diff --git "a/Qwen2.5-7b-Med-REFL-LoraAdapter/trainer_log.jsonl" "b/Qwen2.5-7b-Med-REFL-LoraAdapter/trainer_log.jsonl" new file mode 100644--- /dev/null +++ "b/Qwen2.5-7b-Med-REFL-LoraAdapter/trainer_log.jsonl" @@ -0,0 +1,713 @@ +{"current_steps": 1, "total_steps": 522, "loss": 0.6931, "accuracy": 0.0, "lr": 1.0000000000000002e-06, "epoch": 0.0038305003591094086, "percentage": 0.19, "elapsed_time": "0:01:26", "remaining_time": "12:33:19", "throughput": 4287.53, "total_tokens": 371968} +{"current_steps": 2, "total_steps": 522, "loss": 0.6931, "accuracy": 0.0, "lr": 2.0000000000000003e-06, "epoch": 0.007661000718218817, "percentage": 0.38, "elapsed_time": "0:02:52", "remaining_time": "12:25:32", "throughput": 4307.98, "total_tokens": 741184} +{"current_steps": 3, "total_steps": 522, "loss": 0.7055, "accuracy": 0.4765625, "lr": 3e-06, "epoch": 0.011491501077328227, "percentage": 0.57, "elapsed_time": "0:04:15", "remaining_time": "12:15:41", "throughput": 4356.87, "total_tokens": 1111680} +{"current_steps": 4, "total_steps": 522, "loss": 0.689, "accuracy": 0.5546875, "lr": 4.000000000000001e-06, "epoch": 0.015322001436437634, "percentage": 0.77, "elapsed_time": "0:05:38", "remaining_time": "12:11:35", "throughput": 4359.87, "total_tokens": 1477824} +{"current_steps": 5, "total_steps": 522, "loss": 0.7059, "accuracy": 0.46875, "lr": 5e-06, "epoch": 0.019152501795547044, "percentage": 0.96, "elapsed_time": "0:07:00", "remaining_time": "12:04:10", "throughput": 4390.06, "total_tokens": 1844800} +{"current_steps": 6, "total_steps": 522, "loss": 0.7038, "accuracy": 0.4140625, "lr": 6e-06, "epoch": 0.022983002154656453, "percentage": 1.15, "elapsed_time": "0:08:20", "remaining_time": "11:57:13", "throughput": 4398.09, "total_tokens": 2200768} +{"current_steps": 7, "total_steps": 522, "loss": 0.7043, "accuracy": 0.453125, "lr": 7e-06, "epoch": 0.02681350251376586, "percentage": 1.34, "elapsed_time": "0:09:40", "remaining_time": "11:51:42", "throughput": 4423.39, "total_tokens": 2567424} +{"current_steps": 8, "total_steps": 522, "loss": 0.7051, "accuracy": 0.453125, "lr": 8.000000000000001e-06, "epoch": 0.03064400287287527, "percentage": 1.53, "elapsed_time": "0:11:06", "remaining_time": "11:53:25", "throughput": 4417.35, "total_tokens": 2942976} +{"current_steps": 9, "total_steps": 522, "loss": 0.6838, "accuracy": 0.5625, "lr": 9e-06, "epoch": 0.03447450323198468, "percentage": 1.72, "elapsed_time": "0:12:29", "remaining_time": "11:52:03", "throughput": 4434.07, "total_tokens": 3323520} +{"current_steps": 10, "total_steps": 522, "loss": 0.7004, "accuracy": 0.46875, "lr": 1e-05, "epoch": 0.03830500359109409, "percentage": 1.92, "elapsed_time": "0:13:54", "remaining_time": "11:52:20", "throughput": 4441.37, "total_tokens": 3707584} +{"current_steps": 11, "total_steps": 522, "loss": 0.6831, "accuracy": 0.5859375, "lr": 9.999905876413006e-06, "epoch": 0.0421355039502035, "percentage": 2.11, "elapsed_time": "0:15:18", "remaining_time": "11:51:31", "throughput": 4459.8, "total_tokens": 4098496} +{"current_steps": 12, "total_steps": 522, "loss": 0.6995, "accuracy": 0.5234375, "lr": 9.999623509195724e-06, "epoch": 0.045966004309312906, "percentage": 2.3, "elapsed_time": "0:16:40", "remaining_time": "11:48:59", "throughput": 4460.63, "total_tokens": 4464768} +{"current_steps": 13, "total_steps": 522, "loss": 0.6997, "accuracy": 0.484375, "lr": 9.999152908979117e-06, "epoch": 0.049796504668422316, "percentage": 2.49, "elapsed_time": "0:18:06", "remaining_time": "11:48:42", "throughput": 4465.7, "total_tokens": 4849856} +{"current_steps": 14, "total_steps": 522, "loss": 0.6947, "accuracy": 0.4765625, "lr": 9.998494093481022e-06, "epoch": 0.05362700502753172, "percentage": 2.68, "elapsed_time": "0:19:27", "remaining_time": "11:46:10", "throughput": 4467.95, "total_tokens": 5217152} +{"current_steps": 15, "total_steps": 522, "loss": 0.6908, "accuracy": 0.5234375, "lr": 9.997647087505467e-06, "epoch": 0.05745750538664113, "percentage": 2.87, "elapsed_time": "0:20:47", "remaining_time": "11:42:58", "throughput": 4468.63, "total_tokens": 5576320} +{"current_steps": 16, "total_steps": 522, "loss": 0.6791, "accuracy": 0.578125, "lr": 9.996611922941748e-06, "epoch": 0.06128800574575054, "percentage": 3.07, "elapsed_time": "0:22:09", "remaining_time": "11:40:43", "throughput": 4467.65, "total_tokens": 5939520} +{"current_steps": 17, "total_steps": 522, "loss": 0.6854, "accuracy": 0.546875, "lr": 9.995388638763229e-06, "epoch": 0.06511850610485995, "percentage": 3.26, "elapsed_time": "0:23:29", "remaining_time": "11:37:53", "throughput": 4475.18, "total_tokens": 6308288} +{"current_steps": 18, "total_steps": 522, "loss": 0.6872, "accuracy": 0.5234375, "lr": 9.993977281025862e-06, "epoch": 0.06894900646396936, "percentage": 3.45, "elapsed_time": "0:24:54", "remaining_time": "11:37:30", "throughput": 4473.36, "total_tokens": 6686080} +{"current_steps": 19, "total_steps": 522, "loss": 0.6836, "accuracy": 0.5625, "lr": 9.992377902866474e-06, "epoch": 0.07277950682307877, "percentage": 3.64, "elapsed_time": "0:26:16", "remaining_time": "11:35:27", "throughput": 4474.18, "total_tokens": 7052096} +{"current_steps": 20, "total_steps": 522, "loss": 0.6798, "accuracy": 0.546875, "lr": 9.990590564500745e-06, "epoch": 0.07661000718218818, "percentage": 3.83, "elapsed_time": "0:27:39", "remaining_time": "11:34:19", "throughput": 4464.1, "total_tokens": 7409280} +{"current_steps": 21, "total_steps": 522, "loss": 0.6801, "accuracy": 0.6171875, "lr": 9.98861533322096e-06, "epoch": 0.08044050754129758, "percentage": 4.02, "elapsed_time": "0:29:07", "remaining_time": "11:35:00", "throughput": 4457.14, "total_tokens": 7790784} +{"current_steps": 22, "total_steps": 522, "loss": 0.6602, "accuracy": 0.6328125, "lr": 9.986452283393452e-06, "epoch": 0.084271007900407, "percentage": 4.21, "elapsed_time": "0:30:32", "remaining_time": "11:34:18", "throughput": 4456.71, "total_tokens": 8169024} +{"current_steps": 23, "total_steps": 522, "loss": 0.6697, "accuracy": 0.5390625, "lr": 9.984101496455828e-06, "epoch": 0.0881015082595164, "percentage": 4.41, "elapsed_time": "0:31:54", "remaining_time": "11:32:23", "throughput": 4458.8, "total_tokens": 8537792} +{"current_steps": 24, "total_steps": 522, "loss": 0.651, "accuracy": 0.6796875, "lr": 9.98156306091389e-06, "epoch": 0.09193200861862581, "percentage": 4.6, "elapsed_time": "0:33:15", "remaining_time": "11:29:57", "throughput": 4463.06, "total_tokens": 8904000} +{"current_steps": 25, "total_steps": 522, "loss": 0.6442, "accuracy": 0.6640625, "lr": 9.9788370723383e-06, "epoch": 0.09576250897773522, "percentage": 4.79, "elapsed_time": "0:34:38", "remaining_time": "11:28:45", "throughput": 4464.27, "total_tokens": 9280192} +{"current_steps": 26, "total_steps": 522, "loss": 0.6436, "accuracy": 0.6953125, "lr": 9.975923633360985e-06, "epoch": 0.09959300933684463, "percentage": 4.98, "elapsed_time": "0:36:04", "remaining_time": "11:28:05", "throughput": 4463.9, "total_tokens": 9660480} +{"current_steps": 27, "total_steps": 522, "loss": 0.6451, "accuracy": 0.65625, "lr": 9.972822853671277e-06, "epoch": 0.10342350969595403, "percentage": 5.17, "elapsed_time": "0:37:25", "remaining_time": "11:26:13", "throughput": 4463.8, "total_tokens": 10025024} +{"current_steps": 