diff --git "a/trainer_log.jsonl" "b/trainer_log.jsonl" new file mode 100644--- /dev/null +++ "b/trainer_log.jsonl" @@ -0,0 +1,1228 @@ +{"current_steps": 5, "total_steps": 122600, "loss": 1.8362, "lr": 1.631321370309951e-08, "epoch": 0.0008156606851549756, "percentage": 0.0, "elapsed_time": "0:00:02", "remaining_time": "16:38:43", "throughput": 3653.01, "total_tokens": 8928} +{"current_steps": 10, "total_steps": 122600, "loss": 1.1487, "lr": 3.67047308319739e-08, "epoch": 0.0016313213703099511, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "16:18:03", "throughput": 4271.61, "total_tokens": 20448} +{"current_steps": 15, "total_steps": 122600, "loss": 0.5042, "lr": 5.709624796084829e-08, "epoch": 0.0024469820554649264, "percentage": 0.01, "elapsed_time": "0:00:06", "remaining_time": "15:42:57", "throughput": 4488.16, "total_tokens": 31072} +{"current_steps": 20, "total_steps": 122600, "loss": 1.0508, "lr": 7.748776508972267e-08, "epoch": 0.0032626427406199023, "percentage": 0.02, "elapsed_time": "0:00:09", "remaining_time": "15:43:03", "throughput": 4606.5, "total_tokens": 42528} +{"current_steps": 25, "total_steps": 122600, "loss": 1.3011, "lr": 9.787928221859706e-08, "epoch": 0.004078303425774877, "percentage": 0.02, "elapsed_time": "0:00:11", "remaining_time": "15:18:50", "throughput": 4675.84, "total_tokens": 52576} +{"current_steps": 30, "total_steps": 122600, "loss": 0.7666, "lr": 1.1827079934747146e-07, "epoch": 0.004893964110929853, "percentage": 0.02, "elapsed_time": "0:00:13", "remaining_time": "15:06:22", "throughput": 4728.9, "total_tokens": 62944} +{"current_steps": 35, "total_steps": 122600, "loss": 0.7836, "lr": 1.3866231647634585e-07, "epoch": 0.005709624796084829, "percentage": 0.03, "elapsed_time": "0:00:15", "remaining_time": "14:59:57", "throughput": 4766.89, "total_tokens": 73504} +{"current_steps": 40, "total_steps": 122600, "loss": 1.02, "lr": 1.5905383360522023e-07, "epoch": 0.0065252854812398045, "percentage": 0.03, "elapsed_time": "0:00:17", "remaining_time": "15:00:48", "throughput": 4798.23, "total_tokens": 84640} +{"current_steps": 45, "total_steps": 122600, "loss": 0.718, "lr": 1.7944535073409463e-07, "epoch": 0.00734094616639478, "percentage": 0.04, "elapsed_time": "0:00:19", "remaining_time": "15:06:12", "throughput": 4822.93, "total_tokens": 96288} +{"current_steps": 50, "total_steps": 122600, "loss": 1.0312, "lr": 1.99836867862969e-07, "epoch": 0.008156606851549755, "percentage": 0.04, "elapsed_time": "0:00:22", "remaining_time": "15:06:01", "throughput": 4840.52, "total_tokens": 107360} +{"current_steps": 55, "total_steps": 122600, "loss": 0.8805, "lr": 2.2022838499184342e-07, "epoch": 0.00897226753670473, "percentage": 0.04, "elapsed_time": "0:00:24", "remaining_time": "15:05:33", "throughput": 4856.65, "total_tokens": 118432} +{"current_steps": 60, "total_steps": 122600, "loss": 1.0033, "lr": 2.406199021207178e-07, "epoch": 0.009787928221859706, "percentage": 0.05, "elapsed_time": "0:00:26", "remaining_time": "14:58:57", "throughput": 4862.43, "total_tokens": 128416} +{"current_steps": 65, "total_steps": 122600, "loss": 0.4411, "lr": 2.6101141924959217e-07, "epoch": 0.010603588907014683, "percentage": 0.05, "elapsed_time": "0:00:28", "remaining_time": "14:52:48", "throughput": 4871.63, "total_tokens": 138432} +{"current_steps": 70, "total_steps": 122600, "loss": 0.6391, "lr": 2.814029363784666e-07, "epoch": 0.011419249592169658, "percentage": 0.06, "elapsed_time": "0:00:30", "remaining_time": "14:53:57", "throughput": 4879.01, "total_tokens": 149504} +{"current_steps": 75, "total_steps": 122600, "loss": 0.6581, "lr": 3.01794453507341e-07, "epoch": 0.012234910277324634, "percentage": 0.06, "elapsed_time": "0:00:32", "remaining_time": "14:52:23", "throughput": 4887.6, "total_tokens": 160192} +{"current_steps": 80, "total_steps": 122600, "loss": 0.792, "lr": 3.2218597063621533e-07, "epoch": 0.013050570962479609, "percentage": 0.07, "elapsed_time": "0:00:34", "remaining_time": "14:49:03", "throughput": 4893.14, "total_tokens": 170432} +{"current_steps": 85, "total_steps": 122600, "loss": 0.6432, "lr": 3.4257748776508974e-07, "epoch": 0.013866231647634585, "percentage": 0.07, "elapsed_time": "0:00:36", "remaining_time": "14:45:26", "throughput": 4901.73, "total_tokens": 180672} +{"current_steps": 90, "total_steps": 122600, "loss": 0.759, "lr": 3.6296900489396414e-07, "epoch": 0.01468189233278956, "percentage": 0.07, "elapsed_time": "0:00:39", "remaining_time": "14:49:01", "throughput": 4908.67, "total_tokens": 192352} +{"current_steps": 95, "total_steps": 122600, "loss": 0.7326, "lr": 3.833605220228385e-07, "epoch": 0.015497553017944535, "percentage": 0.08, "elapsed_time": "0:00:41", "remaining_time": "14:47:51", "throughput": 4914.89, "total_tokens": 203040} +{"current_steps": 100, "total_steps": 122600, "loss": 1.0211, "lr": 4.037520391517129e-07, "epoch": 0.01631321370309951, "percentage": 0.08, "elapsed_time": "0:00:43", "remaining_time": "14:50:00", "throughput": 4915.36, "total_tokens": 214272} +{"current_steps": 105, "total_steps": 122600, "loss": 0.6563, "lr": 4.241435562805873e-07, "epoch": 0.017128874388254486, "percentage": 0.09, "elapsed_time": "0:00:45", "remaining_time": "14:52:38", "throughput": 4915.41, "total_tokens": 225664} +{"current_steps": 110, "total_steps": 122600, "loss": 1.6699, "lr": 4.4453507340946166e-07, "epoch": 0.01794453507340946, "percentage": 0.09, "elapsed_time": "0:00:48", "remaining_time": "14:55:18", "throughput": 4917.3, "total_tokens": 237216} +{"current_steps": 115, "total_steps": 122600, "loss": 0.7365, "lr": 4.649265905383361e-07, "epoch": 0.018760195758564437, "percentage": 0.09, "elapsed_time": "0:00:50", "remaining_time": "14:49:31", "throughput": 4920.38, "total_tokens": 246560} +{"current_steps": 120, "total_steps": 122600, "loss": 1.3923, "lr": 4.853181076672105e-07, "epoch": 0.01957585644371941, "percentage": 0.1, "elapsed_time": "0:00:52", "remaining_time": "14:48:08", "throughput": 4926.01, "total_tokens": 257184} +{"current_steps": 125, "total_steps": 122600, "loss": 0.7766, "lr": 5.057096247960849e-07, "epoch": 0.020391517128874388, "percentage": 0.1, "elapsed_time": "0:00:54", "remaining_time": "14:48:36", "throughput": 4932.07, "total_tokens": 268384} +{"current_steps": 130, "total_steps": 122600, "loss": 0.5986, "lr": 5.261011419249592e-07, "epoch": 0.021207177814029365, "percentage": 0.11, "elapsed_time": "0:00:56", "remaining_time": "14:50:32", "throughput": 4931.08, "total_tokens": 279680} +{"current_steps": 135, "total_steps": 122600, "loss": 1.2881, "lr": 5.464926590538336e-07, "epoch": 0.02202283849918434, "percentage": 0.11, "elapsed_time": "0:00:58", "remaining_time": "14:51:18", "throughput": 4930.9, "total_tokens": 290688} +{"current_steps": 140, "total_steps": 122600, "loss": 0.9243, "lr": 5.66884176182708e-07, "epoch": 0.022838499184339316, "percentage": 0.11, "elapsed_time": "0:01:01", "remaining_time": "14:50:48", "throughput": 4932.69, "total_tokens": 301408} +{"current_steps": 145, "total_steps": 122600, "loss": 1.1213, "lr": 5.872756933115824e-07, "epoch": 0.02365415986949429, "percentage": 0.12, "elapsed_time": "0:01:03", "remaining_time": "14:50:04", "throughput": 4933.33, "total_tokens": 311968} +{"current_steps": 150, "total_steps": 122600, "loss": 1.4, "lr": 6.076672104404568e-07, "epoch": 0.024469820554649267, "percentage": 0.12, "elapsed_time": "0:01:05", "remaining_time": "14:48:11", "throughput": 4933.73, "total_tokens": 322080} +{"current_steps": 155, "total_steps": 122600, "loss": 1.2958, "lr": 6.280587275693313e-07, "epoch": 0.02528548123980424, "percentage": 0.13, "elapsed_time": "0:01:07", "remaining_time": "14:50:39", "throughput": 4934.7, "total_tokens": 333824} +{"current_steps": 160, "total_steps": 122600, "loss": 1.6995, "lr": 6.484502446982055e-07, "epoch": 0.026101141924959218, "percentage": 0.13, "elapsed_time": "0:01:09", "remaining_time": "14:51:23", "throughput": 4934.86, "total_tokens": 344896} +{"current_steps": 165, "total_steps": 122600, "loss": 0.9158, "lr": 6.6884176182708e-07, "epoch": 0.026916802610114192, "percentage": 0.13, "elapsed_time": "0:01:12", "remaining_time": "14:52:39", "throughput": 4934.78, "total_tokens": 356192} +{"current_steps": 170, "total_steps": 122600, "loss": 0.6812, "lr": 6.892332789559543e-07, "epoch": 0.02773246329526917, "percentage": 0.14, "elapsed_time": "0:01:14", "remaining_time": "14:52:38", "throughput": 4936.68, "total_tokens": 367136} +{"current_steps": 175, "total_steps": 122600, "loss": 0.7793, "lr": 7.096247960848288e-07, "epoch": 0.028548123980424143, "percentage": 0.14, "elapsed_time": "0:01:16", "remaining_time": "14:49:41", "throughput": 4938.46, "total_tokens": 376832} +{"current_steps": 180, "total_steps": 122600, "loss": 0.5227, "lr": 7.300163132137031e-07, "epoch": 0.02936378466557912, "percentage": 0.15, "elapsed_time": "0:01:18", "remaining_time": "14:48:50", "throughput": 4942.32, "total_tokens": 387552} +{"current_steps": 185, "total_steps": 122600, "loss": 1.0487, "lr": 7.504078303425776e-07, "epoch": 0.030179445350734094, "percentage": 0.15, "elapsed_time": "0:01:20", "remaining_time": "14:49:04", "throughput": 4943.48, "total_tokens": 398528} +{"current_steps": 190, "total_steps": 122600, "loss": 0.9109, "lr": 7.707993474714518e-07, "epoch": 0.03099510603588907, "percentage": 0.15, "elapsed_time": "0:01:22", "remaining_time": "14:48:00", "throughput": 4944.32, "total_tokens": 408896} +{"current_steps": 195, "total_steps": 122600, "loss": 0.7836, "lr": 7.911908646003262e-07, "epoch": 0.03181076672104405, "percentage": 0.16, "elapsed_time": "0:01:25", "remaining_time": "14:49:41", "throughput": 4943.74, "total_tokens": 420416} +{"current_steps": 200, "total_steps": 122600, "loss": 0.6284, "lr": 8.115823817292006e-07, "epoch": 0.03262642740619902, "percentage": 0.16, "elapsed_time": "0:01:27", "remaining_time": "14:49:08", "throughput": 4943.33, "total_tokens": 430912} +{"current_steps": 205, "total_steps": 122600, "loss": 1.0304, "lr": 8.319738988580751e-07, "epoch": 0.033442088091353996, "percentage": 0.17, "elapsed_time": "0:01:29", "remaining_time": "14:49:26", "throughput": 4946.93, "total_tokens": 442176} +{"current_steps": 210, "total_steps": 122600, "loss": 0.6616, "lr": 8.523654159869495e-07, "epoch": 0.03425774877650897, "percentage": 0.17, "elapsed_time": "0:01:31", "remaining_time": "14:52:38", "throughput": 4945.74, "total_tokens": 454496} +{"current_steps": 215, "total_steps": 122600, "loss": 0.5149, "lr": 8.727569331158239e-07, "epoch": 0.03507340946166395, "percentage": 0.18, "elapsed_time": "0:01:33", "remaining_time": "14:51:45", "throughput": 4945.88, "total_tokens": 464896} +{"current_steps": 220, "total_steps": 122600, "loss": 1.2458, "lr": 8.931484502446981e-07, "epoch": 0.03588907014681892, "percentage": 0.18, "elapsed_time": "0:01:36", "remaining_time": "14:54:32", "throughput": 4943.98, "total_tokens": 477024} +{"current_steps": 225, "total_steps": 122600, "loss": 0.7705, "lr": 9.135399673735726e-07, "epoch": 0.0367047308319739, "percentage": 0.18, "elapsed_time": "0:01:38", "remaining_time": "14:54:12", "throughput": 4944.68, "total_tokens": 487776} +{"current_steps": 230, "total_steps": 122600, "loss": 0.7368, "lr": 9.339314845024471e-07, "epoch": 0.037520391517128875, "percentage": 0.19, "elapsed_time": "0:01:40", "remaining_time": "14:53:48", "throughput": 4945.86, "total_tokens": 498528} +{"current_steps": 235, "total_steps": 122600, "loss": 0.4768, "lr": 9.543230016313214e-07, "epoch": 0.03833605220228385, "percentage": 0.19, "elapsed_time": "0:01:42", "remaining_time": "14:53:25", "throughput": 4946.04, "total_tokens": 509184} +{"current_steps": 240, "total_steps": 122600, "loss": 0.7518, "lr": 9.747145187601957e-07, "epoch": 0.03915171288743882, "percentage": 0.2, "elapsed_time": "0:01:45", "remaining_time": "14:53:31", "throughput": 4947.17, "total_tokens": 520224} +{"current_steps": 245, "total_steps": 122600, "loss": 1.7933, "lr": 9.951060358890701e-07, "epoch": 0.0399673735725938, "percentage": 0.2, "elapsed_time": "0:01:47", "remaining_time": "14:52:30", "throughput": 4947.08, "total_tokens": 530464} +{"current_steps": 250, "total_steps": 122600, "loss": 1.3675, "lr": 1.0154975530179446e-06, "epoch": 0.040783034257748776, "percentage": 0.2, "elapsed_time": "0:01:49", "remaining_time": "14:53:16", "throughput": 4948.7, "total_tokens": 541952} +{"current_steps": 255, "total_steps": 122600, "loss": 0.5919, "lr": 1.035889070146819e-06, "epoch": 0.041598694942903754, "percentage": 0.21, "elapsed_time": "0:01:51", "remaining_time": "14:50:50", "throughput": 4949.69, "total_tokens": 551424} +{"current_steps": 260, "total_steps": 122600, "loss": 1.4905, "lr": 1.0562805872756933e-06, "epoch": 0.04241435562805873, "percentage": 0.21, "elapsed_time": "0:01:53", "remaining_time": "14:49:30", "throughput": 4949.88, "total_tokens": 561440} +{"current_steps": 265, "total_steps": 122600, "loss": 1.1333, "lr": 1.0766721044045677e-06, "epoch": 0.0432300163132137, "percentage": 0.22, "elapsed_time": "0:01:55", "remaining_time": "14:51:15", "throughput": 4950.39, "total_tokens": 573440} +{"current_steps": 270, "total_steps": 122600, "loss": 0.5284, "lr": 1.0970636215334422e-06, "epoch": 0.04404567699836868, "percentage": 0.22, "elapsed_time": "0:01:57", "remaining_time": "14:50:52", "throughput": 4950.35, "total_tokens": 584032} +{"current_steps": 275, "total_steps": 122600, "loss": 0.9837, "lr": 1.1174551386623167e-06, "epoch": 0.044861337683523655, "percentage": 0.22, "elapsed_time": "0:02:00", "remaining_time": "14:51:19", "throughput": 4951.71, "total_tokens": 595328} +{"current_steps": 280, "total_steps": 122600, "loss": 1.2619, "lr": 1.137846655791191e-06, "epoch": 0.04567699836867863, "percentage": 0.23, "elapsed_time": "0:02:02", "remaining_time": "14:50:33", "throughput": 4952.55, "total_tokens": 605760} +{"current_steps": 285, "total_steps": 122600, "loss": 0.839, "lr": 1.1582381729200654e-06, "epoch": 0.0464926590538336, "percentage": 0.23, "elapsed_time": "0:02:04", "remaining_time": "14:50:03", "throughput": 4953.54, "total_tokens": 616384} +{"current_steps": 290, "total_steps": 122600, "loss": 0.8221, "lr": 1.1786296900489396e-06, "epoch": 0.04730831973898858, "percentage": 0.24, "elapsed_time": "0:02:06", "remaining_time": "14:49:20", "throughput": 4954.86, "total_tokens": 626880} +{"current_steps": 295, "total_steps": 122600, "loss": 1.0448, "lr": 1.199021207177814e-06, "epoch": 0.04812398042414356, "percentage": 0.24, "elapsed_time": "0:02:08", "remaining_time": "14:48:52", "throughput": 4956.0, "total_tokens": 637536} +{"current_steps": 300, "total_steps": 122600, "loss": 0.9338, "lr": 1.2194127243066883e-06, "epoch": 0.048939641109298535, "percentage": 0.24, "elapsed_time": "0:02:10", "remaining_time": "14:48:04", "throughput": 4957.73, "total_tokens": 648000} +{"current_steps": 305, "total_steps": 122600, "loss": 1.5579, "lr": 1.2398042414355628e-06, "epoch": 0.049755301794453505, "percentage": 0.25, "elapsed_time": "0:02:13", "remaining_time": "14:49:20", "throughput": 4956.77, "total_tokens": 659648} +{"current_steps": 310, "total_steps": 122600, "loss": 0.773, "lr": 1.2601957585644372e-06, "epoch": 0.05057096247960848, "percentage": 0.25, "elapsed_time": "0:02:15", "remaining_time": "14:48:22", "throughput": 4957.94, "total_tokens": 669920} +{"current_steps": 315, "total_steps": 122600, "loss": 1.0225, "lr": 1.2805872756933117e-06, "epoch": 0.05138662316476346, "percentage": 0.26, "elapsed_time": "0:02:17", "remaining_time": "14:48:50", "throughput": 4958.72, "total_tokens": 681216} +{"current_steps": 320, "total_steps": 122600, "loss": 1.2867, "lr": 1.3009787928221861e-06, "epoch": 0.052202283849918436, "percentage": 0.26, "elapsed_time": "0:02:19", "remaining_time": "14:48:27", "throughput": 4959.58, "total_tokens": 691872} +{"current_steps": 325, "total_steps": 122600, "loss": 0.6387, "lr": 1.3213703099510604e-06, "epoch": 0.05301794453507341, "percentage": 0.27, "elapsed_time": "0:02:21", "remaining_time": "14:47:32", "throughput": 4961.1, "total_tokens": 702208} +{"current_steps": 330, "total_steps": 122600, "loss": 0.8364, "lr": 1.3417618270799348e-06, "epoch": 0.053833605220228384, "percentage": 0.27, "elapsed_time": "0:02:23", "remaining_time": "14:46:39", "throughput": 4960.8, "total_tokens": 712288} +{"current_steps": 335, "total_steps": 122600, "loss": 1.5123, "lr": 1.3621533442088093e-06, "epoch": 0.05464926590538336, "percentage": 0.27, "elapsed_time": "0:02:25", "remaining_time": "14:46:31", "throughput": 4960.63, "total_tokens": 722976} +{"current_steps": 340, "total_steps": 122600, "loss": 0.7639, "lr": 1.3825448613376838e-06, "epoch": 0.05546492659053834, "percentage": 0.28, "elapsed_time": "0:02:27", "remaining_time": "14:46:28", "throughput": 4960.69, "total_tokens": 733760} +{"current_steps": 345, "total_steps": 122600, "loss": 1.0048, "lr": 1.402936378466558e-06, "epoch": 0.05628058727569331, "percentage": 0.28, "elapsed_time": "0:02:29", "remaining_time": "14:45:08", "throughput": 4961.12, "total_tokens": 743520} +{"current_steps": 350, "total_steps": 122600, "loss": 0.2781, "lr": 1.4233278955954323e-06, "epoch": 0.057096247960848286, "percentage": 0.29, "elapsed_time": "0:02:31", "remaining_time": "14:44:38", "throughput": 4961.62, "total_tokens": 753984} +{"current_steps": 355, "total_steps": 122600, "loss": 0.6741, "lr": 1.4437194127243067e-06, "epoch": 0.05791190864600326, "percentage": 0.29, "elapsed_time": "0:02:34", "remaining_time": "14:45:08", "throughput": 4962.63, "total_tokens": 765376} +{"current_steps": 360, "total_steps": 122600, "loss": 1.2081, "lr": 1.4641109298531812e-06, "epoch": 0.05872756933115824, "percentage": 0.29, "elapsed_time": "0:02:36", "remaining_time": "14:44:42", "throughput": 4963.23, "total_tokens": 775904} +{"current_steps": 365, "total_steps": 122600, "loss": 1.1012, "lr": 1.4845024469820554e-06, "epoch": 0.05954323001631321, "percentage": 0.3, "elapsed_time": "0:02:38", "remaining_time": "14:46:10", "throughput": 4963.13, "total_tokens": 788000} +{"current_steps": 370, "total_steps": 122600, "loss": 1.3682, "lr": 1.5048939641109299e-06, "epoch": 0.06035889070146819, "percentage": 0.3, "elapsed_time": "0:02:40", "remaining_time": "14:46:10", "throughput": 4963.07, "total_tokens": 798816} +{"current_steps": 375, "total_steps": 122600, "loss": 0.5359, "lr": 1.5252854812398043e-06, "epoch": 0.061174551386623165, "percentage": 0.31, "elapsed_time": "0:02:43", "remaining_time": "14:46:23", "throughput": 4963.14, "total_tokens": 809856} +{"current_steps": 380, "total_steps": 122600, "loss": 0.8371, "lr": 1.5456769983686788e-06, "epoch": 0.06199021207177814, "percentage": 0.31, "elapsed_time": "0:02:45", "remaining_time": "14:46:05", "throughput": 4963.45, "total_tokens": 820448} +{"current_steps": 385, "total_steps": 122600, "loss": 1.4792, "lr": 1.566068515497553e-06, "epoch": 0.06280587275693311, "percentage": 0.31, "elapsed_time": "0:02:47", "remaining_time": "14:45:17", "throughput": 4963.97, "total_tokens": 830624} +{"current_steps": 390, "total_steps": 122600, "loss": 0.9351, "lr": 1.5864600326264277e-06, "epoch": 0.0636215334420881, "percentage": 0.32, "elapsed_time": "0:02:49", "remaining_time": "14:44:03", "throughput": 4963.72, "total_tokens": 840224} +{"current_steps": 395, "total_steps": 122600, "loss": 0.9432, "lr": 1.606851549755302e-06, "epoch": 0.06443719412724307, "percentage": 0.32, "elapsed_time": "0:02:51", "remaining_time": "14:43:00", "throughput": 4964.57, "total_tokens": 850176} +{"current_steps": 400, "total_steps": 122600, "loss": 0.6393, "lr": 1.6272430668841762e-06, "epoch": 0.06525285481239804, "percentage": 0.33, "elapsed_time": "0:02:53", "remaining_time": "14:42:55", "throughput": 4965.6, "total_tokens": 861056} +{"current_steps": 405, "total_steps": 122600, "loss": 1.173, "lr": 1.6476345840130507e-06, "epoch": 0.06606851549755302, "percentage": 0.33, "elapsed_time": "0:02:55", "remaining_time": "14:42:23", "throughput": 4965.7, "total_tokens": 871360} +{"current_steps": 410, "total_steps": 122600, "loss": 2.0493, "lr": 1.668026101141925e-06, "epoch": 0.06688417618270799, "percentage": 0.33, "elapsed_time": "0:02:57", "remaining_time": "14:42:56", "throughput": 4965.43, "total_tokens": 882656} +{"current_steps": 415, "total_steps": 122600, "loss": 0.8889, "lr": 1.6884176182707994e-06, "epoch": 0.06769983686786298, "percentage": 0.34, "elapsed_time": "0:03:00", "remaining_time": "14:43:21", "throughput": 4965.87, "total_tokens": 893952} +{"current_steps": 420, "total_steps": 122600, "loss": 0.8155, "lr": 1.7088091353996738e-06, "epoch": 0.06851549755301795, "percentage": 0.34, "elapsed_time": "0:03:02", "remaining_time": "14:44:06", "throughput": 4965.56, "total_tokens": 905472} +{"current_steps": 425, "total_steps": 122600, "loss": 0.9512, "lr": 1.729200652528548e-06, "epoch": 0.06933115823817292, "percentage": 0.35, "elapsed_time": "0:03:04", "remaining_time": "14:43:51", "throughput": 4965.4, "total_tokens": 916000} +{"current_steps": 430, "total_steps": 122600, "loss": 1.0717, "lr": 1.7495921696574227e-06, "epoch": 0.0701468189233279, "percentage": 0.35, "elapsed_time": "0:03:06", "remaining_time": "14:43:59", "throughput": 4965.39, "total_tokens": 926944} +{"current_steps": 435, "total_steps": 122600, "loss": 1.1159, "lr": 1.769983686786297e-06, "epoch": 0.07096247960848287, "percentage": 0.35, "elapsed_time": "0:03:09", "remaining_time": "14:44:40", "throughput": 4965.43, "total_tokens": 938496} +{"current_steps": 440, "total_steps": 122600, "loss": 1.1045, "lr": 1.7903752039151712e-06, "epoch": 0.07177814029363784, "percentage": 0.36, "elapsed_time": "0:03:11", "remaining_time": "14:44:40", "throughput": 4966.18, "total_tokens": 949472} +{"current_steps": 445, "total_steps": 122600, "loss": 1.1812, "lr": 1.810766721044046e-06, "epoch": 0.07259380097879282, "percentage": 0.36, "elapsed_time": "0:03:13", "remaining_time": "14:44:06", "throughput": 4966.32, "total_tokens": 959712} +{"current_steps": 450, "total_steps": 122600, "loss": 1.5608, "lr": 1.8311582381729201e-06, "epoch": 0.0734094616639478, "percentage": 0.37, "elapsed_time": "0:03:15", "remaining_time": "14:43:30", "throughput": 4966.38, "total_tokens": 969888} +{"current_steps": 455, "total_steps": 122600, "loss": 1.218, "lr": 1.8515497553017948e-06, "epoch": 0.07422512234910278, "percentage": 0.37, "elapsed_time": "0:03:17", "remaining_time": "14:43:49", "throughput": 4966.23, "total_tokens": 981024} +{"current_steps": 460, "total_steps": 122600, "loss": 0.6864, "lr": 1.871941272430669e-06, "epoch": 0.07504078303425775, "percentage": 0.38, "elapsed_time": "0:03:19", "remaining_time": "14:43:50", "throughput": 4965.29, "total_tokens": 991680} +{"current_steps": 465, "total_steps": 122600, "loss": 1.3527, "lr": 1.8923327895595433e-06, "epoch": 0.07585644371941272, "percentage": 0.38, "elapsed_time": "0:03:21", "remaining_time": "14:44:07", "throughput": 4966.19, "total_tokens": 1003008} +{"current_steps": 470, "total_steps": 122600, "loss": 0.7279, "lr": 1.9127243066884178e-06, "epoch": 0.0766721044045677, "percentage": 0.38, "elapsed_time": "0:03:24", "remaining_time": "14:44:40", "throughput": 4965.64, "total_tokens": 1014336} +{"current_steps": 475, "total_steps": 122600, "loss": 1.323, "lr": 1.933115823817292e-06, "epoch": 0.07748776508972267, "percentage": 0.39, "elapsed_time": "0:03:26", "remaining_time": "14:44:31", "throughput": 4965.39, "total_tokens": 1024960} +{"current_steps": 480, "total_steps": 122600, "loss": 0.4815, "lr": 1.9535073409461663e-06, "epoch": 0.07830342577487764, "percentage": 0.39, "elapsed_time": "0:03:28", "remaining_time": "14:43:48", "throughput": 4965.06, "total_tokens": 1034880} +{"current_steps": 485, "total_steps": 122600, "loss": 1.6396, "lr": 1.973898858075041e-06, "epoch": 0.07911908646003263, "percentage": 0.4, "elapsed_time": "0:03:30", "remaining_time": "14:44:18", "throughput": 4964.19, "total_tokens": 1046112} +{"current_steps": 490, "total_steps": 122600, "loss": 1.3603, "lr": 1.994290375203915e-06, "epoch": 0.0799347471451876, "percentage": 0.4, "elapsed_time": "0:03:32", "remaining_time": "14:44:07", "throughput": 4964.87, "total_tokens": 1056864} +{"current_steps": 495, "total_steps": 122600, "loss": 0.8702, "lr": 2.01468189233279e-06, "epoch": 0.08075040783034258, "percentage": 0.4, "elapsed_time": "0:03:34", "remaining_time": "14:43:38", "throughput": 4964.76, "total_tokens": 1067072} +{"current_steps": 500, "total_steps": 122600, "loss": 0.8868, "lr": 2.035073409461664e-06, "epoch": 0.08156606851549755, "percentage": 0.41, "elapsed_time": "0:03:37", "remaining_time": "14:44:47", "throughput": 4964.0, "total_tokens": 1079136} +{"current_steps": 505, "total_steps": 122600, "loss": 1.2583, "lr": 2.0554649265905383e-06, "epoch": 0.08238172920065252, "percentage": 0.41, "elapsed_time": "0:03:39", "remaining_time": "14:44:13", "throughput": 4964.59, "total_tokens": 1089408} +{"current_steps": 510, "total_steps": 122600, "loss": 0.618, "lr": 2.075856443719413e-06, "epoch": 0.08319738988580751, "percentage": 0.42, "elapsed_time": "0:03:41", "remaining_time": "14:43:34", "throughput": 4964.89, "total_tokens": 1099488} +{"current_steps": 515, "total_steps": 122600, "loss": 1.2969, "lr": 2.0962479608482872e-06, "epoch": 0.08401305057096248, "percentage": 0.42, "elapsed_time": "0:03:43", "remaining_time": "14:43:34", "throughput": 4965.54, "total_tokens": 1110464} +{"current_steps": 520, "total_steps": 122600, "loss": 0.7165, "lr": 2.1166394779771615e-06, "epoch": 0.08482871125611746, "percentage": 0.42, "elapsed_time": "0:03:45", "remaining_time": "14:43:27", "throughput": 4965.8, "total_tokens": 1121216} +{"current_steps": 525, "total_steps": 122600, "loss": 1.1827, "lr": 2.137030995106036e-06, "epoch": 0.08564437194127243, "percentage": 0.43, "elapsed_time": "0:03:47", "remaining_time": "14:43:23", "throughput": 4966.86, "total_tokens": 1132192} +{"current_steps": 530, "total_steps": 122600, "loss": 1.2209, "lr": 2.1574225122349104e-06, "epoch": 0.0864600326264274, "percentage": 0.43, "elapsed_time": "0:03:50", "remaining_time": "14:43:18", "throughput": 4967.04, "total_tokens": 1142944} +{"current_steps": 535, "total_steps": 122600, "loss": 1.1577, "lr": 2.177814029363785e-06, "epoch": 0.08727569331158239, "percentage": 0.44, "elapsed_time": "0:03:52", "remaining_time": "14:43:33", "throughput": 4966.95, "total_tokens": 1154080} +{"current_steps": 540, "total_steps": 122600, "loss": 1.0745, "lr": 2.1982055464926593e-06, "epoch": 0.08809135399673736, "percentage": 0.44, "elapsed_time": "0:03:54", "remaining_time": "14:43:41", "throughput": 4967.09, "total_tokens": 1165120} +{"current_steps": 545, "total_steps": 122600, "loss": 0.7636, "lr": 2.2185970636215336e-06, "epoch": 0.08890701468189233, "percentage": 0.44, "elapsed_time": "0:03:56", "remaining_time": "14:43:55", "throughput": 4967.44, "total_tokens": 1176352} +{"current_steps": 550, "total_steps": 122600, "loss": 0.4356, "lr": 2.238988580750408e-06, "epoch": 0.08972267536704731, "percentage": 0.45, "elapsed_time": "0:03:59", "remaining_time": "14:44:43", "throughput": 4967.49, "total_tokens": 1188288} +{"current_steps": 555, "total_steps": 122600, "loss": 1.0234, "lr": 2.2593800978792825e-06, "epoch": 0.09053833605220228, "percentage": 0.45, "elapsed_time": "0:04:01", "remaining_time": "14:45:59", "throughput": 4967.23, "total_tokens": 1200800} +{"current_steps": 560, "total_steps": 122600, "loss": 1.0266, "lr": 2.2797716150081567e-06, "epoch": 0.09135399673735727, "percentage": 0.46, "elapsed_time": "0:04:03", "remaining_time": "14:45:50", "throughput": 4966.85, "total_tokens": 1211360} +{"current_steps": 565, "total_steps": 122600, "loss": 0.6731, "lr": 2.300163132137031e-06, "epoch": 0.09216965742251224, "percentage": 0.46, "elapsed_time": "0:04:05", "remaining_time": "14:45:00", "throughput": 4967.24, "total_tokens": 1221184} +{"current_steps": 570, "total_steps": 122600, "loss": 1.2521, "lr": 2.3205546492659052e-06, "epoch": 0.0929853181076672, "percentage": 0.46, "elapsed_time": "0:04:07", "remaining_time": "14:44:44", "throughput": 4967.84, "total_tokens": 1231808} +{"current_steps": 575, "total_steps": 122600, "loss": 0.5523, "lr": 2.34094616639478e-06, "epoch": 0.09380097879282219, "percentage": 0.47, "elapsed_time": "0:04:10", "remaining_time": "14:44:37", "throughput": 4968.07, "total_tokens": 1242560} +{"current_steps": 580, "total_steps": 122600, "loss": 0.5343, "lr": 2.361337683523654e-06, "epoch": 0.09461663947797716, "percentage": 0.47, "elapsed_time": "0:04:12", "remaining_time": "14:44:38", "throughput": 4968.09, "total_tokens": 1253440} +{"current_steps": 585, "total_steps": 122600, "loss": 1.5794, "lr": 2.3817292006525284e-06, "epoch": 0.09543230016313213, "percentage": 0.48, "elapsed_time": "0:04:14", "remaining_time": "14:44:09", "throughput": 4968.15, "total_tokens": 1263616} +{"current_steps": 590, "total_steps": 122600, "loss": 0.5237, "lr": 2.402120717781403e-06, "epoch": 0.09624796084828711, "percentage": 0.48, "elapsed_time": "0:04:16", "remaining_time": "14:44:55", "throughput": 4967.8, "total_tokens": 1275488} +{"current_steps": 595, "total_steps": 122600, "loss": 0.8767, "lr": 2.4225122349102773e-06, "epoch": 0.09706362153344208, "percentage": 0.49, "elapsed_time": "0:04:19", "remaining_time": "14:45:32", "throughput": 4967.63, "total_tokens": 1287200} +{"current_steps": 600, "total_steps": 122600, "loss": 1.3958, "lr": 2.442903752039152e-06, "epoch": 0.09787928221859707, "percentage": 0.49, "elapsed_time": "0:04:21", "remaining_time": "14:45:41", "throughput": 4967.76, "total_tokens": 1298336} +{"current_steps": 605, "total_steps": 122600, "loss": 1.0729, "lr": 2.4632952691680262e-06, "epoch": 0.09869494290375204, "percentage": 0.49, "elapsed_time": "0:04:23", "remaining_time": "14:45:31", "throughput": 4968.1, "total_tokens": 1309056} +{"current_steps": 610, "total_steps": 122600, "loss": 0.7382, "lr": 2.4836867862969005e-06, "epoch": 0.09951060358890701, "percentage": 0.5, "elapsed_time": "0:04:25", "remaining_time": "14:46:07", "throughput": 4968.26, "total_tokens": 1320864} +{"current_steps": 615, "total_steps": 122600, "loss": 1.3793, "lr": 2.504078303425775e-06, "epoch": 0.100326264274062, "percentage": 0.5, "elapsed_time": "0:04:28", "remaining_time": "14:46:33", "throughput": 4968.46, "total_tokens": 1332448} +{"current_steps": 620, "total_steps": 122600, "loss": 1.1724, "lr": 2.5244698205546494e-06, "epoch": 0.10114192495921696, "percentage": 0.51, "elapsed_time": "0:04:30", "remaining_time": "14:45:50", "throughput": 4968.93, "total_tokens": 1342368} +{"current_steps": 625, "total_steps": 122600, "loss": 0.9557, "lr": 2.5448613376835236e-06, "epoch": 0.10195758564437195, "percentage": 0.51, "elapsed_time": "0:04:32", "remaining_time": "14:45:40", "throughput": 4969.02, "total_tokens": 1353024} +{"current_steps": 630, "total_steps": 122600, "loss": 0.9486, "lr": 2.5652528548123983e-06, "epoch": 0.10277324632952692, "percentage": 0.51, "elapsed_time": "0:04:34", "remaining_time": "14:45:47", "throughput": 4968.75, "total_tokens": 1364000} +{"current_steps": 635, "total_steps": 122600, "loss": 1.4974, "lr": 2.5856443719412725e-06, "epoch": 0.10358890701468189, "percentage": 0.52, "elapsed_time": "0:04:36", "remaining_time": "14:45:45", "throughput": 4968.56, "total_tokens": 1374784} +{"current_steps": 640, "total_steps": 122600, "loss": 0.8678, "lr": 2.6060358890701472e-06, "epoch": 0.10440456769983687, "percentage": 0.52, "elapsed_time": "0:04:38", "remaining_time": "14:44:45", "throughput": 4968.83, "total_tokens": 1384192} +{"current_steps": 645, "total_steps": 122600, "loss": 0.7582, "lr": 2.6264274061990215e-06, "epoch": 0.10522022838499184, "percentage": 0.53, "elapsed_time": "0:04:40", "remaining_time": "14:44:52", "throughput": 4969.39, "total_tokens": 1395392} +{"current_steps": 650, "total_steps": 122600, "loss": 0.7403, "lr": 2.6468189233278957e-06, "epoch": 0.10603588907014681, "percentage": 0.53, "elapsed_time": "0:04:42", "remaining_time": "14:44:44", "throughput": 4969.9, "total_tokens": 1406208} +{"current_steps": 655, "total_steps": 122600, "loss": 0.6243, "lr": 2.6672104404567704e-06, "epoch": 0.1068515497553018, "percentage": 0.53, "elapsed_time": "0:04:45", "remaining_time": "14:44:35", "throughput": 4970.58, "total_tokens": 1417024} +{"current_steps": 660, "total_steps": 122600, "loss": 0.9954, "lr": 2.6876019575856446e-06, "epoch": 0.10766721044045677, "percentage": 0.54, "elapsed_time": "0:04:47", "remaining_time": "14:44:31", "throughput": 4970.62, "total_tokens": 1427808} +{"current_steps": 665, "total_steps": 122600, "loss": 0.5469, "lr": 2.707993474714519e-06, "epoch": 0.10848287112561175, "percentage": 0.54, "elapsed_time": "0:04:49", "remaining_time": "14:43:40", "throughput": 4970.72, "total_tokens": 1437344} +{"current_steps": 670, "total_steps": 122600, "loss": 1.0456, "lr": 2.728384991843393e-06, "epoch": 0.10929853181076672, "percentage": 0.55, "elapsed_time": "0:04:51", "remaining_time": "14:43:45", "throughput": 4970.81, "total_tokens": 1448352} +{"current_steps": 675, "total_steps": 122600, "loss": 0.5595, "lr": 2.7487765089722678e-06, "epoch": 0.11011419249592169, "percentage": 0.55, "elapsed_time": "0:04:53", "remaining_time": "14:43:50", "throughput": 4971.32, "total_tokens": 1459520} +{"current_steps": 680, "total_steps": 122600, "loss": 0.7455, "lr": 2.769168026101142e-06, "epoch": 0.11092985318107668, "percentage": 0.55, "elapsed_time": "0:04:55", "remaining_time": "14:43:50", "throughput": 4971.47, "total_tokens": 1470432} +{"current_steps": 685, "total_steps": 122600, "loss": 0.7005, "lr": 2.7895595432300163e-06, "epoch": 0.11174551386623165, "percentage": 0.56, "elapsed_time": "0:04:57", "remaining_time": "14:43:16", "throughput": 4972.13, "total_tokens": 1480544} +{"current_steps": 690, "total_steps": 122600, "loss": 1.0932, "lr": 2.8099510603588905e-06, "epoch": 0.11256117455138662, "percentage": 0.56, "elapsed_time": "0:04:59", "remaining_time": "14:42:59", "throughput": 4971.51, "total_tokens": 1490752} +{"current_steps": 695, "total_steps": 122600, "loss": 0.9863, "lr": 2.830342577487765e-06, "epoch": 0.1133768352365416, "percentage": 0.57, "elapsed_time": "0:05:02", "remaining_time": "14:43:23", "throughput": 4971.32, "total_tokens": 1502240} +{"current_steps": 700, "total_steps": 122600, "loss": 1.2023, "lr": 2.8507340946166394e-06, "epoch": 0.11419249592169657, "percentage": 0.57, "elapsed_time": "0:05:04", "remaining_time": "14:42:50", "throughput": 4971.65, "total_tokens": 1512256} +{"current_steps": 705, "total_steps": 122600, "loss": 1.0729, "lr": 2.871125611745514e-06, "epoch": 0.11500815660685156, "percentage": 0.58, "elapsed_time": "0:05:06", "remaining_time": "14:42:55", "throughput": 4971.33, "total_tokens": 1523168} +{"current_steps": 710, "total_steps": 122600, "loss": 0.5163, "lr": 2.8915171288743884e-06, "epoch": 0.11582381729200653, "percentage": 0.58, "elapsed_time": "0:05:08", "remaining_time": "14:43:22", "throughput": 4971.8, "total_tokens": 1534976} +{"current_steps": 715, "total_steps": 122600, "loss": 1.1814, "lr": 2.9119086460032626e-06, "epoch": 0.1166394779771615, "percentage": 0.58, "elapsed_time": "0:05:10", "remaining_time": "14:43:19", "throughput": 4972.15, "total_tokens": 1545856} +{"current_steps": 720, "total_steps": 122600, "loss": 0.3174, "lr": 2.9323001631321373e-06, "epoch": 0.11745513866231648, "percentage": 0.59, "elapsed_time": "0:05:12", "remaining_time": "14:42:30", "throughput": 4973.37, "total_tokens": 1555680} +{"current_steps": 725, "total_steps": 122600, "loss": 0.3697, "lr": 2.9526916802610115e-06, "epoch": 0.11827079934747145, "percentage": 0.59, "elapsed_time": "0:05:15", "remaining_time": "14:42:55", "throughput": 4973.51, "total_tokens": 1567328} +{"current_steps": 730, "total_steps": 122600, "loss": 1.3134, "lr": 2.9730831973898858e-06, "epoch": 0.11908646003262642, "percentage": 0.6, "elapsed_time": "0:05:17", "remaining_time": "14:42:25", "throughput": 4973.07, "total_tokens": 1577184} +{"current_steps": 735, "total_steps": 122600, "loss": 1.1673, "lr": 2.9934747145187604e-06, "epoch": 0.1199021207177814, "percentage": 0.6, "elapsed_time": "0:05:19", "remaining_time": "14:42:40", "throughput": 4973.21, "total_tokens": 1588544} +{"current_steps": 740, "total_steps": 122600, "loss": 0.8974, "lr": 3.0138662316476347e-06, "epoch": 0.12071778140293637, "percentage": 0.6, "elapsed_time": "0:05:21", "remaining_time": "14:42:55", "throughput": 4972.58, "total_tokens": 1599648} +{"current_steps": 745, "total_steps": 122600, "loss": 1.2286, "lr": 3.0342577487765094e-06, "epoch": 0.12153344208809136, "percentage": 0.61, "elapsed_time": "0:05:24", "remaining_time": "14:43:48", "throughput": 4972.44, "total_tokens": 1612096} +{"current_steps": 750, "total_steps": 122600, "loss": 0.6522, "lr": 3.0546492659053836e-06, "epoch": 0.12234910277324633, "percentage": 0.61, "elapsed_time": "0:05:26", "remaining_time": "14:44:02", "throughput": 4972.94, "total_tokens": 1623584} +{"current_steps": 755, "total_steps": 122600, "loss": 1.1558, "lr": 3.075040783034258e-06, "epoch": 0.1231647634584013, "percentage": 0.62, "elapsed_time": "0:05:28", "remaining_time": "14:44:08", "throughput": 4973.06, "total_tokens": 1634688} +{"current_steps": 760, "total_steps": 122600, "loss": 1.3778, "lr": 3.0954323001631325e-06, "epoch": 0.12398042414355628, "percentage": 0.62, "elapsed_time": "0:05:30", "remaining_time": "14:44:13", "throughput": 4972.59, "total_tokens": 1645600} +{"current_steps": 765, "total_steps": 122600, "loss": 0.5182, "lr": 3.1158238172920068e-06, "epoch": 0.12479608482871125, "percentage": 0.62, "elapsed_time": "0:05:32", "remaining_time": "14:43:53", "throughput": 4972.89, "total_tokens": 1655968} +{"current_steps": 770, "total_steps": 122600, "loss": 1.3224, "lr": 3.1362153344208814e-06, "epoch": 0.12561174551386622, "percentage": 