughput": 1313.32, "total_tokens": 19612976} {"current_steps": 34535, "total_steps": 40000, "loss": 0.0, "lr": 2.2685523946997382e-06, "epoch": 605.8849557522124, "percentage": 86.34, "elapsed_time": "4:08:56", "remaining_time": "0:39:23", "throughput": 1313.35, "total_tokens": 19616224} {"current_steps": 34540, "total_steps": 40000, "loss": 0.0, "lr": 2.2644677878120245e-06, "epoch": 605.9734513274336, "percentage": 86.35, "elapsed_time": "4:08:58", "remaining_time": "0:39:21", "throughput": 1313.34, "total_tokens": 19618912} {"current_steps": 34545, "total_steps": 40000, "loss": 0.0, "lr": 2.2603866870290897e-06, "epoch": 606.0530973451328, "percentage": 86.36, "elapsed_time": "4:09:00", "remaining_time": "0:39:19", "throughput": 1313.29, "total_tokens": 19621232} {"current_steps": 34550, "total_steps": 40000, "loss": 0.0, "lr": 2.256309092980294e-06, "epoch": 606.141592920354, "percentage": 86.38, "elapsed_time": "4:09:02", "remaining_time": "0:39:17", "throughput": 1313.26, "total_tokens": 19623680} {"current_steps": 34555, "total_steps": 40000, "loss": 0.0, "lr": 2.252235006294448e-06, "epoch": 606.2300884955753, "percentage": 86.39, "elapsed_time": "4:09:04", "remaining_time": "0:39:14", "throughput": 1313.28, "total_tokens": 19626768} {"current_steps": 34560, "total_steps": 40000, "loss": 0.0, "lr": 2.2481644275998333e-06, "epoch": 606.3185840707964, "percentage": 86.4, "elapsed_time": "4:09:06", "remaining_time": "0:39:12", "throughput": 1313.33, "total_tokens": 19630224} {"current_steps": 34565, "total_steps": 40000, "loss": 0.0, "lr": 2.2440973575241832e-06, "epoch": 606.4070796460177, "percentage": 86.41, "elapsed_time": "4:09:09", "remaining_time": "0:39:10", "throughput": 1313.35, "total_tokens": 19633392} {"current_steps": 34570, "total_steps": 40000, "loss": 0.0, "lr": 2.240033796694685e-06, "epoch": 606.4955752212389, "percentage": 86.42, "elapsed_time": "4:09:11", "remaining_time": "0:39:08", "throughput": 1313.33, "total_tokens": 19635872} {"current_steps": 34575, "total_steps": 40000, "loss": 0.0, "lr": 2.235973745737999e-06, "epoch": 606.5840707964602, "percentage": 86.44, "elapsed_time": "4:09:13", "remaining_time": "0:39:06", "throughput": 1313.33, "total_tokens": 19638784} {"current_steps": 34580, "total_steps": 40000, "loss": 0.0, "lr": 2.2319172052802263e-06, "epoch": 606.6725663716815, "percentage": 86.45, "elapsed_time": "4:09:15", "remaining_time": "0:39:04", "throughput": 1313.32, "total_tokens": 19641376} {"current_steps": 34585, "total_steps": 40000, "loss": 0.0, "lr": 2.2278641759469477e-06, "epoch": 606.7610619469026, "percentage": 86.46, "elapsed_time": "4:09:17", "remaining_time": "0:39:01", "throughput": 1313.33, "total_tokens": 19644176} {"current_steps": 34590, "total_steps": 40000, "loss": 0.0, "lr": 2.2238146583631825e-06, "epoch": 606.8495575221239, "percentage": 86.48, "elapsed_time": "4:09:19", "remaining_time": "0:38:59", "throughput": 1313.38, "total_tokens": 19647680} {"current_steps": 34595, "total_steps": 40000, "loss": 0.0, "lr": 2.2197686531534256e-06, "epoch": 606.9380530973451, "percentage": 86.49, "elapsed_time": "4:09:21", "remaining_time": "0:38:57", "throughput": 1313.37, "total_tokens": 19650336} {"current_steps": 34600, "total_steps": 40000, "loss": 0.0, "lr": 2.2157261609416087e-06, "epoch": 607.0176991150443, "percentage": 86.5, "elapsed_time": "4:09:23", "remaining_time": "0:38:55", "throughput": 1313.32, "total_tokens": 19652392} {"current_steps": 34600, "total_steps": 40000, "eval_loss": 0.9027122855186462, "epoch": 607.0176991150443, "percentage": 86.5, "elapsed_time": "4:09:25", "remaining_time": "0:38:55", "throughput": 1313.22, "total_tokens": 19652392} {"current_steps": 34605, "total_steps": 40000, "loss": 0.0, "lr": 2.211687182351149e-06, "epoch": 607.1061946902655, "percentage": 86.51, "elapsed_time": "4:09:29", "remaining_time": "0:38:53", "throughput": 1313.03, "total_tokens": 19654904} {"current_steps": 34610, "total_steps": 40000, "loss": 0.0, "lr": 2.2076517180048993e-06, "epoch": 607.1946902654868, "percentage": 86.52, "elapsed_time": "4:09:31", "remaining_time": "0:38:51", "throughput": 1313.04, "total_tokens": 19657784} {"current_steps": 34615, "total_steps": 40000, "loss": 0.0, "lr": 2.2036197685251834e-06, "epoch": 607.2831858407079, "percentage": 86.54, "elapsed_time": "4:09:33", "remaining_time": "0:38:49", "throughput": 1313.06, "total_tokens": 19660856} {"current_steps": 34620, "total_steps": 40000, "loss": 0.0, "lr": 2.199591334533771e-06, "epoch": 607.3716814159292, "percentage": 86.55, "elapsed_time": "4:09:35", "remaining_time": "0:38:47", "throughput": 1313.05, "total_tokens": 19663528} {"current_steps": 34625, "total_steps": 40000, "loss": 0.0, "lr": 2.1955664166519036e-06, "epoch": 607.4601769911504, "percentage": 86.56, "elapsed_time": "4:09:37", "remaining_time": "0:38:45", "throughput": 1313.05, "total_tokens": 19666168} {"current_steps": 34630, "total_steps": 40000, "loss": 0.0, "lr": 2.1915450155002793e-06, "epoch": 607.5486725663717, "percentage": 86.58, "elapsed_time": "4:09:39", "remaining_time": "0:38:42", "throughput": 1313.06, "total_tokens": 19669096} {"current_steps": 34635, "total_steps": 40000, "loss": 0.0, "lr": 2.187527131699038e-06, "epoch": 607.637168141593, "percentage": 86.59, "elapsed_time": "4:09:41", "remaining_time": "0:38:40", "throughput": 1313.1, "total_tokens": 19672424} {"current_steps": 34640, "total_steps": 40000, "loss": 0.0, "lr": 2.18351276586779e-06, "epoch": 607.7256637168142, "percentage": 86.6, "elapsed_time": "4:09:43", "remaining_time": "0:38:38", "throughput": 1313.1, "total_tokens": 19675128} {"current_steps": 34645, "total_steps": 40000, "loss": 0.0, "lr": 2.1795019186256092e-06, "epoch": 607.8141592920354, "percentage": 86.61, "elapsed_time": "4:09:45", "remaining_time": "0:38:36", "throughput": 1313.11, "total_tokens": 19677944} {"current_steps": 34650, "total_steps": 40000, "loss": 0.0, "lr": 2.1754945905910094e-06, "epoch": 607.9026548672566, "percentage": 86.62, "elapsed_time": "4:09:47", "remaining_time": "0:38:34", "throughput": 1313.14, "total_tokens": 19681160} {"current_steps": 34655, "total_steps": 40000, "loss": 0.0, "lr": 2.171490782381977e-06, "epoch": 607.9911504424779, "percentage": 86.64, "elapsed_time": "4:09:49", "remaining_time": "0:38:31", "throughput": 1313.17, "total_tokens": 19684296} {"current_steps": 34660, "total_steps": 40000, "loss": 0.0, "lr": 2.1674904946159425e-06, "epoch": 608.070796460177, "percentage": 86.65, "elapsed_time": "4:09:52", "remaining_time": "0:38:29", "throughput": 1313.12, "total_tokens": 19686560} {"current_steps": 34665, "total_steps": 40000, "loss": 0.0, "lr": 2.16349372790981e-06, "epoch": 608.1592920353983, "percentage": 86.66, "elapsed_time": "4:09:54", "remaining_time": "0:38:27", "throughput": 1313.13, "total_tokens": 19689328} {"current_steps": 34670, "total_steps": 40000, "loss": 0.0, "lr": 2.159500482879928e-06, "epoch": 608.2477876106195, "percentage": 86.67, "elapsed_time": "4:09:56", "remaining_time": "0:38:25", "throughput": 1313.17, "total_tokens": 19692768} {"current_steps": 34675, "total_steps": 40000, "loss": 0.0, "lr": 2.155510760142096e-06, "epoch": 608.3362831858407, "percentage": 86.69, "elapsed_time": "4:09:58", "remaining_time": "0:38:23", "throughput": 1313.2, "total_tokens": 19695840} {"current_steps": 34680, "total_steps": 40000, "loss": 0.0, "lr": 2.151524560311588e-06, "epoch": 608.4247787610619, "percentage": 86.7, "elapsed_time": "4:10:00", "remaining_time": "0:38:21", "throughput": 1313.23, "total_tokens": 19699120} {"current_steps": 34685, "total_steps": 40000, "loss": 0.0, "lr": 2.147541884003129e-06, "epoch": 608.5132743362832, "percentage": 86.71, "elapsed_time": "4:10:02", "remaining_time": "0:38:18", "throughput": 1313.22, "total_tokens": 19701616} {"current_steps": 34690, "total_steps": 40000, "loss": 0.0, "lr": 2.1435627318308895e-06, "epoch": 608.6017699115044, "percentage": 86.72, "elapsed_time": "4:10:04", "remaining_time": "0:38:16", "throughput": 1313.23, "total_tokens": 19704512} {"current_steps": 34695, "total_steps": 40000, "loss": 0.0, "lr": 2.139587104408511e-06, "epoch": 608.6902654867257, "percentage": 86.74, "elapsed_time": "4:10:06", "remaining_time": "0:38:14", "throughput": 1313.21, "total_tokens": 19706896} {"current_steps": 34700, "total_steps": 40000, "loss": 0.0, "lr": 2.1356150023490783e-06, "epoch": 608.7787610619469, "percentage": 86.75, "elapsed_time": "4:10:08", "remaining_time": "0:38:12", "throughput": 1313.2, "total_tokens": 19709456} {"current_steps": 34705, "total_steps": 40000, "loss": 0.0, "lr": 2.1316464262651464e-06, "epoch": 608.8672566371681, "percentage": 86.76, "elapsed_time": "4:10:10", "remaining_time": "0:38:10", "throughput": 1313.22, "total_tokens": 19712480} {"current_steps": 34710, "total_steps": 40000, "loss": 0.0, "lr": 2.1276813767687224e-06, "epoch": 608.9557522123894, "percentage": 86.78, "elapsed_time": "4:10:12", "remaining_time": "0:38:08", "throughput": 1313.22, "total_tokens": 19715312} {"current_steps": 34715, "total_steps": 40000, "loss": 0.0, "lr": 2.123719854471254e-06, "epoch": 609.0353982300885, "percentage": 86.79, "elapsed_time": "4:10:15", "remaining_time": "0:38:05", "throughput": 1313.17, "total_tokens": 19717576} {"current_steps": 34720, "total_steps": 40000, "loss": 0.0, "lr": 2.119761859983668e-06, "epoch": 609.1238938053098, "percentage": 86.8, "elapsed_time": "4:10:17", "remaining_time": "0:38:03", "throughput": 1313.19, "total_tokens": 19720744} {"current_steps": 34725, "total_steps": 40000, "loss": 0.0, "lr": 2.1158073939163386e-06, "epoch": 609.212389380531, "percentage": 86.81, "elapsed_time": "4:10:19", "remaining_time": "0:38:01", "throughput": 1313.21, "total_tokens": 19723784} {"current_steps": 34730, "total_steps": 40000, "loss": 0.0, "lr": 2.111856456879088e-06, "epoch": 609.3008849557522, "percentage": 86.83, "elapsed_time": "4:10:21", "remaining_time": "0:37:59", "throughput": 1313.23, "total_tokens": 19726920} {"current_steps": 34735, "total_steps": 40000, "loss": 0.0, "lr": 2.1079090494811993e-06, "epoch": 609.3893805309734, "percentage": 86.84, "elapsed_time": "4:10:23", "remaining_time": "0:37:57", "throughput": 1313.25, "total_tokens": 19730088} {"current_steps": 34740, "total_steps": 40000, "loss": 0.0, "lr": 2.103965172331418e-06, "epoch": 609.4778761061947, "percentage": 86.85, "elapsed_time": "4:10:26", "remaining_time": "0:37:55", "throughput": 1313.28, "total_tokens": 19733432} {"current_steps": 34745, "total_steps": 40000, "loss": 0.0, "lr": 2.100024826037933e-06, "epoch": 609.566371681416, "percentage": 86.86, "elapsed_time": "4:10:28", "remaining_time": "0:37:52", "throughput": 1313.27, "total_tokens": 19736040} {"current_steps": 34750, "total_steps": 40000, "loss": 0.0, "lr": 2.0960880112084027e-06, "epoch": 609.6548672566372, "percentage": 86.88, "elapsed_time": "4:10:30", "remaining_time": "0:37:50", "throughput": 1313.27, "total_tokens": 19738776} {"current_steps": 34755, "total_steps": 40000, "loss": 0.0, "lr": 2.092154728449927e-06, "epoch": 609.7433628318585, "percentage": 86.89, "elapsed_time": "4:10:32", "remaining_time": "0:37:48", "throughput": 1313.25, "total_tokens": 19741384} {"current_steps": 34760, "total_steps": 40000, "loss": 0.0, "lr": 2.0882249783690687e-06, "epoch": 609.8318584070796, "percentage": 86.9, "elapsed_time": "4:10:34", "remaining_time": "0:37:46", "throughput": 1313.25, "total_tokens": 19744232} {"current_steps": 34765, "total_steps": 40000, "loss": 0.0, "lr": 2.084298761571851e-06, "epoch": 609.9203539823009, "percentage": 86.91, "elapsed_time": "4:10:36", "remaining_time": "0:37:44", "throughput": 1313.25, "total_tokens": 19746936} {"current_steps": 34770, "total_steps": 40000, "loss": 0.0, "lr": 2.080376078663737e-06, "epoch": 610.0, "percentage": 86.92, "elapsed_time": "4:10:38", "remaining_time": "0:37:42", "throughput": 1313.22, "total_tokens": 19749320} {"current_steps": 34775, "total_steps": 40000, "loss": 0.0, "lr": 2.0764569302496593e-06, "epoch": 610.0884955752213, "percentage": 86.94, "elapsed_time": "4:10:41", "remaining_time": "0:37:39", "throughput": 1313.25, "total_tokens": 19752776} {"current_steps": 34780, "total_steps": 40000, "loss": 0.0, "lr": 2.0725413169339957e-06, "epoch": 610.1769911504425, "percentage": 86.95, "elapsed_time": "4:10:43", "remaining_time": "0:37:37", "throughput": 1313.25, "total_tokens": 19755656} {"current_steps": 34785, "total_steps": 40000, "loss": 0.0, "lr": 2.068629239320588e-06, "epoch": 610.2654867256637, "percentage": 86.96, "elapsed_time": "4:10:45", "remaining_time": "0:37:35", "throughput": 1313.24, "total_tokens": 19758344} {"current_steps": 34790, "total_steps": 40000, "loss": 0.0, "lr": 2.064720698012726e-06, "epoch": 610.3539823008849, "percentage": 86.98, "elapsed_time": "4:10:47", "remaining_time": "0:37:33", "throughput": 1313.25, "total_tokens": 19761240} {"current_steps": 34795, "total_steps": 40000, "loss": 0.0, "lr": 2.0608156936131522e-06, "epoch": 610.4424778761062, "percentage": 86.99, "elapsed_time": "4:10:49", "remaining_time": "0:37:31", "throughput": 1313.26, "total_tokens": 19764248} {"current_steps": 34800, "total_steps": 40000, "loss": 0.0, "lr": 2.056914226724074e-06, "epoch": 610.5309734513274, "percentage": 87.0, "elapsed_time": "4:10:51", "remaining_time": "0:37:29", "throughput": 1313.25, "total_tokens": 19766904} {"current_steps": 34800, "total_steps": 40000, "eval_loss": 0.9086984395980835, "epoch": 610.5309734513274, "percentage": 87.0, "elapsed_time": "4:10:52", "remaining_time": "0:37:29", "throughput": 1313.15, "total_tokens": 19766904} {"current_steps": 34805, "total_steps": 40000, "loss": 0.0, "lr": 2.0530162979471385e-06, "epoch": 610.6194690265487, "percentage": 87.01, "elapsed_time": "4:10:57", "remaining_time": "0:37:27", "throughput": 1312.96, "total_tokens": 19769528} {"current_steps": 34810, "total_steps": 40000, "loss": 0.0, "lr": 2.0491219078834667e-06, "epoch": 610.70796460177, "percentage": 87.02, "elapsed_time": "4:10:59", "remaining_time": "0:37:25", "throughput": 1312.96, "total_tokens": 19772296} {"current_steps": 34815, "total_steps": 40000, "loss": 0.0, "lr": 2.045231057133612e-06, "epoch": 610.7964601769911, "percentage": 87.04, "elapsed_time": "4:11:01", "remaining_time": "0:37:23", "throughput": 1312.96, "total_tokens": 19775096} {"current_steps": 34820, "total_steps": 40000, "loss": 0.0, "lr": 2.0413437462975944e-06, "epoch": 610.8849557522124, "percentage": 87.05, "elapsed_time": "4:11:03", "remaining_time": "0:37:20", "throughput": 1312.96, "total_tokens": 19777944} {"current_steps": 34825, "total_steps": 40000, "loss": 0.0, "lr": 2.0374599759748843e-06, "epoch": 610.9734513274336, "percentage": 87.06, "elapsed_time": "4:11:05", "remaining_time": "0:37:18", "throughput": 1312.95, "total_tokens": 19780600} {"current_steps": 34830, "total_steps": 40000, "loss": 0.0, "lr": 2.033579746764419e-06, "epoch": 611.0530973451328, "percentage": 87.08, "elapsed_time": "4:11:08", "remaining_time": "0:37:16", "throughput": 1312.92, "total_tokens": 19783248} {"current_steps": 34835, "total_steps": 40000, "loss": 0.0, "lr": 2.029703059264565e-06, "epoch": 611.141592920354, "percentage": 87.09, "elapsed_time": "4:11:10", "remaining_time": "0:37:14", "throughput": 1312.95, "total_tokens": 19786496} {"current_steps": 34840, "total_steps": 40000, "loss": 0.0, "lr": 2.02582991407316e-06, "epoch": 611.2300884955753, "percentage": 87.1, "elapsed_time": "4:11:12", "remaining_time": "0:37:12", "throughput": 1312.97, "total_tokens": 19789584} {"current_steps": 34845, "total_steps": 40000, "loss": 0.0, "lr": 2.0219603117874992e-06, "epoch": 611.3185840707964, "percentage": 87.11, "elapsed_time": "4:11:14", "remaining_time": "0:37:10", "throughput": 1312.96, "total_tokens": 19792288} {"current_steps": 34850, "total_steps": 40000, "loss": 0.0, "lr": 2.0180942530043156e-06, "epoch": 611.4070796460177, "percentage": 87.12, "elapsed_time": "4:11:16", "remaining_time": "0:37:07", "throughput": 1312.95, "total_tokens": 19794864} {"current_steps": 34855, "total_steps": 40000, "loss": 0.0, "lr": 2.0142317383198107e-06, "epoch": 611.4955752212389, "percentage": 87.14, "elapsed_time": "4:11:18", "remaining_time": "0:37:05", "throughput": 1312.93, "total_tokens": 19797264} {"current_steps": 34860, "total_steps": 40000, "loss": 0.0, "lr": 2.0103727683296243e-06, "epoch": 611.5840707964602, "percentage": 87.15, "elapsed_time": "4:11:20", "remaining_time": "0:37:03", "throughput": 1312.96, "total_tokens": 19800448} {"current_steps": 34865, "total_steps": 40000, "loss": 0.0, "lr": 2.0065173436288636e-06, "epoch": 611.6725663716815, "percentage": 87.16, "elapsed_time": "4:11:22", "remaining_time": "0:37:01", "throughput": 1312.99, "total_tokens": 19803584} {"current_steps": 34870, "total_steps": 40000, "loss": 0.0, "lr": 2.002665464812087e-06, "epoch": 611.7610619469026, "percentage": 87.17, "elapsed_time": "4:11:24", "remaining_time": "0:36:59", "throughput": 1312.99, "total_tokens": 19806336} {"current_steps": 34875, "total_steps": 40000, "loss": 0.0, "lr": 1.998817132473291e-06, "epoch": 611.8495575221239, "percentage": 87.19, "elapsed_time": "4:11:27", "remaining_time": "0:36:57", "throughput": 1313.01, "total_tokens": 19809456} {"current_steps": 34880, "total_steps": 40000, "loss": 0.0, "lr": 1.9949723472059507e-06, "epoch": 611.9380530973451, "percentage": 87.2, "elapsed_time": "4:11:29", "remaining_time": "0:36:54", "throughput": 1313.05, "total_tokens": 19812656} {"current_steps": 34885, "total_steps": 40000, "loss": 0.0, "lr": 1.9911311096029726e-06, "epoch": 612.0176991150443, "percentage": 87.21, "elapsed_time": "4:11:31", "remaining_time": "0:36:52", "throughput": 1312.99, "total_tokens": 19814672} {"current_steps": 34890, "total_steps": 40000, "loss": 0.0, "lr": 1.9872934202567224e-06, "epoch": 612.1061946902655, "percentage": 87.22, "elapsed_time": "4:11:33", "remaining_time": "0:36:50", "throughput": 1312.98, "total_tokens": 19817376} {"current_steps": 34895, "total_steps": 40000, "loss": 0.0, "lr": 1.9834592797590257e-06, "epoch": 612.1946902654868, "percentage": 87.24, "elapsed_time": "4:11:35", "remaining_time": "0:36:48", "throughput": 1313.0, "total_tokens": 19820384} {"current_steps": 34900, "total_steps": 40000, "loss": 0.0, "lr": 1.979628688701149e-06, "epoch": 612.2831858407079, "percentage": 87.25, "elapsed_time": "4:11:37", "remaining_time": "0:36:46", "throughput": 1313.0, "total_tokens": 19822992} {"current_steps": 34905, "total_steps": 40000, "loss": 0.0, "lr": 1.9758016476738193e-06, "epoch": 612.3716814159292, "percentage": 87.26, "elapsed_time": "4:11:39", "remaining_time": "0:36:44", "throughput": 1312.99, "total_tokens": 19825552} {"current_steps": 34910, "total_steps": 40000, "loss": 0.0, "lr": 1.971978157267221e-06, "epoch": 612.4601769911504, "percentage": 87.28, "elapsed_time": "4:11:41", "remaining_time": "0:36:41", "throughput": 1312.99, "total_tokens": 19828320} {"current_steps": 34915, "total_steps": 40000, "loss": 0.0, "lr": 1.968158218070973e-06, "epoch": 612.5486725663717, "percentage": 87.29, "elapsed_time": "4:11:43", "remaining_time": "0:36:39", "throughput": 1313.05, "total_tokens": 19832016} {"current_steps": 34920, "total_steps": 40000, "loss": 0.0, "lr": 1.9643418306741682e-06, "epoch": 612.637168141593, "percentage": 87.3, "elapsed_time": "4:11:45", "remaining_time": "0:36:37", "throughput": 1313.11, "total_tokens": 19835632} {"current_steps": 34925, "total_steps": 40000, "loss": 0.0, "lr": 1.9605289956653337e-06, "epoch": 612.7256637168142, "percentage": 87.31, "elapsed_time": "4:11:47", "remaining_time": "0:36:35", "throughput": 1313.12, "total_tokens": 19838384} {"current_steps": 34930, "total_steps": 40000, "loss": 0.0, "lr": 1.9567197136324626e-06, "epoch": 612.8141592920354, "percentage": 87.33, "elapsed_time": "4:11:49", "remaining_time": "0:36:33", "throughput": 1313.09, "total_tokens": 19840784} {"current_steps": 34935, "total_steps": 40000, "loss": 0.0, "lr": 1.9529139851629935e-06, "epoch": 612.9026548672566, "percentage": 87.34, "elapsed_time": "4:11:52", "remaining_time": "0:36:30", "throughput": 1313.09, "total_tokens": 19843472} {"current_steps": 34940, "total_steps": 40000, "loss": 0.0, "lr": 1.949111810843812e-06, "epoch": 612.9911504424779, "percentage": 87.35, "elapsed_time": "4:11:54", "remaining_time": "0:36:28", "throughput": 1313.1, "total_tokens": 19846304} {"current_steps": 34945, "total_steps": 40000, "loss": 0.0, "lr": 1.9453131912612694e-06, "epoch": 613.070796460177, "percentage": 87.36, "elapsed_time": "4:11:56", "remaining_time": "0:36:26", "throughput": 1313.06, "total_tokens": 19848624} {"current_steps": 34950, "total_steps": 40000, "loss": 0.0, "lr": 1.941518127001149e-06, "epoch": 613.1592920353983, "percentage": 87.38, "elapsed_time": "4:11:58", "remaining_time": "0:36:24", "throughput": 1313.05, "total_tokens": 19851312} {"current_steps": 34955, "total_steps": 40000, "loss": 0.0, "lr": 1.9377266186487107e-06, "epoch": 613.2477876106195, "percentage": 87.39, "elapsed_time": "4:12:00", "remaining_time": "0:36:22", "throughput": 1313.05, "total_tokens": 19854032} {"current_steps": 34960, "total_steps": 40000, "loss": 0.0, "lr": 1.9339386667886483e-06, "epoch": 613.3362831858407, "percentage": 87.4, "elapsed_time": "4:12:02", "remaining_time": "0:36:20", "throughput": 1313.06, "total_tokens": 19856832} {"current_steps": 34965, "total_steps": 40000, "loss": 0.0, "lr": 1.9301542720051024e-06, "epoch": 613.4247787610619, "percentage": 87.41, "elapsed_time": "4:12:04", "remaining_time": "0:36:17", "throughput": 1313.09, "total_tokens": 19859984} {"current_steps": 34970, "total_steps": 40000, "loss": 0.0, "lr": 1.926373434881684e-06, "epoch": 613.5132743362832, "percentage": 87.42, "elapsed_time": "4:12:06", "remaining_time": "0:36:15", "throughput": 1313.12, "total_tokens": 19863152} {"current_steps": 34975, "total_steps": 40000, "loss": 0.0, "lr": 1.9225961560014468e-06, "epoch": 613.6017699115044, "percentage": 87.44, "elapsed_time": "4:12:08", "remaining_time": "0:36:13", "throughput": 1313.12, "total_tokens": 19865824} {"current_steps": 34980, "total_steps": 40000, "loss": 0.0, "lr": 1.918822435946885e-06, "epoch": 613.6902654867257, "percentage": 87.45, "elapsed_time": "4:12:10", "remaining_time": "0:36:11", "throughput": 1313.13, "total_tokens": 19868768} {"current_steps": 34985, "total_steps": 40000, "loss": 0.0, "lr": 1.915052275299961e-06, "epoch": 613.7787610619469, "percentage": 87.46, "elapsed_time": "4:12:12", "remaining_time": "0:36:09", "throughput": 1313.11, "total_tokens": 19871184} {"current_steps": 34990, "total_steps": 40000, "loss": 0.0, "lr": 1.9112856746420854e-06, "epoch": 613.8672566371681, "percentage": 87.48, "elapsed_time": "4:12:14", "remaining_time": "0:36:07", "throughput": 1313.15, "total_tokens": 19874480} {"current_steps": 34995, "total_steps": 40000, "loss": 0.0, "lr": 1.907522634554104e-06, "epoch": 613.9557522123894, "percentage": 87.49, "elapsed_time": "4:12:17", "remaining_time": "0:36:04", "throughput": 1313.19, "total_tokens": 19877808} {"current_steps": 35000, "total_steps": 40000, "loss": 0.0, "lr": 1.9037631556163337e-06, "epoch": 614.0353982300885, "percentage": 87.5, "elapsed_time": "4:12:19", "remaining_time": "0:36:02", "throughput": 1313.13, "total_tokens": 19879808} {"current_steps": 35000, "total_steps": 40000, "eval_loss": 0.8934006094932556, "epoch": 614.0353982300885, "percentage": 87.5, "elapsed_time": "4:12:20", "remaining_time": "0:36:02", "throughput": 1313.04, "total_tokens": 19879808} {"current_steps": 35005, "total_steps": 40000, "loss": 0.0, "lr": 1.9000072384085272e-06, "epoch": 614.1238938053098, "percentage": 87.51, "elapsed_time": "4:12:24", "remaining_time": "0:36:01", "throughput": 1312.89, "total_tokens": 19882944} {"current_steps": 35010, "total_steps": 40000, "loss": 0.0, "lr": 1.8962548835098987e-06, "epoch": 614.212389380531, "percentage": 87.52, "elapsed_time": "4:12:26", "remaining_time": "0:35:58", "throughput": 1312.89, "total_tokens": 19885712} {"current_steps": 35015, "total_steps": 40000, "loss": 0.0, "lr": 1.8925060914991077e-06, "epoch": 614.3008849557522, "percentage": 87.54, "elapsed_time": "4:12:28", "remaining_time": "0:35:56", "throughput": 1312.94, "total_tokens": 19889200} {"current_steps": 35020, "total_steps": 40000, "loss": 0.0, "lr": 1.888760862954264e-06, "epoch": 614.3893805309734, "percentage": 87.55, "elapsed_time": "4:12:30", "remaining_time": "0:35:54", "throughput": 1312.95, "total_tokens": 19892128} {"current_steps": 35025, "total_steps": 40000, "loss": 0.0, "lr": 1.8850191984529309e-06, "epoch": 614.4778761061947, "percentage": 87.56, "elapsed_time": "4:12:32", "remaining_time": "0:35:52", "throughput": 1312.94, "total_tokens": 19894768} {"current_steps": 35030, "total_steps": 40000, "loss": 0.0, "lr": 1.8812810985721186e-06, "epoch": 614.566371681416, "percentage": 87.58, "elapsed_time": "4:12:34", "remaining_time": "0:35:50", "throughput": 1312.93, "total_tokens": 19897520} {"current_steps": 35035, "total_steps": 40000, "loss": 0.0, "lr": 1.8775465638882856e-06, "epoch": 614.6548672566372, "percentage": 87.59, "elapsed_time": "4:12:37", "remaining_time": "0:35:48", "throughput": 1312.91, "total_tokens": 19899888} {"current_steps": 35040, "total_steps": 40000, "loss": 0.0, "lr": 1.8738155949773517e-06, "epoch": 614.7433628318585, "percentage": 87.6, "elapsed_time": "4:12:39", "remaining_time": "0:35:45", "throughput": 1312.93, "total_tokens": 19903024} {"current_steps": 35045, "total_steps": 40000, "loss": 0.0, "lr": 1.8700881924146707e-06, "epoch": 614.8318584070796, "percentage": 87.61, "elapsed_time": "4:12:41", "remaining_time": "0:35:43", "throughput": 1312.93, "total_tokens": 19905856} {"current_steps": 35050, "total_steps": 40000, "loss": 0.0, "lr": 1.8663643567750577e-06, "epoch": 614.9203539823009, "percentage": 87.62, "elapsed_time": "4:12:43", "remaining_time": "0:35:41", "throughput": 1312.92, "total_tokens": 19908624} {"current_steps": 35055, "total_steps": 40000, "loss": 0.0, "lr": 1.8626440886327813e-06, "epoch": 615.0, "percentage": 87.64, "elapsed_time": "4:12:45", "remaining_time": "0:35:39", "throughput": 1312.94, "total_tokens": 19911632} {"current_steps": 35060, "total_steps": 40000, "loss": 0.0, "lr": 1.8589273885615432e-06, "epoch": 615.0884955752213, "percentage": 87.65, "elapsed_time": "4:12:48", "remaining_time": "0:35:37", "throughput": 1312.93, "total_tokens": 19914528} {"current_steps": 35065, "total_steps": 40000, "loss": 0.0, "lr": 1.8552142571345133e-06, "epoch": 615.1769911504425, "percentage": 87.66, "elapsed_time": "4:12:50", "remaining_time": "0:35:35", "throughput": 1312.93, "total_tokens": 19917424} {"current_steps": 35070, "total_steps": 40000, "loss": 0.0, "lr": 1.8515046949243025e-06, "epoch": 615.2654867256637, "percentage": 87.67, "elapsed_time": "4:12:52", "remaining_time": "0:35:32", "throughput": 1312.91, "total_tokens": 19919952} {"current_steps": 35075, "total_steps": 40000, "loss": 0.0, "lr": 1.8477987025029674e-06, "epoch": 615.3539823008849, "percentage": 87.69, "elapsed_time": "4:12:54", "remaining_time": "0:35:30", "throughput": 1312.9, "total_tokens": 19922608} {"current_steps": 35080, "total_steps": 40000, "loss": 0.0, "lr": 1.8440962804420232e-06, "epoch": 615.4424778761062, "percentage": 87.7, "elapsed_time": "4:12:56", "remaining_time": "0:35:28", "throughput": 1312.91, "total_tokens": 19925584} {"current_steps": 35085, "total_steps": 40000, "loss": 0.0, "lr": 1.8403974293124265e-06, "epoch": 615.5309734513274, "percentage": 87.71, "elapsed_time": "4:12:58", "remaining_time": "0:35:26", "throughput": 1312.92, "total_tokens": 19928576} {"current_steps": 35090, "total_steps": 40000, "loss": 0.0, "lr": 1.8367021496845854e-06, "epoch": 615.6194690265487, "percentage": 87.72, "elapsed_time": "4:13:00", "remaining_time": "0:35:24", "throughput": 1312.95, "total_tokens": 19931808} {"current_steps": 35095, "total_steps": 40000, "loss": 0.0, "lr": 1.8330104421283662e-06, "epoch": 615.70796460177, "percentage": 87.74, "elapsed_time": "4:13:03", "remaining_time": "0:35:22", "throughput": 1312.94, "total_tokens": 19934528} {"current_steps": 35100, "total_steps": 40000, "loss": 0.0, "lr": 1.8293223072130717e-06, "epoch": 615.7964601769911, "percentage": 87.75, "elapsed_time": "4:13:05", "remaining_time": "0:35:19", "throughput": 1312.93, "total_tokens": 19937040} {"current_steps": 35105, "total_steps": 40000, "loss": 0.0, "lr": 1.8256377455074525e-06, "epoch": 615.8849557522124, "percentage": 87.76, "elapsed_time": "4:13:07", "remaining_time": "0:35:17", "throughput": 1312.92, "total_tokens": 19939840} {"current_steps": 35110, "total_steps": 40000, "loss": 0.0, "lr": 1.8219567575797263e-06, "epoch": 615.9734513274336, "percentage": 87.78, "elapsed_time": "4:13:09", "remaining_time": "0:35:15", "throughput": 1312.95, "total_tokens": 19943088} {"current_steps": 35115, "total_steps": 40000, "loss": 0.0, "lr": 1.8182793439975365e-06, "epoch": 616.0530973451328, "percentage": 87.79, "elapsed_time": "4:13:11", "remaining_time": "0:35:13", "throughput": 1312.92, "total_tokens": 19945608} {"current_steps": 35120, "total_steps": 40000, "loss": 0.0, "lr": 1.8146055053279958e-06, "epoch": 616.141592920354, "percentage": 87.8, "elapsed_time": "4:13:13", "remaining_time": "0:35:11", "throughput": 1312.97, "total_tokens": 19949160} {"current_steps": 35125, "total_steps": 40000, "loss": 0.0, "lr": 1.8109352421376486e-06, "epoch": 616.2300884955753, "percentage": 87.81, "elapsed_time": "4:13:16", "remaining_time": "0:35:09", "throughput": 1312.95, "total_tokens": 19951752} {"current_steps": 35130, "total_steps": 40000, "loss": 0.0, "lr": 1.8072685549924972e-06, "epoch": 616.3185840707964, "percentage": 87.83, "elapsed_time": "4:13:18", "remaining_time": "0:35:06", "throughput": 1312.93, "total_tokens": 19954360} {"current_steps": 35135, "total_steps": 40000, "loss": 0.0, "lr": 1.8036054444579982e-06, "epoch": 616.4070796460177, "percentage": 87.84, "elapsed_time": "4:13:20", "remaining_time": "0:35:04", "throughput": 1312.96, "total_tokens": 19957512} {"current_steps": 35140, "total_steps": 40000, "loss": 0.0, "lr": 1.7999459110990407e-06, "epoch": 616.4955752212389, "percentage": 87.85, "elapsed_time": "4:13:22", "remaining_time": "0:35:02", "throughput": 1312.93, "total_tokens": 19959912} {"current_steps": 35145, "total_steps": 40000, "loss": 0.0, "lr": 1.7962899554799712e-06, "epoch": 616.5840707964602, "percentage": 87.86, "elapsed_time": "4:13:24", "remaining_time": "0:35:00", "throughput": 1312.93, "total_tokens": 19962712} {"current_steps": 35150, "total_steps": 40000, "loss": 0.0, "lr": 1.7926375781645937e-06, "epoch": 616.6725663716815, "percentage": 87.88, "elapsed_time": "4:13:26", "remaining_time": "0:34:58", "throughput": 1312.95, "total_tokens": 19965896} {"current_steps": 35155, "total_steps": 40000, "loss": 0.0, "lr": 1.7889887797161359e-06, "epoch": 616.7610619469026, "percentage": 87.89, "elapsed_time": "4:13:29", "remaining_time": "0:34:56", "throughput": 1312.93, "total_tokens": 19968424} {"current_steps": 35160, "total_steps": 40000, "loss": 0.0, "lr": 1.7853435606973028e-06, "epoch": 616.8495575221239, "percentage": 87.9, "elapsed_time": "4:13:31", "remaining_time": "0:34:53", "throughput": 1312.94, "total_tokens": 19971368} {"current_steps": 35165, "total_steps": 40000, "loss": 0.0, "lr": 1.781701921670223e-06, "epoch": 616.9380530973451, "percentage": 87.91, "elapsed_time": "4:13:33", "remaining_time": "0:34:51", "throughput": 1312.97, "total_tokens": 19974552} {"current_steps": 35170, "total_steps": 40000, "loss": 0.0, "lr": 1.7780638631964886e-06, "epoch": 617.0176991150443, "percentage": 87.92, "elapsed_time": "4:13:35", "remaining_time": "0:34:49", "throughput": 1312.91, "total_tokens": 19976784} {"current_steps": 35175, "total_steps": 40000, "loss": 0.0, "lr": 1.7744293858371314e-06, "epoch": 617.1061946902655, "percentage": 87.94, "elapsed_time": "4:13:37", "remaining_time": "0:34:47", "throughput": 1312.9, "total_tokens": 19979376} {"current_steps": 35180, "total_steps": 40000, "loss": 0.0, "lr": 1.770798490152631e-06, "epoch": 617.1946902654868, "percentage": 87.95, "elapsed_time": "4:13:39", "remaining_time": "0:34:45", "throughput": 1312.9, "total_tokens": 19982160} {"current_steps": 35185, "total_steps": 40000, "loss": 0.0, "lr": 1.767171176702917e-06, "epoch": 617.2831858407079, "percentage": 87.96, "elapsed_time": "4:13:42", "remaining_time": "0:34:43", "throughput": 1312.9, "total_tokens": 19985040} {"current_steps": 35190, "total_steps": 40000, "loss": 0.0, "lr": 1.7635474460473755e-06, "epoch": 617.3716814159292, "percentage": 87.98, "elapsed_time": "4:13:44", "remaining_time": "0:34:40", "throughput": 1312.89, "total_tokens": 19987680} {"current_steps": 35195, "total_steps": 40000, "loss": 0.0, "lr": 1.7599272987448206e-06, "epoch": 617.4601769911504, "percentage": 87.99, "elapsed_time": "4:13:46", "remaining_time": "0:34:38", "throughput": 1312.89, "total_tokens": 19990416} {"current_steps": 35200, "total_steps": 40000, "loss": 0.0, "lr": 1.7563107353535362e-06, "epoch": 617.5486725663717, "percentage": 88.0, "elapsed_time": "4:13:48", "remaining_time": "0:34:36", "throughput": 1312.94, "total_tokens": 19993952} {"current_steps": 35200, "total_steps": 40000, "eval_loss": 0.9040440917015076, "epoch": 617.5486725663717, "percentage": 88.0, "elapsed_time": "4:13:49", "remaining_time": "0:34:36", "throughput": 1312.84, "total_tokens": 19993952} {"current_steps": 35205, "total_steps": 40000, "loss": 0.0, "lr": 1.7526977564312263e-06, "epoch": 617.637168141593, "percentage": 88.01, "elapsed_time": "4:13:53", "remaining_time": "0:34:34", "throughput": 1312.72, "total_tokens": 19997328} {"current_steps": 35210, "total_steps": 