28, "total_steps": 522, "loss": 0.6276, "accuracy": 0.71875, "lr": 9.969534850011782e-06, "epoch": 0.10725401005506344, "percentage": 5.36, "elapsed_time": "0:38:44", "remaining_time": "11:23:37", "throughput": 4465.76, "total_tokens": 10382336} +{"current_steps": 29, "total_steps": 522, "loss": 0.6426, "accuracy": 0.671875, "lr": 9.966059746173973e-06, "epoch": 0.11108451041417285, "percentage": 5.56, "elapsed_time": "0:40:06", "remaining_time": "11:21:44", "throughput": 4466.94, "total_tokens": 10748160} +{"current_steps": 30, "total_steps": 522, "loss": 0.6251, "accuracy": 0.7265625, "lr": 9.962397672993552e-06, "epoch": 0.11491501077328226, "percentage": 5.75, "elapsed_time": "0:41:32", "remaining_time": "11:21:10", "throughput": 4465.94, "total_tokens": 11129600} +{"current_steps": 31, "total_steps": 522, "loss": 0.6208, "accuracy": 0.6796875, "lr": 9.958548768345498e-06, "epoch": 0.11874551113239167, "percentage": 5.94, "elapsed_time": "0:42:56", "remaining_time": "11:20:01", "throughput": 4466.63, "total_tokens": 11506240} +{"current_steps": 32, "total_steps": 522, "loss": 0.609, "accuracy": 0.7578125, "lr": 9.9545131771389e-06, "epoch": 0.12257601149150107, "percentage": 6.13, "elapsed_time": "0:44:15", "remaining_time": "11:17:38", "throughput": 4466.85, "total_tokens": 11860736} +{"current_steps": 33, "total_steps": 522, "loss": 0.61, "accuracy": 0.703125, "lr": 9.950291051311486e-06, "epoch": 0.1264065118506105, "percentage": 6.32, "elapsed_time": "0:45:39", "remaining_time": "11:16:30", "throughput": 4468.61, "total_tokens": 12240448} +{"current_steps": 34, "total_steps": 522, "loss": 0.6128, "accuracy": 0.7109375, "lr": 9.945882549823906e-06, "epoch": 0.1302370122097199, "percentage": 6.51, "elapsed_time": "0:47:03", "remaining_time": "11:15:21", "throughput": 4470.67, "total_tokens": 12621632} +{"current_steps": 1, "total_steps": 260, "loss": 0.6931, "accuracy": 0.0, "lr": 1.0000000000000002e-06, "epoch": 0.007659167065581618, "percentage": 0.38, "elapsed_time": "0:01:35", "remaining_time": "6:53:18", "throughput": 7680.28, "total_tokens": 735360} +{"current_steps": 2, "total_steps": 260, "loss": 0.6931, "accuracy": 0.0, "lr": 2.0000000000000003e-06, "epoch": 0.015318334131163236, "percentage": 0.77, "elapsed_time": "0:03:10", "remaining_time": "6:48:32", "throughput": 7717.15, "total_tokens": 1466432} +{"current_steps": 3, "total_steps": 260, "loss": 0.6989, "accuracy": 0.4765625, "lr": 3e-06, "epoch": 0.022977501196744854, "percentage": 1.15, "elapsed_time": "0:04:36", "remaining_time": "6:34:54", "throughput": 7894.39, "total_tokens": 2183488} +{"current_steps": 4, "total_steps": 260, "loss": 0.7061, "accuracy": 0.453125, "lr": 4.000000000000001e-06, "epoch": 0.030636668262326472, "percentage": 1.54, "elapsed_time": "0:06:05", "remaining_time": "6:29:42", "throughput": 7991.98, "total_tokens": 2919872} +{"current_steps": 5, "total_steps": 260, "loss": 0.7005, "accuracy": 0.484375, "lr": 5e-06, "epoch": 0.03829583532790809, "percentage": 1.92, "elapsed_time": "0:07:33", "remaining_time": "6:25:53", "throughput": 8102.55, "total_tokens": 3678464} +{"current_steps": 6, "total_steps": 260, "loss": 0.7007, "accuracy": 0.484375, "lr": 6e-06, "epoch": 0.04595500239348971, "percentage": 2.31, "elapsed_time": "0:09:02", "remaining_time": "6:22:38", "throughput": 8168.32, "total_tokens": 4429824} +{"current_steps": 7, "total_steps": 260, "loss": 0.6939, "accuracy": 0.49609375, "lr": 7e-06, "epoch": 0.053614169459071326, "percentage": 2.69, "elapsed_time": "0:10:30", "remaining_time": "6:19:40", "throughput": 8212.44, "total_tokens": 5176256} +{"current_steps": 8, "total_steps": 260, "loss": 0.6994, "accuracy": 0.4921875, "lr": 8.000000000000001e-06, "epoch": 0.061273336524652944, "percentage": 3.08, "elapsed_time": "0:11:55", "remaining_time": "6:15:51", "throughput": 8231.14, "total_tokens": 5892736} +{"current_steps": 9, "total_steps": 260, "loss": 0.6966, "accuracy": 0.515625, "lr": 9e-06, "epoch": 0.06893250359023456, "percentage": 3.46, "elapsed_time": "0:13:21", "remaining_time": "6:12:46", "throughput": 8271.76, "total_tokens": 6633792} +{"current_steps": 10, "total_steps": 260, "loss": 0.6901, "accuracy": 0.5625, "lr": 1e-05, "epoch": 0.07659167065581618, "percentage": 3.85, "elapsed_time": "0:14:50", "remaining_time": "6:10:58", "throughput": 8257.1, "total_tokens": 7351552} +{"current_steps": 1, "total_steps": 260, "loss": 0.6931, "accuracy": 0.0, "lr": 1.0000000000000002e-06, "epoch": 0.007659167065581618, "percentage": 0.38, "elapsed_time": "0:01:37", "remaining_time": "6:59:05", "throughput": 7574.24, "total_tokens": 735360} +{"current_steps": 2, "total_steps": 260, "loss": 0.6931, "accuracy": 0.0, "lr": 2.0000000000000003e-06, "epoch": 0.015318334131163236, "percentage": 0.77, "elapsed_time": "0:03:11", "remaining_time": "6:52:04", "throughput": 7651.25, "total_tokens": 1466432} +{"current_steps": 3, "total_steps": 260, "loss": 0.699, "accuracy": 0.49609375, "lr": 3e-06, "epoch": 0.022977501196744854, "percentage": 1.15, "elapsed_time": "0:04:38", "remaining_time": "6:37:29", "throughput": 7842.95, "total_tokens": 2183488} +{"current_steps": 4, "total_steps": 260, "loss": 0.704, "accuracy": 0.453125, "lr": 4.000000000000001e-06, "epoch": 0.030636668262326472, "percentage": 1.54, "elapsed_time": "0:06:07", "remaining_time": "6:31:46", "throughput": 7949.92, "total_tokens": 2919872} +{"current_steps": 5, "total_steps": 260, "loss": 0.6998, "accuracy": 0.5078125, "lr": 5e-06, "epoch": 0.03829583532790809, "percentage": 1.92, "elapsed_time": "0:07:36", "remaining_time": "6:27:49", "throughput": 8062.22, "total_tokens": 3678464} +{"current_steps": 6, "total_steps": 260, "loss": 0.6964, "accuracy": 0.5, "lr": 6e-06, "epoch": 0.04595500239348971, "percentage": 2.31, "elapsed_time": "0:09:04", "remaining_time": "6:24:17", "throughput": 8132.93, "total_tokens": 4429824} +{"current_steps": 7, "total_steps": 260, "loss": 0.6966, "accuracy": 0.49609375, "lr": 7e-06, "epoch": 0.053614169459071326, "percentage": 2.69, "elapsed_time": "0:10:32", "remaining_time": "6:21:10", "throughput": 8180.19, "total_tokens": 5176256} +{"current_steps": 8, "total_steps": 260, "loss": 0.6983, "accuracy": 0.47265625, "lr": 8.000000000000001e-06, "epoch": 0.061273336524652944, "percentage": 3.08, "elapsed_time": "0:11:58", "remaining_time": "6:17:09", "throughput": 8202.63, "total_tokens": 5892736} +{"current_steps": 9, "total_steps": 260, "loss": 0.6908, "accuracy": 0.54296875, "lr": 9e-06, "epoch": 0.06893250359023456, "percentage": 3.46, "elapsed_time": "0:13:24", "remaining_time": "6:13:55", "throughput": 8246.21, "total_tokens": 6633792} +{"current_steps": 10, "total_steps": 260, "loss": 0.6941, "accuracy": 0.515625, "lr": 1e-05, "epoch": 0.07659167065581618, "percentage": 3.85, "elapsed_time": "0:14:53", "remaining_time": "6:12:14", "throughput": 8229.08, "total_tokens": 7351552} +{"current_steps": 1, "total_steps": 260, "loss": 0.6931, "accuracy": 0.0, "lr": 1.0000000000000002e-06, "epoch": 0.007659167065581618, "percentage": 0.38, "elapsed_time": "0:01:35", "remaining_time": "6:54:19", "throughput": 7661.29, "total_tokens": 735360} +{"current_steps": 2, "total_steps": 260, "loss": 0.6931, "accuracy": 0.0, "lr": 2.0000000000000003e-06, "epoch": 