0.63, "elapsed_time": "0:05:35", "remaining_time": "14:43:49", "throughput": 4973.31, "total_tokens": 1666848} +{"current_steps": 775, "total_steps": 122600, "loss": 1.0659, "lr": 3.1566068515497553e-06, "epoch": 0.1264274061990212, "percentage": 0.63, "elapsed_time": "0:05:37", "remaining_time": "14:43:07", "throughput": 4973.55, "total_tokens": 1676512} +{"current_steps": 780, "total_steps": 122600, "loss": 1.0524, "lr": 3.17699836867863e-06, "epoch": 0.1272430668841762, "percentage": 0.64, "elapsed_time": "0:05:39", "remaining_time": "14:43:08", "throughput": 4973.77, "total_tokens": 1687488} +{"current_steps": 785, "total_steps": 122600, "loss": 1.3103, "lr": 3.197389885807504e-06, "epoch": 0.12805872756933115, "percentage": 0.64, "elapsed_time": "0:05:41", "remaining_time": "14:42:30", "throughput": 4974.15, "total_tokens": 1697312} +{"current_steps": 790, "total_steps": 122600, "loss": 1.1716, "lr": 3.2177814029363784e-06, "epoch": 0.12887438825448613, "percentage": 0.64, "elapsed_time": "0:05:43", "remaining_time": "14:42:28", "throughput": 4974.13, "total_tokens": 1708096} +{"current_steps": 795, "total_steps": 122600, "loss": 0.7693, "lr": 3.238172920065253e-06, "epoch": 0.12969004893964112, "percentage": 0.65, "elapsed_time": "0:05:45", "remaining_time": "14:41:47", "throughput": 4974.59, "total_tokens": 1717824} +{"current_steps": 800, "total_steps": 122600, "loss": 1.7591, "lr": 3.2585644371941273e-06, "epoch": 0.13050570962479607, "percentage": 0.65, "elapsed_time": "0:05:47", "remaining_time": "14:41:44", "throughput": 4974.65, "total_tokens": 1728608} +{"current_steps": 805, "total_steps": 122600, "loss": 1.1294, "lr": 3.278955954323002e-06, "epoch": 0.13132137030995106, "percentage": 0.66, "elapsed_time": "0:05:49", "remaining_time": "14:41:37", "throughput": 4975.18, "total_tokens": 1739456} +{"current_steps": 810, "total_steps": 122600, "loss": 1.0482, "lr": 3.299347471451876e-06, "epoch": 0.13213703099510604, "percentage": 0.66, "elapsed_time": "0:05:51", "remaining_time": "14:41:37", "throughput": 4975.18, "total_tokens": 1750304} +{"current_steps": 815, "total_steps": 122600, "loss": 0.7904, "lr": 3.3197389885807505e-06, "epoch": 0.132952691680261, "percentage": 0.66, "elapsed_time": "0:05:54", "remaining_time": "14:42:17", "throughput": 4975.11, "total_tokens": 1762496} +{"current_steps": 820, "total_steps": 122600, "loss": 1.2006, "lr": 3.340130505709625e-06, "epoch": 0.13376835236541598, "percentage": 0.67, "elapsed_time": "0:05:56", "remaining_time": "14:41:56", "throughput": 4975.01, "total_tokens": 1772640} +{"current_steps": 825, "total_steps": 122600, "loss": 0.7774, "lr": 3.360522022838499e-06, "epoch": 0.13458401305057097, "percentage": 0.67, "elapsed_time": "0:05:58", "remaining_time": "14:41:12", "throughput": 4975.6, "total_tokens": 1782272} +{"current_steps": 830, "total_steps": 122600, "loss": 0.8329, "lr": 3.3809135399673737e-06, "epoch": 0.13539967373572595, "percentage": 0.68, "elapsed_time": "0:06:00", "remaining_time": "14:41:08", "throughput": 4975.92, "total_tokens": 1793120} +{"current_steps": 835, "total_steps": 122600, "loss": 1.004, "lr": 3.4013050570962483e-06, "epoch": 0.1362153344208809, "percentage": 0.68, "elapsed_time": "0:06:02", "remaining_time": "14:40:38", "throughput": 4976.73, "total_tokens": 1803264} +{"current_steps": 840, "total_steps": 122600, "loss": 0.3828, "lr": 3.421696574225122e-06, "epoch": 0.1370309951060359, "percentage": 0.69, "elapsed_time": "0:06:04", "remaining_time": "14:40:05", "throughput": 4976.94, "total_tokens": 1813088} +{"current_steps": 845, "total_steps": 122600, "loss": 1.1141, "lr": 3.442088091353997e-06, "epoch": 0.13784665579119088, "percentage": 0.69, "elapsed_time": "0:06:06", "remaining_time": "14:40:07", "throughput": 4976.98, "total_tokens": 1824032} +{"current_steps": 850, "total_steps": 122600, "loss": 1.3558, "lr": 3.4624796084828715e-06, "epoch": 0.13866231647634583, "percentage": 0.69, "elapsed_time": "0:06:09", "remaining_time": "14:40:57", "throughput": 4976.68, "total_tokens": 1836512} +{"current_steps": 855, "total_steps": 122600, "loss": 0.8258, "lr": 3.4828711256117453e-06, "epoch": 0.13947797716150082, "percentage": 0.7, "elapsed_time": "0:06:11", "remaining_time": "14:41:16", "throughput": 4977.19, "total_tokens": 1848256} +{"current_steps": 860, "total_steps": 122600, "loss": 0.7032, "lr": 3.50326264274062e-06, "epoch": 0.1402936378466558, "percentage": 0.7, "elapsed_time": "0:06:13", "remaining_time": "14:41:11", "throughput": 4977.42, "total_tokens": 1859040} +{"current_steps": 865, "total_steps": 122600, "loss": 0.7897, "lr": 3.5236541598694946e-06, "epoch": 0.14110929853181076, "percentage": 0.71, "elapsed_time": "0:06:15", "remaining_time": "14:40:53", "throughput": 4977.29, "total_tokens": 1869248} +{"current_steps": 870, "total_steps": 122600, "loss": 1.4054, "lr": 3.5440456769983693e-06, "epoch": 0.14192495921696574, "percentage": 0.71, "elapsed_time": "0:06:17", "remaining_time": "14:41:22", "throughput": 4977.32, "total_tokens": 1881184} +{"current_steps": 875, "total_steps": 122600, "loss": 0.9772, "lr": 3.564437194127243e-06, "epoch": 0.14274061990212072, "percentage": 0.71, "elapsed_time": "0:06:20", "remaining_time": "14:42:07", "throughput": 4977.53, "total_tokens": 1893760} +{"current_steps": 880, "total_steps": 122600, "loss": 0.823, "lr": 3.584828711256118e-06, "epoch": 0.14355628058727568, "percentage": 0.72, "elapsed_time": "0:06:22", "remaining_time": "14:42:13", "throughput": 4977.38, "total_tokens": 1904800} +{"current_steps": 885, "total_steps": 122600, "loss": 0.7852, "lr": 3.6052202283849925e-06, "epoch": 0.14437194127243066, "percentage": 0.72, "elapsed_time": "0:06:24", "remaining_time": "14:41:53", "throughput": 4978.2, "total_tokens": 1915296} +{"current_steps": 890, "total_steps": 122600, "loss": 1.5265, "lr": 3.6256117455138663e-06, "epoch": 0.14518760195758565, "percentage": 0.73, "elapsed_time": "0:06:26", "remaining_time": "14:41:22", "throughput": 4978.38, "total_tokens": 1925152} +{"current_steps": 895, "total_steps": 122600, "loss": 0.8923, "lr": 3.646003262642741e-06, "epoch": 0.14600326264274063, "percentage": 0.73, "elapsed_time": "0:06:28", "remaining_time": "14:40:54", "throughput": 4978.87, "total_tokens": 1935200} +{"current_steps": 900, "total_steps": 122600, "loss": 1.1944, "lr": 3.6663947797716152e-06, "epoch": 0.1468189233278956, "percentage": 0.73, "elapsed_time": "0:06:30", "remaining_time": "14:40:41", "throughput": 4978.86, "total_tokens": 1945632} +{"current_steps": 905, "total_steps": 122600, "loss": 1.6921, "lr": 3.6867862969004895e-06, "epoch": 0.14763458401305057, "percentage": 0.74, "elapsed_time": "0:06:33", "remaining_time": "14:40:51", "throughput": 4979.12, "total_tokens": 1956992} +{"current_steps": 910, "total_steps": 122600, "loss": 1.2355, "lr": 3.707177814029364e-06, "epoch": 0.14845024469820556, "percentage": 0.74, "elapsed_time": "0:06:35", "remaining_time": "14:41:19", "throughput": 4978.8, "total_tokens": 1968800} +{"current_steps": 915, "total_steps": 122600, "loss": 1.0466, "lr": 3.7275693311582384e-06, "epoch": 0.14926590538336051, "percentage": 0.75, "elapsed_time": "0:06:37", "remaining_time": "14:41:14", "throughput": 4978.66, "total_tokens": 1979424} +{"current_steps": 920, "total_steps": 122600, "loss": 1.4593, "lr": 3.7479608482871126e-06, "epoch": 0.1500815660685155, "percentage": 0.75, "elapsed_time": "0:06:39", "remaining_time": "14:41:29", "throughput": 4978.88, "total_tokens": 1990976} +{"current_steps": 925, "total_steps": 122600, "loss": 0.8367, "lr": 3.768352365415987e-06, "epoch": 0.15089722675367048, "percentage": 0.75, "elapsed_time": "0:06:42", "remaining_time": "14:41:45", "throughput": 4978.72, "total_tokens": 2002432} +{"current_steps": 930, "total_steps": 122600, "loss": 0.8898, "lr": 3.7887438825448615e-06, "epoch": 0.15171288743882544, "percentage": 0.76, "elapsed_time": "0:06:44", "remaining_time": "14:41:53", "throughput": 4978.72, "total_tokens": 2013632} +{"current_steps": 935, "total_steps": 122600, "loss": 1.3758, "lr": 3.8091353996737362e-06, "epoch": 0.15252854812398042, "percentage": 0.76, "elapsed_time": "0:06:46", "remaining_time": "14:42:04", "throughput": 4978.65, "total_tokens": 2024960} +{"current_steps": 940, "total_steps": 122600, "loss": 1.0327, "lr": 3.8295269168026105e-06, "epoch": 0.1533442088091354, "percentage": 0.77, "elapsed_time": "0:06:48", "remaining_time": "14:42:05", "throughput": 4978.21, "total_tokens": 2035712} +{"current_steps": 945, "total_steps": 122600, "loss": 0.6374, "lr": 3.849918433931485e-06, "epoch": 0.15415986949429036, "percentage": 0.77, "elapsed_time": "0:06:51", "remaining_time": "14:42:02", "throughput": 4978.54, "total_tokens": 2046656} +{"current_steps": 950, "total_steps": 122600, "loss": 1.4447, "lr": 3.870309951060359e-06, "epoch": 0.15497553017944535, "percentage": 0.77, "elapsed_time": "0:06:53", "remaining_time": "14:42:15", "throughput": 4978.62, "total_tokens": 2058112} +{"current_steps": 955, "total_steps": 122600, "loss": 1.1959, "lr": 3.890701468189234e-06, "epoch": 0.15579119086460033, "percentage": 0.78, "elapsed_time": "0:06:55", "remaining_time": "14:42:08", "throughput": 4978.64, "total_tokens": 2068768} +{"current_steps": 960, "total_steps": 122600, "loss": 1.3193, "lr": 3.911092985318108e-06, "epoch": 0.1566068515497553, "percentage": 0.78, "elapsed_time": "0:06:57", "remaining_time": "14:42:39", "throughput": 4978.69, "total_tokens": 2080928} +{"current_steps": 965, "total_steps": 122600, "loss": 1.1185, "lr": 3.931484502446982e-06, "epoch": 0.15742251223491027, "percentage": 0.79, "elapsed_time": "0:06:59", "remaining_time": "14:42:12", "throughput": 4978.74, "total_tokens": 2090784} +{"current_steps": 970, "total_steps": 122600, "loss": 0.6389, "lr": 3.951876019575857e-06, "epoch": 0.15823817292006526, "percentage": 0.79, "elapsed_time": "0:07:01", "remaining_time": "14:41:36", "throughput": 4979.1, "total_tokens": 2100416} +{"current_steps": 975, "total_steps": 122600, "loss": 0.5067, "lr": 3.972267536704731e-06, "epoch": 0.15905383360522024, "percentage": 0.8, "elapsed_time": "0:07:04", "remaining_time": "14:41:37", "throughput": 4979.21, "total_tokens": 2111424} +{"current_steps": 980, "total_steps": 122600, "loss": 0.7008, "lr": 3.992659053833605e-06, "epoch": 0.1598694942903752, "percentage": 0.8, "elapsed_time": "0:07:06", "remaining_time": "14:41:30", "throughput": 4979.46, "total_tokens": 2122176} +{"current_steps": 985, "total_steps": 122600, "loss": 0.5742, "lr": 4.013050570962479e-06, "epoch": 0.16068515497553018, "percentage": 0.8, "elapsed_time": "0:07:08", "remaining_time": "14:41:25", "throughput": 4979.55, "total_tokens": 2132928} +{"current_steps": 990, "total_steps": 122600, "loss": 0.534, "lr": 4.033442088091354e-06, "epoch": 0.16150081566068517, "percentage": 0.81, "elapsed_time": "0:07:10", "remaining_time": "14:41:38", "throughput": 4979.85, "total_tokens": 2144480} +{"current_steps": 995, "total_steps": 122600, "loss": 0.7764, "lr": 4.0538336052202284e-06, "epoch": 0.16231647634584012, "percentage": 0.81, "elapsed_time": "0:07:12", "remaining_time": "14:41:13", "throughput": 4979.6, "total_tokens": 2154272} +{"current_steps": 1000, "total_steps": 122600, "loss": 0.2635, "lr": 4.074225122349102e-06, "epoch": 0.1631321370309951, "percentage": 0.82, "elapsed_time": "0:07:14", "remaining_time": "14:40:44", "throughput": 4979.41, "total_tokens": 2163936} +{"current_steps": 1005, "total_steps": 122600, "loss": 0.9814, "lr": 4.094616639477977e-06, "epoch": 0.1639477977161501, "percentage": 0.82, "elapsed_time": "0:07:16", "remaining_time": "14:40:56", "throughput": 4979.55, "total_tokens": 2175392} +{"current_steps": 1010, "total_steps": 122600, "loss": 1.0027, "lr": 4.115008156606852e-06, "epoch": 0.16476345840130505, "percentage": 0.82, "elapsed_time": "0:07:18", "remaining_time": "14:40:26", "throughput": 4979.67, "total_tokens": 2185120} +{"current_steps": 1015, "total_steps": 122600, "loss": 1.4309, "lr": 4.135399673735726e-06, "epoch": 0.16557911908646003, "percentage": 0.83, "elapsed_time": "0:07:21", "remaining_time": "14:40:45", "throughput": 4979.75, "total_tokens": 2196864} +{"current_steps": 1020, "total_steps": 122600, "loss": 1.102, "lr": 4.1557911908646e-06, "epoch": 0.16639477977161501, "percentage": 0.83, "elapsed_time": "0:07:23", "remaining_time": "14:40:42", "throughput": 4979.98, "total_tokens": 2207744} +{"current_steps": 1025, "total_steps": 122600, "loss": 1.8282, "lr": 4.176182707993475e-06, "epoch": 0.16721044045676997, "percentage": 0.84, "elapsed_time": "0:07:25", "remaining_time": "14:40:42", "throughput": 4979.69, "total_tokens": 2218528} +{"current_steps": 1030, "total_steps": 122600, "loss": 0.9121, "lr": 4.1965742251223494e-06, "epoch": 0.16802610114192496, "percentage": 0.84, "elapsed_time": "0:07:27", "remaining_time": "14:40:13", "throughput": 4979.87, "total_tokens": 2228320} +{"current_steps": 1035, "total_steps": 122600, "loss": 1.0336, "lr": 4.216965742251223e-06, "epoch": 0.16884176182707994, "percentage": 0.84, "elapsed_time": "0:07:29", "remaining_time": "14:39:54", "throughput": 4980.0, "total_tokens": 2238464} +{"current_steps": 1040, "total_steps": 122600, "loss": 0.6937, "lr": 4.237357259380098e-06, "epoch": 0.16965742251223492, "percentage": 0.85, "elapsed_time": "0:07:31", "remaining_time": "14:39:56", "throughput": 4979.97, "total_tokens": 2249440} +{"current_steps": 1045, "total_steps": 122600, "loss": 0.9229, "lr": 4.257748776508973e-06, "epoch": 0.17047308319738988, "percentage": 0.85, "elapsed_time": "0:07:33", "remaining_time": "14:40:02", "throughput": 4979.92, "total_tokens": 2260576} +{"current_steps": 1050, "total_steps": 122600, "loss": 0.6676, "lr": 4.278140293637846e-06, "epoch": 0.17128874388254486, "percentage": 0.86, "elapsed_time": "0:07:36", "remaining_time": "14:40:12", "throughput": 4979.85, "total_tokens": 2271904} +{"current_steps": 1055, "total_steps": 122600, "loss": 0.6131, "lr": 4.298531810766721e-06, "epoch": 0.17210440456769985, "percentage": 0.86, "elapsed_time": "0:07:38", "remaining_time": "14:39:41", "throughput": 4980.1, "total_tokens": 2281568} +{"current_steps": 1060, "total_steps": 122600, "loss": 0.5354, "lr": 4.318923327895596e-06, "epoch": 0.1729200652528548, "percentage": 0.86, "elapsed_time": "0:07:40", "remaining_time": "14:39:45", "throughput": 4980.17, "total_tokens": 2292704} +{"current_steps": 1065, "total_steps": 122600, "loss": 0.7002, "lr": 4.33931484502447e-06, "epoch": 0.1737357259380098, "percentage": 0.87, "elapsed_time": "0:07:42", "remaining_time": "14:39:53", "throughput": 4980.07, "total_tokens": 2303904} +{"current_steps": 1070, "total_steps": 122600, "loss": 0.4427, "lr": 4.359706362153344e-06, "epoch": 0.17455138662316477, "percentage": 0.87, "elapsed_time": "0:07:44", "remaining_time": "14:39:38", "throughput": 4980.43, "total_tokens": 2314336} +{"current_steps": 1075, "total_steps": 122600, "loss": 0.461, "lr": 4.380097879282219e-06, "epoch": 0.17536704730831973, "percentage": 0.88, "elapsed_time": "0:07:46", "remaining_time": "14:39:34", "throughput": 4980.37, "total_tokens": 2325024} +{"current_steps": 1080, "total_steps": 122600, "loss": 0.6967, "lr": 4.400489396411094e-06, "epoch": 0.1761827079934747, "percentage": 0.88, "elapsed_time": "0:07:49", "remaining_time": "14:39:42", "throughput": 4980.18, "total_tokens": 2336224} +{"current_steps": 1085, "total_steps": 122600, "loss": 0.4496, "lr": 4.420880913539967e-06, "epoch": 0.1769983686786297, "percentage": 0.88, "elapsed_time": "0:07:51", "remaining_time": "14:39:37", "throughput": 4980.18, "total_tokens": 2346880} +{"current_steps": 1090, "total_steps": 122600, "loss": 0.5866, "lr": 4.441272430668842e-06, "epoch": 0.17781402936378465, "percentage": 0.89, "elapsed_time": "0:07:53", "remaining_time": "14:39:36", "throughput": 4979.91, "total_tokens": 2357632} +{"current_steps": 1095, "total_steps": 122600, "loss": 0.5659, "lr": 4.461663947797717e-06, "epoch": 0.17862969004893964, "percentage": 0.89, "elapsed_time": "0:07:56", "remaining_time": "14:40:23", "throughput": 4979.79, "total_tokens": 2370592} +{"current_steps": 1100, "total_steps": 122600, "loss": 0.9621, "lr": 4.4820554649265906e-06, "epoch": 0.17944535073409462, "percentage": 0.9, "elapsed_time": "0:07:58", "remaining_time": "14:40:11", "throughput": 4979.9, "total_tokens": 2381024} +{"current_steps": 1105, "total_steps": 122600, "loss": 0.5808, "lr": 4.502446982055465e-06, "epoch": 0.1802610114192496, "percentage": 0.9, "elapsed_time": "0:08:00", "remaining_time": "14:40:14", "throughput": 4980.07, "total_tokens": 2392160} +{"current_steps": 1110, "total_steps": 122600, "loss": 1.1409, "lr": 4.52283849918434e-06, "epoch": 0.18107667210440456, "percentage": 0.91, "elapsed_time": "0:08:02", "remaining_time": "14:40:29", "throughput": 4979.71, "total_tokens": 2403616} +{"current_steps": 1115, "total_steps": 122600, "loss": 1.3296, "lr": 4.543230016313214e-06, "epoch": 0.18189233278955955, "percentage": 0.91, "elapsed_time": "0:08:05", "remaining_time": "14:41:03", "throughput": 4979.56, "total_tokens": 2416032} +{"current_steps": 1120, "total_steps": 122600, "loss": 0.658, "lr": 4.563621533442088e-06, "epoch": 0.18270799347471453, "percentage": 0.91, "elapsed_time": "0:08:07", "remaining_time": "14:40:45", "throughput": 4979.54, "total_tokens": 2426112} +{"current_steps": 1125, "total_steps": 122600, "loss": 0.6889, "lr": 4.584013050570963e-06, "epoch": 0.1835236541598695, "percentage": 0.92, "elapsed_time": "0:08:09", "remaining_time": "14:40:49", "throughput": 4979.82, "total_tokens": 2437344} +{"current_steps": 1130, "total_steps": 122600, "loss": 0.8567, "lr": 4.604404567699837e-06, "epoch": 0.18433931484502447, "percentage": 0.92, "elapsed_time": "0:08:11", "remaining_time": "14:40:58", "throughput": 4979.7, "total_tokens": 2448672} +{"current_steps": 1135, "total_steps": 122600, "loss": 0.5637, "lr": 4.6247960848287116e-06, "epoch": 0.18515497553017946, "percentage": 0.93, "elapsed_time": "0:08:13", "remaining_time": "14:40:56", "throughput": 4979.79, "total_tokens": 2459552} +{"current_steps": 1140, "total_steps": 122600, "loss": 0.5045, "lr": 4.645187601957586e-06, "epoch": 0.1859706362153344, "percentage": 0.93, "elapsed_time": "0:08:15", "remaining_time": "14:40:26", "throughput": 4980.01, "total_tokens": 2469184} +{"current_steps": 1145, "total_steps": 122600, "loss": 0.319, "lr": 4.66557911908646e-06, "epoch": 0.1867862969004894, "percentage": 0.93, "elapsed_time": "0:08:18", "remaining_time": "14:40:44", "throughput": 4980.3, "total_tokens": 2481120} +{"current_steps": 1150, "total_steps": 122600, "loss": 0.4469, "lr": 4.685970636215335e-06, "epoch": 0.18760195758564438, "percentage": 0.94, "elapsed_time": "0:08:20", "remaining_time": "14:40:21", "throughput": 4980.36, "total_tokens": 2490976} +{"current_steps": 1155, "total_steps": 122600, "loss": 0.7946, "lr": 4.706362153344209e-06, "epoch": 0.18841761827079934, "percentage": 0.94, "elapsed_time": "0:08:22", "remaining_time": "14:40:04", "throughput": 4980.22, "total_tokens": 2501024} +{"current_steps": 1160, "total_steps": 122600, "loss": 0.7222, "lr": 4.726753670473084e-06, "epoch": 0.18923327895595432, "percentage": 0.95, "elapsed_time": "0:08:24", "remaining_time": "14:39:47", "throughput": 4980.41, "total_tokens": 2511264} +{"current_steps": 1165, "total_steps": 122600, "loss": 0.7106, "lr": 4.747145187601958e-06, "epoch": 0.1900489396411093, "percentage": 0.95, "elapsed_time": "0:08:26", "remaining_time": "14:39:40", "throughput": 4980.51, "total_tokens": 2521920} +{"current_steps": 1170, "total_steps": 122600, "loss": 1.3633, "lr": 4.7675367047308326e-06, "epoch": 0.19086460032626426, "percentage": 0.95, "elapsed_time": "0:08:28", "remaining_time": "14:39:46", "throughput": 4980.39, "total_tokens": 2533056} +{"current_steps": 1175, "total_steps": 122600, "loss": 0.8119, "lr": 4.787928221859707e-06, "epoch": 0.19168026101141925, "percentage": 0.96, "elapsed_time": "0:08:30", "remaining_time": "14:39:55", "throughput": 4980.21, "total_tokens": 2544320} +{"current_steps": 1180, "total_steps": 122600, "loss": 1.3252, "lr": 4.808319738988581e-06, "epoch": 0.19249592169657423, "percentage": 0.96, "elapsed_time": "0:08:33", "remaining_time": "14:39:55", "throughput": 4980.03, "total_tokens": 2555168} +{"current_steps": 1185, "total_steps": 122600, "loss": 0.8723, "lr": 4.828711256117456e-06, "epoch": 0.1933115823817292, "percentage": 0.97, "elapsed_time": "0:08:35", "remaining_time": "14:39:59", "throughput": 4980.05, "total_tokens": 2566304} +{"current_steps": 1190, "total_steps": 122600, "loss": 1.29, "lr": 4.84910277324633e-06, "epoch": 0.19412724306688417, "percentage": 0.97, "elapsed_time": "0:08:37", "remaining_time": "14:39:27", "throughput": 4980.5, "total_tokens": 2575936} +{"current_steps": 1195, "total_steps": 122600, "loss": 1.0293, "lr": 4.869494290375204e-06, "epoch": 0.19494290375203915, "percentage": 0.97, "elapsed_time": "0:08:39", "remaining_time": "14:39:18", "throughput": 4980.72, "total_tokens": 2586528} +{"current_steps": 1200, "total_steps": 122600, "loss": 0.5315, "lr": 4.889885807504079e-06, "epoch": 0.19575856443719414, "percentage": 0.98, "elapsed_time": "0:08:41", "remaining_time": "14:38:49", "throughput": 4980.78, "total_tokens": 2596064} +{"current_steps": 1205, "total_steps": 122600, "loss": 0.8695, "lr": 4.910277324632953e-06, "epoch": 0.1965742251223491, "percentage": 0.98, "elapsed_time": "0:08:43", "remaining_time": "14:38:43", "throughput": 4980.41, "total_tokens": 2606464} +{"current_steps": 1210, "total_steps": 122600, "loss": 1.0388, "lr": 4.930668841761827e-06, "epoch": 0.19738988580750408, "percentage": 0.99, "elapsed_time": "0:08:45", "remaining_time": "14:38:46", "throughput": 4980.42, "total_tokens": 2617568} +{"current_steps": 1215, "total_steps": 122600, "loss": 0.5358, "lr": 4.951060358890701e-06, "epoch": 0.19820554649265906, "percentage": 0.99, "elapsed_time": "0:08:47", "remaining_time": "14:38:56", "throughput": 4980.29, "total_tokens": 2628928} +{"current_steps": 1220, "total_steps": 122600, "loss": 0.4948, "lr": 4.971451876019576e-06, "epoch": 0.19902120717781402, "percentage": 1.0, "elapsed_time": "0:08:50", "remaining_time": "14:39:27", "throughput": 4980.23, "total_tokens": 2641344} +{"current_steps": 1225, "total_steps": 122600, "loss": 0.2013, "lr": 4.9918433931484505e-06, "epoch": 0.199836867862969, "percentage": 1.0, "elapsed_time": "0:08:52", "remaining_time": "14:39:11", "throughput": 4980.44, "total_tokens": 2651584} +{"current_steps": 1230, "total_steps": 122600, "loss": 0.3626, "lr": 5.012234910277324e-06, "epoch": 0.200652528548124, "percentage": 1.0, "elapsed_time": "0:08:54", "remaining_time": "14:39:27", "throughput": 4980.42, "total_tokens": 2663360} +{"current_steps": 1235, "total_steps": 122600, "loss": 0.8468, "lr": 5.032626427406199e-06, "epoch": 0.20146818923327894, "percentage": 1.01, "elapsed_time": "0:08:57", "remaining_time": "14:39:40", "throughput": 4980.87, "total_tokens": 2675168} +{"current_steps": 1240, "total_steps": 122600, "loss": 0.7969, "lr": 5.053017944535074e-06, "epoch": 0.20228384991843393, "percentage": 1.01, "elapsed_time": "0:08:59", "remaining_time": "14:39:38", "throughput": 4980.74, "total_tokens": 2685952} +{"current_steps": 1245, "total_steps": 122600, "loss": 0.7401, "lr": 5.0734094616639475e-06, "epoch": 0.2030995106035889, "percentage": 1.02, "elapsed_time": "0:09:01", "remaining_time": "14:39:11", "throughput": 4980.68, "total_tokens": 2695488} +{"current_steps": 1250, "total_steps": 122600, "loss": 0.5898, "lr": 5.093800978792822e-06, "epoch": 0.2039151712887439, "percentage": 1.02, "elapsed_time": "0:09:03", "remaining_time": "14:39:23", "throughput": 4980.41, "total_tokens": 2706880} +{"current_steps": 1255, "total_steps": 122600, "loss": 1.1997, "lr": 5.114192495921697e-06, "epoch": 0.20473083197389885, "percentage": 1.02, "elapsed_time": "0:09:05", "remaining_time": "14:39:08", "throughput": 4980.62, "total_tokens": 2717184} +{"current_steps": 1260, "total_steps": 122600, "loss": 0.7323, "lr": 5.134584013050571e-06, "epoch": 0.20554649265905384, "percentage": 1.03, "elapsed_time": "0:09:07", "remaining_time": "14:39:28", "throughput": 4980.71, "total_tokens": 2729184} +{"current_steps": 1265, "total_steps": 122600, "loss": 0.306, "lr": 5.154975530179445e-06, "epoch": 0.20636215334420882, "percentage": 1.03, "elapsed_time": "0:09:10", "remaining_time": "14:39:40", "throughput": 4980.73, "total_tokens": 2740768} +{"current_steps": 1270, "total_steps": 122600, "loss": 0.6571, "lr": 5.17536704730832e-06, "epoch": 0.20717781402936378, "percentage": 1.04, "elapsed_time": "0:09:12", "remaining_time": "14:39:28", "throughput": 4981.16, "total_tokens": 2751328} +{"current_steps": 1275, "total_steps": 122600, "loss": 0.5627, "lr": 5.195758564437194e-06, "epoch": 0.20799347471451876, "percentage": 1.04, "elapsed_time": "0:09:14", "remaining_time": "14:39:28", "throughput": 4981.5, "total_tokens": 2762464} +{"current_steps": 1280, "total_steps": 122600, "loss": 0.3288, "lr": 5.2161500815660685e-06, "epoch": 0.20880913539967375, "percentage": 1.04, "elapsed_time": "0:09:16", "remaining_time": "14:39:36", "throughput": 4981.54, "total_tokens": 2773824} +{"current_steps": 1285, "total_steps": 122600, "loss": 1.2493, "lr": 5.236541598694943e-06, "epoch": 0.2096247960848287, "percentage": 1.05, "elapsed_time": "0:09:18", "remaining_time": "14:39:26", "throughput": 4982.0, "total_tokens": 2784544} +{"current_steps": 1290, "total_steps": 122600, "loss": 0.2077, "lr": 5.256933115823817e-06, "epoch": 0.21044045676998369, "percentage": 1.05, "elapsed_time": "0:09:21", "remaining_time": "14:39:38", "throughput": 4981.84, "total_tokens": 2796032} +{"current_steps": 1295, "total_steps": 122600, "loss": 0.5234, "lr": 5.277324632952692e-06, "epoch": 0.21125611745513867, "percentage": 1.06, "elapsed_time": "0:09:23", "remaining_time": "14:39:58", "throughput": 4981.94, "total_tokens": 2808096} +{"current_steps": 1300, "total_steps": 122600, "loss": 0.4042, "lr": 5.297716150081566e-06, "epoch": 0.21207177814029363, "percentage": 1.06, "elapsed_time": "0:09:25", "remaining_time": "14:39:40", "throughput": 4981.97, "total_tokens": 2818080} +{"current_steps": 1305, "total_steps": 122600, "loss": 0.9615, "lr": 5.318107667210441e-06, "epoch": 0.2128874388254486, "percentage": 1.06, "elapsed_time": "0:09:27", "remaining_time": "14:39:46", "throughput": 4981.76, "total_tokens": 2829248} +{"current_steps": 1310, "total_steps": 122600, "loss": 0.512, "lr": 5.338499184339315e-06, "epoch": 0.2137030995106036, "percentage": 1.07, "elapsed_time": "0:09:30", "remaining_time": "14:39:46", "throughput": 4981.85, "total_tokens": 2840288} +{"current_steps": 1315, "total_steps": 122600, "loss": 0.8243, "lr": 5.3588907014681895e-06, "epoch": 0.21451876019575855, "percentage": 1.07, "elapsed_time": "0:09:31", "remaining_time": "14:39:15", "throughput": 4981.67, "total_tokens": 2849440} +{"current_steps": 1320, "total_steps": 122600, "loss": 0.4741, "lr": 5.379282218597064e-06, "epoch": 0.21533442088091354, "percentage": 1.08, "elapsed_time": "0:09:34", "remaining_time": "14:39:26", "throughput": 4981.78, "total_tokens": 2861056} +{"current_steps": 1325, "total_steps": 122600, "loss": 0.5862, "lr": 5.399673735725938e-06, "epoch": 0.21615008156606852, "percentage": 1.08, "elapsed_time": "0:09:36", "remaining_time": "14:39:40", "throughput": 4981.9, "total_tokens": 2872832} +{"current_steps": 1330, "total_steps": 122600, "loss": 1.1106, "lr": 5.420065252854813e-06, "epoch": 0.2169657422512235, "percentage": 1.08, "elapsed_time": "0:09:38", "remaining_time": "14:39:47", "throughput": 4981.49, "total_tokens": 2883968} +{"current_steps": 1335, "total_steps": 122600, "loss": 0.45, "lr": 5.440456769983687e-06, "epoch": 0.21778140293637846, "percentage": 1.09, "elapsed_time": "0:09:41", "remaining_time": "14:39:46", "throughput": 4981.56, "total_tokens": 2894880} +{"current_steps": 1340, "total_steps": 122600, "loss": 0.7361, "lr": 5.460848287112561e-06, "epoch": 0.21859706362153344, "percentage": 1.09, "elapsed_time": "0:09:43", "remaining_time": "14:39:36", "throughput": 4981.37, "total_tokens": 2905216} +{"current_steps": 1345, "total_steps": 122600, "loss": 0.1759, "lr": 5.481239804241436e-06, "epoch": 0.21941272430668843, "percentage": 1.1, "elapsed_time": "0:09:45", "remaining_time": "14:39:50", "throughput": 4981.77, "total_tokens": 2917152} +{"current_steps": 1350, "total_steps": 122600, "loss": 0.696, "lr": 5.5016313213703105e-06, "epoch": 0.22022838499184338, "percentage": 1.1, "elapsed_time": "0:09:47", "remaining_time": "14:39:57", "throughput": 4981.68, "total_tokens": 2928448} +{"current_steps": 1355, "total_steps": 122600, "loss": 0.6746, "lr": 5.522022838499184e-06, "epoch": 0.22104404567699837, "percentage": 1.11, "elapsed_time": "0:09:49", "remaining_time": "14:39:37", "throughput": 4981.69, "total_tokens": 2938336} +{"current_steps": 1360, "total_steps": 122600, "loss": 0.1963, "lr": 5.542414355628059e-06, "epoch": 0.22185970636215335, "percentage": 1.11, "elapsed_time": "0:09:52", "remaining_time": "14:40:01", "throughput": 4981.49, "total_tokens": 2950496} +{"current_steps": 1365, "total_steps": 122600, "loss": 1.1886, "lr": 5.562805872756934e-06, "epoch": 0.2226753670473083, "percentage": 1.11, "elapsed_time": "0:09:54", "remaining_time": "14:39:53", "throughput": 4981.49, "total_tokens": 2961024} +{"current_steps": 1370, "total_steps": 122600, "loss": 0.2333, "lr": 5.583197389885808e-06, "epoch": 0.2234910277324633, "percentage": 1.12, "elapsed_time": "0:09:56", "remaining_time": "14:39:47", "throughput": 4981.58, "total_tokens": 2971744} +{"current_steps": 1375, "total_steps": 122600, "loss": 0.4717, "lr": 5.603588907014682e-06, "epoch": 0.22430668841761828, "percentage": 1.12, "elapsed_time": "0:09:59", "remaining_time": "14:40:13", "throughput": 4981.59, "total_tokens": 2984192} +{"current_steps": 1380, "total_steps": 122600, "loss": 0.4531, "lr": 5.623980424143557e-06, "epoch": 0.22512234910277323, "percentage": 1.13, "elapsed_time": "0:10:01", "remaining_time": "14:40:05", "throughput": 4981.82, "total_tokens": 2994816} +{"current_steps": 1385, "total_steps": 122600, "loss": 0.3208, "lr": 5.6443719412724315e-06, "epoch": 0.22593800978792822, "percentage": 1.13, "elapsed_time": "0:10:03", "remaining_time": "14:40:02", "throughput": 4981.73, "total_tokens": 3005568} +{"current_steps": 1390, "total_steps": 122600, "loss": 0.8437, "lr": 5.664763458401305e-06, "epoch": 0.2267536704730832, "percentage": 1.13, "elapsed_time": "0:10:05", "remaining_time": "14:39:47", "throughput": 4981.7, "total_tokens": 3015680} +{"current_steps": 1395, "total_steps": 122600, "loss": 0.363, "lr": 5.68515497553018e-06, "epoch": 0.2275693311582382, "percentage": 1.14, "elapsed_time": "0:10:07", "remaining_time": "14:39:50", "throughput": 4981.62, "total_tokens": 3026752} +{"current_steps": 1400, "total_steps": 122600, "loss": 0.4606, "lr": 5.705546492659055e-06, "epoch": 0.22838499184339314, "percentage": 1.14, "elapsed_time": "0:10:09", "remaining_time": "14:39:31", "throughput": 4981.66, "total_tokens": 3036704} +{"current_steps": 1405, "total_steps": 122600, "loss": 0.6625, "lr": 5.7259380097879285e-06, "epoch": 0.22920065252854813, "percentage": 1.15, "elapsed_time": "0:10:12", "remaining_time": "14:39:53", "throughput": 4981.7, "total_tokens": 3048960} +{"current_steps": 1410, "total_steps": 122600, "loss": 0.8532, "lr": 5.746329526916803e-06, "epoch": 0.2300163132137031, "percentage": 1.15, "elapsed_time": "0:10:14", "remaining_time": "14:39:43", "throughput": 4981.9, "total_tokens": 3059456} +{"current_steps": 1415, "total_steps": 122600, "loss": 0.5241, "lr": 5.766721044045678e-06, "epoch": 0.23083197389885807, "percentage": 1.15, "elapsed_time": "0:10:16", "remaining_time": "14:39:37", "throughput": 4981.95, "total_tokens": 3070112} +{"current_steps": 1420, "total_steps": 122600, "loss": 0.3032, "lr": 5.787112561174552e-06, "epoch": 0.23164763458401305, "percentage": 1.16, "elapsed_time": "0:10:18", "remaining_time": "14:39:21", "throughput": 4982.06, "total_tokens": 3080224} +{"current_steps": 1425, "total_steps": 122600, "loss": 0.7254, "lr": 5.807504078303426e-06, "epoch": 0.23246329526916804, "percentage": 1.16, "elapsed_time": "0:10:20", "remaining_time": "14:39:04", "throughput": 4982.18, "total_tokens": 3090304} +{"current_steps": 1430, "total_steps": 122600, "loss": 0.319, "lr": 5.827895595432301e-06, "epoch": 0.233278955954323, "percentage": 1.17, "elapsed_time": "0:10:22", "remaining_time": "14:38:28", "throughput": 4982.29, "total_tokens": 3099232} +{"current_steps": 1435, "total_steps": 122600, "loss": 0.8097, "lr": 5.848287112561175e-06, "epoch": 0.23409461663947798, "percentage": 1.17, "elapsed_time": "0:10:24", "remaining_time": "14:38:20", "throughput": 4982.31, "total_tokens": 3109696} +{"current_steps": 1440, "total_steps": 122600, "loss": 0.4577, "lr": 5.8686786296900495e-06, "epoch": 0.23491027732463296, "percentage": 1.17, "elapsed_time": "0:10:26", "remaining_time": "14:38:12", "throughput": 4982.25, "total_tokens": 3120160} +{"current_steps": 1445, "total_steps": 122600, "loss": 0.3082, "lr": 5.889070146818923e-06, "epoch": 0.23572593800978792, "percentage": 1.18, "elapsed_time": "0:10:28", "remaining_time": "14:38:07", "throughput": 4982.22, "total_tokens": 3130784} +{"current_steps": 1450, "total_steps": 122600, "loss": 0.8093, "lr": 5.909461663947798e-06, "epoch": 0.2365415986949429, "percentage": 1.18, "elapsed_time": "0:10:30", "remaining_time": "14:38:01", "throughput": 4982.45, "total_tokens": 3141536} +{"current_steps": 1455, "total_steps": 122600, "loss": 0.561, "lr": 5.929853181076672e-06, "epoch": 0.23735725938009788, "percentage": 1.19, "elapsed_time": "0:10:32", "remaining_time": "14:37:52", "throughput": 4982.68, "total_tokens": 3152160} +{"current_steps": 1460, "total_steps": 122600, "loss": 0.21, "lr": 5.9502446982055465e-06, "epoch": 0.23817292006525284, "percentage": 1.19, "elapsed_time": "0:10:34", "remaining_time": "14:37:42", "throughput": 4982.74, "total_tokens": 3162560} +{"current_steps": 1465, "total_steps": 122600, "loss": 0.3041, "lr": 5.970636215334421e-06, "epoch": 0.23898858075040783, "percentage": 1.19, "elapsed_time": "0:10:37", "remaining_time": "14:38:13", "throughput": 4982.75, "total_tokens": 3175360} +{"current_steps": 1470, "total_steps": 122600, "loss": 0.3133, "lr": 5.991027732463295e-06, "epoch": 0.2398042414355628, "percentage": 1.2, "elapsed_time": "0:10:39", "remaining_time": "14:38:41", "throughput": 4982.6, "total_tokens": 3187936} +{"current_steps": 1475, "total_steps": 122600, "loss": 0.8116, "lr": 6.01141924959217e-06, "epoch": 0.2406199021207178, "percentage": 1.2, "elapsed_time": "0:10:42", "remaining_time": "14:38:49", "throughput": 4982.63, "total_tokens": 3199424} +{"current_steps": 1480, "total_steps": 122600, "loss": 0.7472, "lr": 6.031810766721044e-06, "epoch": 0.24143556280587275, "percentage": 1.21, "elapsed_time": "0:10:44", "remaining_time": "14:38:46", "throughput": 4982.71, "total_tokens": 3210272} +{"current_steps": 1485, "total_steps": 122600, "loss": 0.4052, "lr": 6.052202283849918e-06, "epoch": 0.24225122349102773, "percentage": 1.21, "elapsed_time": "0:10:46", "remaining_time": "14:38:20", "throughput": 4982.72, "total_tokens": 3219680} +{"current_steps": 1490, "total_steps": 122600, "loss": 0.3686, "lr": 6.072593800978793e-06, "epoch": 0.24306688417618272, "percentage": 1.22, "elapsed_time": "0:10:48", "remaining_time": "14:37:58", "throughput": 4982.82, "total_tokens": 3229376} +{"current_steps": 1495, "total_steps": 122600, "loss": 0.6032, "lr": 6.0929853181076675e-06, "epoch": 0.24388254486133767, "percentage": 1.22, "elapsed_time": "0:10:50", "remaining_time": "14:38:07", "throughput": 4982.86, "total_tokens": 3240896} +{"current_steps": 1500, "total_steps": 122600, "loss": 1.1279, "lr": 6.113376835236541e-06, "epoch": 0.24469820554649266, "percentage": 1.22, "elapsed_time": "0:10:52", "remaining_time": "14:38:05", "throughput": 4982.95, "total_tokens": 3251808} +{"current_steps": 1505, "total_steps": 122600, "loss": 0.2304, "lr": 6.133768352365416e-06, "epoch": 0.24551386623164764, "percentage": 1.23, "elapsed_time": "0:10:54", "remaining_time": "14:38:04", "throughput": 4982.88, "total_tokens": 3262688} +{"current_steps": 1510, "total_steps": 122600, "loss": 0.219, "lr": 6.154159869494291e-06, "epoch": 0.2463295269168026, "percentage": 1.23, "elapsed_time": "0:10:56", "remaining_time": "14:38:00", "throughput": 4982.75, "total_tokens": 3273344} +{"current_steps": 1515, "total_steps": 122600, "loss": 0.5326, "lr": 6.174551386623165e-06, "epoch": 0.24714518760195758, "percentage": 1.24, "elapsed_time": "0:10:58", "remaining_time": "14:37:44", "throughput": 4983.1, "total_tokens": 3283520} +{"current_steps": 1520, "total_steps": 122600, "loss": 0.5517, "lr": 6.194942903752039e-06, "epoch": 0.24796084828711257, "percentage": 1.24, "elapsed_time": "0:11:01", "remaining_time": "14:37:48", "throughput": 4983.21, "total_tokens": 3294816} +{"current_steps": 1525, "total_steps": 122600, "loss": 0.4364, "lr": 6.215334420880914e-06, "epoch": 0.24877650897226752, "percentage": 1.24, "elapsed_time": "0:11:03", "remaining_time": "14:37:37", "throughput": 4983.3, "total_tokens": 3305152} +{"current_steps": 1530, "total_steps": 122600, "loss": 0.3617, "lr": 6.2357259380097885e-06, "epoch": 0.2495921696574225, "percentage": 1.25, "elapsed_time": "0:11:05", "remaining_time": "14:37:24", "throughput": 4983.21, "total_tokens": 3315264} +{"current_steps": 1535, "total_steps": 122600, "loss": 0.641, "lr": 6.256117455138663e-06, "epoch": 0.25040783034257746, "percentage": 1.25, "elapsed_time": "0:11:07", "remaining_time": "14:37:21", "throughput": 4983.45, "total_tokens": 3326208} +{"current_steps": 1540, "total_steps": 122600, "loss": 