40000, "loss": 0.0, "lr": 1.7490883625350701e-06, "epoch": 617.7256637168142, "percentage": 88.02, "elapsed_time": "4:13:55", "remaining_time": "0:34:32", "throughput": 1312.73, "total_tokens": 20000320} {"current_steps": 35215, "total_steps": 40000, "loss": 0.0, "lr": 1.7454825542216807e-06, "epoch": 617.8141592920354, "percentage": 88.04, "elapsed_time": "4:13:57", "remaining_time": "0:34:30", "throughput": 1312.74, "total_tokens": 20003296} {"current_steps": 35220, "total_steps": 40000, "loss": 0.0, "lr": 1.7418803320471105e-06, "epoch": 617.9026548672566, "percentage": 88.05, "elapsed_time": "4:13:59", "remaining_time": "0:34:28", "throughput": 1312.75, "total_tokens": 20006144} {"current_steps": 35225, "total_steps": 40000, "loss": 0.0, "lr": 1.7382816965668737e-06, "epoch": 617.9911504424779, "percentage": 88.06, "elapsed_time": "4:14:01", "remaining_time": "0:34:26", "throughput": 1312.75, "total_tokens": 20008832} {"current_steps": 35230, "total_steps": 40000, "loss": 0.0, "lr": 1.7346866483359285e-06, "epoch": 618.070796460177, "percentage": 88.08, "elapsed_time": "4:14:04", "remaining_time": "0:34:23", "throughput": 1312.75, "total_tokens": 20011784} {"current_steps": 35235, "total_steps": 40000, "loss": 0.0, "lr": 1.7310951879086657e-06, "epoch": 618.1592920353983, "percentage": 88.09, "elapsed_time": "4:14:06", "remaining_time": "0:34:21", "throughput": 1312.78, "total_tokens": 20014936} {"current_steps": 35240, "total_steps": 40000, "loss": 0.0, "lr": 1.7275073158389471e-06, "epoch": 618.2477876106195, "percentage": 88.1, "elapsed_time": "4:14:08", "remaining_time": "0:34:19", "throughput": 1312.78, "total_tokens": 20017608} {"current_steps": 35245, "total_steps": 40000, "loss": 0.0, "lr": 1.723923032680061e-06, "epoch": 618.3362831858407, "percentage": 88.11, "elapsed_time": "4:14:10", "remaining_time": "0:34:17", "throughput": 1312.8, "total_tokens": 20020616} {"current_steps": 35250, "total_steps": 40000, "loss": 0.0, "lr": 1.7203423389847428e-06, "epoch": 618.4247787610619, "percentage": 88.12, "elapsed_time": "4:14:12", "remaining_time": "0:34:15", "throughput": 1312.8, "total_tokens": 20023352} {"current_steps": 35255, "total_steps": 40000, "loss": 0.0, "lr": 1.7167652353051928e-06, "epoch": 618.5132743362832, "percentage": 88.14, "elapsed_time": "4:14:14", "remaining_time": "0:34:13", "throughput": 1312.79, "total_tokens": 20025912} {"current_steps": 35260, "total_steps": 40000, "loss": 0.0, "lr": 1.7131917221930333e-06, "epoch": 618.6017699115044, "percentage": 88.15, "elapsed_time": "4:14:16", "remaining_time": "0:34:10", "throughput": 1312.77, "total_tokens": 20028280} {"current_steps": 35265, "total_steps": 40000, "loss": 0.0, "lr": 1.7096218001993513e-06, "epoch": 618.6902654867257, "percentage": 88.16, "elapsed_time": "4:14:18", "remaining_time": "0:34:08", "throughput": 1312.78, "total_tokens": 20031176} {"current_steps": 35270, "total_steps": 40000, "loss": 0.0, "lr": 1.706055469874676e-06, "epoch": 618.7787610619469, "percentage": 88.17, "elapsed_time": "4:14:20", "remaining_time": "0:34:06", "throughput": 1312.78, "total_tokens": 20033912} {"current_steps": 35275, "total_steps": 40000, "loss": 0.0, "lr": 1.702492731768976e-06, "epoch": 618.8672566371681, "percentage": 88.19, "elapsed_time": "4:14:22", "remaining_time": "0:34:04", "throughput": 1312.8, "total_tokens": 20036936} {"current_steps": 35280, "total_steps": 40000, "loss": 0.0, "lr": 1.6989335864316724e-06, "epoch": 618.9557522123894, "percentage": 88.2, "elapsed_time": "4:14:24", "remaining_time": "0:34:02", "throughput": 1312.82, "total_tokens": 20039928} {"current_steps": 35285, "total_steps": 40000, "loss": 0.0, "lr": 1.6953780344116265e-06, "epoch": 619.0353982300885, "percentage": 88.21, "elapsed_time": "4:14:27", "remaining_time": "0:34:00", "throughput": 1312.76, "total_tokens": 20041984} {"current_steps": 35290, "total_steps": 40000, "loss": 0.0, "lr": 1.6918260762571497e-06, "epoch": 619.1238938053098, "percentage": 88.22, "elapsed_time": "4:14:29", "remaining_time": "0:33:57", "throughput": 1312.78, "total_tokens": 20044912} {"current_steps": 35295, "total_steps": 40000, "loss": 0.0, "lr": 1.6882777125160093e-06, "epoch": 619.212389380531, "percentage": 88.24, "elapsed_time": "4:14:31", "remaining_time": "0:33:55", "throughput": 1312.79, "total_tokens": 20047888} {"current_steps": 35300, "total_steps": 40000, "loss": 0.0, "lr": 1.6847329437353899e-06, "epoch": 619.3008849557522, "percentage": 88.25, "elapsed_time": "4:14:33", "remaining_time": "0:33:53", "throughput": 1312.81, "total_tokens": 20050784} {"current_steps": 35305, "total_steps": 40000, "loss": 0.0, "lr": 1.6811917704619511e-06, "epoch": 619.3893805309734, "percentage": 88.26, "elapsed_time": "4:14:35", "remaining_time": "0:33:51", "throughput": 1312.8, "total_tokens": 20053376} {"current_steps": 35310, "total_steps": 40000, "loss": 0.0, "lr": 1.67765419324179e-06, "epoch": 619.4778761061947, "percentage": 88.28, "elapsed_time": "4:14:37", "remaining_time": "0:33:49", "throughput": 1312.81, "total_tokens": 20056288} {"current_steps": 35315, "total_steps": 40000, "loss": 0.0, "lr": 1.6741202126204364e-06, "epoch": 619.566371681416, "percentage": 88.29, "elapsed_time": "4:14:39", "remaining_time": "0:33:47", "throughput": 1312.83, "total_tokens": 20059344} {"current_steps": 35320, "total_steps": 40000, "loss": 0.0, "lr": 1.6705898291428767e-06, "epoch": 619.6548672566372, "percentage": 88.3, "elapsed_time": "4:14:41", "remaining_time": "0:33:44", "throughput": 1312.88, "total_tokens": 20062768} {"current_steps": 35325, "total_steps": 40000, "loss": 0.0, "lr": 1.6670630433535395e-06, "epoch": 619.7433628318585, "percentage": 88.31, "elapsed_time": "4:14:43", "remaining_time": "0:33:42", "throughput": 1312.87, "total_tokens": 20065344} {"current_steps": 35330, "total_steps": 40000, "loss": 0.0, "lr": 1.6635398557962979e-06, "epoch": 619.8318584070796, "percentage": 88.33, "elapsed_time": "4:14:45", "remaining_time": "0:33:40", "throughput": 1312.88, "total_tokens": 20068240} {"current_steps": 35335, "total_steps": 40000, "loss": 0.0, "lr": 1.660020267014481e-06, "epoch": 619.9203539823009, "percentage": 88.34, "elapsed_time": "4:14:47", "remaining_time": "0:33:38", "throughput": 1312.87, "total_tokens": 20070784} {"current_steps": 35340, "total_steps": 40000, "loss": 0.0, "lr": 1.6565042775508438e-06, "epoch": 620.0, "percentage": 88.35, "elapsed_time": "4:14:49", "remaining_time": "0:33:36", "throughput": 1312.88, "total_tokens": 20073496} {"current_steps": 35345, "total_steps": 40000, "loss": 0.0, "lr": 1.6529918879475997e-06, "epoch": 620.0884955752213, "percentage": 88.36, "elapsed_time": "4:14:51", "remaining_time": "0:33:33", "throughput": 1312.92, "total_tokens": 20077080} {"current_steps": 35350, "total_steps": 40000, "loss": 0.0, "lr": 1.6494830987464043e-06, "epoch": 620.1769911504425, "percentage": 88.38, "elapsed_time": "4:14:54", "remaining_time": "0:33:31", "throughput": 1312.93, "total_tokens": 20079960} {"current_steps": 35355, "total_steps": 40000, "loss": 0.0, "lr": 1.6459779104883555e-06, "epoch": 620.2654867256637, "percentage": 88.39, "elapsed_time": "4:14:56", "remaining_time": "0:33:29", "throughput": 1312.93, "total_tokens": 20082744} {"current_steps": 35360, "total_steps": 40000, "loss": 0.0, "lr": 1.6424763237140013e-06, "epoch": 620.3539823008849, "percentage": 88.4, "elapsed_time": "4:14:58", "remaining_time": "0:33:27", "throughput": 1312.93, "total_tokens": 20085416} {"current_steps": 35365, "total_steps": 40000, "loss": 0.0, "lr": 1.6389783389633207e-06, "epoch": 620.4424778761062, "percentage": 88.41, "elapsed_time": "4:15:00", "remaining_time": "0:33:25", "throughput": 1312.92, "total_tokens": 20087928} {"current_steps": 35370, "total_steps": 40000, "loss": 0.0, "lr": 1.6354839567757546e-06, "epoch": 620.5309734513274, "percentage": 88.42, "elapsed_time": "4:15:02", "remaining_time": "0:33:23", "throughput": 1312.91, "total_tokens": 20090600} {"current_steps": 35375, "total_steps": 40000, "loss": 0.0, "lr": 1.6319931776901831e-06, "epoch": 620.6194690265487, "percentage": 88.44, "elapsed_time": "4:15:04", "remaining_time": "0:33:20", "throughput": 1312.93, "total_tokens": 20093560} {"current_steps": 35380, "total_steps": 40000, "loss": 0.0, "lr": 1.6285060022449229e-06, "epoch": 620.70796460177, "percentage": 88.45, "elapsed_time": "4:15:06", "remaining_time": "0:33:18", "throughput": 1312.94, "total_tokens": 20096488} {"current_steps": 35385, "total_steps": 40000, "loss": 0.0, "lr": 1.6250224309777434e-06, "epoch": 620.7964601769911, "percentage": 88.46, "elapsed_time": "4:15:08", "remaining_time": "0:33:16", "throughput": 1312.96, "total_tokens": 20099512} {"current_steps": 35390, "total_steps": 40000, "loss": 0.0, "lr": 1.6215424644258515e-06, "epoch": 620.8849557522124, "percentage": 88.48, "elapsed_time": "4:15:10", "remaining_time": "0:33:14", "throughput": 1312.99, "total_tokens": 20102568} {"current_steps": 35395, "total_steps": 40000, "loss": 0.0, "lr": 1.6180661031259036e-06, "epoch": 620.9734513274336, "percentage": 88.49, "elapsed_time": "4:15:12", "remaining_time": "0:33:12", "throughput": 1312.98, "total_tokens": 20105112} {"current_steps": 35400, "total_steps": 40000, "loss": 0.0, "lr": 1.614593347613999e-06, "epoch": 621.0530973451328, "percentage": 88.5, "elapsed_time": "4:15:14", "remaining_time": "0:33:10", "throughput": 1312.94, "total_tokens": 20107560} {"current_steps": 35400, "total_steps": 40000, "eval_loss": 0.911011278629303, "epoch": 621.0530973451328, "percentage": 88.5, "elapsed_time": "4:15:15", "remaining_time": "0:33:10", "throughput": 1312.85, "total_tokens": 20107560} {"current_steps": 35405, "total_steps": 40000, "loss": 0.0, "lr": 1.6111241984256758e-06, "epoch": 621.141592920354, "percentage": 88.51, "elapsed_time": "4:15:19", "remaining_time": "0:33:08", "throughput": 1312.68, "total_tokens": 20110056} {"current_steps": 35410, "total_steps": 40000, "loss": 0.0, "lr": 1.6076586560959257e-06, "epoch": 621.2300884955753, "percentage": 88.52, "elapsed_time": "4:15:21", "remaining_time": "0:33:06", "throughput": 1312.71, "total_tokens": 20113336} {"current_steps": 35415, "total_steps": 40000, "loss": 0.0, "lr": 1.604196721159182e-06, "epoch": 621.3185840707964, "percentage": 88.54, "elapsed_time": "4:15:24", "remaining_time": "0:33:03", "throughput": 1312.7, "total_tokens": 20115784} {"current_steps": 35420, "total_steps": 40000, "loss": 0.0, "lr": 1.6007383941493092e-06, "epoch": 621.4070796460177, "percentage": 88.55, "elapsed_time": "4:15:26", "remaining_time": "0:33:01", "throughput": 1312.71, "total_tokens": 20118760} {"current_steps": 35425, "total_steps": 40000, "loss": 0.0, "lr": 1.5972836755996285e-06, "epoch": 621.4955752212389, "percentage": 88.56, "elapsed_time": "4:15:28", "remaining_time": "0:32:59", "throughput": 1312.74, "total_tokens": 20121896} {"current_steps": 35430, "total_steps": 40000, "loss": 0.0, "lr": 1.5938325660429076e-06, "epoch": 621.5840707964602, "percentage": 88.58, "elapsed_time": "4:15:30", "remaining_time": "0:32:57", "throughput": 1312.73, "total_tokens": 20124536} {"current_steps": 35435, "total_steps": 40000, "loss": 0.0, "lr": 1.5903850660113378e-06, "epoch": 621.6725663716815, "percentage": 88.59, "elapsed_time": "4:15:32", "remaining_time": "0:32:55", "throughput": 1312.75, "total_tokens": 20127448} {"current_steps": 35440, "total_steps": 40000, "loss": 0.0, "lr": 1.5869411760365826e-06, "epoch": 621.7610619469026, "percentage": 88.6, "elapsed_time": "4:15:34", "remaining_time": "0:32:53", "throughput": 1312.77, "total_tokens": 20130504} {"current_steps": 35445, "total_steps": 40000, "loss": 0.0, "lr": 1.58350089664972e-06, "epoch": 621.8495575221239, "percentage": 88.61, "elapsed_time": "4:15:36", "remaining_time": "0:32:50", "throughput": 1312.76, "total_tokens": 20133064} {"current_steps": 35450, "total_steps": 40000, "loss": 0.0, "lr": 1.5800642283812865e-06, "epoch": 621.9380530973451, "percentage": 88.62, "elapsed_time": "4:15:38", "remaining_time": "0:32:48", "throughput": 1312.82, "total_tokens": 20136632} {"current_steps": 35455, "total_steps": 40000, "loss": 0.0, "lr": 1.5766311717612698e-06, "epoch": 622.0176991150443, "percentage": 88.64, "elapsed_time": "4:15:40", "remaining_time": "0:32:46", "throughput": 1312.79, "total_tokens": 20139096} {"current_steps": 35460, "total_steps": 40000, "loss": 0.0, "lr": 1.5732017273190818e-06, "epoch": 622.1061946902655, "percentage": 88.65, "elapsed_time": "4:15:42", "remaining_time": "0:32:44", "throughput": 1312.79, "total_tokens": 20141880} {"current_steps": 35465, "total_steps": 40000, "loss": 0.0, "lr": 1.5697758955835806e-06, "epoch": 622.1946902654868, "percentage": 88.66, "elapsed_time": "4:15:44", "remaining_time": "0:32:42", "throughput": 1312.8, "total_tokens": 20144792} {"current_steps": 35470, "total_steps": 40000, "loss": 0.0, "lr": 1.566353677083085e-06, "epoch": 622.2831858407079, "percentage": 88.67, "elapsed_time": "4:15:46", "remaining_time": "0:32:40", "throughput": 1312.8, "total_tokens": 20147560} {"current_steps": 35475, "total_steps": 40000, "loss": 0.0, "lr": 1.562935072345334e-06, "epoch": 622.3716814159292, "percentage": 88.69, "elapsed_time": "4:15:49", "remaining_time": "0:32:37", "throughput": 1312.81, "total_tokens": 20150424} {"current_steps": 35480, "total_steps": 40000, "loss": 0.0, "lr": 1.5595200818975281e-06, "epoch": 622.4601769911504, "percentage": 88.7, "elapsed_time": "4:15:51", "remaining_time": "0:32:35", "throughput": 1312.79, "total_tokens": 20152920} {"current_steps": 35485, "total_steps": 40000, "loss": 0.0, "lr": 1.5561087062662905e-06, "epoch": 622.5486725663717, "percentage": 88.71, "elapsed_time": "4:15:53", "remaining_time": "0:32:33", "throughput": 1312.81, "total_tokens": 20156088} {"current_steps": 35490, "total_steps": 40000, "loss": 0.0, "lr": 1.5527009459777087e-06, "epoch": 622.637168141593, "percentage": 88.72, "elapsed_time": "4:15:55", "remaining_time": "0:32:31", "throughput": 1312.8, "total_tokens": 20158776} {"current_steps": 35495, "total_steps": 40000, "loss": 0.0, "lr": 1.5492968015572984e-06, "epoch": 622.7256637168142, "percentage": 88.74, "elapsed_time": "4:15:57", "remaining_time": "0:32:29", "throughput": 1312.8, "total_tokens": 20161576} {"current_steps": 35500, "total_steps": 40000, "loss": 0.0, "lr": 1.5458962735300203e-06, "epoch": 622.8141592920354, "percentage": 88.75, "elapsed_time": "4:15:59", "remaining_time": "0:32:27", "throughput": 1312.8, "total_tokens": 20164376} {"current_steps": 35505, "total_steps": 40000, "loss": 0.0, "lr": 1.54249936242028e-06, "epoch": 622.9026548672566, "percentage": 88.76, "elapsed_time": "4:16:01", "remaining_time": "0:32:24", "throughput": 1312.84, "total_tokens": 20167736} {"current_steps": 35510, "total_steps": 40000, "loss": 0.0, "lr": 1.5391060687519222e-06, "epoch": 622.9911504424779, "percentage": 88.78, "elapsed_time": "4:16:04", "remaining_time": "0:32:22", "throughput": 1312.85, "total_tokens": 20170728} {"current_steps": 35515, "total_steps": 40000, "loss": 0.0, "lr": 1.5357163930482367e-06, "epoch": 623.070796460177, "percentage": 88.79, "elapsed_time": "4:16:06", "remaining_time": "0:32:20", "throughput": 1312.8, "total_tokens": 20173000} {"current_steps": 35520, "total_steps": 40000, "loss": 0.0, "lr": 1.532330335831955e-06, "epoch": 623.1592920353983, "percentage": 88.8, "elapsed_time": "4:16:08", "remaining_time": "0:32:18", "throughput": 1312.8, "total_tokens": 20175752} {"current_steps": 35525, "total_steps": 40000, "loss": 0.0, "lr": 1.5289478976252491e-06, "epoch": 623.2477876106195, "percentage": 88.81, "elapsed_time": "4:16:10", "remaining_time": "0:32:16", "throughput": 1312.78, "total_tokens": 20178216} {"current_steps": 35530, "total_steps": 40000, "loss": 0.0, "lr": 1.5255690789497345e-06, "epoch": 623.3362831858407, "percentage": 88.83, "elapsed_time": "4:16:12", "remaining_time": "0:32:14", "throughput": 1312.77, "total_tokens": 20180904} {"current_steps": 35535, "total_steps": 40000, "loss": 0.0, "lr": 1.5221938803264641e-06, "epoch": 623.4247787610619, "percentage": 88.84, "elapsed_time": "4:16:14", "remaining_time": "0:32:11", "throughput": 1312.75, "total_tokens": 20183448} {"current_steps": 35540, "total_steps": 40000, "loss": 0.0, "lr": 1.518822302275938e-06, "epoch": 623.5132743362832, "percentage": 88.85, "elapsed_time": "4:16:17", "remaining_time": "0:32:09", "throughput": 1312.78, "total_tokens": 20186696} {"current_steps": 35545, "total_steps": 40000, "loss": 0.0, "lr": 1.5154543453180958e-06, "epoch": 623.6017699115044, "percentage": 88.86, "elapsed_time": "4:16:19", "remaining_time": "0:32:07", "throughput": 1312.78, "total_tokens": 20189512} {"current_steps": 35550, "total_steps": 40000, "loss": 0.0, "lr": 1.5120900099723167e-06, "epoch": 623.6902654867257, "percentage": 88.88, "elapsed_time": "4:16:21", "remaining_time": "0:32:05", "throughput": 1312.78, "total_tokens": 20192360} {"current_steps": 35555, "total_steps": 40000, "loss": 0.0, "lr": 1.5087292967574273e-06, "epoch": 623.7787610619469, "percentage": 88.89, "elapsed_time": "4:16:23", "remaining_time": "0:32:03", "throughput": 1312.81, "total_tokens": 20195640} {"current_steps": 35560, "total_steps": 40000, "loss": 0.0, "lr": 1.5053722061916908e-06, "epoch": 623.8672566371681, "percentage": 88.9, "elapsed_time": "4:16:25", "remaining_time": "0:32:01", "throughput": 1312.84, "total_tokens": 20198856} {"current_steps": 35565, "total_steps": 40000, "loss": 0.0, "lr": 1.5020187387928124e-06, "epoch": 623.9557522123894, "percentage": 88.91, "elapsed_time": "4:16:27", "remaining_time": "0:31:58", "throughput": 1312.83, "total_tokens": 20201464} {"current_steps": 35570, "total_steps": 40000, "loss": 0.0, "lr": 1.4986688950779343e-06, "epoch": 624.0353982300885, "percentage": 88.92, "elapsed_time": "4:16:30", "remaining_time": "0:31:56", "throughput": 1312.8, "total_tokens": 20204120} {"current_steps": 35575, "total_steps": 40000, "loss": 0.0, "lr": 1.495322675563654e-06, "epoch": 624.1238938053098, "percentage": 88.94, "elapsed_time": "4:16:32", "remaining_time": "0:31:54", "throughput": 1312.79, "total_tokens": 20206728} {"current_steps": 35580, "total_steps": 40000, "loss": 0.0, "lr": 1.4919800807659922e-06, "epoch": 624.212389380531, "percentage": 88.95, "elapsed_time": "4:16:34", "remaining_time": "0:31:52", "throughput": 1312.81, "total_tokens": 20209912} {"current_steps": 35585, "total_steps": 40000, "loss": 0.0, "lr": 1.4886411112004255e-06, "epoch": 624.3008849557522, "percentage": 88.96, "elapsed_time": "4:16:36", "remaining_time": "0:31:50", "throughput": 1312.8, "total_tokens": 20212520} {"current_steps": 35590, "total_steps": 40000, "loss": 0.0, "lr": 1.4853057673818588e-06, "epoch": 624.3893805309734, "percentage": 88.98, "elapsed_time": "4:16:38", "remaining_time": "0:31:48", "throughput": 1312.81, "total_tokens": 20215464} {"current_steps": 35595, "total_steps": 40000, "loss": 0.0, "lr": 1.481974049824647e-06, "epoch": 624.4778761061947, "percentage": 88.99, "elapsed_time": "4:16:40", "remaining_time": "0:31:45", "throughput": 1312.8, "total_tokens": 20218184} {"current_steps": 35600, "total_steps": 40000, "loss": 0.0, "lr": 1.4786459590425849e-06, "epoch": 624.566371681416, "percentage": 89.0, "elapsed_time": "4:16:42", "remaining_time": "0:31:43", "throughput": 1312.8, "total_tokens": 20220888} {"current_steps": 35600, "total_steps": 40000, "eval_loss": 0.8988681435585022, "epoch": 624.566371681416, "percentage": 89.0, "elapsed_time": "4:16:43", "remaining_time": "0:31:43", "throughput": 1312.71, "total_tokens": 20220888} {"current_steps": 35605, "total_steps": 40000, "loss": 0.0, "lr": 1.4753214955489036e-06, "epoch": 624.6548672566372, "percentage": 89.01, "elapsed_time": "4:16:47", "remaining_time": "0:31:41", "throughput": 1312.59, "total_tokens": 20224344} {"current_steps": 35610, "total_steps": 40000, "loss": 0.0, "lr": 1.4720006598562737e-06, "epoch": 624.7433628318585, "percentage": 89.03, "elapsed_time": "4:16:50", "remaining_time": "0:31:39", "throughput": 1312.58, "total_tokens": 20226984} {"current_steps": 35615, "total_steps": 40000, "loss": 0.0, "lr": 1.4686834524768185e-06, "epoch": 624.8318584070796, "percentage": 89.04, "elapsed_time": "4:16:52", "remaining_time": "0:31:37", "throughput": 1312.59, "total_tokens": 20229896} {"current_steps": 35620, "total_steps": 40000, "loss": 0.0, "lr": 1.4653698739220844e-06, "epoch": 624.9203539823009, "percentage": 89.05, "elapsed_time": "4:16:54", "remaining_time": "0:31:35", "throughput": 1312.59, "total_tokens": 20232712} {"current_steps": 35625, "total_steps": 40000, "loss": 0.0, "lr": 1.4620599247030715e-06, "epoch": 625.0, "percentage": 89.06, "elapsed_time": "4:16:56", "remaining_time": "0:31:33", "throughput": 1312.57, "total_tokens": 20235192} {"current_steps": 35630, "total_steps": 40000, "loss": 0.0, "lr": 1.4587536053302125e-06, "epoch": 625.0884955752213, "percentage": 89.08, "elapsed_time": "4:16:58", "remaining_time": "0:31:31", "throughput": 1312.52, "total_tokens": 20237512} {"current_steps": 35635, "total_steps": 40000, "loss": 0.0, "lr": 1.4554509163133862e-06, "epoch": 625.1769911504425, "percentage": 89.09, "elapsed_time": "4:17:00", "remaining_time": "0:31:28", "throughput": 1312.52, "total_tokens": 20240280} {"current_steps": 35640, "total_steps": 40000, "loss": 0.0, "lr": 1.4521518581619098e-06, "epoch": 625.2654867256637, "percentage": 89.1, "elapsed_time": "4:17:03", "remaining_time": "0:31:26", "throughput": 1312.53, "total_tokens": 20243192} {"current_steps": 35645, "total_steps": 40000, "loss": 0.0, "lr": 1.4488564313845348e-06, "epoch": 625.3539823008849, "percentage": 89.11, "elapsed_time": "4:17:05", "remaining_time": "0:31:24", "throughput": 1312.54, "total_tokens": 20246152} {"current_steps": 35650, "total_steps": 40000, "loss": 0.0, "lr": 1.4455646364894603e-06, "epoch": 625.4424778761062, "percentage": 89.12, "elapsed_time": "4:17:07", "remaining_time": "0:31:22", "throughput": 1312.54, "total_tokens": 20248936} {"current_steps": 35655, "total_steps": 40000, "loss": 0.0, "lr": 1.4422764739843247e-06, "epoch": 625.5309734513274, "percentage": 89.14, "elapsed_time": "4:17:09", "remaining_time": "0:31:20", "throughput": 1312.54, "total_tokens": 20251816} {"current_steps": 35660, "total_steps": 40000, "loss": 0.0, "lr": 1.4389919443762e-06, "epoch": 625.6194690265487, "percentage": 89.15, "elapsed_time": "4:17:11", "remaining_time": "0:31:18", "throughput": 1312.55, "total_tokens": 20254776} {"current_steps": 35665, "total_steps": 40000, "loss": 0.0, "lr": 1.4357110481716063e-06, "epoch": 625.70796460177, "percentage": 89.16, "elapsed_time": "4:17:13", "remaining_time": "0:31:15", "throughput": 1312.55, "total_tokens": 20257576} {"current_steps": 35670, "total_steps": 40000, "loss": 0.0, "lr": 1.4324337858764941e-06, "epoch": 625.7964601769911, "percentage": 89.18, "elapsed_time": "4:17:15", "remaining_time": "0:31:13", "throughput": 1312.54, "total_tokens": 20260120} {"current_steps": 35675, "total_steps": 40000, "loss": 0.0, "lr": 1.4291601579962622e-06, "epoch": 625.8849557522124, "percentage": 89.19, "elapsed_time": "4:17:17", "remaining_time": "0:31:11", "throughput": 1312.57, "total_tokens": 20263528} {"current_steps": 35680, "total_steps": 40000, "loss": 0.0, "lr": 1.42589016503574e-06, "epoch": 625.9734513274336, "percentage": 89.2, "elapsed_time": "4:17:20", "remaining_time": "0:31:09", "throughput": 1312.59, "total_tokens": 20266504} {"current_steps": 35685, "total_steps": 40000, "loss": 0.0, "lr": 1.4226238074992099e-06, "epoch": 626.0530973451328, "percentage": 89.21, "elapsed_time": "4:17:22", "remaining_time": "0:31:07", "throughput": 1312.59, "total_tokens": 20269536} {"current_steps": 35690, "total_steps": 40000, "loss": 0.0, "lr": 1.4193610858903778e-06, "epoch": 626.141592920354, "percentage": 89.22, "elapsed_time": "4:17:24", "remaining_time": "0:31:05", "throughput": 1312.6, "total_tokens": 20272560} {"current_steps": 35695, "total_steps": 40000, "loss": 0.0, "lr": 1.416102000712402e-06, "epoch": 626.2300884955753, "percentage": 89.24, "elapsed_time": "4:17:26", "remaining_time": "0:31:02", "throughput": 1312.6, "total_tokens": 20275440} {"current_steps": 35700, "total_steps": 40000, "loss": 0.0, "lr": 1.4128465524678668e-06, "epoch": 626.3185840707964, "percentage": 89.25, "elapsed_time": "4:17:28", "remaining_time": "0:31:00", "throughput": 1312.61, "total_tokens": 20278272} {"current_steps": 35705, "total_steps": 40000, "loss": 0.0, "lr": 1.4095947416588124e-06, "epoch": 626.4070796460177, "percentage": 89.26, "elapsed_time": "4:17:31", "remaining_time": "0:30:58", "throughput": 1312.6, "total_tokens": 20280976} {"current_steps": 35710, "total_steps": 40000, "loss": 0.0, "lr": 1.4063465687866983e-06, "epoch": 626.4955752212389, "percentage": 89.28, "elapsed_time": "4:17:33", "remaining_time": "0:30:56", "throughput": 1312.6, "total_tokens": 20283744} {"current_steps": 35715, "total_steps": 40000, "loss": 0.0, "lr": 1.4031020343524438e-06, "epoch": 626.5840707964602, "percentage": 89.29, "elapsed_time": "4:17:35", "remaining_time": "0:30:54", "throughput": 1312.58, "total_tokens": 20286256} {"current_steps": 35720, "total_steps": 40000, "loss": 0.0, "lr": 1.3998611388563926e-06, "epoch": 626.6725663716815, "percentage": 89.3, "elapsed_time": "4:17:37", "remaining_time": "0:30:52", "throughput": 1312.57, "total_tokens": 20288976} {"current_steps": 35725, "total_steps": 40000, "loss": 0.0, "lr": 1.3966238827983314e-06, "epoch": 626.7610619469026, "percentage": 89.31, "elapsed_time": "4:17:39", "remaining_time": "0:30:49", "throughput": 1312.59, "total_tokens": 20292032} {"current_steps": 35730, "total_steps": 40000, "loss": 0.0, "lr": 1.393390266677483e-06, "epoch": 626.8495575221239, "percentage": 89.33, "elapsed_time": "4:17:41", "remaining_time": "0:30:47", "throughput": 1312.58, "total_tokens": 20294672} {"current_steps": 35735, "total_steps": 40000, "loss": 0.0, "lr": 1.3901602909925204e-06, "epoch": 626.9380530973451, "percentage": 89.34, "elapsed_time": "4:17:43", "remaining_time": "0:30:45", "throughput": 1312.58, "total_tokens": 20297520} {"current_steps": 35740, "total_steps": 40000, "loss": 0.0, "lr": 1.3869339562415373e-06, "epoch": 627.0176991150443, "percentage": 89.35, "elapsed_time": "4:17:46", "remaining_time": "0:30:43", "throughput": 1312.57, "total_tokens": 20300392} {"current_steps": 35745, "total_steps": 40000, "loss": 0.0, "lr": 1.38371126292208e-06, "epoch": 627.1061946902655, "percentage": 89.36, "elapsed_time": "4:17:48", "remaining_time": "0:30:41", "throughput": 1312.58, "total_tokens": 20303432} {"current_steps": 35750, "total_steps": 40000, "loss": 0.0, "lr": 1.3804922115311286e-06, "epoch": 627.1946902654868, "percentage": 89.38, "elapsed_time": "4:17:50", "remaining_time": "0:30:39", "throughput": 1312.61, "total_tokens": 20306616} {"current_steps": 35755, "total_steps": 40000, "loss": 0.0, "lr": 1.3772768025650945e-06, "epoch": 627.2831858407079, "percentage": 89.39, "elapsed_time": "4:17:52", "remaining_time": "0:30:36", "throughput": 1312.61, "total_tokens": 20309384} {"current_steps": 35760, "total_steps": 40000, "loss": 0.0, "lr": 1.3740650365198448e-06, "epoch": 627.3716814159292, "percentage": 89.4, "elapsed_time": "4:17:54", "remaining_time": "0:30:34", "throughput": 1312.61, "total_tokens": 20312280} {"current_steps": 35765, "total_steps": 40000, "loss": 0.0, "lr": 1.3708569138906612e-06, "epoch": 627.4601769911504, "percentage": 89.41, "elapsed_time": "4:17:56", "remaining_time": "0:30:32", "throughput": 1312.58, "total_tokens": 20314664} {"current_steps": 35770, "total_steps": 40000, "loss": 0.0, "lr": 1.367652435172287e-06, "epoch": 627.5486725663717, "percentage": 89.42, "elapsed_time": "4:17:58", "remaining_time": "0:30:30", "throughput": 1312.59, "total_tokens": 20317512} {"current_steps": 35775, "total_steps": 40000, "loss": 0.0, "lr": 1.364451600858893e-06, "epoch": 627.637168141593, "percentage": 89.44, "elapsed_time": "4:18:01", "remaining_time": "0:30:28", "throughput": 1312.63, "total_tokens": 20321016} {"current_steps": 35780, "total_steps": 40000, "loss": 0.0, "lr": 1.3612544114440823e-06, "epoch": 627.7256637168142, "percentage": 89.45, "elapsed_time": "4:18:03", "remaining_time": "0:30:26", "throughput": 1312.64, "total_tokens": 20323928} {"current_steps": 35785, "total_steps": 40000, "loss": 0.0, "lr": 1.3580608674209072e-06, "epoch": 627.8141592920354, "percentage": 89.46, "elapsed_time": "4:18:05", "remaining_time": "0:30:23", "throughput": 1312.61, "total_tokens": 20326360} {"current_steps": 35790, "total_steps": 40000, "loss": 0.0, "lr": 1.3548709692818434e-06, "epoch": 627.9026548672566, "percentage": 89.48, "elapsed_time": "4:18:07", "remaining_time": "0:30:21", "throughput": 1312.6, "total_tokens": 20329016} {"current_steps": 35795, "total_steps": 40000, "loss": 0.0, "lr": 1.3516847175188223e-06, "epoch": 627.9911504424779, "percentage": 89.49, "elapsed_time": "4:18:09", "remaining_time": "0:30:19", "throughput": 1312.6, "total_tokens": 20331704} {"current_steps": 35800, "total_steps": 40000, "loss": 0.0, "lr": 1.348502112623204e-06, "epoch": 628.070796460177, "percentage": 89.5, "elapsed_time": "4:18:11", "remaining_time": "0:30:17", "throughput": 1312.54, "total_tokens": 20333904} {"current_steps": 35800, "total_steps": 40000, "eval_loss": 0.9270323514938354, "epoch": 628.070796460177, "percentage": 89.5, "elapsed_time": "4:18:13", "remaining_time": "0:30:17", "throughput": 1312.45, "total_tokens": 20333904} {"current_steps": 35805, "total_steps": 40000, "loss": 0.0, "lr": 1.3453231550857787e-06, "epoch": 628.1592920353983, "percentage": 89.51, "elapsed_time": "4:18:16", "remaining_time": "0:30:15", "throughput": 1312.33, "total_tokens": 20337120} {"current_steps": 35810, "total_steps": 40000, "loss": 0.0, "lr": 1.3421478453967878e-06, "epoch": 628.2477876106195, "percentage": 89.53, "elapsed_time": "4:18:19", "remaining_time": "0:30:13", "throughput": 1312.33, "total_tokens": 20339840} {"current_steps": 35815, "total_steps": 40000, "loss": 0.0, "lr": 1.3389761840459065e-06, "epoch": 628.3362831858407, "percentage": 89.54, "elapsed_time": "4:18:21", "remaining_time": "0:30:11", "throughput": 1312.32, "total_tokens": 20342368} {"current_steps": 35820, "total_steps": 40000, "loss": 0.0, "lr": 1.3358081715222376e-06, "epoch": 628.4247787610619, "percentage": 89.55, "elapsed_time": "4:18:23", "remaining_time": "0:30:09", "throughput": 1312.31, "total_tokens": 20344928} {"current_steps": 35825, "total_steps": 40000, "loss": 0.0, "lr": 1.3326438083143295e-06, "epoch": 628.5132743362832, "percentage": 89.56, "elapsed_time": "4:18:25", "remaining_time": "0:30:06", "throughput": 1312.31, "total_tokens": 20347616} {"current_steps": 35830, "total_steps": 40000, "loss": 0.0, "lr": 1.3294830949101723e-06, "epoch": 628.6017699115044, "percentage": 89.58, "elapsed_time": "4:18:27", "remaining_time": "0:30:04", "throughput": 1312.33, "total_tokens": 20350736} {"current_steps": 35835, "total_steps": 40000, "loss": 0.0, "lr": 1.3263260317971815e-06, "epoch": 628.6902654867257, "percentage": 89.59, "elapsed_time": "4:18:29", "remaining_time": "0:30:02", "throughput": 1312.37, "total_tokens": 20354064} {"current_steps": 35840, "total_steps": 40000, "loss": 0.0, "lr": 1.3231726194622208e-06, "epoch": 628.7787610619469, "percentage": 89.6, "elapsed_time": "4:18:31", "remaining_time": "0:30:00", "throughput": 1312.36, "total_tokens": 20356624} {"current_steps": 35845, "total_steps": 40000, "loss": 0.0, "lr": 1.3200228583915814e-06, "epoch": 628.8672566371681, "percentage": 89.61, "elapsed_time": "4:18:33", "remaining_time": "0:29:58", "throughput": 1312.36, "total_tokens": 20359232} {"current_steps": 35850, "total_steps": 40000, "loss": 0.0, "lr": 1.3168767490709971e-06, "epoch": 628.9557522123894, "percentage": 89.62, "elapsed_time": "4:18:35", "remaining_time": "0:29:56", "throughput": 1312.39, "total_tokens": 20362432} {"current_steps": 35855, "total_steps": 40000, "loss": 0.0, "lr": 1.3137342919856437e-06, "epoch": 629.0353982300885, "percentage": 89.64, "elapsed_time": "4:18:37", "remaining_time": "0:29:53", "throughput": 1312.34, "total_tokens": 20364664} {"current_steps": 35860, "total_steps": 40000, "loss": 0.0, "lr": 1.310595487620117e-06, "epoch": 629.1238938053098, "percentage": 89.65, "elapsed_time": "4:18:39", "remaining_time": "0:29:51", "throughput": 1312.36, "total_tokens": 20367576} {"current_steps": 35865, "total_steps": 40000, "loss": 0.0, "lr": 1.3074603364584715e-06, "epoch": 629.212389380531, "percentage": 89.66, "elapsed_time": "4:18:41", "remaining_time": "0:29:49", "throughput": 1312.35, "total_tokens": 20370120} {"current_steps": 35870, "total_steps": 40000, "loss": 0.0, "lr": 1.3043288389841758e-06, "epoch": 629.3008849557522, "percentage": 89.68, "elapsed_time": "4:18:43", "remaining_time": "0:29:47", "throughput": 1312.39, "total_tokens": 20373448} {"current_steps": 35875, "total_steps": 40000, "loss": 0.0, "lr": 1.3012009956801546e-06, "epoch": 629.3893805309734, "percentage": 89.69, "elapsed_time": "4:18:46", "remaining_time": "0:29:45", "throughput": 1312.41, "total_tokens": 20376504} {"current_steps": 35880, "total_steps": 40000, "loss": 0.0, "lr": 1.2980768070287586e-06, "epoch": 629.4778761061947, "percentage": 89.7, "elapsed_time": "4:18:48", "remaining_time": "0:29:43", "throughput": 1312.43, "total_tokens": 20379592} {"current_steps": 35885, "total_steps": 40000, "loss": 0.0, "lr": 1.2949562735117716e-06, "epoch": 629.566371681416, "percentage": 89.71, "elapsed_time": "4:18:50", "remaining_time": "0:29:40", "throughput": 1312.42, "total_tokens": 20382168} {"current_steps": 35890, "total_steps": 40000, "loss": 0.0, "lr": 1.291839395610428e-06, "epoch": 629.6548672566372, "percentage": 