0.015318334131163236, "percentage": 0.77, "elapsed_time": "0:03:11", "remaining_time": "6:50:48", "throughput": 7674.59, "total_tokens": 1466432} +{"current_steps": 3, "total_steps": 260, "loss": 0.6972, "accuracy": 0.49609375, "lr": 3e-06, "epoch": 0.022977501196744854, "percentage": 1.15, "elapsed_time": "0:04:37", "remaining_time": "6:36:46", "throughput": 7857.3, "total_tokens": 2183488} +{"current_steps": 4, "total_steps": 260, "loss": 0.6924, "accuracy": 0.5234375, "lr": 4.000000000000001e-06, "epoch": 0.030636668262326472, "percentage": 1.54, "elapsed_time": "0:06:06", "remaining_time": "6:31:14", "throughput": 7960.63, "total_tokens": 2919872} +{"current_steps": 5, "total_steps": 260, "loss": 0.7023, "accuracy": 0.43359375, "lr": 5e-06, "epoch": 0.03829583532790809, "percentage": 1.92, "elapsed_time": "0:07:35", "remaining_time": "6:27:15", "throughput": 8073.77, "total_tokens": 3678464} +{"current_steps": 6, "total_steps": 260, "loss": 0.695, "accuracy": 0.51953125, "lr": 6e-06, "epoch": 0.04595500239348971, "percentage": 2.31, "elapsed_time": "0:09:04", "remaining_time": "6:23:51", "throughput": 8142.18, "total_tokens": 4429824} +{"current_steps": 7, "total_steps": 260, "loss": 0.693, "accuracy": 0.55078125, "lr": 7e-06, "epoch": 0.053614169459071326, "percentage": 2.69, "elapsed_time": "0:10:32", "remaining_time": "6:20:49", "throughput": 8187.66, "total_tokens": 5176256} +{"current_steps": 8, "total_steps": 260, "loss": 0.7103, "accuracy": 0.4765625, "lr": 8.000000000000001e-06, "epoch": 0.061273336524652944, "percentage": 3.08, "elapsed_time": "0:11:57", "remaining_time": "6:16:48", "throughput": 8210.12, "total_tokens": 5892736} +{"current_steps": 9, "total_steps": 260, "loss": 0.698, "accuracy": 0.49609375, "lr": 9e-06, "epoch": 0.06893250359023456, "percentage": 3.46, "elapsed_time": "0:13:23", "remaining_time": "6:13:38", "throughput": 8252.56, "total_tokens": 6633792} +{"current_steps": 10, "total_steps": 260, "loss": 0.696, "accuracy": 0.4921875, "lr": 1e-05, "epoch": 0.07659167065581618, "percentage": 3.85, "elapsed_time": "0:14:52", "remaining_time": "6:12:02", "throughput": 8233.47, "total_tokens": 7351552} +{"current_steps": 1, "total_steps": 260, "loss": 0.6931, "accuracy": 0.0, "lr": 1.0000000000000002e-06, "epoch": 0.007659167065581618, "percentage": 0.38, "elapsed_time": "0:01:41", "remaining_time": "7:18:38", "throughput": 7236.66, "total_tokens": 735360} +{"current_steps": 2, "total_steps": 260, "loss": 0.6931, "accuracy": 0.0, "lr": 2.0000000000000003e-06, "epoch": 0.015318334131163236, "percentage": 0.77, "elapsed_time": "0:03:17", "remaining_time": "7:05:06", "throughput": 7416.61, "total_tokens": 1466432} +{"current_steps": 3, "total_steps": 260, "loss": 0.6892, "accuracy": 0.53515625, "lr": 3e-06, "epoch": 0.022977501196744854, "percentage": 1.15, "elapsed_time": "0:04:47", "remaining_time": "6:50:02", "throughput": 7602.95, "total_tokens": 2183488} +{"current_steps": 4, "total_steps": 260, "loss": 0.7011, "accuracy": 0.46875, "lr": 4.000000000000001e-06, "epoch": 0.030636668262326472, "percentage": 1.54, "elapsed_time": "0:06:18", "remaining_time": "6:44:01", "throughput": 7708.62, "total_tokens": 2919872} +{"current_steps": 5, "total_steps": 260, "loss": 0.6943, "accuracy": 0.5234375, "lr": 5e-06, "epoch": 0.03829583532790809, "percentage": 1.92, "elapsed_time": "0:07:50", "remaining_time": "6:40:14", "throughput": 7812.12, "total_tokens": 3678464} +{"current_steps": 6, "total_steps": 260, "loss": 0.6911, "accuracy": 0.5078125, "lr": 6e-06, "epoch": 0.04595500239348971, "percentage": 2.31, "elapsed_time": "0:09:22", "remaining_time": "6:36:43", "throughput": 7878.21, "total_tokens": 4429824} +{"current_steps": 7, "total_steps": 260, "loss": 0.7047, "accuracy": 0.43359375, "lr": 7e-06, "epoch": 0.053614169459071326, "percentage": 2.69, "elapsed_time": "0:10:53", "remaining_time": "6:33:33", "throughput": 7922.92, "total_tokens": 5176256} +{"current_steps": 8, "total_steps": 260, "loss": 0.7047, "accuracy": 0.45703125, "lr": 8.000000000000001e-06, "epoch": 0.061273336524652944, "percentage": 3.08, "elapsed_time": "0:12:21", "remaining_time": "6:29:28", "throughput": 7943.06, "total_tokens": 5892736} +{"current_steps": 9, "total_steps": 260, "loss": 0.6952, "accuracy": 0.48828125, "lr": 9e-06, "epoch": 0.06893250359023456, "percentage": 3.46, "elapsed_time": "0:13:50", "remaining_time": "6:26:13", "throughput": 7983.53, "total_tokens": 6633792} +{"current_steps": 10, "total_steps": 260, "loss": 0.6951, "accuracy": 0.4921875, "lr": 1e-05, "epoch": 0.07659167065581618, "percentage": 3.85, "elapsed_time": "0:15:22", "remaining_time": "6:24:26", "throughput": 7967.76, "total_tokens": 7351552} +{"current_steps": 11, "total_steps": 260, "loss": 0.6864, "accuracy": 0.546875, "lr": 9.999605221019082e-06, "epoch": 0.0842508377213978, "percentage": 4.23, "elapsed_time": "0:16:58", "remaining_time": "6:24:17", "throughput": 7957.48, "total_tokens": 8105536} +{"current_steps": 12, "total_steps": 260, "loss": 0.69, "accuracy": 0.51171875, "lr": 9.9984209464165e-06, "epoch": 0.09191000478697942, "percentage": 4.62, "elapsed_time": "0:18:29", "remaining_time": "6:22:10", "throughput": 7962.13, "total_tokens": 8834496} +{"current_steps": 13, "total_steps": 260, "loss": 0.6956, "accuracy": 0.52734375, "lr": 9.996447363202947e-06, "epoch": 0.09956917185256103, "percentage": 5.0, "elapsed_time": "0:20:00", "remaining_time": "6:20:09", "throughput": 7984.48, "total_tokens": 9585408} +{"current_steps": 14, "total_steps": 260, "loss": 0.6938, "accuracy": 0.53515625, "lr": 9.99368478303009e-06, "epoch": 0.10722833891814265, "percentage": 5.38, "elapsed_time": "0:21:29", "remaining_time": "6:17:43", "throughput": 7987.15, "total_tokens": 10301760} +{"current_steps": 15, "total_steps": 260, "loss": 0.6889, "accuracy": 0.5234375, "lr": 9.990133642141359e-06, "epoch": 0.11488750598372427, "percentage": 5.77, "elapsed_time": "0:23:00", "remaining_time": "6:15:50", "throughput": 7998.8, "total_tokens": 11043328} +{"current_steps": 16, "total_steps": 260, "loss": 0.6781, "accuracy": 0.578125, "lr": 9.98579450130307e-06, "epoch": 0.12254667304930589, "percentage": 6.15, "elapsed_time": "0:24:30", "remaining_time": "6:13:50", "throughput": 8001.12, "total_tokens": 11768640} +{"current_steps": 17, "total_steps": 260, "loss": 0.685, "accuracy": 0.5390625, "lr": 9.980668045715864e-06, "epoch": 0.1302058401148875, "percentage": 6.54, "elapsed_time": "0:26:06", "remaining_time": "6:13:10", "throughput": 7995.33, "total_tokens": 12523904} +{"current_steps": 18, "total_steps": 260, "loss": 0.6818, "accuracy": 0.58203125, "lr": 9.974755084906503e-06, "epoch": 0.13786500718046912, "percentage": 6.92, "elapsed_time": "0:27:41", "remaining_time": "6:12:13", "throughput": 7989.15, "total_tokens": 13271296} +{"current_steps": 19, "total_steps": 260, "loss": 0.6786, "accuracy": 0.5703125, "lr": 9.968056552600043e-06, "epoch": 0.14552417424605074, "percentage": 7.31, "elapsed_time": "0:29:15", "remaining_time": "6:11:01", "throughput": 7983.73, "total_tokens": 14012096} +{"current_steps": 20, "total_steps": 260, "loss": 0.6712, "accuracy": 0.65234375, "lr": 9.960573506572391e-06, "epoch": 0.15318334131163236, "percentage": 