0.5309, "lr": 6.276508972267536e-06, "epoch": 0.25122349102773245, "percentage": 1.26, "elapsed_time": "0:11:09", "remaining_time": "14:37:24", "throughput": 4983.59, "total_tokens": 3337472} +{"current_steps": 1545, "total_steps": 122600, "loss": 0.2363, "lr": 6.296900489396411e-06, "epoch": 0.25203915171288743, "percentage": 1.26, "elapsed_time": "0:11:11", "remaining_time": "14:37:26", "throughput": 4983.66, "total_tokens": 3348576} +{"current_steps": 1550, "total_steps": 122600, "loss": 0.571, "lr": 6.3172920065252854e-06, "epoch": 0.2528548123980424, "percentage": 1.26, "elapsed_time": "0:11:14", "remaining_time": "14:37:21", "throughput": 4983.58, "total_tokens": 3359200} +{"current_steps": 1555, "total_steps": 122600, "loss": 0.1781, "lr": 6.33768352365416e-06, "epoch": 0.2536704730831974, "percentage": 1.27, "elapsed_time": "0:11:16", "remaining_time": "14:37:14", "throughput": 4983.56, "total_tokens": 3369696} +{"current_steps": 1560, "total_steps": 122600, "loss": 0.4625, "lr": 6.358075040783035e-06, "epoch": 0.2544861337683524, "percentage": 1.27, "elapsed_time": "0:11:18", "remaining_time": "14:37:17", "throughput": 4983.89, "total_tokens": 3381088} +{"current_steps": 1565, "total_steps": 122600, "loss": 0.349, "lr": 6.3784665579119094e-06, "epoch": 0.2553017944535073, "percentage": 1.28, "elapsed_time": "0:11:20", "remaining_time": "14:37:26", "throughput": 4983.98, "total_tokens": 3392704} +{"current_steps": 1570, "total_steps": 122600, "loss": 0.7477, "lr": 6.398858075040784e-06, "epoch": 0.2561174551386623, "percentage": 1.28, "elapsed_time": "0:11:22", "remaining_time": "14:37:16", "throughput": 4984.07, "total_tokens": 3403136} +{"current_steps": 1575, "total_steps": 122600, "loss": 0.3018, "lr": 6.419249592169657e-06, "epoch": 0.2569331158238173, "percentage": 1.28, "elapsed_time": "0:11:24", "remaining_time": "14:36:44", "throughput": 4984.0, "total_tokens": 3411968} +{"current_steps": 1580, "total_steps": 122600, "loss": 0.2863, "lr": 6.439641109298532e-06, "epoch": 0.25774877650897227, "percentage": 1.29, "elapsed_time": "0:11:26", "remaining_time": "14:36:17", "throughput": 4984.03, "total_tokens": 3421216} +{"current_steps": 1585, "total_steps": 122600, "loss": 0.6718, "lr": 6.4600326264274064e-06, "epoch": 0.25856443719412725, "percentage": 1.29, "elapsed_time": "0:11:28", "remaining_time": "14:36:33", "throughput": 4983.91, "total_tokens": 3433120} +{"current_steps": 1590, "total_steps": 122600, "loss": 0.3018, "lr": 6.480424143556281e-06, "epoch": 0.25938009787928223, "percentage": 1.3, "elapsed_time": "0:11:31", "remaining_time": "14:36:47", "throughput": 4983.83, "total_tokens": 3444960} +{"current_steps": 1595, "total_steps": 122600, "loss": 0.2191, "lr": 6.500815660685156e-06, "epoch": 0.2601957585644372, "percentage": 1.3, "elapsed_time": "0:11:33", "remaining_time": "14:36:54", "throughput": 4983.99, "total_tokens": 3456512} +{"current_steps": 1600, "total_steps": 122600, "loss": 0.1749, "lr": 6.5212071778140304e-06, "epoch": 0.26101141924959215, "percentage": 1.31, "elapsed_time": "0:11:35", "remaining_time": "14:36:46", "throughput": 4983.88, "total_tokens": 3466880} +{"current_steps": 1605, "total_steps": 122600, "loss": 0.2532, "lr": 6.541598694942903e-06, "epoch": 0.26182707993474713, "percentage": 1.31, "elapsed_time": "0:11:37", "remaining_time": "14:36:57", "throughput": 4983.81, "total_tokens": 3478528} +{"current_steps": 1610, "total_steps": 122600, "loss": 0.5224, "lr": 6.561990212071778e-06, "epoch": 0.2626427406199021, "percentage": 1.31, "elapsed_time": "0:11:40", "remaining_time": "14:37:09", "throughput": 4983.69, "total_tokens": 3490240} +{"current_steps": 1615, "total_steps": 122600, "loss": 0.5808, "lr": 6.582381729200653e-06, "epoch": 0.2634584013050571, "percentage": 1.32, "elapsed_time": "0:11:42", "remaining_time": "14:37:09", "throughput": 4983.59, "total_tokens": 3501152} +{"current_steps": 1620, "total_steps": 122600, "loss": 0.4902, "lr": 6.6027732463295274e-06, "epoch": 0.2642740619902121, "percentage": 1.32, "elapsed_time": "0:11:44", "remaining_time": "14:36:55", "throughput": 4983.76, "total_tokens": 3511360} +{"current_steps": 1625, "total_steps": 122600, "loss": 0.1692, "lr": 6.623164763458402e-06, "epoch": 0.26508972267536707, "percentage": 1.33, "elapsed_time": "0:11:46", "remaining_time": "14:37:04", "throughput": 4983.67, "total_tokens": 3522880} +{"current_steps": 1630, "total_steps": 122600, "loss": 0.3091, "lr": 6.643556280587277e-06, "epoch": 0.265905383360522, "percentage": 1.33, "elapsed_time": "0:11:49", "remaining_time": "14:37:18", "throughput": 4983.56, "total_tokens": 3534720} +{"current_steps": 1635, "total_steps": 122600, "loss": 0.1405, "lr": 6.6639477977161514e-06, "epoch": 0.266721044045677, "percentage": 1.33, "elapsed_time": "0:11:51", "remaining_time": "14:36:55", "throughput": 4983.56, "total_tokens": 3544128} +{"current_steps": 1640, "total_steps": 122600, "loss": 0.2464, "lr": 6.684339314845024e-06, "epoch": 0.26753670473083196, "percentage": 1.34, "elapsed_time": "0:11:53", "remaining_time": "14:37:01", "throughput": 4983.6, "total_tokens": 3555552} +{"current_steps": 1645, "total_steps": 122600, "loss": 0.1965, "lr": 6.704730831973899e-06, "epoch": 0.26835236541598695, "percentage": 1.34, "elapsed_time": "0:11:55", "remaining_time": "14:36:50", "throughput": 4983.58, "total_tokens": 3565824} +{"current_steps": 1650, "total_steps": 122600, "loss": 0.1876, "lr": 6.725122349102774e-06, "epoch": 0.26916802610114193, "percentage": 1.35, "elapsed_time": "0:11:57", "remaining_time": "14:36:50", "throughput": 4983.66, "total_tokens": 3576864} +{"current_steps": 1655, "total_steps": 122600, "loss": 0.245, "lr": 6.745513866231648e-06, "epoch": 0.2699836867862969, "percentage": 1.35, "elapsed_time": "0:11:59", "remaining_time": "14:36:51", "throughput": 4983.84, "total_tokens": 3588032} +{"current_steps": 1660, "total_steps": 122600, "loss": 0.2744, "lr": 6.765905383360522e-06, "epoch": 0.2707993474714519, "percentage": 1.35, "elapsed_time": "0:12:02", "remaining_time": "14:36:56", "throughput": 4984.06, "total_tokens": 3599488} +{"current_steps": 1665, "total_steps": 122600, "loss": 0.0231, "lr": 6.786296900489397e-06, "epoch": 0.27161500815660683, "percentage": 1.36, "elapsed_time": "0:12:04", "remaining_time": "14:36:55", "throughput": 4984.02, "total_tokens": 3610368} +{"current_steps": 1670, "total_steps": 122600, "loss": 0.4946, "lr": 6.806688417618271e-06, "epoch": 0.2724306688417618, "percentage": 1.36, "elapsed_time": "0:12:06", "remaining_time": "14:36:38", "throughput": 4983.93, "total_tokens": 3620128} +{"current_steps": 1675, "total_steps": 122600, "loss": 0.2589, "lr": 6.827079934747145e-06, "epoch": 0.2732463295269168, "percentage": 1.37, "elapsed_time": "0:12:08", "remaining_time": "14:36:49", "throughput": 4983.86, "total_tokens": 3631872} +{"current_steps": 1680, "total_steps": 122600, "loss": 0.7041, "lr": 6.84747145187602e-06, "epoch": 0.2740619902120718, "percentage": 1.37, "elapsed_time": "0:12:11", "remaining_time": "14:36:55", "throughput": 4983.88, "total_tokens": 3643296} +{"current_steps": 1685, "total_steps": 122600, "loss": 0.4755, "lr": 6.867862969004894e-06, "epoch": 0.27487765089722677, "percentage": 1.37, "elapsed_time": "0:12:13", "remaining_time": "14:36:59", "throughput": 4983.96, "total_tokens": 3654592} +{"current_steps": 1690, "total_steps": 122600, "loss": 0.9392, "lr": 6.8882544861337686e-06, "epoch": 0.27569331158238175, "percentage": 1.38, "elapsed_time": "0:12:15", "remaining_time": "14:36:54", "throughput": 4984.03, "total_tokens": 3665312} +{"current_steps": 1695, "total_steps": 122600, "loss": 0.2736, "lr": 6.908646003262643e-06, "epoch": 0.2765089722675367, "percentage": 1.38, "elapsed_time": "0:12:17", "remaining_time": "14:37:07", "throughput": 4983.81, "total_tokens": 3677024} +{"current_steps": 1700, "total_steps": 122600, "loss": 0.5365, "lr": 6.929037520391518e-06, "epoch": 0.27732463295269166, "percentage": 1.39, "elapsed_time": "0:12:19", "remaining_time": "14:37:03", "throughput": 4984.0, "total_tokens": 3687904} +{"current_steps": 1705, "total_steps": 122600, "loss": 0.5298, "lr": 6.949429037520392e-06, "epoch": 0.27814029363784665, "percentage": 1.39, "elapsed_time": "0:12:22", "remaining_time": "14:37:01", "throughput": 4984.08, "total_tokens": 3698848} +{"current_steps": 1710, "total_steps": 122600, "loss": 0.4405, "lr": 6.9698205546492656e-06, "epoch": 0.27895595432300163, "percentage": 1.39, "elapsed_time": "0:12:24", "remaining_time": "14:37:02", "throughput": 4984.03, "total_tokens": 3709856} +{"current_steps": 1715, "total_steps": 122600, "loss": 0.3741, "lr": 6.99021207177814e-06, "epoch": 0.2797716150081566, "percentage": 1.4, "elapsed_time": "0:12:26", "remaining_time": "14:37:02", "throughput": 4983.85, "total_tokens": 3720736} +{"current_steps": 1720, "total_steps": 122600, "loss": 0.5432, "lr": 7.010603588907015e-06, "epoch": 0.2805872756933116, "percentage": 1.4, "elapsed_time": "0:12:28", "remaining_time": "14:36:54", "throughput": 4984.0, "total_tokens": 3731264} +{"current_steps": 1725, "total_steps": 122600, "loss": 0.5617, "lr": 7.0309951060358896e-06, "epoch": 0.2814029363784666, "percentage": 1.41, "elapsed_time": "0:12:31", "remaining_time": "14:37:05", "throughput": 4984.03, "total_tokens": 3743072} +{"current_steps": 1730, "total_steps": 122600, "loss": 0.5109, "lr": 7.051386623164764e-06, "epoch": 0.2822185970636215, "percentage": 1.41, "elapsed_time": "0:12:33", "remaining_time": "14:37:11", "throughput": 4984.22, "total_tokens": 3754656} +{"current_steps": 1735, "total_steps": 122600, "loss": 0.2639, "lr": 7.071778140293637e-06, "epoch": 0.2830342577487765, "percentage": 1.42, "elapsed_time": "0:12:35", "remaining_time": "14:37:02", "throughput": 4984.5, "total_tokens": 3765248} +{"current_steps": 1740, "total_steps": 122600, "loss": 0.6553, "lr": 7.092169657422512e-06, "epoch": 0.2838499184339315, "percentage": 1.42, "elapsed_time": "0:12:37", "remaining_time": "14:36:39", "throughput": 4984.29, "total_tokens": 3774464} +{"current_steps": 1745, "total_steps": 122600, "loss": 0.4469, "lr": 7.1125611745513865e-06, "epoch": 0.28466557911908646, "percentage": 1.42, "elapsed_time": "0:12:39", "remaining_time": "14:36:22", "throughput": 4984.82, "total_tokens": 3784608} +{"current_steps": 1750, "total_steps": 122600, "loss": 0.3063, "lr": 7.132952691680261e-06, "epoch": 0.28548123980424145, "percentage": 1.43, "elapsed_time": "0:12:41", "remaining_time": "14:36:35", "throughput": 4984.99, "total_tokens": 3796672} +{"current_steps": 1755, "total_steps": 122600, "loss": 0.2076, "lr": 7.153344208809136e-06, "epoch": 0.28629690048939643, "percentage": 1.43, "elapsed_time": "0:12:43", "remaining_time": "14:36:37", "throughput": 4984.84, "total_tokens": 3807712} +{"current_steps": 1760, "total_steps": 122600, "loss": 0.26, "lr": 7.1737357259380106e-06, "epoch": 0.28711256117455136, "percentage": 1.44, "elapsed_time": "0:12:45", "remaining_time": "14:36:24", "throughput": 4985.06, "total_tokens": 3817984} +{"current_steps": 1765, "total_steps": 122600, "loss": 0.0456, "lr": 7.194127243066885e-06, "epoch": 0.28792822185970635, "percentage": 1.44, "elapsed_time": "0:12:48", "remaining_time": "14:36:26", "throughput": 4985.11, "total_tokens": 3829152} +{"current_steps": 1770, "total_steps": 122600, "loss": 0.6324, "lr": 7.214518760195758e-06, "epoch": 0.28874388254486133, "percentage": 1.44, "elapsed_time": "0:12:50", "remaining_time": "14:36:27", "throughput": 4985.29, "total_tokens": 3840352} +{"current_steps": 1775, "total_steps": 122600, "loss": 0.4965, "lr": 7.234910277324633e-06, "epoch": 0.2895595432300163, "percentage": 1.45, "elapsed_time": "0:12:52", "remaining_time": "14:36:30", "throughput": 4985.12, "total_tokens": 3851456} +{"current_steps": 1780, "total_steps": 122600, "loss": 0.0458, "lr": 7.2553017944535075e-06, "epoch": 0.2903752039151713, "percentage": 1.45, "elapsed_time": "0:12:54", "remaining_time": "14:36:37", "throughput": 4985.23, "total_tokens": 3863040} +{"current_steps": 1785, "total_steps": 122600, "loss": 0.1017, "lr": 7.275693311582382e-06, "epoch": 0.2911908646003263, "percentage": 1.46, "elapsed_time": "0:12:57", "remaining_time": "14:36:37", "throughput": 4985.38, "total_tokens": 3874176} +{"current_steps": 1790, "total_steps": 122600, "loss": 0.4597, "lr": 7.296084828711257e-06, "epoch": 0.29200652528548127, "percentage": 1.46, "elapsed_time": "0:12:59", "remaining_time": "14:36:30", "throughput": 4985.43, "total_tokens": 3884736} +{"current_steps": 1795, "total_steps": 122600, "loss": 0.2325, "lr": 7.3164763458401316e-06, "epoch": 0.2928221859706362, "percentage": 1.46, "elapsed_time": "0:13:01", "remaining_time": "14:36:27", "throughput": 4985.55, "total_tokens": 3895584} +{"current_steps": 1800, "total_steps": 122600, "loss": 0.367, "lr": 7.3368678629690045e-06, "epoch": 0.2936378466557912, "percentage": 1.47, "elapsed_time": "0:13:03", "remaining_time": "14:36:40", "throughput": 4985.53, "total_tokens": 3907584} +{"current_steps": 1805, "total_steps": 122600, "loss": 0.2881, "lr": 7.357259380097879e-06, "epoch": 0.29445350734094616, "percentage": 1.47, "elapsed_time": "0:13:06", "remaining_time": "14:36:51", "throughput": 4985.54, "total_tokens": 3919424} +{"current_steps": 1810, "total_steps": 122600, "loss": 0.2354, "lr": 7.377650897226754e-06, "epoch": 0.29526916802610115, "percentage": 1.48, "elapsed_time": "0:13:08", "remaining_time": "14:36:33", "throughput": 4985.64, "total_tokens": 3929152} +{"current_steps": 1815, "total_steps": 122600, "loss": 0.3228, "lr": 7.3980424143556285e-06, "epoch": 0.29608482871125613, "percentage": 1.48, "elapsed_time": "0:13:10", "remaining_time": "14:36:41", "throughput": 4985.81, "total_tokens": 3940928} +{"current_steps": 1820, "total_steps": 122600, "loss": 0.1687, "lr": 7.418433931484503e-06, "epoch": 0.2969004893964111, "percentage": 1.48, "elapsed_time": "0:13:12", "remaining_time": "14:36:06", "throughput": 4986.11, "total_tokens": 3949568} +{"current_steps": 1825, "total_steps": 122600, "loss": 0.2202, "lr": 7.438825448613378e-06, "epoch": 0.29771615008156604, "percentage": 1.49, "elapsed_time": "0:13:14", "remaining_time": "14:36:11", "throughput": 4986.27, "total_tokens": 3961088} +{"current_steps": 1830, "total_steps": 122600, "loss": 0.4944, "lr": 7.4592169657422525e-06, "epoch": 0.29853181076672103, "percentage": 1.49, "elapsed_time": "0:13:16", "remaining_time": "14:36:24", "throughput": 4986.32, "total_tokens": 3973088} +{"current_steps": 1835, "total_steps": 122600, "loss": 0.2503, "lr": 7.4796084828711255e-06, "epoch": 0.299347471451876, "percentage": 1.5, "elapsed_time": "0:13:18", "remaining_time": "14:36:07", "throughput": 4986.46, "total_tokens": 3982976} +{"current_steps": 1840, "total_steps": 122600, "loss": 0.4938, "lr": 7.5e-06, "epoch": 0.300163132137031, "percentage": 1.5, "elapsed_time": "0:13:20", "remaining_time": "14:35:58", "throughput": 4986.64, "total_tokens": 3993440} +{"current_steps": 1845, "total_steps": 122600, "loss": 0.0841, "lr": 7.520391517128875e-06, "epoch": 0.300978792822186, "percentage": 1.5, "elapsed_time": "0:13:22", "remaining_time": "14:35:35", "throughput": 4986.63, "total_tokens": 4002720} +{"current_steps": 1850, "total_steps": 122600, "loss": 0.7429, "lr": 7.5407830342577495e-06, "epoch": 0.30179445350734097, "percentage": 1.51, "elapsed_time": "0:13:24", "remaining_time": "14:35:25", "throughput": 4986.6, "total_tokens": 4012896} +{"current_steps": 1855, "total_steps": 122600, "loss": 0.1405, "lr": 7.561174551386624e-06, "epoch": 0.30261011419249595, "percentage": 1.51, "elapsed_time": "0:13:26", "remaining_time": "14:35:21", "throughput": 4986.72, "total_tokens": 4023680} +{"current_steps": 1860, "total_steps": 122600, "loss": 0.0978, "lr": 7.581566068515499e-06, "epoch": 0.3034257748776509, "percentage": 1.52, "elapsed_time": "0:13:28", "remaining_time": "14:35:08", "throughput": 4986.78, "total_tokens": 4033760} +{"current_steps": 1865, "total_steps": 122600, "loss": 0.3304, "lr": 7.601957585644372e-06, "epoch": 0.30424143556280586, "percentage": 1.52, "elapsed_time": "0:13:30", "remaining_time": "14:35:00", "throughput": 4986.84, "total_tokens": 4044192} +{"current_steps": 1870, "total_steps": 122600, "loss": 0.3055, "lr": 7.6223491027732465e-06, "epoch": 0.30505709624796085, "percentage": 1.53, "elapsed_time": "0:13:33", "remaining_time": "14:35:05", "throughput": 4986.75, "total_tokens": 4055520} +{"current_steps": 1875, "total_steps": 122600, "loss": 0.1572, "lr": 7.642740619902121e-06, "epoch": 0.30587275693311583, "percentage": 1.53, "elapsed_time": "0:13:35", "remaining_time": "14:35:15", "throughput": 4986.63, "total_tokens": 4067264} +{"current_steps": 1880, "total_steps": 122600, "loss": 0.4497, "lr": 7.663132137030995e-06, "epoch": 0.3066884176182708, "percentage": 1.53, "elapsed_time": "0:13:37", "remaining_time": "14:35:13", "throughput": 4986.56, "total_tokens": 4078016} +{"current_steps": 1885, "total_steps": 122600, "loss": 0.2322, "lr": 7.68352365415987e-06, "epoch": 0.3075040783034258, "percentage": 1.54, "elapsed_time": "0:13:39", "remaining_time": "14:35:05", "throughput": 4986.49, "total_tokens": 4088352} +{"current_steps": 1890, "total_steps": 122600, "loss": 0.2785, "lr": 7.703915171288744e-06, "epoch": 0.3083197389885807, "percentage": 1.54, "elapsed_time": "0:13:42", "remaining_time": "14:35:17", "throughput": 4986.63, "total_tokens": 4100416} +{"current_steps": 1895, "total_steps": 122600, "loss": 0.3426, "lr": 7.724306688417618e-06, "epoch": 0.3091353996737357, "percentage": 1.55, "elapsed_time": "0:13:44", "remaining_time": "14:35:00", "throughput": 4986.58, "total_tokens": 4110080} +{"current_steps": 1900, "total_steps": 122600, "loss": 0.7649, "lr": 7.744698205546492e-06, "epoch": 0.3099510603588907, "percentage": 1.55, "elapsed_time": "0:13:46", "remaining_time": "14:34:55", "throughput": 4986.66, "total_tokens": 4120736} +{"current_steps": 1905, "total_steps": 122600, "loss": 0.191, "lr": 7.765089722675368e-06, "epoch": 0.3107667210440457, "percentage": 1.55, "elapsed_time": "0:13:48", "remaining_time": "14:35:06", "throughput": 4986.73, "total_tokens": 4132736} +{"current_steps": 1910, "total_steps": 122600, "loss": 0.4255, "lr": 7.785481239804241e-06, "epoch": 0.31158238172920066, "percentage": 1.56, "elapsed_time": "0:13:50", "remaining_time": "14:35:06", "throughput": 4986.79, "total_tokens": 4143808} +{"current_steps": 1915, "total_steps": 122600, "loss": 0.2782, "lr": 7.805872756933117e-06, "epoch": 0.31239804241435565, "percentage": 1.56, "elapsed_time": "0:13:53", "remaining_time": "14:35:07", "throughput": 4986.93, "total_tokens": 4154976} +{"current_steps": 1920, "total_steps": 122600, "loss": 0.4086, "lr": 7.82626427406199e-06, "epoch": 0.3132137030995106, "percentage": 1.57, "elapsed_time": "0:13:55", "remaining_time": "14:35:00", "throughput": 4987.01, "total_tokens": 4165504} +{"current_steps": 1925, "total_steps": 122600, "loss": 0.361, "lr": 7.846655791190866e-06, "epoch": 0.31402936378466556, "percentage": 1.57, "elapsed_time": "0:13:57", "remaining_time": "14:35:10", "throughput": 4986.82, "total_tokens": 4177184} +{"current_steps": 1930, "total_steps": 122600, "loss": 0.3303, "lr": 7.867047308319738e-06, "epoch": 0.31484502446982054, "percentage": 1.57, "elapsed_time": "0:14:00", "remaining_time": "14:35:24", "throughput": 4986.57, "total_tokens": 4189088} +{"current_steps": 1935, "total_steps": 122600, "loss": 0.075, "lr": 7.887438825448614e-06, "epoch": 0.31566068515497553, "percentage": 1.58, "elapsed_time": "0:14:02", "remaining_time": "14:35:23", "throughput": 4986.59, "total_tokens": 4200064} +{"current_steps": 1940, "total_steps": 122600, "loss": 0.3072, "lr": 7.907830342577488e-06, "epoch": 0.3164763458401305, "percentage": 1.58, "elapsed_time": "0:14:04", "remaining_time": "14:35:33", "throughput": 4986.61, "total_tokens": 4211936} +{"current_steps": 1945, "total_steps": 122600, "loss": 0.2618, "lr": 7.928221859706363e-06, "epoch": 0.3172920065252855, "percentage": 1.59, "elapsed_time": "0:14:06", "remaining_time": "14:35:21", "throughput": 4986.58, "total_tokens": 4221952} +{"current_steps": 1950, "total_steps": 122600, "loss": 0.4715, "lr": 7.948613376835237e-06, "epoch": 0.3181076672104405, "percentage": 1.59, "elapsed_time": "0:14:08", "remaining_time": "14:35:18", "throughput": 4986.89, "total_tokens": 4233024} +{"current_steps": 1955, "total_steps": 122600, "loss": 0.1094, "lr": 7.969004893964113e-06, "epoch": 0.3189233278955954, "percentage": 1.59, "elapsed_time": "0:14:11", "remaining_time": "14:35:22", "throughput": 4987.02, "total_tokens": 4244480} +{"current_steps": 1960, "total_steps": 122600, "loss": 0.3445, "lr": 7.989396411092985e-06, "epoch": 0.3197389885807504, "percentage": 1.6, "elapsed_time": "0:14:13", "remaining_time": "14:35:24", "throughput": 4987.27, "total_tokens": 4255904} +{"current_steps": 1965, "total_steps": 122600, "loss": 0.7167, "lr": 8.00978792822186e-06, "epoch": 0.3205546492659054, "percentage": 1.6, "elapsed_time": "0:14:15", "remaining_time": "14:35:11", "throughput": 4987.17, "total_tokens": 4265792} +{"current_steps": 1970, "total_steps": 122600, "loss": 0.0966, "lr": 8.030179445350734e-06, "epoch": 0.32137030995106036, "percentage": 1.61, "elapsed_time": "0:14:17", "remaining_time": "14:35:03", "throughput": 4987.13, "total_tokens": 4276160} +{"current_steps": 1975, "total_steps": 122600, "loss": 0.4224, "lr": 8.05057096247961e-06, "epoch": 0.32218597063621535, "percentage": 1.61, "elapsed_time": "0:14:19", "remaining_time": "14:34:57", "throughput": 4987.08, "total_tokens": 4286624} +{"current_steps": 1980, "total_steps": 122600, "loss": 0.1887, "lr": 8.070962479608483e-06, "epoch": 0.32300163132137033, "percentage": 1.62, "elapsed_time": "0:14:21", "remaining_time": "14:34:58", "throughput": 4986.9, "total_tokens": 4297600} +{"current_steps": 1985, "total_steps": 122600, "loss": 0.3318, "lr": 8.091353996737359e-06, "epoch": 0.32381729200652526, "percentage": 1.62, "elapsed_time": "0:14:23", "remaining_time": "14:34:54", "throughput": 4986.97, "total_tokens": 4308352} +{"current_steps": 1990, "total_steps": 122600, "loss": 0.3892, "lr": 8.111745513866233e-06, "epoch": 0.32463295269168024, "percentage": 1.62, "elapsed_time": "0:14:26", "remaining_time": "14:34:56", "throughput": 4986.78, "total_tokens": 4319360} +{"current_steps": 1995, "total_steps": 122600, "loss": 0.1236, "lr": 8.132137030995106e-06, "epoch": 0.3254486133768352, "percentage": 1.63, "elapsed_time": "0:14:28", "remaining_time": "14:35:09", "throughput": 4986.89, "total_tokens": 4331552} +{"current_steps": 2000, "total_steps": 122600, "loss": 0.5698, "lr": 8.15252854812398e-06, "epoch": 0.3262642740619902, "percentage": 1.63, "elapsed_time": "0:14:31", "remaining_time": "14:35:24", "throughput": 4986.75, "total_tokens": 4343744} +{"current_steps": 2005, "total_steps": 122600, "loss": 0.3382, "lr": 8.172920065252856e-06, "epoch": 0.3270799347471452, "percentage": 1.64, "elapsed_time": "0:14:33", "remaining_time": "14:35:19", "throughput": 4986.74, "total_tokens": 4354304} +{"current_steps": 2010, "total_steps": 122600, "loss": 0.2151, "lr": 8.19331158238173e-06, "epoch": 0.3278955954323002, "percentage": 1.64, "elapsed_time": "0:14:35", "remaining_time": "14:35:21", "throughput": 4986.95, "total_tokens": 4365696} +{"current_steps": 2015, "total_steps": 122600, "loss": 0.5117, "lr": 8.213703099510603e-06, "epoch": 0.32871125611745516, "percentage": 1.64, "elapsed_time": "0:14:37", "remaining_time": "14:35:21", "throughput": 4986.95, "total_tokens": 4376736} +{"current_steps": 2020, "total_steps": 122600, "loss": 0.2806, "lr": 8.234094616639479e-06, "epoch": 0.3295269168026101, "percentage": 1.65, "elapsed_time": "0:14:39", "remaining_time": "14:35:26", "throughput": 4986.79, "total_tokens": 4388064} +{"current_steps": 2025, "total_steps": 122600, "loss": 0.2341, "lr": 8.254486133768353e-06, "epoch": 0.3303425774877651, "percentage": 1.65, "elapsed_time": "0:14:42", "remaining_time": "14:35:23", "throughput": 4986.84, "total_tokens": 4398912} +{"current_steps": 2030, "total_steps": 122600, "loss": 0.3317, "lr": 8.274877650897227e-06, "epoch": 0.33115823817292006, "percentage": 1.66, "elapsed_time": "0:14:44", "remaining_time": "14:35:19", "throughput": 4987.12, "total_tokens": 4409856} +{"current_steps": 2035, "total_steps": 122600, "loss": 0.2103, "lr": 8.295269168026102e-06, "epoch": 0.33197389885807504, "percentage": 1.66, "elapsed_time": "0:14:46", "remaining_time": "14:35:03", "throughput": 4987.11, "total_tokens": 4419552} +{"current_steps": 2040, "total_steps": 122600, "loss": 0.245, "lr": 8.315660685154976e-06, "epoch": 0.33278955954323003, "percentage": 1.66, "elapsed_time": "0:14:48", "remaining_time": "14:34:57", "throughput": 4987.09, "total_tokens": 4430080} +{"current_steps": 2045, "total_steps": 122600, "loss": 0.3979, "lr": 8.33605220228385e-06, "epoch": 0.333605220228385, "percentage": 1.67, "elapsed_time": "0:14:50", "remaining_time": "14:35:03", "throughput": 4986.98, "total_tokens": 4441568} +{"current_steps": 2050, "total_steps": 122600, "loss": 0.5355, "lr": 8.356443719412725e-06, "epoch": 0.33442088091353994, "percentage": 1.67, "elapsed_time": "0:14:52", "remaining_time": "14:34:48", "throughput": 4986.88, "total_tokens": 4451200} +{"current_steps": 2055, "total_steps": 122600, "loss": 0.3409, "lr": 8.376835236541599e-06, "epoch": 0.3352365415986949, "percentage": 1.68, "elapsed_time": "0:14:54", "remaining_time": "14:34:44", "throughput": 4986.8, "total_tokens": 4461888} +{"current_steps": 2060, "total_steps": 122600, "loss": 0.1644, "lr": 8.397226753670473e-06, "epoch": 0.3360522022838499, "percentage": 1.68, "elapsed_time": "0:14:56", "remaining_time": "14:34:24", "throughput": 4986.98, "total_tokens": 4471392} +{"current_steps": 2065, "total_steps": 122600, "loss": 0.1741, "lr": 8.417618270799347e-06, "epoch": 0.3368678629690049, "percentage": 1.68, "elapsed_time": "0:14:58", "remaining_time": "14:34:25", "throughput": 4987.19, "total_tokens": 4482656} +{"current_steps": 2070, "total_steps": 122600, "loss": 0.1922, "lr": 8.438009787928222e-06, "epoch": 0.3376835236541599, "percentage": 1.69, "elapsed_time": "0:15:01", "remaining_time": "14:34:30", "throughput": 4987.39, "total_tokens": 4494336} +{"current_steps": 2075, "total_steps": 122600, "loss": 0.4428, "lr": 8.458401305057096e-06, "epoch": 0.33849918433931486, "percentage": 1.69, "elapsed_time": "0:15:03", "remaining_time": "14:34:36", "throughput": 4987.26, "total_tokens": 4505760} +{"current_steps": 2080, "total_steps": 122600, "loss": 0.3476, "lr": 8.478792822185972e-06, "epoch": 0.33931484502446985, "percentage": 1.7, "elapsed_time": "0:15:05", "remaining_time": "14:34:14", "throughput": 4987.3, "total_tokens": 4514976} +{"current_steps": 2085, "total_steps": 122600, "loss": 0.1375, "lr": 8.499184339314845e-06, "epoch": 0.3401305057096248, "percentage": 1.7, "elapsed_time": "0:15:07", "remaining_time": "14:34:01", "throughput": 4987.38, "total_tokens": 4524928} +{"current_steps": 2090, "total_steps": 122600, "loss": 0.3217, "lr": 8.51957585644372e-06, "epoch": 0.34094616639477976, "percentage": 1.7, "elapsed_time": "0:15:09", "remaining_time": "14:34:03", "throughput": 4987.46, "total_tokens": 4536192} +{"current_steps": 2095, "total_steps": 122600, "loss": 0.1745, "lr": 8.539967373572593e-06, "epoch": 0.34176182707993474, "percentage": 1.71, "elapsed_time": "0:15:11", "remaining_time": "14:34:15", "throughput": 4987.34, "total_tokens": 4548160} +{"current_steps": 2100, "total_steps": 122600, "loss": 0.3299, "lr": 8.560358890701469e-06, "epoch": 0.3425774877650897, "percentage": 1.71, "elapsed_time": "0:15:14", "remaining_time": "14:34:06", "throughput": 4987.43, "total_tokens": 4558560} +{"current_steps": 2105, "total_steps": 122600, "loss": 0.3961, "lr": 8.580750407830342e-06, "epoch": 0.3433931484502447, "percentage": 1.72, "elapsed_time": "0:15:16", "remaining_time": "14:34:15", "throughput": 4987.31, "total_tokens": 4570272} +{"current_steps": 2110, "total_steps": 122600, "loss": 0.3544, "lr": 8.601141924959218e-06, "epoch": 0.3442088091353997, "percentage": 1.72, "elapsed_time": "0:15:18", "remaining_time": "14:34:07", "throughput": 4987.29, "total_tokens": 4580608} +{"current_steps": 2115, "total_steps": 122600, "loss": 0.1665, "lr": 8.621533442088092e-06, "epoch": 0.3450244698205546, "percentage": 1.73, "elapsed_time": "0:15:20", "remaining_time": "14:34:01", "throughput": 4987.28, "total_tokens": 4591072} +{"current_steps": 2120, "total_steps": 122600, "loss": 0.174, "lr": 8.641924959216967e-06, "epoch": 0.3458401305057096, "percentage": 1.73, "elapsed_time": "0:15:22", "remaining_time": "14:34:04", "throughput": 4987.23, "total_tokens": 4602368} +{"current_steps": 2125, "total_steps": 122600, "loss": 0.188, "lr": 8.66231647634584e-06, "epoch": 0.3466557911908646, "percentage": 1.73, "elapsed_time": "0:15:25", "remaining_time": "14:34:05", "throughput": 4987.33, "total_tokens": 4613600} +{"current_steps": 2130, "total_steps": 122600, "loss": 0.2258, "lr": 8.682707993474715e-06, "epoch": 0.3474714518760196, "percentage": 1.74, "elapsed_time": "0:15:27", "remaining_time": "14:33:58", "throughput": 4987.14, "total_tokens": 4623872} +{"current_steps": 2135, "total_steps": 122600, "loss": 0.4417, "lr": 8.703099510603589e-06, "epoch": 0.34828711256117456, "percentage": 1.74, "elapsed_time": "0:15:29", "remaining_time": "14:34:00", "throughput": 4987.2, "total_tokens": 4635136} +{"current_steps": 2140, "total_steps": 122600, "loss": 0.0318, "lr": 8.723491027732464e-06, "epoch": 0.34910277324632955, "percentage": 1.75, "elapsed_time": "0:15:31", "remaining_time": "14:33:47", "throughput": 4987.32, "total_tokens": 4645152} +{"current_steps": 2145, "total_steps": 122600, "loss": 0.2682, "lr": 8.743882544861338e-06, "epoch": 0.34991843393148453, "percentage": 1.75, "elapsed_time": "0:15:33", "remaining_time": "14:33:25", "throughput": 4987.32, "total_tokens": 4654240} +{"current_steps": 2150, "total_steps": 122600, "loss": 0.246, "lr": 8.764274061990214e-06, "epoch": 0.35073409461663946, "percentage": 1.75, "elapsed_time": "0:15:35", "remaining_time": "14:33:37", "throughput": 4987.21, "total_tokens": 4666240} +{"current_steps": 2155, "total_steps": 122600, "loss": 0.1963, "lr": 8.784665579119086e-06, "epoch": 0.35154975530179444, "percentage": 1.76, "elapsed_time": "0:15:38", "remaining_time": "14:33:52", "throughput": 4987.15, "total_tokens": 4678528} +{"current_steps": 2160, "total_steps": 122600, "loss": 0.3466, "lr": 8.805057096247961e-06, "epoch": 0.3523654159869494, "percentage": 1.76, "elapsed_time": "0:15:40", "remaining_time": "14:33:43", "throughput": 4987.08, "total_tokens": 4688768} +{"current_steps": 2165, "total_steps": 122600, "loss": 0.1565, "lr": 8.825448613376835e-06, "epoch": 0.3531810766721044, "percentage": 1.77, "elapsed_time": "0:15:42", "remaining_time": "14:33:27", "throughput": 4987.2, "total_tokens": 4698496} +{"current_steps": 2170, "total_steps": 122600, "loss": 0.1101, "lr": 8.84584013050571e-06, "epoch": 0.3539967373572594, "percentage": 1.77, "elapsed_time": "0:15:44", "remaining_time": "14:33:35", "throughput": 4987.19, "total_tokens": 4710208} +{"current_steps": 2175, "total_steps": 122600, "loss": 0.3345, "lr": 8.866231647634584e-06, "epoch": 0.3548123980424144, "percentage": 1.77, "elapsed_time": "0:15:46", "remaining_time": "14:33:27", "throughput": 4987.15, "total_tokens": 4720480} +{"current_steps": 2180, "total_steps": 122600, "loss": 0.5494, "lr": 8.88662316476346e-06, "epoch": 0.3556280587275693, "percentage": 1.78, "elapsed_time": "0:15:48", "remaining_time": "14:33:16", "throughput": 4987.17, "total_tokens": 4730560} +{"current_steps": 2185, "total_steps": 122600, "loss": 0.0332, "lr": 8.907014681892334e-06, "epoch": 0.3564437194127243, "percentage": 1.78, "elapsed_time": "0:15:50", "remaining_time": "14:33:05", "throughput": 4987.32, "total_tokens": 4740768} +{"current_steps": 2190, "total_steps": 122600, "loss": 0.6973, "lr": 8.927406199021208e-06, "epoch": 0.3572593800978793, "percentage": 1.79, "elapsed_time": "0:15:52", "remaining_time": "14:32:55", "throughput": 4987.42, "total_tokens": 4751040} +{"current_steps": 2195, "total_steps": 122600, "loss": 0.1786, "lr": 8.947797716150081e-06, "epoch": 0.35807504078303426, "percentage": 1.79, "elapsed_time": "0:15:54", "remaining_time": "14:32:54", "throughput": 4987.47, "total_tokens": 4762016} +{"current_steps": 2200, "total_steps": 122600, "loss": 0.2195, "lr": 8.968189233278957e-06, "epoch": 0.35889070146818924, "percentage": 1.79, "elapsed_time": "0:15:56", "remaining_time": "14:32:40", "throughput": 4987.36, "total_tokens": 4771648} +{"current_steps": 2205, "total_steps": 122600, "loss": 0.2572, "lr": 8.98858075040783e-06, "epoch": 0.35970636215334423, "percentage": 1.8, "elapsed_time": "0:15:58", "remaining_time": "14:32:24", "throughput": 4987.55, "total_tokens": 4781440} +{"current_steps": 2210, "total_steps": 122600, "loss": 0.2168, "lr": 9.008972267536706e-06, "epoch": 0.3605220228384992, "percentage": 1.8, "elapsed_time": "0:16:01", "remaining_time": "14:32:34", "throughput": 4987.42, "total_tokens": 4793312} +{"current_steps": 2215, "total_steps": 122600, "loss": 0.1372, "lr": 9.02936378466558e-06, "epoch": 0.36133768352365414, "percentage": 1.81, "elapsed_time": "0:16:03", "remaining_time": "14:32:34", "throughput": 4987.35, "total_tokens": 4804288} +{"current_steps": 2220, "total_steps": 122600, "loss": 0.5373, "lr": 9.049755301794454e-06, "epoch": 0.3621533442088091, "percentage": 1.81, "elapsed_time": "0:16:05", "remaining_time": "14:32:28", "throughput": 4987.43, "total_tokens": 4814784} +{"current_steps": 2225, "total_steps": 122600, "loss": 0.6647, "lr": 9.070146818923328e-06, "epoch": 0.3629690048939641, "percentage": 1.81, "elapsed_time": "0:16:07", "remaining_time": "14:32:20", "throughput": 4987.46, "total_tokens": 4825152} +{"current_steps": 2230, "total_steps": 122600, "loss": 0.3815, "lr": 9.090538336052203e-06, "epoch": 0.3637846655791191, "percentage": 1.82, "elapsed_time": "0:16:09", "remaining_time": "14:32:16", "throughput": 4987.38, "total_tokens": 4835776} +{"current_steps": 2235, "total_steps": 122600, "loss": 0.1083, "lr": 9.110929853181077e-06, "epoch": 0.3646003262642741, "percentage": 1.82, "elapsed_time": "0:16:11", "remaining_time": "14:32:17", "throughput": 4987.38, "total_tokens": 4846848} +{"current_steps": 2240, "total_steps": 122600, "loss": 0.0096, "lr": 9.131321370309953e-06, "epoch": 0.36541598694942906, "percentage": 1.83, "elapsed_time": "0:16:13", "remaining_time": "14:32:13", "throughput": 4987.48, "total_tokens": 4857664} +{"current_steps": 2245, "total_steps": 122600, "loss": 0.3865, "lr": 9.151712887438826e-06, "epoch": 0.366231647634584, "percentage": 1.83, "elapsed_time": "0:16:16", "remaining_time": "14:32:13", "throughput": 4987.54, "total_tokens": 4868800} +{"current_steps": 2250, "total_steps": 122600, "loss": 0.3825, "lr": 9.1721044045677e-06, "epoch": 0.367047308319739, "percentage": 1.84, "elapsed_time": "0:16:18", "remaining_time": "14:32:13", "throughput": 4987.48, "total_tokens": 4879776} +{"current_steps": 2255, "total_steps": 122600, "loss": 0.3502, "lr": 9.192495921696574e-06, "epoch": 0.36786296900489396, "percentage": 1.84, "elapsed_time": "0:16:20", "remaining_time": "14:32:13", "throughput": 4987.52, "total_tokens": 4890816} +{"current_steps": 2260, "total_steps": 122600, "loss": 0.2848, "lr": 9.21288743882545e-06, "epoch": 0.36867862969004894, "percentage": 1.84, "elapsed_time": "0:16:22", "remaining_time": "14:31:43", "throughput": 4987.54, "total_tokens": 4899136} +{"current_steps": 2265, "total_steps": 122600, "loss": 0.1367, "lr": 9.233278955954323e-06, "epoch": 0.3694942903752039, "percentage": 1.85, "elapsed_time": "0:16:24", "remaining_time": "14:31:41", "throughput": 4987.73, "total_tokens": 4910112} +{"current_steps": 2270, "total_steps": 122600, "loss": 0.4234, "lr": 9.253670473083197e-06, "epoch": 0.3703099510603589, "percentage": 1.85, "elapsed_time": "0:16:26", "remaining_time": "14:31:28", "throughput": 4987.8, "total_tokens": 4920032} +{"current_steps": 2275, "total_steps": 122600, "loss": 0.2471, "lr": 9.274061990212073e-06, "epoch": 0.37112561174551384, "percentage": 1.86, "elapsed_time": "0:16:28", "remaining_time": "14:31:24", "throughput": 4987.91, "total_tokens": 4930752} +{"current_steps": 2280, "total_steps": 122600, "loss": 0.2174, "lr": 9.294453507340947e-06, "epoch": 0.3719412724306688, "percentage": 1.86, "elapsed_time": "0:16:30", "remaining_time": "14:31:14", "throughput": 4987.99, "total_tokens": 4940960} +{"current_steps": 2285, "total_steps": 122600, "loss": 0.2848, "lr": 9.31484502446982e-06, "epoch": 0.3727569331158238, "percentage": 1.86, "elapsed_time": "0:16:32", "remaining_time": "14:31:16", "throughput": 4987.88, "total_tokens": 4952128} +{"current_steps": 2290, "total_steps": 122600, "loss": 0.5019, "lr": 9.335236541598694e-06, "epoch": 0.3735725938009788, "percentage": 1.87, "elapsed_time": "0:16:34", "remaining_time": "14:31:11", "throughput": 4988.09, "total_tokens": 4962848} +{"current_steps": 2295, "total_steps": 122600, "loss": 0.0659, "lr": 9.35562805872757e-06, "epoch": 0.3743882544861338, "percentage": 1.87, "elapsed_time": "0:16:36", "remaining_time": "14:30:54", "throughput": 4988.24, "total_tokens": 4972448} +{"current_steps": 2300, "total_steps": 122600, "loss": 0.2185, "lr": 9.376019575856444e-06, "epoch": 0.37520391517128876, "percentage": 1.88, "elapsed_time": "0:16:38", "remaining_time": "14:30:42", "throughput": 4988.34, "total_tokens": 4982432} +{"current_steps": 2305, "total_steps": 122600, "loss": 0.0939, "lr": 9.396411092985319e-06, "epoch": 0.37601957585644374, "percentage": 1.88, "elapsed_time": "0:16:40", "remaining_time": "14:30:35", "throughput": 4988.34, "total_tokens": 