89.72, "elapsed_time": "4:18:52", "remaining_time": "0:29:38", "throughput": 1312.44, "total_tokens": 20385176} {"current_steps": 35895, "total_steps": 40000, "loss": 0.0, "lr": 1.2887261738053852e-06, "epoch": 629.7433628318585, "percentage": 89.74, "elapsed_time": "4:18:54", "remaining_time": "0:29:36", "throughput": 1312.47, "total_tokens": 20388248} {"current_steps": 35900, "total_steps": 40000, "loss": 0.0, "lr": 1.2856166085767396e-06, "epoch": 629.8318584070796, "percentage": 89.75, "elapsed_time": "4:18:56", "remaining_time": "0:29:34", "throughput": 1312.45, "total_tokens": 20390744} {"current_steps": 35905, "total_steps": 40000, "loss": 0.0, "lr": 1.2825107004040272e-06, "epoch": 629.9203539823009, "percentage": 89.76, "elapsed_time": "4:18:58", "remaining_time": "0:29:32", "throughput": 1312.48, "total_tokens": 20393832} {"current_steps": 35910, "total_steps": 40000, "loss": 0.0, "lr": 1.2794084497662146e-06, "epoch": 630.0, "percentage": 89.78, "elapsed_time": "4:19:00", "remaining_time": "0:29:29", "throughput": 1312.43, "total_tokens": 20395800} {"current_steps": 35915, "total_steps": 40000, "loss": 0.0, "lr": 1.276309857141711e-06, "epoch": 630.0884955752213, "percentage": 89.79, "elapsed_time": "4:19:02", "remaining_time": "0:29:27", "throughput": 1312.41, "total_tokens": 20398424} {"current_steps": 35920, "total_steps": 40000, "loss": 0.0, "lr": 1.273214923008359e-06, "epoch": 630.1769911504425, "percentage": 89.8, "elapsed_time": "4:19:04", "remaining_time": "0:29:25", "throughput": 1312.41, "total_tokens": 20401128} {"current_steps": 35925, "total_steps": 40000, "loss": 0.0, "lr": 1.2701236478434352e-06, "epoch": 630.2654867256637, "percentage": 89.81, "elapsed_time": "4:19:06", "remaining_time": "0:29:23", "throughput": 1312.41, "total_tokens": 20403816} {"current_steps": 35930, "total_steps": 40000, "loss": 0.0, "lr": 1.2670360321236502e-06, "epoch": 630.3539823008849, "percentage": 89.83, "elapsed_time": "4:19:08", "remaining_time": "0:29:21", "throughput": 1312.4, "total_tokens": 20406408} {"current_steps": 35935, "total_steps": 40000, "loss": 0.0, "lr": 1.2639520763251617e-06, "epoch": 630.4424778761062, "percentage": 89.84, "elapsed_time": "4:19:10", "remaining_time": "0:29:19", "throughput": 1312.42, "total_tokens": 20409496} {"current_steps": 35940, "total_steps": 40000, "loss": 0.0, "lr": 1.2608717809235448e-06, "epoch": 630.5309734513274, "percentage": 89.85, "elapsed_time": "4:19:13", "remaining_time": "0:29:16", "throughput": 1312.45, "total_tokens": 20412616} {"current_steps": 35945, "total_steps": 40000, "loss": 0.0, "lr": 1.2577951463938282e-06, "epoch": 630.6194690265487, "percentage": 89.86, "elapsed_time": "4:19:15", "remaining_time": "0:29:14", "throughput": 1312.49, "total_tokens": 20415896} {"current_steps": 35950, "total_steps": 40000, "loss": 0.0, "lr": 1.2547221732104569e-06, "epoch": 630.70796460177, "percentage": 89.88, "elapsed_time": "4:19:17", "remaining_time": "0:29:12", "throughput": 1312.47, "total_tokens": 20418376} {"current_steps": 35955, "total_steps": 40000, "loss": 0.0, "lr": 1.25165286184733e-06, "epoch": 630.7964601769911, "percentage": 89.89, "elapsed_time": "4:19:19", "remaining_time": "0:29:10", "throughput": 1312.51, "total_tokens": 20421608} {"current_steps": 35960, "total_steps": 40000, "loss": 0.0, "lr": 1.248587212777777e-06, "epoch": 630.8849557522124, "percentage": 89.9, "elapsed_time": "4:19:21", "remaining_time": "0:29:08", "throughput": 1312.51, "total_tokens": 20424360} {"current_steps": 35965, "total_steps": 40000, "loss": 0.0, "lr": 1.2455252264745532e-06, "epoch": 630.9734513274336, "percentage": 89.91, "elapsed_time": "4:19:23", "remaining_time": "0:29:06", "throughput": 1312.52, "total_tokens": 20427240} {"current_steps": 35970, "total_steps": 40000, "loss": 0.0, "lr": 1.2424669034098528e-06, "epoch": 631.0530973451328, "percentage": 89.92, "elapsed_time": "4:19:25", "remaining_time": "0:29:03", "throughput": 1312.49, "total_tokens": 20429808} {"current_steps": 35975, "total_steps": 40000, "loss": 0.0, "lr": 1.2394122440553185e-06, "epoch": 631.141592920354, "percentage": 89.94, "elapsed_time": "4:19:27", "remaining_time": "0:29:01", "throughput": 1312.53, "total_tokens": 20433088} {"current_steps": 35980, "total_steps": 40000, "loss": 0.0, "lr": 1.2363612488820037e-06, "epoch": 631.2300884955753, "percentage": 89.95, "elapsed_time": "4:19:29", "remaining_time": "0:28:59", "throughput": 1312.53, "total_tokens": 20435744} {"current_steps": 35985, "total_steps": 40000, "loss": 0.0, "lr": 1.2333139183604208e-06, "epoch": 631.3185840707964, "percentage": 89.96, "elapsed_time": "4:19:31", "remaining_time": "0:28:57", "throughput": 1312.53, "total_tokens": 20438528} {"current_steps": 35990, "total_steps": 40000, "loss": 0.0, "lr": 1.2302702529604998e-06, "epoch": 631.4070796460177, "percentage": 89.98, "elapsed_time": "4:19:33", "remaining_time": "0:28:55", "throughput": 1312.55, "total_tokens": 20441504} {"current_steps": 35995, "total_steps": 40000, "loss": 0.0, "lr": 1.227230253151615e-06, "epoch": 631.4955752212389, "percentage": 89.99, "elapsed_time": "4:19:35", "remaining_time": "0:28:53", "throughput": 1312.53, "total_tokens": 20443952} {"current_steps": 36000, "total_steps": 40000, "loss": 0.0, "lr": 1.2241939194025748e-06, "epoch": 631.5840707964602, "percentage": 90.0, "elapsed_time": "4:19:38", "remaining_time": "0:28:50", "throughput": 1312.54, "total_tokens": 20446736} {"current_steps": 36000, "total_steps": 40000, "eval_loss": 0.8908863067626953, "epoch": 631.5840707964602, "percentage": 90.0, "elapsed_time": "4:19:39", "remaining_time": "0:28:51", "throughput": 1312.45, "total_tokens": 20446736} {"current_steps": 36005, "total_steps": 40000, "loss": 0.0, "lr": 1.2211612521816156e-06, "epoch": 631.6725663716815, "percentage": 90.01, "elapsed_time": "4:19:43", "remaining_time": "0:28:49", "throughput": 1312.27, "total_tokens": 20449360} {"current_steps": 36010, "total_steps": 40000, "loss": 0.0, "lr": 1.2181322519564137e-06, "epoch": 631.7610619469026, "percentage": 90.03, "elapsed_time": "4:19:45", "remaining_time": "0:28:46", "throughput": 1312.27, "total_tokens": 20452112} {"current_steps": 36015, "total_steps": 40000, "loss": 0.0, "lr": 1.2151069191940839e-06, "epoch": 631.8495575221239, "percentage": 90.04, "elapsed_time": "4:19:47", "remaining_time": "0:28:44", "throughput": 1312.29, "total_tokens": 20455136} {"current_steps": 36020, "total_steps": 40000, "loss": 0.0, "lr": 1.2120852543611644e-06, "epoch": 631.9380530973451, "percentage": 90.05, "elapsed_time": "4:19:49", "remaining_time": "0:28:42", "throughput": 1312.33, "total_tokens": 20458336} {"current_steps": 36025, "total_steps": 40000, "loss": 0.0, "lr": 1.2090672579236379e-06, "epoch": 632.0176991150443, "percentage": 90.06, "elapsed_time": "4:19:51", "remaining_time": "0:28:40", "throughput": 1312.29, "total_tokens": 20460712} {"current_steps": 36030, "total_steps": 40000, "loss": 0.0, "lr": 1.2060529303469126e-06, "epoch": 632.1061946902655, "percentage": 90.08, "elapsed_time": "4:19:53", "remaining_time": "0:28:38", "throughput": 1312.27, "total_tokens": 20463080} {"current_steps": 36035, "total_steps": 40000, "loss": 0.0, "lr": 1.2030422720958445e-06, "epoch": 632.1946902654868, "percentage": 90.09, "elapsed_time": "4:19:55", "remaining_time": "0:28:36", "throughput": 1312.26, "total_tokens": 20465736} {"current_steps": 36040, "total_steps": 40000, "loss": 0.0, "lr": 1.200035283634704e-06, "epoch": 632.2831858407079, "percentage": 90.1, "elapsed_time": "4:19:57", "remaining_time": "0:28:33", "throughput": 1312.29, "total_tokens": 20468808} {"current_steps": 36045, "total_steps": 40000, "loss": 0.0, "lr": 1.1970319654272144e-06, "epoch": 632.3716814159292, "percentage": 90.11, "elapsed_time": "4:19:59", "remaining_time": "0:28:31", "throughput": 1312.27, "total_tokens": 20471240} {"current_steps": 36050, "total_steps": 40000, "loss": 0.0, "lr": 1.1940323179365192e-06, "epoch": 632.4601769911504, "percentage": 90.12, "elapsed_time": "4:20:01", "remaining_time": "0:28:29", "throughput": 1312.31, "total_tokens": 20474536} {"current_steps": 36055, "total_steps": 40000, "loss": 0.0, "lr": 1.1910363416252095e-06, "epoch": 632.5486725663717, "percentage": 90.14, "elapsed_time": "4:20:04", "remaining_time": "0:28:27", "throughput": 1312.32, "total_tokens": 20477512} {"current_steps": 36060, "total_steps": 40000, "loss": 0.0, "lr": 1.1880440369552964e-06, "epoch": 632.637168141593, "percentage": 90.15, "elapsed_time": "4:20:06", "remaining_time": "0:28:25", "throughput": 1312.34, "total_tokens": 20480408} {"current_steps": 36065, "total_steps": 40000, "loss": 0.0, "lr": 1.1850554043882328e-06, "epoch": 632.7256637168142, "percentage": 90.16, "elapsed_time": "4:20:08", "remaining_time": "0:28:22", "throughput": 1312.38, "total_tokens": 20483864} {"current_steps": 36070, "total_steps": 40000, "loss": 0.0, "lr": 1.1820704443849028e-06, "epoch": 632.8141592920354, "percentage": 90.18, "elapsed_time": "4:20:10", "remaining_time": "0:28:20", "throughput": 1312.39, "total_tokens": 20486632} {"current_steps": 36075, "total_steps": 40000, "loss": 0.0, "lr": 1.1790891574056219e-06, "epoch": 632.9026548672566, "percentage": 90.19, "elapsed_time": "4:20:12", "remaining_time": "0:28:18", "throughput": 1312.4, "total_tokens": 20489480} {"current_steps": 36080, "total_steps": 40000, "loss": 0.0, "lr": 1.1761115439101523e-06, "epoch": 632.9911504424779, "percentage": 90.2, "elapsed_time": "4:20:14", "remaining_time": "0:28:16", "throughput": 1312.41, "total_tokens": 20492392} {"current_steps": 36085, "total_steps": 40000, "loss": 0.0, "lr": 1.1731376043576659e-06, "epoch": 633.070796460177, "percentage": 90.21, "elapsed_time": "4:20:16", "remaining_time": "0:28:14", "throughput": 1312.41, "total_tokens": 20495352} {"current_steps": 36090, "total_steps": 40000, "loss": 0.0, "lr": 1.1701673392067875e-06, "epoch": 633.1592920353983, "percentage": 90.22, "elapsed_time": "4:20:18", "remaining_time": "0:28:12", "throughput": 1312.42, "total_tokens": 20498184} {"current_steps": 36095, "total_steps": 40000, "loss": 0.0, "lr": 1.1672007489155757e-06, "epoch": 633.2477876106195, "percentage": 90.24, "elapsed_time": "4:20:20", "remaining_time": "0:28:09", "throughput": 1312.41, "total_tokens": 20500760} {"current_steps": 36100, "total_steps": 40000, "loss": 0.0, "lr": 1.164237833941506e-06, "epoch": 633.3362831858407, "percentage": 90.25, "elapsed_time": "4:20:22", "remaining_time": "0:28:07", "throughput": 1312.41, "total_tokens": 20503464} {"current_steps": 36105, "total_steps": 40000, "loss": 0.0, "lr": 1.1612785947415022e-06, "epoch": 633.4247787610619, "percentage": 90.26, "elapsed_time": "4:20:24", "remaining_time": "0:28:05", "throughput": 1312.41, "total_tokens": 20506168} {"current_steps": 36110, "total_steps": 40000, "loss": 0.0, "lr": 1.1583230317719185e-06, "epoch": 633.5132743362832, "percentage": 90.28, "elapsed_time": "4:20:26", "remaining_time": "0:28:03", "throughput": 1312.47, "total_tokens": 20509784} {"current_steps": 36115, "total_steps": 40000, "loss": 0.0, "lr": 1.1553711454885318e-06, "epoch": 633.6017699115044, "percentage": 90.29, "elapsed_time": "4:20:28", "remaining_time": "0:28:01", "throughput": 1312.49, "total_tokens": 20512824} {"current_steps": 36120, "total_steps": 40000, "loss": 0.0, "lr": 1.152422936346567e-06, "epoch": 633.6902654867257, "percentage": 90.3, "elapsed_time": "4:20:31", "remaining_time": "0:27:59", "throughput": 1312.5, "total_tokens": 20515640} {"current_steps": 36125, "total_steps": 40000, "loss": 0.0, "lr": 1.1494784048006718e-06, "epoch": 633.7787610619469, "percentage": 90.31, "elapsed_time": "4:20:33", "remaining_time": "0:27:56", "throughput": 1312.49, "total_tokens": 20518248} {"current_steps": 36130, "total_steps": 40000, "loss": 0.0, "lr": 1.1465375513049326e-06, "epoch": 633.8672566371681, "percentage": 90.33, "elapsed_time": "4:20:35", "remaining_time": "0:27:54", "throughput": 1312.48, "total_tokens": 20520824} {"current_steps": 36135, "total_steps": 40000, "loss": 0.0, "lr": 1.1436003763128616e-06, "epoch": 633.9557522123894, "percentage": 90.34, "elapsed_time": "4:20:37", "remaining_time": "0:27:52", "throughput": 1312.48, "total_tokens": 20523560} {"current_steps": 36140, "total_steps": 40000, "loss": 0.0, "lr": 1.1406668802774106e-06, "epoch": 634.0353982300885, "percentage": 90.35, "elapsed_time": "4:20:39", "remaining_time": "0:27:50", "throughput": 1312.46, "total_tokens": 20526128} {"current_steps": 36145, "total_steps": 40000, "loss": 0.0, "lr": 1.137737063650965e-06, "epoch": 634.1238938053098, "percentage": 90.36, "elapsed_time": "4:20:41", "remaining_time": "0:27:48", "throughput": 1312.44, "total_tokens": 20528576} {"current_steps": 36150, "total_steps": 40000, "loss": 0.0, "lr": 1.1348109268853323e-06, "epoch": 634.212389380531, "percentage": 90.38, "elapsed_time": "4:20:43", "remaining_time": "0:27:46", "throughput": 1312.45, "total_tokens": 20531360} {"current_steps": 36155, "total_steps": 40000, "loss": 0.0, "lr": 1.1318884704317634e-06, "epoch": 634.3008849557522, "percentage": 90.39, "elapsed_time": "4:20:45", "remaining_time": "0:27:43", "throughput": 1312.45, "total_tokens": 20534064} {"current_steps": 36160, "total_steps": 40000, "loss": 0.0, "lr": 1.1289696947409417e-06, "epoch": 634.3893805309734, "percentage": 90.4, "elapsed_time": "4:20:47", "remaining_time": "0:27:41", "throughput": 1312.46, "total_tokens": 20537040} {"current_steps": 36165, "total_steps": 40000, "loss": 0.0, "lr": 1.126054600262974e-06, "epoch": 634.4778761061947, "percentage": 90.41, "elapsed_time": "4:20:49", "remaining_time": "0:27:39", "throughput": 1312.48, "total_tokens": 20540064} {"current_steps": 36170, "total_steps": 40000, "loss": 0.0, "lr": 1.1231431874474064e-06, "epoch": 634.566371681416, "percentage": 90.42, "elapsed_time": "4:20:51", "remaining_time": "0:27:37", "throughput": 1312.48, "total_tokens": 20542720} {"current_steps": 36175, "total_steps": 40000, "loss": 0.0, "lr": 1.12023545674321e-06, "epoch": 634.6548672566372, "percentage": 90.44, "elapsed_time": "4:20:53", "remaining_time": "0:27:35", "throughput": 1312.5, "total_tokens": 20545760} {"current_steps": 36180, "total_steps": 40000, "loss": 0.0, "lr": 1.117331408598804e-06, "epoch": 634.7433628318585, "percentage": 90.45, "elapsed_time": "4:20:55", "remaining_time": "0:27:33", "throughput": 1312.5, "total_tokens": 20548464} {"current_steps": 36185, "total_steps": 40000, "loss": 0.0, "lr": 1.1144310434620191e-06, "epoch": 634.8318584070796, "percentage": 90.46, "elapsed_time": "4:20:58", "remaining_time": "0:27:30", "throughput": 1312.5, "total_tokens": 20551200} {"current_steps": 36190, "total_steps": 40000, "loss": 0.0, "lr": 1.1115343617801365e-06, "epoch": 634.9203539823009, "percentage": 90.48, "elapsed_time": "4:21:00", "remaining_time": "0:27:28", "throughput": 1312.55, "total_tokens": 20554720} {"current_steps": 36195, "total_steps": 40000, "loss": 0.0, "lr": 1.1086413639998515e-06, "epoch": 635.0, "percentage": 90.49, "elapsed_time": "4:21:02", "remaining_time": "0:27:26", "throughput": 1312.55, "total_tokens": 20557256} {"current_steps": 36200, "total_steps": 40000, "loss": 0.0, "lr": 1.1057520505673103e-06, "epoch": 635.0884955752213, "percentage": 90.5, "elapsed_time": "4:21:04", "remaining_time": "0:27:24", "throughput": 1312.56, "total_tokens": 20560472} {"current_steps": 36200, "total_steps": 40000, "eval_loss": 0.9129029512405396, "epoch": 635.0884955752213, "percentage": 90.5, "elapsed_time": "4:21:05", "remaining_time": "0:27:24", "throughput": 1312.47, "total_tokens": 20560472} {"current_steps": 36205, "total_steps": 40000, "loss": 0.0, "lr": 1.1028664219280727e-06, "epoch": 635.1769911504425, "percentage": 90.51, "elapsed_time": "4:21:09", "remaining_time": "0:27:22", "throughput": 1312.34, "total_tokens": 20563496} {"current_steps": 36210, "total_steps": 40000, "loss": 0.0, "lr": 1.0999844785271468e-06, "epoch": 635.2654867256637, "percentage": 90.53, "elapsed_time": "4:21:11", "remaining_time": "0:27:20", "throughput": 1312.34, "total_tokens": 20566216} {"current_steps": 36215, "total_steps": 40000, "loss": 0.0, "lr": 1.097106220808955e-06, "epoch": 635.3539823008849, "percentage": 90.54, "elapsed_time": "4:21:13", "remaining_time": "0:27:18", "throughput": 1312.35, "total_tokens": 20569064} {"current_steps": 36220, "total_steps": 40000, "loss": 0.0, "lr": 1.0942316492173698e-06, "epoch": 635.4424778761062, "percentage": 90.55, "elapsed_time": "4:21:15", "remaining_time": "0:27:15", "throughput": 1312.36, "total_tokens": 20571896} {"current_steps": 36225, "total_steps": 40000, "loss": 0.0, "lr": 1.0913607641956841e-06, "epoch": 635.5309734513274, "percentage": 90.56, "elapsed_time": "4:21:17", "remaining_time": "0:27:13", "throughput": 1312.35, "total_tokens": 20574440} {"current_steps": 36230, "total_steps": 40000, "loss": 0.0, "lr": 1.0884935661866213e-06, "epoch": 635.6194690265487, "percentage": 90.58, "elapsed_time": "4:21:19", "remaining_time": "0:27:11", "throughput": 1312.35, "total_tokens": 20577096} {"current_steps": 36235, "total_steps": 40000, "loss": 0.0, "lr": 1.0856300556323418e-06, "epoch": 635.70796460177, "percentage": 90.59, "elapsed_time": "4:21:21", "remaining_time": "0:27:09", "throughput": 1312.35, "total_tokens": 20579912} {"current_steps": 36240, "total_steps": 40000, "loss": 0.0, "lr": 1.0827702329744365e-06, "epoch": 635.7964601769911, "percentage": 90.6, "elapsed_time": "4:21:23", "remaining_time": "0:27:07", "throughput": 1312.36, "total_tokens": 20582664} {"current_steps": 36245, "total_steps": 40000, "loss": 0.0, "lr": 1.0799140986539197e-06, "epoch": 635.8849557522124, "percentage": 90.61, "elapsed_time": "4:21:25", "remaining_time": "0:27:05", "throughput": 1312.36, "total_tokens": 20585496} {"current_steps": 36250, "total_steps": 40000, "loss": 0.0, "lr": 1.0770616531112526e-06, "epoch": 635.9734513274336, "percentage": 90.62, "elapsed_time": "4:21:27", "remaining_time": "0:27:02", "throughput": 1312.38, "total_tokens": 20588536} {"current_steps": 36255, "total_steps": 40000, "loss": 0.0, "lr": 1.0742128967863085e-06, "epoch": 636.0530973451328, "percentage": 90.64, "elapsed_time": "4:21:30", "remaining_time": "0:27:00", "throughput": 1312.35, "total_tokens": 20591024} {"current_steps": 36260, "total_steps": 40000, "loss": 0.0, "lr": 1.071367830118411e-06, "epoch": 636.141592920354, "percentage": 90.65, "elapsed_time": "4:21:32", "remaining_time": "0:26:58", "throughput": 1312.33, "total_tokens": 20593424} {"current_steps": 36265, "total_steps": 40000, "loss": 0.0, "lr": 1.068526453546298e-06, "epoch": 636.2300884955753, "percentage": 90.66, "elapsed_time": "4:21:34", "remaining_time": "0:26:56", "throughput": 1312.38, "total_tokens": 20596960} {"current_steps": 36270, "total_steps": 40000, "loss": 0.0, "lr": 1.0656887675081467e-06, "epoch": 636.3185840707964, "percentage": 90.67, "elapsed_time": "4:21:36", "remaining_time": "0:26:54", "throughput": 1312.38, "total_tokens": 20599664} {"current_steps": 36275, "total_steps": 40000, "loss": 0.0, "lr": 1.0628547724415628e-06, "epoch": 636.4070796460177, "percentage": 90.69, "elapsed_time": "4:21:38", "remaining_time": "0:26:52", "throughput": 1312.41, "total_tokens": 20602688} {"current_steps": 36280, "total_steps": 40000, "loss": 0.0, "lr": 1.0600244687835881e-06, "epoch": 636.4955752212389, "percentage": 90.7, "elapsed_time": "4:21:40", "remaining_time": "0:26:49", "throughput": 1312.44, "total_tokens": 20605920} {"current_steps": 36285, "total_steps": 40000, "loss": 0.0, "lr": 1.0571978569706876e-06, "epoch": 636.5840707964602, "percentage": 90.71, "elapsed_time": "4:21:42", "remaining_time": "0:26:47", "throughput": 1312.45, "total_tokens": 20608800} {"current_steps": 36290, "total_steps": 40000, "loss": 0.0, "lr": 1.0543749374387652e-06, "epoch": 636.6725663716815, "percentage": 90.72, "elapsed_time": "4:21:44", "remaining_time": "0:26:45", "throughput": 1312.45, "total_tokens": 20611552} {"current_steps": 36295, "total_steps": 40000, "loss": 0.0, "lr": 1.051555710623142e-06, "epoch": 636.7610619469026, "percentage": 90.74, "elapsed_time": "4:21:46", "remaining_time": "0:26:43", "throughput": 1312.45, "total_tokens": 20614256} {"current_steps": 36300, "total_steps": 40000, "loss": 0.0, "lr": 1.0487401769585847e-06, "epoch": 636.8495575221239, "percentage": 90.75, "elapsed_time": "4:21:48", "remaining_time": "0:26:41", "throughput": 1312.48, "total_tokens": 20617344} {"current_steps": 36305, "total_steps": 40000, "loss": 0.0, "lr": 1.0459283368792845e-06, "epoch": 636.9380530973451, "percentage": 90.76, "elapsed_time": "4:21:50", "remaining_time": "0:26:38", "throughput": 1312.47, "total_tokens": 20619888} {"current_steps": 36310, "total_steps": 40000, "loss": 0.0, "lr": 1.043120190818858e-06, "epoch": 637.0176991150443, "percentage": 90.77, "elapsed_time": "4:21:53", "remaining_time": "0:26:36", "throughput": 1312.45, "total_tokens": 20622528} {"current_steps": 36315, "total_steps": 40000, "loss": 0.0, "lr": 1.0403157392103596e-06, "epoch": 637.1061946902655, "percentage": 90.79, "elapsed_time": "4:21:55", "remaining_time": "0:26:34", "throughput": 1312.42, "total_tokens": 20624848} {"current_steps": 36320, "total_steps": 40000, "loss": 0.0, "lr": 1.0375149824862735e-06, "epoch": 637.1946902654868, "percentage": 90.8, "elapsed_time": "4:21:57", "remaining_time": "0:26:32", "throughput": 1312.46, "total_tokens": 20628256} {"current_steps": 36325, "total_steps": 40000, "loss": 0.0, "lr": 1.034717921078507e-06, "epoch": 637.2831858407079, "percentage": 90.81, "elapsed_time": "4:21:59", "remaining_time": "0:26:30", "throughput": 1312.46, "total_tokens": 20631040} {"current_steps": 36330, "total_steps": 40000, "loss": 0.0, "lr": 1.0319245554184009e-06, "epoch": 637.3716814159292, "percentage": 90.83, "elapsed_time": "4:22:01", "remaining_time": "0:26:28", "throughput": 1312.49, "total_tokens": 20634352} {"current_steps": 36335, "total_steps": 40000, "loss": 0.0, "lr": 1.0291348859367361e-06, "epoch": 637.4601769911504, "percentage": 90.84, "elapsed_time": "4:22:03", "remaining_time": "0:26:25", "throughput": 1312.49, "total_tokens": 20637104} {"current_steps": 36340, "total_steps": 40000, "loss": 0.0, "lr": 1.0263489130637016e-06, "epoch": 637.5486725663717, "percentage": 90.85, "elapsed_time": "4:22:05", "remaining_time": "0:26:23", "throughput": 1312.51, "total_tokens": 20640240} {"current_steps": 36345, "total_steps": 40000, "loss": 0.0, "lr": 1.0235666372289427e-06, "epoch": 637.637168141593, "percentage": 90.86, "elapsed_time": "4:22:07", "remaining_time": "0:26:21", "throughput": 1312.51, "total_tokens": 20643136} {"current_steps": 36350, "total_steps": 40000, "loss": 0.0, "lr": 1.0207880588615076e-06, "epoch": 637.7256637168142, "percentage": 90.88, "elapsed_time": "4:22:10", "remaining_time": "0:26:19", "throughput": 1312.52, "total_tokens": 20646000} {"current_steps": 36355, "total_steps": 40000, "loss": 0.0, "lr": 1.0180131783898984e-06, "epoch": 637.8141592920354, "percentage": 90.89, "elapsed_time": "4:22:12", "remaining_time": "0:26:17", "throughput": 1312.5, "total_tokens": 20648592} {"current_steps": 36360, "total_steps": 40000, "loss": 0.0, "lr": 1.0152419962420362e-06, "epoch": 637.9026548672566, "percentage": 90.9, "elapsed_time": "4:22:14", "remaining_time": "0:26:15", "throughput": 1312.51, "total_tokens": 20651536} {"current_steps": 36365, "total_steps": 40000, "loss": 0.0, "lr": 1.0124745128452685e-06, "epoch": 637.9911504424779, "percentage": 90.91, "elapsed_time": "4:22:16", "remaining_time": "0:26:12", "throughput": 1312.52, "total_tokens": 20654448} {"current_steps": 36370, "total_steps": 40000, "loss": 0.0, "lr": 1.0097107286263758e-06, "epoch": 638.070796460177, "percentage": 90.92, "elapsed_time": "4:22:18", "remaining_time": "0:26:10", "throughput": 1312.5, "total_tokens": 20657120} {"current_steps": 36375, "total_steps": 40000, "loss": 0.0, "lr": 1.00695064401157e-06, "epoch": 638.1592920353983, "percentage": 90.94, "elapsed_time": "4:22:20", "remaining_time": "0:26:08", "throughput": 1312.49, "total_tokens": 20659856} {"current_steps": 36380, "total_steps": 40000, "loss": 0.0, "lr": 1.0041942594264886e-06, "epoch": 638.2477876106195, "percentage": 90.95, "elapsed_time": "4:22:23", "remaining_time": "0:26:06", "throughput": 1312.47, "total_tokens": 20662240} {"current_steps": 36385, "total_steps": 40000, "loss": 0.0, "lr": 1.001441575296208e-06, "epoch": 638.3362831858407, "percentage": 90.96, "elapsed_time": "4:22:25", "remaining_time": "0:26:04", "throughput": 1312.46, "total_tokens": 20664880} {"current_steps": 36390, "total_steps": 40000, "loss": 0.0, "lr": 9.986925920452139e-07, "epoch": 638.4247787610619, "percentage": 90.97, "elapsed_time": "4:22:27", "remaining_time": "0:26:02", "throughput": 1312.48, "total_tokens": 20668016} {"current_steps": 36395, "total_steps": 40000, "loss": 0.0, "lr": 9.959473100974475e-07, "epoch": 638.5132743362832, "percentage": 90.99, "elapsed_time": "4:22:29", "remaining_time": "0:26:00", "throughput": 1312.48, "total_tokens": 20670928} {"current_steps": 36400, "total_steps": 40000, "loss": 0.0, "lr": 9.932057298762564e-07, "epoch": 638.6017699115044, "percentage": 91.0, "elapsed_time": "4:22:31", "remaining_time": "0:25:57", "throughput": 1312.5, "total_tokens": 20673984} {"current_steps": 36400, "total_steps": 40000, "eval_loss": 0.8988261818885803, "epoch": 638.6017699115044, "percentage": 91.0, "elapsed_time": "4:22:32", "remaining_time": "0:25:57", "throughput": 1312.41, "total_tokens": 20673984} {"current_steps": 36405, "total_steps": 40000, "loss": 0.0, "lr": 9.90467851804433e-07, "epoch": 638.6902654867257, "percentage": 91.01, "elapsed_time": "4:22:36", "remaining_time": "0:25:55", "throughput": 1312.28, "total_tokens": 20677056} {"current_steps": 36410, "total_steps": 40000, "loss": 0.0, "lr": 9.877336763041895e-07, "epoch": 638.7787610619469, "percentage": 91.03, "elapsed_time": "4:22:38", "remaining_time": "0:25:53", "throughput": 1312.29, "total_tokens": 20680048} {"current_steps": 36415, "total_steps": 40000, "loss": 0.0, "lr": 9.850032037971662e-07, "epoch": 638.8672566371681, "percentage": 91.04, "elapsed_time": "4:22:40", "remaining_time": "0:25:51", "throughput": 1312.29, "total_tokens": 20682864} {"current_steps": 36420, "total_steps": 40000, "loss": 0.0, "lr": 9.822764347044406e-07, "epoch": 638.9557522123894, "percentage": 91.05, "elapsed_time": "4:22:43", "remaining_time": "0:25:49", "throughput": 1312.26, "total_tokens": 20685248} {"current_steps": 36425, "total_steps": 40000, "loss": 0.0, "lr": 9.795533694465175e-07, "epoch": 639.0353982300885, "percentage": 91.06, "elapsed_time": "4:22:45", "remaining_time": "0:25:47", "throughput": 1312.22, "total_tokens": 20687624} {"current_steps": 36430, "total_steps": 40000, "loss": 0.0, "lr": 9.768340084433197e-07, "epoch": 639.1238938053098, "percentage": 91.07, "elapsed_time": "4:22:47", "remaining_time": "0:25:45", "throughput": 1312.19, "total_tokens": 20689992} {"current_steps": 36435, "total_steps": 40000, "loss": 0.0, "lr": 9.741183521142143e-07, "epoch": 639.212389380531, "percentage": 91.09, "elapsed_time": "4:22:49", "remaining_time": "0:25:42", "throughput": 1312.18, "total_tokens": 20692520} {"current_steps": 36440, "total_steps": 40000, "loss": 0.0, "lr": 9.714064008779889e-07, "epoch": 639.3008849557522, "percentage": 91.1, "elapsed_time": "4:22:51", "remaining_time": "0:25:40", "throughput": 1312.17, "total_tokens": 20695176} {"current_steps": 36445, "total_steps": 40000, "loss": 0.0, "lr": 9.686981551528584e-07, "epoch": 639.3893805309734, "percentage": 91.11, "elapsed_time": "4:22:53", "remaining_time": "0:25:38", "throughput": 1312.21, "total_tokens": 20698584} {"current_steps": 36450, "total_steps": 40000, "loss": 0.0, "lr": 9.65993615356467e-07, "epoch": 639.4778761061947, "percentage": 91.12, "elapsed_time": "4:22:56", "remaining_time": "0:25:36", "throughput": 1312.21, "total_tokens": 20701416} {"current_steps": 36455, "total_steps": 40000, "loss": 0.0, "lr": 9.632927819058917e-07, "epoch": 639.566371681416, "percentage": 91.14, "elapsed_time": "4:22:58", "remaining_time": "0:25:34", "throughput": 1312.24, "total_tokens": 20704680} {"current_steps": 36460, "total_steps": 40000, "loss": 0.0, "lr": 9.605956552176305e-07, "epoch": 639.6548672566372, "percentage": 91.15, "elapsed_time": "4:23:00", "remaining_time": "0:25:32", "throughput": 1312.22, "total_tokens": 20707304} {"current_steps": 36465, "total_steps": 40000, "loss": 0.0, "lr": 9.579022357076223e-07, "epoch": 639.7433628318585, "percentage": 91.16, "elapsed_time": "4:23:02", "remaining_time": "0:25:29", "throughput": 1312.24, "total_tokens": 20710280} {"current_steps": 36470, "total_steps": 40000, "loss": 0.0, "lr": 9.552125237912158e-07, "epoch": 639.8318584070796, "percentage": 91.17, "elapsed_time": "4:23:04", "remaining_time": "0:25:27", "throughput": 1312.25, "total_tokens": 20713256} {"current_steps": 36475, "total_steps": 40000, "loss": 0.0, "lr": 9.525265198832096e-07, "epoch": 639.9203539823009, "percentage": 91.19, "elapsed_time": "4:23:06", "remaining_time": "0:25:25", "throughput": 1312.29, "total_tokens": 20716728} {"current_steps": 36480, "total_steps": 40000, "loss": 0.0, "lr": 9.498442243978112e-07, "epoch": 640.0, "percentage": 91.2, "elapsed_time": "4:23:08", "remaining_time": "0:25:23", "throughput": 1312.26, "total_tokens": 20718920} {"current_steps": 36485, "total_steps": 40000, "loss": 0.0, "lr": 9.471656377486649e-07, "epoch": 640.0884955752213, "percentage": 91.21, "elapsed_time": "4:23:11", "remaining_time": "0:25:21", "throughput": 1312.22, "total_tokens": 20721464} {"current_steps": 36490, "total_steps": 40000, "loss": 0.0, "lr": 9.444907603488456e-07, "epoch": 640.1769911504425, "percentage": 91.22, "elapsed_time": "4:23:13", "remaining_time": "0:25:19", "throughput": 1312.24, "total_tokens": 20724536} {"current_steps": 36495, "total_steps": 40000, "loss": 0.0, "lr": 9.418195926108514e-07, "epoch": 640.2654867256637, "percentage": 91.24, "elapsed_time": "4:23:15", "remaining_time": "0:25:17", "throughput": 1312.25, "total_tokens": 20727496} {"current_steps": 36500, "total_steps": 40000, "loss": 0.0, "lr": 9.391521349466053e-07, "epoch": 640.3539823008849, "percentage": 91.25, "elapsed_time": "4:23:17", "remaining_time": "0:25:14", "throughput": 1312.25, "total_tokens": 20730328} {"current_steps": 36505, "total_steps": 40000, "loss": 0.0, "lr": 9.364883877674758e-07, "epoch": 640.4424778761062, "percentage": 91.26, "elapsed_time": "4:23:19", "remaining_time": "0:25:12", "throughput": 1312.23, "total_tokens": 20732840} {"current_steps": 36510, "total_steps": 40000, "loss": 0.0, "lr": 9.33828351484231e-07, "epoch": 640.5309734513274, "percentage": 91.27, "elapsed_time": "4:23:21", "remaining_time": "0:25:10", "throughput": 1312.22, "total_tokens": 20735528} {"current_steps": 36515, "total_steps": 40000, "loss": 0.0, "lr": 9.311720265070906e-07, "epoch": 640.6194690265487, "percentage": 91.29, "elapsed_time": "4:23:23", "remaining_time": "0:25:08", "throughput": 1312.24, "total_tokens": 20738520} {"current_steps": 36520, "total_steps": 40000, "loss": 0.0, "lr": 9.285194132456931e-07, "epoch": 640.70796460177, "percentage": 91.3, "elapsed_time": "4:23:26", "remaining_time": "0:25:06", "throughput": 1312.25, "total_tokens": 20741624} {"current_steps": 36525, "total_steps": 40000, "loss": 0.0, "lr": 9.258705121091032e-07, "epoch": 640.7964601769911, "percentage": 91.31, "elapsed_time": "4:23:28", "remaining_time": "0:25:04", "throughput": 1312.3, "total_tokens": 20745176} {"current_steps": 36530, "total_steps": 40000, "loss": 0.0, "lr": 9.232253235058136e-07, "epoch": 640.8849557522124, "percentage": 91.33, "elapsed_time": "4:23:30", "remaining_time": "0:25:01", "throughput": 1312.3, "total_tokens": 20748024} {"current_steps": 36535, "total_steps": 40000, "loss": 0.0, "lr": 9.205838478437478e-07, "epoch": 640.9734513274336, "percentage": 91.34, "elapsed_time": "4:23:32", "remaining_time": "0:24:59", "throughput": 1312.29, "total_tokens": 20750584} {"current_steps": 36540, "total_steps": 40000, "loss": 0.0, "lr": 9.179460855302524e-07, "epoch": 641.0530973451328, "percentage": 91.35, "elapsed_time": "4:23:34", "remaining_time": "0:24:57", "throughput": 1312.24, "total_tokens": 20752816} {"current_steps": 36545, "total_steps": 40000, "loss": 0.0, "lr": 9.153120369721046e-07, "epoch": 641.141592920354, "percentage": 91.36, "elapsed_time": "4:23:36", "remaining_time": "0:24:55", "throughput": 1312.23, "total_tokens": 20755440} {"current_steps": 36550, "total_steps": 40000, "loss": 0.0, "lr": 9.126817025755103e-07, "epoch": 641.2300884955753, "percentage": 91.38, "elapsed_time": "4:23:39", "remaining_time": "0:24:53", "throughput": 1312.21, "total_tokens": 20757968} {"current_steps": 36555, "total_steps": 40000, "loss": 0.0, "lr": 9.100550827460947e-07, "epoch": 641.3185840707964, "percentage": 91.39, "elapsed_time": "4:23:41", "remaining_time": "0:24:51", "throughput": 1312.24, "total_tokens": 20761344} {"current_steps": 36560, "total_steps": 40000, "loss": 0.0, "lr": 9.0743217788892e-07, "epoch": 641.4070796460177, "percentage": 91.4, "elapsed_time": "4:23:43", "remaining_time": "0:24:48", "throughput": 1312.22, "total_tokens": 20763728} {"current_steps": 36565, "total_steps": 40000, "loss": 0.0, "lr": 9.048129884084683e-07, "epoch": 641.4955752212389, "percentage": 91.41, "elapsed_time": "4:23:45", "remaining_time": "0:24:46", "throughput": 1312.22, "total_tokens": 20766512} {"current_steps": 36570, "total_steps": 40000, "loss": 0.0, "lr": 9.021975147086553e-07, "epoch": 641.5840707964602, "percentage": 91.42, "elapsed_time": "4:23:47", "remaining_time": "0:24:44", "throughput": 1312.21, "total_tokens": 