7.69, "elapsed_time": "0:30:42", "remaining_time": "6:08:29", "throughput": 7999.51, "total_tokens": 14738752} +{"current_steps": 21, "total_steps": 260, "loss": 0.661, "accuracy": 0.66796875, "lr": 9.952307128483257e-06, "epoch": 0.16084250837721398, "percentage": 8.08, "elapsed_time": "0:32:11", "remaining_time": "6:06:24", "throughput": 8012.81, "total_tokens": 15478208} +{"current_steps": 22, "total_steps": 260, "loss": 0.6642, "accuracy": 0.6171875, "lr": 9.94325872368957e-06, "epoch": 0.1685016754427956, "percentage": 8.46, "elapsed_time": "0:33:40", "remaining_time": "6:04:14", "throughput": 8017.09, "total_tokens": 16196096} +{"current_steps": 23, "total_steps": 260, "loss": 0.6455, "accuracy": 0.6953125, "lr": 9.93342972103934e-06, "epoch": 0.1761608425083772, "percentage": 8.85, "elapsed_time": "0:35:17", "remaining_time": "6:03:34", "throughput": 8000.97, "total_tokens": 16938176} +{"current_steps": 24, "total_steps": 260, "loss": 0.646, "accuracy": 0.68359375, "lr": 9.922821672646028e-06, "epoch": 0.18382000957395883, "percentage": 9.23, "elapsed_time": "0:36:50", "remaining_time": "6:02:17", "throughput": 7989.45, "total_tokens": 17661440} +{"current_steps": 25, "total_steps": 260, "loss": 0.6465, "accuracy": 0.66796875, "lr": 9.911436253643445e-06, "epoch": 0.19147917663954045, "percentage": 9.62, "elapsed_time": "0:38:20", "remaining_time": "6:00:27", "throughput": 7997.75, "total_tokens": 18401408} +{"current_steps": 26, "total_steps": 260, "loss": 0.6335, "accuracy": 0.7265625, "lr": 9.899275261921236e-06, "epoch": 0.19913834370512207, "percentage": 10.0, "elapsed_time": "0:39:50", "remaining_time": "5:58:31", "throughput": 8005.56, "total_tokens": 19134912} +{"current_steps": 27, "total_steps": 260, "loss": 0.6179, "accuracy": 0.76171875, "lr": 9.886340617840968e-06, "epoch": 0.20679751077070369, "percentage": 10.38, "elapsed_time": "0:41:19", "remaining_time": "5:56:36", "throughput": 8011.53, "total_tokens": 19863616} +{"current_steps": 28, "total_steps": 260, "loss": 0.607, "accuracy": 0.77734375, "lr": 9.872634363932887e-06, "epoch": 0.2144566778362853, "percentage": 10.77, "elapsed_time": "0:42:52", "remaining_time": "5:55:17", "throughput": 8010.0, "total_tokens": 20608512} +{"current_steps": 29, "total_steps": 260, "loss": 0.6013, "accuracy": 0.77734375, "lr": 9.85815866457337e-06, "epoch": 0.22211584490186692, "percentage": 11.15, "elapsed_time": "0:44:21", "remaining_time": "5:53:21", "throughput": 8012.12, "total_tokens": 21325952} +{"current_steps": 30, "total_steps": 260, "loss": 0.5852, "accuracy": 0.78125, "lr": 9.842915805643156e-06, "epoch": 0.22977501196744854, "percentage": 11.54, "elapsed_time": "0:45:51", "remaining_time": "5:51:35", "throughput": 8019.26, "total_tokens": 22065984} +{"current_steps": 31, "total_steps": 260, "loss": 0.5936, "accuracy": 0.7890625, "lr": 9.82690819416637e-06, "epoch": 0.23743417903303016, "percentage": 11.92, "elapsed_time": "0:47:18", "remaining_time": "5:49:26", "throughput": 8021.64, "total_tokens": 22767808} +{"current_steps": 32, "total_steps": 260, "loss": 0.5801, "accuracy": 0.78125, "lr": 9.81013835793043e-06, "epoch": 0.24509334609861178, "percentage": 12.31, "elapsed_time": "0:48:47", "remaining_time": "5:47:35", "throughput": 8027.61, "total_tokens": 23497600} +{"current_steps": 33, "total_steps": 260, "loss": 0.5599, "accuracy": 0.81640625, "lr": 9.79260894508688e-06, "epoch": 0.2527525131641934, "percentage": 12.69, "elapsed_time": "0:50:17", "remaining_time": "5:45:56", "throughput": 8031.38, "total_tokens": 24234624} +{"current_steps": 34, "total_steps": 260, "loss": 0.5483, "accuracy": 0.8125, "lr": 9.774322723733216e-06, "epoch": 0.260411680229775, "percentage": 13.08, "elapsed_time": "0:51:46", "remaining_time": "5:44:09", "throughput": 8038.07, "total_tokens": 24971008} +{"current_steps": 35, "total_steps": 260, "loss": 0.5437, "accuracy": 0.81640625, "lr": 9.755282581475769e-06, "epoch": 0.26807084729535663, "percentage": 13.46, "elapsed_time": "0:53:21", "remaining_time": "5:43:00", "throughput": 8033.93, "total_tokens": 25720192} +{"current_steps": 36, "total_steps": 260, "loss": 0.534, "accuracy": 0.83203125, "lr": 9.735491524973723e-06, "epoch": 0.27573001436093825, "percentage": 13.85, "elapsed_time": "0:54:49", "remaining_time": "5:41:07", "throughput": 8041.95, "total_tokens": 26453632} +{"current_steps": 37, "total_steps": 260, "loss": 0.5393, "accuracy": 0.81640625, "lr": 9.714952679464324e-06, "epoch": 0.28338918142651986, "percentage": 14.23, "elapsed_time": "0:56:22", "remaining_time": "5:39:44", "throughput": 8035.9, "total_tokens": 27179136} +{"current_steps": 38, "total_steps": 260, "loss": 0.5231, "accuracy": 0.80859375, "lr": 9.693669288269371e-06, "epoch": 0.2910483484921015, "percentage": 14.62, "elapsed_time": "0:57:53", "remaining_time": "5:38:15", "throughput": 8038.82, "total_tokens": 27926656} +{"current_steps": 39, "total_steps": 260, "loss": 0.5175, "accuracy": 0.7890625, "lr": 9.671644712283061e-06, "epoch": 0.2987075155576831, "percentage": 15.0, "elapsed_time": "0:59:20", "remaining_time": "5:36:18", "throughput": 8048.33, "total_tokens": 28659776} +{"current_steps": 40, "total_steps": 260, "loss": 0.5138, "accuracy": 0.80078125, "lr": 9.648882429441258e-06, "epoch": 0.3063666826232647, "percentage": 15.38, "elapsed_time": "1:00:52", "remaining_time": "5:34:48", "throughput": 8050.79, "total_tokens": 29404928} +{"current_steps": 41, "total_steps": 260, "loss": 0.4794, "accuracy": 0.8125, "lr": 9.62538603417229e-06, "epoch": 0.31402584968884634, "percentage": 15.77, "elapsed_time": "1:02:22", "remaining_time": "5:33:09", "throughput": 8049.64, "total_tokens": 30124096} +{"current_steps": 42, "total_steps": 260, "loss": 0.4868, "accuracy": 0.8359375, "lr": 9.601159236829353e-06, "epoch": 0.32168501675442795, "percentage": 16.15, "elapsed_time": "1:03:52", "remaining_time": "5:31:30", "throughput": 8055.29, "total_tokens": 30868160} +{"current_steps": 43, "total_steps": 260, "loss": 0.4612, "accuracy": 0.8203125, "lr": 9.576205863104588e-06, "epoch": 0.3293441838200096, "percentage": 16.54, "elapsed_time": "1:05:21", "remaining_time": "5:29:50", "throughput": 8057.22, "total_tokens": 31598144} +{"current_steps": 44, "total_steps": 260, "loss": 0.4751, "accuracy": 0.84765625, "lr": 9.550529853424979e-06, "epoch": 0.3370033508855912, "percentage": 16.92, "elapsed_time": "1:06:52", "remaining_time": "5:28:15", "throughput": 8059.49, "total_tokens": 32335488} +{"current_steps": 45, "total_steps": 260, "loss": 0.4637, "accuracy": 0.8203125, "lr": 9.524135262330098e-06, "epoch": 0.3446625179511728, "percentage": 17.31, "elapsed_time": "1:08:22", "remaining_time": "5:26:40", "throughput": 8062.24, "total_tokens": 33073984} +{"current_steps": 46, "total_steps": 260, "loss": 0.4324, "accuracy": 0.859375, "lr": 9.497026257831856e-06, "epoch": 0.3523216850167544, "percentage": 17.69, "elapsed_time": "1:09:54", "remaining_time": "5:25:13", "throughput": 8066.83, "total_tokens": 33835904} +{"current_steps": 47, "total_steps": 260, "loss": 0.4301, "accuracy": 0.859375, "lr": 9.46920712075632e-06, "epoch": 0.35998085208233604, "percentage": 18.08, "elapsed_time": "1:11:23", "remaining_time": "5:23:33", "throughput": 8071.77, "total_tokens": 