4992800} +{"current_steps": 2310, "total_steps": 122600, "loss": 0.0402, "lr": 9.416802610114193e-06, "epoch": 0.3768352365415987, "percentage": 1.88, "elapsed_time": "0:16:43", "remaining_time": "14:30:39", "throughput": 4988.48, "total_tokens": 5004352} +{"current_steps": 2315, "total_steps": 122600, "loss": 0.2118, "lr": 9.437194127243067e-06, "epoch": 0.37765089722675366, "percentage": 1.89, "elapsed_time": "0:16:45", "remaining_time": "14:30:45", "throughput": 4988.42, "total_tokens": 5015968} +{"current_steps": 2320, "total_steps": 122600, "loss": 0.0666, "lr": 9.45758564437194e-06, "epoch": 0.37846655791190864, "percentage": 1.89, "elapsed_time": "0:16:47", "remaining_time": "14:30:42", "throughput": 4988.37, "total_tokens": 5026624} +{"current_steps": 2325, "total_steps": 122600, "loss": 0.1838, "lr": 9.477977161500816e-06, "epoch": 0.3792822185970636, "percentage": 1.9, "elapsed_time": "0:16:49", "remaining_time": "14:30:38", "throughput": 4988.35, "total_tokens": 5037312} +{"current_steps": 2330, "total_steps": 122600, "loss": 0.2209, "lr": 9.49836867862969e-06, "epoch": 0.3800978792822186, "percentage": 1.9, "elapsed_time": "0:16:52", "remaining_time": "14:30:40", "throughput": 4988.38, "total_tokens": 5048544} +{"current_steps": 2335, "total_steps": 122600, "loss": 0.1917, "lr": 9.518760195758565e-06, "epoch": 0.3809135399673736, "percentage": 1.9, "elapsed_time": "0:16:54", "remaining_time": "14:30:41", "throughput": 4988.33, "total_tokens": 5059584} +{"current_steps": 2340, "total_steps": 122600, "loss": 0.3295, "lr": 9.53915171288744e-06, "epoch": 0.3817292006525285, "percentage": 1.91, "elapsed_time": "0:16:56", "remaining_time": "14:31:02", "throughput": 4988.4, "total_tokens": 5072736} +{"current_steps": 2345, "total_steps": 122600, "loss": 0.6389, "lr": 9.559543230016315e-06, "epoch": 0.3825448613376835, "percentage": 1.91, "elapsed_time": "0:16:59", "remaining_time": "14:30:58", "throughput": 4988.4, "total_tokens": 5083456} +{"current_steps": 2350, "total_steps": 122600, "loss": 0.1956, "lr": 9.579934747145187e-06, "epoch": 0.3833605220228385, "percentage": 1.92, "elapsed_time": "0:17:01", "remaining_time": "14:30:55", "throughput": 4988.48, "total_tokens": 5094240} +{"current_steps": 2355, "total_steps": 122600, "loss": 0.1972, "lr": 9.600326264274062e-06, "epoch": 0.3841761827079935, "percentage": 1.92, "elapsed_time": "0:17:03", "remaining_time": "14:30:39", "throughput": 4988.49, "total_tokens": 5103744} +{"current_steps": 2360, "total_steps": 122600, "loss": 0.2742, "lr": 9.620717781402936e-06, "epoch": 0.38499184339314846, "percentage": 1.92, "elapsed_time": "0:17:05", "remaining_time": "14:30:30", "throughput": 4988.6, "total_tokens": 5114048} +{"current_steps": 2365, "total_steps": 122600, "loss": 0.5062, "lr": 9.641109298531812e-06, "epoch": 0.38580750407830344, "percentage": 1.93, "elapsed_time": "0:17:07", "remaining_time": "14:30:15", "throughput": 4988.72, "total_tokens": 5123744} +{"current_steps": 2370, "total_steps": 122600, "loss": 0.2739, "lr": 9.661500815660686e-06, "epoch": 0.3866231647634584, "percentage": 1.93, "elapsed_time": "0:17:09", "remaining_time": "14:30:05", "throughput": 4988.76, "total_tokens": 5133888} +{"current_steps": 2375, "total_steps": 122600, "loss": 0.2247, "lr": 9.681892332789561e-06, "epoch": 0.38743882544861336, "percentage": 1.94, "elapsed_time": "0:17:11", "remaining_time": "14:30:06", "throughput": 4988.81, "total_tokens": 5145024} +{"current_steps": 2380, "total_steps": 122600, "loss": 0.0302, "lr": 9.702283849918433e-06, "epoch": 0.38825448613376834, "percentage": 1.94, "elapsed_time": "0:17:13", "remaining_time": "14:30:10", "throughput": 4988.81, "total_tokens": 5156544} +{"current_steps": 2385, "total_steps": 122600, "loss": 0.439, "lr": 9.722675367047309e-06, "epoch": 0.3890701468189233, "percentage": 1.95, "elapsed_time": "0:17:15", "remaining_time": "14:30:15", "throughput": 4988.91, "total_tokens": 5168192} +{"current_steps": 2390, "total_steps": 122600, "loss": 0.3195, "lr": 9.743066884176183e-06, "epoch": 0.3898858075040783, "percentage": 1.95, "elapsed_time": "0:17:17", "remaining_time": "14:30:06", "throughput": 4988.87, "total_tokens": 5178240} +{"current_steps": 2395, "total_steps": 122600, "loss": 0.0923, "lr": 9.763458401305058e-06, "epoch": 0.3907014681892333, "percentage": 1.95, "elapsed_time": "0:17:20", "remaining_time": "14:30:07", "throughput": 4988.68, "total_tokens": 5189248} +{"current_steps": 2400, "total_steps": 122600, "loss": 0.1188, "lr": 9.783849918433932e-06, "epoch": 0.3915171288743883, "percentage": 1.96, "elapsed_time": "0:17:22", "remaining_time": "14:29:58", "throughput": 4988.69, "total_tokens": 5199392} +{"current_steps": 2405, "total_steps": 122600, "loss": 0.2752, "lr": 9.804241435562807e-06, "epoch": 0.3923327895595432, "percentage": 1.96, "elapsed_time": "0:17:24", "remaining_time": "14:29:57", "throughput": 4988.56, "total_tokens": 5210240} +{"current_steps": 2410, "total_steps": 122600, "loss": 0.3948, "lr": 9.824632952691681e-06, "epoch": 0.3931484502446982, "percentage": 1.97, "elapsed_time": "0:17:26", "remaining_time": "14:29:44", "throughput": 4988.61, "total_tokens": 5220000} +{"current_steps": 2415, "total_steps": 122600, "loss": 0.0973, "lr": 9.845024469820555e-06, "epoch": 0.3939641109298532, "percentage": 1.97, "elapsed_time": "0:17:28", "remaining_time": "14:29:48", "throughput": 4988.68, "total_tokens": 5231520} +{"current_steps": 2420, "total_steps": 122600, "loss": 0.3451, "lr": 9.865415986949429e-06, "epoch": 0.39477977161500816, "percentage": 1.97, "elapsed_time": "0:17:31", "remaining_time": "14:29:56", "throughput": 4988.56, "total_tokens": 5243200} +{"current_steps": 2425, "total_steps": 122600, "loss": 0.1705, "lr": 9.885807504078304e-06, "epoch": 0.39559543230016314, "percentage": 1.98, "elapsed_time": "0:17:33", "remaining_time": "14:29:50", "throughput": 4988.52, "total_tokens": 5253632} +{"current_steps": 2430, "total_steps": 122600, "loss": 0.1888, "lr": 9.906199021207178e-06, "epoch": 0.3964110929853181, "percentage": 1.98, "elapsed_time": "0:17:35", "remaining_time": "14:29:50", "throughput": 4988.56, "total_tokens": 5264736} +{"current_steps": 2435, "total_steps": 122600, "loss": 0.276, "lr": 9.926590538336054e-06, "epoch": 0.3972267536704731, "percentage": 1.99, "elapsed_time": "0:17:37", "remaining_time": "14:29:54", "throughput": 4988.58, "total_tokens": 5276192} +{"current_steps": 2440, "total_steps": 122600, "loss": 0.2301, "lr": 9.946982055464928e-06, "epoch": 0.39804241435562804, "percentage": 1.99, "elapsed_time": "0:17:39", "remaining_time": "14:29:55", "throughput": 4988.47, "total_tokens": 5287296} +{"current_steps": 2445, "total_steps": 122600, "loss": 0.312, "lr": 9.967373572593801e-06, "epoch": 0.398858075040783, "percentage": 1.99, "elapsed_time": "0:17:42", "remaining_time": "14:29:57", "throughput": 4988.33, "total_tokens": 5298336} +{"current_steps": 2450, "total_steps": 122600, "loss": 0.1243, "lr": 9.987765089722675e-06, "epoch": 0.399673735725938, "percentage": 2.0, "elapsed_time": "0:17:44", "remaining_time": "14:29:56", "throughput": 4988.29, "total_tokens": 5309248} +{"current_steps": 2455, "total_steps": 122600, "loss": 0.5038, "lr": 1.000815660685155e-05, "epoch": 0.400489396411093, "percentage": 2.0, "elapsed_time": "0:17:46", "remaining_time": "14:29:56", "throughput": 4988.29, "total_tokens": 5320384} +{"current_steps": 2460, "total_steps": 122600, "loss": 0.0403, "lr": 1.0028548123980425e-05, "epoch": 0.401305057096248, "percentage": 2.01, "elapsed_time": "0:17:48", "remaining_time": "14:30:02", "throughput": 4988.16, "total_tokens": 5331904} +{"current_steps": 2465, "total_steps": 122600, "loss": 0.2566, "lr": 1.00489396411093e-05, "epoch": 0.40212071778140296, "percentage": 2.01, "elapsed_time": "0:17:51", "remaining_time": "14:30:13", "throughput": 4988.02, "total_tokens": 5343904} +{"current_steps": 2470, "total_steps": 122600, "loss": 0.0988, "lr": 1.0069331158238174e-05, "epoch": 0.4029363784665579, "percentage": 2.01, "elapsed_time": "0:17:53", "remaining_time": "14:30:09", "throughput": 4987.85, "total_tokens": 5354336} +{"current_steps": 2475, "total_steps": 122600, "loss": 0.32, "lr": 1.0089722675367048e-05, "epoch": 0.40375203915171287, "percentage": 2.02, "elapsed_time": "0:17:55", "remaining_time": "14:30:17", "throughput": 4987.7, "total_tokens": 5366144} +{"current_steps": 2480, "total_steps": 122600, "loss": 0.1461, "lr": 1.0110114192495921e-05, "epoch": 0.40456769983686786, "percentage": 2.02, "elapsed_time": "0:17:58", "remaining_time": "14:30:19", "throughput": 4987.66, "total_tokens": 5377344} +{"current_steps": 2485, "total_steps": 122600, "loss": 0.1045, "lr": 1.0130505709624797e-05, "epoch": 0.40538336052202284, "percentage": 2.03, "elapsed_time": "0:18:00", "remaining_time": "14:30:04", "throughput": 4987.54, "total_tokens": 5386752} +{"current_steps": 2490, "total_steps": 122600, "loss": 0.096, "lr": 1.015089722675367e-05, "epoch": 0.4061990212071778, "percentage": 2.03, "elapsed_time": "0:18:01", "remaining_time": "14:29:51", "throughput": 4987.52, "total_tokens": 5396384} +{"current_steps": 2495, "total_steps": 122600, "loss": 0.2788, "lr": 1.0171288743882545e-05, "epoch": 0.4070146818923328, "percentage": 2.04, "elapsed_time": "0:18:04", "remaining_time": "14:29:58", "throughput": 4987.62, "total_tokens": 5408256} +{"current_steps": 2500, "total_steps": 122600, "loss": 0.2226, "lr": 1.019168026101142e-05, "epoch": 0.4078303425774878, "percentage": 2.04, "elapsed_time": "0:18:06", "remaining_time": "14:29:51", "throughput": 4987.74, "total_tokens": 5418752} +{"current_steps": 2505, "total_steps": 122600, "loss": 0.1557, "lr": 1.0212071778140294e-05, "epoch": 0.4086460032626427, "percentage": 2.04, "elapsed_time": "0:18:08", "remaining_time": "14:29:50", "throughput": 4987.76, "total_tokens": 5429792} +{"current_steps": 2510, "total_steps": 122600, "loss": 0.3616, "lr": 1.0232463295269168e-05, "epoch": 0.4094616639477977, "percentage": 2.05, "elapsed_time": "0:18:10", "remaining_time": "14:29:48", "throughput": 4987.77, "total_tokens": 5440608} +{"current_steps": 2515, "total_steps": 122600, "loss": 0.3613, "lr": 1.0252854812398043e-05, "epoch": 0.4102773246329527, "percentage": 2.05, "elapsed_time": "0:18:12", "remaining_time": "14:29:31", "throughput": 4987.86, "total_tokens": 5450016} +{"current_steps": 2520, "total_steps": 122600, "loss": 0.6025, "lr": 1.0273246329526917e-05, "epoch": 0.4110929853181077, "percentage": 2.06, "elapsed_time": "0:18:14", "remaining_time": "14:29:33", "throughput": 4987.73, "total_tokens": 5461120} +{"current_steps": 2525, "total_steps": 122600, "loss": 0.0903, "lr": 1.0293637846655791e-05, "epoch": 0.41190864600326266, "percentage": 2.06, "elapsed_time": "0:18:17", "remaining_time": "14:29:28", "throughput": 4987.73, "total_tokens": 5471648} +{"current_steps": 2530, "total_steps": 122600, "loss": 0.3465, "lr": 1.0314029363784666e-05, "epoch": 0.41272430668841764, "percentage": 2.06, "elapsed_time": "0:18:19", "remaining_time": "14:29:28", "throughput": 4987.7, "total_tokens": 5482656} +{"current_steps": 2535, "total_steps": 122600, "loss": 0.0684, "lr": 1.033442088091354e-05, "epoch": 0.41353996737357257, "percentage": 2.07, "elapsed_time": "0:18:20", "remaining_time": "14:29:01", "throughput": 4987.9, "total_tokens": 5491168} +{"current_steps": 2540, "total_steps": 122600, "loss": 0.3827, "lr": 1.0354812398042416e-05, "epoch": 0.41435562805872755, "percentage": 2.07, "elapsed_time": "0:18:23", "remaining_time": "14:28:57", "throughput": 4987.88, "total_tokens": 5501792} +{"current_steps": 2545, "total_steps": 122600, "loss": 0.4043, "lr": 1.0375203915171288e-05, "epoch": 0.41517128874388254, "percentage": 2.08, "elapsed_time": "0:18:25", "remaining_time": "14:29:00", "throughput": 4987.89, "total_tokens": 5513152} +{"current_steps": 2550, "total_steps": 122600, "loss": 0.0484, "lr": 1.0395595432300163e-05, "epoch": 0.4159869494290375, "percentage": 2.08, "elapsed_time": "0:18:27", "remaining_time": "14:29:04", "throughput": 4987.77, "total_tokens": 5524480} +{"current_steps": 2555, "total_steps": 122600, "loss": 0.1424, "lr": 1.0415986949429037e-05, "epoch": 0.4168026101141925, "percentage": 2.08, "elapsed_time": "0:18:29", "remaining_time": "14:28:59", "throughput": 4987.78, "total_tokens": 5535008} +{"current_steps": 2560, "total_steps": 122600, "loss": 0.108, "lr": 1.0436378466557913e-05, "epoch": 0.4176182707993475, "percentage": 2.09, "elapsed_time": "0:18:31", "remaining_time": "14:28:57", "throughput": 4987.88, "total_tokens": 5546048} +{"current_steps": 2565, "total_steps": 122600, "loss": 0.4851, "lr": 1.0456769983686787e-05, "epoch": 0.4184339314845024, "percentage": 2.09, "elapsed_time": "0:18:34", "remaining_time": "14:29:03", "throughput": 4987.94, "total_tokens": 5557760} +{"current_steps": 2570, "total_steps": 122600, "loss": 0.312, "lr": 1.0477161500815662e-05, "epoch": 0.4192495921696574, "percentage": 2.1, "elapsed_time": "0:18:36", "remaining_time": "14:28:49", "throughput": 4988.04, "total_tokens": 5567488} +{"current_steps": 2575, "total_steps": 122600, "loss": 0.3677, "lr": 1.0497553017944534e-05, "epoch": 0.4200652528548124, "percentage": 2.1, "elapsed_time": "0:18:38", "remaining_time": "14:28:49", "throughput": 4988.08, "total_tokens": 5578592} +{"current_steps": 2580, "total_steps": 122600, "loss": 0.0575, "lr": 1.051794453507341e-05, "epoch": 0.42088091353996737, "percentage": 2.1, "elapsed_time": "0:18:40", "remaining_time": "14:28:38", "throughput": 4988.15, "total_tokens": 5588576} +{"current_steps": 2585, "total_steps": 122600, "loss": 0.1166, "lr": 1.0538336052202284e-05, "epoch": 0.42169657422512236, "percentage": 2.11, "elapsed_time": "0:18:42", "remaining_time": "14:28:34", "throughput": 4988.25, "total_tokens": 5599264} +{"current_steps": 2590, "total_steps": 122600, "loss": 0.1589, "lr": 1.0558727569331159e-05, "epoch": 0.42251223491027734, "percentage": 2.11, "elapsed_time": "0:18:44", "remaining_time": "14:28:27", "throughput": 4988.21, "total_tokens": 5609504} +{"current_steps": 2595, "total_steps": 122600, "loss": 0.3561, "lr": 1.0579119086460033e-05, "epoch": 0.4233278955954323, "percentage": 2.12, "elapsed_time": "0:18:46", "remaining_time": "14:28:25", "throughput": 4988.09, "total_tokens": 5620256} +{"current_steps": 2600, "total_steps": 122600, "loss": 0.5994, "lr": 1.0599510603588908e-05, "epoch": 0.42414355628058725, "percentage": 2.12, "elapsed_time": "0:18:48", "remaining_time": "14:28:18", "throughput": 4988.11, "total_tokens": 5630592} +{"current_steps": 2605, "total_steps": 122600, "loss": 0.4714, "lr": 1.061990212071778e-05, "epoch": 0.42495921696574224, "percentage": 2.12, "elapsed_time": "0:18:50", "remaining_time": "14:28:17", "throughput": 4988.12, "total_tokens": 5641536} +{"current_steps": 2610, "total_steps": 122600, "loss": 0.0271, "lr": 1.0640293637846656e-05, "epoch": 0.4257748776508972, "percentage": 2.13, "elapsed_time": "0:18:53", "remaining_time": "14:28:15", "throughput": 4988.17, "total_tokens": 5652416} +{"current_steps": 2615, "total_steps": 122600, "loss": 0.2538, "lr": 1.066068515497553e-05, "epoch": 0.4265905383360522, "percentage": 2.13, "elapsed_time": "0:18:55", "remaining_time": "14:28:06", "throughput": 4988.12, "total_tokens": 5662528} +{"current_steps": 2620, "total_steps": 122600, "loss": 0.223, "lr": 1.0681076672104405e-05, "epoch": 0.4274061990212072, "percentage": 2.14, "elapsed_time": "0:18:57", "remaining_time": "14:27:54", "throughput": 4988.17, "total_tokens": 5672288} +{"current_steps": 2625, "total_steps": 122600, "loss": 0.0976, "lr": 1.070146818923328e-05, "epoch": 0.4282218597063622, "percentage": 2.14, "elapsed_time": "0:18:59", "remaining_time": "14:27:51", "throughput": 4988.17, "total_tokens": 5682976} +{"current_steps": 2630, "total_steps": 122600, "loss": 0.105, "lr": 1.0721859706362155e-05, "epoch": 0.4290375203915171, "percentage": 2.15, "elapsed_time": "0:19:01", "remaining_time": "14:27:53", "throughput": 4988.12, "total_tokens": 5694240} +{"current_steps": 2635, "total_steps": 122600, "loss": 0.1578, "lr": 1.0742251223491029e-05, "epoch": 0.4298531810766721, "percentage": 2.15, "elapsed_time": "0:19:03", "remaining_time": "14:27:43", "throughput": 4988.13, "total_tokens": 5704192} +{"current_steps": 2640, "total_steps": 122600, "loss": 0.0991, "lr": 1.0762642740619902e-05, "epoch": 0.43066884176182707, "percentage": 2.15, "elapsed_time": "0:19:05", "remaining_time": "14:27:50", "throughput": 4988.09, "total_tokens": 5715968} +{"current_steps": 2645, "total_steps": 122600, "loss": 0.078, "lr": 1.0783034257748776e-05, "epoch": 0.43148450244698205, "percentage": 2.16, "elapsed_time": "0:19:08", "remaining_time": "14:27:49", "throughput": 4987.91, "total_tokens": 5726784} +{"current_steps": 2650, "total_steps": 122600, "loss": 0.4613, "lr": 1.0803425774877652e-05, "epoch": 0.43230016313213704, "percentage": 2.16, "elapsed_time": "0:19:10", "remaining_time": "14:27:52", "throughput": 4987.77, "total_tokens": 5737952} +{"current_steps": 2655, "total_steps": 122600, "loss": 0.1405, "lr": 1.0823817292006526e-05, "epoch": 0.433115823817292, "percentage": 2.17, "elapsed_time": "0:19:12", "remaining_time": "14:27:46", "throughput": 4987.83, "total_tokens": 5748512} +{"current_steps": 2660, "total_steps": 122600, "loss": 0.2177, "lr": 1.0844208809135401e-05, "epoch": 0.433931484502447, "percentage": 2.17, "elapsed_time": "0:19:14", "remaining_time": "14:27:42", "throughput": 4987.72, "total_tokens": 5758944} +{"current_steps": 2665, "total_steps": 122600, "loss": 0.326, "lr": 1.0864600326264275e-05, "epoch": 0.43474714518760194, "percentage": 2.17, "elapsed_time": "0:19:16", "remaining_time": "14:27:40", "throughput": 4987.6, "total_tokens": 5769632} +{"current_steps": 2670, "total_steps": 122600, "loss": 0.15, "lr": 1.0884991843393149e-05, "epoch": 0.4355628058727569, "percentage": 2.18, "elapsed_time": "0:19:19", "remaining_time": "14:27:45", "throughput": 4987.58, "total_tokens": 5781248} +{"current_steps": 2675, "total_steps": 122600, "loss": 0.2446, "lr": 1.0905383360522023e-05, "epoch": 0.4363784665579119, "percentage": 2.18, "elapsed_time": "0:19:21", "remaining_time": "14:27:44", "throughput": 4987.56, "total_tokens": 5792192} +{"current_steps": 2680, "total_steps": 122600, "loss": 0.0698, "lr": 1.0925774877650898e-05, "epoch": 0.4371941272430669, "percentage": 2.19, "elapsed_time": "0:19:23", "remaining_time": "14:27:43", "throughput": 4987.65, "total_tokens": 5803264} +{"current_steps": 2685, "total_steps": 122600, "loss": 0.074, "lr": 1.0946166394779772e-05, "epoch": 0.43800978792822187, "percentage": 2.19, "elapsed_time": "0:19:25", "remaining_time": "14:27:51", "throughput": 4987.51, "total_tokens": 5815072} +{"current_steps": 2690, "total_steps": 122600, "loss": 0.3131, "lr": 1.0966557911908647e-05, "epoch": 0.43882544861337686, "percentage": 2.19, "elapsed_time": "0:19:27", "remaining_time": "14:27:44", "throughput": 4987.37, "total_tokens": 5825248} +{"current_steps": 2695, "total_steps": 122600, "loss": 0.3418, "lr": 1.0986949429037521e-05, "epoch": 0.4396411092985318, "percentage": 2.2, "elapsed_time": "0:19:30", "remaining_time": "14:27:40", "throughput": 4987.46, "total_tokens": 5835904} +{"current_steps": 2700, "total_steps": 122600, "loss": 0.2068, "lr": 1.1007340946166395e-05, "epoch": 0.44045676998368677, "percentage": 2.2, "elapsed_time": "0:19:31", "remaining_time": "14:27:21", "throughput": 4987.4, "total_tokens": 5844736} +{"current_steps": 2705, "total_steps": 122600, "loss": 0.4, "lr": 1.1027732463295269e-05, "epoch": 0.44127243066884175, "percentage": 2.21, "elapsed_time": "0:19:34", "remaining_time": "14:27:28", "throughput": 4987.45, "total_tokens": 5856672} +{"current_steps": 2710, "total_steps": 122600, "loss": 0.182, "lr": 1.1048123980424144e-05, "epoch": 0.44208809135399674, "percentage": 2.21, "elapsed_time": "0:19:36", "remaining_time": "14:27:20", "throughput": 4987.45, "total_tokens": 5866848} +{"current_steps": 2715, "total_steps": 122600, "loss": 0.0394, "lr": 1.1068515497553018e-05, "epoch": 0.4429037520391517, "percentage": 2.21, "elapsed_time": "0:19:38", "remaining_time": "14:27:19", "throughput": 4987.5, "total_tokens": 5877856} +{"current_steps": 2720, "total_steps": 122600, "loss": 0.1898, "lr": 1.1088907014681894e-05, "epoch": 0.4437194127243067, "percentage": 2.22, "elapsed_time": "0:19:40", "remaining_time": "14:27:19", "throughput": 4987.43, "total_tokens": 5888896} +{"current_steps": 2725, "total_steps": 122600, "loss": 0.2505, "lr": 1.1109298531810768e-05, "epoch": 0.4445350734094617, "percentage": 2.22, "elapsed_time": "0:19:42", "remaining_time": "14:27:18", "throughput": 4987.51, "total_tokens": 5899872} +{"current_steps": 2730, "total_steps": 122600, "loss": 0.1542, "lr": 1.1129690048939641e-05, "epoch": 0.4453507340946166, "percentage": 2.23, "elapsed_time": "0:19:45", "remaining_time": "14:27:12", "throughput": 4987.46, "total_tokens": 5910272} +{"current_steps": 2735, "total_steps": 122600, "loss": 0.2802, "lr": 1.1150081566068515e-05, "epoch": 0.4461663947797716, "percentage": 2.23, "elapsed_time": "0:19:47", "remaining_time": "14:27:12", "throughput": 4987.41, "total_tokens": 5921312} +{"current_steps": 2740, "total_steps": 122600, "loss": 0.1235, "lr": 1.117047308319739e-05, "epoch": 0.4469820554649266, "percentage": 2.23, "elapsed_time": "0:19:49", "remaining_time": "14:27:20", "throughput": 4986.35, "total_tokens": 5932032} +{"current_steps": 2745, "total_steps": 122600, "loss": 0.1224, "lr": 1.1190864600326265e-05, "epoch": 0.44779771615008157, "percentage": 2.24, "elapsed_time": "0:19:51", "remaining_time": "14:27:11", "throughput": 4986.51, "total_tokens": 5942176} +{"current_steps": 2750, "total_steps": 122600, "loss": 0.6411, "lr": 1.1211256117455138e-05, "epoch": 0.44861337683523655, "percentage": 2.24, "elapsed_time": "0:19:54", "remaining_time": "14:27:19", "throughput": 4986.57, "total_tokens": 5954336} +{"current_steps": 2755, "total_steps": 122600, "loss": 0.4493, "lr": 1.1231647634584014e-05, "epoch": 0.44942903752039154, "percentage": 2.25, "elapsed_time": "0:19:56", "remaining_time": "14:27:18", "throughput": 4986.48, "total_tokens": 5965152} +{"current_steps": 2760, "total_steps": 122600, "loss": 0.3033, "lr": 1.1252039151712888e-05, "epoch": 0.45024469820554647, "percentage": 2.25, "elapsed_time": "0:19:58", "remaining_time": "14:27:26", "throughput": 4986.56, "total_tokens": 5977216} +{"current_steps": 2765, "total_steps": 122600, "loss": 0.2326, "lr": 1.1272430668841763e-05, "epoch": 0.45106035889070145, "percentage": 2.26, "elapsed_time": "0:20:00", "remaining_time": "14:27:23", "throughput": 4986.55, "total_tokens": 5988000} +{"current_steps": 2770, "total_steps": 122600, "loss": 0.1897, "lr": 1.1292822185970635e-05, "epoch": 0.45187601957585644, "percentage": 2.26, "elapsed_time": "0:20:02", "remaining_time": "14:27:16", "throughput": 4986.7, "total_tokens": 5998400} +{"current_steps": 2775, "total_steps": 122600, "loss": 0.2611, "lr": 1.1313213703099511e-05, "epoch": 0.4526916802610114, "percentage": 2.26, "elapsed_time": "0:20:05", "remaining_time": "14:27:23", "throughput": 4986.64, "total_tokens": 6010176} +{"current_steps": 2780, "total_steps": 122600, "loss": 0.1845, "lr": 1.1333605220228385e-05, "epoch": 0.4535073409461664, "percentage": 2.27, "elapsed_time": "0:20:07", "remaining_time": "14:27:24", "throughput": 4986.6, "total_tokens": 6021312} +{"current_steps": 2785, "total_steps": 122600, "loss": 0.2288, "lr": 1.135399673735726e-05, "epoch": 0.4543230016313214, "percentage": 2.27, "elapsed_time": "0:20:09", "remaining_time": "14:27:28", "throughput": 4986.65, "total_tokens": 6033024} +{"current_steps": 2790, "total_steps": 122600, "loss": 0.1196, "lr": 1.1374388254486134e-05, "epoch": 0.4551386623164764, "percentage": 2.28, "elapsed_time": "0:20:11", "remaining_time": "14:27:14", "throughput": 4986.65, "total_tokens": 6042432} +{"current_steps": 2795, "total_steps": 122600, "loss": 0.27, "lr": 1.139477977161501e-05, "epoch": 0.4559543230016313, "percentage": 2.28, "elapsed_time": "0:20:14", "remaining_time": "14:27:22", "throughput": 4986.53, "total_tokens": 6054304} +{"current_steps": 2800, "total_steps": 122600, "loss": 0.1915, "lr": 1.1415171288743882e-05, "epoch": 0.4567699836867863, "percentage": 2.28, "elapsed_time": "0:20:16", "remaining_time": "14:27:21", "throughput": 4986.54, "total_tokens": 6065312} +{"current_steps": 2805, "total_steps": 122600, "loss": 0.4966, "lr": 1.1435562805872757e-05, "epoch": 0.45758564437194127, "percentage": 2.29, "elapsed_time": "0:20:18", "remaining_time": "14:27:10", "throughput": 4986.51, "total_tokens": 6075072} +{"current_steps": 2810, "total_steps": 122600, "loss": 0.0717, "lr": 1.1455954323001631e-05, "epoch": 0.45840130505709625, "percentage": 2.29, "elapsed_time": "0:20:20", "remaining_time": "14:27:00", "throughput": 4986.51, "total_tokens": 6084992} +{"current_steps": 2815, "total_steps": 122600, "loss": 0.1337, "lr": 1.1476345840130507e-05, "epoch": 0.45921696574225124, "percentage": 2.3, "elapsed_time": "0:20:22", "remaining_time": "14:26:55", "throughput": 4986.46, "total_tokens": 6095424} +{"current_steps": 2820, "total_steps": 122600, "loss": 0.1333, "lr": 1.149673735725938e-05, "epoch": 0.4600326264274062, "percentage": 2.3, "elapsed_time": "0:20:24", "remaining_time": "14:27:01", "throughput": 4986.58, "total_tokens": 6107328} +{"current_steps": 2825, "total_steps": 122600, "loss": 0.0131, "lr": 1.1517128874388256e-05, "epoch": 0.46084828711256115, "percentage": 2.3, "elapsed_time": "0:20:26", "remaining_time": "14:26:56", "throughput": 4986.74, "total_tokens": 6118048} +{"current_steps": 2830, "total_steps": 122600, "loss": 0.4867, "lr": 1.153752039151713e-05, "epoch": 0.46166394779771613, "percentage": 2.31, "elapsed_time": "0:20:28", "remaining_time": "14:26:51", "throughput": 4986.72, "total_tokens": 6128512} +{"current_steps": 2835, "total_steps": 122600, "loss": 0.0464, "lr": 1.1557911908646004e-05, "epoch": 0.4624796084828711, "percentage": 2.31, "elapsed_time": "0:20:31", "remaining_time": "14:26:45", "throughput": 4986.64, "total_tokens": 6138720} +{"current_steps": 2840, "total_steps": 122600, "loss": 0.3125, "lr": 1.1578303425774877e-05, "epoch": 0.4632952691680261, "percentage": 2.32, "elapsed_time": "0:20:33", "remaining_time": "14:26:42", "throughput": 4986.78, "total_tokens": 6149600} +{"current_steps": 2845, "total_steps": 122600, "loss": 0.1762, "lr": 1.1598694942903753e-05, "epoch": 0.4641109298531811, "percentage": 2.32, "elapsed_time": "0:20:35", "remaining_time": "14:26:41", "throughput": 4986.77, "total_tokens": 6160608} +{"current_steps": 2850, "total_steps": 122600, "loss": 0.282, "lr": 1.1619086460032627e-05, "epoch": 0.46492659053833607, "percentage": 2.32, "elapsed_time": "0:20:37", "remaining_time": "14:26:43", "throughput": 4986.82, "total_tokens": 6171968} +{"current_steps": 2855, "total_steps": 122600, "loss": 0.1962, "lr": 1.1639477977161502e-05, "epoch": 0.46574225122349105, "percentage": 2.33, "elapsed_time": "0:20:39", "remaining_time": "14:26:45", "throughput": 4986.82, "total_tokens": 6183360} +{"current_steps": 2860, "total_steps": 122600, "loss": 0.0824, "lr": 1.1659869494290376e-05, "epoch": 0.466557911908646, "percentage": 2.33, "elapsed_time": "0:20:42", "remaining_time": "14:26:39", "throughput": 4986.82, "total_tokens": 6193664} +{"current_steps": 2865, "total_steps": 122600, "loss": 0.0409, "lr": 1.168026101141925e-05, "epoch": 0.46737357259380097, "percentage": 2.34, "elapsed_time": "0:20:44", "remaining_time": "14:26:35", "throughput": 4986.84, "total_tokens": 6204320} +{"current_steps": 2870, "total_steps": 122600, "loss": 0.3969, "lr": 1.1700652528548124e-05, "epoch": 0.46818923327895595, "percentage": 2.34, "elapsed_time": "0:20:46", "remaining_time": "14:26:28", "throughput": 4986.84, "total_tokens": 6214560} +{"current_steps": 2875, "total_steps": 122600, "loss": 0.3594, "lr": 1.1721044045677e-05, "epoch": 0.46900489396411094, "percentage": 2.35, "elapsed_time": "0:20:48", "remaining_time": "14:26:32", "throughput": 4986.91, "total_tokens": 6226176} +{"current_steps": 2880, "total_steps": 122600, "loss": 0.6178, "lr": 1.1741435562805873e-05, "epoch": 0.4698205546492659, "percentage": 2.35, "elapsed_time": "0:20:50", "remaining_time": "14:26:26", "throughput": 4987.04, "total_tokens": 6236768} +{"current_steps": 2885, "total_steps": 122600, "loss": 0.2086, "lr": 1.1761827079934749e-05, "epoch": 0.4706362153344209, "percentage": 2.35, "elapsed_time": "0:20:52", "remaining_time": "14:26:23", "throughput": 4987.01, "total_tokens": 6247424} +{"current_steps": 2890, "total_steps": 122600, "loss": 0.0575, "lr": 1.1782218597063622e-05, "epoch": 0.47145187601957583, "percentage": 2.36, "elapsed_time": "0:20:54", "remaining_time": "14:26:12", "throughput": 4987.06, "total_tokens": 6257280} +{"current_steps": 2895, "total_steps": 122600, "loss": 0.2357, "lr": 1.1802610114192498e-05, "epoch": 0.4722675367047308, "percentage": 2.36, "elapsed_time": "0:20:56", "remaining_time": "14:26:11", "throughput": 4987.0, "total_tokens": 6268160} +{"current_steps": 2900, "total_steps": 122600, "loss": 0.0907, "lr": 1.182300163132137e-05, "epoch": 0.4730831973898858, "percentage": 2.37, "elapsed_time": "0:20:59", "remaining_time": "14:26:08", "throughput": 4987.02, "total_tokens": 6278976} +{"current_steps": 2905, "total_steps": 122600, "loss": 0.2266, "lr": 1.1843393148450246e-05, "epoch": 0.4738988580750408, "percentage": 2.37, "elapsed_time": "0:21:01", "remaining_time": "14:26:08", "throughput": 4987.1, "total_tokens": 6290144} +{"current_steps": 2910, "total_steps": 122600, "loss": 0.1051, "lr": 1.186378466557912e-05, "epoch": 0.47471451876019577, "percentage": 2.37, "elapsed_time": "0:21:03", "remaining_time": "14:26:12", "throughput": 4987.14, "total_tokens": 6301760} +{"current_steps": 2915, "total_steps": 122600, "loss": 0.5611, "lr": 1.1884176182707995e-05, "epoch": 0.47553017944535075, "percentage": 2.38, "elapsed_time": "0:21:05", "remaining_time": "14:26:06", "throughput": 4987.38, "total_tokens": 6312416} +{"current_steps": 2920, "total_steps": 122600, "loss": 0.1318, "lr": 1.1904567699836869e-05, "epoch": 0.4763458401305057, "percentage": 2.38, "elapsed_time": "0:21:07", "remaining_time": "14:26:05", "throughput": 4987.49, "total_tokens": 6323488} +{"current_steps": 2925, "total_steps": 122600, "loss": 0.3946, "lr": 1.1924959216965744e-05, "epoch": 0.47716150081566067, "percentage": 2.39, "elapsed_time": "0:21:10", "remaining_time": "14:26:05", "throughput": 4987.37, "total_tokens": 6334496} +{"current_steps": 2930, "total_steps": 122600, "loss": 0.4419, "lr": 1.1945350734094616e-05, "epoch": 0.47797716150081565, "percentage": 2.39, "elapsed_time": "0:21:12", "remaining_time": "14:25:53", "throughput": 4987.59, "total_tokens": 6344320} +{"current_steps": 2935, "total_steps": 122600, "loss": 0.3277, "lr": 1.1965742251223492e-05, "epoch": 0.47879282218597063, "percentage": 2.39, "elapsed_time": "0:21:14", "remaining_time": "14:25:58", "throughput": 4987.45, "total_tokens": 6355904} +{"current_steps": 2940, "total_steps": 122600, "loss": 0.4008, "lr": 1.1986133768352366e-05, "epoch": 0.4796084828711256, "percentage": 2.4, "elapsed_time": "0:21:16", "remaining_time": "14:25:49", "throughput": 4987.6, "total_tokens": 6366016} +{"current_steps": 2945, "total_steps": 122600, "loss": 0.081, "lr": 1.2006525285481241e-05, "epoch": 0.4804241435562806, "percentage": 2.4, "elapsed_time": "0:21:18", "remaining_time": "14:25:35", "throughput": 4987.77, "total_tokens": 6375712} +{"current_steps": 2950, "total_steps": 122600, "loss": 0.1307, "lr": 1.2026916802610115e-05, "epoch": 0.4812398042414356, "percentage": 2.41, "elapsed_time": "0:21:20", "remaining_time": "14:25:35", "throughput": 4987.73, "total_tokens": 6386720} +{"current_steps": 2955, "total_steps": 122600, "loss": 0.1092, "lr": 1.2047308319738989e-05, "epoch": 0.4820554649265905, "percentage": 2.41, "elapsed_time": "0:21:22", "remaining_time": "14:25:32", "throughput": 4987.8, "total_tokens": 6397536} +{"current_steps": 2960, "total_steps": 122600, "loss": 0.2775, "lr": 1.2067699836867863e-05, "epoch": 0.4828711256117455, "percentage": 2.41, "elapsed_time": "0:21:24", "remaining_time": "14:25:29", "throughput": 4987.91, "total_tokens": 6408384} +{"current_steps": 2965, "total_steps": 122600, "loss": 0.1411, "lr": 1.2088091353996738e-05, "epoch": 0.4836867862969005, "percentage": 2.42, "elapsed_time": "0:21:27", "remaining_time": "14:25:40", "throughput": 4987.8, "total_tokens": 6420640} +{"current_steps": 2970, "total_steps": 122600, "loss": 0.208, "lr": 1.2108482871125612e-05, "epoch": 0.48450244698205547, "percentage": 2.42, "elapsed_time": "0:21:29", "remaining_time": "14:25:39", "throughput": 4987.82, "total_tokens": 6431680} +{"current_steps": 2975, "total_steps": 122600, "loss": 0.0776, "lr": 1.2128874388254486e-05, "epoch": 0.48531810766721045, "percentage": 2.43, "elapsed_time": "0:21:31", "remaining_time": "14:25:37", "throughput": 4987.72, "total_tokens": 6442368} +{"current_steps": 2980, "total_steps": 122600, "loss": 0.1199, "lr": 1.2149265905383361e-05, "epoch": 0.48613376835236544, "percentage": 2.43, "elapsed_time": "0:21:33", "remaining_time": "14:25:40", "throughput": 4987.66, "total_tokens": 6453856} +{"current_steps": 2985, "total_steps": 122600, "loss": 0.3692, "lr": 1.2169657422512235e-05, "epoch": 0.48694942903752036, "percentage": 2.43, "elapsed_time": "0:21:36", "remaining_time": "14:25:40", "throughput": 4987.49, "total_tokens": 6464640} +{"current_steps": 2990, "total_steps": 122600, "loss": 0.2179, "lr": 1.219004893964111e-05, "epoch": 0.48776508972267535, "percentage": 2.44, "elapsed_time": "0:21:38", "remaining_time": "14:25:36", "throughput": 4987.55, "total_tokens": 6475392} +{"current_steps": 2995, "total_steps": 122600, "loss": 0.1634, "lr": 1.2210440456769985e-05, "epoch": 0.48858075040783033, "percentage": 2.44, "elapsed_time": "0:21:40", "remaining_time": "14:25:40", "throughput": 4987.51, "total_tokens": 6486880} +{"current_steps": 3000, "total_steps": 122600, "loss": 0.14, "lr": 1.2230831973898858e-05, "epoch": 0.4893964110929853, "percentage": 2.45, "elapsed_time": "0:21:42", "remaining_time": "14:25:34", "throughput": 4987.52, "total_tokens": 6497216} +{"current_steps": 3005, "total_steps": 122600, "loss": 0.2846, "lr": 1.2251223491027732e-05, "epoch": 0.4902120717781403, "percentage": 2.45, "elapsed_time": "0:21:44", "remaining_time": "14:25:34", "throughput": 4987.48, "total_tokens": 6508320} +{"current_steps": 3010, "total_steps": 122600, "loss": 0.3147, "lr": 1.2271615008156608e-05, "epoch": 0.4910277324632953, "percentage": 2.46, "elapsed_time": "0:21:47", "remaining_time": "14:25:35", "throughput": 4987.49, "total_tokens": 6519520} +{"current_steps": 3015, "total_steps": 122600, "loss": 0.2018, "lr": 1.2292006525285482e-05, "epoch": 0.49184339314845027, "percentage": 2.46, "elapsed_time": "0:21:49", "remaining_time": "14:25:33", "throughput": 4987.4, "total_tokens": 6530240} +{"current_steps": 3020, "total_steps": 122600, "loss": 0.4027, "lr": 1.2312398042414357e-05, "epoch": 0.4926590538336052, "percentage": 2.46, "elapsed_time": "0:21:51", "remaining_time": "14:25:25", "throughput": 4987.27, "total_tokens": 6540192} +{"current_steps": 3025, "total_steps": 122600, "loss": 0.1055, "lr": 1.233278955954323e-05, "epoch": 0.4934747145187602, "percentage": 2.47, "elapsed_time": "0:21:53", "remaining_time": "14:25:15", "throughput": 4987.28, "total_tokens": 6550016} +{"current_steps": 3030, "total_steps": 122600, "loss": 0.1489, "lr": 1.2353181076672105e-05, "epoch": 0.49429037520391517, "percentage": 2.47, "elapsed_time": "0:21:55", "remaining_time": "14:25:10", "throughput": 4987.35, "total_tokens": 6560672} +{"current_steps": 3035, "total_steps": 122600, "loss": 0.0875, "lr": 1.2373572593800978e-05, "epoch": 0.49510603588907015, "percentage": 2.48, "elapsed_time": "0:21:57", "remaining_time": "14:25:10", "throughput": 4987.38, "total_tokens": 6571808} +{"current_steps": 3040, "total_steps": 122600, "loss": 0.3464, "lr": 1.2393964110929854e-05, "epoch": 0.49592169657422513, "percentage": 2.48, "elapsed_time": "0:21:59", "remaining_time": "14:25:08", "throughput": 4987.38, "total_tokens": 6582624} +{"current_steps": 3045, "total_steps": 122600, "loss": 0.3052, "lr": 1.2414355628058728e-05, "epoch": 0.4967373572593801, "percentage": 2.48, "elapsed_time": "0:22:02", "remaining_time": "14:25:20", "throughput": 4987.24, "total_tokens": 6595008} +{"current_steps": 3050, "total_steps": 122600, "loss": 0.1467, "lr": 1.2434747145187603e-05, "epoch": 0.49755301794453505, "percentage": 2.49, "elapsed_time": "0:22:04", "remaining_time": "14:25:27", "throughput": 4987.16, "total_tokens": 6606976} +{"current_steps": 3055, "total_steps": 122600, "loss": 0.1543, "lr": 1.2455138662316477e-05, "epoch": 0.49836867862969003, "percentage": 2.49, "elapsed_time": "0:22:06", "remaining_time": "14:25:24", "throughput": 4987.18, "total_tokens": 6617760} +{"current_steps": 3060, "total_steps": 122600, "loss": 0.1359, "lr": 1.2475530179445351e-05, "epoch": 0.499184339314845, "percentage": 2.5, "elapsed_time": "0:22:09", "remaining_time": "14:25:24", "throughput": 4987.24, "total_tokens": 6628896} +{"current_steps": 3065, "total_steps": 122600, "loss": 0.3561, "lr": 1.2495921696574225e-05, "epoch": 0.5, "percentage": 2.5, "elapsed_time": "0:22:11", "remaining_time": "14:25:20", "throughput": 4987.16, "total_tokens": 6639424} +{"current_steps": 3070, "total_steps": 122600, "loss": 0.302, "lr": 1.2516313213703102e-05, "epoch": 0.5008156606851549, "percentage": 2.5, "elapsed_time": "0:22:13", "remaining_time": "14:25:11", "throughput": 4987.13, "total_tokens": 6649280} +{"current_steps": 3075, "total_steps": 122600, "loss": 0.1157, "lr": 1.2536704730831974e-05, "epoch": 