20769168} {"current_steps": 36575, "total_steps": 40000, "loss": 0.0, "lr": 8.995857571928141e-07, "epoch": 641.6725663716815, "percentage": 91.44, "elapsed_time": "4:23:49", "remaining_time": "0:24:42", "throughput": 1312.18, "total_tokens": 20771456} {"current_steps": 36580, "total_steps": 40000, "loss": 0.0, "lr": 8.969777162637139e-07, "epoch": 641.7610619469026, "percentage": 91.45, "elapsed_time": "4:23:51", "remaining_time": "0:24:40", "throughput": 1312.24, "total_tokens": 20775248} {"current_steps": 36585, "total_steps": 40000, "loss": 0.0, "lr": 8.943733923235525e-07, "epoch": 641.8495575221239, "percentage": 91.46, "elapsed_time": "4:23:54", "remaining_time": "0:24:38", "throughput": 1312.26, "total_tokens": 20778432} {"current_steps": 36590, "total_steps": 40000, "loss": 0.0, "lr": 8.917727857739394e-07, "epoch": 641.9380530973451, "percentage": 91.47, "elapsed_time": "4:23:56", "remaining_time": "0:24:35", "throughput": 1312.26, "total_tokens": 20781216} {"current_steps": 36595, "total_steps": 40000, "loss": 0.0, "lr": 8.891758970159258e-07, "epoch": 642.0176991150443, "percentage": 91.49, "elapsed_time": "4:23:58", "remaining_time": "0:24:33", "throughput": 1312.24, "total_tokens": 20783856} {"current_steps": 36600, "total_steps": 40000, "loss": 0.0, "lr": 8.86582726449986e-07, "epoch": 642.1061946902655, "percentage": 91.5, "elapsed_time": "4:24:00", "remaining_time": "0:24:31", "throughput": 1312.21, "total_tokens": 20786240} {"current_steps": 36600, "total_steps": 40000, "eval_loss": 0.8976834416389465, "epoch": 642.1061946902655, "percentage": 91.5, "elapsed_time": "4:24:01", "remaining_time": "0:24:31", "throughput": 1312.12, "total_tokens": 20786240} {"current_steps": 36605, "total_steps": 40000, "loss": 0.0, "lr": 8.839932744760165e-07, "epoch": 642.1946902654868, "percentage": 91.51, "elapsed_time": "4:24:05", "remaining_time": "0:24:29", "throughput": 1311.97, "total_tokens": 20789136} {"current_steps": 36610, "total_steps": 40000, "loss": 0.0, "lr": 8.814075414933482e-07, "epoch": 642.2831858407079, "percentage": 91.53, "elapsed_time": "4:24:07", "remaining_time": "0:24:27", "throughput": 1312.0, "total_tokens": 20792432} {"current_steps": 36615, "total_steps": 40000, "loss": 0.0, "lr": 8.788255279007257e-07, "epoch": 642.3716814159292, "percentage": 91.54, "elapsed_time": "4:24:10", "remaining_time": "0:24:25", "throughput": 1312.01, "total_tokens": 20795424} {"current_steps": 36620, "total_steps": 40000, "loss": 0.0, "lr": 8.762472340963362e-07, "epoch": 642.4601769911504, "percentage": 91.55, "elapsed_time": "4:24:12", "remaining_time": "0:24:23", "throughput": 1312.01, "total_tokens": 20798112} {"current_steps": 36625, "total_steps": 40000, "loss": 0.0, "lr": 8.736726604777811e-07, "epoch": 642.5486725663717, "percentage": 91.56, "elapsed_time": "4:24:14", "remaining_time": "0:24:20", "throughput": 1312.03, "total_tokens": 20801360} {"current_steps": 36630, "total_steps": 40000, "loss": 0.0, "lr": 8.711018074420901e-07, "epoch": 642.637168141593, "percentage": 91.57, "elapsed_time": "4:24:16", "remaining_time": "0:24:18", "throughput": 1312.05, "total_tokens": 20804464} {"current_steps": 36635, "total_steps": 40000, "loss": 0.0, "lr": 8.685346753857209e-07, "epoch": 642.7256637168142, "percentage": 91.59, "elapsed_time": "4:24:18", "remaining_time": "0:24:16", "throughput": 1312.04, "total_tokens": 20807040} {"current_steps": 36640, "total_steps": 40000, "loss": 0.0, "lr": 8.659712647045654e-07, "epoch": 642.8141592920354, "percentage": 91.6, "elapsed_time": "4:24:20", "remaining_time": "0:24:14", "throughput": 1312.03, "total_tokens": 20809696} {"current_steps": 36645, "total_steps": 40000, "loss": 0.0, "lr": 8.634115757939209e-07, "epoch": 642.9026548672566, "percentage": 91.61, "elapsed_time": "4:24:22", "remaining_time": "0:24:12", "throughput": 1312.02, "total_tokens": 20812320} {"current_steps": 36650, "total_steps": 40000, "loss": 0.0, "lr": 8.608556090485387e-07, "epoch": 642.9911504424779, "percentage": 91.62, "elapsed_time": "4:24:24", "remaining_time": "0:24:10", "throughput": 1312.01, "total_tokens": 20814832} {"current_steps": 36655, "total_steps": 40000, "loss": 0.0, "lr": 8.583033648625671e-07, "epoch": 643.070796460177, "percentage": 91.64, "elapsed_time": "4:24:27", "remaining_time": "0:24:07", "throughput": 1311.97, "total_tokens": 20817328} {"current_steps": 36660, "total_steps": 40000, "loss": 0.0, "lr": 8.557548436295998e-07, "epoch": 643.1592920353983, "percentage": 91.65, "elapsed_time": "4:24:29", "remaining_time": "0:24:05", "throughput": 1311.98, "total_tokens": 20820272} {"current_steps": 36665, "total_steps": 40000, "loss": 0.0, "lr": 8.532100457426556e-07, "epoch": 643.2477876106195, "percentage": 91.66, "elapsed_time": "4:24:31", "remaining_time": "0:24:03", "throughput": 1311.97, "total_tokens": 20822992} {"current_steps": 36670, "total_steps": 40000, "loss": 0.0, "lr": 8.506689715941679e-07, "epoch": 643.3362831858407, "percentage": 91.67, "elapsed_time": "4:24:33", "remaining_time": "0:24:01", "throughput": 1311.98, "total_tokens": 20825984} {"current_steps": 36675, "total_steps": 40000, "loss": 0.0, "lr": 8.481316215760011e-07, "epoch": 643.4247787610619, "percentage": 91.69, "elapsed_time": "4:24:35", "remaining_time": "0:23:59", "throughput": 1311.98, "total_tokens": 20828704} {"current_steps": 36680, "total_steps": 40000, "loss": 0.0, "lr": 8.455979960794558e-07, "epoch": 643.5132743362832, "percentage": 91.7, "elapsed_time": "4:24:37", "remaining_time": "0:23:57", "throughput": 1311.99, "total_tokens": 20831696} {"current_steps": 36685, "total_steps": 40000, "loss": 0.0, "lr": 8.430680954952364e-07, "epoch": 643.6017699115044, "percentage": 91.71, "elapsed_time": "4:24:40", "remaining_time": "0:23:54", "throughput": 1312.01, "total_tokens": 20834800} {"current_steps": 36690, "total_steps": 40000, "loss": 0.0, "lr": 8.405419202134974e-07, "epoch": 643.6902654867257, "percentage": 91.72, "elapsed_time": "4:24:42", "remaining_time": "0:23:52", "throughput": 1312.02, "total_tokens": 20837744} {"current_steps": 36695, "total_steps": 40000, "loss": 0.0, "lr": 8.380194706237993e-07, "epoch": 643.7787610619469, "percentage": 91.74, "elapsed_time": "4:24:44", "remaining_time": "0:23:50", "throughput": 1312.01, "total_tokens": 20840480} {"current_steps": 36700, "total_steps": 40000, "loss": 0.0, "lr": 8.355007471151366e-07, "epoch": 643.8672566371681, "percentage": 91.75, "elapsed_time": "4:24:46", "remaining_time": "0:23:48", "throughput": 1312.0, "total_tokens": 20843088} {"current_steps": 36705, "total_steps": 40000, "loss": 0.0, "lr": 8.329857500759292e-07, "epoch": 643.9557522123894, "percentage": 91.76, "elapsed_time": "4:24:48", "remaining_time": "0:23:46", "throughput": 1312.03, "total_tokens": 20846304} {"current_steps": 36710, "total_steps": 40000, "loss": 0.0, "lr": 8.304744798940194e-07, "epoch": 644.0353982300885, "percentage": 91.77, "elapsed_time": "4:24:50", "remaining_time": "0:23:44", "throughput": 1311.96, "total_tokens": 20848320} {"current_steps": 36715, "total_steps": 40000, "loss": 0.0, "lr": 8.279669369566756e-07, "epoch": 644.1238938053098, "percentage": 91.79, "elapsed_time": "4:24:53", "remaining_time": "0:23:41", "throughput": 1311.96, "total_tokens": 20851008} {"current_steps": 36720, "total_steps": 40000, "loss": 0.0, "lr": 8.254631216505993e-07, "epoch": 644.212389380531, "percentage": 91.8, "elapsed_time": "4:24:55", "remaining_time": "0:23:39", "throughput": 1311.96, "total_tokens": 20853856} {"current_steps": 36725, "total_steps": 40000, "loss": 0.0, "lr": 8.229630343619038e-07, "epoch": 644.3008849557522, "percentage": 91.81, "elapsed_time": "4:24:57", "remaining_time": "0:23:37", "throughput": 1311.98, "total_tokens": 20857056} {"current_steps": 36730, "total_steps": 40000, "loss": 0.0, "lr": 8.204666754761392e-07, "epoch": 644.3893805309734, "percentage": 91.83, "elapsed_time": "4:24:59", "remaining_time": "0:23:35", "throughput": 1312.0, "total_tokens": 20860064} {"current_steps": 36735, "total_steps": 40000, "loss": 0.0, "lr": 8.179740453782669e-07, "epoch": 644.4778761061947, "percentage": 91.84, "elapsed_time": "4:25:01", "remaining_time": "0:23:33", "throughput": 1312.02, "total_tokens": 20863216} {"current_steps": 36740, "total_steps": 40000, "loss": 0.0, "lr": 8.154851444526907e-07, "epoch": 644.566371681416, "percentage": 91.85, "elapsed_time": "4:25:03", "remaining_time": "0:23:31", "throughput": 1312.04, "total_tokens": 20866288} {"current_steps": 36745, "total_steps": 40000, "loss": 0.0, "lr": 8.129999730832283e-07, "epoch": 644.6548672566372, "percentage": 91.86, "elapsed_time": "4:25:05", "remaining_time": "0:23:28", "throughput": 1312.02, "total_tokens": 20868816} {"current_steps": 36750, "total_steps": 40000, "loss": 0.0, "lr": 8.105185316531178e-07, "epoch": 644.7433628318585, "percentage": 91.88, "elapsed_time": "4:25:08", "remaining_time": "0:23:26", "throughput": 1311.98, "total_tokens": 20871056} {"current_steps": 36755, "total_steps": 40000, "loss": 0.0, "lr": 8.08040820545039e-07, "epoch": 644.8318584070796, "percentage": 91.89, "elapsed_time": "4:25:10", "remaining_time": "0:23:24", "throughput": 1312.0, "total_tokens": 20874096} {"current_steps": 36760, "total_steps": 40000, "loss": 0.0, "lr": 8.055668401410782e-07, "epoch": 644.9203539823009, "percentage": 91.9, "elapsed_time": "4:25:12", "remaining_time": "0:23:22", "throughput": 1312.02, "total_tokens": 20877168} {"current_steps": 36765, "total_steps": 40000, "loss": 0.0, "lr": 8.030965908227578e-07, "epoch": 645.0, "percentage": 91.91, "elapsed_time": "4:25:14", "remaining_time": "0:23:20", "throughput": 1311.99, "total_tokens": 20879464} {"current_steps": 36770, "total_steps": 40000, "loss": 0.0, "lr": 8.006300729710203e-07, "epoch": 645.0884955752213, "percentage": 91.92, "elapsed_time": "4:25:16", "remaining_time": "0:23:18", "throughput": 1311.97, "total_tokens": 20882296} {"current_steps": 36775, "total_steps": 40000, "loss": 0.0, "lr": 7.981672869662337e-07, "epoch": 645.1769911504425, "percentage": 91.94, "elapsed_time": "4:25:18", "remaining_time": "0:23:16", "throughput": 1311.99, "total_tokens": 20885384} {"current_steps": 36780, "total_steps": 40000, "loss": 0.0, "lr": 7.957082331881888e-07, "epoch": 645.2654867256637, "percentage": 91.95, "elapsed_time": "4:25:20", "remaining_time": "0:23:13", "throughput": 1311.96, "total_tokens": 20887736} {"current_steps": 36785, "total_steps": 40000, "loss": 0.0, "lr": 7.932529120161069e-07, "epoch": 645.3539823008849, "percentage": 91.96, "elapsed_time": "4:25:23", "remaining_time": "0:23:11", "throughput": 1311.97, "total_tokens": 20890680} {"current_steps": 36790, "total_steps": 40000, "loss": 0.0, "lr": 7.908013238286243e-07, "epoch": 645.4424778761062, "percentage": 91.97, "elapsed_time": "4:25:25", "remaining_time": "0:23:09", "throughput": 1311.97, "total_tokens": 20893480} {"current_steps": 36795, "total_steps": 40000, "loss": 0.0, "lr": 7.883534690038136e-07, "epoch": 645.5309734513274, "percentage": 91.99, "elapsed_time": "4:25:27", "remaining_time": "0:23:07", "throughput": 1311.97, "total_tokens": 20896312} {"current_steps": 36800, "total_steps": 40000, "loss": 0.0, "lr": 7.859093479191559e-07, "epoch": 645.6194690265487, "percentage": 92.0, "elapsed_time": "4:25:29", "remaining_time": "0:23:05", "throughput": 1311.97, "total_tokens": 20899128} {"current_steps": 36800, "total_steps": 40000, "eval_loss": 0.8956204652786255, "epoch": 645.6194690265487, "percentage": 92.0, "elapsed_time": "4:25:30", "remaining_time": "0:23:05", "throughput": 1311.88, "total_tokens": 20899128} {"current_steps": 36805, "total_steps": 40000, "loss": 0.0, "lr": 7.834689609515722e-07, "epoch": 645.70796460177, "percentage": 92.01, "elapsed_time": "4:25:34", "remaining_time": "0:23:03", "throughput": 1311.73, "total_tokens": 20901880} {"current_steps": 36810, "total_steps": 40000, "loss": 0.0, "lr": 7.810323084774002e-07, "epoch": 645.7964601769911, "percentage": 92.03, "elapsed_time": "4:25:36", "remaining_time": "0:23:01", "throughput": 1311.74, "total_tokens": 20904840} {"current_steps": 36815, "total_steps": 40000, "loss": 0.0, "lr": 7.785993908723976e-07, "epoch": 645.8849557522124, "percentage": 92.04, "elapsed_time": "4:25:38", "remaining_time": "0:22:58", "throughput": 1311.74, "total_tokens": 20907688} {"current_steps": 36820, "total_steps": 40000, "loss": 0.0, "lr": 7.761702085117534e-07, "epoch": 645.9734513274336, "percentage": 92.05, "elapsed_time": "4:25:40", "remaining_time": "0:22:56", "throughput": 1311.78, "total_tokens": 20911096} {"current_steps": 36825, "total_steps": 40000, "loss": 0.0, "lr": 7.737447617700844e-07, "epoch": 646.0530973451328, "percentage": 92.06, "elapsed_time": "4:25:43", "remaining_time": "0:22:54", "throughput": 1311.77, "total_tokens": 20913912} {"current_steps": 36830, "total_steps": 40000, "loss": 0.0, "lr": 7.713230510214136e-07, "epoch": 646.141592920354, "percentage": 92.07, "elapsed_time": "4:25:45", "remaining_time": "0:22:52", "throughput": 1311.77, "total_tokens": 20916776} {"current_steps": 36835, "total_steps": 40000, "loss": 0.0, "lr": 7.689050766392092e-07, "epoch": 646.2300884955753, "percentage": 92.09, "elapsed_time": "4:25:47", "remaining_time": "0:22:50", "throughput": 1311.78, "total_tokens": 20919736} {"current_steps": 36840, "total_steps": 40000, "loss": 0.0, "lr": 7.664908389963477e-07, "epoch": 646.3185840707964, "percentage": 92.1, "elapsed_time": "4:25:49", "remaining_time": "0:22:48", "throughput": 1311.8, "total_tokens": 20922872} {"current_steps": 36845, "total_steps": 40000, "loss": 0.0, "lr": 7.64080338465134e-07, "epoch": 646.4070796460177, "percentage": 92.11, "elapsed_time": "4:25:51", "remaining_time": "0:22:45", "throughput": 1311.78, "total_tokens": 20925352} {"current_steps": 36850, "total_steps": 40000, "loss": 0.0, "lr": 7.616735754173043e-07, "epoch": 646.4955752212389, "percentage": 92.12, "elapsed_time": "4:25:53", "remaining_time": "0:22:43", "throughput": 1311.77, "total_tokens": 20928024} {"current_steps": 36855, "total_steps": 40000, "loss": 0.0, "lr": 7.592705502240005e-07, "epoch": 646.5840707964602, "percentage": 92.14, "elapsed_time": "4:25:56", "remaining_time": "0:22:41", "throughput": 1311.77, "total_tokens": 20930792} {"current_steps": 36860, "total_steps": 40000, "loss": 0.0, "lr": 7.568712632558095e-07, "epoch": 646.6725663716815, "percentage": 92.15, "elapsed_time": "4:25:58", "remaining_time": "0:22:39", "throughput": 1311.78, "total_tokens": 20933800} {"current_steps": 36865, "total_steps": 40000, "loss": 0.0, "lr": 7.544757148827297e-07, "epoch": 646.7610619469026, "percentage": 92.16, "elapsed_time": "4:26:00", "remaining_time": "0:22:37", "throughput": 1311.79, "total_tokens": 20936744} {"current_steps": 36870, "total_steps": 40000, "loss": 0.0, "lr": 7.520839054741797e-07, "epoch": 646.8495575221239, "percentage": 92.17, "elapsed_time": "4:26:02", "remaining_time": "0:22:35", "throughput": 1311.8, "total_tokens": 20939656} {"current_steps": 36875, "total_steps": 40000, "loss": 0.0, "lr": 7.496958353990113e-07, "epoch": 646.9380530973451, "percentage": 92.19, "elapsed_time": "4:26:04", "remaining_time": "0:22:32", "throughput": 1311.81, "total_tokens": 20942680} {"current_steps": 36880, "total_steps": 40000, "loss": 0.0, "lr": 7.473115050254941e-07, "epoch": 647.0176991150443, "percentage": 92.2, "elapsed_time": "4:26:07", "remaining_time": "0:22:30", "throughput": 1311.75, "total_tokens": 20944744} {"current_steps": 36885, "total_steps": 40000, "loss": 0.0, "lr": 7.449309147213173e-07, "epoch": 647.1061946902655, "percentage": 92.21, "elapsed_time": "4:26:09", "remaining_time": "0:22:28", "throughput": 1311.75, "total_tokens": 20947528} {"current_steps": 36890, "total_steps": 40000, "loss": 0.0, "lr": 7.425540648536067e-07, "epoch": 647.1946902654868, "percentage": 92.22, "elapsed_time": "4:26:11", "remaining_time": "0:22:26", "throughput": 1311.74, "total_tokens": 20950200} {"current_steps": 36895, "total_steps": 40000, "loss": 0.0, "lr": 7.40180955788894e-07, "epoch": 647.2831858407079, "percentage": 92.24, "elapsed_time": "4:26:13", "remaining_time": "0:22:24", "throughput": 1311.72, "total_tokens": 20952680} {"current_steps": 36900, "total_steps": 40000, "loss": 0.0, "lr": 7.378115878931474e-07, "epoch": 647.3716814159292, "percentage": 92.25, "elapsed_time": "4:26:15", "remaining_time": "0:22:22", "throughput": 1311.71, "total_tokens": 20955272} {"current_steps": 36905, "total_steps": 40000, "loss": 0.0, "lr": 7.354459615317527e-07, "epoch": 647.4601769911504, "percentage": 92.26, "elapsed_time": "4:26:17", "remaining_time": "0:22:19", "throughput": 1311.72, "total_tokens": 20958232} {"current_steps": 36910, "total_steps": 40000, "loss": 0.0, "lr": 7.33084077069518e-07, "epoch": 647.5486725663717, "percentage": 92.27, "elapsed_time": "4:26:19", "remaining_time": "0:22:17", "throughput": 1311.76, "total_tokens": 20961640} {"current_steps": 36915, "total_steps": 40000, "loss": 0.0, "lr": 7.307259348706768e-07, "epoch": 647.637168141593, "percentage": 92.29, "elapsed_time": "4:26:21", "remaining_time": "0:22:15", "throughput": 1311.77, "total_tokens": 20964552} {"current_steps": 36920, "total_steps": 40000, "loss": 0.0, "lr": 7.283715352988801e-07, "epoch": 647.7256637168142, "percentage": 92.3, "elapsed_time": "4:26:24", "remaining_time": "0:22:13", "throughput": 1311.76, "total_tokens": 20967304} {"current_steps": 36925, "total_steps": 40000, "loss": 0.0, "lr": 7.260208787172068e-07, "epoch": 647.8141592920354, "percentage": 92.31, "elapsed_time": "4:26:26", "remaining_time": "0:22:11", "throughput": 1311.79, "total_tokens": 20970504} {"current_steps": 36930, "total_steps": 40000, "loss": 0.0, "lr": 7.23673965488167e-07, "epoch": 647.9026548672566, "percentage": 92.33, "elapsed_time": "4:26:28", "remaining_time": "0:22:09", "throughput": 1311.78, "total_tokens": 20973240} {"current_steps": 36935, "total_steps": 40000, "loss": 0.0, "lr": 7.213307959736709e-07, "epoch": 647.9911504424779, "percentage": 92.34, "elapsed_time": "4:26:30", "remaining_time": "0:22:06", "throughput": 1311.8, "total_tokens": 20976248} {"current_steps": 36940, "total_steps": 40000, "loss": 0.0, "lr": 7.189913705350715e-07, "epoch": 648.070796460177, "percentage": 92.35, "elapsed_time": "4:26:32", "remaining_time": "0:22:04", "throughput": 1311.77, "total_tokens": 20978880} {"current_steps": 36945, "total_steps": 40000, "loss": 0.0, "lr": 7.166556895331411e-07, "epoch": 648.1592920353983, "percentage": 92.36, "elapsed_time": "4:26:34", "remaining_time": "0:22:02", "throughput": 1311.76, "total_tokens": 20981456} {"current_steps": 36950, "total_steps": 40000, "loss": 0.0, "lr": 7.143237533280639e-07, "epoch": 648.2477876106195, "percentage": 92.38, "elapsed_time": "4:26:37", "remaining_time": "0:22:00", "throughput": 1311.75, "total_tokens": 20984208} {"current_steps": 36955, "total_steps": 40000, "loss": 0.0, "lr": 7.119955622794578e-07, "epoch": 648.3362831858407, "percentage": 92.39, "elapsed_time": "4:26:39", "remaining_time": "0:21:58", "throughput": 1311.75, "total_tokens": 20986896} {"current_steps": 36960, "total_steps": 40000, "loss": 0.0, "lr": 7.096711167463577e-07, "epoch": 648.4247787610619, "percentage": 92.4, "elapsed_time": "4:26:41", "remaining_time": "0:21:56", "throughput": 1311.73, "total_tokens": 20989504} {"current_steps": 36965, "total_steps": 40000, "loss": 0.0, "lr": 7.073504170872213e-07, "epoch": 648.5132743362832, "percentage": 92.41, "elapsed_time": "4:26:43", "remaining_time": "0:21:53", "throughput": 1311.74, "total_tokens": 20992400} {"current_steps": 36970, "total_steps": 40000, "loss": 0.0, "lr": 7.05033463659932e-07, "epoch": 648.6017699115044, "percentage": 92.42, "elapsed_time": "4:26:45", "remaining_time": "0:21:51", "throughput": 1311.75, "total_tokens": 20995376} {"current_steps": 36975, "total_steps": 40000, "loss": 0.0, "lr": 7.027202568217928e-07, "epoch": 648.6902654867257, "percentage": 92.44, "elapsed_time": "4:26:47", "remaining_time": "0:21:49", "throughput": 1311.76, "total_tokens": 20998352} {"current_steps": 36980, "total_steps": 40000, "loss": 0.0, "lr": 7.004107969295293e-07, "epoch": 648.7787610619469, "percentage": 92.45, "elapsed_time": "4:26:49", "remaining_time": "0:21:47", "throughput": 1311.77, "total_tokens": 21001280} {"current_steps": 36985, "total_steps": 40000, "loss": 0.0, "lr": 6.9810508433929e-07, "epoch": 648.8672566371681, "percentage": 92.46, "elapsed_time": "4:26:52", "remaining_time": "0:21:45", "throughput": 1311.81, "total_tokens": 21004672} {"current_steps": 36990, "total_steps": 40000, "loss": 0.0, "lr": 6.958031194066406e-07, "epoch": 648.9557522123894, "percentage": 92.47, "elapsed_time": "4:26:54", "remaining_time": "0:21:43", "throughput": 1311.79, "total_tokens": 21007280} {"current_steps": 36995, "total_steps": 40000, "loss": 0.0, "lr": 6.935049024865776e-07, "epoch": 649.0353982300885, "percentage": 92.49, "elapsed_time": "4:26:56", "remaining_time": "0:21:40", "throughput": 1311.74, "total_tokens": 21009448} {"current_steps": 37000, "total_steps": 40000, "loss": 0.0, "lr": 6.912104339335118e-07, "epoch": 649.1238938053098, "percentage": 92.5, "elapsed_time": "4:26:58", "remaining_time": "0:21:38", "throughput": 1311.72, "total_tokens": 21011928} {"current_steps": 37000, "total_steps": 40000, "eval_loss": 0.9296573996543884, "epoch": 649.1238938053098, "percentage": 92.5, "elapsed_time": "4:26:59", "remaining_time": "0:21:38", "throughput": 1311.63, "total_tokens": 21011928} {"current_steps": 37005, "total_steps": 40000, "loss": 0.0, "lr": 6.889197141012799e-07, "epoch": 649.212389380531, "percentage": 92.51, "elapsed_time": "4:27:03", "remaining_time": "0:21:36", "throughput": 1311.46, "total_tokens": 21014648} {"current_steps": 37010, "total_steps": 40000, "loss": 0.0, "lr": 6.866327433431435e-07, "epoch": 649.3008849557522, "percentage": 92.53, "elapsed_time": "4:27:06", "remaining_time": "0:21:34", "throughput": 1311.46, "total_tokens": 21017384} {"current_steps": 37015, "total_steps": 40000, "loss": 0.0, "lr": 6.843495220117735e-07, "epoch": 649.3893805309734, "percentage": 92.54, "elapsed_time": "4:27:08", "remaining_time": "0:21:32", "throughput": 1311.46, "total_tokens": 21020280} {"current_steps": 37020, "total_steps": 40000, "loss": 0.0, "lr": 6.820700504592798e-07, "epoch": 649.4778761061947, "percentage": 92.55, "elapsed_time": "4:27:10", "remaining_time": "0:21:30", "throughput": 1311.5, "total_tokens": 21023752} {"current_steps": 37025, "total_steps": 40000, "loss": 0.0, "lr": 6.797943290371839e-07, "epoch": 649.566371681416, "percentage": 92.56, "elapsed_time": "4:27:12", "remaining_time": "0:21:28", "throughput": 1311.53, "total_tokens": 21026904} {"current_steps": 37030, "total_steps": 40000, "loss": 0.0, "lr": 6.775223580964274e-07, "epoch": 649.6548672566372, "percentage": 92.58, "elapsed_time": "4:27:14", "remaining_time": "0:21:26", "throughput": 1311.5, "total_tokens": 21029224} {"current_steps": 37035, "total_steps": 40000, "loss": 0.0, "lr": 6.7525413798738e-07, "epoch": 649.7433628318585, "percentage": 92.59, "elapsed_time": "4:27:16", "remaining_time": "0:21:23", "throughput": 1311.51, "total_tokens": 21032296} {"current_steps": 37040, "total_steps": 40000, "loss": 0.0, "lr": 6.729896690598259e-07, "epoch": 649.8318584070796, "percentage": 92.6, "elapsed_time": "4:27:18", "remaining_time": "0:21:21", "throughput": 1311.51, "total_tokens": 21035096} {"current_steps": 37045, "total_steps": 40000, "loss": 0.0, "lr": 6.707289516629772e-07, "epoch": 649.9203539823009, "percentage": 92.61, "elapsed_time": "4:27:20", "remaining_time": "0:21:19", "throughput": 1311.52, "total_tokens": 21037944} {"current_steps": 37050, "total_steps": 40000, "loss": 0.0, "lr": 6.684719861454692e-07, "epoch": 650.0, "percentage": 92.62, "elapsed_time": "4:27:23", "remaining_time": "0:21:17", "throughput": 1311.51, "total_tokens": 21040632} {"current_steps": 37055, "total_steps": 40000, "loss": 0.0, "lr": 6.662187728553481e-07, "epoch": 650.0884955752213, "percentage": 92.64, "elapsed_time": "4:27:25", "remaining_time": "0:21:15", "throughput": 1311.51, "total_tokens": 21043736} {"current_steps": 37060, "total_steps": 40000, "loss": 0.0, "lr": 6.639693121400892e-07, "epoch": 650.1769911504425, "percentage": 92.65, "elapsed_time": "4:27:27", "remaining_time": "0:21:13", "throughput": 1311.5, "total_tokens": 21046376} {"current_steps": 37065, "total_steps": 40000, "loss": 0.0, "lr": 6.617236043465868e-07, "epoch": 650.2654867256637, "percentage": 92.66, "elapsed_time": "4:27:29", "remaining_time": "0:21:10", "throughput": 1311.51, "total_tokens": 21049368} {"current_steps": 37070, "total_steps": 40000, "loss": 0.0, "lr": 6.594816498211587e-07, "epoch": 650.3539823008849, "percentage": 92.67, "elapsed_time": "4:27:31", "remaining_time": "0:21:08", "throughput": 1311.49, "total_tokens": 21051832} {"current_steps": 37075, "total_steps": 40000, "loss": 0.0, "lr": 6.572434489095447e-07, "epoch": 650.4424778761062, "percentage": 92.69, "elapsed_time": "4:27:33", "remaining_time": "0:21:06", "throughput": 1311.52, "total_tokens": 21055064} {"current_steps": 37080, "total_steps": 40000, "loss": 0.0, "lr": 6.550090019568994e-07, "epoch": 650.5309734513274, "percentage": 92.7, "elapsed_time": "4:27:36", "remaining_time": "0:21:04", "throughput": 1311.52, "total_tokens": 21057800} {"current_steps": 37085, "total_steps": 40000, "loss": 0.0, "lr": 6.527783093078027e-07, "epoch": 650.6194690265487, "percentage": 92.71, "elapsed_time": "4:27:38", "remaining_time": "0:21:02", "throughput": 1311.56, "total_tokens": 21061336} {"current_steps": 37090, "total_steps": 40000, "loss": 0.0, "lr": 6.5055137130626e-07, "epoch": 650.70796460177, "percentage": 92.73, "elapsed_time": "4:27:40", "remaining_time": "0:21:00", "throughput": 1311.57, "total_tokens": 21064280} {"current_steps": 37095, "total_steps": 40000, "loss": 0.0, "lr": 6.483281882956854e-07, "epoch": 650.7964601769911, "percentage": 92.74, "elapsed_time": "4:27:42", "remaining_time": "0:20:57", "throughput": 1311.56, "total_tokens": 21066888} {"current_steps": 37100, "total_steps": 40000, "loss": 0.0, "lr": 6.461087606189298e-07, "epoch": 650.8849557522124, "percentage": 92.75, "elapsed_time": "4:27:44", "remaining_time": "0:20:55", "throughput": 1311.55, "total_tokens": 21069544} {"current_steps": 37105, "total_steps": 40000, "loss": 0.0, "lr": 6.438930886182554e-07, "epoch": 650.9734513274336, "percentage": 92.76, "elapsed_time": "4:27:46", "remaining_time": "0:20:53", "throughput": 1311.55, "total_tokens": 21072312} {"current_steps": 37110, "total_steps": 40000, "loss": 0.0, "lr": 6.416811726353417e-07, "epoch": 651.0530973451328, "percentage": 92.77, "elapsed_time": "4:27:49", "remaining_time": "0:20:51", "throughput": 1311.51, "total_tokens": 21074672} {"current_steps": 37115, "total_steps": 40000, "loss": 0.0, "lr": 6.394730130112991e-07, "epoch": 651.141592920354, "percentage": 92.79, "elapsed_time": "4:27:51", "remaining_time": "0:20:49", "throughput": 1311.52, "total_tokens": 21077696} {"current_steps": 37120, "total_steps": 40000, "loss": 0.0, "lr": 6.372686100866471e-07, "epoch": 651.2300884955753, "percentage": 92.8, "elapsed_time": "4:27:53", "remaining_time": "0:20:47", "throughput": 1311.53, "total_tokens": 21080592} {"current_steps": 37125, "total_steps": 40000, "loss": 0.0, "lr": 6.350679642013413e-07, "epoch": 651.3185840707964, "percentage": 92.81, "elapsed_time": "4:27:55", "remaining_time": "0:20:44", "throughput": 1311.56, "total_tokens": 21083920} {"current_steps": 37130, "total_steps": 40000, "loss": 0.0, "lr": 6.328710756947437e-07, "epoch": 651.4070796460177, "percentage": 92.83, "elapsed_time": "4:27:57", "remaining_time": "0:20:42", "throughput": 1311.56, "total_tokens": 21086736} {"current_steps": 37135, "total_steps": 40000, "loss": 0.0, "lr": 6.306779449056416e-07, "epoch": 651.4955752212389, "percentage": 92.84, "elapsed_time": "4:27:59", "remaining_time": "0:20:40", "throughput": 1311.52, "total_tokens": 21088992} {"current_steps": 37140, "total_steps": 40000, "loss": 0.0, "lr": 6.284885721722422e-07, "epoch": 651.5840707964602, "percentage": 92.85, "elapsed_time": "4:28:01", "remaining_time": "0:20:38", "throughput": 1311.56, "total_tokens": 21092416} {"current_steps": 37145, "total_steps": 40000, "loss": 0.0, "lr": 6.26302957832181e-07, "epoch": 651.6725663716815, "percentage": 92.86, "elapsed_time": "4:28:04", "remaining_time": "0:20:36", "throughput": 1311.56, "total_tokens": 21095232} {"current_steps": 37150, "total_steps": 40000, "loss": 0.0, "lr": 6.241211022224997e-07, "epoch": 651.7610619469026, "percentage": 92.88, "elapsed_time": "4:28:06", "remaining_time": "0:20:34", "throughput": 1311.57, "total_tokens": 21098064} {"current_steps": 37155, "total_steps": 40000, "loss": 0.0, "lr": 6.219430056796732e-07, "epoch": 651.8495575221239, "percentage": 92.89, "elapsed_time": "4:28:08", "remaining_time": "0:20:31", "throughput": 1311.58, "total_tokens": 21101136} {"current_steps": 37160, "total_steps": 40000, "loss": 0.0, "lr": 6.19768668539586e-07, "epoch": 651.9380530973451, "percentage": 92.9, "elapsed_time": "4:28:10", "remaining_time": "0:20:29", "throughput": 1311.6, "total_tokens": 21104112} {"current_steps": 37165, "total_steps": 40000, "loss": 0.0, "lr": 6.175980911375528e-07, "epoch": 652.0176991150443, "percentage": 92.91, "elapsed_time": "4:28:12", "remaining_time": "0:20:27", "throughput": 1311.55, "total_tokens": 21106448} {"current_steps": 37170, "total_steps": 40000, "loss": 0.0, "lr": 6.154312738083034e-07, "epoch": 652.1061946902655, "percentage": 92.92, "elapsed_time": "4:28:14", "remaining_time": "0:20:25", "throughput": 1311.56, "total_tokens": 21109408} {"current_steps": 37175, "total_steps": 40000, "loss": 0.0, "lr": 6.132682168859843e-07, "epoch": 652.1946902654868, "percentage": 92.94, "elapsed_time": "4:28:17", "remaining_time": "0:20:23", "throughput": 1311.58, "total_tokens": 21112464} {"current_steps": 37180, "total_steps": 40000, "loss": 0.0, "lr": 6.111089207041704e-07, "epoch": 652.2831858407079, "percentage": 92.95, "elapsed_time": "4:28:19", "remaining_time": "0:20:21", "throughput": 1311.59, "total_tokens": 21115408} {"current_steps": 37185, "total_steps": 40000, "loss": 0.0, "lr": 6.089533855958507e-07, "epoch": 652.3716814159292, "percentage": 92.96, "elapsed_time": "4:28:21", "remaining_time": "0:20:18", "throughput": 1311.6, "total_tokens": 21118480} {"current_steps": 37190, "total_steps": 40000, "loss": 0.0, "lr": 6.068016118934372e-07, "epoch": 652.4601769911504, "percentage": 92.97, "elapsed_time": "4:28:23", "remaining_time": "0:20:16", "throughput": 1311.59, "total_tokens": 21121104} {"current_steps": 37195, "total_steps": 40000, "loss": 0.0, "lr": 6.04653599928759e-07, "epoch": 652.5486725663717, "percentage": 92.99, "elapsed_time": "4:28:25", "remaining_time": "0:20:14", "throughput": 1311.6, "total_tokens": 21124112} {"current_steps": 37200, "total_steps": 40000, "loss": 0.0, "lr": 6.025093500330675e-07, "epoch": 652.637168141593, "percentage": 93.0, "elapsed_time": "4:28:27", "remaining_time": "0:20:12", "throughput": 1311.6, "total_tokens": 21126880} {"current_steps": 37200, "total_steps": 40000, "eval_loss": 0.8969581127166748, "epoch": 652.637168141593, "percentage": 93.0, "elapsed_time": "4:28:28", "remaining_time": "0:20:12", "throughput": 1311.51, "total_tokens": 21126880} {"current_steps": 37205, "total_steps": 40000, "loss": 0.0, "lr": 6.003688625370291e-07, "epoch": 652.7256637168142, "percentage": 93.01, "elapsed_time": "4:28:32", "remaining_time": "0:20:10", "throughput": 1311.39, "total_tokens": 21130272} {"current_steps": 37210, "total_steps": 40000, "loss": 0.0, "lr": 5.982321377707406e-07, "epoch": 652.8141592920354, "percentage": 93.03, "elapsed_time": "4:28:35", "remaining_time": "0:20:08", "throughput": 1311.36, "total_tokens": 21132608} {"current_steps": 37215, "total_steps": 40000, "loss": 0.0, "lr": 5.96099176063708e-07, "epoch": 652.9026548672566, "percentage": 93.04, "elapsed_time": "4:28:37", "remaining_time": "0:20:06", "throughput": 1311.35, "total_tokens": 21135184} {"current_steps": 37220, "total_steps": 40000, "loss": 0.0, "lr": 5.93969977744857e-07, "epoch": 652.9911504424779, "percentage": 93.05, "elapsed_time": "4:28:39", "remaining_time": "0:20:03", "throughput": 1311.36, "total_tokens": 21138096} {"current_steps": 37225, "total_steps": 40000, "loss": 0.0, "lr": 5.918445431425445e-07, "epoch": 653.070796460177, "percentage": 93.06, "elapsed_time": "4:28:41", "remaining_time": "0:20:01", "throughput": 1311.31, "total_tokens": 21140472} {"current_steps": 37230, "total_steps": 40000, "loss": 0.0, "lr": 5.897228725845333e-07, "epoch": 653.1592920353983, "percentage": 93.08, "elapsed_time": "4:28:43", "remaining_time": "0:19:59", "throughput": 1311.29, "total_tokens": 21142856} {"current_steps": 37235, "total_steps": 40000, "loss": 0.0, "lr": 5.876049663980171e-07, "epoch": 653.2477876106195, "percentage": 93.09, "elapsed_time": "4:28:45", "remaining_time": "0:19:57", "throughput": 1311.29, "total_tokens": 21145688} {"current_steps": 37240, "total_steps": 40000, "loss": 0.0, "lr": 5.854908249095959e-07, "epoch": 653.3362831858407, "percentage": 93.1, "elapsed_time": "4:28:48", "remaining_time": "0:19:55", "throughput": 1311.3, "total_tokens": 21148728} {"current_steps": 37245, "total_steps": 40000, "loss": 0.0, "lr": 5.833804484453031e-07, "epoch": 653.4247787610619, "percentage": 93.11, "elapsed_time": "4:28:50", "remaining_time": "0:19:53", "throughput": 1311.32, "total_tokens": 21151800} {"current_steps": 37250, "total_steps": 40000, "loss": 0.0, "lr": 5.81273837330587e-07, "epoch": 653.5132743362832, "percentage": 93.12, "elapsed_time": "4:28:52", "remaining_time": "0:19:50", "throughput": 