34577216} +{"current_steps": 48, "total_steps": 260, "loss": 0.396, "accuracy": 0.890625, "lr": 9.440682244067724e-06, "epoch": 0.36764001914791766, "percentage": 18.46, "elapsed_time": "1:12:55", "remaining_time": "5:22:05", "throughput": 8070.85, "total_tokens": 35315136} +{"current_steps": 49, "total_steps": 260, "loss": 0.4038, "accuracy": 0.875, "lr": 9.411456132174768e-06, "epoch": 0.3752991862134993, "percentage": 18.85, "elapsed_time": "1:14:26", "remaining_time": "5:20:34", "throughput": 8074.31, "total_tokens": 36066688} +{"current_steps": 50, "total_steps": 260, "loss": 0.3948, "accuracy": 0.8515625, "lr": 9.381533400219319e-06, "epoch": 0.3829583532790809, "percentage": 19.23, "elapsed_time": "1:15:58", "remaining_time": "5:19:06", "throughput": 8073.95, "total_tokens": 36806464} +{"current_steps": 51, "total_steps": 260, "loss": 0.4296, "accuracy": 0.83984375, "lr": 9.35091877334763e-06, "epoch": 0.3906175203446625, "percentage": 19.62, "elapsed_time": "1:17:29", "remaining_time": "5:17:34", "throughput": 8073.86, "total_tokens": 37541312} +{"current_steps": 52, "total_steps": 260, "loss": 0.4131, "accuracy": 0.87109375, "lr": 9.319617085964177e-06, "epoch": 0.39827668741024413, "percentage": 20.0, "elapsed_time": "1:18:57", "remaining_time": "5:15:51", "throughput": 8075.85, "total_tokens": 38262912} +{"current_steps": 53, "total_steps": 260, "loss": 0.3526, "accuracy": 0.90625, "lr": 9.287633280968263e-06, "epoch": 0.40593585447582575, "percentage": 20.38, "elapsed_time": "1:20:28", "remaining_time": "5:14:17", "throughput": 8078.43, "total_tokens": 39004096} +{"current_steps": 54, "total_steps": 260, "loss": 0.3653, "accuracy": 0.85546875, "lr": 9.25497240897346e-06, "epoch": 0.41359502154140737, "percentage": 20.77, "elapsed_time": "1:21:59", "remaining_time": "5:12:47", "throughput": 8076.14, "total_tokens": 39731840} +{"current_steps": 55, "total_steps": 260, "loss": 0.4117, "accuracy": 0.84375, "lr": 9.221639627510076e-06, "epoch": 0.421254188606989, "percentage": 21.15, "elapsed_time": "1:23:27", "remaining_time": "5:11:04", "throughput": 8079.37, "total_tokens": 40458624} +{"current_steps": 56, "total_steps": 260, "loss": 0.3873, "accuracy": 0.85546875, "lr": 9.18764020021071e-06, "epoch": 0.4289133556725706, "percentage": 21.54, "elapsed_time": "1:24:57", "remaining_time": "5:09:30", "throughput": 8083.58, "total_tokens": 41208896} +{"current_steps": 57, "total_steps": 260, "loss": 0.3616, "accuracy": 0.88671875, "lr": 9.152979495979064e-06, "epoch": 0.4365725227381522, "percentage": 21.92, "elapsed_time": "1:26:24", "remaining_time": "5:07:43", "throughput": 8086.28, "total_tokens": 41922112} +{"current_steps": 58, "total_steps": 260, "loss": 0.3809, "accuracy": 0.84375, "lr": 9.117662988142138e-06, "epoch": 0.44423168980373384, "percentage": 22.31, "elapsed_time": "1:27:49", "remaining_time": "5:05:53", "throughput": 8089.72, "total_tokens": 42630400} +{"current_steps": 59, "total_steps": 260, "loss": 0.3325, "accuracy": 0.8828125, "lr": 9.08169625358592e-06, "epoch": 0.45189085686931546, "percentage": 22.69, "elapsed_time": "1:29:20", "remaining_time": "5:04:23", "throughput": 8091.15, "total_tokens": 43374912} +{"current_steps": 60, "total_steps": 260, "loss": 0.3279, "accuracy": 0.88671875, "lr": 9.045084971874738e-06, "epoch": 0.4595500239348971, "percentage": 23.08, "elapsed_time": "1:30:49", "remaining_time": "5:02:44", "throughput": 8091.86, "total_tokens": 44094272} +{"current_steps": 61, "total_steps": 260, "loss": 0.33, "accuracy": 0.875, "lr": 9.007834924354384e-06, "epoch": 0.4672091910004787, "percentage": 23.46, "elapsed_time": "1:32:18", "remaining_time": "5:01:08", "throughput": 8094.04, "total_tokens": 44828992} +{"current_steps": 62, "total_steps": 260, "loss": 0.3396, "accuracy": 0.87109375, "lr": 8.969951993239177e-06, "epoch": 0.4748683580660603, "percentage": 23.85, "elapsed_time": "1:33:46", "remaining_time": "4:59:29", "throughput": 8099.31, "total_tokens": 45573952} +{"current_steps": 63, "total_steps": 260, "loss": 0.3279, "accuracy": 0.8515625, "lr": 8.931442160683094e-06, "epoch": 0.48252752513164193, "percentage": 24.23, "elapsed_time": "1:35:17", "remaining_time": "4:57:59", "throughput": 8099.04, "total_tokens": 46307968} +{"current_steps": 64, "total_steps": 260, "loss": 0.3147, "accuracy": 0.91015625, "lr": 8.892311507835118e-06, "epoch": 0.49018669219722355, "percentage": 24.62, "elapsed_time": "1:36:48", "remaining_time": "4:56:28", "throughput": 8102.35, "total_tokens": 47061952} +{"current_steps": 65, "total_steps": 260, "loss": 0.3134, "accuracy": 0.8984375, "lr": 8.852566213878947e-06, "epoch": 0.49784585926280517, "percentage": 25.0, "elapsed_time": "1:38:22", "remaining_time": "4:55:08", "throughput": 8099.71, "total_tokens": 47810368} +{"current_steps": 66, "total_steps": 260, "loss": 0.3161, "accuracy": 0.88671875, "lr": 8.81221255505724e-06, "epoch": 0.5055050263283868, "percentage": 25.38, "elapsed_time": "1:39:51", "remaining_time": "4:53:32", "throughput": 8102.62, "total_tokens": 48549120} +{"current_steps": 67, "total_steps": 260, "loss": 0.3172, "accuracy": 0.8671875, "lr": 8.77125690368052e-06, "epoch": 0.5131641933939685, "percentage": 25.77, "elapsed_time": "1:41:28", "remaining_time": "4:52:18", "throughput": 8098.61, "total_tokens": 49307392} +{"current_steps": 68, "total_steps": 260, "loss": 0.2939, "accuracy": 0.8984375, "lr": 8.729705727120911e-06, "epoch": 0.52082336045955, "percentage": 26.15, "elapsed_time": "1:42:56", "remaining_time": "4:50:40", "throughput": 8101.16, "total_tokens": 50039616} +{"current_steps": 69, "total_steps": 260, "loss": 0.3207, "accuracy": 0.8671875, "lr": 8.68756558679087e-06, "epoch": 0.5284825275251317, "percentage": 26.54, "elapsed_time": "1:44:29", "remaining_time": "4:49:15", "throughput": 8099.03, "total_tokens": 50779200} +{"current_steps": 70, "total_steps": 260, "loss": 0.2916, "accuracy": 0.875, "lr": 8.644843137107058e-06, "epoch": 0.5361416945907133, "percentage": 26.92, "elapsed_time": "1:46:00", "remaining_time": "4:47:43", "throughput": 8101.29, "total_tokens": 51525056} +{"current_steps": 71, "total_steps": 260, "loss": 0.2892, "accuracy": 0.890625, "lr": 8.601545124439535e-06, "epoch": 0.5438008616562949, "percentage": 27.31, "elapsed_time": "1:47:26", "remaining_time": "4:46:00", "throughput": 8105.59, "total_tokens": 52252288} +{"current_steps": 72, "total_steps": 260, "loss": 0.268, "accuracy": 0.921875, "lr": 8.557678386046429e-06, "epoch": 0.5514600287218765, "percentage": 27.69, "elapsed_time": "1:48:57", "remaining_time": "4:44:31", "throughput": 8107.73, "total_tokens": 53008192} +{"current_steps": 73, "total_steps": 260, "loss": 0.2748, "accuracy": 0.90625, "lr": 8.513249848994248e-06, "epoch": 0.5591191957874582, "percentage": 28.08, "elapsed_time": "1:50:28", "remaining_time": "4:43:01", "throughput": 8108.83, "total_tokens": 53753088} +{"current_steps": 74, "total_steps": 260, "loss": 0.239, "accuracy": 0.9453125, "lr": 8.468266529064025e-06, "epoch": 0.5667783628530397, "percentage": 28.46, "elapsed_time": "1:51:54", "remaining_time": "4:41:16", "throughput": 8110.44, "total_tokens": 54456896} +{"current_steps": 75, "total_steps": 260, "loss": 0.2653, "accuracy": 0.91015625, "lr": 8.422735529643445e-06, "epoch": 