0.50163132137031, "percentage": 2.51, "elapsed_time": "0:22:15", "remaining_time": "14:25:00", "throughput": 4987.17, "total_tokens": 6659008} +{"current_steps": 3080, "total_steps": 122600, "loss": 0.1948, "lr": 1.2557096247960848e-05, "epoch": 0.5024469820554649, "percentage": 2.51, "elapsed_time": "0:22:17", "remaining_time": "14:24:51", "throughput": 4987.38, "total_tokens": 6669312} +{"current_steps": 3085, "total_steps": 122600, "loss": 0.4479, "lr": 1.2577487765089723e-05, "epoch": 0.5032626427406199, "percentage": 2.52, "elapsed_time": "0:22:19", "remaining_time": "14:24:49", "throughput": 4987.28, "total_tokens": 6679968} +{"current_steps": 3090, "total_steps": 122600, "loss": 0.26, "lr": 1.2597879282218597e-05, "epoch": 0.5040783034257749, "percentage": 2.52, "elapsed_time": "0:22:21", "remaining_time": "14:24:37", "throughput": 4987.37, "total_tokens": 6689728} +{"current_steps": 3095, "total_steps": 122600, "loss": 0.6018, "lr": 1.2618270799347473e-05, "epoch": 0.5048939641109299, "percentage": 2.52, "elapsed_time": "0:22:23", "remaining_time": "14:24:34", "throughput": 4987.44, "total_tokens": 6700448} +{"current_steps": 3100, "total_steps": 122600, "loss": 0.1564, "lr": 1.2638662316476347e-05, "epoch": 0.5057096247960848, "percentage": 2.53, "elapsed_time": "0:22:25", "remaining_time": "14:24:34", "throughput": 4987.34, "total_tokens": 6711424} +{"current_steps": 3105, "total_steps": 122600, "loss": 0.0642, "lr": 1.2659053833605219e-05, "epoch": 0.5065252854812398, "percentage": 2.53, "elapsed_time": "0:22:27", "remaining_time": "14:24:36", "throughput": 4987.29, "total_tokens": 6722752} +{"current_steps": 3110, "total_steps": 122600, "loss": 0.4945, "lr": 1.2679445350734096e-05, "epoch": 0.5073409461663948, "percentage": 2.54, "elapsed_time": "0:22:30", "remaining_time": "14:24:38", "throughput": 4987.25, "total_tokens": 6734080} +{"current_steps": 3115, "total_steps": 122600, "loss": 0.0787, "lr": 1.2699836867862968e-05, "epoch": 0.5081566068515497, "percentage": 2.54, "elapsed_time": "0:22:32", "remaining_time": "14:24:34", "throughput": 4987.28, "total_tokens": 6744672} +{"current_steps": 3120, "total_steps": 122600, "loss": 0.2613, "lr": 1.2720228384991845e-05, "epoch": 0.5089722675367048, "percentage": 2.54, "elapsed_time": "0:22:34", "remaining_time": "14:24:29", "throughput": 4987.22, "total_tokens": 6755104} +{"current_steps": 3125, "total_steps": 122600, "loss": 0.2699, "lr": 1.2740619902120717e-05, "epoch": 0.5097879282218597, "percentage": 2.55, "elapsed_time": "0:22:36", "remaining_time": "14:24:37", "throughput": 4987.17, "total_tokens": 6767168} +{"current_steps": 3130, "total_steps": 122600, "loss": 0.2118, "lr": 1.2761011419249595e-05, "epoch": 0.5106035889070146, "percentage": 2.55, "elapsed_time": "0:22:38", "remaining_time": "14:24:30", "throughput": 4987.25, "total_tokens": 6777472} +{"current_steps": 3135, "total_steps": 122600, "loss": 0.3344, "lr": 1.2781402936378467e-05, "epoch": 0.5114192495921697, "percentage": 2.56, "elapsed_time": "0:22:41", "remaining_time": "14:24:24", "throughput": 4987.2, "total_tokens": 6787776} +{"current_steps": 3140, "total_steps": 122600, "loss": 0.3943, "lr": 1.280179445350734e-05, "epoch": 0.5122349102773246, "percentage": 2.56, "elapsed_time": "0:22:43", "remaining_time": "14:24:25", "throughput": 4987.27, "total_tokens": 6799008} +{"current_steps": 3145, "total_steps": 122600, "loss": 0.1362, "lr": 1.2822185970636216e-05, "epoch": 0.5130505709624796, "percentage": 2.57, "elapsed_time": "0:22:45", "remaining_time": "14:24:20", "throughput": 4987.19, "total_tokens": 6809440} +{"current_steps": 3150, "total_steps": 122600, "loss": 0.0624, "lr": 1.284257748776509e-05, "epoch": 0.5138662316476346, "percentage": 2.57, "elapsed_time": "0:22:47", "remaining_time": "14:24:12", "throughput": 4987.22, "total_tokens": 6819456} +{"current_steps": 3155, "total_steps": 122600, "loss": 0.1007, "lr": 1.2862969004893965e-05, "epoch": 0.5146818923327896, "percentage": 2.57, "elapsed_time": "0:22:49", "remaining_time": "14:24:00", "throughput": 4987.4, "total_tokens": 6829312} +{"current_steps": 3160, "total_steps": 122600, "loss": 0.4687, "lr": 1.288336052202284e-05, "epoch": 0.5154975530179445, "percentage": 2.58, "elapsed_time": "0:22:51", "remaining_time": "14:23:52", "throughput": 4987.5, "total_tokens": 6839456} +{"current_steps": 3165, "total_steps": 122600, "loss": 0.3085, "lr": 1.2903752039151715e-05, "epoch": 0.5163132137030995, "percentage": 2.58, "elapsed_time": "0:22:53", "remaining_time": "14:23:54", "throughput": 4987.42, "total_tokens": 6850752} +{"current_steps": 3170, "total_steps": 122600, "loss": 0.1192, "lr": 1.2924143556280589e-05, "epoch": 0.5171288743882545, "percentage": 2.59, "elapsed_time": "0:22:55", "remaining_time": "14:23:57", "throughput": 4987.37, "total_tokens": 6862144} +{"current_steps": 3175, "total_steps": 122600, "loss": 0.2326, "lr": 1.294453507340946e-05, "epoch": 0.5179445350734094, "percentage": 2.59, "elapsed_time": "0:22:58", "remaining_time": "14:23:53", "throughput": 4987.34, "total_tokens": 6872704} +{"current_steps": 3180, "total_steps": 122600, "loss": 0.1858, "lr": 1.2964926590538336e-05, "epoch": 0.5187601957585645, "percentage": 2.59, "elapsed_time": "0:23:00", "remaining_time": "14:23:50", "throughput": 4987.22, "total_tokens": 6883232} +{"current_steps": 3185, "total_steps": 122600, "loss": 0.3418, "lr": 1.298531810766721e-05, "epoch": 0.5195758564437194, "percentage": 2.6, "elapsed_time": "0:23:02", "remaining_time": "14:23:50", "throughput": 4987.18, "total_tokens": 6894368} +{"current_steps": 3190, "total_steps": 122600, "loss": 0.212, "lr": 1.3005709624796086e-05, "epoch": 0.5203915171288744, "percentage": 2.6, "elapsed_time": "0:23:04", "remaining_time": "14:23:59", "throughput": 4987.0, "total_tokens": 6906336} +{"current_steps": 3195, "total_steps": 122600, "loss": 0.1273, "lr": 1.302610114192496e-05, "epoch": 0.5212071778140294, "percentage": 2.61, "elapsed_time": "0:23:07", "remaining_time": "14:23:58", "throughput": 4987.06, "total_tokens": 6917440} +{"current_steps": 3200, "total_steps": 122600, "loss": 0.4718, "lr": 1.3046492659053835e-05, "epoch": 0.5220228384991843, "percentage": 2.61, "elapsed_time": "0:23:09", "remaining_time": "14:23:59", "throughput": 4987.1, "total_tokens": 6928736} +{"current_steps": 3205, "total_steps": 122600, "loss": 0.2197, "lr": 1.3066884176182709e-05, "epoch": 0.5228384991843393, "percentage": 2.61, "elapsed_time": "0:23:11", "remaining_time": "14:23:56", "throughput": 4987.11, "total_tokens": 6939488} +{"current_steps": 3210, "total_steps": 122600, "loss": 0.046, "lr": 1.3087275693311583e-05, "epoch": 0.5236541598694943, "percentage": 2.62, "elapsed_time": "0:23:13", "remaining_time": "14:23:52", "throughput": 4987.06, "total_tokens": 6950016} +{"current_steps": 3215, "total_steps": 122600, "loss": 0.3526, "lr": 1.3107667210440458e-05, "epoch": 0.5244698205546493, "percentage": 2.62, "elapsed_time": "0:23:15", "remaining_time": "14:23:53", "throughput": 4987.12, "total_tokens": 6961280} +{"current_steps": 3220, "total_steps": 122600, "loss": 0.0987, "lr": 1.3128058727569332e-05, "epoch": 0.5252854812398042, "percentage": 2.63, "elapsed_time": "0:23:17", "remaining_time": "14:23:45", "throughput": 4987.16, "total_tokens": 6971360} +{"current_steps": 3225, "total_steps": 122600, "loss": 0.52, "lr": 1.3148450244698207e-05, "epoch": 0.5261011419249593, "percentage": 2.63, "elapsed_time": "0:23:20", "remaining_time": "14:23:45", "throughput": 4987.15, "total_tokens": 6982528} +{"current_steps": 3230, "total_steps": 122600, "loss": 0.0967, "lr": 1.316884176182708e-05, "epoch": 0.5269168026101142, "percentage": 2.63, "elapsed_time": "0:23:22", "remaining_time": "14:23:38", "throughput": 4987.11, "total_tokens": 6992704} +{"current_steps": 3235, "total_steps": 122600, "loss": 0.3483, "lr": 1.3189233278955953e-05, "epoch": 0.5277324632952691, "percentage": 2.64, "elapsed_time": "0:23:24", "remaining_time": "14:23:32", "throughput": 4987.17, "total_tokens": 7003072} +{"current_steps": 3240, "total_steps": 122600, "loss": 0.1927, "lr": 1.3209624796084829e-05, "epoch": 0.5285481239804242, "percentage": 2.64, "elapsed_time": "0:23:26", "remaining_time": "14:23:30", "throughput": 4987.05, "total_tokens": 7013728} +{"current_steps": 3245, "total_steps": 122600, "loss": 0.1035, "lr": 1.3230016313213703e-05, "epoch": 0.5293637846655791, "percentage": 2.65, "elapsed_time": "0:23:28", "remaining_time": "14:23:25", "throughput": 4987.14, "total_tokens": 7024256} +{"current_steps": 3250, "total_steps": 122600, "loss": 0.4672, "lr": 1.3250407830342578e-05, "epoch": 0.5301794453507341, "percentage": 2.65, "elapsed_time": "0:23:30", "remaining_time": "14:23:21", "throughput": 4987.06, "total_tokens": 7034688} +{"current_steps": 3255, "total_steps": 122600, "loss": 0.1605, "lr": 1.3270799347471452e-05, "epoch": 0.5309951060358891, "percentage": 2.65, "elapsed_time": "0:23:32", "remaining_time": "14:23:22", "throughput": 4987.13, "total_tokens": 7046080} +{"current_steps": 3260, "total_steps": 122600, "loss": 0.2109, "lr": 1.3291190864600328e-05, "epoch": 0.531810766721044, "percentage": 2.66, "elapsed_time": "0:23:34", "remaining_time": "14:23:13", "throughput": 4987.17, "total_tokens": 7056032} +{"current_steps": 3265, "total_steps": 122600, "loss": 0.2165, "lr": 1.3311582381729201e-05, "epoch": 0.532626427406199, "percentage": 2.66, "elapsed_time": "0:23:37", "remaining_time": "14:23:11", "throughput": 4987.16, "total_tokens": 7066880} +{"current_steps": 3270, "total_steps": 122600, "loss": 0.374, "lr": 1.3331973898858075e-05, "epoch": 0.533442088091354, "percentage": 2.67, "elapsed_time": "0:23:39", "remaining_time": "14:23:09", "throughput": 4987.11, "total_tokens": 7077664} +{"current_steps": 3275, "total_steps": 122600, "loss": 0.1719, "lr": 1.335236541598695e-05, "epoch": 0.534257748776509, "percentage": 2.67, "elapsed_time": "0:23:41", "remaining_time": "14:23:10", "throughput": 4987.08, "total_tokens": 7088928} +{"current_steps": 3280, "total_steps": 122600, "loss": 0.2315, "lr": 1.3372756933115823e-05, "epoch": 0.5350734094616639, "percentage": 2.68, "elapsed_time": "0:23:43", "remaining_time": "14:23:17", "throughput": 4987.02, "total_tokens": 7100800} +{"current_steps": 3285, "total_steps": 122600, "loss": 0.1882, "lr": 1.33931484502447e-05, "epoch": 0.535889070146819, "percentage": 2.68, "elapsed_time": "0:23:46", "remaining_time": "14:23:18", "throughput": 4987.04, "total_tokens": 7112160} +{"current_steps": 3290, "total_steps": 122600, "loss": 0.2084, "lr": 1.3413539967373572e-05, "epoch": 0.5367047308319739, "percentage": 2.68, "elapsed_time": "0:23:48", "remaining_time": "14:23:14", "throughput": 4987.1, "total_tokens": 7122848} +{"current_steps": 3295, "total_steps": 122600, "loss": 0.2348, "lr": 1.343393148450245e-05, "epoch": 0.5375203915171288, "percentage": 2.69, "elapsed_time": "0:23:50", "remaining_time": "14:23:04", "throughput": 4987.24, "total_tokens": 7132800} +{"current_steps": 3300, "total_steps": 122600, "loss": 0.142, "lr": 1.3454323001631322e-05, "epoch": 0.5383360522022839, "percentage": 2.69, "elapsed_time": "0:23:52", "remaining_time": "14:23:06", "throughput": 4987.18, "total_tokens": 7144064} +{"current_steps": 3305, "total_steps": 122600, "loss": 0.2005, "lr": 1.3474714518760195e-05, "epoch": 0.5391517128874388, "percentage": 2.7, "elapsed_time": "0:23:54", "remaining_time": "14:23:10", "throughput": 4987.17, "total_tokens": 7155744} +{"current_steps": 3310, "total_steps": 122600, "loss": 0.0384, "lr": 1.3495106035889071e-05, "epoch": 0.5399673735725938, "percentage": 2.7, "elapsed_time": "0:23:56", "remaining_time": "14:23:07", "throughput": 4987.13, "total_tokens": 7166336} +{"current_steps": 3315, "total_steps": 122600, "loss": 0.287, "lr": 1.3515497553017945e-05, "epoch": 0.5407830342577488, "percentage": 2.7, "elapsed_time": "0:23:59", "remaining_time": "14:23:02", "throughput": 4987.16, "total_tokens": 7176832} +{"current_steps": 3320, "total_steps": 122600, "loss": 0.2365, "lr": 1.353588907014682e-05, "epoch": 0.5415986949429038, "percentage": 2.71, "elapsed_time": "0:24:01", "remaining_time": "14:22:59", "throughput": 4987.17, "total_tokens": 7187616} +{"current_steps": 3325, "total_steps": 122600, "loss": 0.205, "lr": 1.3556280587275694e-05, "epoch": 0.5424143556280587, "percentage": 2.71, "elapsed_time": "0:24:03", "remaining_time": "14:22:55", "throughput": 4987.18, "total_tokens": 7198144} +{"current_steps": 3330, "total_steps": 122600, "loss": 0.1434, "lr": 1.357667210440457e-05, "epoch": 0.5432300163132137, "percentage": 2.72, "elapsed_time": "0:24:05", "remaining_time": "14:22:51", "throughput": 4987.34, "total_tokens": 7208960} +{"current_steps": 3335, "total_steps": 122600, "loss": 0.4265, "lr": 1.3597063621533443e-05, "epoch": 0.5440456769983687, "percentage": 2.72, "elapsed_time": "0:24:07", "remaining_time": "14:22:50", "throughput": 4987.41, "total_tokens": 7220064} +{"current_steps": 3340, "total_steps": 122600, "loss": 0.2715, "lr": 1.3617455138662316e-05, "epoch": 0.5448613376835236, "percentage": 2.72, "elapsed_time": "0:24:09", "remaining_time": "14:22:50", "throughput": 4987.32, "total_tokens": 7231008} +{"current_steps": 3345, "total_steps": 122600, "loss": 0.4378, "lr": 1.3637846655791193e-05, "epoch": 0.5456769983686787, "percentage": 2.73, "elapsed_time": "0:24:12", "remaining_time": "14:22:50", "throughput": 4987.34, "total_tokens": 7242144} +{"current_steps": 3350, "total_steps": 122600, "loss": 0.3236, "lr": 1.3658238172920065e-05, "epoch": 0.5464926590538336, "percentage": 2.73, "elapsed_time": "0:24:14", "remaining_time": "14:22:44", "throughput": 4987.34, "total_tokens": 7252448} +{"current_steps": 3355, "total_steps": 122600, "loss": 0.181, "lr": 1.3678629690048942e-05, "epoch": 0.5473083197389886, "percentage": 2.74, "elapsed_time": "0:24:16", "remaining_time": "14:22:31", "throughput": 4987.42, "total_tokens": 7261856} +{"current_steps": 3360, "total_steps": 122600, "loss": 0.1057, "lr": 1.3699021207177814e-05, "epoch": 0.5481239804241436, "percentage": 2.74, "elapsed_time": "0:24:18", "remaining_time": "14:22:29", "throughput": 4987.41, "total_tokens": 7272800} +{"current_steps": 3365, "total_steps": 122600, "loss": 0.2415, "lr": 1.3719412724306688e-05, "epoch": 0.5489396411092985, "percentage": 2.74, "elapsed_time": "0:24:20", "remaining_time": "14:22:29", "throughput": 4987.35, "total_tokens": 7283808} +{"current_steps": 3370, "total_steps": 122600, "loss": 0.0459, "lr": 1.3739804241435564e-05, "epoch": 0.5497553017944535, "percentage": 2.75, "elapsed_time": "0:24:22", "remaining_time": "14:22:29", "throughput": 4987.42, "total_tokens": 7294976} +{"current_steps": 3375, "total_steps": 122600, "loss": 0.1956, "lr": 1.3760195758564437e-05, "epoch": 0.5505709624796085, "percentage": 2.75, "elapsed_time": "0:24:25", "remaining_time": "14:22:33", "throughput": 4987.35, "total_tokens": 7306560} +{"current_steps": 3380, "total_steps": 122600, "loss": 0.0288, "lr": 1.3780587275693313e-05, "epoch": 0.5513866231647635, "percentage": 2.76, "elapsed_time": "0:24:27", "remaining_time": "14:22:33", "throughput": 4987.26, "total_tokens": 7317600} +{"current_steps": 3385, "total_steps": 122600, "loss": 0.104, "lr": 1.3800978792822187e-05, "epoch": 0.5522022838499184, "percentage": 2.76, "elapsed_time": "0:24:29", "remaining_time": "14:22:44", "throughput": 4987.2, "total_tokens": 7330144} +{"current_steps": 3390, "total_steps": 122600, "loss": 0.2228, "lr": 1.3821370309951062e-05, "epoch": 0.5530179445350734, "percentage": 2.77, "elapsed_time": "0:24:32", "remaining_time": "14:22:44", "throughput": 4987.14, "total_tokens": 7341248} +{"current_steps": 3395, "total_steps": 122600, "loss": 0.2886, "lr": 1.3841761827079936e-05, "epoch": 0.5538336052202284, "percentage": 2.77, "elapsed_time": "0:24:34", "remaining_time": "14:22:36", "throughput": 4987.12, "total_tokens": 7351200} +{"current_steps": 3400, "total_steps": 122600, "loss": 0.04, "lr": 1.3862153344208808e-05, "epoch": 0.5546492659053833, "percentage": 2.77, "elapsed_time": "0:24:36", "remaining_time": "14:22:31", "throughput": 4987.17, "total_tokens": 7361792} +{"current_steps": 3405, "total_steps": 122600, "loss": 0.1777, "lr": 1.3882544861337685e-05, "epoch": 0.5554649265905384, "percentage": 2.78, "elapsed_time": "0:24:38", "remaining_time": "14:22:26", "throughput": 4987.19, "total_tokens": 7372160} +{"current_steps": 3410, "total_steps": 122600, "loss": 0.0734, "lr": 1.3902936378466558e-05, "epoch": 0.5562805872756933, "percentage": 2.78, "elapsed_time": "0:24:40", "remaining_time": "14:22:11", "throughput": 4987.3, "total_tokens": 7381408} +{"current_steps": 3415, "total_steps": 122600, "loss": 0.2951, "lr": 1.3923327895595433e-05, "epoch": 0.5570962479608483, "percentage": 2.79, "elapsed_time": "0:24:42", "remaining_time": "14:22:12", "throughput": 4987.26, "total_tokens": 7392512} +{"current_steps": 3420, "total_steps": 122600, "loss": 0.277, "lr": 1.3943719412724307e-05, "epoch": 0.5579119086460033, "percentage": 2.79, "elapsed_time": "0:24:44", "remaining_time": "14:22:16", "throughput": 4987.2, "total_tokens": 7404192} +{"current_steps": 3425, "total_steps": 122600, "loss": 0.2104, "lr": 1.3964110929853182e-05, "epoch": 0.5587275693311582, "percentage": 2.79, "elapsed_time": "0:24:46", "remaining_time": "14:22:14", "throughput": 4987.16, "total_tokens": 7415008} +{"current_steps": 3430, "total_steps": 122600, "loss": 0.1257, "lr": 1.3984502446982056e-05, "epoch": 0.5595432300163132, "percentage": 2.8, "elapsed_time": "0:24:48", "remaining_time": "14:22:08", "throughput": 4987.09, "total_tokens": 7425088} +{"current_steps": 3435, "total_steps": 122600, "loss": 0.3503, "lr": 1.400489396411093e-05, "epoch": 0.5603588907014682, "percentage": 2.8, "elapsed_time": "0:24:51", "remaining_time": "14:22:11", "throughput": 4987.0, "total_tokens": 7436608} +{"current_steps": 3440, "total_steps": 122600, "loss": 0.2086, "lr": 1.4025285481239806e-05, "epoch": 0.5611745513866232, "percentage": 2.81, "elapsed_time": "0:24:53", "remaining_time": "14:22:04", "throughput": 4987.05, "total_tokens": 7446784} +{"current_steps": 3445, "total_steps": 122600, "loss": 0.2149, "lr": 1.404567699836868e-05, "epoch": 0.5619902120717781, "percentage": 2.81, "elapsed_time": "0:24:55", "remaining_time": "14:21:55", "throughput": 4987.09, "total_tokens": 7456640} +{"current_steps": 3450, "total_steps": 122600, "loss": 0.2954, "lr": 1.4066068515497555e-05, "epoch": 0.5628058727569332, "percentage": 2.81, "elapsed_time": "0:24:57", "remaining_time": "14:21:56", "throughput": 4987.17, "total_tokens": 7468096} +{"current_steps": 3455, "total_steps": 122600, "loss": 0.2578, "lr": 1.4086460032626429e-05, "epoch": 0.5636215334420881, "percentage": 2.82, "elapsed_time": "0:24:59", "remaining_time": "14:22:02", "throughput": 4987.15, "total_tokens": 7480096} +{"current_steps": 3460, "total_steps": 122600, "loss": 0.1368, "lr": 1.4106851549755301e-05, "epoch": 0.564437194127243, "percentage": 2.82, "elapsed_time": "0:25:02", "remaining_time": "14:22:01", "throughput": 4987.17, "total_tokens": 7491136} +{"current_steps": 3465, "total_steps": 122600, "loss": 0.0962, "lr": 1.4127243066884176e-05, "epoch": 0.5652528548123981, "percentage": 2.83, "elapsed_time": "0:25:04", "remaining_time": "14:22:02", "throughput": 4987.1, "total_tokens": 7502304} +{"current_steps": 3470, "total_steps": 122600, "loss": 0.1592, "lr": 1.414763458401305e-05, "epoch": 0.566068515497553, "percentage": 2.83, "elapsed_time": "0:25:06", "remaining_time": "14:21:58", "throughput": 4987.18, "total_tokens": 7512928} +{"current_steps": 3475, "total_steps": 122600, "loss": 0.2737, "lr": 1.4168026101141926e-05, "epoch": 0.566884176182708, "percentage": 2.83, "elapsed_time": "0:25:08", "remaining_time": "14:21:56", "throughput": 4987.22, "total_tokens": 7523904} +{"current_steps": 3480, "total_steps": 122600, "loss": 0.4419, "lr": 1.41884176182708e-05, "epoch": 0.567699836867863, "percentage": 2.84, "elapsed_time": "0:25:10", "remaining_time": "14:21:51", "throughput": 4987.33, "total_tokens": 7534496} +{"current_steps": 3485, "total_steps": 122600, "loss": 0.4877, "lr": 1.4208809135399675e-05, "epoch": 0.5685154975530179, "percentage": 2.84, "elapsed_time": "0:25:12", "remaining_time": "14:21:48", "throughput": 4987.35, "total_tokens": 7545120} +{"current_steps": 3490, "total_steps": 122600, "loss": 0.1305, "lr": 1.4229200652528549e-05, "epoch": 0.5693311582381729, "percentage": 2.85, "elapsed_time": "0:25:14", "remaining_time": "14:21:44", "throughput": 4987.34, "total_tokens": 7555712} +{"current_steps": 3495, "total_steps": 122600, "loss": 0.0639, "lr": 1.4249592169657423e-05, "epoch": 0.5701468189233279, "percentage": 2.85, "elapsed_time": "0:25:17", "remaining_time": "14:21:47", "throughput": 4987.28, "total_tokens": 7567200} +{"current_steps": 3500, "total_steps": 122600, "loss": 0.308, "lr": 1.4269983686786298e-05, "epoch": 0.5709624796084829, "percentage": 2.85, "elapsed_time": "0:25:19", "remaining_time": "14:21:48", "throughput": 4987.28, "total_tokens": 7578464} +{"current_steps": 3505, "total_steps": 122600, "loss": 0.2254, "lr": 1.429037520391517e-05, "epoch": 0.5717781402936378, "percentage": 2.86, "elapsed_time": "0:25:21", "remaining_time": "14:21:39", "throughput": 4987.26, "total_tokens": 7588256} +{"current_steps": 3510, "total_steps": 122600, "loss": 0.3492, "lr": 1.4310766721044048e-05, "epoch": 0.5725938009787929, "percentage": 2.86, "elapsed_time": "0:25:23", "remaining_time": "14:21:35", "throughput": 4987.23, "total_tokens": 7598848} +{"current_steps": 3515, "total_steps": 122600, "loss": 0.1528, "lr": 1.433115823817292e-05, "epoch": 0.5734094616639478, "percentage": 2.87, "elapsed_time": "0:25:25", "remaining_time": "14:21:33", "throughput": 4987.29, "total_tokens": 7609696} +{"current_steps": 3520, "total_steps": 122600, "loss": 0.0893, "lr": 1.4351549755301797e-05, "epoch": 0.5742251223491027, "percentage": 2.87, "elapsed_time": "0:25:28", "remaining_time": "14:21:33", "throughput": 4987.31, "total_tokens": 7620864} +{"current_steps": 3525, "total_steps": 122600, "loss": 0.0906, "lr": 1.4371941272430669e-05, "epoch": 0.5750407830342578, "percentage": 2.88, "elapsed_time": "0:25:30", "remaining_time": "14:21:28", "throughput": 4987.35, "total_tokens": 7631392} +{"current_steps": 3530, "total_steps": 122600, "loss": 0.1368, "lr": 1.4392332789559543e-05, "epoch": 0.5758564437194127, "percentage": 2.88, "elapsed_time": "0:25:32", "remaining_time": "14:21:34", "throughput": 4987.27, "total_tokens": 7643232} +{"current_steps": 3535, "total_steps": 122600, "loss": 0.2441, "lr": 1.4412724306688418e-05, "epoch": 0.5766721044045677, "percentage": 2.88, "elapsed_time": "0:25:34", "remaining_time": "14:21:38", "throughput": 4987.25, "total_tokens": 7654944} +{"current_steps": 3540, "total_steps": 122600, "loss": 0.121, "lr": 1.4433115823817292e-05, "epoch": 0.5774877650897227, "percentage": 2.89, "elapsed_time": "0:25:37", "remaining_time": "14:21:35", "throughput": 4987.26, "total_tokens": 7665760} +{"current_steps": 3545, "total_steps": 122600, "loss": 0.0997, "lr": 1.4453507340946168e-05, "epoch": 0.5783034257748777, "percentage": 2.89, "elapsed_time": "0:25:39", "remaining_time": "14:21:33", "throughput": 4987.23, "total_tokens": 7676576} +{"current_steps": 3550, "total_steps": 122600, "loss": 0.369, "lr": 1.4473898858075042e-05, "epoch": 0.5791190864600326, "percentage": 2.9, "elapsed_time": "0:25:41", "remaining_time": "14:21:29", "throughput": 4987.21, "total_tokens": 7687104} +{"current_steps": 3555, "total_steps": 122600, "loss": 0.1137, "lr": 1.4494290375203917e-05, "epoch": 0.5799347471451876, "percentage": 2.9, "elapsed_time": "0:25:43", "remaining_time": "14:21:29", "throughput": 4987.14, "total_tokens": 7698080} +{"current_steps": 3560, "total_steps": 122600, "loss": 0.2795, "lr": 1.4514681892332791e-05, "epoch": 0.5807504078303426, "percentage": 2.9, "elapsed_time": "0:25:45", "remaining_time": "14:21:33", "throughput": 4987.06, "total_tokens": 7709632} +{"current_steps": 3565, "total_steps": 122600, "loss": 0.0711, "lr": 1.4535073409461663e-05, "epoch": 0.5815660685154975, "percentage": 2.91, "elapsed_time": "0:25:47", "remaining_time": "14:21:26", "throughput": 4987.15, "total_tokens": 7719936} +{"current_steps": 3570, "total_steps": 122600, "loss": 0.0991, "lr": 1.455546492659054e-05, "epoch": 0.5823817292006526, "percentage": 2.91, "elapsed_time": "0:25:50", "remaining_time": "14:21:20", "throughput": 4987.1, "total_tokens": 7730080} +{"current_steps": 3575, "total_steps": 122600, "loss": 0.1623, "lr": 1.4575856443719412e-05, "epoch": 0.5831973898858075, "percentage": 2.92, "elapsed_time": "0:25:52", "remaining_time": "14:21:16", "throughput": 4987.07, "total_tokens": 7740576} +{"current_steps": 3580, "total_steps": 122600, "loss": 0.2797, "lr": 1.459624796084829e-05, "epoch": 0.5840130505709625, "percentage": 2.92, "elapsed_time": "0:25:54", "remaining_time": "14:21:11", "throughput": 4987.07, "total_tokens": 7751040} +{"current_steps": 3585, "total_steps": 122600, "loss": 0.0735, "lr": 1.4616639477977162e-05, "epoch": 0.5848287112561175, "percentage": 2.92, "elapsed_time": "0:25:56", "remaining_time": "14:21:02", "throughput": 4987.05, "total_tokens": 7760768} +{"current_steps": 3590, "total_steps": 122600, "loss": 0.0824, "lr": 1.4637030995106035e-05, "epoch": 0.5856443719412724, "percentage": 2.93, "elapsed_time": "0:25:58", "remaining_time": "14:21:00", "throughput": 4987.06, "total_tokens": 7771680} +{"current_steps": 3595, "total_steps": 122600, "loss": 0.1187, "lr": 1.4657422512234911e-05, "epoch": 0.5864600326264274, "percentage": 2.93, "elapsed_time": "0:26:00", "remaining_time": "14:21:02", "throughput": 4987.04, "total_tokens": 7783072} +{"current_steps": 3600, "total_steps": 122600, "loss": 0.1112, "lr": 1.4677814029363785e-05, "epoch": 0.5872756933115824, "percentage": 2.94, "elapsed_time": "0:26:02", "remaining_time": "14:20:51", "throughput": 4987.04, "total_tokens": 7792608} +{"current_steps": 3605, "total_steps": 122600, "loss": 0.2973, "lr": 1.469820554649266e-05, "epoch": 0.5880913539967374, "percentage": 2.94, "elapsed_time": "0:26:04", "remaining_time": "14:20:52", "throughput": 4986.99, "total_tokens": 7803744} +{"current_steps": 3610, "total_steps": 122600, "loss": 0.1352, "lr": 1.4718597063621534e-05, "epoch": 0.5889070146818923, "percentage": 2.94, "elapsed_time": "0:26:07", "remaining_time": "14:20:52", "throughput": 4987.01, "total_tokens": 7815008} +{"current_steps": 3615, "total_steps": 122600, "loss": 0.3407, "lr": 1.473898858075041e-05, "epoch": 0.5897226753670473, "percentage": 2.95, "elapsed_time": "0:26:09", "remaining_time": "14:20:49", "throughput": 4986.93, "total_tokens": 7825536} +{"current_steps": 3620, "total_steps": 122600, "loss": 0.1972, "lr": 1.4759380097879284e-05, "epoch": 0.5905383360522023, "percentage": 2.95, "elapsed_time": "0:26:11", "remaining_time": "14:20:44", "throughput": 4987.08, "total_tokens": 7836160} +{"current_steps": 3625, "total_steps": 122600, "loss": 0.0973, "lr": 1.4779771615008156e-05, "epoch": 0.5913539967373572, "percentage": 2.96, "elapsed_time": "0:26:13", "remaining_time": "14:20:54", "throughput": 4987.08, "total_tokens": 7848864} +{"current_steps": 3630, "total_steps": 122600, "loss": 0.1583, "lr": 1.4800163132137033e-05, "epoch": 0.5921696574225123, "percentage": 2.96, "elapsed_time": "0:26:15", "remaining_time": "14:20:50", "throughput": 4987.14, "total_tokens": 7859488} +{"current_steps": 3635, "total_steps": 122600, "loss": 0.1804, "lr": 1.4820554649265905e-05, "epoch": 0.5929853181076672, "percentage": 2.96, "elapsed_time": "0:26:17", "remaining_time": "14:20:43", "throughput": 4987.16, "total_tokens": 7869600} +{"current_steps": 3640, "total_steps": 122600, "loss": 0.2618, "lr": 1.484094616639478e-05, "epoch": 0.5938009787928222, "percentage": 2.97, "elapsed_time": "0:26:20", "remaining_time": "14:20:36", "throughput": 4987.2, "total_tokens": 7879840} +{"current_steps": 3645, "total_steps": 122600, "loss": 0.102, "lr": 1.4861337683523654e-05, "epoch": 0.5946166394779772, "percentage": 2.97, "elapsed_time": "0:26:22", "remaining_time": "14:20:31", "throughput": 4987.22, "total_tokens": 7890272} +{"current_steps": 3650, "total_steps": 122600, "loss": 0.3684, "lr": 1.488172920065253e-05, "epoch": 0.5954323001631321, "percentage": 2.98, "elapsed_time": "0:26:24", "remaining_time": "14:20:30", "throughput": 4987.18, "total_tokens": 7901120} +{"current_steps": 3655, "total_steps": 122600, "loss": 0.0699, "lr": 1.4902120717781404e-05, "epoch": 0.5962479608482871, "percentage": 2.98, "elapsed_time": "0:26:26", "remaining_time": "14:20:33", "throughput": 4987.08, "total_tokens": 7912608} +{"current_steps": 3660, "total_steps": 122600, "loss": 0.2962, "lr": 1.4922512234910277e-05, "epoch": 0.5970636215334421, "percentage": 2.99, "elapsed_time": "0:26:28", "remaining_time": "14:20:34", "throughput": 4987.08, "total_tokens": 7923936} +{"current_steps": 3665, "total_steps": 122600, "loss": 0.2931, "lr": 1.4942903752039153e-05, "epoch": 0.5978792822185971, "percentage": 2.99, "elapsed_time": "0:26:31", "remaining_time": "14:20:31", "throughput": 4987.0, "total_tokens": 7934496} +{"current_steps": 3670, "total_steps": 122600, "loss": 0.2266, "lr": 1.4963295269168027e-05, "epoch": 0.598694942903752, "percentage": 2.99, "elapsed_time": "0:26:33", "remaining_time": "14:20:31", "throughput": 4987.04, "total_tokens": 7945728} +{"current_steps": 3675, "total_steps": 122600, "loss": 0.163, "lr": 1.4983686786296902e-05, "epoch": 0.5995106035889071, "percentage": 3.0, "elapsed_time": "0:26:35", "remaining_time": "14:20:32", "throughput": 4987.03, "total_tokens": 7956960} +{"current_steps": 3680, "total_steps": 122600, "loss": 0.1721, "lr": 1.5004078303425776e-05, "epoch": 0.600326264274062, "percentage": 3.0, "elapsed_time": "0:26:38", "remaining_time": "14:20:41", "throughput": 4986.95, "total_tokens": 7969440} +{"current_steps": 3685, "total_steps": 122600, "loss": 0.1716, "lr": 1.5024469820554652e-05, "epoch": 0.6011419249592169, "percentage": 3.01, "elapsed_time": "0:26:39", "remaining_time": "14:20:29", "throughput": 4986.86, "total_tokens": 7978560} +{"current_steps": 3690, "total_steps": 122600, "loss": 0.2924, "lr": 1.5044861337683524e-05, "epoch": 0.601957585644372, "percentage": 3.01, "elapsed_time": "0:26:42", "remaining_time": "14:20:33", "throughput": 4986.89, "total_tokens": 7990400} +{"current_steps": 3695, "total_steps": 122600, "loss": 0.1883, "lr": 1.5065252854812398e-05, "epoch": 0.6027732463295269, "percentage": 3.01, "elapsed_time": "0:26:44", "remaining_time": "14:20:23", "throughput": 4986.93, "total_tokens": 8000128} +{"current_steps": 3700, "total_steps": 122600, "loss": 0.1324, "lr": 1.5085644371941273e-05, "epoch": 0.6035889070146819, "percentage": 3.02, "elapsed_time": "0:26:46", "remaining_time": "14:20:19", "throughput": 4986.9, "total_tokens": 8010592} +{"current_steps": 3705, "total_steps": 122600, "loss": 0.2703, "lr": 1.5106035889070147e-05, "epoch": 0.6044045676998369, "percentage": 3.02, "elapsed_time": "0:26:48", "remaining_time": "14:20:23", "throughput": 4986.85, "total_tokens": 8022240} +{"current_steps": 3710, "total_steps": 122600, "loss": 0.2663, "lr": 1.5126427406199022e-05, "epoch": 0.6052202283849919, "percentage": 3.03, "elapsed_time": "0:26:50", "remaining_time": "14:20:14", "throughput": 4986.91, "total_tokens": 8032096} +{"current_steps": 3715, "total_steps": 122600, "loss": 0.3208, "lr": 1.5146818923327896e-05, "epoch": 0.6060358890701468, "percentage": 3.03, "elapsed_time": "0:26:52", "remaining_time": "14:20:08", "throughput": 4986.94, "total_tokens": 8042400} +{"current_steps": 3720, "total_steps": 122600, "loss": 0.0799, "lr": 1.516721044045677e-05, "epoch": 0.6068515497553018, "percentage": 3.03, "elapsed_time": "0:26:54", "remaining_time": "14:20:02", "throughput": 4986.93, "total_tokens": 8052672} +{"current_steps": 3725, "total_steps": 122600, "loss": 0.1629, "lr": 1.5187601957585646e-05, "epoch": 0.6076672104404568, "percentage": 3.04, "elapsed_time": "0:26:56", "remaining_time": "14:20:02", "throughput": 4986.92, "total_tokens": 8063712} +{"current_steps": 3730, "total_steps": 122600, "loss": 0.1227, "lr": 1.520799347471452e-05, "epoch": 0.6084828711256117, "percentage": 3.04, "elapsed_time": "0:26:58", "remaining_time": "14:19:54", "throughput": 4986.87, "total_tokens": 8073600} +{"current_steps": 3735, "total_steps": 122600, "loss": 0.1897, "lr": 1.5228384991843395e-05, "epoch": 0.6092985318107668, "percentage": 3.05, "elapsed_time": "0:27:01", "remaining_time": "14:20:00", "throughput": 4986.85, "total_tokens": 8085664} +{"current_steps": 3740, "total_steps": 122600, "loss": 0.2321, "lr": 1.5248776508972267e-05, "epoch": 0.6101141924959217, "percentage": 3.05, "elapsed_time": "0:27:03", "remaining_time": "14:20:03", "throughput": 4986.71, "total_tokens": 8097152} +{"current_steps": 3745, "total_steps": 122600, "loss": 0.1143, "lr": 1.5269168026101143e-05, "epoch": 0.6109298531810766, "percentage": 3.05, "elapsed_time": "0:27:05", "remaining_time": "14:19:59", "throughput": 4986.74, "total_tokens": 8107648} +{"current_steps": 3750, "total_steps": 122600, "loss": 0.3896, "lr": 1.5289559543230016e-05, "epoch": 0.6117455138662317, "percentage": 3.06, "elapsed_time": "0:27:07", "remaining_time": "14:19:55", "throughput": 4986.75, "total_tokens": 8118272} +{"current_steps": 3755, "total_steps": 122600, "loss": 0.1129, "lr": 1.530995106035889e-05, "epoch": 0.6125611745513866, "percentage": 3.06, "elapsed_time": "0:27:10", "remaining_time": "14:19:53", "throughput": 4986.81, "total_tokens": 8129120} +{"current_steps": 3760, "total_steps": 122600, "loss": 0.1997, "lr": 1.5330342577487767e-05, "epoch": 0.6133768352365416, "percentage": 3.07, "elapsed_time": "0:27:12", "remaining_time": "14:19:45", "throughput": 4986.86, "total_tokens": 8139200} +{"current_steps": 3765, "total_steps": 122600, "loss": 0.1545, "lr": 1.5350734094616638e-05, "epoch": 0.6141924959216966, "percentage": 3.07, "elapsed_time": "0:27:14", "remaining_time": "14:19:45", "throughput": 4986.83, "total_tokens": 8150272} +{"current_steps": 3770, "total_steps": 122600, "loss": 0.3661, "lr": 1.5371125611745515e-05, "epoch": 0.6150081566068516, "percentage": 3.08, "elapsed_time": "0:27:16", "remaining_time": "14:19:51", "throughput": 4986.85, "total_tokens": 8162496} +{"current_steps": 3775, "total_steps": 122600, "loss": 0.1918, "lr": 1.539151712887439e-05, "epoch": 0.6158238172920065, "percentage": 3.08, "elapsed_time": "0:27:19", "remaining_time": "14:19:52", "throughput": 4986.84, "total_tokens": 8173664} +{"current_steps": 3780, "total_steps": 122600, "loss": 0.3646, "lr": 1.5411908646003266e-05, "epoch": 0.6166394779771615, "percentage": 3.08, "elapsed_time": "0:27:21", "remaining_time": "14:19:50", "throughput": 4986.82, "total_tokens": 8184512} +{"current_steps": 3785, "total_steps": 122600, "loss": 0.2594, "lr": 1.5432300163132137e-05, "epoch": 0.6174551386623165, "percentage": 3.09, "elapsed_time": "0:27:23", "remaining_time": "14:19:41", "throughput": 4986.86, "total_tokens": 8194432} +{"current_steps": 3790, "total_steps": 122600, "loss": 0.1057, "lr": 1.545269168026101e-05, "epoch": 0.6182707993474714, "percentage": 3.09, "elapsed_time": "0:27:25", "remaining_time": "14:19:39", "throughput": 4986.79, "total_tokens": 8205152} +{"current_steps": 3795, "total_steps": 122600, "loss": 0.2131, "lr": 1.5473083197389888e-05, "epoch": 0.6190864600326265, "percentage": 3.1, "elapsed_time": "0:27:27", "remaining_time": "14:19:34", "throughput": 4986.73, "total_tokens": 8215360} +{"current_steps": 3800, "total_steps": 122600, "loss": 0.1355, "lr": 1.549347471451876e-05, "epoch": 0.6199021207177814, "percentage": 3.1, "elapsed_time": "0:27:29", "remaining_time": "14:19:24", "throughput": 4986.86, "total_tokens": 8225216} +{"current_steps": 3805, "total_steps": 122600, "loss": 0.239, "lr": 1.5513866231647635e-05, "epoch": 0.6207177814029364, "percentage": 3.1, "elapsed_time": "0:27:31", "remaining_time": "14:19:18", "throughput": 4986.89, "total_tokens": 8235488} +{"current_steps": 3810, "total_steps": 122600, "loss": 0.1525, "lr": 1.553425774877651e-05, "epoch": 0.6215334420880914, "percentage": 3.11, "elapsed_time": "0:27:33", "remaining_time": "14:19:14", "throughput": 4987.0, "total_tokens": 8246208} +{"current_steps": 3815, "total_steps": 122600, "loss": 0.1828, "lr": 1.5554649265905383e-05, "epoch": 0.6223491027732463, "percentage": 3.11, "elapsed_time": "0:27:35", "remaining_time": "14:19:19", "throughput": 4986.97, "total_tokens": 8258048} +{"current_steps": 3820, "total_steps": 122600, "loss": 0.1377, "lr": 1.557504078303426e-05, "epoch": 0.6231647634584013, "percentage": 3.12, "elapsed_time": "0:27:38", "remaining_time": "14:19:22", "throughput": 4986.84, "total_tokens": 8269472} +{"current_steps": 3825, "total_steps": 122600, "loss": 0.3828, "lr": 1.559543230016313e-05, "epoch": 0.6239804241435563, "percentage": 3.12, "elapsed_time": "0:27:40", "remaining_time": "14:19:21", "throughput": 4986.85, "total_tokens": 8280512} +{"current_steps": 3830, "total_steps": 122600, "loss": 0.225, "lr": 1.5615823817292008e-05, "epoch": 0.6247960848287113, "percentage": 3.12, "elapsed_time": "0:27:42", "remaining_time": "14:19:18", "throughput": 4986.95, "total_tokens": 8291360} +{"current_steps": 3835, "total_steps": 122600, "loss": 0.0446, "lr": 1.563621533442088e-05, "epoch": 0.6256117455138662, "percentage": 3.13, "elapsed_time": "0:27:44", "remaining_time": "14:19:11", "throughput": 4986.94, "total_tokens": 8301440} +{"current_steps": 3840, "total_steps": 122600, "loss": 0.3302, "lr": 1.565660685154976e-05, "epoch": 0.6264274061990212, "percentage": 3.13, "elapsed_time": "0:27:47", "remaining_time": "14:19:17", "throughput": 4986.93, "total_tokens": 