1311.31, "total_tokens": 21154456} {"current_steps": 37255, "total_steps": 40000, "loss": 0.0, "lr": 5.791709918903071e-07, "epoch": 653.6017699115044, "percentage": 93.14, "elapsed_time": "4:28:54", "remaining_time": "0:19:48", "throughput": 1311.31, "total_tokens": 21157192} {"current_steps": 37260, "total_steps": 40000, "loss": 0.0, "lr": 5.770719124487483e-07, "epoch": 653.6902654867257, "percentage": 93.15, "elapsed_time": "4:28:56", "remaining_time": "0:19:46", "throughput": 1311.34, "total_tokens": 21160504} {"current_steps": 37265, "total_steps": 40000, "loss": 0.0, "lr": 5.749765993296241e-07, "epoch": 653.7787610619469, "percentage": 93.16, "elapsed_time": "4:28:58", "remaining_time": "0:19:44", "throughput": 1311.32, "total_tokens": 21163080} {"current_steps": 37270, "total_steps": 40000, "loss": 0.0, "lr": 5.728850528560509e-07, "epoch": 653.8672566371681, "percentage": 93.17, "elapsed_time": "4:29:00", "remaining_time": "0:19:42", "throughput": 1311.36, "total_tokens": 21166392} {"current_steps": 37275, "total_steps": 40000, "loss": 0.0, "lr": 5.707972733505707e-07, "epoch": 653.9557522123894, "percentage": 93.19, "elapsed_time": "4:29:02", "remaining_time": "0:19:40", "throughput": 1311.36, "total_tokens": 21169320} {"current_steps": 37280, "total_steps": 40000, "loss": 0.0, "lr": 5.687132611351509e-07, "epoch": 654.0353982300885, "percentage": 93.2, "elapsed_time": "4:29:05", "remaining_time": "0:19:37", "throughput": 1311.33, "total_tokens": 21171848} {"current_steps": 37285, "total_steps": 40000, "loss": 0.0, "lr": 5.666330165311651e-07, "epoch": 654.1238938053098, "percentage": 93.21, "elapsed_time": "4:29:07", "remaining_time": "0:19:35", "throughput": 1311.32, "total_tokens": 21174520} {"current_steps": 37290, "total_steps": 40000, "loss": 0.0, "lr": 5.645565398594204e-07, "epoch": 654.212389380531, "percentage": 93.23, "elapsed_time": "4:29:09", "remaining_time": "0:19:33", "throughput": 1311.36, "total_tokens": 21177896} {"current_steps": 37295, "total_steps": 40000, "loss": 0.0, "lr": 5.624838314401304e-07, "epoch": 654.3008849557522, "percentage": 93.24, "elapsed_time": "4:29:11", "remaining_time": "0:19:31", "throughput": 1311.39, "total_tokens": 21181176} {"current_steps": 37300, "total_steps": 40000, "loss": 0.0, "lr": 5.604148915929336e-07, "epoch": 654.3893805309734, "percentage": 93.25, "elapsed_time": "4:29:13", "remaining_time": "0:19:29", "throughput": 1311.41, "total_tokens": 21184296} {"current_steps": 37305, "total_steps": 40000, "loss": 0.0, "lr": 5.583497206368887e-07, "epoch": 654.4778761061947, "percentage": 93.26, "elapsed_time": "4:29:15", "remaining_time": "0:19:27", "throughput": 1311.39, "total_tokens": 21186808} {"current_steps": 37310, "total_steps": 40000, "loss": 0.0, "lr": 5.562883188904688e-07, "epoch": 654.566371681416, "percentage": 93.27, "elapsed_time": "4:29:18", "remaining_time": "0:19:24", "throughput": 1311.38, "total_tokens": 21189352} {"current_steps": 37315, "total_steps": 40000, "loss": 0.0, "lr": 5.542306866715724e-07, "epoch": 654.6548672566372, "percentage": 93.29, "elapsed_time": "4:29:20", "remaining_time": "0:19:22", "throughput": 1311.37, "total_tokens": 21192088} {"current_steps": 37320, "total_steps": 40000, "loss": 0.0, "lr": 5.52176824297504e-07, "epoch": 654.7433628318585, "percentage": 93.3, "elapsed_time": "4:29:22", "remaining_time": "0:19:20", "throughput": 1311.39, "total_tokens": 21195112} {"current_steps": 37325, "total_steps": 40000, "loss": 0.0, "lr": 5.501267320850018e-07, "epoch": 654.8318584070796, "percentage": 93.31, "elapsed_time": "4:29:24", "remaining_time": "0:19:18", "throughput": 1311.37, "total_tokens": 21197720} {"current_steps": 37330, "total_steps": 40000, "loss": 0.0, "lr": 5.480804103502157e-07, "epoch": 654.9203539823009, "percentage": 93.33, "elapsed_time": "4:29:26", "remaining_time": "0:19:16", "throughput": 1311.39, "total_tokens": 21200888} {"current_steps": 37335, "total_steps": 40000, "loss": 0.0, "lr": 5.460378594087101e-07, "epoch": 655.0, "percentage": 93.34, "elapsed_time": "4:29:28", "remaining_time": "0:19:14", "throughput": 1311.35, "total_tokens": 21202968} {"current_steps": 37340, "total_steps": 40000, "loss": 0.0, "lr": 5.439990795754773e-07, "epoch": 655.0884955752213, "percentage": 93.35, "elapsed_time": "4:29:31", "remaining_time": "0:19:11", "throughput": 1311.37, "total_tokens": 21206328} {"current_steps": 37345, "total_steps": 40000, "loss": 0.0, "lr": 5.419640711649188e-07, "epoch": 655.1769911504425, "percentage": 93.36, "elapsed_time": "4:29:33", "remaining_time": "0:19:09", "throughput": 1311.37, "total_tokens": 21209128} {"current_steps": 37350, "total_steps": 40000, "loss": 0.0, "lr": 5.399328344908583e-07, "epoch": 655.2654867256637, "percentage": 93.38, "elapsed_time": "4:29:35", "remaining_time": "0:19:07", "throughput": 1311.36, "total_tokens": 21211752} {"current_steps": 37355, "total_steps": 40000, "loss": 0.0, "lr": 5.379053698665399e-07, "epoch": 655.3539823008849, "percentage": 93.39, "elapsed_time": "4:29:37", "remaining_time": "0:19:05", "throughput": 1311.37, "total_tokens": 21214664} {"current_steps": 37360, "total_steps": 40000, "loss": 0.0, "lr": 5.358816776046216e-07, "epoch": 655.4424778761062, "percentage": 93.4, "elapsed_time": "4:29:39", "remaining_time": "0:19:03", "throughput": 1311.36, "total_tokens": 21217400} {"current_steps": 37365, "total_steps": 40000, "loss": 0.0, "lr": 5.338617580171817e-07, "epoch": 655.5309734513274, "percentage": 93.41, "elapsed_time": "4:29:41", "remaining_time": "0:19:01", "throughput": 1311.34, "total_tokens": 21219896} {"current_steps": 37370, "total_steps": 40000, "loss": 0.0, "lr": 5.318456114157239e-07, "epoch": 655.6194690265487, "percentage": 93.42, "elapsed_time": "4:29:43", "remaining_time": "0:18:58", "throughput": 1311.36, "total_tokens": 21223032} {"current_steps": 37375, "total_steps": 40000, "loss": 0.0, "lr": 5.298332381111576e-07, "epoch": 655.70796460177, "percentage": 93.44, "elapsed_time": "4:29:46", "remaining_time": "0:18:56", "throughput": 1311.35, "total_tokens": 21225592} {"current_steps": 37380, "total_steps": 40000, "loss": 0.0, "lr": 5.27824638413818e-07, "epoch": 655.7964601769911, "percentage": 93.45, "elapsed_time": "4:29:48", "remaining_time": "0:18:54", "throughput": 1311.37, "total_tokens": 21228680} {"current_steps": 37385, "total_steps": 40000, "loss": 0.0, "lr": 5.258198126334546e-07, "epoch": 655.8849557522124, "percentage": 93.46, "elapsed_time": "4:29:50", "remaining_time": "0:18:52", "throughput": 1311.39, "total_tokens": 21231832} {"current_steps": 37390, "total_steps": 40000, "loss": 0.0, "lr": 5.238187610792367e-07, "epoch": 655.9734513274336, "percentage": 93.47, "elapsed_time": "4:29:52", "remaining_time": "0:18:50", "throughput": 1311.4, "total_tokens": 21234840} {"current_steps": 37395, "total_steps": 40000, "loss": 0.0, "lr": 5.218214840597563e-07, "epoch": 656.0530973451328, "percentage": 93.49, "elapsed_time": "4:29:54", "remaining_time": "0:18:48", "throughput": 1311.37, "total_tokens": 21237344} {"current_steps": 37400, "total_steps": 40000, "loss": 0.0, "lr": 5.198279818830115e-07, "epoch": 656.141592920354, "percentage": 93.5, "elapsed_time": "4:29:56", "remaining_time": "0:18:45", "throughput": 1311.34, "total_tokens": 21239760} {"current_steps": 37400, "total_steps": 40000, "eval_loss": 0.9158565998077393, "epoch": 656.141592920354, "percentage": 93.5, "elapsed_time": "4:29:58", "remaining_time": "0:18:46", "throughput": 1311.26, "total_tokens": 21239760} {"current_steps": 37405, "total_steps": 40000, "loss": 0.0, "lr": 5.178382548564287e-07, "epoch": 656.2300884955753, "percentage": 93.51, "elapsed_time": "4:30:01", "remaining_time": "0:18:44", "throughput": 1311.1, "total_tokens": 21242448} {"current_steps": 37410, "total_steps": 40000, "loss": 0.0, "lr": 5.15852303286854e-07, "epoch": 656.3185840707964, "percentage": 93.53, "elapsed_time": "4:30:04", "remaining_time": "0:18:41", "throughput": 1311.12, "total_tokens": 21245472} {"current_steps": 37415, "total_steps": 40000, "loss": 0.0, "lr": 5.138701274805396e-07, "epoch": 656.4070796460177, "percentage": 93.54, "elapsed_time": "4:30:06", "remaining_time": "0:18:39", "throughput": 1311.13, "total_tokens": 21248432} {"current_steps": 37420, "total_steps": 40000, "loss": 0.0, "lr": 5.118917277431606e-07, "epoch": 656.4955752212389, "percentage": 93.55, "elapsed_time": "4:30:08", "remaining_time": "0:18:37", "throughput": 1311.13, "total_tokens": 21251152} {"current_steps": 37425, "total_steps": 40000, "loss": 0.0, "lr": 5.099171043798145e-07, "epoch": 656.5840707964602, "percentage": 93.56, "elapsed_time": "4:30:10", "remaining_time": "0:18:35", "throughput": 1311.17, "total_tokens": 21254528} {"current_steps": 37430, "total_steps": 40000, "loss": 0.0, "lr": 5.079462576950133e-07, "epoch": 656.6725663716815, "percentage": 93.58, "elapsed_time": "4:30:12", "remaining_time": "0:18:33", "throughput": 1311.17, "total_tokens": 21257216} {"current_steps": 37435, "total_steps": 40000, "loss": 0.0, "lr": 5.059791879926862e-07, "epoch": 656.7610619469026, "percentage": 93.59, "elapsed_time": "4:30:14", "remaining_time": "0:18:30", "throughput": 1311.17, "total_tokens": 21259872} {"current_steps": 37440, "total_steps": 40000, "loss": 0.0, "lr": 5.040158955761793e-07, "epoch": 656.8495575221239, "percentage": 93.6, "elapsed_time": "4:30:16", "remaining_time": "0:18:28", "throughput": 1311.18, "total_tokens": 21262784} {"current_steps": 37445, "total_steps": 40000, "loss": 0.0, "lr": 5.020563807482559e-07, "epoch": 656.9380530973451, "percentage": 93.61, "elapsed_time": "4:30:18", "remaining_time": "0:18:26", "throughput": 1311.21, "total_tokens": 21265920} {"current_steps": 37450, "total_steps": 40000, "loss": 0.0, "lr": 5.001006438110995e-07, "epoch": 657.0176991150443, "percentage": 93.62, "elapsed_time": "4:30:20", "remaining_time": "0:18:24", "throughput": 1311.17, "total_tokens": 21268192} {"current_steps": 37455, "total_steps": 40000, "loss": 0.0, "lr": 4.981486850663075e-07, "epoch": 657.1061946902655, "percentage": 93.64, "elapsed_time": "4:30:22", "remaining_time": "0:18:22", "throughput": 1311.15, "total_tokens": 21270656} {"current_steps": 37460, "total_steps": 40000, "loss": 0.0, "lr": 4.962005048149005e-07, "epoch": 657.1946902654868, "percentage": 93.65, "elapsed_time": "4:30:24", "remaining_time": "0:18:20", "throughput": 1311.19, "total_tokens": 21274016} {"current_steps": 37465, "total_steps": 40000, "loss": 0.0, "lr": 4.942561033573073e-07, "epoch": 657.2831858407079, "percentage": 93.66, "elapsed_time": "4:30:27", "remaining_time": "0:18:17", "throughput": 1311.23, "total_tokens": 21277312} {"current_steps": 37470, "total_steps": 40000, "loss": 0.0, "lr": 4.923154809933827e-07, "epoch": 657.3716814159292, "percentage": 93.67, "elapsed_time": "4:30:29", "remaining_time": "0:18:15", "throughput": 1311.25, "total_tokens": 21280400} {"current_steps": 37475, "total_steps": 40000, "loss": 0.0, "lr": 4.903786380223957e-07, "epoch": 657.4601769911504, "percentage": 93.69, "elapsed_time": "4:30:31", "remaining_time": "0:18:13", "throughput": 1311.26, "total_tokens": 21283216} {"current_steps": 37480, "total_steps": 40000, "loss": 0.0, "lr": 4.884455747430266e-07, "epoch": 657.5486725663717, "percentage": 93.7, "elapsed_time": "4:30:33", "remaining_time": "0:18:11", "throughput": 1311.25, "total_tokens": 21285856} {"current_steps": 37485, "total_steps": 40000, "loss": 0.0, "lr": 4.865162914533816e-07, "epoch": 657.637168141593, "percentage": 93.71, "elapsed_time": "4:30:35", "remaining_time": "0:18:09", "throughput": 1311.27, "total_tokens": 21288784} {"current_steps": 37490, "total_steps": 40000, "loss": 0.0, "lr": 4.845907884509809e-07, "epoch": 657.7256637168142, "percentage": 93.73, "elapsed_time": "4:30:37", "remaining_time": "0:18:07", "throughput": 1311.25, "total_tokens": 21291312} {"current_steps": 37495, "total_steps": 40000, "loss": 0.0, "lr": 4.82669066032762e-07, "epoch": 657.8141592920354, "percentage": 93.74, "elapsed_time": "4:30:39", "remaining_time": "0:18:04", "throughput": 1311.29, "total_tokens": 21294640} {"current_steps": 37500, "total_steps": 40000, "loss": 0.0, "lr": 4.807511244950768e-07, "epoch": 657.9026548672566, "percentage": 93.75, "elapsed_time": "4:30:41", "remaining_time": "0:18:02", "throughput": 1311.29, "total_tokens": 21297344} {"current_steps": 37505, "total_steps": 40000, "loss": 0.0, "lr": 4.788369641336943e-07, "epoch": 657.9911504424779, "percentage": 93.76, "elapsed_time": "4:30:43", "remaining_time": "0:18:00", "throughput": 1311.29, "total_tokens": 21299936} {"current_steps": 37510, "total_steps": 40000, "loss": 0.0, "lr": 4.769265852438032e-07, "epoch": 658.070796460177, "percentage": 93.77, "elapsed_time": "4:30:45", "remaining_time": "0:17:58", "throughput": 1311.25, "total_tokens": 21302256} {"current_steps": 37515, "total_steps": 40000, "loss": 0.0, "lr": 4.750199881200124e-07, "epoch": 658.1592920353983, "percentage": 93.79, "elapsed_time": "4:30:47", "remaining_time": "0:17:56", "throughput": 1311.29, "total_tokens": 21305648} {"current_steps": 37520, "total_steps": 40000, "loss": 0.0, "lr": 4.7311717305633664e-07, "epoch": 658.2477876106195, "percentage": 93.8, "elapsed_time": "4:30:49", "remaining_time": "0:17:54", "throughput": 1311.3, "total_tokens": 21308576} {"current_steps": 37525, "total_steps": 40000, "loss": 0.0, "lr": 4.7121814034621623e-07, "epoch": 658.3362831858407, "percentage": 93.81, "elapsed_time": "4:30:51", "remaining_time": "0:17:51", "throughput": 1311.32, "total_tokens": 21311584} {"current_steps": 37530, "total_steps": 40000, "loss": 0.0, "lr": 4.693228902825114e-07, "epoch": 658.4247787610619, "percentage": 93.83, "elapsed_time": "4:30:54", "remaining_time": "0:17:49", "throughput": 1311.33, "total_tokens": 21314480} {"current_steps": 37535, "total_steps": 40000, "loss": 0.0, "lr": 4.6743142315748277e-07, "epoch": 658.5132743362832, "percentage": 93.84, "elapsed_time": "4:30:56", "remaining_time": "0:17:47", "throughput": 1311.32, "total_tokens": 21317104} {"current_steps": 37540, "total_steps": 40000, "loss": 0.0, "lr": 4.655437392628276e-07, "epoch": 658.6017699115044, "percentage": 93.85, "elapsed_time": "4:30:58", "remaining_time": "0:17:45", "throughput": 1311.32, "total_tokens": 21319792} {"current_steps": 37545, "total_steps": 40000, "loss": 0.0, "lr": 4.636598388896463e-07, "epoch": 658.6902654867257, "percentage": 93.86, "elapsed_time": "4:31:00", "remaining_time": "0:17:43", "throughput": 1311.34, "total_tokens": 21322816} {"current_steps": 37550, "total_steps": 40000, "loss": 0.0, "lr": 4.6177972232845925e-07, "epoch": 658.7787610619469, "percentage": 93.88, "elapsed_time": "4:31:02", "remaining_time": "0:17:41", "throughput": 1311.34, "total_tokens": 21325536} {"current_steps": 37555, "total_steps": 40000, "loss": 0.0, "lr": 4.5990338986920953e-07, "epoch": 658.8672566371681, "percentage": 93.89, "elapsed_time": "4:31:04", "remaining_time": "0:17:38", "throughput": 1311.34, "total_tokens": 21328272} {"current_steps": 37560, "total_steps": 40000, "loss": 0.0, "lr": 4.5803084180124633e-07, "epoch": 658.9557522123894, "percentage": 93.9, "elapsed_time": "4:31:06", "remaining_time": "0:17:36", "throughput": 1311.37, "total_tokens": 21331344} {"current_steps": 37565, "total_steps": 40000, "loss": 0.0, "lr": 4.561620784133386e-07, "epoch": 659.0353982300885, "percentage": 93.91, "elapsed_time": "4:31:08", "remaining_time": "0:17:34", "throughput": 1311.33, "total_tokens": 21333712} {"current_steps": 37570, "total_steps": 40000, "loss": 0.0, "lr": 4.5429709999367796e-07, "epoch": 659.1238938053098, "percentage": 93.92, "elapsed_time": "4:31:10", "remaining_time": "0:17:32", "throughput": 1311.33, "total_tokens": 21336400} {"current_steps": 37575, "total_steps": 40000, "loss": 0.0, "lr": 4.5243590682986223e-07, "epoch": 659.212389380531, "percentage": 93.94, "elapsed_time": "4:31:12", "remaining_time": "0:17:30", "throughput": 1311.35, "total_tokens": 21339440} {"current_steps": 37580, "total_steps": 40000, "loss": 0.0, "lr": 4.5057849920891735e-07, "epoch": 659.3008849557522, "percentage": 93.95, "elapsed_time": "4:31:14", "remaining_time": "0:17:28", "throughput": 1311.35, "total_tokens": 21342160} {"current_steps": 37585, "total_steps": 40000, "loss": 0.0, "lr": 4.487248774172698e-07, "epoch": 659.3893805309734, "percentage": 93.96, "elapsed_time": "4:31:17", "remaining_time": "0:17:25", "throughput": 1311.37, "total_tokens": 21345168} {"current_steps": 37590, "total_steps": 40000, "loss": 0.0, "lr": 4.4687504174077965e-07, "epoch": 659.4778761061947, "percentage": 93.97, "elapsed_time": "4:31:19", "remaining_time": "0:17:23", "throughput": 1311.37, "total_tokens": 21347808} {"current_steps": 37595, "total_steps": 40000, "loss": 0.0, "lr": 4.450289924647133e-07, "epoch": 659.566371681416, "percentage": 93.99, "elapsed_time": "4:31:21", "remaining_time": "0:17:21", "throughput": 1311.38, "total_tokens": 21350704} {"current_steps": 37600, "total_steps": 40000, "loss": 0.0, "lr": 4.431867298737513e-07, "epoch": 659.6548672566372, "percentage": 94.0, "elapsed_time": "4:31:23", "remaining_time": "0:17:19", "throughput": 1311.4, "total_tokens": 21353776} {"current_steps": 37600, "total_steps": 40000, "eval_loss": 0.9120059609413147, "epoch": 659.6548672566372, "percentage": 94.0, "elapsed_time": "4:31:24", "remaining_time": "0:17:19", "throughput": 1311.31, "total_tokens": 21353776} {"current_steps": 37605, "total_steps": 40000, "loss": 0.0, "lr": 4.41348254251997e-07, "epoch": 659.7433628318585, "percentage": 94.01, "elapsed_time": "4:31:28", "remaining_time": "0:17:17", "throughput": 1311.2, "total_tokens": 21356960} {"current_steps": 37610, "total_steps": 40000, "loss": 0.0, "lr": 4.395135658829652e-07, "epoch": 659.8318584070796, "percentage": 94.03, "elapsed_time": "4:31:30", "remaining_time": "0:17:15", "throughput": 1311.2, "total_tokens": 21359680} {"current_steps": 37615, "total_steps": 40000, "loss": 0.0, "lr": 4.376826650495852e-07, "epoch": 659.9203539823009, "percentage": 94.04, "elapsed_time": "4:31:32", "remaining_time": "0:17:13", "throughput": 1311.22, "total_tokens": 21362736} {"current_steps": 37620, "total_steps": 40000, "loss": 0.0, "lr": 4.358555520342117e-07, "epoch": 660.0, "percentage": 94.05, "elapsed_time": "4:31:34", "remaining_time": "0:17:10", "throughput": 1311.2, "total_tokens": 21365112} {"current_steps": 37625, "total_steps": 40000, "loss": 0.0, "lr": 4.3403222711860257e-07, "epoch": 660.0884955752213, "percentage": 94.06, "elapsed_time": "4:31:36", "remaining_time": "0:17:08", "throughput": 1311.23, "total_tokens": 21368568} {"current_steps": 37630, "total_steps": 40000, "loss": 0.0, "lr": 4.3221269058394133e-07, "epoch": 660.1769911504425, "percentage": 94.08, "elapsed_time": "4:31:38", "remaining_time": "0:17:06", "throughput": 1311.23, "total_tokens": 21371352} {"current_steps": 37635, "total_steps": 40000, "loss": 0.0, "lr": 4.303969427108173e-07, "epoch": 660.2654867256637, "percentage": 94.09, "elapsed_time": "4:31:40", "remaining_time": "0:17:04", "throughput": 1311.23, "total_tokens": 21373912} {"current_steps": 37640, "total_steps": 40000, "loss": 0.0, "lr": 4.2858498377924825e-07, "epoch": 660.3539823008849, "percentage": 94.1, "elapsed_time": "4:31:42", "remaining_time": "0:17:02", "throughput": 1311.25, "total_tokens": 21376952} {"current_steps": 37645, "total_steps": 40000, "loss": 0.0, "lr": 4.267768140686579e-07, "epoch": 660.4424778761062, "percentage": 94.11, "elapsed_time": "4:31:44", "remaining_time": "0:16:59", "throughput": 1311.25, "total_tokens": 21379656} {"current_steps": 37650, "total_steps": 40000, "loss": 0.0, "lr": 4.2497243385788975e-07, "epoch": 660.5309734513274, "percentage": 94.12, "elapsed_time": "4:31:46", "remaining_time": "0:16:57", "throughput": 1311.22, "total_tokens": 21381944} {"current_steps": 37655, "total_steps": 40000, "loss": 0.0, "lr": 4.231718434251991e-07, "epoch": 660.6194690265487, "percentage": 94.14, "elapsed_time": "4:31:48", "remaining_time": "0:16:55", "throughput": 1311.23, "total_tokens": 21384792} {"current_steps": 37660, "total_steps": 40000, "loss": 0.0, "lr": 4.213750430482666e-07, "epoch": 660.70796460177, "percentage": 94.15, "elapsed_time": "4:31:51", "remaining_time": "0:16:53", "throughput": 1311.22, "total_tokens": 21387288} {"current_steps": 37665, "total_steps": 40000, "loss": 0.0, "lr": 4.1958203300417054e-07, "epoch": 660.7964601769911, "percentage": 94.16, "elapsed_time": "4:31:53", "remaining_time": "0:16:51", "throughput": 1311.22, "total_tokens": 21390072} {"current_steps": 37670, "total_steps": 40000, "loss": 0.0, "lr": 4.177928135694259e-07, "epoch": 660.8849557522124, "percentage": 94.17, "elapsed_time": "4:31:55", "remaining_time": "0:16:49", "throughput": 1311.25, "total_tokens": 21393304} {"current_steps": 37675, "total_steps": 40000, "loss": 0.0, "lr": 4.1600738501994807e-07, "epoch": 660.9734513274336, "percentage": 94.19, "elapsed_time": "4:31:57", "remaining_time": "0:16:46", "throughput": 1311.29, "total_tokens": 21396600} {"current_steps": 37680, "total_steps": 40000, "loss": 0.0, "lr": 4.1422574763107237e-07, "epoch": 661.0530973451328, "percentage": 94.2, "elapsed_time": "4:31:59", "remaining_time": "0:16:44", "throughput": 1311.25, "total_tokens": 21398984} {"current_steps": 37685, "total_steps": 40000, "loss": 0.0, "lr": 4.124479016775512e-07, "epoch": 661.141592920354, "percentage": 94.21, "elapsed_time": "4:32:01", "remaining_time": "0:16:42", "throughput": 1311.27, "total_tokens": 21401896} {"current_steps": 37690, "total_steps": 40000, "loss": 0.0, "lr": 4.106738474335514e-07, "epoch": 661.2300884955753, "percentage": 94.23, "elapsed_time": "4:32:03", "remaining_time": "0:16:40", "throughput": 1311.26, "total_tokens": 21404488} {"current_steps": 37695, "total_steps": 40000, "loss": 0.0, "lr": 4.089035851726486e-07, "epoch": 661.3185840707964, "percentage": 94.24, "elapsed_time": "4:32:05", "remaining_time": "0:16:38", "throughput": 1311.27, "total_tokens": 21407368} {"current_steps": 37700, "total_steps": 40000, "loss": 0.0, "lr": 4.0713711516784937e-07, "epoch": 661.4070796460177, "percentage": 94.25, "elapsed_time": "4:32:07", "remaining_time": "0:16:36", "throughput": 1311.25, "total_tokens": 21409768} {"current_steps": 37705, "total_steps": 40000, "loss": 0.0, "lr": 4.05374437691558e-07, "epoch": 661.4955752212389, "percentage": 94.26, "elapsed_time": "4:32:09", "remaining_time": "0:16:33", "throughput": 1311.28, "total_tokens": 21412952} {"current_steps": 37710, "total_steps": 40000, "loss": 0.0, "lr": 4.036155530156044e-07, "epoch": 661.5840707964602, "percentage": 94.27, "elapsed_time": "4:32:11", "remaining_time": "0:16:31", "throughput": 1311.28, "total_tokens": 21415720} {"current_steps": 37715, "total_steps": 40000, "loss": 0.0, "lr": 4.018604614112298e-07, "epoch": 661.6725663716815, "percentage": 94.29, "elapsed_time": "4:32:13", "remaining_time": "0:16:29", "throughput": 1311.32, "total_tokens": 21418968} {"current_steps": 37720, "total_steps": 40000, "loss": 0.0, "lr": 4.0010916314908996e-07, "epoch": 661.7610619469026, "percentage": 94.3, "elapsed_time": "4:32:16", "remaining_time": "0:16:27", "throughput": 1311.32, "total_tokens": 21421832} {"current_steps": 37725, "total_steps": 40000, "loss": 0.0, "lr": 3.983616584992578e-07, "epoch": 661.8495575221239, "percentage": 94.31, "elapsed_time": "4:32:18", "remaining_time": "0:16:25", "throughput": 1311.32, "total_tokens": 21424504} {"current_steps": 37730, "total_steps": 40000, "loss": 0.0, "lr": 3.9661794773122595e-07, "epoch": 661.9380530973451, "percentage": 94.33, "elapsed_time": "4:32:20", "remaining_time": "0:16:23", "throughput": 1311.35, "total_tokens": 21427624} {"current_steps": 37735, "total_steps": 40000, "loss": 0.0, "lr": 3.9487803111388777e-07, "epoch": 662.0176991150443, "percentage": 94.34, "elapsed_time": "4:32:22", "remaining_time": "0:16:20", "throughput": 1311.33, "total_tokens": 21430248} {"current_steps": 37740, "total_steps": 40000, "loss": 0.0, "lr": 3.9314190891556747e-07, "epoch": 662.1061946902655, "percentage": 94.35, "elapsed_time": "4:32:24", "remaining_time": "0:16:18", "throughput": 1311.35, "total_tokens": 21433352} {"current_steps": 37745, "total_steps": 40000, "loss": 0.0, "lr": 3.914095814039925e-07, "epoch": 662.1946902654868, "percentage": 94.36, "elapsed_time": "4:32:26", "remaining_time": "0:16:16", "throughput": 1311.33, "total_tokens": 21436120} {"current_steps": 37750, "total_steps": 40000, "loss": 0.0, "lr": 3.896810488463104e-07, "epoch": 662.2831858407079, "percentage": 94.38, "elapsed_time": "4:32:28", "remaining_time": "0:16:14", "throughput": 1311.33, "total_tokens": 21438856} {"current_steps": 37755, "total_steps": 40000, "loss": 0.0, "lr": 3.8795631150908565e-07, "epoch": 662.3716814159292, "percentage": 94.39, "elapsed_time": "4:32:30", "remaining_time": "0:16:12", "throughput": 1311.33, "total_tokens": 21441576} {"current_steps": 37760, "total_steps": 40000, "loss": 0.0, "lr": 3.862353696582888e-07, "epoch": 662.4601769911504, "percentage": 94.4, "elapsed_time": "4:32:33", "remaining_time": "0:16:10", "throughput": 1311.35, "total_tokens": 21444552} {"current_steps": 37765, "total_steps": 40000, "loss": 0.0, "lr": 3.8451822355931313e-07, "epoch": 662.5486725663717, "percentage": 94.41, "elapsed_time": "4:32:35", "remaining_time": "0:16:07", "throughput": 1311.35, "total_tokens": 21447208} {"current_steps": 37770, "total_steps": 40000, "loss": 0.0, "lr": 3.82804873476969e-07, "epoch": 662.637168141593, "percentage": 94.42, "elapsed_time": "4:32:37", "remaining_time": "0:16:05", "throughput": 1311.38, "total_tokens": 21450504} {"current_steps": 37775, "total_steps": 40000, "loss": 0.0, "lr": 3.810953196754702e-07, "epoch": 662.7256637168142, "percentage": 94.44, "elapsed_time": "4:32:39", "remaining_time": "0:16:03", "throughput": 1311.41, "total_tokens": 21453704} {"current_steps": 37780, "total_steps": 40000, "loss": 0.0, "lr": 3.793895624184529e-07, "epoch": 662.8141592920354, "percentage": 94.45, "elapsed_time": "4:32:41", "remaining_time": "0:16:01", "throughput": 1311.44, "total_tokens": 21456856} {"current_steps": 37785, "total_steps": 40000, "loss": 0.0, "lr": 3.776876019689679e-07, "epoch": 662.9026548672566, "percentage": 94.46, "elapsed_time": "4:32:43", "remaining_time": "0:15:59", "throughput": 1311.42, "total_tokens": 21459224} {"current_steps": 37790, "total_steps": 40000, "loss": 0.0, "lr": 3.7598943858947743e-07, "epoch": 662.9911504424779, "percentage": 94.47, "elapsed_time": "4:32:45", "remaining_time": "0:15:57", "throughput": 1311.44, "total_tokens": 21462200} {"current_steps": 37795, "total_steps": 40000, "loss": 0.0, "lr": 3.742950725418637e-07, "epoch": 663.070796460177, "percentage": 94.49, "elapsed_time": "4:32:47", "remaining_time": "0:15:54", "throughput": 1311.41, "total_tokens": 21464776} {"current_steps": 37800, "total_steps": 40000, "loss": 0.0, "lr": 3.726045040874093e-07, "epoch": 663.1592920353983, "percentage": 94.5, "elapsed_time": "4:32:49", "remaining_time": "0:15:52", "throughput": 1311.41, "total_tokens": 21467368} {"current_steps": 37800, "total_steps": 40000, "eval_loss": 0.8969388604164124, "epoch": 663.1592920353983, "percentage": 94.5, "elapsed_time": "4:32:50", "remaining_time": "0:15:52", "throughput": 1311.32, "total_tokens": 21467368} {"current_steps": 37805, "total_steps": 40000, "loss": 0.0, "lr": 3.709177334868308e-07, "epoch": 663.2477876106195, "percentage": 94.51, "elapsed_time": "4:32:54", "remaining_time": "0:15:50", "throughput": 1311.14, "total_tokens": 21469960} {"current_steps": 37810, "total_steps": 40000, "loss": 0.0, "lr": 3.692347610002478e-07, "epoch": 663.3362831858407, "percentage": 94.53, "elapsed_time": "4:32:57", "remaining_time": "0:15:48", "throughput": 1311.16, "total_tokens": 21473000} {"current_steps": 37815, "total_steps": 40000, "loss": 0.0, "lr": 3.675555868871916e-07, "epoch": 663.4247787610619, "percentage": 94.54, "elapsed_time": "4:32:59", "remaining_time": "0:15:46", "throughput": 1311.17, "total_tokens": 21475912} {"current_steps": 37820, "total_steps": 40000, "loss": 0.0, "lr": 3.658802114066162e-07, "epoch": 663.5132743362832, "percentage": 94.55, "elapsed_time": "4:33:01", "remaining_time": "0:15:44", "throughput": 1311.21, "total_tokens": 21479224} {"current_steps": 37825, "total_steps": 40000, "loss": 0.0, "lr": 3.6420863481688437e-07, "epoch": 663.6017699115044, "percentage": 94.56, "elapsed_time": "4:33:03", "remaining_time": "0:15:42", "throughput": 1311.22, "total_tokens": 21482200} {"current_steps": 37830, "total_steps": 40000, "loss": 0.0, "lr": 3.625408573757705e-07, "epoch": 663.6902654867257, "percentage": 94.58, "elapsed_time": "4:33:05", "remaining_time": "0:15:39", "throughput": 1311.24, "total_tokens": 21485160} {"current_steps": 37835, "total_steps": 40000, "loss": 0.0, "lr": 3.608768793404743e-07, "epoch": 663.7787610619469, "percentage": 94.59, "elapsed_time": "4:33:07", "remaining_time": "0:15:37", "throughput": 1311.26, "total_tokens": 21488104} {"current_steps": 37840, "total_steps": 40000, "loss": 0.0, "lr": 3.592167009675934e-07, "epoch": 663.8672566371681, "percentage": 94.6, "elapsed_time": "4:33:09", "remaining_time": "0:15:35", "throughput": 1311.27, "total_tokens": 21490952} {"current_steps": 37845, "total_steps": 40000, "loss": 0.0, "lr": 3.575603225131563e-07, "epoch": 663.9557522123894, "percentage": 94.61, "elapsed_time": "4:33:11", "remaining_time": "0:15:33", "throughput": 1311.28, "total_tokens": 21493880} {"current_steps": 37850, "total_steps": 40000, "loss": 0.0, "lr": 3.55907744232592e-07, "epoch": 664.0353982300885, "percentage": 94.62, "elapsed_time": "4:33:13", "remaining_time": "0:15:31", "throughput": 1311.25, "total_tokens": 21496280} {"current_steps": 37855, "total_steps": 40000, "loss": 0.0, "lr": 3.5425896638075217e-07, "epoch": 664.1238938053098, "percentage": 94.64, "elapsed_time": "4:33:15", "remaining_time": "0:15:29", "throughput": 1311.25, "total_tokens": 21499048} {"current_steps": 37860, "total_steps": 40000, "loss": 0.0, "lr": 3.5261398921189736e-07, "epoch": 664.212389380531, "percentage": 94.65, "elapsed_time": "4:33:17", "remaining_time": "0:15:26", "throughput": 1311.27, "total_tokens": 21502184} {"current_steps": 37865, "total_steps": 40000, "loss": 0.0, "lr": 3.509728129797024e-07, "epoch": 664.3008849557522, "percentage": 94.66, "elapsed_time": "4:33:19", "remaining_time": "0:15:24", "throughput": 1311.27, "total_tokens": 21504856} {"current_steps": 37870, "total_steps": 40000, "loss": 0.0, "lr": 3.4933543793725656e-07, "epoch": 664.3893805309734, "percentage": 94.67, "elapsed_time": "4:33:22", "remaining_time": "0:15:22", "throughput": 1311.31, "total_tokens": 21508200} {"current_steps": 37875, "total_steps": 40000, "loss": 0.0, "lr": 3.4770186433707163e-07, "epoch": 664.4778761061947, "percentage": 94.69, "elapsed_time": "4:33:24", "remaining_time": "0:15:20", "throughput": 1311.32, "total_tokens": 21511096} {"current_steps": 37880, "total_steps": 40000, "loss": 0.0, "lr": 3.4607209243105453e-07, "epoch": 664.566371681416, "percentage": 94.7, "elapsed_time": "4:33:26", "remaining_time": "0:15:18", "throughput": 1311.32, "total_tokens": 21513864} {"current_steps": 37885, "total_steps": 40000, "loss": 0.0, "lr": 3.444461224705431e-07, "epoch": 664.6548672566372, "percentage": 94.71, "elapsed_time": "4:33:28", "remaining_time": "0:15:16", "throughput": 1311.33, "total_tokens": 21516584} {"current_steps": 37890, "total_steps": 40000, "loss": 0.0, "lr": 3.4282395470628116e-07, "epoch": 664.7433628318585, "percentage": 94.73, "elapsed_time": "4:33:30", "remaining_time": "0:15:13", "throughput": 1311.33, "total_tokens": 21519432} {"current_steps": 37895, "total_steps": 40000, "loss": 0.0, "lr": 3.4120558938842417e-07, "epoch": 664.8318584070796, "percentage": 94.74, "elapsed_time": "4:33:32", "remaining_time": "0:15:11", "throughput": 1311.34, "total_tokens": 21522168} {"current_steps": 37900, "total_steps": 40000, "loss": 0.0, "lr": 3.395910267665503e-07, "epoch": 664.9203539823009, "percentage": 94.75, "elapsed_time": "4:33:34", "remaining_time": "0:15:09", "throughput": 1311.37, "total_tokens": 21525368} {"current_steps": 37905, "total_steps": 40000, "loss": 0.0, "lr": 3.3798026708964094e-07, "epoch": 665.0, "percentage": 94.76, "elapsed_time": "4:33:36", "remaining_time": "0:15:07", "throughput": 1311.35, "total_tokens": 21527784} {"current_steps": 37910, "total_steps": 40000, "loss": 0.0, "lr": 3.3637331060609456e-07, "epoch": 665.0884955752213, "percentage": 94.77, "elapsed_time": "4:33:38", "remaining_time": "0:15:05", "throughput": 1311.31, "total_tokens": 21530072} {"current_steps": 37915, "total_steps": 40000, "loss": 0.0, "lr": 3.3477015756372966e-07, "epoch": 665.1769911504425, "percentage": 94.79, "elapsed_time": "4:33:40", "remaining_time": "0:15:03", "throughput": 1311.32, "total_tokens": 21532872} {"current_steps": 37920, "total_steps": 40000, "loss": 0.0, "lr": 3.3317080820976785e-07, "epoch": 665.2654867256637, "percentage": 94.8, "elapsed_time": "4:33:42", "remaining_time": "0:15:00", "throughput": 1311.32, "total_tokens": 21535672} {"current_steps": 37925, "total_steps": 40000, "loss": 0.0, "lr": 3.315752627908508e-07, "epoch": 665.3539823008849, "percentage": 94.81, "elapsed_time": "4:33:44", "remaining_time": "0:14:58", "throughput": 1311.35, "total_tokens": 21538840} {"current_steps": 37930, "total_steps": 40000, "loss": 0.0, "lr": 3.299835215530317e-07, "epoch": 665.4424778761062, "percentage": 94.83, "elapsed_time": "4:33:47", "remaining_time": "0:14:56", "throughput": 1311.34, "total_tokens": 21541464} {"current_steps": 37935, "total_steps": 40000, "loss": 0.0, "lr": 3.2839558474177245e-07, "epoch": 