0.5744375299186214, "percentage": 28.85, "elapsed_time": "1:53:23", "remaining_time": "4:39:41", "throughput": 8113.07, "total_tokens": 55195264} +{"current_steps": 76, "total_steps": 260, "loss": 0.2671, "accuracy": 0.93359375, "lr": 8.376664040605122e-06, "epoch": 0.582096696984203, "percentage": 29.23, "elapsed_time": "1:54:55", "remaining_time": "4:38:14", "throughput": 8114.22, "total_tokens": 55952960} +{"current_steps": 77, "total_steps": 260, "loss": 0.2482, "accuracy": 0.91796875, "lr": 8.33005933717126e-06, "epoch": 0.5897558640497846, "percentage": 29.62, "elapsed_time": "1:56:25", "remaining_time": "4:36:41", "throughput": 8112.41, "total_tokens": 56668800} +{"current_steps": 78, "total_steps": 260, "loss": 0.2907, "accuracy": 0.9140625, "lr": 8.282928778764783e-06, "epoch": 0.5974150311153662, "percentage": 30.0, "elapsed_time": "1:58:00", "remaining_time": "4:35:21", "throughput": 8109.42, "total_tokens": 57419840} +{"current_steps": 79, "total_steps": 260, "loss": 0.2535, "accuracy": 0.9140625, "lr": 8.235279807847223e-06, "epoch": 0.6050741981809479, "percentage": 30.38, "elapsed_time": "1:59:28", "remaining_time": "4:33:44", "throughput": 8111.23, "total_tokens": 58147840} +{"current_steps": 80, "total_steps": 260, "loss": 0.2513, "accuracy": 0.93359375, "lr": 8.18711994874345e-06, "epoch": 0.6127333652465294, "percentage": 30.77, "elapsed_time": "2:00:57", "remaining_time": "4:32:09", "throughput": 8113.51, "total_tokens": 58884608} +{"current_steps": 81, "total_steps": 260, "loss": 0.2481, "accuracy": 0.93359375, "lr": 8.138456806453503e-06, "epoch": 0.6203925323121111, "percentage": 31.15, "elapsed_time": "2:02:26", "remaining_time": "4:30:35", "throughput": 8114.61, "total_tokens": 59617664} +{"current_steps": 82, "total_steps": 260, "loss": 0.2525, "accuracy": 0.91015625, "lr": 8.089298065451673e-06, "epoch": 0.6280516993776927, "percentage": 31.54, "elapsed_time": "2:03:53", "remaining_time": "4:28:56", "throughput": 8116.93, "total_tokens": 60340288} +{"current_steps": 83, "total_steps": 260, "loss": 0.2589, "accuracy": 0.91796875, "lr": 8.039651488473028e-06, "epoch": 0.6357108664432743, "percentage": 31.92, "elapsed_time": "2:05:20", "remaining_time": "4:27:18", "throughput": 8117.48, "total_tokens": 61049920} +{"current_steps": 84, "total_steps": 260, "loss": 0.2305, "accuracy": 0.93359375, "lr": 7.989524915287595e-06, "epoch": 0.6433700335088559, "percentage": 32.31, "elapsed_time": "2:06:49", "remaining_time": "4:25:42", "throughput": 8118.78, "total_tokens": 61776064} +{"current_steps": 85, "total_steps": 260, "loss": 0.2068, "accuracy": 0.9453125, "lr": 7.938926261462366e-06, "epoch": 0.6510292005744376, "percentage": 32.69, "elapsed_time": "2:08:20", "remaining_time": "4:24:13", "throughput": 8118.34, "total_tokens": 62513664} +{"current_steps": 86, "total_steps": 260, "loss": 0.2496, "accuracy": 0.90234375, "lr": 7.887863517111337e-06, "epoch": 0.6586883676400191, "percentage": 33.08, "elapsed_time": "2:09:50", "remaining_time": "4:22:41", "throughput": 8115.56, "total_tokens": 63222720} +{"current_steps": 87, "total_steps": 260, "loss": 0.2166, "accuracy": 0.93359375, "lr": 7.836344745633785e-06, "epoch": 0.6663475347056008, "percentage": 33.46, "elapsed_time": "2:11:18", "remaining_time": "4:21:06", "throughput": 8117.39, "total_tokens": 63953344} +{"current_steps": 88, "total_steps": 260, "loss": 0.2219, "accuracy": 0.953125, "lr": 7.78437808244094e-06, "epoch": 0.6740067017711824, "percentage": 33.85, "elapsed_time": "2:12:50", "remaining_time": "4:19:38", "throughput": 8118.59, "total_tokens": 64706496} +{"current_steps": 89, "total_steps": 260, "loss": 0.2378, "accuracy": 0.92578125, "lr": 7.731971733671347e-06, "epoch": 0.681665868836764, "percentage": 34.23, "elapsed_time": "2:14:21", "remaining_time": "4:18:08", "throughput": 8119.56, "total_tokens": 65452480} +{"current_steps": 90, "total_steps": 260, "loss": 0.2418, "accuracy": 0.921875, "lr": 7.679133974894984e-06, "epoch": 0.6893250359023456, "percentage": 34.62, "elapsed_time": "2:15:49", "remaining_time": "4:16:33", "throughput": 8120.76, "total_tokens": 66179200} +{"current_steps": 91, "total_steps": 260, "loss": 0.2315, "accuracy": 0.94140625, "lr": 7.6258731498064796e-06, "epoch": 0.6969842029679273, "percentage": 35.0, "elapsed_time": "2:17:17", "remaining_time": "4:14:58", "throughput": 8121.53, "total_tokens": 66901056} +{"current_steps": 92, "total_steps": 260, "loss": 0.2134, "accuracy": 0.9375, "lr": 7.572197668907533e-06, "epoch": 0.7046433700335089, "percentage": 35.38, "elapsed_time": "2:18:47", "remaining_time": "4:13:27", "throughput": 8122.34, "total_tokens": 67641344} +{"current_steps": 93, "total_steps": 260, "loss": 0.2381, "accuracy": 0.91796875, "lr": 7.518116008178805e-06, "epoch": 0.7123025370990905, "percentage": 35.77, "elapsed_time": "2:20:18", "remaining_time": "4:11:57", "throughput": 8122.14, "total_tokens": 68377600} +{"current_steps": 94, "total_steps": 260, "loss": 0.2492, "accuracy": 0.90234375, "lr": 7.463636707741458e-06, "epoch": 0.7199617041646721, "percentage": 36.15, "elapsed_time": "2:21:50", "remaining_time": "4:10:29", "throughput": 8119.86, "total_tokens": 69105728} +{"current_steps": 95, "total_steps": 260, "loss": 0.2348, "accuracy": 0.90625, "lr": 7.408768370508577e-06, "epoch": 0.7276208712302538, "percentage": 36.54, "elapsed_time": "2:23:19", "remaining_time": "4:08:56", "throughput": 8118.85, "total_tokens": 69821376} +{"current_steps": 96, "total_steps": 260, "loss": 0.2112, "accuracy": 0.91796875, "lr": 7.353519660826665e-06, "epoch": 0.7352800382958353, "percentage": 36.92, "elapsed_time": "2:24:54", "remaining_time": "4:07:33", "throughput": 8112.01, "total_tokens": 70532608} +{"current_steps": 97, "total_steps": 260, "loss": 0.2289, "accuracy": 0.9140625, "lr": 7.297899303107441e-06, "epoch": 0.742939205361417, "percentage": 37.31, "elapsed_time": "2:26:27", "remaining_time": "4:06:05", "throughput": 8112.59, "total_tokens": 71286144} +{"current_steps": 98, "total_steps": 260, "loss": 0.1835, "accuracy": 0.95703125, "lr": 7.241916080450163e-06, "epoch": 0.7505983724269986, "percentage": 37.69, "elapsed_time": "2:27:57", "remaining_time": "4:04:34", "throughput": 8114.57, "total_tokens": 72033856} +{"current_steps": 99, "total_steps": 260, "loss": 0.2259, "accuracy": 0.921875, "lr": 7.185578833254665e-06, "epoch": 0.7582575394925802, "percentage": 38.08, "elapsed_time": "2:29:27", "remaining_time": "4:03:04", "throughput": 8116.61, "total_tokens": 72789504} +{"current_steps": 100, "total_steps": 260, "loss": 0.1958, "accuracy": 0.94140625, "lr": 7.128896457825364e-06, "epoch": 0.7659167065581618, "percentage": 38.46, "elapsed_time": "2:30:59", "remaining_time": "4:01:35", "throughput": 8115.62, "total_tokens": 73524480} +{"current_steps": 101, "total_steps": 260, "loss": 0.2036, "accuracy": 0.953125, "lr": 7.071877904966422e-06, "epoch": 0.7735758736237435, "percentage": 38.85, "elapsed_time": "2:32:32", "remaining_time": "4:00:07", "throughput": 8115.85, "total_tokens": 74277760} +{"current_steps": 102, "total_steps": 260, "loss": 0.2042, "accuracy": 0.94140625, "lr": 7.014532178568314e-06, "epoch": 0.781235040689325, "percentage": 39.23, "elapsed_time": "2:34:02", "remaining_time": "3:58:36", "throughput": 