8313472} +{"current_steps": 3845, "total_steps": 122600, "loss": 0.0285, "lr": 1.567699836867863e-05, "epoch": 0.6272430668841762, "percentage": 3.14, "elapsed_time": "0:27:49", "remaining_time": "14:19:08", "throughput": 4987.06, "total_tokens": 8323488} +{"current_steps": 3850, "total_steps": 122600, "loss": 0.0552, "lr": 1.5697389885807503e-05, "epoch": 0.6280587275693311, "percentage": 3.14, "elapsed_time": "0:27:51", "remaining_time": "14:19:17", "throughput": 4987.02, "total_tokens": 8336096} +{"current_steps": 3855, "total_steps": 122600, "loss": 0.2791, "lr": 1.571778140293638e-05, "epoch": 0.6288743882544862, "percentage": 3.14, "elapsed_time": "0:27:53", "remaining_time": "14:19:01", "throughput": 4987.07, "total_tokens": 8344736} +{"current_steps": 3860, "total_steps": 122600, "loss": 0.1276, "lr": 1.5738172920065254e-05, "epoch": 0.6296900489396411, "percentage": 3.15, "elapsed_time": "0:27:55", "remaining_time": "14:19:04", "throughput": 4987.06, "total_tokens": 8356416} +{"current_steps": 3865, "total_steps": 122600, "loss": 0.2479, "lr": 1.5758564437194128e-05, "epoch": 0.6305057096247961, "percentage": 3.15, "elapsed_time": "0:27:57", "remaining_time": "14:19:04", "throughput": 4987.13, "total_tokens": 8367712} +{"current_steps": 3870, "total_steps": 122600, "loss": 0.2297, "lr": 1.5778955954323002e-05, "epoch": 0.6313213703099511, "percentage": 3.16, "elapsed_time": "0:28:00", "remaining_time": "14:19:04", "throughput": 4987.06, "total_tokens": 8378752} +{"current_steps": 3875, "total_steps": 122600, "loss": 0.251, "lr": 1.579934747145188e-05, "epoch": 0.632137030995106, "percentage": 3.16, "elapsed_time": "0:28:02", "remaining_time": "14:19:01", "throughput": 4987.1, "total_tokens": 8389472} +{"current_steps": 3880, "total_steps": 122600, "loss": 0.2196, "lr": 1.5819738988580753e-05, "epoch": 0.632952691680261, "percentage": 3.16, "elapsed_time": "0:28:04", "remaining_time": "14:18:58", "throughput": 4987.04, "total_tokens": 8400064} +{"current_steps": 3885, "total_steps": 122600, "loss": 0.1061, "lr": 1.5840130505709623e-05, "epoch": 0.633768352365416, "percentage": 3.17, "elapsed_time": "0:28:06", "remaining_time": "14:18:51", "throughput": 4987.1, "total_tokens": 8410176} +{"current_steps": 3890, "total_steps": 122600, "loss": 0.3241, "lr": 1.58605220228385e-05, "epoch": 0.634584013050571, "percentage": 3.17, "elapsed_time": "0:28:08", "remaining_time": "14:18:44", "throughput": 4987.09, "total_tokens": 8420256} +{"current_steps": 3895, "total_steps": 122600, "loss": 0.1872, "lr": 1.5880913539967374e-05, "epoch": 0.6353996737357259, "percentage": 3.18, "elapsed_time": "0:28:10", "remaining_time": "14:18:46", "throughput": 4987.1, "total_tokens": 8431808} +{"current_steps": 3900, "total_steps": 122600, "loss": 0.077, "lr": 1.5901305057096248e-05, "epoch": 0.636215334420881, "percentage": 3.18, "elapsed_time": "0:28:13", "remaining_time": "14:18:54", "throughput": 4987.03, "total_tokens": 8444064} +{"current_steps": 3905, "total_steps": 122600, "loss": 0.3273, "lr": 1.5921696574225122e-05, "epoch": 0.6370309951060359, "percentage": 3.19, "elapsed_time": "0:28:15", "remaining_time": "14:18:52", "throughput": 4987.07, "total_tokens": 8454944} +{"current_steps": 3910, "total_steps": 122600, "loss": 0.0679, "lr": 1.5942088091354e-05, "epoch": 0.6378466557911908, "percentage": 3.19, "elapsed_time": "0:28:17", "remaining_time": "14:18:53", "throughput": 4987.01, "total_tokens": 8466208} +{"current_steps": 3915, "total_steps": 122600, "loss": 0.1407, "lr": 1.5962479608482873e-05, "epoch": 0.6386623164763459, "percentage": 3.19, "elapsed_time": "0:28:19", "remaining_time": "14:18:48", "throughput": 4986.91, "total_tokens": 8476480} +{"current_steps": 3920, "total_steps": 122600, "loss": 0.222, "lr": 1.5982871125611747e-05, "epoch": 0.6394779771615008, "percentage": 3.2, "elapsed_time": "0:28:21", "remaining_time": "14:18:43", "throughput": 4986.83, "total_tokens": 8486688} +{"current_steps": 3925, "total_steps": 122600, "loss": 0.2238, "lr": 1.600326264274062e-05, "epoch": 0.6402936378466558, "percentage": 3.2, "elapsed_time": "0:28:24", "remaining_time": "14:18:51", "throughput": 4986.84, "total_tokens": 8499200} +{"current_steps": 3930, "total_steps": 122600, "loss": 0.1703, "lr": 1.6023654159869494e-05, "epoch": 0.6411092985318108, "percentage": 3.21, "elapsed_time": "0:28:26", "remaining_time": "14:18:47", "throughput": 4986.85, "total_tokens": 8509728} +{"current_steps": 3935, "total_steps": 122600, "loss": 0.1859, "lr": 1.604404567699837e-05, "epoch": 0.6419249592169658, "percentage": 3.21, "elapsed_time": "0:28:28", "remaining_time": "14:18:48", "throughput": 4986.76, "total_tokens": 8520928} +{"current_steps": 3940, "total_steps": 122600, "loss": 0.1996, "lr": 1.6064437194127242e-05, "epoch": 0.6427406199021207, "percentage": 3.21, "elapsed_time": "0:28:31", "remaining_time": "14:18:50", "throughput": 4986.75, "total_tokens": 8532448} +{"current_steps": 3945, "total_steps": 122600, "loss": 0.2494, "lr": 1.6084828711256116e-05, "epoch": 0.6435562805872757, "percentage": 3.22, "elapsed_time": "0:28:33", "remaining_time": "14:18:48", "throughput": 4986.82, "total_tokens": 8543360} +{"current_steps": 3950, "total_steps": 122600, "loss": 0.2239, "lr": 1.6105220228384993e-05, "epoch": 0.6443719412724307, "percentage": 3.22, "elapsed_time": "0:28:35", "remaining_time": "14:18:45", "throughput": 4986.84, "total_tokens": 8554176} +{"current_steps": 3955, "total_steps": 122600, "loss": 0.1445, "lr": 1.6125611745513867e-05, "epoch": 0.6451876019575856, "percentage": 3.23, "elapsed_time": "0:28:37", "remaining_time": "14:18:45", "throughput": 4986.86, "total_tokens": 8565376} +{"current_steps": 3960, "total_steps": 122600, "loss": 0.3292, "lr": 1.614600326264274e-05, "epoch": 0.6460032626427407, "percentage": 3.23, "elapsed_time": "0:28:39", "remaining_time": "14:18:44", "throughput": 4986.95, "total_tokens": 8576480} +{"current_steps": 3965, "total_steps": 122600, "loss": 0.1125, "lr": 1.6166394779771615e-05, "epoch": 0.6468189233278956, "percentage": 3.23, "elapsed_time": "0:28:41", "remaining_time": "14:18:39", "throughput": 4986.98, "total_tokens": 8586944} +{"current_steps": 3970, "total_steps": 122600, "loss": 0.1776, "lr": 1.6186786296900492e-05, "epoch": 0.6476345840130505, "percentage": 3.24, "elapsed_time": "0:28:43", "remaining_time": "14:18:30", "throughput": 4986.96, "total_tokens": 8596640} +{"current_steps": 3975, "total_steps": 122600, "loss": 0.0941, "lr": 1.6207177814029366e-05, "epoch": 0.6484502446982056, "percentage": 3.24, "elapsed_time": "0:28:46", "remaining_time": "14:18:33", "throughput": 4986.89, "total_tokens": 8608256} +{"current_steps": 3980, "total_steps": 122600, "loss": 0.1917, "lr": 1.622756933115824e-05, "epoch": 0.6492659053833605, "percentage": 3.25, "elapsed_time": "0:28:48", "remaining_time": "14:18:28", "throughput": 4987.03, "total_tokens": 8618752} +{"current_steps": 3985, "total_steps": 122600, "loss": 0.1677, "lr": 1.6247960848287113e-05, "epoch": 0.6500815660685155, "percentage": 3.25, "elapsed_time": "0:28:50", "remaining_time": "14:18:27", "throughput": 4987.02, "total_tokens": 8629824} +{"current_steps": 3990, "total_steps": 122600, "loss": 0.2197, "lr": 1.6268352365415987e-05, "epoch": 0.6508972267536705, "percentage": 3.25, "elapsed_time": "0:28:52", "remaining_time": "14:18:26", "throughput": 4987.05, "total_tokens": 8640832} +{"current_steps": 3995, "total_steps": 122600, "loss": 0.2218, "lr": 1.6288743882544864e-05, "epoch": 0.6517128874388255, "percentage": 3.26, "elapsed_time": "0:28:54", "remaining_time": "14:18:20", "throughput": 4987.07, "total_tokens": 8651104} +{"current_steps": 4000, "total_steps": 122600, "loss": 0.2313, "lr": 1.6309135399673735e-05, "epoch": 0.6525285481239804, "percentage": 3.26, "elapsed_time": "0:28:56", "remaining_time": "14:18:19", "throughput": 4987.04, "total_tokens": 8662112} +{"current_steps": 4005, "total_steps": 122600, "loss": 0.1173, "lr": 1.6329526916802612e-05, "epoch": 0.6533442088091354, "percentage": 3.27, "elapsed_time": "0:28:59", "remaining_time": "14:18:16", "throughput": 4987.14, "total_tokens": 8672960} +{"current_steps": 4010, "total_steps": 122600, "loss": 0.1281, "lr": 1.6349918433931486e-05, "epoch": 0.6541598694942904, "percentage": 3.27, "elapsed_time": "0:29:01", "remaining_time": "14:18:15", "throughput": 4987.2, "total_tokens": 8683968} +{"current_steps": 4015, "total_steps": 122600, "loss": 0.1686, "lr": 1.637030995106036e-05, "epoch": 0.6549755301794453, "percentage": 3.27, "elapsed_time": "0:29:03", "remaining_time": "14:18:15", "throughput": 4987.2, "total_tokens": 8695200} +{"current_steps": 4020, "total_steps": 122600, "loss": 0.2519, "lr": 1.6390701468189233e-05, "epoch": 0.6557911908646004, "percentage": 3.28, "elapsed_time": "0:29:05", "remaining_time": "14:18:09", "throughput": 4987.16, "total_tokens": 8705408} +{"current_steps": 4025, "total_steps": 122600, "loss": 0.1461, "lr": 1.6411092985318107e-05, "epoch": 0.6566068515497553, "percentage": 3.28, "elapsed_time": "0:29:07", "remaining_time": "14:18:07", "throughput": 4987.07, "total_tokens": 8716128} +{"current_steps": 4030, "total_steps": 122600, "loss": 0.3905, "lr": 1.6431484502446984e-05, "epoch": 0.6574225122349103, "percentage": 3.29, "elapsed_time": "0:29:10", "remaining_time": "14:18:11", "throughput": 4986.99, "total_tokens": 8727744} +{"current_steps": 4035, "total_steps": 122600, "loss": 0.2071, "lr": 1.6451876019575858e-05, "epoch": 0.6582381729200653, "percentage": 3.29, "elapsed_time": "0:29:12", "remaining_time": "14:18:18", "throughput": 4987.0, "total_tokens": 8740128} +{"current_steps": 4040, "total_steps": 122600, "loss": 0.2677, "lr": 1.6472267536704732e-05, "epoch": 0.6590538336052202, "percentage": 3.3, "elapsed_time": "0:29:15", "remaining_time": "14:18:24", "throughput": 4986.94, "total_tokens": 8752320} +{"current_steps": 4045, "total_steps": 122600, "loss": 0.1923, "lr": 1.6492659053833606e-05, "epoch": 0.6598694942903752, "percentage": 3.3, "elapsed_time": "0:29:17", "remaining_time": "14:18:19", "throughput": 4987.03, "total_tokens": 8762784} +{"current_steps": 4050, "total_steps": 122600, "loss": 0.1534, "lr": 1.651305057096248e-05, "epoch": 0.6606851549755302, "percentage": 3.3, "elapsed_time": "0:29:19", "remaining_time": "14:18:16", "throughput": 4986.97, "total_tokens": 8773312} +{"current_steps": 4055, "total_steps": 122600, "loss": 0.2183, "lr": 1.6533442088091357e-05, "epoch": 0.6615008156606852, "percentage": 3.31, "elapsed_time": "0:29:21", "remaining_time": "14:18:11", "throughput": 4986.97, "total_tokens": 8783744} +{"current_steps": 4060, "total_steps": 122600, "loss": 0.0714, "lr": 1.6553833605220227e-05, "epoch": 0.6623164763458401, "percentage": 3.31, "elapsed_time": "0:29:23", "remaining_time": "14:18:11", "throughput": 4987.06, "total_tokens": 8795104} +{"current_steps": 4065, "total_steps": 122600, "loss": 0.131, "lr": 1.6574225122349105e-05, "epoch": 0.6631321370309952, "percentage": 3.32, "elapsed_time": "0:29:25", "remaining_time": "14:18:08", "throughput": 4987.06, "total_tokens": 8805760} +{"current_steps": 4070, "total_steps": 122600, "loss": 0.1016, "lr": 1.659461663947798e-05, "epoch": 0.6639477977161501, "percentage": 3.32, "elapsed_time": "0:29:28", "remaining_time": "14:18:11", "throughput": 4987.06, "total_tokens": 8817536} +{"current_steps": 4075, "total_steps": 122600, "loss": 0.0403, "lr": 1.6615008156606852e-05, "epoch": 0.664763458401305, "percentage": 3.32, "elapsed_time": "0:29:30", "remaining_time": "14:18:13", "throughput": 4987.09, "total_tokens": 8829184} +{"current_steps": 4080, "total_steps": 122600, "loss": 0.1116, "lr": 1.6635399673735726e-05, "epoch": 0.6655791190864601, "percentage": 3.33, "elapsed_time": "0:29:32", "remaining_time": "14:18:07", "throughput": 4987.06, "total_tokens": 8839328} +{"current_steps": 4085, "total_steps": 122600, "loss": 0.1802, "lr": 1.66557911908646e-05, "epoch": 0.666394779771615, "percentage": 3.33, "elapsed_time": "0:29:34", "remaining_time": "14:18:05", "throughput": 4987.2, "total_tokens": 8850336} +{"current_steps": 4090, "total_steps": 122600, "loss": 0.2197, "lr": 1.6676182707993477e-05, "epoch": 0.66721044045677, "percentage": 3.34, "elapsed_time": "0:29:36", "remaining_time": "14:17:52", "throughput": 4987.25, "total_tokens": 8859392} +{"current_steps": 4095, "total_steps": 122600, "loss": 0.1303, "lr": 1.669657422512235e-05, "epoch": 0.668026101141925, "percentage": 3.34, "elapsed_time": "0:29:38", "remaining_time": "14:17:55", "throughput": 4987.22, "total_tokens": 8871008} +{"current_steps": 4100, "total_steps": 122600, "loss": 0.2302, "lr": 1.6716965742251225e-05, "epoch": 0.6688417618270799, "percentage": 3.34, "elapsed_time": "0:29:40", "remaining_time": "14:17:52", "throughput": 4987.2, "total_tokens": 8881760} +{"current_steps": 4105, "total_steps": 122600, "loss": 0.39, "lr": 1.67373572593801e-05, "epoch": 0.6696574225122349, "percentage": 3.35, "elapsed_time": "0:29:43", "remaining_time": "14:17:50", "throughput": 4987.13, "total_tokens": 8892544} +{"current_steps": 4110, "total_steps": 122600, "loss": 0.3103, "lr": 1.6757748776508972e-05, "epoch": 0.6704730831973899, "percentage": 3.35, "elapsed_time": "0:29:45", "remaining_time": "14:17:52", "throughput": 4987.1, "total_tokens": 8903936} +{"current_steps": 4115, "total_steps": 122600, "loss": 0.1904, "lr": 1.677814029363785e-05, "epoch": 0.6712887438825449, "percentage": 3.36, "elapsed_time": "0:29:47", "remaining_time": "14:17:45", "throughput": 4987.05, "total_tokens": 8913952} +{"current_steps": 4120, "total_steps": 122600, "loss": 0.264, "lr": 1.679853181076672e-05, "epoch": 0.6721044045676998, "percentage": 3.36, "elapsed_time": "0:29:49", "remaining_time": "14:17:45", "throughput": 4987.03, "total_tokens": 8925120} +{"current_steps": 4125, "total_steps": 122600, "loss": 0.125, "lr": 1.6818923327895597e-05, "epoch": 0.6729200652528549, "percentage": 3.36, "elapsed_time": "0:29:51", "remaining_time": "14:17:42", "throughput": 4987.13, "total_tokens": 8935872} +{"current_steps": 4130, "total_steps": 122600, "loss": 0.1876, "lr": 1.683931484502447e-05, "epoch": 0.6737357259380098, "percentage": 3.37, "elapsed_time": "0:29:53", "remaining_time": "14:17:40", "throughput": 4987.09, "total_tokens": 8946624} +{"current_steps": 4135, "total_steps": 122600, "loss": 0.1155, "lr": 1.6859706362153345e-05, "epoch": 0.6745513866231647, "percentage": 3.37, "elapsed_time": "0:29:56", "remaining_time": "14:17:38", "throughput": 4987.11, "total_tokens": 8957568} +{"current_steps": 4140, "total_steps": 122600, "loss": 0.2617, "lr": 1.688009787928222e-05, "epoch": 0.6753670473083198, "percentage": 3.38, "elapsed_time": "0:29:58", "remaining_time": "14:17:34", "throughput": 4987.17, "total_tokens": 8968160} +{"current_steps": 4145, "total_steps": 122600, "loss": 0.163, "lr": 1.6900489396411092e-05, "epoch": 0.6761827079934747, "percentage": 3.38, "elapsed_time": "0:30:00", "remaining_time": "14:17:29", "throughput": 4987.15, "total_tokens": 8978560} +{"current_steps": 4150, "total_steps": 122600, "loss": 0.1845, "lr": 1.692088091353997e-05, "epoch": 0.6769983686786297, "percentage": 3.38, "elapsed_time": "0:30:02", "remaining_time": "14:17:24", "throughput": 4987.14, "total_tokens": 8988896} +{"current_steps": 4155, "total_steps": 122600, "loss": 0.2085, "lr": 1.6941272430668844e-05, "epoch": 0.6778140293637847, "percentage": 3.39, "elapsed_time": "0:30:04", "remaining_time": "14:17:29", "throughput": 4987.12, "total_tokens": 9000928} +{"current_steps": 4160, "total_steps": 122600, "loss": 0.12, "lr": 1.6961663947797717e-05, "epoch": 0.6786296900489397, "percentage": 3.39, "elapsed_time": "0:30:07", "remaining_time": "14:17:27", "throughput": 4987.09, "total_tokens": 9011712} +{"current_steps": 4165, "total_steps": 122600, "loss": 0.2304, "lr": 1.698205546492659e-05, "epoch": 0.6794453507340946, "percentage": 3.4, "elapsed_time": "0:30:09", "remaining_time": "14:17:26", "throughput": 4987.05, "total_tokens": 9022624} +{"current_steps": 4170, "total_steps": 122600, "loss": 0.2156, "lr": 1.7002446982055465e-05, "epoch": 0.6802610114192496, "percentage": 3.4, "elapsed_time": "0:30:11", "remaining_time": "14:17:21", "throughput": 4987.06, "total_tokens": 9033088} +{"current_steps": 4175, "total_steps": 122600, "loss": 0.3067, "lr": 1.702283849918434e-05, "epoch": 0.6810766721044046, "percentage": 3.41, "elapsed_time": "0:30:13", "remaining_time": "14:17:17", "throughput": 4987.14, "total_tokens": 9043680} +{"current_steps": 4180, "total_steps": 122600, "loss": 0.1854, "lr": 1.7043230016313213e-05, "epoch": 0.6818923327895595, "percentage": 3.41, "elapsed_time": "0:30:15", "remaining_time": "14:17:20", "throughput": 4987.12, "total_tokens": 9055424} +{"current_steps": 4185, "total_steps": 122600, "loss": 0.0725, "lr": 1.706362153344209e-05, "epoch": 0.6827079934747146, "percentage": 3.41, "elapsed_time": "0:30:18", "remaining_time": "14:17:22", "throughput": 4987.03, "total_tokens": 9066816} +{"current_steps": 4190, "total_steps": 122600, "loss": 0.2072, "lr": 1.7084013050570964e-05, "epoch": 0.6835236541598695, "percentage": 3.42, "elapsed_time": "0:30:20", "remaining_time": "14:17:21", "throughput": 4987.04, "total_tokens": 9077792} +{"current_steps": 4195, "total_steps": 122600, "loss": 0.2716, "lr": 1.7104404567699837e-05, "epoch": 0.6843393148450244, "percentage": 3.42, "elapsed_time": "0:30:22", "remaining_time": "14:17:17", "throughput": 4986.99, "total_tokens": 9088160} +{"current_steps": 4200, "total_steps": 122600, "loss": 0.0526, "lr": 1.712479608482871e-05, "epoch": 0.6851549755301795, "percentage": 3.43, "elapsed_time": "0:30:24", "remaining_time": "14:17:16", "throughput": 4986.96, "total_tokens": 9099264} +{"current_steps": 4205, "total_steps": 122600, "loss": 0.2833, "lr": 1.7145187601957585e-05, "epoch": 0.6859706362153344, "percentage": 3.43, "elapsed_time": "0:30:26", "remaining_time": "14:17:15", "throughput": 4987.02, "total_tokens": 9110336} +{"current_steps": 4210, "total_steps": 122600, "loss": 0.0624, "lr": 1.7165579119086462e-05, "epoch": 0.6867862969004894, "percentage": 3.43, "elapsed_time": "0:30:29", "remaining_time": "14:17:14", "throughput": 4986.96, "total_tokens": 9121248} +{"current_steps": 4215, "total_steps": 122600, "loss": 0.1335, "lr": 1.7185970636215333e-05, "epoch": 0.6876019575856444, "percentage": 3.44, "elapsed_time": "0:30:31", "remaining_time": "14:17:17", "throughput": 4986.85, "total_tokens": 9132896} +{"current_steps": 4220, "total_steps": 122600, "loss": 0.131, "lr": 1.720636215334421e-05, "epoch": 0.6884176182707994, "percentage": 3.44, "elapsed_time": "0:30:33", "remaining_time": "14:17:16", "throughput": 4986.9, "total_tokens": 9143968} +{"current_steps": 4225, "total_steps": 122600, "loss": 0.1222, "lr": 1.7226753670473084e-05, "epoch": 0.6892332789559543, "percentage": 3.45, "elapsed_time": "0:30:35", "remaining_time": "14:17:13", "throughput": 4986.98, "total_tokens": 9154848} +{"current_steps": 4230, "total_steps": 122600, "loss": 0.2354, "lr": 1.724714518760196e-05, "epoch": 0.6900489396411092, "percentage": 3.45, "elapsed_time": "0:30:38", "remaining_time": "14:17:19", "throughput": 4987.01, "total_tokens": 9167264} +{"current_steps": 4235, "total_steps": 122600, "loss": 0.0888, "lr": 1.726753670473083e-05, "epoch": 0.6908646003262643, "percentage": 3.45, "elapsed_time": "0:30:40", "remaining_time": "14:17:16", "throughput": 4987.07, "total_tokens": 9178016} +{"current_steps": 4240, "total_steps": 122600, "loss": 0.1393, "lr": 1.7287928221859705e-05, "epoch": 0.6916802610114192, "percentage": 3.46, "elapsed_time": "0:30:42", "remaining_time": "14:17:11", "throughput": 4987.05, "total_tokens": 9188224} +{"current_steps": 4245, "total_steps": 122600, "loss": 0.042, "lr": 1.7308319738988583e-05, "epoch": 0.6924959216965743, "percentage": 3.46, "elapsed_time": "0:30:44", "remaining_time": "14:17:03", "throughput": 4987.1, "total_tokens": 9198208} +{"current_steps": 4250, "total_steps": 122600, "loss": 0.1658, "lr": 1.7328711256117456e-05, "epoch": 0.6933115823817292, "percentage": 3.47, "elapsed_time": "0:30:46", "remaining_time": "14:16:55", "throughput": 4987.15, "total_tokens": 9208128} +{"current_steps": 4255, "total_steps": 122600, "loss": 0.081, "lr": 1.734910277324633e-05, "epoch": 0.6941272430668842, "percentage": 3.47, "elapsed_time": "0:30:48", "remaining_time": "14:16:48", "throughput": 4987.23, "total_tokens": 9218080} +{"current_steps": 4260, "total_steps": 122600, "loss": 0.021, "lr": 1.7369494290375204e-05, "epoch": 0.6949429037520392, "percentage": 3.47, "elapsed_time": "0:30:50", "remaining_time": "14:16:43", "throughput": 4987.17, "total_tokens": 9228416} +{"current_steps": 4265, "total_steps": 122600, "loss": 0.279, "lr": 1.738988580750408e-05, "epoch": 0.6957585644371941, "percentage": 3.48, "elapsed_time": "0:30:52", "remaining_time": "14:16:42", "throughput": 4987.09, "total_tokens": 9239296} +{"current_steps": 4270, "total_steps": 122600, "loss": 0.254, "lr": 1.7410277324632955e-05, "epoch": 0.6965742251223491, "percentage": 3.48, "elapsed_time": "0:30:54", "remaining_time": "14:16:37", "throughput": 4987.06, "total_tokens": 9249472} +{"current_steps": 4275, "total_steps": 122600, "loss": 0.1752, "lr": 1.7430668841761825e-05, "epoch": 0.697389885807504, "percentage": 3.49, "elapsed_time": "0:30:56", "remaining_time": "14:16:30", "throughput": 4987.11, "total_tokens": 9259616} +{"current_steps": 4280, "total_steps": 122600, "loss": 0.1025, "lr": 1.7451060358890703e-05, "epoch": 0.6982055464926591, "percentage": 3.49, "elapsed_time": "0:30:59", "remaining_time": "14:16:33", "throughput": 4987.13, "total_tokens": 9271360} +{"current_steps": 4285, "total_steps": 122600, "loss": 0.1817, "lr": 1.7471451876019576e-05, "epoch": 0.699021207177814, "percentage": 3.5, "elapsed_time": "0:31:01", "remaining_time": "14:16:30", "throughput": 4987.09, "total_tokens": 9281952} +{"current_steps": 4290, "total_steps": 122600, "loss": 0.2328, "lr": 1.7491843393148454e-05, "epoch": 0.6998368678629691, "percentage": 3.5, "elapsed_time": "0:31:03", "remaining_time": "14:16:26", "throughput": 4987.08, "total_tokens": 9292480} +{"current_steps": 4295, "total_steps": 122600, "loss": 0.3547, "lr": 1.7512234910277324e-05, "epoch": 0.700652528548124, "percentage": 3.5, "elapsed_time": "0:31:05", "remaining_time": "14:16:14", "throughput": 4987.17, "total_tokens": 9301696} +{"current_steps": 4300, "total_steps": 122600, "loss": 0.0847, "lr": 1.7532626427406198e-05, "epoch": 0.7014681892332789, "percentage": 3.51, "elapsed_time": "0:31:07", "remaining_time": "14:16:06", "throughput": 4987.16, "total_tokens": 9311360} +{"current_steps": 4305, "total_steps": 122600, "loss": 0.3086, "lr": 1.7553017944535075e-05, "epoch": 0.702283849918434, "percentage": 3.51, "elapsed_time": "0:31:09", "remaining_time": "14:16:00", "throughput": 4987.13, "total_tokens": 9321504} +{"current_steps": 4310, "total_steps": 122600, "loss": 0.1991, "lr": 1.757340946166395e-05, "epoch": 0.7030995106035889, "percentage": 3.52, "elapsed_time": "0:31:11", "remaining_time": "14:16:02", "throughput": 4987.12, "total_tokens": 9333024} +{"current_steps": 4315, "total_steps": 122600, "loss": 0.1336, "lr": 1.7593800978792823e-05, "epoch": 0.7039151712887439, "percentage": 3.52, "elapsed_time": "0:31:13", "remaining_time": "14:15:57", "throughput": 4987.13, "total_tokens": 9343424} +{"current_steps": 4320, "total_steps": 122600, "loss": 0.0734, "lr": 1.7614192495921697e-05, "epoch": 0.7047308319738989, "percentage": 3.52, "elapsed_time": "0:31:15", "remaining_time": "14:15:53", "throughput": 4987.18, "total_tokens": 9354016} +{"current_steps": 4325, "total_steps": 122600, "loss": 0.2438, "lr": 1.7634584013050574e-05, "epoch": 0.7055464926590538, "percentage": 3.53, "elapsed_time": "0:31:17", "remaining_time": "14:15:56", "throughput": 4987.08, "total_tokens": 9365600} +{"current_steps": 4330, "total_steps": 122600, "loss": 0.1938, "lr": 1.7654975530179448e-05, "epoch": 0.7063621533442088, "percentage": 3.53, "elapsed_time": "0:31:20", "remaining_time": "14:15:59", "throughput": 4987.02, "total_tokens": 9377216} +{"current_steps": 4335, "total_steps": 122600, "loss": 0.136, "lr": 1.7675367047308318e-05, "epoch": 0.7071778140293637, "percentage": 3.54, "elapsed_time": "0:31:22", "remaining_time": "14:15:56", "throughput": 4987.03, "total_tokens": 9388000} +{"current_steps": 4340, "total_steps": 122600, "loss": 0.2438, "lr": 1.7695758564437195e-05, "epoch": 0.7079934747145188, "percentage": 3.54, "elapsed_time": "0:31:24", "remaining_time": "14:16:00", "throughput": 4986.9, "total_tokens": 9399616} +{"current_steps": 4345, "total_steps": 122600, "loss": 0.1581, "lr": 1.771615008156607e-05, "epoch": 0.7088091353996737, "percentage": 3.54, "elapsed_time": "0:31:27", "remaining_time": "14:16:06", "throughput": 4986.86, "total_tokens": 9411872} +{"current_steps": 4350, "total_steps": 122600, "loss": 0.2257, "lr": 1.7736541598694943e-05, "epoch": 0.7096247960848288, "percentage": 3.55, "elapsed_time": "0:31:29", "remaining_time": "14:16:05", "throughput": 4986.87, "total_tokens": 9422912} +{"current_steps": 4355, "total_steps": 122600, "loss": 0.0386, "lr": 1.7756933115823817e-05, "epoch": 0.7104404567699837, "percentage": 3.55, "elapsed_time": "0:31:31", "remaining_time": "14:16:07", "throughput": 4986.71, "total_tokens": 9434176} +{"current_steps": 4360, "total_steps": 122600, "loss": 0.175, "lr": 1.7777324632952694e-05, "epoch": 0.7112561174551386, "percentage": 3.56, "elapsed_time": "0:31:33", "remaining_time": "14:15:59", "throughput": 4986.64, "total_tokens": 9443936} +{"current_steps": 4365, "total_steps": 122600, "loss": 0.0986, "lr": 1.7797716150081568e-05, "epoch": 0.7120717781402937, "percentage": 3.56, "elapsed_time": "0:31:35", "remaining_time": "14:15:53", "throughput": 4986.63, "total_tokens": 9453984} +{"current_steps": 4370, "total_steps": 122600, "loss": 0.1973, "lr": 1.781810766721044e-05, "epoch": 0.7128874388254486, "percentage": 3.56, "elapsed_time": "0:31:38", "remaining_time": "14:15:54", "throughput": 4986.59, "total_tokens": 9465408} +{"current_steps": 4375, "total_steps": 122600, "loss": 0.1956, "lr": 1.7838499184339315e-05, "epoch": 0.7137030995106036, "percentage": 3.57, "elapsed_time": "0:31:40", "remaining_time": "14:15:48", "throughput": 4986.57, "total_tokens": 9475392} +{"current_steps": 4380, "total_steps": 122600, "loss": 0.2474, "lr": 1.785889070146819e-05, "epoch": 0.7145187601957586, "percentage": 3.57, "elapsed_time": "0:31:42", "remaining_time": "14:15:41", "throughput": 4986.53, "total_tokens": 9485280} +{"current_steps": 4385, "total_steps": 122600, "loss": 0.0946, "lr": 1.7879282218597066e-05, "epoch": 0.7153344208809136, "percentage": 3.58, "elapsed_time": "0:31:44", "remaining_time": "14:15:40", "throughput": 4986.5, "total_tokens": 9496224} +{"current_steps": 4390, "total_steps": 122600, "loss": 0.1322, "lr": 1.789967373572594e-05, "epoch": 0.7161500815660685, "percentage": 3.58, "elapsed_time": "0:31:46", "remaining_time": "14:15:41", "throughput": 4986.43, "total_tokens": 9507456} +{"current_steps": 4395, "total_steps": 122600, "loss": 0.3969, "lr": 1.7920065252854814e-05, "epoch": 0.7169657422512234, "percentage": 3.58, "elapsed_time": "0:31:48", "remaining_time": "14:15:36", "throughput": 4986.48, "total_tokens": 9517952} +{"current_steps": 4400, "total_steps": 122600, "loss": 0.1661, "lr": 1.7940456769983688e-05, "epoch": 0.7177814029363785, "percentage": 3.59, "elapsed_time": "0:31:50", "remaining_time": "14:15:33", "throughput": 4986.47, "total_tokens": 9528672} +{"current_steps": 4405, "total_steps": 122600, "loss": 0.0686, "lr": 1.7960848287112562e-05, "epoch": 0.7185970636215334, "percentage": 3.59, "elapsed_time": "0:31:53", "remaining_time": "14:15:31", "throughput": 4986.49, "total_tokens": 9539552} +{"current_steps": 4410, "total_steps": 122600, "loss": 0.2639, "lr": 1.7981239804241436e-05, "epoch": 0.7194127243066885, "percentage": 3.6, "elapsed_time": "0:31:55", "remaining_time": "14:15:27", "throughput": 4986.53, "total_tokens": 9550112} +{"current_steps": 4415, "total_steps": 122600, "loss": 0.2097, "lr": 1.800163132137031e-05, "epoch": 0.7202283849918434, "percentage": 3.6, "elapsed_time": "0:31:57", "remaining_time": "14:15:23", "throughput": 4986.48, "total_tokens": 9560544} +{"current_steps": 4420, "total_steps": 122600, "loss": 0.2592, "lr": 1.8022022838499187e-05, "epoch": 0.7210440456769984, "percentage": 3.61, "elapsed_time": "0:31:59", "remaining_time": "14:15:21", "throughput": 4986.48, "total_tokens": 9571232} +{"current_steps": 4425, "total_steps": 122600, "loss": 0.0671, "lr": 1.804241435562806e-05, "epoch": 0.7218597063621534, "percentage": 3.61, "elapsed_time": "0:32:01", "remaining_time": "14:15:17", "throughput": 4986.5, "total_tokens": 9581920} +{"current_steps": 4430, "total_steps": 122600, "loss": 0.0675, "lr": 1.8062805872756934e-05, "epoch": 0.7226753670473083, "percentage": 3.61, "elapsed_time": "0:32:03", "remaining_time": "14:15:13", "throughput": 4986.53, "total_tokens": 9592448} +{"current_steps": 4435, "total_steps": 122600, "loss": 0.2023, "lr": 1.8083197389885808e-05, "epoch": 0.7234910277324633, "percentage": 3.62, "elapsed_time": "0:32:05", "remaining_time": "14:15:12", "throughput": 4986.5, "total_tokens": 9603360} +{"current_steps": 4440, "total_steps": 122600, "loss": 0.1619, "lr": 1.8103588907014682e-05, "epoch": 0.7243066884176182, "percentage": 3.62, "elapsed_time": "0:32:08", "remaining_time": "14:15:11", "throughput": 4986.5, "total_tokens": 9614336} +{"current_steps": 4445, "total_steps": 122600, "loss": 0.1385, "lr": 1.812398042414356e-05, "epoch": 0.7251223491027733, "percentage": 3.63, "elapsed_time": "0:32:10", "remaining_time": "14:15:05", "throughput": 4986.47, "total_tokens": 9624512} +{"current_steps": 4450, "total_steps": 122600, "loss": 0.2617, "lr": 1.814437194127243e-05, "epoch": 0.7259380097879282, "percentage": 3.63, "elapsed_time": "0:32:12", "remaining_time": "14:15:03", "throughput": 4986.43, "total_tokens": 9635168} +{"current_steps": 4455, "total_steps": 122600, "loss": 0.2748, "lr": 1.8164763458401307e-05, "epoch": 0.7267536704730831, "percentage": 3.63, "elapsed_time": "0:32:14", "remaining_time": "14:14:56", "throughput": 4986.44, "total_tokens": 9645280} +{"current_steps": 4460, "total_steps": 122600, "loss": 0.1309, "lr": 1.818515497553018e-05, "epoch": 0.7275693311582382, "percentage": 3.64, "elapsed_time": "0:32:16", "remaining_time": "14:14:55", "throughput": 4986.37, "total_tokens": 9656032} +{"current_steps": 4465, "total_steps": 122600, "loss": 0.2864, "lr": 1.8205546492659054e-05, "epoch": 0.7283849918433931, "percentage": 3.64, "elapsed_time": "0:32:18", "remaining_time": "14:14:58", "throughput": 4986.41, "total_tokens": 9667968} +{"current_steps": 4470, "total_steps": 122600, "loss": 0.0962, "lr": 1.8225938009787928e-05, "epoch": 0.7292006525285482, "percentage": 3.65, "elapsed_time": "0:32:21", "remaining_time": "14:15:03", "throughput": 4986.37, "total_tokens": 9680032} +{"current_steps": 4475, "total_steps": 122600, "loss": 0.2624, "lr": 1.8246329526916802e-05, "epoch": 0.7300163132137031, "percentage": 3.65, "elapsed_time": "0:32:23", "remaining_time": "14:15:04", "throughput": 4986.36, "total_tokens": 9691424} +{"current_steps": 4480, "total_steps": 122600, "loss": 0.2629, "lr": 1.826672104404568e-05, "epoch": 0.7308319738988581, "percentage": 3.65, "elapsed_time": "0:32:25", "remaining_time": "14:15:02", "throughput": 4986.35, "total_tokens": 9702400} +{"current_steps": 4485, "total_steps": 122600, "loss": 0.0727, "lr": 1.8287112561174553e-05, "epoch": 0.731647634584013, "percentage": 3.66, "elapsed_time": "0:32:27", "remaining_time": "14:14:59", "throughput": 4986.35, "total_tokens": 9712928} +{"current_steps": 4490, "total_steps": 122600, "loss": 0.5759, "lr": 1.8307504078303427e-05, "epoch": 0.732463295269168, "percentage": 3.66, "elapsed_time": "0:32:29", "remaining_time": "14:14:54", "throughput": 4986.42, "total_tokens": 9723360} +{"current_steps": 4495, "total_steps": 122600, "loss": 0.121, "lr": 1.83278955954323e-05, "epoch": 0.733278955954323, "percentage": 3.67, "elapsed_time": "0:32:32", "remaining_time": "14:14:53", "throughput": 4986.45, "total_tokens": 9734496} +{"current_steps": 4500, "total_steps": 122600, "loss": 0.2252, "lr": 1.8348287112561175e-05, "epoch": 0.734094616639478, "percentage": 3.67, "elapsed_time": "0:32:34", "remaining_time": "14:14:45", "throughput": 4986.44, "total_tokens": 9744288} +{"current_steps": 4505, "total_steps": 122600, "loss": 0.308, "lr": 1.8368678629690052e-05, "epoch": 0.734910277324633, "percentage": 3.67, "elapsed_time": "0:32:36", "remaining_time": "14:14:43", "throughput": 4986.41, "total_tokens": 9755072} +{"current_steps": 4510, "total_steps": 122600, "loss": 0.1591, "lr": 1.8389070146818922e-05, "epoch": 0.7357259380097879, "percentage": 3.68, "elapsed_time": "0:32:38", "remaining_time": "14:14:32", "throughput": 4986.41, "total_tokens": 9764192} +{"current_steps": 4515, "total_steps": 122600, "loss": 0.3258, "lr": 1.84094616639478e-05, "epoch": 0.736541598694943, "percentage": 3.68, "elapsed_time": "0:32:40", "remaining_time": "14:14:32", "throughput": 4986.4, "total_tokens": 9775392} +{"current_steps": 4520, "total_steps": 122600, "loss": 0.1217, "lr": 1.8429853181076673e-05, "epoch": 0.7373572593800979, "percentage": 3.69, "elapsed_time": "0:32:42", "remaining_time": "14:14:22", "throughput": 4986.46, "total_tokens": 9784864} +{"current_steps": 4525, "total_steps": 122600, "loss": 0.0615, "lr": 1.8450244698205547e-05, "epoch": 0.7381729200652528, "percentage": 3.69, "elapsed_time": "0:32:44", "remaining_time": "14:14:24", "throughput": 4986.47, "total_tokens": 9796512} +{"current_steps": 4530, "total_steps": 122600, "loss": 0.122, "lr": 1.847063621533442e-05, "epoch": 0.7389885807504079, "percentage": 3.69, "elapsed_time": "0:32:47", "remaining_time": "14:14:28", "throughput": 4986.45, "total_tokens": 9808416} +{"current_steps": 4535, "total_steps": 122600, "loss": 0.1742, "lr": 1.8491027732463295e-05, "epoch": 0.7398042414355628, "percentage": 3.7, "elapsed_time": "0:32:49", "remaining_time": "14:14:28", "throughput": 4986.39, "total_tokens": 9819552} +{"current_steps": 4540, "total_steps": 122600, "loss": 0.1021, "lr": 1.8511419249592172e-05, "epoch": 0.7406199021207178, "percentage": 3.7, "elapsed_time": "0:32:51", "remaining_time": "14:14:29", "throughput": 4986.42, "total_tokens": 9831168} +{"current_steps": 4545, "total_steps": 122600, "loss": 0.0776, "lr": 1.8531810766721046e-05, "epoch": 0.7414355628058727, "percentage": 3.71, "elapsed_time": "0:32:53", "remaining_time": "14:14:23", "throughput": 4986.49, "total_tokens": 9841280} +{"current_steps": 4550, "total_steps": 122600, "loss": 0.2205, "lr": 1.855220228384992e-05, "epoch": 0.7422512234910277, "percentage": 3.71, "elapsed_time": "0:32:55", "remaining_time": "14:14:21", "throughput": 4986.53, "total_tokens": 9852224} +{"current_steps": 4555, "total_steps": 122600, "loss": 0.3931, "lr": 1.8572593800978793e-05, "epoch": 0.7430668841761827, "percentage": 3.72, "elapsed_time": "0:32:57", "remaining_time": "14:14:17", "throughput": 4986.48, "total_tokens": 9862656} +{"current_steps": 4560, "total_steps": 122600, "loss": 0.0372, "lr": 1.8592985318107667e-05, "epoch": 0.7438825448613376, "percentage": 3.72, "elapsed_time": "0:33:00", "remaining_time": "14:14:19", "throughput": 4986.52, "total_tokens": 9874304} +{"current_steps": 4565, "total_steps": 122600, "loss": 0.1286, "lr": 1.8613376835236544e-05, "epoch": 0.7446982055464927, "percentage": 3.72, "elapsed_time": "0:33:02", "remaining_time": "14:14:11", "throughput": 4986.6, "total_tokens": 9884128} +{"current_steps": 4570, "total_steps": 122600, "loss": 0.1248, "lr": 1.8633768352365415e-05, "epoch": 0.7455138662316476, "percentage": 3.73, "elapsed_time": "0:33:04", "remaining_time": "14:14:05", "throughput": 4986.6, "total_tokens": 9894208} +{"current_steps": 4575, "total_steps": 122600, "loss": 0.2435, "lr": 1.8654159869494292e-05, "epoch": 0.7463295269168027, "percentage": 3.73, "elapsed_time": "0:33:06", "remaining_time": "14:14:01", "throughput": 4986.64, "total_tokens": 9904864} +{"current_steps": 4580, "total_steps": 122600, "loss": 0.1838, "lr": 1.8674551386623166e-05, "epoch": 0.7471451876019576, "percentage": 3.74, "elapsed_time": "0:33:08", "remaining_time": "14:14:01", "throughput": 4986.6, "total_tokens": 9915904} +{"current_steps": 4585, "total_steps": 122600, "loss": 0.2423, "lr": 1.869494290375204e-05, "epoch": 0.7479608482871125, "percentage": 3.74, "elapsed_time": "0:33:10", "remaining_time": "14:13:55", "throughput": 4986.6, "total_tokens": 9926048} +{"current_steps": 4590, "total_steps": 122600, "loss": 0.0807, "lr": 1.8715334420880914e-05, "epoch": 0.7487765089722676, "percentage": 3.74, "elapsed_time": "0:33:12", "remaining_time": "14:13:52", "throughput": 4986.64, "total_tokens": 9936736} +{"current_steps": 4595, "total_steps": 122600, "loss": 0.1935, "lr": 1.8735725938009787e-05, "epoch": 0.7495921696574225, "percentage": 3.75, "elapsed_time": "0:33:15", "remaining_time": "14:13:59", "throughput": 4986.6, "total_tokens": 9949408} +{"current_steps": 4600, "total_steps": 122600, "loss": 0.0972, "lr": 1.8756117455138665e-05, "epoch": 0.7504078303425775, "percentage": 3.75, "elapsed_time": "0:33:17", "remaining_time": "14:13:57", "throughput": 4986.6, "total_tokens": 9960160} +{"current_steps": 4605, "total_steps": 122600, "loss": 0.227, "lr": 1.877650897226754e-05, "epoch": 0.7512234910277324, "percentage": 3.76, "elapsed_time": "0:33:19", "remaining_time": "14:13:53", "throughput": 4986.6, "total_tokens": 9970624} +{"current_steps": 4610, "total_steps": 122600, "loss": 0.1586, "lr": 1.8796900489396412e-05, "epoch": 0.7520391517128875, "percentage": 