665.5309734513274, "percentage": 94.84, "elapsed_time": "4:33:49", "remaining_time": "0:14:54", "throughput": 1311.35, "total_tokens": 21544216} {"current_steps": 37940, "total_steps": 40000, "loss": 0.0, "lr": 3.2681145260196056e-07, "epoch": 665.6194690265487, "percentage": 94.85, "elapsed_time": "4:33:51", "remaining_time": "0:14:52", "throughput": 1311.39, "total_tokens": 21547576} {"current_steps": 37945, "total_steps": 40000, "loss": 0.0, "lr": 3.252311253778839e-07, "epoch": 665.70796460177, "percentage": 94.86, "elapsed_time": "4:33:53", "remaining_time": "0:14:49", "throughput": 1311.39, "total_tokens": 21550392} {"current_steps": 37950, "total_steps": 40000, "loss": 0.0, "lr": 3.2365460331325034e-07, "epoch": 665.7964601769911, "percentage": 94.88, "elapsed_time": "4:33:55", "remaining_time": "0:14:47", "throughput": 1311.41, "total_tokens": 21553416} {"current_steps": 37955, "total_steps": 40000, "loss": 0.0, "lr": 3.2208188665117934e-07, "epoch": 665.8849557522124, "percentage": 94.89, "elapsed_time": "4:33:57", "remaining_time": "0:14:45", "throughput": 1311.45, "total_tokens": 21556792} {"current_steps": 37960, "total_steps": 40000, "loss": 0.0, "lr": 3.205129756342018e-07, "epoch": 665.9734513274336, "percentage": 94.9, "elapsed_time": "4:33:59", "remaining_time": "0:14:43", "throughput": 1311.45, "total_tokens": 21559416} {"current_steps": 37965, "total_steps": 40000, "loss": 0.0, "lr": 3.189478705042659e-07, "epoch": 666.0530973451328, "percentage": 94.91, "elapsed_time": "4:34:01", "remaining_time": "0:14:41", "throughput": 1311.41, "total_tokens": 21561768} {"current_steps": 37970, "total_steps": 40000, "loss": 0.0, "lr": 3.173865715027341e-07, "epoch": 666.141592920354, "percentage": 94.92, "elapsed_time": "4:34:03", "remaining_time": "0:14:39", "throughput": 1311.42, "total_tokens": 21564568} {"current_steps": 37975, "total_steps": 40000, "loss": 0.0, "lr": 3.158290788703694e-07, "epoch": 666.2300884955753, "percentage": 94.94, "elapsed_time": "4:34:05", "remaining_time": "0:14:36", "throughput": 1311.44, "total_tokens": 21567640} {"current_steps": 37980, "total_steps": 40000, "loss": 0.0, "lr": 3.1427539284736297e-07, "epoch": 666.3185840707964, "percentage": 94.95, "elapsed_time": "4:34:07", "remaining_time": "0:14:34", "throughput": 1311.45, "total_tokens": 21570568} {"current_steps": 37985, "total_steps": 40000, "loss": 0.0, "lr": 3.127255136733093e-07, "epoch": 666.4070796460177, "percentage": 94.96, "elapsed_time": "4:34:09", "remaining_time": "0:14:32", "throughput": 1311.45, "total_tokens": 21573176} {"current_steps": 37990, "total_steps": 40000, "loss": 0.0, "lr": 3.1117944158722544e-07, "epoch": 666.4955752212389, "percentage": 94.97, "elapsed_time": "4:34:11", "remaining_time": "0:14:30", "throughput": 1311.47, "total_tokens": 21576184} {"current_steps": 37995, "total_steps": 40000, "loss": 0.0, "lr": 3.0963717682752635e-07, "epoch": 666.5840707964602, "percentage": 94.99, "elapsed_time": "4:34:14", "remaining_time": "0:14:28", "throughput": 1311.46, "total_tokens": 21578840} {"current_steps": 38000, "total_steps": 40000, "loss": 0.0, "lr": 3.080987196320578e-07, "epoch": 666.6725663716815, "percentage": 95.0, "elapsed_time": "4:34:16", "remaining_time": "0:14:26", "throughput": 1311.46, "total_tokens": 21581512} {"current_steps": 38000, "total_steps": 40000, "eval_loss": 0.8925443887710571, "epoch": 666.6725663716815, "percentage": 95.0, "elapsed_time": "4:34:17", "remaining_time": "0:14:26", "throughput": 1311.37, "total_tokens": 21581512} {"current_steps": 38005, "total_steps": 40000, "loss": 0.0, "lr": 3.065640702380607e-07, "epoch": 666.7610619469026, "percentage": 95.01, "elapsed_time": "4:34:20", "remaining_time": "0:14:24", "throughput": 1311.28, "total_tokens": 21584920} {"current_steps": 38010, "total_steps": 40000, "loss": 0.0, "lr": 3.050332288822011e-07, "epoch": 666.8495575221239, "percentage": 95.03, "elapsed_time": "4:34:23", "remaining_time": "0:14:21", "throughput": 1311.27, "total_tokens": 21587512} {"current_steps": 38015, "total_steps": 40000, "loss": 0.0, "lr": 3.035061958005542e-07, "epoch": 666.9380530973451, "percentage": 95.04, "elapsed_time": "4:34:25", "remaining_time": "0:14:19", "throughput": 1311.27, "total_tokens": 21590312} {"current_steps": 38020, "total_steps": 40000, "loss": 0.0, "lr": 3.019829712286093e-07, "epoch": 667.0176991150443, "percentage": 95.05, "elapsed_time": "4:34:27", "remaining_time": "0:14:17", "throughput": 1311.22, "total_tokens": 21592400} {"current_steps": 38025, "total_steps": 40000, "loss": 0.0, "lr": 3.004635554012647e-07, "epoch": 667.1061946902655, "percentage": 95.06, "elapsed_time": "4:34:29", "remaining_time": "0:14:15", "throughput": 1311.26, "total_tokens": 21595792} {"current_steps": 38030, "total_steps": 40000, "loss": 0.0, "lr": 2.9894794855283017e-07, "epoch": 667.1946902654868, "percentage": 95.08, "elapsed_time": "4:34:31", "remaining_time": "0:14:13", "throughput": 1311.26, "total_tokens": 21598464} {"current_steps": 38035, "total_steps": 40000, "loss": 0.0, "lr": 2.9743615091703816e-07, "epoch": 667.2831858407079, "percentage": 95.09, "elapsed_time": "4:34:33", "remaining_time": "0:14:11", "throughput": 1311.27, "total_tokens": 21601408} {"current_steps": 38040, "total_steps": 40000, "loss": 0.0, "lr": 2.959281627270216e-07, "epoch": 667.3716814159292, "percentage": 95.1, "elapsed_time": "4:34:35", "remaining_time": "0:14:08", "throughput": 1311.28, "total_tokens": 21604192} {"current_steps": 38045, "total_steps": 40000, "loss": 0.0, "lr": 2.944239842153362e-07, "epoch": 667.4601769911504, "percentage": 95.11, "elapsed_time": "4:34:37", "remaining_time": "0:14:06", "throughput": 1311.31, "total_tokens": 21607360} {"current_steps": 38050, "total_steps": 40000, "loss": 0.0, "lr": 2.929236156139381e-07, "epoch": 667.5486725663717, "percentage": 95.12, "elapsed_time": "4:34:39", "remaining_time": "0:14:04", "throughput": 1311.3, "total_tokens": 21610000} {"current_steps": 38055, "total_steps": 40000, "loss": 0.0, "lr": 2.9142705715420883e-07, "epoch": 667.637168141593, "percentage": 95.14, "elapsed_time": "4:34:41", "remaining_time": "0:14:02", "throughput": 1311.34, "total_tokens": 21613296} {"current_steps": 38060, "total_steps": 40000, "loss": 0.0, "lr": 2.8993430906693595e-07, "epoch": 667.7256637168142, "percentage": 95.15, "elapsed_time": "4:34:43", "remaining_time": "0:14:00", "throughput": 1311.32, "total_tokens": 21615648} {"current_steps": 38065, "total_steps": 40000, "loss": 0.0, "lr": 2.88445371582316e-07, "epoch": 667.8141592920354, "percentage": 95.16, "elapsed_time": "4:34:45", "remaining_time": "0:13:58", "throughput": 1311.32, "total_tokens": 21618352} {"current_steps": 38070, "total_steps": 40000, "loss": 0.0, "lr": 2.8696024492996796e-07, "epoch": 667.9026548672566, "percentage": 95.17, "elapsed_time": "4:34:48", "remaining_time": "0:13:55", "throughput": 1311.34, "total_tokens": 21621520} {"current_steps": 38075, "total_steps": 40000, "loss": 0.0, "lr": 2.854789293389115e-07, "epoch": 667.9911504424779, "percentage": 95.19, "elapsed_time": "4:34:50", "remaining_time": "0:13:53", "throughput": 1311.35, "total_tokens": 21624368} {"current_steps": 38080, "total_steps": 40000, "loss": 0.0, "lr": 2.8400142503758606e-07, "epoch": 668.070796460177, "percentage": 95.2, "elapsed_time": "4:34:52", "remaining_time": "0:13:51", "throughput": 1311.32, "total_tokens": 21626816} {"current_steps": 38085, "total_steps": 40000, "loss": 0.0, "lr": 2.8252773225384276e-07, "epoch": 668.1592920353983, "percentage": 95.21, "elapsed_time": "4:34:54", "remaining_time": "0:13:49", "throughput": 1311.32, "total_tokens": 21629504} {"current_steps": 38090, "total_steps": 40000, "loss": 0.0, "lr": 2.8105785121494143e-07, "epoch": 668.2477876106195, "percentage": 95.23, "elapsed_time": "4:34:56", "remaining_time": "0:13:47", "throughput": 1311.33, "total_tokens": 21632416} {"current_steps": 38095, "total_steps": 40000, "loss": 0.0, "lr": 2.795917821475563e-07, "epoch": 668.3362831858407, "percentage": 95.24, "elapsed_time": "4:34:58", "remaining_time": "0:13:45", "throughput": 1311.34, "total_tokens": 21635264} {"current_steps": 38100, "total_steps": 40000, "loss": 0.0, "lr": 2.78129525277776e-07, "epoch": 668.4247787610619, "percentage": 95.25, "elapsed_time": "4:35:00", "remaining_time": "0:13:42", "throughput": 1311.35, "total_tokens": 21638192} {"current_steps": 38105, "total_steps": 40000, "loss": 0.0, "lr": 2.766710808310952e-07, "epoch": 668.5132743362832, "percentage": 95.26, "elapsed_time": "4:35:02", "remaining_time": "0:13:40", "throughput": 1311.39, "total_tokens": 21641504} {"current_steps": 38110, "total_steps": 40000, "loss": 0.0, "lr": 2.7521644903242827e-07, "epoch": 668.6017699115044, "percentage": 95.28, "elapsed_time": "4:35:04", "remaining_time": "0:13:38", "throughput": 1311.42, "total_tokens": 21644672} {"current_steps": 38115, "total_steps": 40000, "loss": 0.0, "lr": 2.7376563010609593e-07, "epoch": 668.6902654867257, "percentage": 95.29, "elapsed_time": "4:35:06", "remaining_time": "0:13:36", "throughput": 1311.41, "total_tokens": 21647200} {"current_steps": 38120, "total_steps": 40000, "loss": 0.0, "lr": 2.72318624275833e-07, "epoch": 668.7787610619469, "percentage": 95.3, "elapsed_time": "4:35:08", "remaining_time": "0:13:34", "throughput": 1311.4, "total_tokens": 21649808} {"current_steps": 38125, "total_steps": 40000, "loss": 0.0, "lr": 2.7087543176478324e-07, "epoch": 668.8672566371681, "percentage": 95.31, "elapsed_time": "4:35:10", "remaining_time": "0:13:32", "throughput": 1311.42, "total_tokens": 21652784} {"current_steps": 38130, "total_steps": 40000, "loss": 0.0, "lr": 2.694360527955103e-07, "epoch": 668.9557522123894, "percentage": 95.33, "elapsed_time": "4:35:12", "remaining_time": "0:13:29", "throughput": 1311.42, "total_tokens": 21655456} {"current_steps": 38135, "total_steps": 40000, "loss": 0.0, "lr": 2.680004875899811e-07, "epoch": 669.0353982300885, "percentage": 95.34, "elapsed_time": "4:35:15", "remaining_time": "0:13:27", "throughput": 1311.36, "total_tokens": 21657464} {"current_steps": 38140, "total_steps": 40000, "loss": 0.0, "lr": 2.665687363695768e-07, "epoch": 669.1238938053098, "percentage": 95.35, "elapsed_time": "4:35:17", "remaining_time": "0:13:25", "throughput": 1311.36, "total_tokens": 21660184} {"current_steps": 38145, "total_steps": 40000, "loss": 0.0, "lr": 2.6514079935509584e-07, "epoch": 669.212389380531, "percentage": 95.36, "elapsed_time": "4:35:19", "remaining_time": "0:13:23", "throughput": 1311.35, "total_tokens": 21662776} {"current_steps": 38150, "total_steps": 40000, "loss": 0.0, "lr": 2.6371667676673983e-07, "epoch": 669.3008849557522, "percentage": 95.38, "elapsed_time": "4:35:21", "remaining_time": "0:13:21", "throughput": 1311.35, "total_tokens": 21665384} {"current_steps": 38155, "total_steps": 40000, "loss": 0.0, "lr": 2.6229636882412755e-07, "epoch": 669.3893805309734, "percentage": 95.39, "elapsed_time": "4:35:23", "remaining_time": "0:13:19", "throughput": 1311.39, "total_tokens": 21668760} {"current_steps": 38160, "total_steps": 40000, "loss": 0.0, "lr": 2.6087987574628935e-07, "epoch": 669.4778761061947, "percentage": 95.4, "elapsed_time": "4:35:25", "remaining_time": "0:13:16", "throughput": 1311.39, "total_tokens": 21671592} {"current_steps": 38165, "total_steps": 40000, "loss": 0.0, "lr": 2.5946719775166437e-07, "epoch": 669.566371681416, "percentage": 95.41, "elapsed_time": "4:35:27", "remaining_time": "0:13:14", "throughput": 1311.42, "total_tokens": 21674664} {"current_steps": 38170, "total_steps": 40000, "loss": 0.0, "lr": 2.5805833505810616e-07, "epoch": 669.6548672566372, "percentage": 95.43, "elapsed_time": "4:35:29", "remaining_time": "0:13:12", "throughput": 1311.43, "total_tokens": 21677672} {"current_steps": 38175, "total_steps": 40000, "loss": 0.0, "lr": 2.566532878828798e-07, "epoch": 669.7433628318585, "percentage": 95.44, "elapsed_time": "4:35:31", "remaining_time": "0:13:10", "throughput": 1311.46, "total_tokens": 21680728} {"current_steps": 38180, "total_steps": 40000, "loss": 0.0, "lr": 2.552520564426619e-07, "epoch": 669.8318584070796, "percentage": 95.45, "elapsed_time": "4:35:33", "remaining_time": "0:13:08", "throughput": 1311.46, "total_tokens": 21683464} {"current_steps": 38185, "total_steps": 40000, "loss": 0.0, "lr": 2.5385464095353803e-07, "epoch": 669.9203539823009, "percentage": 95.46, "elapsed_time": "4:35:35", "remaining_time": "0:13:05", "throughput": 1311.48, "total_tokens": 21686568} {"current_steps": 38190, "total_steps": 40000, "loss": 0.0, "lr": 2.5246104163100804e-07, "epoch": 670.0, "percentage": 95.47, "elapsed_time": "4:35:37", "remaining_time": "0:13:03", "throughput": 1311.45, "total_tokens": 21688728} {"current_steps": 38195, "total_steps": 40000, "loss": 0.0, "lr": 2.510712586899833e-07, "epoch": 670.0884955752213, "percentage": 95.49, "elapsed_time": "4:35:40", "remaining_time": "0:13:01", "throughput": 1311.44, "total_tokens": 21691496} {"current_steps": 38200, "total_steps": 40000, "loss": 0.0, "lr": 2.4968529234478124e-07, "epoch": 670.1769911504425, "percentage": 95.5, "elapsed_time": "4:35:42", "remaining_time": "0:12:59", "throughput": 1311.45, "total_tokens": 21694376} {"current_steps": 38200, "total_steps": 40000, "eval_loss": 0.899570882320404, "epoch": 670.1769911504425, "percentage": 95.5, "elapsed_time": "4:35:43", "remaining_time": "0:12:59", "throughput": 1311.37, "total_tokens": 21694376} {"current_steps": 38205, "total_steps": 40000, "loss": 0.0, "lr": 2.483031428091448e-07, "epoch": 670.2654867256637, "percentage": 95.51, "elapsed_time": "4:35:47", "remaining_time": "0:12:57", "throughput": 1311.24, "total_tokens": 21697336} {"current_steps": 38210, "total_steps": 40000, "loss": 0.0, "lr": 2.469248102962091e-07, "epoch": 670.3539823008849, "percentage": 95.53, "elapsed_time": "4:35:49", "remaining_time": "0:12:55", "throughput": 1311.26, "total_tokens": 21700440} {"current_steps": 38215, "total_steps": 40000, "loss": 0.0, "lr": 2.4555029501853455e-07, "epoch": 670.4424778761062, "percentage": 95.54, "elapsed_time": "4:35:51", "remaining_time": "0:12:53", "throughput": 1311.28, "total_tokens": 21703448} {"current_steps": 38220, "total_steps": 40000, "loss": 0.0, "lr": 2.441795971880906e-07, "epoch": 670.5309734513274, "percentage": 95.55, "elapsed_time": "4:35:53", "remaining_time": "0:12:50", "throughput": 1311.3, "total_tokens": 21706408} {"current_steps": 38225, "total_steps": 40000, "loss": 0.0, "lr": 2.4281271701625255e-07, "epoch": 670.6194690265487, "percentage": 95.56, "elapsed_time": "4:35:55", "remaining_time": "0:12:48", "throughput": 1311.31, "total_tokens": 21709368} {"current_steps": 38230, "total_steps": 40000, "loss": 0.0, "lr": 2.4144965471381007e-07, "epoch": 670.70796460177, "percentage": 95.58, "elapsed_time": "4:35:57", "remaining_time": "0:12:46", "throughput": 1311.31, "total_tokens": 21712104} {"current_steps": 38235, "total_steps": 40000, "loss": 0.0, "lr": 2.400904104909674e-07, "epoch": 670.7964601769911, "percentage": 95.59, "elapsed_time": "4:35:59", "remaining_time": "0:12:44", "throughput": 1311.34, "total_tokens": 21715304} {"current_steps": 38240, "total_steps": 40000, "loss": 0.0, "lr": 2.3873498455733725e-07, "epoch": 670.8849557522124, "percentage": 95.6, "elapsed_time": "4:36:01", "remaining_time": "0:12:42", "throughput": 1311.35, "total_tokens": 21718184} {"current_steps": 38245, "total_steps": 40000, "loss": 0.0, "lr": 2.3738337712194137e-07, "epoch": 670.9734513274336, "percentage": 95.61, "elapsed_time": "4:36:03", "remaining_time": "0:12:40", "throughput": 1311.34, "total_tokens": 21720712} {"current_steps": 38250, "total_steps": 40000, "loss": 0.0, "lr": 2.3603558839321305e-07, "epoch": 671.0530973451328, "percentage": 95.62, "elapsed_time": "4:36:05", "remaining_time": "0:12:37", "throughput": 1311.33, "total_tokens": 21723472} {"current_steps": 38255, "total_steps": 40000, "loss": 0.0, "lr": 2.3469161857900267e-07, "epoch": 671.141592920354, "percentage": 95.64, "elapsed_time": "4:36:08", "remaining_time": "0:12:35", "throughput": 1311.34, "total_tokens": 21726368} {"current_steps": 38260, "total_steps": 40000, "loss": 0.0, "lr": 2.3335146788656393e-07, "epoch": 671.2300884955753, "percentage": 95.65, "elapsed_time": "4:36:10", "remaining_time": "0:12:33", "throughput": 1311.35, "total_tokens": 21729168} {"current_steps": 38265, "total_steps": 40000, "loss": 0.0, "lr": 2.3201513652256757e-07, "epoch": 671.3185840707964, "percentage": 95.66, "elapsed_time": "4:36:12", "remaining_time": "0:12:31", "throughput": 1311.35, "total_tokens": 21731824} {"current_steps": 38270, "total_steps": 40000, "loss": 0.0, "lr": 2.3068262469308766e-07, "epoch": 671.4070796460177, "percentage": 95.67, "elapsed_time": "4:36:14", "remaining_time": "0:12:29", "throughput": 1311.37, "total_tokens": 21734896} {"current_steps": 38275, "total_steps": 40000, "loss": 0.0, "lr": 2.2935393260362093e-07, "epoch": 671.4955752212389, "percentage": 95.69, "elapsed_time": "4:36:16", "remaining_time": "0:12:27", "throughput": 1311.36, "total_tokens": 21737392} {"current_steps": 38280, "total_steps": 40000, "loss": 0.0, "lr": 2.2802906045906458e-07, "epoch": 671.5840707964602, "percentage": 95.7, "elapsed_time": "4:36:18", "remaining_time": "0:12:24", "throughput": 1311.35, "total_tokens": 21740080} {"current_steps": 38285, "total_steps": 40000, "loss": 0.0, "lr": 2.2670800846373018e-07, "epoch": 671.6725663716815, "percentage": 95.71, "elapsed_time": "4:36:20", "remaining_time": "0:12:22", "throughput": 1311.37, "total_tokens": 21743056} {"current_steps": 38290, "total_steps": 40000, "loss": 0.0, "lr": 2.2539077682134367e-07, "epoch": 671.7610619469026, "percentage": 95.73, "elapsed_time": "4:36:22", "remaining_time": "0:12:20", "throughput": 1311.38, "total_tokens": 21745856} {"current_steps": 38295, "total_steps": 40000, "loss": 0.0, "lr": 2.2407736573503423e-07, "epoch": 671.8495575221239, "percentage": 95.74, "elapsed_time": "4:36:24", "remaining_time": "0:12:18", "throughput": 1311.39, "total_tokens": 21748784} {"current_steps": 38300, "total_steps": 40000, "loss": 0.0, "lr": 2.2276777540735093e-07, "epoch": 671.9380530973451, "percentage": 95.75, "elapsed_time": "4:36:26", "remaining_time": "0:12:16", "throughput": 1311.38, "total_tokens": 21751360} {"current_steps": 38305, "total_steps": 40000, "loss": 0.0, "lr": 2.2146200604024613e-07, "epoch": 672.0176991150443, "percentage": 95.76, "elapsed_time": "4:36:28", "remaining_time": "0:12:14", "throughput": 1311.37, "total_tokens": 21754216} {"current_steps": 38310, "total_steps": 40000, "loss": 0.0, "lr": 2.2016005783508375e-07, "epoch": 672.1061946902655, "percentage": 95.78, "elapsed_time": "4:36:30", "remaining_time": "0:12:11", "throughput": 1311.38, "total_tokens": 21757096} {"current_steps": 38315, "total_steps": 40000, "loss": 0.0, "lr": 2.1886193099264763e-07, "epoch": 672.1946902654868, "percentage": 95.79, "elapsed_time": "4:36:32", "remaining_time": "0:12:09", "throughput": 1311.38, "total_tokens": 21759656} {"current_steps": 38320, "total_steps": 40000, "loss": 0.0, "lr": 2.175676257131165e-07, "epoch": 672.2831858407079, "percentage": 95.8, "elapsed_time": "4:36:35", "remaining_time": "0:12:07", "throughput": 1311.4, "total_tokens": 21762728} {"current_steps": 38325, "total_steps": 40000, "loss": 0.0, "lr": 2.162771421960974e-07, "epoch": 672.3716814159292, "percentage": 95.81, "elapsed_time": "4:36:37", "remaining_time": "0:12:05", "throughput": 1311.39, "total_tokens": 21765384} {"current_steps": 38330, "total_steps": 40000, "loss": 0.0, "lr": 2.1499048064059224e-07, "epoch": 672.4601769911504, "percentage": 95.83, "elapsed_time": "4:36:39", "remaining_time": "0:12:03", "throughput": 1311.39, "total_tokens": 21768072} {"current_steps": 38335, "total_steps": 40000, "loss": 0.0, "lr": 2.1370764124502285e-07, "epoch": 672.5486725663717, "percentage": 95.84, "elapsed_time": "4:36:41", "remaining_time": "0:12:01", "throughput": 1311.39, "total_tokens": 21770776} {"current_steps": 38340, "total_steps": 40000, "loss": 0.0, "lr": 2.1242862420721988e-07, "epoch": 672.637168141593, "percentage": 95.85, "elapsed_time": "4:36:43", "remaining_time": "0:11:58", "throughput": 1311.41, "total_tokens": 21773688} {"current_steps": 38345, "total_steps": 40000, "loss": 0.0, "lr": 2.1115342972442276e-07, "epoch": 672.7256637168142, "percentage": 95.86, "elapsed_time": "4:36:45", "remaining_time": "0:11:56", "throughput": 1311.41, "total_tokens": 21776520} {"current_steps": 38350, "total_steps": 40000, "loss": 0.0, "lr": 2.0988205799328252e-07, "epoch": 672.8141592920354, "percentage": 95.88, "elapsed_time": "4:36:47", "remaining_time": "0:11:54", "throughput": 1311.46, "total_tokens": 21779912} {"current_steps": 38355, "total_steps": 40000, "loss": 0.0, "lr": 2.0861450920986182e-07, "epoch": 672.9026548672566, "percentage": 95.89, "elapsed_time": "4:36:49", "remaining_time": "0:11:52", "throughput": 1311.48, "total_tokens": 21783064} {"current_steps": 38360, "total_steps": 40000, "loss": 0.0, "lr": 2.07350783569632e-07, "epoch": 672.9911504424779, "percentage": 95.9, "elapsed_time": "4:36:51", "remaining_time": "0:11:50", "throughput": 1311.48, "total_tokens": 21785752} {"current_steps": 38365, "total_steps": 40000, "loss": 0.0, "lr": 2.060908812674761e-07, "epoch": 673.070796460177, "percentage": 95.91, "elapsed_time": "4:36:53", "remaining_time": "0:11:48", "throughput": 1311.46, "total_tokens": 21788280} {"current_steps": 38370, "total_steps": 40000, "loss": 0.0, "lr": 2.0483480249768317e-07, "epoch": 673.1592920353983, "percentage": 95.93, "elapsed_time": "4:36:55", "remaining_time": "0:11:45", "throughput": 1311.45, "total_tokens": 21790888} {"current_steps": 38375, "total_steps": 40000, "loss": 0.0, "lr": 2.035825474539621e-07, "epoch": 673.2477876106195, "percentage": 95.94, "elapsed_time": "4:36:57", "remaining_time": "0:11:43", "throughput": 1311.47, "total_tokens": 21793880} {"current_steps": 38380, "total_steps": 40000, "loss": 0.0, "lr": 2.0233411632942235e-07, "epoch": 673.3362831858407, "percentage": 95.95, "elapsed_time": "4:37:00", "remaining_time": "0:11:41", "throughput": 1311.47, "total_tokens": 21796712} {"current_steps": 38385, "total_steps": 40000, "loss": 0.0, "lr": 2.0108950931658764e-07, "epoch": 673.4247787610619, "percentage": 95.96, "elapsed_time": "4:37:02", "remaining_time": "0:11:39", "throughput": 1311.5, "total_tokens": 21799816} {"current_steps": 38390, "total_steps": 40000, "loss": 0.0, "lr": 1.998487266073934e-07, "epoch": 673.5132743362832, "percentage": 95.97, "elapsed_time": "4:37:04", "remaining_time": "0:11:37", "throughput": 1311.51, "total_tokens": 21802776} {"current_steps": 38395, "total_steps": 40000, "loss": 0.0, "lr": 1.986117683931865e-07, "epoch": 673.6017699115044, "percentage": 95.99, "elapsed_time": "4:37:06", "remaining_time": "0:11:35", "throughput": 1311.53, "total_tokens": 21805768} {"current_steps": 38400, "total_steps": 40000, "loss": 0.0, "lr": 1.9737863486471442e-07, "epoch": 673.6902654867257, "percentage": 96.0, "elapsed_time": "4:37:08", "remaining_time": "0:11:32", "throughput": 1311.54, "total_tokens": 21808568} {"current_steps": 38400, "total_steps": 40000, "eval_loss": 0.8810822367668152, "epoch": 673.6902654867257, "percentage": 96.0, "elapsed_time": "4:37:09", "remaining_time": "0:11:32", "throughput": 1311.45, "total_tokens": 21808568} {"current_steps": 38405, "total_steps": 40000, "loss": 0.0, "lr": 1.9614932621215e-07, "epoch": 673.7787610619469, "percentage": 96.01, "elapsed_time": "4:37:13", "remaining_time": "0:11:30", "throughput": 1311.32, "total_tokens": 21811496} {"current_steps": 38410, "total_steps": 40000, "loss": 0.0, "lr": 1.9492384262506102e-07, "epoch": 673.8672566371681, "percentage": 96.03, "elapsed_time": "4:37:15", "remaining_time": "0:11:28", "throughput": 1311.3, "total_tokens": 21813784} {"current_steps": 38415, "total_steps": 40000, "loss": 0.0, "lr": 1.9370218429243524e-07, "epoch": 673.9557522123894, "percentage": 96.04, "elapsed_time": "4:37:17", "remaining_time": "0:11:26", "throughput": 1311.34, "total_tokens": 21817224} {"current_steps": 38420, "total_steps": 40000, "loss": 0.0, "lr": 1.9248435140267197e-07, "epoch": 674.0353982300885, "percentage": 96.05, "elapsed_time": "4:37:19", "remaining_time": "0:11:24", "throughput": 1311.31, "total_tokens": 21819688} {"current_steps": 38425, "total_steps": 40000, "loss": 0.0, "lr": 1.9127034414356814e-07, "epoch": 674.1238938053098, "percentage": 96.06, "elapsed_time": "4:37:21", "remaining_time": "0:11:22", "throughput": 1311.31, "total_tokens": 21822312} {"current_steps": 38430, "total_steps": 40000, "loss": 0.0, "lr": 1.9006016270234627e-07, "epoch": 674.212389380531, "percentage": 96.08, "elapsed_time": "4:37:23", "remaining_time": "0:11:19", "throughput": 1311.31, "total_tokens": 21825144} {"current_steps": 38435, "total_steps": 40000, "loss": 0.0, "lr": 1.888538072656293e-07, "epoch": 674.3008849557522, "percentage": 96.09, "elapsed_time": "4:37:25", "remaining_time": "0:11:17", "throughput": 1311.32, "total_tokens": 21828008} {"current_steps": 38440, "total_steps": 40000, "loss": 0.0, "lr": 1.8765127801944893e-07, "epoch": 674.3893805309734, "percentage": 96.1, "elapsed_time": "4:37:27", "remaining_time": "0:11:15", "throughput": 1311.36, "total_tokens": 21831432} {"current_steps": 38445, "total_steps": 40000, "loss": 0.0, "lr": 1.8645257514925406e-07, "epoch": 674.4778761061947, "percentage": 96.11, "elapsed_time": "4:37:29", "remaining_time": "0:11:13", "throughput": 1311.38, "total_tokens": 21834472} {"current_steps": 38450, "total_steps": 40000, "loss": 0.0, "lr": 1.8525769883989685e-07, "epoch": 674.566371681416, "percentage": 96.12, "elapsed_time": "4:37:32", "remaining_time": "0:11:11", "throughput": 1311.36, "total_tokens": 21836840} {"current_steps": 38455, "total_steps": 40000, "loss": 0.0, "lr": 1.8406664927564654e-07, "epoch": 674.6548672566372, "percentage": 96.14, "elapsed_time": "4:37:34", "remaining_time": "0:11:09", "throughput": 1311.39, "total_tokens": 21839992} {"current_steps": 38460, "total_steps": 40000, "loss": 0.0, "lr": 1.8287942664017566e-07, "epoch": 674.7433628318585, "percentage": 96.15, "elapsed_time": "4:37:36", "remaining_time": "0:11:06", "throughput": 1311.4, "total_tokens": 21842968} {"current_steps": 38465, "total_steps": 40000, "loss": 0.0, "lr": 1.8169603111656552e-07, "epoch": 674.8318584070796, "percentage": 96.16, "elapsed_time": "4:37:38", "remaining_time": "0:11:04", "throughput": 1311.39, "total_tokens": 21845400} {"current_steps": 38470, "total_steps": 40000, "loss": 0.0, "lr": 1.805164628873146e-07, "epoch": 674.9203539823009, "percentage": 96.17, "elapsed_time": "4:37:40", "remaining_time": "0:11:02", "throughput": 1311.39, "total_tokens": 21848168} {"current_steps": 38475, "total_steps": 40000, "loss": 0.0, "lr": 1.793407221343274e-07, "epoch": 675.0, "percentage": 96.19, "elapsed_time": "4:37:42", "remaining_time": "0:11:00", "throughput": 1311.39, "total_tokens": 21850760} {"current_steps": 38480, "total_steps": 40000, "loss": 0.0, "lr": 1.781688090389172e-07, "epoch": 675.0884955752213, "percentage": 96.2, "elapsed_time": "4:37:44", "remaining_time": "0:10:58", "throughput": 1311.36, "total_tokens": 21853336} {"current_steps": 38485, "total_steps": 40000, "loss": 0.0, "lr": 1.770007237818061e-07, "epoch": 675.1769911504425, "percentage": 96.21, "elapsed_time": "4:37:46", "remaining_time": "0:10:56", "throughput": 1311.38, "total_tokens": 21856296} {"current_steps": 38490, "total_steps": 40000, "loss": 0.0, "lr": 1.7583646654313059e-07, "epoch": 675.2654867256637, "percentage": 96.23, "elapsed_time": "4:37:48", "remaining_time": "0:10:53", "throughput": 1311.37, "total_tokens": 21858936} {"current_steps": 38495, "total_steps": 40000, "loss": 0.0, "lr": 1.7467603750242757e-07, "epoch": 675.3539823008849, "percentage": 96.24, "elapsed_time": "4:37:50", "remaining_time": "0:10:51", "throughput": 1311.41, "total_tokens": 21862184} {"current_steps": 38500, "total_steps": 40000, "loss": 0.0, "lr": 1.7351943683865944e-07, "epoch": 675.4424778761062, "percentage": 96.25, "elapsed_time": "4:37:52", "remaining_time": "0:10:49", "throughput": 1311.4, "total_tokens": 21864792} {"current_steps": 38505, "total_steps": 40000, "loss": 0.0, "lr": 1.723666647301808e-07, "epoch": 675.5309734513274, "percentage": 96.26, "elapsed_time": "4:37:54", "remaining_time": "0:10:47", "throughput": 1311.42, "total_tokens": 21867800} {"current_steps": 38510, "total_steps": 40000, "loss": 0.0, "lr": 1.712177213547661e-07, "epoch": 675.6194690265487, "percentage": 96.28, "elapsed_time": "4:37:57", "remaining_time": "0:10:45", "throughput": 1311.44, "total_tokens": 21870968} {"current_steps": 38515, "total_steps": 40000, "loss": 0.0, "lr": 1.7007260688959581e-07, "epoch": 675.70796460177, "percentage": 96.29, "elapsed_time": "4:37:59", "remaining_time": "0:10:43", "throughput": 1311.45, "total_tokens": 21873736} {"current_steps": 38520, "total_steps": 40000, "loss": 0.0, "lr": 1.68931321511262e-07, "epoch": 675.7964601769911, "percentage": 96.3, "elapsed_time": "4:38:01", "remaining_time": "0:10:40", "throughput": 1311.47, "total_tokens": 21876808} {"current_steps": 38525, "total_steps": 40000, "loss": 0.0, "lr": 1.6779386539576835e-07, "epoch": 675.8849557522124, "percentage": 96.31, "elapsed_time": "4:38:03", "remaining_time": "0:10:38", "throughput": 1311.5, "total_tokens": 21879944} {"current_steps": 38530, "total_steps": 40000, "loss": 0.0, "lr": 1.666602387185162e-07, "epoch": 675.9734513274336, "percentage": 96.33, "elapsed_time": "4:38:05", "remaining_time": "0:10:36", "throughput": 1311.51, "total_tokens": 21882920} {"current_steps": 38535, "total_steps": 40000, "loss": 0.0, "lr": 1.655304416543352e-07, "epoch": 676.0530973451328, "percentage": 96.34, "elapsed_time": "4:38:07", "remaining_time": "0:10:34", "throughput": 1311.46, "total_tokens": 21885056} {"current_steps": 38540, "total_steps": 40000, "loss": 0.0, "lr": 1.6440447437744698e-07, "epoch": 676.141592920354, "percentage": 96.35, "elapsed_time": "4:38:09", "remaining_time": "0:10:32", "throughput": 1311.46, "total_tokens": 21887664} {"current_steps": 38545, "total_steps": 40000, "loss": 0.0, "lr": 1.6328233706149332e-07, "epoch": 676.2300884955753, "percentage": 96.36, "elapsed_time": "4:38:11", "remaining_time": "0:10:30", "throughput": 1311.49, "total_tokens": 21890864} {"current_steps": 38550, "total_steps": 40000, "loss": 0.0, "lr": 1.6216402987951906e-07, "epoch": 676.3185840707964, "percentage": 96.38, "elapsed_time": "4:38:13", "remaining_time": "0:10:27", "throughput": 1311.47, "total_tokens": 21893232} {"current_steps": 38555, "total_steps": 40000, "loss": 0.0, "lr": 1.6104955300398627e-07, "epoch": 676.4070796460177, "percentage": 96.39, "elapsed_time": "4:38:15", "remaining_time": "0:10:25", "throughput": 1311.48, "total_tokens": 21896128} {"current_steps": 38560, "total_steps": 40000, "loss": 0.0, "lr": 1.5993890660675748e-07, "epoch": 676.4955752212389, "percentage": 96.4, "elapsed_time": "4:38:17", "remaining_time": "0:10:23", "throughput": 1311.47, "total_tokens": 21898768} {"current_steps": 38565, "total_steps": 40000, "loss": 0.0, "lr": 1.5883209085910678e-07, "epoch": 676.5840707964602, "percentage": 96.41, "elapsed_time": "4:38:19", "remaining_time": "0:10:21", "throughput": 1311.5, "total_tokens": 21901824} {"current_steps": 38570, "total_steps": 40000, "loss": 0.0, "lr": 1.5772910593172264e-07, "epoch": 676.6725663716815, "percentage": 96.43, "elapsed_time": "4:38:21", "remaining_time": "0:10:19", "throughput": 1311.51, "total_tokens": 21904816} {"current_steps": 38575, "total_steps": 40000, "loss": 0.0, "lr": 1.5662995199469954e-07, "epoch": 676.7610619469026, "percentage": 96.44, "elapsed_time": "4:38:24", "remaining_time": "0:10:17", "throughput": 1311.55, "total_tokens": 21908208} {"current_steps": 38580, "total_steps": 40000, "loss": 0.0, "lr": 1.5553462921753802e-07, "epoch": 676.8495575221239, "percentage": 96.45, "elapsed_time": "4:38:26", "remaining_time": "0:10:14", "throughput": 1311.56, "total_tokens": 21911136} {"current_steps": 38585, "total_steps": 40000, "loss": 0.0, "lr": 1.544431377691502e-07, "epoch": 676.9380530973451, "percentage": 96.46, "elapsed_time": "4:38:28", "remaining_time": "0:10:12", "throughput": 1311.57, "total_tokens": 21913952} {"current_steps": 38590, "total_steps": 40000, "loss": 0.0, "lr": 1.5335547781785975e-07, "epoch": 677.0176991150443, "percentage": 96.47, "elapsed_time": "4:38:30", "remaining_time": "0:10:10", "throughput": 1311.55, "total_tokens": 21916616} {"current_steps": 38595, "total_steps": 40000, "loss": 0.0, "lr": 1.5227164953139917e-07, "epoch": 677.1061946902655, "percentage": 96.49, "elapsed_time": "4:38:32", "remaining_time": "0:10:08", "throughput": 1311.56, "total_tokens": 21919464} {"current_steps": 38600, "total_steps": 40000, "loss": 0.0, "lr": 1.511916530769042e-07, "epoch": 677.1946902654868, "percentage": 96.5, "elapsed_time": "4:38:34", "remaining_time": "0:10:06", "throughput": 1311.58, "total_tokens": 21922424} {"current_steps": 38600, "total_steps": 40000, "eval_loss": 0.9197937846183777, "epoch": 677.1946902654868, "percentage": 96.5, "elapsed_time": "4:38:35", "remaining_time": "0:10:06", "throughput": 1311.49, "total_tokens": 21922424} {"current_steps": 38605, "total_steps": 40000, "loss": 0.0, "lr": 1.5011548862092773e-07, "epoch": 677.2831858407079, "percentage": 96.51, "elapsed_time": "4:38:39", "remaining_time": "0:10:04", "throughput": 1311.37, "total_tokens": 21925352} {"current_steps": 38610, "total_steps": 40000, "loss": 0.0, "lr": 1.490431563294231e-07, "epoch": 677.3716814159292, "percentage": 96.53, "elapsed_time": "4:38:41", "remaining_time": "0:10:01", "throughput": 