8114.93, "total_tokens": 75000768} +{"current_steps": 103, "total_steps": 260, "loss": 0.1902, "accuracy": 0.953125, "lr": 6.9568683341860135e-06, "epoch": 0.7888942077549067, "percentage": 39.62, "elapsed_time": "2:35:31", "remaining_time": "3:57:03", "throughput": 8115.36, "total_tokens": 75729152} +{"current_steps": 104, "total_steps": 260, "loss": 0.207, "accuracy": 0.9375, "lr": 6.898895477609007e-06, "epoch": 0.7965533748204883, "percentage": 40.0, "elapsed_time": "2:37:03", "remaining_time": "3:55:35", "throughput": 8116.24, "total_tokens": 76486080} +{"current_steps": 105, "total_steps": 260, "loss": 0.2188, "accuracy": 0.921875, "lr": 6.840622763423391e-06, "epoch": 0.8042125418860699, "percentage": 40.38, "elapsed_time": "2:38:33", "remaining_time": "3:54:03", "throughput": 8116.95, "total_tokens": 77220736} +{"current_steps": 106, "total_steps": 260, "loss": 0.1896, "accuracy": 0.9296875, "lr": 6.782059393566254e-06, "epoch": 0.8118717089516515, "percentage": 40.77, "elapsed_time": "2:40:05", "remaining_time": "3:52:34", "throughput": 8117.73, "total_tokens": 77972992} +{"current_steps": 107, "total_steps": 260, "loss": 0.2132, "accuracy": 0.9140625, "lr": 6.723214615872585e-06, "epoch": 0.8195308760172332, "percentage": 41.15, "elapsed_time": "2:41:35", "remaining_time": "3:51:04", "throughput": 8118.09, "total_tokens": 78712832} +{"current_steps": 108, "total_steps": 260, "loss": 0.1976, "accuracy": 0.9375, "lr": 6.664097722614934e-06, "epoch": 0.8271900430828147, "percentage": 41.54, "elapsed_time": "2:43:06", "remaining_time": "3:49:33", "throughput": 8119.08, "total_tokens": 79455552} +{"current_steps": 109, "total_steps": 260, "loss": 0.1942, "accuracy": 0.9296875, "lr": 6.604718049036047e-06, "epoch": 0.8348492101483964, "percentage": 41.92, "elapsed_time": "2:44:37", "remaining_time": "3:48:03", "throughput": 8117.75, "total_tokens": 80182272} +{"current_steps": 110, "total_steps": 260, "loss": 0.1877, "accuracy": 0.9453125, "lr": 6.545084971874738e-06, "epoch": 0.842508377213978, "percentage": 42.31, "elapsed_time": "2:46:06", "remaining_time": "3:46:31", "throughput": 8119.19, "total_tokens": 80923776} +{"current_steps": 111, "total_steps": 260, "loss": 0.1755, "accuracy": 0.9453125, "lr": 6.485207907885175e-06, "epoch": 0.8501675442795597, "percentage": 42.69, "elapsed_time": "2:47:37", "remaining_time": "3:45:00", "throughput": 8118.93, "total_tokens": 81653568} +{"current_steps": 112, "total_steps": 260, "loss": 0.1596, "accuracy": 0.97265625, "lr": 6.425096312349881e-06, "epoch": 0.8578267113451412, "percentage": 43.08, "elapsed_time": "2:49:06", "remaining_time": "3:43:28", "throughput": 8119.61, "total_tokens": 82386688} +{"current_steps": 113, "total_steps": 260, "loss": 0.1895, "accuracy": 0.93359375, "lr": 6.364759677586627e-06, "epoch": 0.8654858784107229, "percentage": 43.46, "elapsed_time": "2:50:38", "remaining_time": "3:41:59", "throughput": 8119.3, "total_tokens": 83130240} +{"current_steps": 114, "total_steps": 260, "loss": 0.1876, "accuracy": 0.94140625, "lr": 6.304207531449486e-06, "epoch": 0.8731450454763044, "percentage": 43.85, "elapsed_time": "2:52:10", "remaining_time": "3:40:30", "throughput": 8118.75, "total_tokens": 83869312} +{"current_steps": 115, "total_steps": 260, "loss": 0.159, "accuracy": 0.9375, "lr": 6.243449435824276e-06, "epoch": 0.8808042125418861, "percentage": 44.23, "elapsed_time": "2:53:39", "remaining_time": "3:38:57", "throughput": 8117.31, "total_tokens": 84575808} +{"current_steps": 116, "total_steps": 260, "loss": 0.1617, "accuracy": 0.9453125, "lr": 6.182494985118625e-06, "epoch": 0.8884633796074677, "percentage": 44.62, "elapsed_time": "2:55:13", "remaining_time": "3:37:30", "throughput": 8117.34, "total_tokens": 85338880} +{"current_steps": 117, "total_steps": 260, "loss": 0.1782, "accuracy": 0.9609375, "lr": 6.121353804746907e-06, "epoch": 0.8961225466730494, "percentage": 45.0, "elapsed_time": "2:56:42", "remaining_time": "3:35:59", "throughput": 8119.55, "total_tokens": 86090176} +{"current_steps": 118, "total_steps": 260, "loss": 0.2164, "accuracy": 0.92578125, "lr": 6.060035549610275e-06, "epoch": 0.9037817137386309, "percentage": 45.38, "elapsed_time": "2:58:13", "remaining_time": "3:34:28", "throughput": 8120.66, "total_tokens": 86839104} +{"current_steps": 119, "total_steps": 260, "loss": 0.2003, "accuracy": 0.9296875, "lr": 5.9985499025720354e-06, "epoch": 0.9114408808042126, "percentage": 45.77, "elapsed_time": "2:59:41", "remaining_time": "3:32:54", "throughput": 8123.31, "total_tokens": 87579584} +{"current_steps": 120, "total_steps": 260, "loss": 0.1615, "accuracy": 0.94140625, "lr": 5.936906572928625e-06, "epoch": 0.9191000478697942, "percentage": 46.15, "elapsed_time": "3:01:10", "remaining_time": "3:31:22", "throughput": 8123.83, "total_tokens": 88308736} +{"current_steps": 121, "total_steps": 260, "loss": 0.1908, "accuracy": 0.9296875, "lr": 5.8751152948763815e-06, "epoch": 0.9267592149353758, "percentage": 46.54, "elapsed_time": "3:02:42", "remaining_time": "3:29:52", "throughput": 8124.76, "total_tokens": 89063680} +{"current_steps": 122, "total_steps": 260, "loss": 0.138, "accuracy": 0.95703125, "lr": 5.813185825974419e-06, "epoch": 0.9344183820009574, "percentage": 46.92, "elapsed_time": "3:04:13", "remaining_time": "3:28:23", "throughput": 8123.15, "total_tokens": 89789952} +{"current_steps": 123, "total_steps": 260, "loss": 0.1382, "accuracy": 0.9609375, "lr": 5.751127945603786e-06, "epoch": 0.9420775490665391, "percentage": 47.31, "elapsed_time": "3:05:41", "remaining_time": "3:26:49", "throughput": 8121.79, "total_tokens": 90488768} +{"current_steps": 124, "total_steps": 260, "loss": 0.1456, "accuracy": 0.9609375, "lr": 5.68895145342319e-06, "epoch": 0.9497367161321206, "percentage": 47.69, "elapsed_time": "3:07:12", "remaining_time": "3:25:20", "throughput": 8122.54, "total_tokens": 91240448} +{"current_steps": 125, "total_steps": 260, "loss": 0.1962, "accuracy": 0.921875, "lr": 5.626666167821522e-06, "epoch": 0.9573958831977023, "percentage": 48.08, "elapsed_time": "3:08:46", "remaining_time": "3:23:53", "throughput": 8122.91, "total_tokens": 92008064} +{"current_steps": 126, "total_steps": 260, "loss": 0.18, "accuracy": 0.94140625, "lr": 5.5642819243674085e-06, "epoch": 0.9650550502632839, "percentage": 48.46, "elapsed_time": "3:10:17", "remaining_time": "3:22:22", "throughput": 8122.06, "total_tokens": 92734656} +{"current_steps": 1, "total_steps": 522, "loss": 0.6931, "accuracy": 0.0, "lr": 2.0000000000000003e-06, "epoch": 0.0038305003591094086, "percentage": 0.19, "elapsed_time": "0:00:51", "remaining_time": "7:31:11", "throughput": 6285.9, "total_tokens": 326624} +{"current_steps": 2, "total_steps": 522, "loss": 0.6931, "accuracy": 0.0, "lr": 4.000000000000001e-06, "epoch": 0.007661000718218817, "percentage": 0.38, "elapsed_time": "0:01:42", "remaining_time": "7:22:33", "throughput": 6355.2, "total_tokens": 649056} +{"current_steps": 3, "total_steps": 522, "loss": 0.6978, "accuracy": 0.484375, "lr": 6e-06, "epoch": 0.011491501077328227, "percentage": 0.57, "elapsed_time": "0:02:31", "remaining_time": "7:17:57", "throughput": 6444.75, "total_tokens": 978912} +{"current_steps": 4, "total_steps": 522, "loss": 