3.76, "elapsed_time": "0:33:21", "remaining_time": "14:13:54", "throughput": 4986.62, "total_tokens": 9982080} +{"current_steps": 4615, "total_steps": 122600, "loss": 0.0266, "lr": 1.8817292006525286e-05, "epoch": 0.7528548123980424, "percentage": 3.76, "elapsed_time": "0:33:23", "remaining_time": "14:13:49", "throughput": 4986.64, "total_tokens": 9992480} +{"current_steps": 4620, "total_steps": 122600, "loss": 0.217, "lr": 1.8837683523654163e-05, "epoch": 0.7536704730831973, "percentage": 3.77, "elapsed_time": "0:33:25", "remaining_time": "14:13:43", "throughput": 4986.63, "total_tokens": 10002496} +{"current_steps": 4625, "total_steps": 122600, "loss": 0.3279, "lr": 1.8858075040783034e-05, "epoch": 0.7544861337683524, "percentage": 3.77, "elapsed_time": "0:33:28", "remaining_time": "14:13:41", "throughput": 4986.63, "total_tokens": 10013408} +{"current_steps": 4630, "total_steps": 122600, "loss": 0.1808, "lr": 1.8878466557911908e-05, "epoch": 0.7553017944535073, "percentage": 3.78, "elapsed_time": "0:33:29", "remaining_time": "14:13:32", "throughput": 4986.67, "total_tokens": 10022880} +{"current_steps": 4635, "total_steps": 122600, "loss": 0.108, "lr": 1.8898858075040785e-05, "epoch": 0.7561174551386624, "percentage": 3.78, "elapsed_time": "0:33:32", "remaining_time": "14:13:32", "throughput": 4986.68, "total_tokens": 10034208} +{"current_steps": 4640, "total_steps": 122600, "loss": 0.2018, "lr": 1.891924959216966e-05, "epoch": 0.7569331158238173, "percentage": 3.78, "elapsed_time": "0:33:34", "remaining_time": "14:13:29", "throughput": 4986.65, "total_tokens": 10044832} +{"current_steps": 4645, "total_steps": 122600, "loss": 0.1811, "lr": 1.8939641109298532e-05, "epoch": 0.7577487765089723, "percentage": 3.79, "elapsed_time": "0:33:36", "remaining_time": "14:13:27", "throughput": 4986.71, "total_tokens": 10055712} +{"current_steps": 4650, "total_steps": 122600, "loss": 0.1927, "lr": 1.8960032626427406e-05, "epoch": 0.7585644371941273, "percentage": 3.79, "elapsed_time": "0:33:38", "remaining_time": "14:13:27", "throughput": 4986.64, "total_tokens": 10066976} +{"current_steps": 4655, "total_steps": 122600, "loss": 0.244, "lr": 1.898042414355628e-05, "epoch": 0.7593800978792822, "percentage": 3.8, "elapsed_time": "0:33:41", "remaining_time": "14:13:27", "throughput": 4986.72, "total_tokens": 10078304} +{"current_steps": 4660, "total_steps": 122600, "loss": 0.369, "lr": 1.9000815660685157e-05, "epoch": 0.7601957585644372, "percentage": 3.8, "elapsed_time": "0:33:43", "remaining_time": "14:13:24", "throughput": 4986.77, "total_tokens": 10089056} +{"current_steps": 4665, "total_steps": 122600, "loss": 0.2619, "lr": 1.902120717781403e-05, "epoch": 0.7610114192495921, "percentage": 3.81, "elapsed_time": "0:33:45", "remaining_time": "14:13:21", "throughput": 4986.87, "total_tokens": 10099904} +{"current_steps": 4670, "total_steps": 122600, "loss": 0.0881, "lr": 1.9041598694942905e-05, "epoch": 0.7618270799347472, "percentage": 3.81, "elapsed_time": "0:33:47", "remaining_time": "14:13:23", "throughput": 4986.84, "total_tokens": 10111552} +{"current_steps": 4675, "total_steps": 122600, "loss": 0.2715, "lr": 1.906199021207178e-05, "epoch": 0.7626427406199021, "percentage": 3.81, "elapsed_time": "0:33:49", "remaining_time": "14:13:17", "throughput": 4986.82, "total_tokens": 10121568} +{"current_steps": 4680, "total_steps": 122600, "loss": 0.2534, "lr": 1.9082381729200656e-05, "epoch": 0.763458401305057, "percentage": 3.82, "elapsed_time": "0:33:51", "remaining_time": "14:13:12", "throughput": 4986.93, "total_tokens": 10132000} +{"current_steps": 4685, "total_steps": 122600, "loss": 0.1696, "lr": 1.9102773246329526e-05, "epoch": 0.7642740619902121, "percentage": 3.82, "elapsed_time": "0:33:53", "remaining_time": "14:13:06", "throughput": 4986.86, "total_tokens": 10141952} +{"current_steps": 4690, "total_steps": 122600, "loss": 0.1331, "lr": 1.91231647634584e-05, "epoch": 0.765089722675367, "percentage": 3.83, "elapsed_time": "0:33:55", "remaining_time": "14:12:58", "throughput": 4986.95, "total_tokens": 10151776} +{"current_steps": 4695, "total_steps": 122600, "loss": 0.1812, "lr": 1.9143556280587277e-05, "epoch": 0.765905383360522, "percentage": 3.83, "elapsed_time": "0:33:57", "remaining_time": "14:12:56", "throughput": 4986.91, "total_tokens": 10162688} +{"current_steps": 4700, "total_steps": 122600, "loss": 0.0239, "lr": 1.916394779771615e-05, "epoch": 0.766721044045677, "percentage": 3.83, "elapsed_time": "0:34:00", "remaining_time": "14:12:59", "throughput": 4986.95, "total_tokens": 10174624} +{"current_steps": 4705, "total_steps": 122600, "loss": 0.0914, "lr": 1.9184339314845025e-05, "epoch": 0.767536704730832, "percentage": 3.84, "elapsed_time": "0:34:02", "remaining_time": "14:12:56", "throughput": 4986.97, "total_tokens": 10185248} +{"current_steps": 4710, "total_steps": 122600, "loss": 0.0583, "lr": 1.92047308319739e-05, "epoch": 0.768352365415987, "percentage": 3.84, "elapsed_time": "0:34:04", "remaining_time": "14:12:58", "throughput": 4986.93, "total_tokens": 10196768} +{"current_steps": 4715, "total_steps": 122600, "loss": 0.0826, "lr": 1.9225122349102776e-05, "epoch": 0.7691680261011419, "percentage": 3.85, "elapsed_time": "0:34:06", "remaining_time": "14:12:51", "throughput": 4986.99, "total_tokens": 10206816} +{"current_steps": 4720, "total_steps": 122600, "loss": 0.1108, "lr": 1.924551386623165e-05, "epoch": 0.7699836867862969, "percentage": 3.85, "elapsed_time": "0:34:08", "remaining_time": "14:12:49", "throughput": 4986.93, "total_tokens": 10217600} +{"current_steps": 4725, "total_steps": 122600, "loss": 0.1994, "lr": 1.926590538336052e-05, "epoch": 0.7707993474714518, "percentage": 3.85, "elapsed_time": "0:34:11", "remaining_time": "14:12:47", "throughput": 4986.98, "total_tokens": 10228544} +{"current_steps": 4730, "total_steps": 122600, "loss": 0.1391, "lr": 1.9286296900489398e-05, "epoch": 0.7716150081566069, "percentage": 3.86, "elapsed_time": "0:34:13", "remaining_time": "14:12:44", "throughput": 4986.97, "total_tokens": 10239168} +{"current_steps": 4735, "total_steps": 122600, "loss": 0.1631, "lr": 1.930668841761827e-05, "epoch": 0.7724306688417618, "percentage": 3.86, "elapsed_time": "0:34:15", "remaining_time": "14:12:46", "throughput": 4986.96, "total_tokens": 10250784} +{"current_steps": 4740, "total_steps": 122600, "loss": 0.0676, "lr": 1.932707993474715e-05, "epoch": 0.7732463295269169, "percentage": 3.87, "elapsed_time": "0:34:17", "remaining_time": "14:12:39", "throughput": 4986.93, "total_tokens": 10260480} +{"current_steps": 4745, "total_steps": 122600, "loss": 0.2181, "lr": 1.934747145187602e-05, "epoch": 0.7740619902120718, "percentage": 3.87, "elapsed_time": "0:34:19", "remaining_time": "14:12:40", "throughput": 4986.92, "total_tokens": 10272064} +{"current_steps": 4750, "total_steps": 122600, "loss": 0.0817, "lr": 1.9367862969004896e-05, "epoch": 0.7748776508972267, "percentage": 3.87, "elapsed_time": "0:34:21", "remaining_time": "14:12:31", "throughput": 4986.9, "total_tokens": 10281472} +{"current_steps": 4755, "total_steps": 122600, "loss": 0.1089, "lr": 1.938825448613377e-05, "epoch": 0.7756933115823818, "percentage": 3.88, "elapsed_time": "0:34:24", "remaining_time": "14:12:35", "throughput": 4986.89, "total_tokens": 10293536} +{"current_steps": 4760, "total_steps": 122600, "loss": 0.1255, "lr": 1.9408646003262644e-05, "epoch": 0.7765089722675367, "percentage": 3.88, "elapsed_time": "0:34:26", "remaining_time": "14:12:32", "throughput": 4986.86, "total_tokens": 10303968} +{"current_steps": 4765, "total_steps": 122600, "loss": 0.085, "lr": 1.9429037520391518e-05, "epoch": 0.7773246329526917, "percentage": 3.89, "elapsed_time": "0:34:28", "remaining_time": "14:12:36", "throughput": 4986.87, "total_tokens": 10316064} +{"current_steps": 4770, "total_steps": 122600, "loss": 0.1315, "lr": 1.944942903752039e-05, "epoch": 0.7781402936378466, "percentage": 3.89, "elapsed_time": "0:34:30", "remaining_time": "14:12:36", "throughput": 4986.82, "total_tokens": 10327328} +{"current_steps": 4775, "total_steps": 122600, "loss": 0.273, "lr": 1.946982055464927e-05, "epoch": 0.7789559543230016, "percentage": 3.89, "elapsed_time": "0:34:32", "remaining_time": "14:12:29", "throughput": 4986.84, "total_tokens": 10337088} +{"current_steps": 4780, "total_steps": 122600, "loss": 0.3135, "lr": 1.9490212071778143e-05, "epoch": 0.7797716150081566, "percentage": 3.9, "elapsed_time": "0:34:34", "remaining_time": "14:12:25", "throughput": 4986.8, "total_tokens": 10347488} +{"current_steps": 4785, "total_steps": 122600, "loss": 0.3207, "lr": 1.9510603588907013e-05, "epoch": 0.7805872756933115, "percentage": 3.9, "elapsed_time": "0:34:37", "remaining_time": "14:12:24", "throughput": 4986.8, "total_tokens": 10358656} +{"current_steps": 4790, "total_steps": 122600, "loss": 0.172, "lr": 1.953099510603589e-05, "epoch": 0.7814029363784666, "percentage": 3.91, "elapsed_time": "0:34:39", "remaining_time": "14:12:29", "throughput": 4986.73, "total_tokens": 10370816} +{"current_steps": 4795, "total_steps": 122600, "loss": 0.0673, "lr": 1.9551386623164764e-05, "epoch": 0.7822185970636215, "percentage": 3.91, "elapsed_time": "0:34:41", "remaining_time": "14:12:28", "throughput": 4986.78, "total_tokens": 10381856} +{"current_steps": 4800, "total_steps": 122600, "loss": 0.2123, "lr": 1.957177814029364e-05, "epoch": 0.7830342577487766, "percentage": 3.92, "elapsed_time": "0:34:43", "remaining_time": "14:12:23", "throughput": 4986.84, "total_tokens": 10392320} +{"current_steps": 4805, "total_steps": 122600, "loss": 0.284, "lr": 1.959216965742251e-05, "epoch": 0.7838499184339315, "percentage": 3.92, "elapsed_time": "0:34:45", "remaining_time": "14:12:13", "throughput": 4986.83, "total_tokens": 10401568} +{"current_steps": 4810, "total_steps": 122600, "loss": 0.1634, "lr": 1.961256117455139e-05, "epoch": 0.7846655791190864, "percentage": 3.92, "elapsed_time": "0:34:48", "remaining_time": "14:12:15", "throughput": 4986.87, "total_tokens": 10413248} +{"current_steps": 4815, "total_steps": 122600, "loss": 0.0796, "lr": 1.9632952691680263e-05, "epoch": 0.7854812398042414, "percentage": 3.93, "elapsed_time": "0:34:50", "remaining_time": "14:12:08", "throughput": 4986.9, "total_tokens": 10423168} +{"current_steps": 4820, "total_steps": 122600, "loss": 0.1722, "lr": 1.9653344208809136e-05, "epoch": 0.7862969004893964, "percentage": 3.93, "elapsed_time": "0:34:52", "remaining_time": "14:12:05", "throughput": 4986.9, "total_tokens": 10433792} +{"current_steps": 4825, "total_steps": 122600, "loss": 0.1737, "lr": 1.967373572593801e-05, "epoch": 0.7871125611745514, "percentage": 3.94, "elapsed_time": "0:34:54", "remaining_time": "14:12:05", "throughput": 4986.89, "total_tokens": 10445120} +{"current_steps": 4830, "total_steps": 122600, "loss": 0.2057, "lr": 1.9694127243066884e-05, "epoch": 0.7879282218597063, "percentage": 3.94, "elapsed_time": "0:34:56", "remaining_time": "14:12:02", "throughput": 4986.81, "total_tokens": 10455584} +{"current_steps": 4835, "total_steps": 122600, "loss": 0.089, "lr": 1.971451876019576e-05, "epoch": 0.7887438825448614, "percentage": 3.94, "elapsed_time": "0:34:58", "remaining_time": "14:12:02", "throughput": 4986.77, "total_tokens": 10466752} +{"current_steps": 4840, "total_steps": 122600, "loss": 0.2318, "lr": 1.9734910277324635e-05, "epoch": 0.7895595432300163, "percentage": 3.95, "elapsed_time": "0:35:01", "remaining_time": "14:11:59", "throughput": 4986.8, "total_tokens": 10477376} +{"current_steps": 4845, "total_steps": 122600, "loss": 0.1767, "lr": 1.975530179445351e-05, "epoch": 0.7903752039151712, "percentage": 3.95, "elapsed_time": "0:35:03", "remaining_time": "14:11:53", "throughput": 4986.78, "total_tokens": 10487392} +{"current_steps": 4850, "total_steps": 122600, "loss": 0.3594, "lr": 1.9775693311582383e-05, "epoch": 0.7911908646003263, "percentage": 3.96, "elapsed_time": "0:35:05", "remaining_time": "14:11:50", "throughput": 4986.78, "total_tokens": 10498208} +{"current_steps": 4855, "total_steps": 122600, "loss": 0.1194, "lr": 1.9796084828711257e-05, "epoch": 0.7920065252854812, "percentage": 3.96, "elapsed_time": "0:35:07", "remaining_time": "14:11:40", "throughput": 4986.77, "total_tokens": 10507200} +{"current_steps": 4860, "total_steps": 122600, "loss": 0.1535, "lr": 1.981647634584013e-05, "epoch": 0.7928221859706363, "percentage": 3.96, "elapsed_time": "0:35:08", "remaining_time": "14:11:29", "throughput": 4986.83, "total_tokens": 10516416} +{"current_steps": 4865, "total_steps": 122600, "loss": 0.2233, "lr": 1.9836867862969004e-05, "epoch": 0.7936378466557912, "percentage": 3.97, "elapsed_time": "0:35:11", "remaining_time": "14:11:28", "throughput": 4986.86, "total_tokens": 10527648} +{"current_steps": 4870, "total_steps": 122600, "loss": 0.0481, "lr": 1.985725938009788e-05, "epoch": 0.7944535073409462, "percentage": 3.97, "elapsed_time": "0:35:13", "remaining_time": "14:11:24", "throughput": 4986.87, "total_tokens": 10537952} +{"current_steps": 4875, "total_steps": 122600, "loss": 0.1564, "lr": 1.9877650897226755e-05, "epoch": 0.7952691680261011, "percentage": 3.98, "elapsed_time": "0:35:15", "remaining_time": "14:11:18", "throughput": 4987.0, "total_tokens": 10548320} +{"current_steps": 4880, "total_steps": 122600, "loss": 0.164, "lr": 1.989804241435563e-05, "epoch": 0.7960848287112561, "percentage": 3.98, "elapsed_time": "0:35:17", "remaining_time": "14:11:10", "throughput": 4986.95, "total_tokens": 10557824} +{"current_steps": 4885, "total_steps": 122600, "loss": 0.0413, "lr": 1.9918433931484503e-05, "epoch": 0.7969004893964111, "percentage": 3.98, "elapsed_time": "0:35:19", "remaining_time": "14:11:10", "throughput": 4986.86, "total_tokens": 10568896} +{"current_steps": 4890, "total_steps": 122600, "loss": 0.3596, "lr": 1.9938825448613377e-05, "epoch": 0.797716150081566, "percentage": 3.99, "elapsed_time": "0:35:21", "remaining_time": "14:11:10", "throughput": 4986.82, "total_tokens": 10580064} +{"current_steps": 4895, "total_steps": 122600, "loss": 0.1764, "lr": 1.9959216965742254e-05, "epoch": 0.7985318107667211, "percentage": 3.99, "elapsed_time": "0:35:23", "remaining_time": "14:11:08", "throughput": 4986.83, "total_tokens": 10590976} +{"current_steps": 4900, "total_steps": 122600, "loss": 0.1711, "lr": 1.9979608482871124e-05, "epoch": 0.799347471451876, "percentage": 4.0, "elapsed_time": "0:35:25", "remaining_time": "14:10:59", "throughput": 4986.89, "total_tokens": 10600448} +{"current_steps": 4905, "total_steps": 122600, "loss": 0.2006, "lr": 2e-05, "epoch": 0.8001631321370309, "percentage": 4.0, "elapsed_time": "0:35:27", "remaining_time": "14:11:00", "throughput": 4986.87, "total_tokens": 10611904} +{"current_steps": 4910, "total_steps": 122600, "loss": 0.1323, "lr": 2.0020391517128875e-05, "epoch": 0.800978792822186, "percentage": 4.0, "elapsed_time": "0:35:30", "remaining_time": "14:10:56", "throughput": 4986.85, "total_tokens": 10622240} +{"current_steps": 4915, "total_steps": 122600, "loss": 0.3223, "lr": 2.004078303425775e-05, "epoch": 0.8017944535073409, "percentage": 4.01, "elapsed_time": "0:35:32", "remaining_time": "14:10:52", "throughput": 4986.86, "total_tokens": 10632864} +{"current_steps": 4920, "total_steps": 122600, "loss": 0.0925, "lr": 2.0061174551386623e-05, "epoch": 0.802610114192496, "percentage": 4.01, "elapsed_time": "0:35:34", "remaining_time": "14:10:44", "throughput": 4986.88, "total_tokens": 10642464} +{"current_steps": 4925, "total_steps": 122600, "loss": 0.171, "lr": 2.0081566068515497e-05, "epoch": 0.8034257748776509, "percentage": 4.02, "elapsed_time": "0:35:36", "remaining_time": "14:10:41", "throughput": 4986.87, "total_tokens": 10653024} +{"current_steps": 4930, "total_steps": 122600, "loss": 0.1613, "lr": 2.0101957585644374e-05, "epoch": 0.8042414355628059, "percentage": 4.02, "elapsed_time": "0:35:38", "remaining_time": "14:10:41", "throughput": 4986.92, "total_tokens": 10664384} +{"current_steps": 4935, "total_steps": 122600, "loss": 0.3286, "lr": 2.0122349102773248e-05, "epoch": 0.8050570962479608, "percentage": 4.03, "elapsed_time": "0:35:40", "remaining_time": "14:10:39", "throughput": 4986.95, "total_tokens": 10675360} +{"current_steps": 4940, "total_steps": 122600, "loss": 0.1887, "lr": 2.0142740619902122e-05, "epoch": 0.8058727569331158, "percentage": 4.03, "elapsed_time": "0:35:42", "remaining_time": "14:10:35", "throughput": 4986.98, "total_tokens": 10685824} +{"current_steps": 4945, "total_steps": 122600, "loss": 0.2242, "lr": 2.0163132137030996e-05, "epoch": 0.8066884176182708, "percentage": 4.03, "elapsed_time": "0:35:45", "remaining_time": "14:10:37", "throughput": 4986.94, "total_tokens": 10697536} +{"current_steps": 4950, "total_steps": 122600, "loss": 0.0984, "lr": 2.018352365415987e-05, "epoch": 0.8075040783034257, "percentage": 4.04, "elapsed_time": "0:35:47", "remaining_time": "14:10:43", "throughput": 4986.93, "total_tokens": 10709888} +{"current_steps": 4955, "total_steps": 122600, "loss": 0.1, "lr": 2.0203915171288747e-05, "epoch": 0.8083197389885808, "percentage": 4.04, "elapsed_time": "0:35:49", "remaining_time": "14:10:43", "throughput": 4986.92, "total_tokens": 10721216} +{"current_steps": 4960, "total_steps": 122600, "loss": 0.0954, "lr": 2.0224306688417617e-05, "epoch": 0.8091353996737357, "percentage": 4.05, "elapsed_time": "0:35:51", "remaining_time": "14:10:31", "throughput": 4986.9, "total_tokens": 10729952} +{"current_steps": 4965, "total_steps": 122600, "loss": 0.1188, "lr": 2.0244698205546494e-05, "epoch": 0.8099510603588908, "percentage": 4.05, "elapsed_time": "0:35:53", "remaining_time": "14:10:31", "throughput": 4986.92, "total_tokens": 10741216} +{"current_steps": 4970, "total_steps": 122600, "loss": 0.1811, "lr": 2.0265089722675368e-05, "epoch": 0.8107667210440457, "percentage": 4.05, "elapsed_time": "0:35:56", "remaining_time": "14:10:31", "throughput": 4986.91, "total_tokens": 10752544} +{"current_steps": 4975, "total_steps": 122600, "loss": 0.2101, "lr": 2.0285481239804245e-05, "epoch": 0.8115823817292006, "percentage": 4.06, "elapsed_time": "0:35:58", "remaining_time": "14:10:36", "throughput": 4986.94, "total_tokens": 10764960} +{"current_steps": 4980, "total_steps": 122600, "loss": 0.0936, "lr": 2.0305872756933116e-05, "epoch": 0.8123980424143556, "percentage": 4.06, "elapsed_time": "0:36:00", "remaining_time": "14:10:33", "throughput": 4986.85, "total_tokens": 10775296} +{"current_steps": 4985, "total_steps": 122600, "loss": 0.1795, "lr": 2.032626427406199e-05, "epoch": 0.8132137030995106, "percentage": 4.07, "elapsed_time": "0:36:02", "remaining_time": "14:10:30", "throughput": 4986.88, "total_tokens": 10786112} +{"current_steps": 4990, "total_steps": 122600, "loss": 0.1646, "lr": 2.0346655791190867e-05, "epoch": 0.8140293637846656, "percentage": 4.07, "elapsed_time": "0:36:05", "remaining_time": "14:10:30", "throughput": 4986.85, "total_tokens": 10797152} +{"current_steps": 4995, "total_steps": 122600, "loss": 0.2062, "lr": 2.036704730831974e-05, "epoch": 0.8148450244698205, "percentage": 4.07, "elapsed_time": "0:36:07", "remaining_time": "14:10:30", "throughput": 4986.87, "total_tokens": 10808480} +{"current_steps": 5000, "total_steps": 122600, "loss": 0.0847, "lr": 2.0387438825448614e-05, "epoch": 0.8156606851549756, "percentage": 4.08, "elapsed_time": "0:36:09", "remaining_time": "14:10:28", "throughput": 4986.85, "total_tokens": 10819424} +{"current_steps": 5005, "total_steps": 122600, "loss": 0.1871, "lr": 2.0407830342577488e-05, "epoch": 0.8164763458401305, "percentage": 4.08, "elapsed_time": "0:36:11", "remaining_time": "14:10:26", "throughput": 4986.8, "total_tokens": 10830048} +{"current_steps": 5010, "total_steps": 122600, "loss": 0.2137, "lr": 2.0428221859706362e-05, "epoch": 0.8172920065252854, "percentage": 4.09, "elapsed_time": "0:36:13", "remaining_time": "14:10:23", "throughput": 4986.76, "total_tokens": 10840768} +{"current_steps": 5015, "total_steps": 122600, "loss": 0.1949, "lr": 2.044861337683524e-05, "epoch": 0.8181076672104405, "percentage": 4.09, "elapsed_time": "0:36:15", "remaining_time": "14:10:13", "throughput": 4986.78, "total_tokens": 10849792} +{"current_steps": 5020, "total_steps": 122600, "loss": 0.0341, "lr": 2.046900489396411e-05, "epoch": 0.8189233278955954, "percentage": 4.09, "elapsed_time": "0:36:18", "remaining_time": "14:10:15", "throughput": 4986.69, "total_tokens": 10861472} +{"current_steps": 5025, "total_steps": 122600, "loss": 0.176, "lr": 2.0489396411092987e-05, "epoch": 0.8197389885807504, "percentage": 4.1, "elapsed_time": "0:36:20", "remaining_time": "14:10:13", "throughput": 4986.59, "total_tokens": 10871968} +{"current_steps": 5030, "total_steps": 122600, "loss": 0.222, "lr": 2.050978792822186e-05, "epoch": 0.8205546492659054, "percentage": 4.1, "elapsed_time": "0:36:22", "remaining_time": "14:10:09", "throughput": 4986.61, "total_tokens": 10882560} +{"current_steps": 5035, "total_steps": 122600, "loss": 0.1755, "lr": 2.0530179445350735e-05, "epoch": 0.8213703099510603, "percentage": 4.11, "elapsed_time": "0:36:24", "remaining_time": "14:10:11", "throughput": 4986.56, "total_tokens": 10894048} +{"current_steps": 5040, "total_steps": 122600, "loss": 0.2418, "lr": 2.055057096247961e-05, "epoch": 0.8221859706362153, "percentage": 4.11, "elapsed_time": "0:36:26", "remaining_time": "14:10:11", "throughput": 4986.6, "total_tokens": 10905408} +{"current_steps": 5045, "total_steps": 122600, "loss": 0.1268, "lr": 2.0570962479608482e-05, "epoch": 0.8230016313213703, "percentage": 4.12, "elapsed_time": "0:36:28", "remaining_time": "14:10:06", "throughput": 4986.64, "total_tokens": 10915648} +{"current_steps": 5050, "total_steps": 122600, "loss": 0.1598, "lr": 2.059135399673736e-05, "epoch": 0.8238172920065253, "percentage": 4.12, "elapsed_time": "0:36:31", "remaining_time": "14:10:06", "throughput": 4986.6, "total_tokens": 10926880} +{"current_steps": 5055, "total_steps": 122600, "loss": 0.2375, "lr": 2.0611745513866233e-05, "epoch": 0.8246329526916802, "percentage": 4.12, "elapsed_time": "0:36:33", "remaining_time": "14:10:07", "throughput": 4986.63, "total_tokens": 10938432} +{"current_steps": 5060, "total_steps": 122600, "loss": 0.2654, "lr": 2.0632137030995107e-05, "epoch": 0.8254486133768353, "percentage": 4.13, "elapsed_time": "0:36:35", "remaining_time": "14:10:03", "throughput": 4986.65, "total_tokens": 10948992} +{"current_steps": 5065, "total_steps": 122600, "loss": 0.2703, "lr": 2.065252854812398e-05, "epoch": 0.8262642740619902, "percentage": 4.13, "elapsed_time": "0:36:37", "remaining_time": "14:09:54", "throughput": 4986.65, "total_tokens": 10958272} +{"current_steps": 5070, "total_steps": 122600, "loss": 0.125, "lr": 2.0672920065252858e-05, "epoch": 0.8270799347471451, "percentage": 4.14, "elapsed_time": "0:36:39", "remaining_time": "14:09:49", "throughput": 4986.63, "total_tokens": 10968512} +{"current_steps": 5075, "total_steps": 122600, "loss": 0.1416, "lr": 2.0693311582381732e-05, "epoch": 0.8278955954323002, "percentage": 4.14, "elapsed_time": "0:36:41", "remaining_time": "14:09:46", "throughput": 4986.56, "total_tokens": 10979072} +{"current_steps": 5080, "total_steps": 122600, "loss": 0.1521, "lr": 2.0713703099510602e-05, "epoch": 0.8287112561174551, "percentage": 4.14, "elapsed_time": "0:36:43", "remaining_time": "14:09:39", "throughput": 4986.53, "total_tokens": 10988736} +{"current_steps": 5085, "total_steps": 122600, "loss": 0.1597, "lr": 2.073409461663948e-05, "epoch": 0.8295269168026101, "percentage": 4.15, "elapsed_time": "0:36:46", "remaining_time": "14:09:42", "throughput": 4986.45, "total_tokens": 11000512} +{"current_steps": 5090, "total_steps": 122600, "loss": 0.2225, "lr": 2.0754486133768353e-05, "epoch": 0.8303425774877651, "percentage": 4.15, "elapsed_time": "0:36:48", "remaining_time": "14:09:35", "throughput": 4986.44, "total_tokens": 11010240} +{"current_steps": 5095, "total_steps": 122600, "loss": 0.2447, "lr": 2.0774877650897227e-05, "epoch": 0.8311582381729201, "percentage": 4.16, "elapsed_time": "0:36:50", "remaining_time": "14:09:32", "throughput": 4986.41, "total_tokens": 11020672} +{"current_steps": 5100, "total_steps": 122600, "loss": 0.11, "lr": 2.07952691680261e-05, "epoch": 0.831973898858075, "percentage": 4.16, "elapsed_time": "0:36:52", "remaining_time": "14:09:30", "throughput": 4986.49, "total_tokens": 11031808} +{"current_steps": 5105, "total_steps": 122600, "loss": 0.1357, "lr": 2.0815660685154978e-05, "epoch": 0.83278955954323, "percentage": 4.16, "elapsed_time": "0:36:54", "remaining_time": "14:09:26", "throughput": 4986.5, "total_tokens": 11042144} +{"current_steps": 5110, "total_steps": 122600, "loss": 0.1225, "lr": 2.0836052202283852e-05, "epoch": 0.833605220228385, "percentage": 4.17, "elapsed_time": "0:36:56", "remaining_time": "14:09:27", "throughput": 4986.46, "total_tokens": 11053728} +{"current_steps": 5115, "total_steps": 122600, "loss": 0.2429, "lr": 2.0856443719412726e-05, "epoch": 0.8344208809135399, "percentage": 4.17, "elapsed_time": "0:36:58", "remaining_time": "14:09:22", "throughput": 4986.5, "total_tokens": 11064032} +{"current_steps": 5120, "total_steps": 122600, "loss": 0.2549, "lr": 2.08768352365416e-05, "epoch": 0.835236541598695, "percentage": 4.18, "elapsed_time": "0:37:00", "remaining_time": "14:09:15", "throughput": 4986.5, "total_tokens": 11073792} +{"current_steps": 5125, "total_steps": 122600, "loss": 0.096, "lr": 2.0897226753670474e-05, "epoch": 0.8360522022838499, "percentage": 4.18, "elapsed_time": "0:37:03", "remaining_time": "14:09:16", "throughput": 4986.54, "total_tokens": 11085216} +{"current_steps": 5130, "total_steps": 122600, "loss": 0.2858, "lr": 2.091761827079935e-05, "epoch": 0.8368678629690048, "percentage": 4.18, "elapsed_time": "0:37:05", "remaining_time": "14:09:15", "throughput": 4986.53, "total_tokens": 11096288} +{"current_steps": 5135, "total_steps": 122600, "loss": 0.1461, "lr": 2.093800978792822e-05, "epoch": 0.8376835236541599, "percentage": 4.19, "elapsed_time": "0:37:07", "remaining_time": "14:09:16", "throughput": 4986.45, "total_tokens": 11107584} +{"current_steps": 5140, "total_steps": 122600, "loss": 0.092, "lr": 2.0958401305057095e-05, "epoch": 0.8384991843393148, "percentage": 4.19, "elapsed_time": "0:37:09", "remaining_time": "14:09:16", "throughput": 4986.39, "total_tokens": 11118752} +{"current_steps": 5145, "total_steps": 122600, "loss": 0.1345, "lr": 2.0978792822185972e-05, "epoch": 0.8393148450244698, "percentage": 4.2, "elapsed_time": "0:37:11", "remaining_time": "14:09:06", "throughput": 4986.36, "total_tokens": 11127840} +{"current_steps": 5150, "total_steps": 122600, "loss": 0.1755, "lr": 2.0999184339314846e-05, "epoch": 0.8401305057096248, "percentage": 4.2, "elapsed_time": "0:37:13", "remaining_time": "14:09:00", "throughput": 4986.41, "total_tokens": 11137952} +{"current_steps": 5155, "total_steps": 122600, "loss": 0.1542, "lr": 2.101957585644372e-05, "epoch": 0.8409461663947798, "percentage": 4.2, "elapsed_time": "0:37:15", "remaining_time": "14:08:50", "throughput": 4986.39, "total_tokens": 11147008} +{"current_steps": 5160, "total_steps": 122600, "loss": 0.1156, "lr": 2.1039967373572594e-05, "epoch": 0.8417618270799347, "percentage": 4.21, "elapsed_time": "0:37:17", "remaining_time": "14:08:54", "throughput": 4986.32, "total_tokens": 11158912} +{"current_steps": 5165, "total_steps": 122600, "loss": 0.1068, "lr": 2.106035889070147e-05, "epoch": 0.8425774877650897, "percentage": 4.21, "elapsed_time": "0:37:20", "remaining_time": "14:08:50", "throughput": 4986.33, "total_tokens": 11169440} +{"current_steps": 5170, "total_steps": 122600, "loss": 0.2052, "lr": 2.1080750407830345e-05, "epoch": 0.8433931484502447, "percentage": 4.22, "elapsed_time": "0:37:21", "remaining_time": "14:08:44", "throughput": 4986.39, "total_tokens": 11179488} +{"current_steps": 5175, "total_steps": 122600, "loss": 0.2445, "lr": 2.1101141924959215e-05, "epoch": 0.8442088091353996, "percentage": 4.22, "elapsed_time": "0:37:24", "remaining_time": "14:08:44", "throughput": 4986.39, "total_tokens": 11190912} +{"current_steps": 5180, "total_steps": 122600, "loss": 0.1913, "lr": 2.1121533442088092e-05, "epoch": 0.8450244698205547, "percentage": 4.23, "elapsed_time": "0:37:26", "remaining_time": "14:08:45", "throughput": 4986.31, "total_tokens": 11202208} +{"current_steps": 5185, "total_steps": 122600, "loss": 0.3169, "lr": 2.1141924959216966e-05, "epoch": 0.8458401305057096, "percentage": 4.23, "elapsed_time": "0:37:28", "remaining_time": "14:08:40", "throughput": 4986.33, "total_tokens": 11212448} +{"current_steps": 5190, "total_steps": 122600, "loss": 0.1771, "lr": 2.1162316476345843e-05, "epoch": 0.8466557911908646, "percentage": 4.23, "elapsed_time": "0:37:30", "remaining_time": "14:08:40", "throughput": 4986.29, "total_tokens": 11223648} +{"current_steps": 5195, "total_steps": 122600, "loss": 0.2278, "lr": 2.1182707993474714e-05, "epoch": 0.8474714518760196, "percentage": 4.24, "elapsed_time": "0:37:33", "remaining_time": "14:08:40", "throughput": 4986.25, "total_tokens": 11234880} +{"current_steps": 5200, "total_steps": 122600, "loss": 0.1136, "lr": 2.120309951060359e-05, "epoch": 0.8482871125611745, "percentage": 4.24, "elapsed_time": "0:37:35", "remaining_time": "14:08:35", "throughput": 4986.32, "total_tokens": 11245184} +{"current_steps": 5205, "total_steps": 122600, "loss": 0.1236, "lr": 2.1223491027732465e-05, "epoch": 0.8491027732463295, "percentage": 4.25, "elapsed_time": "0:37:37", "remaining_time": "14:08:35", "throughput": 4986.28, "total_tokens": 11256288} +{"current_steps": 5210, "total_steps": 122600, "loss": 0.1647, "lr": 2.124388254486134e-05, "epoch": 0.8499184339314845, "percentage": 4.25, "elapsed_time": "0:37:39", "remaining_time": "14:08:25", "throughput": 4986.38, "total_tokens": 11265728} +{"current_steps": 5215, "total_steps": 122600, "loss": 0.1402, "lr": 2.1264274061990213e-05, "epoch": 0.8507340946166395, "percentage": 4.25, "elapsed_time": "0:37:41", "remaining_time": "14:08:20", "throughput": 4986.33, "total_tokens": 11275712} +{"current_steps": 5220, "total_steps": 122600, "loss": 0.1226, "lr": 2.1284665579119086e-05, "epoch": 0.8515497553017944, "percentage": 4.26, "elapsed_time": "0:37:43", "remaining_time": "14:08:24", "throughput": 4986.28, "total_tokens": 11287776} +{"current_steps": 5225, "total_steps": 122600, "loss": 0.1594, "lr": 2.1305057096247964e-05, "epoch": 0.8523654159869495, "percentage": 4.26, "elapsed_time": "0:37:45", "remaining_time": "14:08:22", "throughput": 4986.26, "total_tokens": 11298528} +{"current_steps": 5230, "total_steps": 122600, "loss": 0.2644, "lr": 2.1325448613376837e-05, "epoch": 0.8531810766721044, "percentage": 4.27, "elapsed_time": "0:37:48", "remaining_time": "14:08:21", "throughput": 4986.24, "total_tokens": 11309536} +{"current_steps": 5235, "total_steps": 122600, "loss": 0.3404, "lr": 2.1345840130505708e-05, "epoch": 0.8539967373572593, "percentage": 4.27, "elapsed_time": "0:37:50", "remaining_time": "14:08:13", "throughput": 4986.22, "total_tokens": 11319200} +{"current_steps": 5240, "total_steps": 122600, "loss": 0.1437, "lr": 2.1366231647634585e-05, "epoch": 0.8548123980424144, "percentage": 4.27, "elapsed_time": "0:37:52", "remaining_time": "14:08:08", "throughput": 4986.17, "total_tokens": 11329120} +{"current_steps": 5245, "total_steps": 122600, "loss": 0.1569, "lr": 2.138662316476346e-05, "epoch": 0.8556280587275693, "percentage": 4.28, "elapsed_time": "0:37:54", "remaining_time": "14:08:03", "throughput": 4986.15, "total_tokens": 11339360} +{"current_steps": 5250, "total_steps": 122600, "loss": 0.2654, "lr": 2.1407014681892336e-05, "epoch": 0.8564437194127243, "percentage": 4.28, "elapsed_time": "0:37:56", "remaining_time": "14:08:05", "throughput": 4986.08, "total_tokens": 11350848} +{"current_steps": 5255, "total_steps": 122600, "loss": 0.16, "lr": 2.1427406199021206e-05, "epoch": 0.8572593800978793, "percentage": 4.29, "elapsed_time": "0:37:58", "remaining_time": "14:07:58", "throughput": 4986.1, "total_tokens": 11360704} +{"current_steps": 5260, "total_steps": 122600, "loss": 0.1137, "lr": 2.1447797716150084e-05, "epoch": 0.8580750407830342, "percentage": 4.29, "elapsed_time": "0:38:00", "remaining_time": "14:07:53", "throughput": 4986.06, "total_tokens": 11370816} +{"current_steps": 5265, "total_steps": 122600, "loss": 0.1757, "lr": 2.1468189233278958e-05, "epoch": 0.8588907014681892, "percentage": 4.29, "elapsed_time": "0:38:02", "remaining_time": "14:07:52", "throughput": 4986.14, "total_tokens": 11382080} +{"current_steps": 5270, "total_steps": 122600, "loss": 0.2735, "lr": 2.148858075040783e-05, "epoch": 0.8597063621533442, "percentage": 4.3, "elapsed_time": "0:38:04", "remaining_time": "14:07:49", "throughput": 4986.2, "total_tokens": 11392736} +{"current_steps": 5275, "total_steps": 122600, "loss": 0.1726, "lr": 2.1508972267536705e-05, "epoch": 0.8605220228384992, "percentage": 4.3, "elapsed_time": "0:38:06", "remaining_time": "14:07:43", "throughput": 4986.22, "total_tokens": 11402720} +{"current_steps": 5280, "total_steps": 122600, "loss": 0.0706, "lr": 2.152936378466558e-05, "epoch": 0.8613376835236541, "percentage": 4.31, "elapsed_time": "0:38:09", "remaining_time": "14:07:43", "throughput": 4986.21, "total_tokens": 11413984} +{"current_steps": 5285, "total_steps": 122600, "loss": 0.24, "lr": 2.1549755301794456e-05, "epoch": 0.8621533442088092, "percentage": 4.31, "elapsed_time": "0:38:11", "remaining_time": "14:07:40", "throughput": 4986.32, "total_tokens": 11424832} +{"current_steps": 5290, "total_steps": 122600, "loss": 0.106, "lr": 2.157014681892333e-05, "epoch": 0.8629690048939641, "percentage": 4.31, "elapsed_time": "0:38:13", "remaining_time": "14:07:40", "throughput": 4986.26, "total_tokens": 11436128} +{"current_steps": 5295, "total_steps": 122600, "loss": 0.1991, "lr": 2.1590538336052204e-05, "epoch": 0.863784665579119, "percentage": 4.32, "elapsed_time": "0:38:15", "remaining_time": "14:07:44", "throughput": 4986.3, "total_tokens": 11448448} +{"current_steps": 5300, "total_steps": 122600, "loss": 0.1511, "lr": 2.1610929853181078e-05, "epoch": 0.8646003262642741, "percentage": 4.32, "elapsed_time": "0:38:17", "remaining_time": "14:07:38", "throughput": 4986.27, "total_tokens": 11458176} +{"current_steps": 5305, "total_steps": 122600, "loss": 0.1642, "lr": 2.163132137030995e-05, "epoch": 0.865415986949429, "percentage": 4.33, "elapsed_time": "0:38:19", "remaining_time": "14:07:33", "throughput": 4986.34, "total_tokens": 11468480} +{"current_steps": 5310, "total_steps": 122600, "loss": 0.2098, "lr": 2.1651712887438825e-05, "epoch": 0.866231647634584, "percentage": 4.33, "elapsed_time": "0:38:22", "remaining_time": "14:07:28", "throughput": 4986.38, "total_tokens": 11478880} +{"current_steps": 5315, "total_steps": 122600, "loss": 0.2109, "lr": 2.16721044045677e-05, "epoch": 0.867047308319739, "percentage": 4.34, "elapsed_time": "0:38:24", "remaining_time": "14:07:28", "throughput": 4986.38, "total_tokens": 11490176} +{"current_steps": 5320, "total_steps": 122600, "loss": 0.1837, "lr": 2.1692495921696576e-05, "epoch": 0.867862969004894, "percentage": 4.34, "elapsed_time": "0:38:26", "remaining_time": "14:07:26", "throughput": 4986.43, "total_tokens": 11500992} +{"current_steps": 5325, "total_steps": 122600, "loss": 0.0619, "lr": 2.171288743882545e-05, "epoch": 0.8686786296900489, "percentage": 4.34, "elapsed_time": "0:38:28", "remaining_time": "14:07:26", "throughput": 4986.44, "total_tokens": 11512288} +{"current_steps": 5330, "total_steps": 122600, "loss": 0.2689, "lr": 2.1733278955954324e-05, "epoch": 0.8694942903752039, "percentage": 4.35, "elapsed_time": "0:38:30", "remaining_time": "14:07:18", "throughput": 4986.39, "total_tokens": 11521664} +{"current_steps": 5335, "total_steps": 122600, "loss": 0.0521, "lr": 2.1753670473083198e-05, "epoch": 0.8703099510603589, "percentage": 4.35, "elapsed_time": "0:38:32", "remaining_time": "14:07:16", "throughput": 4986.42, "total_tokens": 11532608} +{"current_steps": 5340, "total_steps": 122600, "loss": 0.2486, "lr": 2.177406199021207e-05, "epoch": 0.8711256117455138, "percentage": 4.36, "elapsed_time": "0:38:34", "remaining_time": "14:07:12", "throughput": 4986.38, "total_tokens": 11543072} +{"current_steps": 5345, "total_steps": 122600, "loss": 0.0971, "lr": 2.179445350734095e-05, "epoch": 0.8719412724306689, "percentage": 4.36, "elapsed_time": "0:38:37", "remaining_time": "14:07:11", "throughput": 4986.44, "total_tokens": 11554144} +{"current_steps": 5350, "total_steps": 122600, "loss": 0.1113, "lr": 2.1814845024469823e-05, "epoch": 0.8727569331158238, "percentage": 4.36, "elapsed_time": "0:38:39", "remaining_time": "14:07:10", "throughput": 4986.45, "total_tokens": 11565376} +{"current_steps": 5355, "total_steps": 122600, "loss": 0.3152, "lr": 2.1835236541598697e-05, "epoch": 0.8735725938009788, "percentage": 4.37, "elapsed_time": "0:38:41", "remaining_time": "14:07:08", "throughput": 4986.45, "total_tokens": 11576128} +{"current_steps": 5360, "total_steps": 122600, "loss": 0.1034, "lr": 2.185562805872757e-05, "epoch": 0.8743882544861338, "percentage": 4.37, "elapsed_time": "0:38:43", "remaining_time": "14:07:11", "throughput": 4986.43, "total_tokens": 11588000} +{"current_steps": 5365, "total_steps": 122600, "loss": 0.0994, "lr": 2.1876019575856444e-05, "epoch": 0.8752039151712887, "percentage": 4.38, "elapsed_time": "0:38:46", "remaining_time": "14:07:12", "throughput": 4986.38, "total_tokens": 11599520} +{"current_steps": 5370, "total_steps": 122600, "loss": 0.1263, "lr": 2.1896411092985318e-05, "epoch": 0.8760195758564437, "percentage": 4.38, "elapsed_time": "0:38:48", "remaining_time": "14:07:14", "throughput": 4986.32, "total_tokens": 11611168} +{"current_steps": 5375, "total_steps": 122600, "loss": 0.0807, "lr": 2.1916802610114192e-05, "epoch": 0.8768352365415987, "percentage": 4.38, "elapsed_time": "0:38:50", "remaining_time": "14:07:11", "throughput": 