1311.38, "total_tokens": 21928232} {"current_steps": 38615, "total_steps": 40000, "loss": 0.0, "lr": 1.4797465636776365e-07, "epoch": 677.4601769911504, "percentage": 96.54, "elapsed_time": "4:38:43", "remaining_time": "0:09:59", "throughput": 1311.38, "total_tokens": 21930936} {"current_steps": 38620, "total_steps": 40000, "loss": 0.0, "lr": 1.4690998890072027e-07, "epoch": 677.5486725663717, "percentage": 96.55, "elapsed_time": "4:38:45", "remaining_time": "0:09:57", "throughput": 1311.39, "total_tokens": 21933832} {"current_steps": 38625, "total_steps": 40000, "loss": 0.0, "lr": 1.4584915409248112e-07, "epoch": 677.637168141593, "percentage": 96.56, "elapsed_time": "4:38:47", "remaining_time": "0:09:55", "throughput": 1311.39, "total_tokens": 21936584} {"current_steps": 38630, "total_steps": 40000, "loss": 0.0, "lr": 1.4479215210663754e-07, "epoch": 677.7256637168142, "percentage": 96.58, "elapsed_time": "4:38:49", "remaining_time": "0:09:53", "throughput": 1311.37, "total_tokens": 21938936} {"current_steps": 38635, "total_steps": 40000, "loss": 0.0, "lr": 1.4373898310619528e-07, "epoch": 677.8141592920354, "percentage": 96.59, "elapsed_time": "4:38:51", "remaining_time": "0:09:51", "throughput": 1311.39, "total_tokens": 21941928} {"current_steps": 38640, "total_steps": 40000, "loss": 0.0, "lr": 1.4268964725356604e-07, "epoch": 677.9026548672566, "percentage": 96.6, "elapsed_time": "4:38:53", "remaining_time": "0:09:48", "throughput": 1311.41, "total_tokens": 21944952} {"current_steps": 38645, "total_steps": 40000, "loss": 0.0, "lr": 1.4164414471056764e-07, "epoch": 677.9911504424779, "percentage": 96.61, "elapsed_time": "4:38:55", "remaining_time": "0:09:46", "throughput": 1311.41, "total_tokens": 21947768} {"current_steps": 38650, "total_steps": 40000, "loss": 0.0, "lr": 1.4060247563843497e-07, "epoch": 678.070796460177, "percentage": 96.62, "elapsed_time": "4:38:58", "remaining_time": "0:09:44", "throughput": 1311.39, "total_tokens": 21950296} {"current_steps": 38655, "total_steps": 40000, "loss": 0.0, "lr": 1.3956464019780068e-07, "epoch": 678.1592920353983, "percentage": 96.64, "elapsed_time": "4:39:00", "remaining_time": "0:09:42", "throughput": 1311.39, "total_tokens": 21953080} {"current_steps": 38660, "total_steps": 40000, "loss": 0.0, "lr": 1.385306385487145e-07, "epoch": 678.2477876106195, "percentage": 96.65, "elapsed_time": "4:39:02", "remaining_time": "0:09:40", "throughput": 1311.39, "total_tokens": 21955736} {"current_steps": 38665, "total_steps": 40000, "loss": 0.0, "lr": 1.3750047085063222e-07, "epoch": 678.3362831858407, "percentage": 96.66, "elapsed_time": "4:39:04", "remaining_time": "0:09:38", "throughput": 1311.42, "total_tokens": 21958952} {"current_steps": 38670, "total_steps": 40000, "loss": 0.0, "lr": 1.3647413726242119e-07, "epoch": 678.4247787610619, "percentage": 96.67, "elapsed_time": "4:39:06", "remaining_time": "0:09:35", "throughput": 1311.44, "total_tokens": 21962056} {"current_steps": 38675, "total_steps": 40000, "loss": 0.0, "lr": 1.3545163794235205e-07, "epoch": 678.5132743362832, "percentage": 96.69, "elapsed_time": "4:39:08", "remaining_time": "0:09:33", "throughput": 1311.44, "total_tokens": 21964808} {"current_steps": 38680, "total_steps": 40000, "loss": 0.0, "lr": 1.3443297304810698e-07, "epoch": 678.6017699115044, "percentage": 96.7, "elapsed_time": "4:39:10", "remaining_time": "0:09:31", "throughput": 1311.47, "total_tokens": 21967928} {"current_steps": 38685, "total_steps": 40000, "loss": 0.0, "lr": 1.3341814273677977e-07, "epoch": 678.6902654867257, "percentage": 96.71, "elapsed_time": "4:39:12", "remaining_time": "0:09:29", "throughput": 1311.45, "total_tokens": 21970376} {"current_steps": 38690, "total_steps": 40000, "loss": 0.0, "lr": 1.324071471648647e-07, "epoch": 678.7787610619469, "percentage": 96.73, "elapsed_time": "4:39:14", "remaining_time": "0:09:27", "throughput": 1311.46, "total_tokens": 21973208} {"current_steps": 38695, "total_steps": 40000, "loss": 0.0, "lr": 1.3139998648827312e-07, "epoch": 678.8672566371681, "percentage": 96.74, "elapsed_time": "4:39:16", "remaining_time": "0:09:25", "throughput": 1311.51, "total_tokens": 21976712} {"current_steps": 38700, "total_steps": 40000, "loss": 0.0, "lr": 1.3039666086232526e-07, "epoch": 678.9557522123894, "percentage": 96.75, "elapsed_time": "4:39:18", "remaining_time": "0:09:22", "throughput": 1311.53, "total_tokens": 21979784} {"current_steps": 38705, "total_steps": 40000, "loss": 0.0, "lr": 1.2939717044174183e-07, "epoch": 679.0353982300885, "percentage": 96.76, "elapsed_time": "4:39:21", "remaining_time": "0:09:20", "throughput": 1311.49, "total_tokens": 21982024} {"current_steps": 38710, "total_steps": 40000, "loss": 0.0, "lr": 1.284015153806578e-07, "epoch": 679.1238938053098, "percentage": 96.78, "elapsed_time": "4:39:23", "remaining_time": "0:09:18", "throughput": 1311.5, "total_tokens": 21984936} {"current_steps": 38715, "total_steps": 40000, "loss": 0.0, "lr": 1.274096958326171e-07, "epoch": 679.212389380531, "percentage": 96.79, "elapsed_time": "4:39:25", "remaining_time": "0:09:16", "throughput": 1311.52, "total_tokens": 21988008} {"current_steps": 38720, "total_steps": 40000, "loss": 0.0, "lr": 1.2642171195056952e-07, "epoch": 679.3008849557522, "percentage": 96.8, "elapsed_time": "4:39:27", "remaining_time": "0:09:14", "throughput": 1311.52, "total_tokens": 21990760} {"current_steps": 38725, "total_steps": 40000, "loss": 0.0, "lr": 1.2543756388687377e-07, "epoch": 679.3893805309734, "percentage": 96.81, "elapsed_time": "4:39:29", "remaining_time": "0:09:12", "throughput": 1311.52, "total_tokens": 21993464} {"current_steps": 38730, "total_steps": 40000, "loss": 0.0, "lr": 1.2445725179330014e-07, "epoch": 679.4778761061947, "percentage": 96.83, "elapsed_time": "4:39:31", "remaining_time": "0:09:09", "throughput": 1311.53, "total_tokens": 21996376} {"current_steps": 38735, "total_steps": 40000, "loss": 0.0, "lr": 1.2348077582102212e-07, "epoch": 679.566371681416, "percentage": 96.84, "elapsed_time": "4:39:33", "remaining_time": "0:09:07", "throughput": 1311.52, "total_tokens": 21998856} {"current_steps": 38740, "total_steps": 40000, "loss": 0.0, "lr": 1.2250813612062762e-07, "epoch": 679.6548672566372, "percentage": 96.85, "elapsed_time": "4:39:35", "remaining_time": "0:09:05", "throughput": 1311.53, "total_tokens": 22001784} {"current_steps": 38745, "total_steps": 40000, "loss": 0.0, "lr": 1.215393328421105e-07, "epoch": 679.7433628318585, "percentage": 96.86, "elapsed_time": "4:39:37", "remaining_time": "0:09:03", "throughput": 1311.54, "total_tokens": 22004616} {"current_steps": 38750, "total_steps": 40000, "loss": 0.0, "lr": 1.2057436613486796e-07, "epoch": 679.8318584070796, "percentage": 96.88, "elapsed_time": "4:39:39", "remaining_time": "0:09:01", "throughput": 1311.54, "total_tokens": 22007400} {"current_steps": 38755, "total_steps": 40000, "loss": 0.0, "lr": 1.1961323614771424e-07, "epoch": 679.9203539823009, "percentage": 96.89, "elapsed_time": "4:39:41", "remaining_time": "0:08:59", "throughput": 1311.59, "total_tokens": 22010792} {"current_steps": 38760, "total_steps": 40000, "loss": 0.0, "lr": 1.1865594302886418e-07, "epoch": 680.0, "percentage": 96.9, "elapsed_time": "4:39:43", "remaining_time": "0:08:56", "throughput": 1311.59, "total_tokens": 22013496} {"current_steps": 38765, "total_steps": 40000, "loss": 0.0, "lr": 1.1770248692594687e-07, "epoch": 680.0884955752213, "percentage": 96.91, "elapsed_time": "4:39:46", "remaining_time": "0:08:54", "throughput": 1311.57, "total_tokens": 22016200} {"current_steps": 38770, "total_steps": 40000, "loss": 0.0, "lr": 1.167528679859975e-07, "epoch": 680.1769911504425, "percentage": 96.92, "elapsed_time": "4:39:48", "remaining_time": "0:08:52", "throughput": 1311.6, "total_tokens": 22019496} {"current_steps": 38775, "total_steps": 40000, "loss": 0.0, "lr": 1.1580708635545446e-07, "epoch": 680.2654867256637, "percentage": 96.94, "elapsed_time": "4:39:50", "remaining_time": "0:08:50", "throughput": 1311.6, "total_tokens": 22022168} {"current_steps": 38780, "total_steps": 40000, "loss": 0.0, "lr": 1.1486514218017885e-07, "epoch": 680.3539823008849, "percentage": 96.95, "elapsed_time": "4:39:52", "remaining_time": "0:08:48", "throughput": 1311.63, "total_tokens": 22025416} {"current_steps": 38785, "total_steps": 40000, "loss": 0.0, "lr": 1.1392703560542117e-07, "epoch": 680.4424778761062, "percentage": 96.96, "elapsed_time": "4:39:54", "remaining_time": "0:08:46", "throughput": 1311.67, "total_tokens": 22028696} {"current_steps": 38790, "total_steps": 40000, "loss": 0.0, "lr": 1.129927667758518e-07, "epoch": 680.5309734513274, "percentage": 96.97, "elapsed_time": "4:39:56", "remaining_time": "0:08:43", "throughput": 1311.64, "total_tokens": 22031016} {"current_steps": 38795, "total_steps": 40000, "loss": 0.0, "lr": 1.1206233583554992e-07, "epoch": 680.6194690265487, "percentage": 96.99, "elapsed_time": "4:39:58", "remaining_time": "0:08:41", "throughput": 1311.65, "total_tokens": 22033752} {"current_steps": 38800, "total_steps": 40000, "loss": 0.0, "lr": 1.1113574292799523e-07, "epoch": 680.70796460177, "percentage": 97.0, "elapsed_time": "4:40:00", "remaining_time": "0:08:39", "throughput": 1311.65, "total_tokens": 22036600} {"current_steps": 38800, "total_steps": 40000, "eval_loss": 0.9036830067634583, "epoch": 680.70796460177, "percentage": 97.0, "elapsed_time": "4:40:01", "remaining_time": "0:08:39", "throughput": 1311.57, "total_tokens": 22036600} {"current_steps": 38805, "total_steps": 40000, "loss": 0.0, "lr": 1.1021298819608449e-07, "epoch": 680.7964601769911, "percentage": 97.01, "elapsed_time": "4:40:05", "remaining_time": "0:08:37", "throughput": 1311.43, "total_tokens": 22039480} {"current_steps": 38810, "total_steps": 40000, "loss": 0.0, "lr": 1.0929407178211226e-07, "epoch": 680.8849557522124, "percentage": 97.02, "elapsed_time": "4:40:07", "remaining_time": "0:08:35", "throughput": 1311.46, "total_tokens": 22042696} {"current_steps": 38815, "total_steps": 40000, "loss": 0.0, "lr": 1.0837899382779293e-07, "epoch": 680.9734513274336, "percentage": 97.04, "elapsed_time": "4:40:09", "remaining_time": "0:08:33", "throughput": 1311.45, "total_tokens": 22045272} {"current_steps": 38820, "total_steps": 40000, "loss": 0.0, "lr": 1.0746775447423862e-07, "epoch": 681.0530973451328, "percentage": 97.05, "elapsed_time": "4:40:12", "remaining_time": "0:08:31", "throughput": 1311.43, "total_tokens": 22047824} {"current_steps": 38825, "total_steps": 40000, "loss": 0.0, "lr": 1.0656035386197583e-07, "epoch": 681.141592920354, "percentage": 97.06, "elapsed_time": "4:40:14", "remaining_time": "0:08:28", "throughput": 1311.47, "total_tokens": 22051280} {"current_steps": 38830, "total_steps": 40000, "loss": 0.0, "lr": 1.0565679213093982e-07, "epoch": 681.2300884955753, "percentage": 97.08, "elapsed_time": "4:40:16", "remaining_time": "0:08:26", "throughput": 1311.49, "total_tokens": 22054256} {"current_steps": 38835, "total_steps": 40000, "loss": 0.0, "lr": 1.0475706942046638e-07, "epoch": 681.3185840707964, "percentage": 97.09, "elapsed_time": "4:40:18", "remaining_time": "0:08:24", "throughput": 1311.48, "total_tokens": 22056848} {"current_steps": 38840, "total_steps": 40000, "loss": 0.0, "lr": 1.0386118586930282e-07, "epoch": 681.4070796460177, "percentage": 97.1, "elapsed_time": "4:40:20", "remaining_time": "0:08:22", "throughput": 1311.5, "total_tokens": 22059824} {"current_steps": 38845, "total_steps": 40000, "loss": 0.0, "lr": 1.0296914161561367e-07, "epoch": 681.4955752212389, "percentage": 97.11, "elapsed_time": "4:40:22", "remaining_time": "0:08:20", "throughput": 1311.5, "total_tokens": 22062544} {"current_steps": 38850, "total_steps": 40000, "loss": 0.0, "lr": 1.0208093679695552e-07, "epoch": 681.5840707964602, "percentage": 97.12, "elapsed_time": "4:40:24", "remaining_time": "0:08:18", "throughput": 1311.51, "total_tokens": 22065504} {"current_steps": 38855, "total_steps": 40000, "loss": 0.0, "lr": 1.0119657155030493e-07, "epoch": 681.6725663716815, "percentage": 97.14, "elapsed_time": "4:40:26", "remaining_time": "0:08:15", "throughput": 1311.52, "total_tokens": 22068304} {"current_steps": 38860, "total_steps": 40000, "loss": 0.0, "lr": 1.003160460120417e-07, "epoch": 681.7610619469026, "percentage": 97.15, "elapsed_time": "4:40:28", "remaining_time": "0:08:13", "throughput": 1311.51, "total_tokens": 22070832} {"current_steps": 38865, "total_steps": 40000, "loss": 0.0, "lr": 9.943936031795165e-08, "epoch": 681.8495575221239, "percentage": 97.16, "elapsed_time": "4:40:30", "remaining_time": "0:08:11", "throughput": 1311.53, "total_tokens": 22073968} {"current_steps": 38870, "total_steps": 40000, "loss": 0.0, "lr": 9.856651460323219e-08, "epoch": 681.9380530973451, "percentage": 97.17, "elapsed_time": "4:40:32", "remaining_time": "0:08:09", "throughput": 1311.53, "total_tokens": 22076576} {"current_steps": 38875, "total_steps": 40000, "loss": 0.0, "lr": 9.769750900248953e-08, "epoch": 682.0176991150443, "percentage": 97.19, "elapsed_time": "4:40:34", "remaining_time": "0:08:07", "throughput": 1311.49, "total_tokens": 22078808} {"current_steps": 38880, "total_steps": 40000, "loss": 0.0, "lr": 9.683234364973038e-08, "epoch": 682.1061946902655, "percentage": 97.2, "elapsed_time": "4:40:37", "remaining_time": "0:08:05", "throughput": 1311.53, "total_tokens": 22082264} {"current_steps": 38885, "total_steps": 40000, "loss": 0.0, "lr": 9.597101867837854e-08, "epoch": 682.1946902654868, "percentage": 97.21, "elapsed_time": "4:40:39", "remaining_time": "0:08:02", "throughput": 1311.54, "total_tokens": 22085080} {"current_steps": 38890, "total_steps": 40000, "loss": 0.0, "lr": 9.511353422125835e-08, "epoch": 682.2831858407079, "percentage": 97.22, "elapsed_time": "4:40:41", "remaining_time": "0:08:00", "throughput": 1311.57, "total_tokens": 22088376} {"current_steps": 38895, "total_steps": 40000, "loss": 0.0, "lr": 9.42598904106029e-08, "epoch": 682.3716814159292, "percentage": 97.24, "elapsed_time": "4:40:43", "remaining_time": "0:07:58", "throughput": 1311.58, "total_tokens": 22091160} {"current_steps": 38900, "total_steps": 40000, "loss": 0.0, "lr": 9.341008737806245e-08, "epoch": 682.4601769911504, "percentage": 97.25, "elapsed_time": "4:40:45", "remaining_time": "0:07:56", "throughput": 1311.6, "total_tokens": 22094216} {"current_steps": 38905, "total_steps": 40000, "loss": 0.0, "lr": 9.256412525467661e-08, "epoch": 682.5486725663717, "percentage": 97.26, "elapsed_time": "4:40:47", "remaining_time": "0:07:54", "throughput": 1311.65, "total_tokens": 22097736} {"current_steps": 38910, "total_steps": 40000, "loss": 0.0, "lr": 9.172200417091326e-08, "epoch": 682.637168141593, "percentage": 97.28, "elapsed_time": "4:40:49", "remaining_time": "0:07:52", "throughput": 1311.64, "total_tokens": 22100328} {"current_steps": 38915, "total_steps": 40000, "loss": 0.0, "lr": 9.088372425663239e-08, "epoch": 682.7256637168142, "percentage": 97.29, "elapsed_time": "4:40:51", "remaining_time": "0:07:49", "throughput": 1311.64, "total_tokens": 22103096} {"current_steps": 38920, "total_steps": 40000, "loss": 0.0, "lr": 9.004928564110837e-08, "epoch": 682.8141592920354, "percentage": 97.3, "elapsed_time": "4:40:53", "remaining_time": "0:07:47", "throughput": 1311.63, "total_tokens": 22105624} {"current_steps": 38925, "total_steps": 40000, "loss": 0.0, "lr": 8.92186884530244e-08, "epoch": 682.9026548672566, "percentage": 97.31, "elapsed_time": "4:40:55", "remaining_time": "0:07:45", "throughput": 1311.62, "total_tokens": 22108104} {"current_steps": 38930, "total_steps": 40000, "loss": 0.0, "lr": 8.83919328204641e-08, "epoch": 682.9911504424779, "percentage": 97.32, "elapsed_time": "4:40:57", "remaining_time": "0:07:43", "throughput": 1311.62, "total_tokens": 22110808} {"current_steps": 38935, "total_steps": 40000, "loss": 0.0, "lr": 8.756901887093105e-08, "epoch": 683.070796460177, "percentage": 97.34, "elapsed_time": "4:40:59", "remaining_time": "0:07:41", "throughput": 1311.57, "total_tokens": 22112896} {"current_steps": 38940, "total_steps": 40000, "loss": 0.0, "lr": 8.674994673132098e-08, "epoch": 683.1592920353983, "percentage": 97.35, "elapsed_time": "4:41:01", "remaining_time": "0:07:39", "throughput": 1311.61, "total_tokens": 22116272} {"current_steps": 38945, "total_steps": 40000, "loss": 0.0, "lr": 8.593471652794949e-08, "epoch": 683.2477876106195, "percentage": 97.36, "elapsed_time": "4:41:04", "remaining_time": "0:07:36", "throughput": 1311.64, "total_tokens": 22119456} {"current_steps": 38950, "total_steps": 40000, "loss": 0.0, "lr": 8.512332838653548e-08, "epoch": 683.3362831858407, "percentage": 97.38, "elapsed_time": "4:41:06", "remaining_time": "0:07:34", "throughput": 1311.66, "total_tokens": 22122544} {"current_steps": 38955, "total_steps": 40000, "loss": 0.0, "lr": 8.431578243220106e-08, "epoch": 683.4247787610619, "percentage": 97.39, "elapsed_time": "4:41:08", "remaining_time": "0:07:32", "throughput": 1311.69, "total_tokens": 22125728} {"current_steps": 38960, "total_steps": 40000, "loss": 0.0, "lr": 8.351207878948552e-08, "epoch": 683.5132743362832, "percentage": 97.4, "elapsed_time": "4:41:10", "remaining_time": "0:07:30", "throughput": 1311.71, "total_tokens": 22128864} {"current_steps": 38965, "total_steps": 40000, "loss": 0.0, "lr": 8.271221758232583e-08, "epoch": 683.6017699115044, "percentage": 97.41, "elapsed_time": "4:41:12", "remaining_time": "0:07:28", "throughput": 1311.7, "total_tokens": 22131408} {"current_steps": 38970, "total_steps": 40000, "loss": 0.0, "lr": 8.191619893407332e-08, "epoch": 683.6902654867257, "percentage": 97.42, "elapsed_time": "4:41:14", "remaining_time": "0:07:25", "throughput": 1311.69, "total_tokens": 22133920} {"current_steps": 38975, "total_steps": 40000, "loss": 0.0, "lr": 8.112402296748534e-08, "epoch": 683.7787610619469, "percentage": 97.44, "elapsed_time": "4:41:16", "remaining_time": "0:07:23", "throughput": 1311.68, "total_tokens": 22136384} {"current_steps": 38980, "total_steps": 40000, "loss": 0.0, "lr": 8.033568980471973e-08, "epoch": 683.8672566371681, "percentage": 97.45, "elapsed_time": "4:41:18", "remaining_time": "0:07:21", "throughput": 1311.68, "total_tokens": 22139024} {"current_steps": 38985, "total_steps": 40000, "loss": 0.0, "lr": 7.955119956735146e-08, "epoch": 683.9557522123894, "percentage": 97.46, "elapsed_time": "4:41:20", "remaining_time": "0:07:19", "throughput": 1311.7, "total_tokens": 22142064} {"current_steps": 38990, "total_steps": 40000, "loss": 0.0, "lr": 7.877055237636155e-08, "epoch": 684.0353982300885, "percentage": 97.47, "elapsed_time": "4:41:22", "remaining_time": "0:07:17", "throughput": 1311.67, "total_tokens": 22144496} {"current_steps": 38995, "total_steps": 40000, "loss": 0.0, "lr": 7.79937483521287e-08, "epoch": 684.1238938053098, "percentage": 97.49, "elapsed_time": "4:41:24", "remaining_time": "0:07:15", "throughput": 1311.67, "total_tokens": 22147328} {"current_steps": 39000, "total_steps": 40000, "loss": 0.0, "lr": 7.722078761444873e-08, "epoch": 684.212389380531, "percentage": 97.5, "elapsed_time": "4:41:26", "remaining_time": "0:07:12", "throughput": 1311.73, "total_tokens": 22150992} {"current_steps": 39000, "total_steps": 40000, "eval_loss": 0.8996666669845581, "epoch": 684.212389380531, "percentage": 97.5, "elapsed_time": "4:41:27", "remaining_time": "0:07:13", "throughput": 1311.65, "total_tokens": 22150992} {"current_steps": 39005, "total_steps": 40000, "loss": 0.0, "lr": 7.645167028252631e-08, "epoch": 684.3008849557522, "percentage": 97.51, "elapsed_time": "4:41:32", "remaining_time": "0:07:10", "throughput": 1311.42, "total_tokens": 22153408} {"current_steps": 39010, "total_steps": 40000, "loss": 0.0, "lr": 7.568639647496379e-08, "epoch": 684.3893805309734, "percentage": 97.52, "elapsed_time": "4:41:34", "remaining_time": "0:07:08", "throughput": 1311.46, "total_tokens": 22156784} {"current_steps": 39015, "total_steps": 40000, "loss": 0.0, "lr": 7.492496630977508e-08, "epoch": 684.4778761061947, "percentage": 97.54, "elapsed_time": "4:41:36", "remaining_time": "0:07:06", "throughput": 1311.48, "total_tokens": 22159968} {"current_steps": 39020, "total_steps": 40000, "loss": 0.0, "lr": 7.416737990438571e-08, "epoch": 684.566371681416, "percentage": 97.55, "elapsed_time": "4:41:38", "remaining_time": "0:07:04", "throughput": 1311.47, "total_tokens": 22162464} {"current_steps": 39025, "total_steps": 40000, "loss": 0.0, "lr": 7.341363737562445e-08, "epoch": 684.6548672566372, "percentage": 97.56, "elapsed_time": "4:41:40", "remaining_time": "0:07:02", "throughput": 1311.45, "total_tokens": 22164880} {"current_steps": 39030, "total_steps": 40000, "loss": 0.0, "lr": 7.266373883972887e-08, "epoch": 684.7433628318585, "percentage": 97.58, "elapsed_time": "4:41:43", "remaining_time": "0:07:00", "throughput": 1311.44, "total_tokens": 22167280} {"current_steps": 39035, "total_steps": 40000, "loss": 0.0, "lr": 7.191768441233981e-08, "epoch": 684.8318584070796, "percentage": 97.59, "elapsed_time": "4:41:45", "remaining_time": "0:06:57", "throughput": 1311.45, "total_tokens": 22170144} {"current_steps": 39040, "total_steps": 40000, "loss": 0.0, "lr": 7.11754742085069e-08, "epoch": 684.9203539823009, "percentage": 97.6, "elapsed_time": "4:41:47", "remaining_time": "0:06:55", "throughput": 1311.45, "total_tokens": 22172912} {"current_steps": 39045, "total_steps": 40000, "loss": 0.0, "lr": 7.043710834269413e-08, "epoch": 685.0, "percentage": 97.61, "elapsed_time": "4:41:49", "remaining_time": "0:06:53", "throughput": 1311.43, "total_tokens": 22175264} {"current_steps": 39050, "total_steps": 40000, "loss": 0.0, "lr": 6.970258692876319e-08, "epoch": 685.0884955752213, "percentage": 97.62, "elapsed_time": "4:41:51", "remaining_time": "0:06:51", "throughput": 1311.42, "total_tokens": 22178128} {"current_steps": 39055, "total_steps": 40000, "loss": 0.0, "lr": 6.897191007998738e-08, "epoch": 685.1769911504425, "percentage": 97.64, "elapsed_time": "4:41:53", "remaining_time": "0:06:49", "throughput": 1311.43, "total_tokens": 22180960} {"current_steps": 39060, "total_steps": 40000, "loss": 0.0, "lr": 6.824507790904599e-08, "epoch": 685.2654867256637, "percentage": 97.65, "elapsed_time": "4:41:55", "remaining_time": "0:06:47", "throughput": 1311.44, "total_tokens": 22183760} {"current_steps": 39065, "total_steps": 40000, "loss": 0.0, "lr": 6.752209052802439e-08, "epoch": 685.3539823008849, "percentage": 97.66, "elapsed_time": "4:41:57", "remaining_time": "0:06:44", "throughput": 1311.43, "total_tokens": 22186400} {"current_steps": 39070, "total_steps": 40000, "loss": 0.0, "lr": 6.680294804841946e-08, "epoch": 685.4424778761062, "percentage": 97.67, "elapsed_time": "4:41:59", "remaining_time": "0:06:42", "throughput": 1311.43, "total_tokens": 22189040} {"current_steps": 39075, "total_steps": 40000, "loss": 0.0, "lr": 6.608765058112865e-08, "epoch": 685.5309734513274, "percentage": 97.69, "elapsed_time": "4:42:01", "remaining_time": "0:06:40", "throughput": 1311.43, "total_tokens": 22191728} {"current_steps": 39080, "total_steps": 40000, "loss": 0.0, "lr": 6.537619823646368e-08, "epoch": 685.6194690265487, "percentage": 97.7, "elapsed_time": "4:42:03", "remaining_time": "0:06:38", "throughput": 1311.45, "total_tokens": 22194880} {"current_steps": 39085, "total_steps": 40000, "loss": 0.0, "lr": 6.466859112413404e-08, "epoch": 685.70796460177, "percentage": 97.71, "elapsed_time": "4:42:05", "remaining_time": "0:06:36", "throughput": 1311.48, "total_tokens": 22198032} {"current_steps": 39090, "total_steps": 40000, "loss": 0.0, "lr": 6.39648293532663e-08, "epoch": 685.7964601769911, "percentage": 97.72, "elapsed_time": "4:42:07", "remaining_time": "0:06:34", "throughput": 1311.51, "total_tokens": 22201184} {"current_steps": 39095, "total_steps": 40000, "loss": 0.0, "lr": 6.32649130323848e-08, "epoch": 685.8849557522124, "percentage": 97.74, "elapsed_time": "4:42:10", "remaining_time": "0:06:31", "throughput": 1311.52, "total_tokens": 22204144} {"current_steps": 39100, "total_steps": 40000, "loss": 0.0, "lr": 6.256884226943094e-08, "epoch": 685.9734513274336, "percentage": 97.75, "elapsed_time": "4:42:12", "remaining_time": "0:06:29", "throughput": 1311.53, "total_tokens": 22206912} {"current_steps": 39105, "total_steps": 40000, "loss": 0.0, "lr": 6.187661717174386e-08, "epoch": 686.0530973451328, "percentage": 97.76, "elapsed_time": "4:42:14", "remaining_time": "0:06:27", "throughput": 1311.49, "total_tokens": 22209152} {"current_steps": 39110, "total_steps": 40000, "loss": 0.0, "lr": 6.118823784607708e-08, "epoch": 686.141592920354, "percentage": 97.78, "elapsed_time": "4:42:16", "remaining_time": "0:06:25", "throughput": 1311.49, "total_tokens": 22211904} {"current_steps": 39115, "total_steps": 40000, "loss": 0.0, "lr": 6.050370439858178e-08, "epoch": 686.2300884955753, "percentage": 97.79, "elapsed_time": "4:42:18", "remaining_time": "0:06:23", "throughput": 1311.5, "total_tokens": 22214864} {"current_steps": 39120, "total_steps": 40000, "loss": 0.0, "lr": 5.98230169348235e-08, "epoch": 686.3185840707964, "percentage": 97.8, "elapsed_time": "4:42:20", "remaining_time": "0:06:21", "throughput": 1311.49, "total_tokens": 22217424} {"current_steps": 39125, "total_steps": 40000, "loss": 0.0, "lr": 5.914617555977664e-08, "epoch": 686.4070796460177, "percentage": 97.81, "elapsed_time": "4:42:22", "remaining_time": "0:06:18", "throughput": 1311.48, "total_tokens": 22219936} {"current_steps": 39130, "total_steps": 40000, "loss": 0.0, "lr": 5.8473180377816017e-08, "epoch": 686.4955752212389, "percentage": 97.82, "elapsed_time": "4:42:24", "remaining_time": "0:06:16", "throughput": 1311.47, "total_tokens": 22222432} {"current_steps": 39135, "total_steps": 40000, "loss": 0.0, "lr": 5.780403149272251e-08, "epoch": 686.5840707964602, "percentage": 97.84, "elapsed_time": "4:42:26", "remaining_time": "0:06:14", "throughput": 1311.49, "total_tokens": 22225456} {"current_steps": 39140, "total_steps": 40000, "loss": 0.0, "lr": 5.7138729007694126e-08, "epoch": 686.6725663716815, "percentage": 97.85, "elapsed_time": "4:42:28", "remaining_time": "0:06:12", "throughput": 1311.5, "total_tokens": 22228304} {"current_steps": 39145, "total_steps": 40000, "loss": 0.0, "lr": 5.64772730253238e-08, "epoch": 686.7610619469026, "percentage": 97.86, "elapsed_time": "4:42:30", "remaining_time": "0:06:10", "throughput": 1311.54, "total_tokens": 22231824} {"current_steps": 39150, "total_steps": 40000, "loss": 0.0, "lr": 5.5819663647618814e-08, "epoch": 686.8495575221239, "percentage": 97.88, "elapsed_time": "4:42:32", "remaining_time": "0:06:08", "throughput": 1311.55, "total_tokens": 22234688} {"current_steps": 39155, "total_steps": 40000, "loss": 0.0, "lr": 5.5165900975989723e-08, "epoch": 686.9380530973451, "percentage": 97.89, "elapsed_time": "4:42:34", "remaining_time": "0:06:05", "throughput": 1311.57, "total_tokens": 22237632} {"current_steps": 39160, "total_steps": 40000, "loss": 0.0, "lr": 5.451598511125311e-08, "epoch": 687.0176991150443, "percentage": 97.9, "elapsed_time": "4:42:37", "remaining_time": "0:06:03", "throughput": 1311.55, "total_tokens": 22240208} {"current_steps": 39165, "total_steps": 40000, "loss": 0.0, "lr": 5.3869916153637124e-08, "epoch": 687.1061946902655, "percentage": 97.91, "elapsed_time": "4:42:39", "remaining_time": "0:06:01", "throughput": 1311.58, "total_tokens": 22243472} {"current_steps": 39170, "total_steps": 40000, "loss": 0.0, "lr": 5.322769420277318e-08, "epoch": 687.1946902654868, "percentage": 97.92, "elapsed_time": "4:42:41", "remaining_time": "0:05:59", "throughput": 1311.59, "total_tokens": 22246384} {"current_steps": 39175, "total_steps": 40000, "loss": 0.0, "lr": 5.258931935769873e-08, "epoch": 687.2831858407079, "percentage": 97.94, "elapsed_time": "4:42:43", "remaining_time": "0:05:57", "throughput": 1311.62, "total_tokens": 22249520} {"current_steps": 39180, "total_steps": 40000, "loss": 0.0, "lr": 5.19547917168628e-08, "epoch": 687.3716814159292, "percentage": 97.95, "elapsed_time": "4:42:45", "remaining_time": "0:05:55", "throughput": 1311.62, "total_tokens": 22252336} {"current_steps": 39185, "total_steps": 40000, "loss": 0.0, "lr": 5.13241113781121e-08, "epoch": 687.4601769911504, "percentage": 97.96, "elapsed_time": "4:42:47", "remaining_time": "0:05:52", "throughput": 1311.62, "total_tokens": 22254912} {"current_steps": 39190, "total_steps": 40000, "loss": 0.0, "lr": 5.0697278438707755e-08, "epoch": 687.5486725663717, "percentage": 97.97, "elapsed_time": "4:42:49", "remaining_time": "0:05:50", "throughput": 1311.64, "total_tokens": 22258080} {"current_steps": 39195, "total_steps": 40000, "loss": 0.0, "lr": 5.0074292995316854e-08, "epoch": 687.637168141593, "percentage": 97.99, "elapsed_time": "4:42:51", "remaining_time": "0:05:48", "throughput": 1311.66, "total_tokens": 22261072} {"current_steps": 39200, "total_steps": 40000, "loss": 0.0, "lr": 4.945515514400978e-08, "epoch": 687.7256637168142, "percentage": 98.0, "elapsed_time": "4:42:53", "remaining_time": "0:05:46", "throughput": 1311.65, "total_tokens": 22263616} {"current_steps": 39200, "total_steps": 40000, "eval_loss": 0.9019477367401123, "epoch": 687.7256637168142, "percentage": 98.0, "elapsed_time": "4:42:54", "remaining_time": "0:05:46", "throughput": 1311.57, "total_tokens": 22263616} {"current_steps": 39205, "total_steps": 40000, "loss": 0.0, "lr": 4.883986498026571e-08, "epoch": 687.8141592920354, "percentage": 98.01, "elapsed_time": "4:42:58", "remaining_time": "0:05:44", "throughput": 1311.43, "total_tokens": 22266288} {"current_steps": 39210, "total_steps": 40000, "loss": 0.0, "lr": 4.822842259896987e-08, "epoch": 687.9026548672566, "percentage": 98.02, "elapsed_time": "4:43:01", "remaining_time": "0:05:42", "throughput": 1311.42, "total_tokens": 22269216} {"current_steps": 39215, "total_steps": 40000, "loss": 0.0, "lr": 4.762082809441626e-08, "epoch": 687.9911504424779, "percentage": 98.04, "elapsed_time": "4:43:03", "remaining_time": "0:05:39", "throughput": 1311.42, "total_tokens": 22271984} {"current_steps": 39220, "total_steps": 40000, "loss": 0.0, "lr": 4.7017081560302156e-08, "epoch": 688.070796460177, "percentage": 98.05, "elapsed_time": "4:43:05", "remaining_time": "0:05:37", "throughput": 1311.37, "total_tokens": 22274032} {"current_steps": 39225, "total_steps": 40000, "loss": 0.0, "lr": 4.6417183089730866e-08, "epoch": 688.1592920353983, "percentage": 98.06, "elapsed_time": "4:43:07", "remaining_time": "0:05:35", "throughput": 1311.37, "total_tokens": 22276752} {"current_steps": 39230, "total_steps": 40000, "loss": 0.0, "lr": 4.5821132775217265e-08, "epoch": 688.2477876106195, "percentage": 98.08, "elapsed_time": "4:43:09", "remaining_time": "0:05:33", "throughput": 1311.38, "total_tokens": 22279616} {"current_steps": 39235, "total_steps": 40000, "loss": 0.0, "lr": 4.5228930708679504e-08, "epoch": 688.3362831858407, "percentage": 98.09, "elapsed_time": "4:43:11", "remaining_time": "0:05:31", "throughput": 1311.38, "total_tokens": 22282272} {"current_steps": 39240, "total_steps": 40000, "loss": 0.0, "lr": 4.464057698144175e-08, "epoch": 688.4247787610619, "percentage": 98.1, "elapsed_time": "4:43:13", "remaining_time": "0:05:29", "throughput": 1311.4, "total_tokens": 22285376} {"current_steps": 39245, "total_steps": 40000, "loss": 0.0, "lr": 4.4056071684236974e-08, "epoch": 688.5132743362832, "percentage": 98.11, "elapsed_time": "4:43:15", "remaining_time": "0:05:26", "throughput": 1311.42, "total_tokens": 22288400} {"current_steps": 39250, "total_steps": 40000, "loss": 0.0, "lr": 4.347541490719864e-08, "epoch": 688.6017699115044, "percentage": 98.12, "elapsed_time": "4:43:17", "remaining_time": "0:05:24", "throughput": 1311.44, "total_tokens": 22291408} {"current_steps": 39255, "total_steps": 40000, "loss": 0.0, "lr": 4.2898606739877336e-08, "epoch": 688.6902654867257, "percentage": 98.14, "elapsed_time": "4:43:19", "remaining_time": "0:05:22", "throughput": 1311.47, "total_tokens": 22294608} {"current_steps": 39260, "total_steps": 40000, "loss": 0.0, "lr": 4.232564727122135e-08, "epoch": 688.7787610619469, "percentage": 98.15, "elapsed_time": "4:43:21", "remaining_time": "0:05:20", "throughput": 1311.48, "total_tokens": 22297488} {"current_steps": 39265, "total_steps": 40000, "loss": 0.0, "lr": 4.1756536589585004e-08, "epoch": 688.8672566371681, "percentage": 98.16, "elapsed_time": "4:43:23", "remaining_time": "0:05:18", "throughput": 1311.5, "total_tokens": 22300544} {"current_steps": 39270, "total_steps": 40000, "loss": 0.0, "lr": 4.119127478273976e-08, "epoch": 688.9557522123894, "percentage": 98.17, "elapsed_time": "4:43:25", "remaining_time": "0:05:16", "throughput": 1311.51, "total_tokens": 22303408} {"current_steps": 39275, "total_steps": 40000, "loss": 0.0, "lr": 4.062986193784923e-08, "epoch": 689.0353982300885, "percentage": 98.19, "elapsed_time": "4:43:28", "remaining_time": "0:05:13", "throughput": 1311.47, "total_tokens": 22305656} {"current_steps": 39280, "total_steps": 40000, "loss": 0.0, "lr": 4.007229814149416e-08, "epoch": 689.1238938053098, "percentage": 98.2, "elapsed_time": "4:43:30", "remaining_time": "0:05:11", "throughput": 1311.45, "total_tokens": 22308152} {"current_steps": 39285, "total_steps": 40000, "loss": 0.0, "lr": 3.951858347965576e-08, "epoch": 689.212389380531, "percentage": 98.21, "elapsed_time": "4:43:32", "remaining_time": "0:05:09", "throughput": 1311.47, "total_tokens": 22311112} {"current_steps": 39290, "total_steps": 40000, "loss": 0.0, "lr": 3.896871803772684e-08, "epoch": 689.3008849557522, "percentage": 98.22, "elapsed_time": "4:43:34", "remaining_time": "0:05:07", "throughput": 1311.47, "total_tokens": 22313784} {"current_steps": 39295, "total_steps": 40000, "loss": 0.0, "lr": 3.842270190050068e-08, "epoch": 689.3893805309734, "percentage": 98.24, "elapsed_time": "4:43:36", "remaining_time": "0:05:05", "throughput": 1311.47, "total_tokens": 22316552} {"current_steps": 39300, "total_steps": 40000, "loss": 0.0, "lr": 3.7880535152179376e-08, "epoch": 689.4778761061947, "percentage": 98.25, "elapsed_time": "4:43:38", "remaining_time": "0:05:03", "throughput": 1311.49, "total_tokens": 22319544} {"current_steps": 39305, "total_steps": 40000, "loss": 0.0, "lr": 3.734221787637382e-08, "epoch": 689.566371681416, "percentage": 98.26, "elapsed_time": "4:43:40", "remaining_time": "0:05:00", "throughput": 1311.48, "total_tokens": 22322152} {"current_steps": 39310, "total_steps": 40000, "loss": 0.0, "lr": 3.680775015609817e-08, "epoch": 689.6548672566372, "percentage": 98.28, "elapsed_time": "4:43:42", "remaining_time": "0:04:58", "throughput": 1311.51, "total_tokens": 22325224} {"current_steps": 39315, "total_steps": 40000, "loss": 0.0, "lr": 3.627713207377537e-08, "epoch": 689.7433628318585, "percentage": 98.29, "elapsed_time": "4:43:44", "remaining_time": "0:04:56", "throughput": 1311.53, "total_tokens": 22328312} {"current_steps": 39320, "total_steps": 40000, "loss": 0.0, "lr": 3.575036371123164e-08, "epoch": 689.8318584070796, "percentage": 98.3, "elapsed_time": "4:43:46", "remaining_time": "0:04:54", "throughput": 1311.53, "total_tokens": 22330952} {"current_steps": 39325, "total_steps": 40000, "loss": 0.0, "lr": 3.5227445149704776e-08, "epoch": 689.9203539823009, "percentage": 98.31, "elapsed_time": "4:43:48", "remaining_time": "0:04:52", "throughput": 1311.56, "total_tokens": 22334248} {"current_steps": 39330, "total_steps": 40000, "loss": 0.0, "lr": 3.470837646983027e-08, "epoch": 690.0, "percentage": 98.32, "elapsed_time": "4:43:50", "remaining_time": "0:04:50", "throughput": 1311.55, "total_tokens": 22336792} {"current_steps": 39335, "total_steps": 40000, "loss": 0.0, "lr": 3.419315775165799e-08, "epoch": 690.0884955752213, "percentage": 98.34, "elapsed_time": "4:43:53", "remaining_time": "0:04:47", "throughput": 1311.56, "total_tokens": 22339912} {"current_steps": 39340, "total_steps": 40000, "loss": 0.0, "lr": 3.368178907464103e-08, "epoch": 690.1769911504425, "percentage": 98.35, "elapsed_time": "4:43:55", "remaining_time": "0:04:45", "throughput": 1311.55, "total_tokens": 22342344} {"current_steps": 39345, "total_steps": 40000, "loss": 0.0, "lr": 3.317427051763855e-08, "epoch": 690.2654867256637, "percentage": 98.36, "elapsed_time": "4:43:57", "remaining_time": "0:04:43", "throughput": 1311.57, "total_tokens": 22345512} {"current_steps": 39350, "total_steps": 40000, "loss": 0.0, "lr": 3.267060215891571e-08, "epoch": 690.3539823008849, "percentage": 98.38, "elapsed_time": "4:43:59", "remaining_time": "0:04:41", "throughput": 1311.57, "total_tokens": 22348264} {"current_steps": 39355, "total_steps": 40000, "loss": 0.0, "lr": 3.217078407614649e-08, "epoch": 690.4424778761062, "percentage": 98.39, "elapsed_time": "4:44:01", "remaining_time": "0:04:39", "throughput": 1311.59, "total_tokens": 22351208} {"current_steps": 39360, "total_steps": 40000, "loss": 0.0, "lr": 3.1674816346405345e-08, "epoch": 690.5309734513274, "percentage": 98.4, "elapsed_time": "4:44:03", "remaining_time": "0:04:37", "throughput": 1311.64, "total_tokens": 22354824} {"current_steps": 39365, "total_steps": 40000, "loss": 0.0, "lr": 3.11826990461811e-08, "epoch": 690.6194690265487, "percentage": 98.41, "elapsed_time": "4:44:05", "remaining_time": "0:04:34", "throughput": 1311.66, "total_tokens": 22357864} {"current_steps": 39370, "total_steps": 40000, "loss": 0.0, "lr": 3.069443225136304e-08, "epoch": 690.70796460177, "percentage": 98.42, "elapsed_time": "4:44:07", "remaining_time": "0:04:32", "throughput": 1311.66, "total_tokens": 22360520} {"current_steps": 39375, "total_steps": 40000, "loss": 0.0, "lr": 3.021001603724372e-08, "epoch": 690.7964601769911, "percentage": 98.44, "elapsed_time": "4:44:09", "remaining_time": "0:04:30", "throughput": 1311.67, "total_tokens": 22363416} {"current_steps": 39380, "total_steps": 40000, "loss": 0.0, "lr": 2.9729450478532818e-08, "epoch": 690.8849557522124, "percentage": 98.45, "elapsed_time": "4:44:11", "remaining_time": "0:04:28", "throughput": 1311.68, "total_tokens": 22366376} {"current_steps": 39385, "total_steps": 40000, "loss": 0.0, "lr": 2.9252735649337726e-08, "epoch": 690.9734513274336, "percentage": 98.46, "elapsed_time": "4:44:13", "remaining_time": "0:04:26", "throughput": 1311.68, "total_tokens": 22368984} {"current_steps": 39390, "total_steps": 40000, "loss": 0.0, "lr": 2.8779871623171863e-08, "epoch": 691.0530973451328, "percentage": 98.47, "elapsed_time": "4:44:15", "remaining_time": "0:04:24", "throughput": 1311.64, "total_tokens": 22371184} {"current_steps": 39395, "total_steps": 40000, "loss": 0.0, "lr": 2.8310858472957448e-08, "epoch": 691.141592920354, "percentage": 98.49, "elapsed_time": "4:44:18", "remaining_time": "0:04:21", "throughput": 1311.66, "total_tokens": 22374272} {"current_steps": 39400, "total_steps": 40000, "loss": 0.0, "lr": 2.784569627101996e-08, "epoch": 691.2300884955753, "percentage": 98.5, "elapsed_time": "4:44:20", "remaining_time": "0:04:19", "throughput": 1311.71, "total_tokens": 22377936} {"current_steps": 39400, "total_steps": 40000, "eval_loss": 0.8945109844207764, "epoch": 691.2300884955753, "percentage": 98.5, "elapsed_time": "4:44:21", "remaining_time": "0:04:19", "throughput": 1311.63, "total_tokens": 22377936} {"current_steps": 39405, "total_steps": 40000, "loss": 0.0, "lr": 2.738438508909924e-08, "epoch": 691.3185840707964, "percentage": 98.51, "elapsed_time": "4:44:25", "remaining_time": "0:04:17", "throughput": 1311.48, "total_tokens": 22380656} {"current_steps": 39410, "total_steps": 40000, "loss": 0.0, "lr": 2.692692499833005e-08, "epoch": 691.4070796460177, "percentage": 98.52, "elapsed_time": "4:44:27", "remaining_time": "0:04:15", "throughput": 1311.48, "total_tokens": 22383424} {"current_steps": 39415, "total_steps": 40000, "loss": 0.0, "lr": 2.647331606926151e-08, "epoch": 691.4955752212389, "percentage": 98.54, "elapsed_time": "4:44:29", "remaining_time": "0:04:13", "throughput": 1311.46, "total_tokens": 22385840} {"current_steps": 39420, "total_steps": 40000, "loss": 0.0, "lr": 2.6023558371843225e-08, "epoch": 691.5840707964602, "percentage": 98.55, "elapsed_time": "4:44:31", "remaining_time": "0:04:11", "throughput": 1311.47, "total_tokens": 22388720} {"current_steps": 39425, "total_steps": 40000, "loss": 0.0, "lr": 2.557765197543638e-08, "epoch": 691.6725663716815, "percentage": 98.56, "elapsed_time": "4:44:33", "remaining_time": "0:04:09", "throughput": 1311.48, "total_tokens": 22391520} {"current_steps": 39430, "total_steps": 40000, "loss": 0.0, "lr": 2.513559694880263e-08, "epoch": 691.7610619469026, "percentage": 98.58, "elapsed_time": "4:44:35", "remaining_time": "0:04:06", "throughput": 1311.49, "total_tokens": 22394432} {"current_steps": 39435, "total_steps": 40000, "loss": 0.0, "lr": 2.469739336011523e-08, "epoch": 691.8495575221239, "percentage": 98.59, "elapsed_time": "4:44:37", "remaining_time": "0:04:04", "throughput": 1311.5, "total_tokens": 22397264} {"current_steps": 39440, "total_steps": 40000, "loss": 0.0, "lr": 2.4263041276947894e-08, "epoch": 691.9380530973451, "percentage": 98.6, "elapsed_time": "4:44:39", "remaining_time": "0:04:02", "throughput": 1311.51, "total_tokens": 22400176} {"current_steps": 39445, "total_steps": 40000, "loss": 0.0, "lr": 2.3832540766283164e-08, "epoch": 692.0176991150443, "percentage": 98.61, "elapsed_time": "4:44:41", "remaining_time": "0:04:00", "throughput": 1311.47, "total_tokens": 22402368} {"current_steps": 39450, "total_steps": 40000, "loss": 0.0, "lr": 2.3405891894512366e-08, "epoch": 692.1061946902655, "percentage": 98.62, "elapsed_time": "4:44:43", "remaining_time": "0:03:58", "throughput": 1311.46, "total_tokens": 22404960} {"current_steps": 39455, "total_steps": 40000, "loss": 0.0, "lr": 2.29830947274301e-08, "epoch": 692.1946902654868, "percentage": 98.64, "elapsed_time": "4:44:46", "remaining_time": "0:03:56", "throughput": 1311.46, "total_tokens": 22407568} {"current_steps": 39460, "total_steps": 40000, "loss": 0.0, "lr": 2.2564149330231432e-08, "epoch": 692.2831858407079, "percentage": 98.65, "elapsed_time": "4:44:48", "remaining_time": "0:03:53", "throughput": 1311.47, "total_tokens": 22410464} {"current_steps": 39465, "total_steps": 40000, "loss": 0.0, "lr": 2.2149055767528572e-08, "epoch": 692.3716814159292, "percentage": 98.66, "elapsed_time": "4:44:50", "remaining_time": "0:03:51", "throughput": 1311.46, "total_tokens": 22413088} {"current_steps": 39470, "total_steps": 40000, "loss": 0.0, "lr": 2.1737814103334197e-08, "epoch": 692.4601769911504, "percentage": 98.67, "elapsed_time": "4:44:52", "remaining_time": "0:03:49", "throughput": 1311.49, "total_tokens": 22416144} {"current_steps": 39475, "total_steps": 40000, "loss": 0.0, "lr": 2.1330424401064253e-08, "epoch": 692.5486725663717, "percentage": 98.69, "elapsed_time": "4:44:54", "remaining_time": "0:03:47", "throughput": 1311.48, "total_tokens": 22418752} {"current_steps": 39480, "total_steps": 40000, "loss": 0.0, "lr": 2.092688672354348e-08, "epoch": 692.637168141593, "percentage": 98.7, "elapsed_time": "4:44:56", "remaining_time": "0:03:45", "throughput": 1311.51, "total_tokens": 22422064} {"current_steps": 39485, "total_steps": 40000, "loss": 0.0, "lr": 2.0527201133005435e-08, "epoch": 692.7256637168142, "percentage": 98.71, "elapsed_time": "4:44:58", "remaining_time": "0:03:43", "throughput": 1311.57, "total_tokens": 22425712} {"current_steps": 39490, "total_steps": 40000, "loss": 0.0, "lr": 2.0131367691084148e-08, "epoch": 692.8141592920354, "percentage": 98.72, "elapsed_time": "4:45:00", "remaining_time": "0:03:40", "throughput": 1311.58, "total_tokens": 22428624} {"current_steps": 39495, "total_steps": 40000, "loss": 0.0, "lr": 1.9739386458819675e-08, "epoch": 692.9026548672566, "percentage": 98.74, "elapsed_time": "4:45:02", "remaining_time": "0:03:38", "throughput": 1311.58, "total_tokens": 22431344} {"current_steps": 39500, "total_steps": 40000, "loss": 0.0, "lr": 1.9351257496666442e-08, "epoch": 692.9911504424779, "percentage": 98.75, "elapsed_time": "4:45:04", "remaining_time": "0:03:36", "throughput": 1311.58, "total_tokens": 22434000} {"current_steps": 39505, "total_steps": 40000, "loss": 0.0, "lr": 1.896698086447657e-08, "epoch": 693.070796460177, "percentage": 98.76, "elapsed_time": "4:45:06", "remaining_time": "0:03:34", "throughput": 1311.55, "total_tokens": 22436352} {"current_steps": 39510, "total_steps": 40000, "loss": 0.0, "lr": 1.8586556621505436e-08, "epoch": 693.1592920353983, "percentage": 98.78, "elapsed_time": "4:45:08", "remaining_time": "0:03:32", "throughput": 1311.55, "total_tokens": 22439056} {"current_steps": 39515, "total_steps": 40000, "loss": 0.0, "lr": 1.820998482642833e-08, "epoch": 693.2477876106195, "percentage": 98.79, "elapsed_time": "4:45:10", "remaining_time": "0:03:30", "throughput": 1311.58, "total_tokens": 22442384} {"current_steps": 39520, "total_steps": 40000, "loss": 0.0, "lr": 1.7837265537309912e-08, "epoch": 693.3362831858407, "percentage": 98.8, "elapsed_time": "4:45:12", "remaining_time": "0:03:27", "throughput": 1311.62, "total_tokens": 22445760} {"current_steps": 39525, "total_steps": 40000, "loss": 0.0, "lr": 1.7468398811629206e-08, "epoch": 693.4247787610619, "percentage": 98.81, "elapsed_time": "4:45:15", "remaining_time": "0:03:25", "throughput": 1311.63, "total_tokens": 22448672} {"current_steps": 39530, "total_steps": 40000, "loss": 0.0, "lr": 1.710338470627404e-08, "epoch": 693.5132743362832, "percentage": 98.83, "elapsed_time": "4:45:17", "remaining_time": "0:03:23", "throughput": 1311.62, "total_tokens": 22451120} {"current_steps": 39535, "total_steps": 40000, "loss": 0.0, "lr": 1.6742223277529945e-08, "epoch": 693.6017699115044, "percentage": 98.84, "elapsed_time": "4:45:19", "remaining_time": "0:03:21", "throughput": 1311.61, "total_tokens": 22453728} {"current_steps": 39540, "total_steps": 40000, "loss": 0.0, "lr": 1.6384914581094036e-08, "epoch": 693.6902654867257, "percentage": 98.85, "elapsed_time": "4:45:21", "remaining_time": "0:03:19", "throughput": 1311.64, "total_tokens": 22456832} {"current_steps": 39545, "total_steps": 40000, "loss": 0.0, "lr": 1.6031458672069455e-08, "epoch": 693.7787610619469, "percentage": 98.86, "elapsed_time": "4:45:23", "remaining_time": "0:03:17", "throughput": 1311.63, "total_tokens": 22459456} {"current_steps": 39550, "total_steps": 40000, "loss": 0.0, "lr": 1.5681855604962602e-08, "epoch": 693.8672566371681, "percentage": 98.88, "elapsed_time": "4:45:25", "remaining_time": "0:03:14", "throughput": 1311.65, "total_tokens": 22462416} {"current_steps": 39555, "total_steps": 40000, "loss": 0.0, "lr": 1.5336105433683135e-08, "epoch": 693.9557522123894, "percentage": 98.89, "elapsed_time": "4:45:27", "remaining_time": "0:03:12", "throughput": 1311.65, "total_tokens": 22465168} {"current_steps": 39560, "total_steps": 40000, "loss": 0.0, "lr": 1.499420821155506e-08, "epoch": 694.0353982300885, "percentage": 98.9, "elapsed_time": "4:45:29", "remaining_time": "0:03:10", "throughput": 1311.62, "total_tokens": 22467592} {"current_steps": 39565, "total_steps": 40000, "loss": 0.0, "lr": 1.4656163991302874e-08, "epoch": 694.1238938053098, "percentage": 98.91, "elapsed_time": "4:45:31", "remaining_time": "0:03:08", "throughput": 1311.62, "total_tokens": 22470280} {"current_steps": 39570, "total_steps": 40000, "loss": 0.0, "lr": 1.4321972825051544e-08, "epoch": 694.212389380531, "percentage": 98.92, "elapsed_time": "4:45:33", "remaining_time": "0:03:06", "throughput": 1311.65, "total_tokens": 22473576} {"current_steps": 39575, "total_steps": 40000, "loss": 0.0, "lr": 1.3991634764345951e-08, "epoch": 694.3008849557522, "percentage": 98.94, "elapsed_time": "4:45:35", "remaining_time": "0:03:04", "throughput": 1311.64, "total_tokens": 22475960} {"current_steps": 39580, "total_steps": 40000, "loss": 0.0, "lr": 1.3665149860120352e-08, "epoch": 694.3893805309734, "percentage": 98.95, "elapsed_time": "4:45:37", "remaining_time": "0:03:01", "throughput": 1311.65, "total_tokens": 22478872} {"current_steps": 39585, "total_steps": 40000, "loss": 0.0, "lr": 1.3342518162728912e-08, "epoch": 694.4778761061947, "percentage": 98.96, "elapsed_time": "4:45:39", "remaining_time": "0:02:59", "throughput": 1311.64, "total_tokens": 22481368} {"current_steps": 39590, "total_steps": 40000, "loss": 0.0, "lr": 1.30237397219235e-08, "epoch": 694.566371681416, "percentage": 98.98, "elapsed_time": "4:45:41", "remaining_time": "0:02:57", "throughput": 1311.66, "total_tokens": 22484472} {"current_steps": 39595, "total_steps": 40000, "loss": 0.0, "lr": 1.2708814586862016e-08, "epoch": 694.6548672566372, "percentage": 98.99, "elapsed_time": "4:45:44", "remaining_time": "0:02:55", "throughput": 1311.69, "total_tokens": 22487672} {"current_steps": 39600, "total_steps": 40000, "loss": 0.0, "lr": 1.2397742806111168e-08, "epoch": 694.7433628318585, "percentage": 99.0, "elapsed_time": "4:45:46", "remaining_time": "0:02:53", "throughput": 1311.69, "total_tokens": 22490328} {"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.9180490970611572, "epoch": 694.7433628318585, "percentage": 99.0, "elapsed_time": "4:45:47", "remaining_time": "0:02:53", "throughput": 1311.61, "total_tokens": 22490328} {"current_steps": 39605, "total_steps": 40000, "loss": 0.0, "lr": 1.209052442764369e-08, "epoch": 694.8318584070796, "percentage": 99.01, "elapsed_time": "4:45:51", "remaining_time": "0:02:51", "throughput": 1311.47, "total_tokens": 22493160} {"current_steps": 39610, "total_steps": 40000, "loss": 0.0, "lr": 1.17871594988328e-08, "epoch": 694.9203539823009, "percentage": 99.02, "elapsed_time": "4:45:53", "remaining_time": "0:02:48", "throughput": 1311.48, "total_tokens": 22496040} {"current_steps": 39615, "total_steps": 40000, "loss": 0.0, "lr": 1.1487648066466072e-08, "epoch": 695.0, "percentage": 99.04, "elapsed_time": "4:45:55", "remaining_time": "0:02:46", "throughput": 1311.49, "total_tokens": 22498816} {"current_steps": 39620, "total_steps": 40000, "loss": 0.0, "lr": 1.1191990176728784e-08, "epoch": 695.0884955752213, "percentage": 99.05, "elapsed_time": "4:45:57", "remaining_time": "0:02:44", "throughput": 1311.49, "total_tokens": 22501760} {"current_steps": 39625, "total_steps": 40000, "loss": 0.0, "lr": 1.0900185875215018e-08, "epoch": 695.1769911504425, "percentage": 99.06, "elapsed_time": "4:45:59", "remaining_time": "0:02:42", "throughput": 1311.51, "total_tokens": 22504800} {"current_steps": 39630, "total_steps": 40000, "loss": 0.0, "lr": 1.0612235206924891e-08, "epoch": 695.2654867256637, "percentage": 99.08, "elapsed_time": "4:46:01", "remaining_time": "0:02:40", "throughput": 1311.53, "total_tokens": 22507888} {"current_steps": 39635, "total_steps": 40000, "loss": 0.0, "lr": 1.0328138216264549e-08, "epoch": 695.3539823008849, "percentage": 99.09, "elapsed_time": "4:46:03", "remaining_time": "0:02:38", "throughput": 1311.5, "total_tokens": 22510160} {"current_steps": 39640, "total_steps": 40000, "loss": 0.0, "lr": 1.004789494704339e-08, "epoch": 695.4424778761062, "percentage": 99.1, "elapsed_time": "4:46:05", "remaining_time": "0:02:35", "throughput": 1311.5, "total_tokens": 22512816} {"current_steps": 39645, "total_steps": 40000, "loss": 0.0, "lr": 9.771505442482397e-09, "epoch": 695.5309734513274, "percentage": 99.11, "elapsed_time": "4:46:07", "remaining_time": "0:02:33", "throughput": 1311.52, "total_tokens": 22515760} {"current_steps": 39650, "total_steps": 40000, "loss": 0.0, "lr": 9.498969745200259e-09, "epoch": 695.6194690265487, "percentage": 99.12, "elapsed_time": "4:46:09", "remaining_time": "0:02:31", "throughput": 1311.53, "total_tokens": 22518624} {"current_steps": 39655, "total_steps": 40000, "loss": 0.0, "lr": 9.230287897230017e-09, "epoch": 695.70796460177, "percentage": 99.14, "elapsed_time": "4:46:11", "remaining_time": "0:02:29", "throughput": 1311.53, "total_tokens": 22521344} {"current_steps": 39660, "total_steps": 40000, "loss": 0.0, "lr": 8.965459940002419e-09, "epoch": 695.7964601769911, "percentage": 99.15, "elapsed_time": "4:46:13", "remaining_time": "0:02:27", "throughput": 1311.53, "total_tokens": 22524096} {"current_steps": 39665, "total_steps": 40000, "loss": 0.0, "lr": 8.704485914357019e-09, "epoch": 695.8849557522124, "percentage": 99.16, "elapsed_time": "4:46:15", "remaining_time": "0:02:25", "throughput": 1311.56, "total_tokens": 22527280} {"current_steps": 39670, "total_steps": 40000, "loss": 0.0, "lr": 8.447365860539402e-09, "epoch": 695.9734513274336, "percentage": 99.17, "elapsed_time": "4:46:17", "remaining_time": "0:02:22", "throughput": 1311.6, "total_tokens": 22530672} {"current_steps": 39675, "total_steps": 40000, "loss": 0.0, "lr": 8.194099818201184e-09, "epoch": 696.0530973451328, "percentage": 99.19, "elapsed_time": "4:46:20", "remaining_time": "0:02:20", "throughput": 1311.56, "total_tokens": 22532944} {"current_steps": 39680, "total_steps": 40000, "loss": 0.0, "lr": 7.944687826400011e-09, "epoch": 696.141592920354, "percentage": 99.2, "elapsed_time": "4:46:22", "remaining_time": "0:02:18", "throughput": 1311.61, "total_tokens": 22536400} {"current_steps": 39685, "total_steps": 40000, "loss": 0.0, "lr": 7.699129923599557e-09, "epoch": 696.2300884955753, "percentage": 99.21, "elapsed_time": "4:46:24", "remaining_time": "0:02:16", "throughput": 1311.58, "total_tokens": 22538688} {"current_steps": 39690, "total_steps": 40000, "loss": 0.0, "lr": 7.457426147663982e-09, "epoch": 696.3185840707964, "percentage": 99.22, "elapsed_time": "4:46:26", "remaining_time": "0:02:14", "throughput": 1311.63, "total_tokens": 22542336} {"current_steps": 39695, "total_steps": 40000, "loss": 0.0, "lr": 7.219576535871797e-09, "epoch": 696.4070796460177, "percentage": 99.24, "elapsed_time": "4:46:28", "remaining_time": "0:02:12", "throughput": 1311.64, "total_tokens": 22545184} {"current_steps": 39700, "total_steps": 40000, "loss": 0.0, "lr": 6.985581124896445e-09, "epoch": 696.4955752212389, "percentage": 99.25, "elapsed_time": "4:46:30", "remaining_time": "0:02:09", "throughput": 1311.64, "total_tokens": 22547920} {"current_steps": 39705, "total_steps": 40000, "loss": 0.0, "lr": 6.755439950828501e-09, "epoch": 696.5840707964602, "percentage": 99.26, "elapsed_time": "4:46:32", "remaining_time": "0:02:07", "throughput": 1311.64, "total_tokens": 22550592} {"current_steps": 39710, "total_steps": 40000, "loss": 0.0, "lr": 6.5291530491562444e-09, "epoch": 696.6725663716815, "percentage": 99.28, "elapsed_time": "4:46:34", "remaining_time": "0:02:05", "throughput": 1311.64, "total_tokens": 22553216} {"current_steps": 39715, "total_steps": 40000, "loss": 0.0, "lr": 6.3067204547739845e-09, "epoch": 696.7610619469026, "percentage": 99.29, "elapsed_time": "4:46:36", "remaining_time": "0:02:03", "throughput": 1311.65, "total_tokens": 22556144} {"current_steps": 39720, "total_steps": 40000, "loss": 0.0, "lr": 6.088142201987612e-09, "epoch": 696.8495575221239, "percentage": 99.3, "elapsed_time": "4:46:38", "remaining_time": "0:02:01", "throughput": 1311.68, "total_tokens": 22559264} {"current_steps": 39725, "total_steps": 40000, "loss": 0.0, "lr": 5.873418324503499e-09, "epoch": 696.9380530973451, "percentage": 99.31, "elapsed_time": "4:46:40", "remaining_time": "0:01:59", "throughput": 1311.68, "total_tokens": 22562016} {"current_steps": 39730, "total_steps": 40000, "loss": 0.0, "lr": 5.6625488554340465e-09, "epoch": 697.0176991150443, "percentage": 99.33, "elapsed_time": "4:46:43", "remaining_time": "0:01:56", "throughput": 1311.64, "total_tokens": 22564280} {"current_steps": 39735, "total_steps": 40000, "loss": 0.0, "lr": 5.455533827297688e-09, "epoch": 697.1061946902655, "percentage": 99.34, "elapsed_time": "4:46:45", "remaining_time": "0:01:54", "throughput": 1311.66, "total_tokens": 22567400} {"current_steps": 39740, "total_steps": 40000, "loss": 0.0, "lr": 5.252373272018885e-09, "epoch": 697.1946902654868, "percentage": 99.35, "elapsed_time": "4:46:47", "remaining_time": "0:01:52", "throughput": 1311.69, "total_tokens": 22570520} {"current_steps": 39745, "total_steps": 40000, "loss": 0.0, "lr": 5.053067220925356e-09, "epoch": 697.2831858407079, "percentage": 99.36, "elapsed_time": "4:46:49", "remaining_time": "0:01:50", "throughput": 1311.7, "total_tokens": 22573336} {"current_steps": 39750, "total_steps": 40000, "loss": 0.0, "lr": 4.857615704759177e-09, "epoch": 697.3716814159292, "percentage": 99.38, "elapsed_time": "4:46:51", "remaining_time": "0:01:48", "throughput": 1311.7, "total_tokens": 22576152} {"current_steps": 39755, "total_steps": 40000, "loss": 0.0, "lr": 4.666018753654577e-09, "epoch": 697.4601769911504, "percentage": 99.39, "elapsed_time": "4:46:53", "remaining_time": "0:01:46", "throughput": 1311.71, "total_tokens": 22578920} {"current_steps": 39760, "total_steps": 40000, "loss": 0.0, "lr": 4.478276397162917e-09, "epoch": 697.5486725663717, "percentage": 99.4, "elapsed_time": "4:46:55", "remaining_time": "0:01:43", "throughput": 1311.69, "total_tokens": 22581352} {"current_steps": 39765, "total_steps": 40000, "loss": 0.0, "lr": 4.294388664233262e-09, "epoch": 697.637168141593, "percentage": 99.41, "elapsed_time": "4:46:57", "remaining_time": "0:01:41", "throughput": 1311.69, "total_tokens": 22584152} {"current_steps": 39770, "total_steps": 40000, "loss": 0.0, "lr": 4.114355583223484e-09, "epoch": 697.7256637168142, "percentage": 99.42, "elapsed_time": "4:46:59", "remaining_time": "0:01:39", "throughput": 1311.72, "total_tokens": 22587384} {"current_steps": 39775, "total_steps": 40000, "loss": 0.0, "lr": 3.9381771818974845e-09, "epoch": 697.8141592920354, "percentage": 99.44, "elapsed_time": "4:47:01", "remaining_time": "0:01:37", "throughput": 1311.74, "total_tokens": 22590296} {"current_steps": 39780, "total_steps": 40000, "loss": 0.0, "lr": 3.765853487427973e-09, "epoch": 697.9026548672566, "percentage": 99.45, "elapsed_time": "4:47:03", "remaining_time": "0:01:35", "throughput": 1311.74, "total_tokens": 22593032} {"current_steps": 39785, "total_steps": 40000, "loss": 0.0, "lr": 3.5973845263825857e-09, "epoch": 697.9911504424779, "percentage": 99.46, "elapsed_time": "4:47:05", "remaining_time": "0:01:33", "throughput": 1311.76, "total_tokens": 22596136} {"current_steps": 39790, "total_steps": 40000, "loss": 0.0, "lr": 3.4327703247488684e-09, "epoch": 698.070796460177, "percentage": 99.48, "elapsed_time": "4:47:08", "remaining_time": "0:01:30", "throughput": 1311.72, "total_tokens": 22598352} {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 698.1592920353983, "percentage": 99.49, "elapsed_time": "4:47:10", "remaining_time": "0:01:28", "throughput": 1311.72, "total_tokens": 22601024} {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "4:47:12", "remaining_time": "0:01:26", "throughput": 1311.74, "total_tokens": 22604096} {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.909034013748169, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "4:47:13", "remaining_time": "0:01:26", "throughput": 1311.66, "total_tokens": 22604096} {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 698.3362831858407, "percentage": 99.51, "elapsed_time": "4:47:18", "remaining_time": "0:01:24", "throughput": 1311.44, "total_tokens": 22607040} {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 698.4247787610619, "percentage": 99.52, "elapsed_time": "4:47:20", "remaining_time": "0:01:22", "throughput": 1311.43, "total_tokens": 22609568} {"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 2.6675215753724223e-09, "epoch": 698.5132743362832, "percentage": 99.54, "elapsed_time": "4:47:22", "remaining_time": "0:01:20", "throughput": 1311.43, "total_tokens": 22612320} {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 698.6017699115044, "percentage": 99.55, "elapsed_time": "4:47:24", "remaining_time": "0:01:17", "throughput": 1311.45, "total_tokens": 22615328} {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 698.6902654867257, "percentage": 99.56, "elapsed_time": "4:47:26", "remaining_time": "0:01:15", "throughput": 1311.49, "total_tokens": 22618784} {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 698.7787610619469, "percentage": 99.58, "elapsed_time": "4:47:28", "remaining_time": "0:01:13", "throughput": 1311.48, "total_tokens": 22621376} {"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 2.1247106758215397e-09, "epoch": 698.8672566371681, "percentage": 99.59, "elapsed_time": "4:47:30", "remaining_time": "0:01:11", "throughput": 1311.47, "total_tokens": 22623936} {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 698.9557522123894, "percentage": 99.6, "elapsed_time": "4:47:32", "remaining_time": "0:01:09", "throughput": 1311.5, "total_tokens": 22627120} {"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 699.0353982300885, "percentage": 99.61, "elapsed_time": "4:47:35", "remaining_time": "0:01:07", "throughput": 1311.5, "total_tokens": 22629960} {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 699.1238938053098, "percentage": 99.62, "elapsed_time": "4:47:37", "remaining_time": "0:01:04", "throughput": 1311.51, "total_tokens": 22632840} {"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 699.212389380531, "percentage": 99.64, "elapsed_time": "4:47:39", "remaining_time": "0:01:02", "throughput": 1311.51, "total_tokens": 22635656} {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 699.3008849557522, "percentage": 99.65, "elapsed_time": "4:47:41", "remaining_time": "0:01:00", "throughput": 1311.53, "total_tokens": 22638632} {"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 1.4261442765006739e-09, "epoch": 699.3893805309734, "percentage": 99.66, "elapsed_time": "4:47:43", "remaining_time": "0:00:58", "throughput": 1311.53, "total_tokens": 22641400} {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 699.4778761061947, "percentage": 99.67, "elapsed_time": "4:47:45", "remaining_time": "0:00:56", "throughput": 1311.54, "total_tokens": 22644264} {"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 1.2241293807918607e-09, "epoch": 699.566371681416, "percentage": 99.69, "elapsed_time": "4:47:47", "remaining_time": "0:00:54", "throughput": 1311.55, "total_tokens": 22647128} {"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 699.6548672566372, "percentage": 99.7, "elapsed_time": "4:47:49", "remaining_time": "0:00:51", "throughput": 1311.56, "total_tokens": 22649928} {"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 1.0375349860591853e-09, "epoch": 699.7433628318585, "percentage": 99.71, "elapsed_time": "4:47:51", "remaining_time": "0:00:49", "throughput": 1311.57, "total_tokens": 22652840} {"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 699.8318584070796, "percentage": 99.72, "elapsed_time": "4:47:53", "remaining_time": "0:00:47", "throughput": 1311.56, "total_tokens": 22655384} {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 699.9203539823009, "percentage": 99.74, "elapsed_time": "4:47:55", "remaining_time": "0:00:45", "throughput": 1311.57, "total_tokens": 22658232} {"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 700.0, "percentage": 99.75, "elapsed_time": "4:47:57", "remaining_time": "0:00:43", "throughput": 1311.54, "total_tokens": 22660488} {"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 700.0884955752213, "percentage": 99.76, "elapsed_time": "4:48:00", "remaining_time": "0:00:41", "throughput": 1311.53, "total_tokens": 22663336} {"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 700.1769911504425, "percentage": 99.78, "elapsed_time": "4:48:02", "remaining_time": "0:00:38", "throughput": 1311.54, "total_tokens": 22666120} {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 700.2654867256637, "percentage": 99.79, "elapsed_time": "4:48:04", "remaining_time": "0:00:36", "throughput": 1311.53, "total_tokens": 22668648} {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 700.3539823008849, "percentage": 99.8, "elapsed_time": "4:48:06", "remaining_time": "0:00:34", "throughput": 1311.54, "total_tokens": 22671464} {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 700.4424778761062, "percentage": 99.81, "elapsed_time": "4:48:08", "remaining_time": "0:00:32", "throughput": 1311.55, "total_tokens": 22674360} {"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 700.5309734513274, "percentage": 99.83, "elapsed_time": "4:48:10", "remaining_time": "0:00:30", "throughput": 1311.57, "total_tokens": 22677432} {"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 700.6194690265487, "percentage": 99.84, "elapsed_time": "4:48:12", "remaining_time": "0:00:28", "throughput": 1311.58, "total_tokens": 22680296} {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 700.70796460177, "percentage": 99.85, "elapsed_time": "4:48:14", "remaining_time": "0:00:25", "throughput": 1311.6, "total_tokens": 22683304} {"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 700.7964601769911, "percentage": 99.86, "elapsed_time": "4:48:16", "remaining_time": "0:00:23", "throughput": 1311.63, "total_tokens": 22686520} {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 700.8849557522124, "percentage": 99.88, "elapsed_time": "4:48:18", "remaining_time": "0:00:21", "throughput": 1311.63, "total_tokens": 22689240} {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 700.9734513274336, "percentage": 99.89, "elapsed_time": "4:48:20", "remaining_time": "0:00:19", "throughput": 1311.67, "total_tokens": 22692696} {"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 1.2961555204693555e-10, "epoch": 701.0530973451328, "percentage": 99.9, "elapsed_time": "4:48:22", "remaining_time": "0:00:17", "throughput": 1311.63, "total_tokens": 22694888} {"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 9.992967798799768e-11, "epoch": 701.141592920354, "percentage": 99.91, "elapsed_time": "4:48:24", "remaining_time": "0:00:15", "throughput": 1311.66, "total_tokens": 22698120} {"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 701.2300884955753, "percentage": 99.92, "elapsed_time": "4:48:27", "remaining_time": "0:00:12", "throughput": 1311.67, "total_tokens": 22701000} {"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 5.212383012986877e-11, "epoch": 701.3185840707964, "percentage": 99.94, "elapsed_time": "4:48:29", "remaining_time": "0:00:10", "throughput": 1311.71, "total_tokens": 22704392} {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 701.4070796460177, "percentage": 99.95, "elapsed_time": "4:48:31", "remaining_time": "0:00:08", "throughput": 1311.7, "total_tokens": 22707096} {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 701.4955752212389, "percentage": 99.96, "elapsed_time": "4:48:33", "remaining_time": "0:00:06", "throughput": 1311.73, "total_tokens": 22710184} {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 701.5840707964602, "percentage": 99.98, "elapsed_time": "4:48:35", "remaining_time": "0:00:04", "throughput": 1311.75, "total_tokens": 22713240} {"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 2.7758261855748148e-12, "epoch": 701.6725663716815, "percentage": 99.99, "elapsed_time": "4:48:37", "remaining_time": "0:00:02", "throughput": 1311.75, "total_tokens": 22715928} {"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "4:48:39", "remaining_time": "0:00:00", "throughput": 1311.73, "total_tokens": 22718312} {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.9119619131088257, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "4:48:40", "remaining_time": "0:00:00", "throughput": 1311.65, "total_tokens": 22718312} {"current_steps": 40000, "total_steps": 40000, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "4:48:42", "remaining_time": "0:00:00", "throughput": 1311.51, "total_tokens": 22718312}