4986.31, "total_tokens": 11621632} +{"current_steps": 5380, "total_steps": 122600, "loss": 0.3897, "lr": 2.193719412724307e-05, "epoch": 0.8776508972267537, "percentage": 4.39, "elapsed_time": "0:38:52", "remaining_time": "14:07:06", "throughput": 4986.42, "total_tokens": 11632160} +{"current_steps": 5385, "total_steps": 122600, "loss": 0.2004, "lr": 2.1957585644371943e-05, "epoch": 0.8784665579119086, "percentage": 4.39, "elapsed_time": "0:38:54", "remaining_time": "14:06:57", "throughput": 4986.42, "total_tokens": 11641344} +{"current_steps": 5390, "total_steps": 122600, "loss": 0.1352, "lr": 2.1977977161500817e-05, "epoch": 0.8792822185970636, "percentage": 4.4, "elapsed_time": "0:38:56", "remaining_time": "14:06:55", "throughput": 4986.39, "total_tokens": 11652128} +{"current_steps": 5395, "total_steps": 122600, "loss": 0.1029, "lr": 2.199836867862969e-05, "epoch": 0.8800978792822186, "percentage": 4.4, "elapsed_time": "0:38:58", "remaining_time": "14:06:51", "throughput": 4986.4, "total_tokens": 11662528} +{"current_steps": 5400, "total_steps": 122600, "loss": 0.1681, "lr": 2.2018760195758564e-05, "epoch": 0.8809135399673735, "percentage": 4.4, "elapsed_time": "0:39:00", "remaining_time": "14:06:45", "throughput": 4986.4, "total_tokens": 11672544} +{"current_steps": 5405, "total_steps": 122600, "loss": 0.1449, "lr": 2.203915171288744e-05, "epoch": 0.8817292006525286, "percentage": 4.41, "elapsed_time": "0:39:03", "remaining_time": "14:06:44", "throughput": 4986.35, "total_tokens": 11683552} +{"current_steps": 5410, "total_steps": 122600, "loss": 0.1559, "lr": 2.2059543230016312e-05, "epoch": 0.8825448613376835, "percentage": 4.41, "elapsed_time": "0:39:05", "remaining_time": "14:06:37", "throughput": 4986.43, "total_tokens": 11693408} +{"current_steps": 5415, "total_steps": 122600, "loss": 0.1528, "lr": 2.207993474714519e-05, "epoch": 0.8833605220228385, "percentage": 4.42, "elapsed_time": "0:39:07", "remaining_time": "14:06:36", "throughput": 4986.36, "total_tokens": 11704160} +{"current_steps": 5420, "total_steps": 122600, "loss": 0.1504, "lr": 2.2100326264274063e-05, "epoch": 0.8841761827079935, "percentage": 4.42, "elapsed_time": "0:39:09", "remaining_time": "14:06:33", "throughput": 4986.32, "total_tokens": 11714752} +{"current_steps": 5425, "total_steps": 122600, "loss": 0.08, "lr": 2.212071778140294e-05, "epoch": 0.8849918433931484, "percentage": 4.42, "elapsed_time": "0:39:11", "remaining_time": "14:06:30", "throughput": 4986.32, "total_tokens": 11725408} +{"current_steps": 5430, "total_steps": 122600, "loss": 0.2061, "lr": 2.214110929853181e-05, "epoch": 0.8858075040783034, "percentage": 4.43, "elapsed_time": "0:39:13", "remaining_time": "14:06:31", "throughput": 4986.22, "total_tokens": 11736640} +{"current_steps": 5435, "total_steps": 122600, "loss": 0.1487, "lr": 2.2161500815660684e-05, "epoch": 0.8866231647634584, "percentage": 4.43, "elapsed_time": "0:39:15", "remaining_time": "14:06:27", "throughput": 4986.21, "total_tokens": 11747008} +{"current_steps": 5440, "total_steps": 122600, "loss": 0.1275, "lr": 2.218189233278956e-05, "epoch": 0.8874388254486134, "percentage": 4.44, "elapsed_time": "0:39:18", "remaining_time": "14:06:25", "throughput": 4986.18, "total_tokens": 11757728} +{"current_steps": 5445, "total_steps": 122600, "loss": 0.1846, "lr": 2.2202283849918435e-05, "epoch": 0.8882544861337683, "percentage": 4.44, "elapsed_time": "0:39:20", "remaining_time": "14:06:23", "throughput": 4986.24, "total_tokens": 11768704} +{"current_steps": 5450, "total_steps": 122600, "loss": 0.2984, "lr": 2.222267536704731e-05, "epoch": 0.8890701468189234, "percentage": 4.45, "elapsed_time": "0:39:22", "remaining_time": "14:06:24", "throughput": 4986.19, "total_tokens": 11780288} +{"current_steps": 5455, "total_steps": 122600, "loss": 0.3289, "lr": 2.2243066884176183e-05, "epoch": 0.8898858075040783, "percentage": 4.45, "elapsed_time": "0:39:24", "remaining_time": "14:06:18", "throughput": 4986.17, "total_tokens": 11790080} +{"current_steps": 5460, "total_steps": 122600, "loss": 0.3891, "lr": 2.2263458401305057e-05, "epoch": 0.8907014681892332, "percentage": 4.45, "elapsed_time": "0:39:26", "remaining_time": "14:06:21", "throughput": 4986.12, "total_tokens": 11801952} +{"current_steps": 5465, "total_steps": 122600, "loss": 0.1253, "lr": 2.2283849918433934e-05, "epoch": 0.8915171288743883, "percentage": 4.46, "elapsed_time": "0:39:28", "remaining_time": "14:06:13", "throughput": 4986.11, "total_tokens": 11811520} +{"current_steps": 5470, "total_steps": 122600, "loss": 0.2709, "lr": 2.2304241435562805e-05, "epoch": 0.8923327895595432, "percentage": 4.46, "elapsed_time": "0:39:31", "remaining_time": "14:06:11", "throughput": 4986.12, "total_tokens": 11822240} +{"current_steps": 5475, "total_steps": 122600, "loss": 0.2641, "lr": 2.2324632952691682e-05, "epoch": 0.8931484502446982, "percentage": 4.47, "elapsed_time": "0:39:33", "remaining_time": "14:06:11", "throughput": 4986.16, "total_tokens": 11833632} +{"current_steps": 5480, "total_steps": 122600, "loss": 0.0883, "lr": 2.2345024469820556e-05, "epoch": 0.8939641109298532, "percentage": 4.47, "elapsed_time": "0:39:35", "remaining_time": "14:06:10", "throughput": 4986.12, "total_tokens": 11844640} +{"current_steps": 5485, "total_steps": 122600, "loss": 0.1979, "lr": 2.2365415986949433e-05, "epoch": 0.8947797716150081, "percentage": 4.47, "elapsed_time": "0:39:37", "remaining_time": "14:06:08", "throughput": 4986.2, "total_tokens": 11855776} +{"current_steps": 5490, "total_steps": 122600, "loss": 0.3515, "lr": 2.2385807504078303e-05, "epoch": 0.8955954323001631, "percentage": 4.48, "elapsed_time": "0:39:39", "remaining_time": "14:06:03", "throughput": 4986.21, "total_tokens": 11865856} +{"current_steps": 5495, "total_steps": 122600, "loss": 0.1442, "lr": 2.2406199021207177e-05, "epoch": 0.8964110929853181, "percentage": 4.48, "elapsed_time": "0:39:42", "remaining_time": "14:06:03", "throughput": 4986.29, "total_tokens": 11877504} +{"current_steps": 5500, "total_steps": 122600, "loss": 0.2518, "lr": 2.2426590538336054e-05, "epoch": 0.8972267536704731, "percentage": 4.49, "elapsed_time": "0:39:44", "remaining_time": "14:06:02", "throughput": 4986.26, "total_tokens": 11888320} +{"current_steps": 5505, "total_steps": 122600, "loss": 0.1775, "lr": 2.2446982055464928e-05, "epoch": 0.898042414355628, "percentage": 4.49, "elapsed_time": "0:39:46", "remaining_time": "14:06:00", "throughput": 4986.32, "total_tokens": 11899456} +{"current_steps": 5510, "total_steps": 122600, "loss": 0.1723, "lr": 2.2467373572593802e-05, "epoch": 0.8988580750407831, "percentage": 4.49, "elapsed_time": "0:39:48", "remaining_time": "14:05:58", "throughput": 4986.32, "total_tokens": 11910240} +{"current_steps": 5515, "total_steps": 122600, "loss": 0.0773, "lr": 2.2487765089722676e-05, "epoch": 0.899673735725938, "percentage": 4.5, "elapsed_time": "0:39:50", "remaining_time": "14:05:53", "throughput": 4986.36, "total_tokens": 11920512} +{"current_steps": 5520, "total_steps": 122600, "loss": 0.2462, "lr": 2.2508156606851553e-05, "epoch": 0.9004893964110929, "percentage": 4.5, "elapsed_time": "0:39:52", "remaining_time": "14:05:48", "throughput": 4986.35, "total_tokens": 11930592} +{"current_steps": 5525, "total_steps": 122600, "loss": 0.328, "lr": 2.2528548123980427e-05, "epoch": 0.901305057096248, "percentage": 4.51, "elapsed_time": "0:39:54", "remaining_time": "14:05:44", "throughput": 4986.35, "total_tokens": 11941088} +{"current_steps": 5530, "total_steps": 122600, "loss": 0.1576, "lr": 2.2548939641109297e-05, "epoch": 0.9021207177814029, "percentage": 4.51, "elapsed_time": "0:39:57", "remaining_time": "14:05:44", "throughput": 4986.34, "total_tokens": 11952320} +{"current_steps": 5535, "total_steps": 122600, "loss": 0.1925, "lr": 2.2569331158238174e-05, "epoch": 0.9029363784665579, "percentage": 4.51, "elapsed_time": "0:39:59", "remaining_time": "14:05:41", "throughput": 4986.36, "total_tokens": 11962880} +{"current_steps": 5540, "total_steps": 122600, "loss": 0.1056, "lr": 2.2589722675367048e-05, "epoch": 0.9037520391517129, "percentage": 4.52, "elapsed_time": "0:40:01", "remaining_time": "14:05:38", "throughput": 4986.36, "total_tokens": 11973472} +{"current_steps": 5545, "total_steps": 122600, "loss": 0.3671, "lr": 2.2610114192495922e-05, "epoch": 0.9045676998368679, "percentage": 4.52, "elapsed_time": "0:40:03", "remaining_time": "14:05:35", "throughput": 4986.36, "total_tokens": 11984096} +{"current_steps": 5550, "total_steps": 122600, "loss": 0.1178, "lr": 2.2630505709624796e-05, "epoch": 0.9053833605220228, "percentage": 4.53, "elapsed_time": "0:40:05", "remaining_time": "14:05:35", "throughput": 4986.39, "total_tokens": 11995488} +{"current_steps": 5555, "total_steps": 122600, "loss": 0.1664, "lr": 2.2650897226753673e-05, "epoch": 0.9061990212071778, "percentage": 4.53, "elapsed_time": "0:40:08", "remaining_time": "14:05:37", "throughput": 4986.34, "total_tokens": 12007104} +{"current_steps": 5560, "total_steps": 122600, "loss": 0.2129, "lr": 2.2671288743882547e-05, "epoch": 0.9070146818923328, "percentage": 4.54, "elapsed_time": "0:40:10", "remaining_time": "14:05:40", "throughput": 4986.07, "total_tokens": 12018688} +{"current_steps": 5565, "total_steps": 122600, "loss": 0.0707, "lr": 2.269168026101142e-05, "epoch": 0.9078303425774877, "percentage": 4.54, "elapsed_time": "0:40:12", "remaining_time": "14:05:32", "throughput": 4986.11, "total_tokens": 12028096} +{"current_steps": 5570, "total_steps": 122600, "loss": 0.1553, "lr": 2.2712071778140295e-05, "epoch": 0.9086460032626428, "percentage": 4.54, "elapsed_time": "0:40:14", "remaining_time": "14:05:30", "throughput": 4986.08, "total_tokens": 12038976} +{"current_steps": 5575, "total_steps": 122600, "loss": 0.2604, "lr": 2.273246329526917e-05, "epoch": 0.9094616639477977, "percentage": 4.55, "elapsed_time": "0:40:16", "remaining_time": "14:05:33", "throughput": 4986.07, "total_tokens": 12050816} +{"current_steps": 5580, "total_steps": 122600, "loss": 0.1887, "lr": 2.2752854812398046e-05, "epoch": 0.9102773246329527, "percentage": 4.55, "elapsed_time": "0:40:19", "remaining_time": "14:05:34", "throughput": 4986.04, "total_tokens": 12062336} +{"current_steps": 5585, "total_steps": 122600, "loss": 0.1854, "lr": 2.2773246329526916e-05, "epoch": 0.9110929853181077, "percentage": 4.56, "elapsed_time": "0:40:21", "remaining_time": "14:05:27", "throughput": 4986.06, "total_tokens": 12072096} +{"current_steps": 5590, "total_steps": 122600, "loss": 0.1105, "lr": 2.279363784665579e-05, "epoch": 0.9119086460032626, "percentage": 4.56, "elapsed_time": "0:40:23", "remaining_time": "14:05:26", "throughput": 4986.07, "total_tokens": 12083136} +{"current_steps": 5595, "total_steps": 122600, "loss": 0.2371, "lr": 2.2814029363784667e-05, "epoch": 0.9127243066884176, "percentage": 4.56, "elapsed_time": "0:40:25", "remaining_time": "14:05:24", "throughput": 4986.14, "total_tokens": 12094272} +{"current_steps": 5600, "total_steps": 122600, "loss": 0.2442, "lr": 2.283442088091354e-05, "epoch": 0.9135399673735726, "percentage": 4.57, "elapsed_time": "0:40:27", "remaining_time": "14:05:23", "throughput": 4986.11, "total_tokens": 12105280} +{"current_steps": 5605, "total_steps": 122600, "loss": 0.2279, "lr": 2.2854812398042415e-05, "epoch": 0.9143556280587276, "percentage": 4.57, "elapsed_time": "0:40:29", "remaining_time": "14:05:20", "throughput": 4986.17, "total_tokens": 12115968} +{"current_steps": 5610, "total_steps": 122600, "loss": 0.171, "lr": 2.287520391517129e-05, "epoch": 0.9151712887438825, "percentage": 4.58, "elapsed_time": "0:40:32", "remaining_time": "14:05:20", "throughput": 4986.06, "total_tokens": 12127136} +{"current_steps": 5615, "total_steps": 122600, "loss": 0.151, "lr": 2.2895595432300166e-05, "epoch": 0.9159869494290375, "percentage": 4.58, "elapsed_time": "0:40:34", "remaining_time": "14:05:13", "throughput": 4986.04, "total_tokens": 12136704} +{"current_steps": 5620, "total_steps": 122600, "loss": 0.0754, "lr": 2.291598694942904e-05, "epoch": 0.9168026101141925, "percentage": 4.58, "elapsed_time": "0:40:36", "remaining_time": "14:05:08", "throughput": 4986.04, "total_tokens": 12146784} +{"current_steps": 5625, "total_steps": 122600, "loss": 0.0868, "lr": 2.2936378466557913e-05, "epoch": 0.9176182707993474, "percentage": 4.59, "elapsed_time": "0:40:38", "remaining_time": "14:05:04", "throughput": 4986.05, "total_tokens": 12157248} +{"current_steps": 5630, "total_steps": 122600, "loss": 0.1813, "lr": 2.2956769983686787e-05, "epoch": 0.9184339314845025, "percentage": 4.59, "elapsed_time": "0:40:40", "remaining_time": "14:05:03", "throughput": 4986.03, "total_tokens": 12168256} +{"current_steps": 5635, "total_steps": 122600, "loss": 0.1507, "lr": 2.297716150081566e-05, "epoch": 0.9192495921696574, "percentage": 4.6, "elapsed_time": "0:40:42", "remaining_time": "14:04:56", "throughput": 4986.01, "total_tokens": 12177760} +{"current_steps": 5640, "total_steps": 122600, "loss": 0.0836, "lr": 2.2997553017944538e-05, "epoch": 0.9200652528548124, "percentage": 4.6, "elapsed_time": "0:40:44", "remaining_time": "14:04:51", "throughput": 4986.1, "total_tokens": 12188192} +{"current_steps": 5645, "total_steps": 122600, "loss": 0.2373, "lr": 2.301794453507341e-05, "epoch": 0.9208809135399674, "percentage": 4.6, "elapsed_time": "0:40:46", "remaining_time": "14:04:48", "throughput": 4986.15, "total_tokens": 12198880} +{"current_steps": 5650, "total_steps": 122600, "loss": 0.2172, "lr": 2.3038336052202286e-05, "epoch": 0.9216965742251223, "percentage": 4.61, "elapsed_time": "0:40:48", "remaining_time": "14:04:42", "throughput": 4986.17, "total_tokens": 12208800} +{"current_steps": 5655, "total_steps": 122600, "loss": 0.2169, "lr": 2.305872756933116e-05, "epoch": 0.9225122349102773, "percentage": 4.61, "elapsed_time": "0:40:50", "remaining_time": "14:04:39", "throughput": 4986.13, "total_tokens": 12219360} +{"current_steps": 5660, "total_steps": 122600, "loss": 0.1324, "lr": 2.3079119086460034e-05, "epoch": 0.9233278955954323, "percentage": 4.62, "elapsed_time": "0:40:52", "remaining_time": "14:04:34", "throughput": 4986.15, "total_tokens": 12229376} +{"current_steps": 5665, "total_steps": 122600, "loss": 0.2289, "lr": 2.3099510603588907e-05, "epoch": 0.9241435562805873, "percentage": 4.62, "elapsed_time": "0:40:55", "remaining_time": "14:04:35", "throughput": 4986.15, "total_tokens": 12241152} +{"current_steps": 5670, "total_steps": 122600, "loss": 0.2789, "lr": 2.311990212071778e-05, "epoch": 0.9249592169657422, "percentage": 4.62, "elapsed_time": "0:40:57", "remaining_time": "14:04:34", "throughput": 4986.18, "total_tokens": 12252192} +{"current_steps": 5675, "total_steps": 122600, "loss": 0.2238, "lr": 2.314029363784666e-05, "epoch": 0.9257748776508973, "percentage": 4.63, "elapsed_time": "0:40:59", "remaining_time": "14:04:31", "throughput": 4986.23, "total_tokens": 12262848} +{"current_steps": 5680, "total_steps": 122600, "loss": 0.2379, "lr": 2.3160685154975532e-05, "epoch": 0.9265905383360522, "percentage": 4.63, "elapsed_time": "0:41:01", "remaining_time": "14:04:29", "throughput": 4986.22, "total_tokens": 12273728} +{"current_steps": 5685, "total_steps": 122600, "loss": 0.1383, "lr": 2.3181076672104406e-05, "epoch": 0.9274061990212071, "percentage": 4.64, "elapsed_time": "0:41:03", "remaining_time": "14:04:27", "throughput": 4986.22, "total_tokens": 12284512} +{"current_steps": 5690, "total_steps": 122600, "loss": 0.1962, "lr": 2.320146818923328e-05, "epoch": 0.9282218597063622, "percentage": 4.64, "elapsed_time": "0:41:05", "remaining_time": "14:04:27", "throughput": 4986.23, "total_tokens": 12295968} +{"current_steps": 5695, "total_steps": 122600, "loss": 0.1461, "lr": 2.3221859706362154e-05, "epoch": 0.9290375203915171, "percentage": 4.65, "elapsed_time": "0:41:08", "remaining_time": "14:04:28", "throughput": 4986.23, "total_tokens": 12307616} +{"current_steps": 5700, "total_steps": 122600, "loss": 0.1539, "lr": 2.324225122349103e-05, "epoch": 0.9298531810766721, "percentage": 4.65, "elapsed_time": "0:41:10", "remaining_time": "14:04:26", "throughput": 4986.21, "total_tokens": 12318400} +{"current_steps": 5705, "total_steps": 122600, "loss": 0.114, "lr": 2.32626427406199e-05, "epoch": 0.9306688417618271, "percentage": 4.65, "elapsed_time": "0:41:12", "remaining_time": "14:04:26", "throughput": 4986.17, "total_tokens": 12329472} +{"current_steps": 5710, "total_steps": 122600, "loss": 0.1043, "lr": 2.328303425774878e-05, "epoch": 0.9314845024469821, "percentage": 4.66, "elapsed_time": "0:41:14", "remaining_time": "14:04:23", "throughput": 4986.11, "total_tokens": 12340032} +{"current_steps": 5715, "total_steps": 122600, "loss": 0.0954, "lr": 2.3303425774877652e-05, "epoch": 0.932300163132137, "percentage": 4.66, "elapsed_time": "0:41:17", "remaining_time": "14:04:25", "throughput": 4986.04, "total_tokens": 12351584} +{"current_steps": 5720, "total_steps": 122600, "loss": 0.3214, "lr": 2.3323817292006526e-05, "epoch": 0.933115823817292, "percentage": 4.67, "elapsed_time": "0:41:19", "remaining_time": "14:04:24", "throughput": 4986.03, "total_tokens": 12362752} +{"current_steps": 5725, "total_steps": 122600, "loss": 0.2946, "lr": 2.33442088091354e-05, "epoch": 0.933931484502447, "percentage": 4.67, "elapsed_time": "0:41:21", "remaining_time": "14:04:27", "throughput": 4986.02, "total_tokens": 12374720} +{"current_steps": 5730, "total_steps": 122600, "loss": 0.111, "lr": 2.3364600326264274e-05, "epoch": 0.9347471451876019, "percentage": 4.67, "elapsed_time": "0:41:23", "remaining_time": "14:04:22", "throughput": 4986.05, "total_tokens": 12384896} +{"current_steps": 5735, "total_steps": 122600, "loss": 0.1392, "lr": 2.338499184339315e-05, "epoch": 0.935562805872757, "percentage": 4.68, "elapsed_time": "0:41:26", "remaining_time": "14:04:20", "throughput": 4986.02, "total_tokens": 12395808} +{"current_steps": 5740, "total_steps": 122600, "loss": 0.1845, "lr": 2.3405383360522025e-05, "epoch": 0.9363784665579119, "percentage": 4.68, "elapsed_time": "0:41:28", "remaining_time": "14:04:20", "throughput": 4985.95, "total_tokens": 12406880} +{"current_steps": 5745, "total_steps": 122600, "loss": 0.2687, "lr": 2.34257748776509e-05, "epoch": 0.9371941272430668, "percentage": 4.69, "elapsed_time": "0:41:30", "remaining_time": "14:04:20", "throughput": 4985.96, "total_tokens": 12418240} +{"current_steps": 5750, "total_steps": 122600, "loss": 0.2047, "lr": 2.3446166394779773e-05, "epoch": 0.9380097879282219, "percentage": 4.69, "elapsed_time": "0:41:32", "remaining_time": "14:04:17", "throughput": 4985.97, "total_tokens": 12428896} +{"current_steps": 5755, "total_steps": 122600, "loss": 0.0551, "lr": 2.3466557911908646e-05, "epoch": 0.9388254486133768, "percentage": 4.69, "elapsed_time": "0:41:34", "remaining_time": "14:04:16", "throughput": 4985.97, "total_tokens": 12439872} +{"current_steps": 5760, "total_steps": 122600, "loss": 0.0868, "lr": 2.3486949429037524e-05, "epoch": 0.9396411092985318, "percentage": 4.7, "elapsed_time": "0:41:37", "remaining_time": "14:04:19", "throughput": 4985.9, "total_tokens": 12451840} +{"current_steps": 5765, "total_steps": 122600, "loss": 0.1803, "lr": 2.3507340946166394e-05, "epoch": 0.9404567699836868, "percentage": 4.7, "elapsed_time": "0:41:39", "remaining_time": "14:04:20", "throughput": 4985.85, "total_tokens": 12463328} +{"current_steps": 5770, "total_steps": 122600, "loss": 0.2671, "lr": 2.352773246329527e-05, "epoch": 0.9412724306688418, "percentage": 4.71, "elapsed_time": "0:41:41", "remaining_time": "14:04:17", "throughput": 4985.88, "total_tokens": 12474080} +{"current_steps": 5775, "total_steps": 122600, "loss": 0.3396, "lr": 2.3548123980424145e-05, "epoch": 0.9420880913539967, "percentage": 4.71, "elapsed_time": "0:41:44", "remaining_time": "14:04:15", "throughput": 4985.92, "total_tokens": 12484960} +{"current_steps": 5780, "total_steps": 122600, "loss": 0.0783, "lr": 2.356851549755302e-05, "epoch": 0.9429037520391517, "percentage": 4.71, "elapsed_time": "0:41:46", "remaining_time": "14:04:12", "throughput": 4985.96, "total_tokens": 12495584} +{"current_steps": 5785, "total_steps": 122600, "loss": 0.1999, "lr": 2.3588907014681893e-05, "epoch": 0.9437194127243067, "percentage": 4.72, "elapsed_time": "0:41:48", "remaining_time": "14:04:06", "throughput": 4985.96, "total_tokens": 12505568} +{"current_steps": 5790, "total_steps": 122600, "loss": 0.2111, "lr": 2.3609298531810767e-05, "epoch": 0.9445350734094616, "percentage": 4.72, "elapsed_time": "0:41:50", "remaining_time": "14:04:04", "throughput": 4985.97, "total_tokens": 12516480} +{"current_steps": 5795, "total_steps": 122600, "loss": 0.3659, "lr": 2.3629690048939644e-05, "epoch": 0.9453507340946167, "percentage": 4.73, "elapsed_time": "0:41:52", "remaining_time": "14:04:01", "throughput": 4986.01, "total_tokens": 12527136} +{"current_steps": 5800, "total_steps": 122600, "loss": 0.3405, "lr": 2.3650081566068518e-05, "epoch": 0.9461663947797716, "percentage": 4.73, "elapsed_time": "0:41:54", "remaining_time": "14:03:57", "throughput": 4986.05, "total_tokens": 12537568} +{"current_steps": 5805, "total_steps": 122600, "loss": 0.1261, "lr": 2.367047308319739e-05, "epoch": 0.9469820554649266, "percentage": 4.73, "elapsed_time": "0:41:56", "remaining_time": "14:03:56", "throughput": 4986.1, "total_tokens": 12548736} +{"current_steps": 5810, "total_steps": 122600, "loss": 0.122, "lr": 2.3690864600326265e-05, "epoch": 0.9477977161500816, "percentage": 4.74, "elapsed_time": "0:41:59", "remaining_time": "14:03:57", "throughput": 4986.06, "total_tokens": 12560192} +{"current_steps": 5815, "total_steps": 122600, "loss": 0.1114, "lr": 2.371125611745514e-05, "epoch": 0.9486133768352365, "percentage": 4.74, "elapsed_time": "0:42:01", "remaining_time": "14:03:53", "throughput": 4986.1, "total_tokens": 12570816} +{"current_steps": 5820, "total_steps": 122600, "loss": 0.2757, "lr": 2.3731647634584013e-05, "epoch": 0.9494290375203915, "percentage": 4.75, "elapsed_time": "0:42:03", "remaining_time": "14:03:53", "throughput": 4986.13, "total_tokens": 12582272} +{"current_steps": 5825, "total_steps": 122600, "loss": 0.2501, "lr": 2.3752039151712887e-05, "epoch": 0.9502446982055465, "percentage": 4.75, "elapsed_time": "0:42:05", "remaining_time": "14:03:57", "throughput": 4986.1, "total_tokens": 12594432} +{"current_steps": 5830, "total_steps": 122600, "loss": 0.0541, "lr": 2.3772430668841764e-05, "epoch": 0.9510603588907015, "percentage": 4.76, "elapsed_time": "0:42:08", "remaining_time": "14:03:58", "throughput": 4986.12, "total_tokens": 12606048} +{"current_steps": 5835, "total_steps": 122600, "loss": 0.3241, "lr": 2.3792822185970638e-05, "epoch": 0.9518760195758564, "percentage": 4.76, "elapsed_time": "0:42:10", "remaining_time": "14:03:56", "throughput": 4986.14, "total_tokens": 12617088} +{"current_steps": 5840, "total_steps": 122600, "loss": 0.3314, "lr": 2.381321370309951e-05, "epoch": 0.9526916802610114, "percentage": 4.76, "elapsed_time": "0:42:12", "remaining_time": "14:03:54", "throughput": 4986.1, "total_tokens": 12627808} +{"current_steps": 5845, "total_steps": 122600, "loss": 0.0808, "lr": 2.3833605220228385e-05, "epoch": 0.9535073409461664, "percentage": 4.77, "elapsed_time": "0:42:14", "remaining_time": "14:03:53", "throughput": 4986.08, "total_tokens": 12638720} +{"current_steps": 5850, "total_steps": 122600, "loss": 0.1142, "lr": 2.385399673735726e-05, "epoch": 0.9543230016313213, "percentage": 4.77, "elapsed_time": "0:42:16", "remaining_time": "14:03:46", "throughput": 4986.12, "total_tokens": 12648608} +{"current_steps": 5855, "total_steps": 122600, "loss": 0.1, "lr": 2.3874388254486136e-05, "epoch": 0.9551386623164764, "percentage": 4.78, "elapsed_time": "0:42:18", "remaining_time": "14:03:41", "throughput": 4986.21, "total_tokens": 12658944} +{"current_steps": 5860, "total_steps": 122600, "loss": 0.1741, "lr": 2.3894779771615007e-05, "epoch": 0.9559543230016313, "percentage": 4.78, "elapsed_time": "0:42:20", "remaining_time": "14:03:39", "throughput": 4986.23, "total_tokens": 12669856} +{"current_steps": 5865, "total_steps": 122600, "loss": 0.2221, "lr": 2.3915171288743884e-05, "epoch": 0.9567699836867863, "percentage": 4.78, "elapsed_time": "0:42:23", "remaining_time": "14:03:35", "throughput": 4986.23, "total_tokens": 12680096} +{"current_steps": 5870, "total_steps": 122600, "loss": 0.0489, "lr": 2.3935562805872758e-05, "epoch": 0.9575856443719413, "percentage": 4.79, "elapsed_time": "0:42:25", "remaining_time": "14:03:33", "throughput": 4986.26, "total_tokens": 12691040} +{"current_steps": 5875, "total_steps": 122600, "loss": 0.1704, "lr": 2.3955954323001635e-05, "epoch": 0.9584013050570962, "percentage": 4.79, "elapsed_time": "0:42:27", "remaining_time": "14:03:30", "throughput": 4986.34, "total_tokens": 12701728} +{"current_steps": 5880, "total_steps": 122600, "loss": 0.1481, "lr": 2.3976345840130505e-05, "epoch": 0.9592169657422512, "percentage": 4.8, "elapsed_time": "0:42:29", "remaining_time": "14:03:26", "throughput": 4986.35, "total_tokens": 12712224} +{"current_steps": 5885, "total_steps": 122600, "loss": 0.2615, "lr": 2.399673735725938e-05, "epoch": 0.9600326264274062, "percentage": 4.8, "elapsed_time": "0:42:31", "remaining_time": "14:03:25", "throughput": 4986.38, "total_tokens": 12723264} +{"current_steps": 5890, "total_steps": 122600, "loss": 0.2007, "lr": 2.4017128874388257e-05, "epoch": 0.9608482871125612, "percentage": 4.8, "elapsed_time": "0:42:33", "remaining_time": "14:03:24", "throughput": 4986.39, "total_tokens": 12734400} +{"current_steps": 5895, "total_steps": 122600, "loss": 0.1548, "lr": 2.403752039151713e-05, "epoch": 0.9616639477977161, "percentage": 4.81, "elapsed_time": "0:42:36", "remaining_time": "14:03:23", "throughput": 4986.36, "total_tokens": 12745504} +{"current_steps": 5900, "total_steps": 122600, "loss": 0.2637, "lr": 2.4057911908646004e-05, "epoch": 0.9624796084828712, "percentage": 4.81, "elapsed_time": "0:42:38", "remaining_time": "14:03:18", "throughput": 4986.33, "total_tokens": 12755520} +{"current_steps": 5905, "total_steps": 122600, "loss": 0.0647, "lr": 2.4078303425774878e-05, "epoch": 0.9632952691680261, "percentage": 4.82, "elapsed_time": "0:42:40", "remaining_time": "14:03:15", "throughput": 4986.36, "total_tokens": 12766336} +{"current_steps": 5910, "total_steps": 122600, "loss": 0.1637, "lr": 2.4098694942903755e-05, "epoch": 0.964110929853181, "percentage": 4.82, "elapsed_time": "0:42:42", "remaining_time": "14:03:11", "throughput": 4986.36, "total_tokens": 12776704} +{"current_steps": 5915, "total_steps": 122600, "loss": 0.255, "lr": 2.411908646003263e-05, "epoch": 0.9649265905383361, "percentage": 4.82, "elapsed_time": "0:42:44", "remaining_time": "14:03:11", "throughput": 4986.36, "total_tokens": 12787872} +{"current_steps": 5920, "total_steps": 122600, "loss": 0.0978, "lr": 2.41394779771615e-05, "epoch": 0.965742251223491, "percentage": 4.83, "elapsed_time": "0:42:46", "remaining_time": "14:03:09", "throughput": 4986.36, "total_tokens": 12798880} +{"current_steps": 5925, "total_steps": 122600, "loss": 0.1887, "lr": 2.4159869494290377e-05, "epoch": 0.966557911908646, "percentage": 4.83, "elapsed_time": "0:42:48", "remaining_time": "14:03:07", "throughput": 4986.39, "total_tokens": 12809696} +{"current_steps": 5930, "total_steps": 122600, "loss": 0.1373, "lr": 2.418026101141925e-05, "epoch": 0.967373572593801, "percentage": 4.84, "elapsed_time": "0:42:51", "remaining_time": "14:03:04", "throughput": 4986.38, "total_tokens": 12820192} +{"current_steps": 5935, "total_steps": 122600, "loss": 0.0635, "lr": 2.4200652528548128e-05, "epoch": 0.968189233278956, "percentage": 4.84, "elapsed_time": "0:42:53", "remaining_time": "14:03:08", "throughput": 4986.3, "total_tokens": 12832384} +{"current_steps": 5940, "total_steps": 122600, "loss": 0.111, "lr": 2.4221044045676998e-05, "epoch": 0.9690048939641109, "percentage": 4.85, "elapsed_time": "0:42:55", "remaining_time": "14:03:09", "throughput": 4986.28, "total_tokens": 12843936} +{"current_steps": 5945, "total_steps": 122600, "loss": 0.1334, "lr": 2.4241435562805872e-05, "epoch": 0.9698205546492659, "percentage": 4.85, "elapsed_time": "0:42:58", "remaining_time": "14:03:07", "throughput": 4986.25, "total_tokens": 12854752} +{"current_steps": 5950, "total_steps": 122600, "loss": 0.0807, "lr": 2.426182707993475e-05, "epoch": 0.9706362153344209, "percentage": 4.85, "elapsed_time": "0:43:00", "remaining_time": "14:03:04", "throughput": 4986.2, "total_tokens": 12865248} +{"current_steps": 5955, "total_steps": 122600, "loss": 0.1781, "lr": 2.4282218597063623e-05, "epoch": 0.9714518760195758, "percentage": 4.86, "elapsed_time": "0:43:02", "remaining_time": "14:03:01", "throughput": 4986.26, "total_tokens": 12876128} +{"current_steps": 5960, "total_steps": 122600, "loss": 0.2655, "lr": 2.4302610114192497e-05, "epoch": 0.9722675367047309, "percentage": 4.86, "elapsed_time": "0:43:04", "remaining_time": "14:02:59", "throughput": 4986.29, "total_tokens": 12887008} +{"current_steps": 5965, "total_steps": 122600, "loss": 0.062, "lr": 2.432300163132137e-05, "epoch": 0.9730831973898858, "percentage": 4.87, "elapsed_time": "0:43:06", "remaining_time": "14:03:01", "throughput": 4986.2, "total_tokens": 12898624} +{"current_steps": 5970, "total_steps": 122600, "loss": 0.1135, "lr": 2.4343393148450248e-05, "epoch": 0.9738988580750407, "percentage": 4.87, "elapsed_time": "0:43:09", "remaining_time": "14:03:00", "throughput": 4986.26, "total_tokens": 12909888} +{"current_steps": 5975, "total_steps": 122600, "loss": 0.2772, "lr": 2.436378466557912e-05, "epoch": 0.9747145187601958, "percentage": 4.87, "elapsed_time": "0:43:11", "remaining_time": "14:02:55", "throughput": 4986.24, "total_tokens": 12920032} +{"current_steps": 5980, "total_steps": 122600, "loss": 0.3602, "lr": 2.4384176182707992e-05, "epoch": 0.9755301794453507, "percentage": 4.88, "elapsed_time": "0:43:13", "remaining_time": "14:02:56", "throughput": 4986.23, "total_tokens": 12931392} +{"current_steps": 5985, "total_steps": 122600, "loss": 0.1633, "lr": 2.440456769983687e-05, "epoch": 0.9763458401305057, "percentage": 4.88, "elapsed_time": "0:43:15", "remaining_time": "14:02:50", "throughput": 4986.28, "total_tokens": 12941472} +{"current_steps": 5990, "total_steps": 122600, "loss": 0.0981, "lr": 2.4424959216965743e-05, "epoch": 0.9771615008156607, "percentage": 4.89, "elapsed_time": "0:43:17", "remaining_time": "14:02:48", "throughput": 4986.21, "total_tokens": 12952192} +{"current_steps": 5995, "total_steps": 122600, "loss": 0.2383, "lr": 2.4445350734094617e-05, "epoch": 0.9779771615008157, "percentage": 4.89, "elapsed_time": "0:43:19", "remaining_time": "14:02:47", "throughput": 4986.21, "total_tokens": 12963200} +{"current_steps": 6000, "total_steps": 122600, "loss": 0.2022, "lr": 2.446574225122349e-05, "epoch": 0.9787928221859706, "percentage": 4.89, "elapsed_time": "0:43:21", "remaining_time": "14:02:40", "throughput": 4986.23, "total_tokens": 12972768} +{"current_steps": 6005, "total_steps": 122600, "loss": 0.0935, "lr": 2.4486133768352368e-05, "epoch": 0.9796084828711256, "percentage": 4.9, "elapsed_time": "0:43:23", "remaining_time": "14:02:39", "throughput": 4986.21, "total_tokens": 12984064} +{"current_steps": 6010, "total_steps": 122600, "loss": 0.1821, "lr": 2.4506525285481242e-05, "epoch": 0.9804241435562806, "percentage": 4.9, "elapsed_time": "0:43:26", "remaining_time": "14:02:35", "throughput": 4986.21, "total_tokens": 12994336} +{"current_steps": 6015, "total_steps": 122600, "loss": 0.067, "lr": 2.4526916802610116e-05, "epoch": 0.9812398042414355, "percentage": 4.91, "elapsed_time": "0:43:28", "remaining_time": "14:02:29", "throughput": 4986.2, "total_tokens": 13004096} +{"current_steps": 6020, "total_steps": 122600, "loss": 0.0523, "lr": 2.454730831973899e-05, "epoch": 0.9820554649265906, "percentage": 4.91, "elapsed_time": "0:43:30", "remaining_time": "14:02:27", "throughput": 4986.25, "total_tokens": 13015168} +{"current_steps": 6025, "total_steps": 122600, "loss": 0.0606, "lr": 2.4567699836867863e-05, "epoch": 0.9828711256117455, "percentage": 4.91, "elapsed_time": "0:43:32", "remaining_time": "14:02:26", "throughput": 4986.26, "total_tokens": 13026080} +{"current_steps": 6030, "total_steps": 122600, "loss": 0.2877, "lr": 2.458809135399674e-05, "epoch": 0.9836867862969005, "percentage": 4.92, "elapsed_time": "0:43:34", "remaining_time": "14:02:27", "throughput": 4986.32, "total_tokens": 13037888} +{"current_steps": 6035, "total_steps": 122600, "loss": 0.3981, "lr": 2.4608482871125614e-05, "epoch": 0.9845024469820555, "percentage": 4.92, "elapsed_time": "0:43:37", "remaining_time": "14:02:28", "throughput": 4986.3, "total_tokens": 13049440} +{"current_steps": 6040, "total_steps": 122600, "loss": 0.0789, "lr": 2.4628874388254488e-05, "epoch": 0.9853181076672104, "percentage": 4.93, "elapsed_time": "0:43:39", "remaining_time": "14:02:27", "throughput": 4986.25, "total_tokens": 13060480} +{"current_steps": 6045, "total_steps": 122600, "loss": 0.1231, "lr": 2.4649265905383362e-05, "epoch": 0.9861337683523654, "percentage": 4.93, "elapsed_time": "0:43:41", "remaining_time": "14:02:25", "throughput": 4986.29, "total_tokens": 13071584} +{"current_steps": 6050, "total_steps": 122600, "loss": 0.1513, "lr": 2.4669657422512236e-05, "epoch": 0.9869494290375204, "percentage": 4.93, "elapsed_time": "0:43:43", "remaining_time": "14:02:19", "throughput": 4986.34, "total_tokens": 13081376} +{"current_steps": 6055, "total_steps": 122600, "loss": 0.0877, "lr": 2.469004893964111e-05, "epoch": 0.9877650897226754, "percentage": 4.94, "elapsed_time": "0:43:45", "remaining_time": "14:02:18", "throughput": 4986.41, "total_tokens": 13092768} +{"current_steps": 6060, "total_steps": 122600, "loss": 0.2423, "lr": 2.4710440456769983e-05, "epoch": 0.9885807504078303, "percentage": 4.94, "elapsed_time": "0:43:47", "remaining_time": "14:02:18", "throughput": 4986.38, "total_tokens": 13104096} +{"current_steps": 6065, "total_steps": 122600, "loss": 0.1011, "lr": 2.473083197389886e-05, "epoch": 0.9893964110929854, "percentage": 4.95, "elapsed_time": "0:43:50", "remaining_time": "14:02:18", "throughput": 4986.4, "total_tokens": 13115488} +{"current_steps": 6070, "total_steps": 122600, "loss": 0.0866, "lr": 2.4751223491027734e-05, "epoch": 0.9902120717781403, "percentage": 4.95, "elapsed_time": "0:43:52", "remaining_time": "14:02:17", "throughput": 4986.44, "total_tokens": 13126752} +{"current_steps": 6075, "total_steps": 122600, "loss": 0.1264, "lr": 2.4771615008156608e-05, "epoch": 0.9910277324632952, "percentage": 4.96, "elapsed_time": "0:43:54", "remaining_time": "14:02:16", "throughput": 4986.49, "total_tokens": 13137920} +{"current_steps": 6080, "total_steps": 122600, "loss": 0.1739, "lr": 2.4792006525285482e-05, "epoch": 0.9918433931484503, "percentage": 4.96, "elapsed_time": "0:43:56", "remaining_time": "14:02:13", "throughput": 4986.48, "total_tokens": 13148416} +{"current_steps": 6085, "total_steps": 122600, "loss": 0.0809, "lr": 2.4812398042414356e-05, "epoch": 0.9926590538336052, "percentage": 4.96, "elapsed_time": "0:43:58", "remaining_time": "14:02:05", "throughput": 4986.48, "total_tokens": 13157920} +{"current_steps": 6090, "total_steps": 122600, "loss": 0.0802, "lr": 2.4832789559543233e-05, "epoch": 0.9934747145187602, "percentage": 4.97, "elapsed_time": "0:44:00", "remaining_time": "14:02:00", "throughput": 4986.54, "total_tokens": 13167968} +{"current_steps": 6095, "total_steps": 122600, "loss": 0.2245, "lr": 2.4853181076672104e-05, "epoch": 0.9942903752039152, "percentage": 4.97, "elapsed_time": "0:44:03", "remaining_time": "14:02:01", "throughput": 4986.54, "total_tokens": 13179648} +{"current_steps": 6100, "total_steps": 122600, "loss": 0.1574, "lr": 2.487357259380098e-05, "epoch": 0.9951060358890701, "percentage": 4.98, "elapsed_time": "0:44:05", "remaining_time": "14:01:59", "throughput": 4986.57, "total_tokens": 13190656} +{"current_steps": 6105, "total_steps": 122600, "loss": 0.1946, "lr": 2.4893964110929855e-05, "epoch": 0.9959216965742251, "percentage": 4.98, "elapsed_time": "0:44:07", "remaining_time": "14:01:55", "throughput": 4986.62, "total_tokens": 13201120} +{"current_steps": 6110, "total_steps": 122600, "loss": 0.0936, "lr": 2.491435562805873e-05, "epoch": 0.9967373572593801, "percentage": 4.98, "elapsed_time": "0:44:09", "remaining_time": "14:01:52", "throughput": 4986.63, "total_tokens": 13211744} +{"current_steps": 6115, "total_steps": 122600, "loss": 0.198, "lr": 2.4934747145187602e-05, "epoch": 0.9975530179445351, "percentage": 4.99, "elapsed_time": "0:44:11", "remaining_time": "14:01:50", "throughput": 4986.68, "total_tokens": 13222752} +{"current_steps": 6120, "total_steps": 122600, "loss": 0.2443, "lr": 2.4955138662316476e-05, "epoch": 0.99836867862969, "percentage": 4.99, "elapsed_time": "0:44:13", "remaining_time": "14:01:49", "throughput": 4986.67, "total_tokens": 13233696} +{"current_steps": 6125, "total_steps": 122600, "loss": 0.1975, "lr": 2.4975530179445353e-05, "epoch": 0.9991843393148451, "percentage": 5.0, "elapsed_time": "0:44:16", "remaining_time": "14:01:51", "throughput": 4986.65, "total_tokens": 13245504} +{"current_steps": 6130, "total_steps": 122600, "loss": 0.2557, "lr": 2.4995921696574227e-05, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:44:18", "remaining_time": "14:01:47", "throughput": 4986.48, "total_tokens": 13255424} +{"current_steps": 6130, "total_steps": 122600, "eval_loss": 0.16971780359745026, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:45:48", "remaining_time": "14:30:28", "throughput": 4822.09, "total_tokens": 13255424} +{"current_steps": 6135, "total_steps": 122600, "loss": 0.1987, "lr": 2.50163132137031e-05, "epoch": 1.000815660685155, "percentage": 5.0, "elapsed_time": "0:45:52", "remaining_time": "14:30:49", "throughput": 4819.89, "total_tokens": 13265952}