0.6985, "accuracy": 0.46875, "lr": 8.000000000000001e-06, "epoch": 0.015322001436437634, "percentage": 0.77, "elapsed_time": "0:03:21", "remaining_time": "7:15:33", "throughput": 6475.34, "total_tokens": 1306720} +{"current_steps": 5, "total_steps": 522, "loss": 0.6851, "accuracy": 0.5546875, "lr": 1e-05, "epoch": 0.019152501795547044, "percentage": 0.96, "elapsed_time": "0:04:11", "remaining_time": "7:13:25", "throughput": 6503.23, "total_tokens": 1635584} +{"current_steps": 6, "total_steps": 522, "loss": 0.707, "accuracy": 0.4453125, "lr": 1.2e-05, "epoch": 0.022983002154656453, "percentage": 1.15, "elapsed_time": "0:05:00", "remaining_time": "7:10:16", "throughput": 6502.44, "total_tokens": 1952000} +{"current_steps": 7, "total_steps": 522, "loss": 0.7024, "accuracy": 0.46875, "lr": 1.4e-05, "epoch": 0.02681350251376586, "percentage": 1.34, "elapsed_time": "0:05:49", "remaining_time": "7:09:03", "throughput": 6502.07, "total_tokens": 2275136} +{"current_steps": 8, "total_steps": 522, "loss": 0.6983, "accuracy": 0.5234375, "lr": 1.6000000000000003e-05, "epoch": 0.03064400287287527, "percentage": 1.53, "elapsed_time": "0:06:40", "remaining_time": "7:08:49", "throughput": 6509.79, "total_tokens": 2606880} +{"current_steps": 9, "total_steps": 522, "loss": 0.6874, "accuracy": 0.5390625, "lr": 1.8e-05, "epoch": 0.03447450323198468, "percentage": 1.72, "elapsed_time": "0:07:31", "remaining_time": "7:08:36", "throughput": 6532.7, "total_tokens": 2947296} +{"current_steps": 10, "total_steps": 522, "loss": 0.6993, "accuracy": 0.484375, "lr": 2e-05, "epoch": 0.03830500359109409, "percentage": 1.92, "elapsed_time": "0:08:27", "remaining_time": "7:13:22", "throughput": 6471.37, "total_tokens": 3286528} +{"current_steps": 11, "total_steps": 522, "loss": 0.6849, "accuracy": 0.5546875, "lr": 1.9999811752826012e-05, "epoch": 0.0421355039502035, "percentage": 2.11, "elapsed_time": "0:09:19", "remaining_time": "7:12:58", "throughput": 6491.59, "total_tokens": 3630304} +{"current_steps": 12, "total_steps": 522, "loss": 0.6892, "accuracy": 0.5703125, "lr": 1.999924701839145e-05, "epoch": 0.045966004309312906, "percentage": 2.3, "elapsed_time": "0:10:08", "remaining_time": "7:11:11", "throughput": 6502.4, "total_tokens": 3958208} +{"current_steps": 13, "total_steps": 522, "loss": 0.6791, "accuracy": 0.59375, "lr": 1.9998305817958235e-05, "epoch": 0.049796504668422316, "percentage": 2.49, "elapsed_time": "0:10:59", "remaining_time": "7:10:25", "throughput": 6512.51, "total_tokens": 4295584} +{"current_steps": 14, "total_steps": 522, "loss": 0.6689, "accuracy": 0.59375, "lr": 1.9996988186962044e-05, "epoch": 0.05362700502753172, "percentage": 2.68, "elapsed_time": "0:11:49", "remaining_time": "7:09:07", "throughput": 6522.11, "total_tokens": 4627968} +{"current_steps": 15, "total_steps": 522, "loss": 0.6516, "accuracy": 0.6796875, "lr": 1.9995294175010934e-05, "epoch": 0.05745750538664113, "percentage": 2.87, "elapsed_time": "0:12:38", "remaining_time": "7:07:14", "throughput": 6515.79, "total_tokens": 4941696} +{"current_steps": 16, "total_steps": 522, "loss": 0.6677, "accuracy": 0.578125, "lr": 1.9993223845883496e-05, "epoch": 0.06128800574575054, "percentage": 3.07, "elapsed_time": "0:13:28", "remaining_time": "7:06:05", "throughput": 6516.62, "total_tokens": 5268000} +{"current_steps": 17, "total_steps": 522, "loss": 0.6288, "accuracy": 0.6875, "lr": 1.9990777277526458e-05, "epoch": 0.06511850610485995, "percentage": 3.26, "elapsed_time": "0:14:19", "remaining_time": "7:05:22", "throughput": 6513.06, "total_tokens": 5595904} +{"current_steps": 18, "total_steps": 522, "loss": 0.6231, "accuracy": 0.71875, "lr": 1.9987954562051724e-05, "epoch": 0.06894900646396936, "percentage": 3.45, "elapsed_time": "0:15:10", "remaining_time": "7:04:45", "throughput": 6527.6, "total_tokens": 5941312} +{"current_steps": 19, "total_steps": 522, "loss": 0.6199, "accuracy": 0.7265625, "lr": 1.9984755805732948e-05, "epoch": 0.07277950682307877, "percentage": 3.64, "elapsed_time": "0:16:00", "remaining_time": "7:03:38", "throughput": 6527.71, "total_tokens": 6267424} +{"current_steps": 20, "total_steps": 522, "loss": 0.6015, "accuracy": 0.71875, "lr": 1.998118112900149e-05, "epoch": 0.07661000718218818, "percentage": 3.83, "elapsed_time": "0:16:49", "remaining_time": "7:02:21", "throughput": 6527.62, "total_tokens": 6590368} +{"current_steps": 21, "total_steps": 522, "loss": 0.6003, "accuracy": 0.71875, "lr": 1.997723066644192e-05, "epoch": 0.08044050754129758, "percentage": 4.02, "elapsed_time": "0:17:41", "remaining_time": "7:02:07", "throughput": 6527.74, "total_tokens": 6930112} +{"current_steps": 22, "total_steps": 522, "loss": 0.5536, "accuracy": 0.8203125, "lr": 1.9972904566786903e-05, "epoch": 0.084271007900407, "percentage": 4.21, "elapsed_time": "0:19:19", "remaining_time": "7:19:10", "throughput": 6268.14, "total_tokens": 7267360} +{"current_steps": 23, "total_steps": 522, "loss": 0.5813, "accuracy": 0.796875, "lr": 1.9968202992911657e-05, "epoch": 0.0881015082595164, "percentage": 4.41, "elapsed_time": "0:20:09", "remaining_time": "7:17:22", "throughput": 6282.43, "total_tokens": 7599200} +{"current_steps": 24, "total_steps": 522, "loss": 0.5351, "accuracy": 0.765625, "lr": 1.996312612182778e-05, "epoch": 0.09193200861862581, "percentage": 4.6, "elapsed_time": "0:20:58", "remaining_time": "7:15:13", "throughput": 6299.02, "total_tokens": 7927200} +{"current_steps": 25, "total_steps": 522, "loss": 0.5131, "accuracy": 0.78125, "lr": 1.99576741446766e-05, "epoch": 0.09576250897773522, "percentage": 4.79, "elapsed_time": "0:21:48", "remaining_time": "7:13:36", "throughput": 6312.24, "total_tokens": 8260800} +{"current_steps": 26, "total_steps": 522, "loss": 0.5195, "accuracy": 0.8359375, "lr": 1.995184726672197e-05, "epoch": 0.09959300933684463, "percentage": 4.98, "elapsed_time": "0:22:39", "remaining_time": "7:12:14", "throughput": 6321.13, "total_tokens": 8593440} +{"current_steps": 27, "total_steps": 522, "loss": 0.5156, "accuracy": 0.703125, "lr": 1.9945645707342555e-05, "epoch": 0.10342350969595403, "percentage": 5.17, "elapsed_time": "0:23:28", "remaining_time": "7:10:28", "throughput": 6326.49, "total_tokens": 8913024} +{"current_steps": 28, "total_steps": 522, "loss": 0.4667, "accuracy": 0.8125, "lr": 1.9939069700023564e-05, "epoch": 0.10725401005506344, "percentage": 5.36, "elapsed_time": "0:24:17", "remaining_time": "7:08:29", "throughput": 6342.6, "total_tokens": 9242464} +{"current_steps": 29, "total_steps": 522, "loss": 0.4858, "accuracy": 0.796875, "lr": 1.9932119492347947e-05, "epoch": 0.11108451041417285, "percentage": 5.56, "elapsed_time": "0:25:06", "remaining_time": "7:06:54", "throughput": 6352.07, "total_tokens": 9570976} +{"current_steps": 30, "total_steps": 522, "loss": 0.4546, "accuracy": 0.828125, "lr": 1.9924795345987103e-05, "epoch": 0.11491501077328226, "percentage": 5.75, "elapsed_time": "0:25:58", "remaining_time": "7:05:52", "throughput": 6358.72, "total_tokens": 9907360} +{"current_steps": 31, "total_steps": 522, "loss": 0.426, "accuracy": 0.8203125, "lr": 1.9917097536690997e-05, "epoch": 0.11874551113239167, "percentage": 5.94, "elapsed_time": "0:26:48", "remaining_time": "7:04:32", "throughput": 6365.77, "total_tokens": 10237760} +{"current_steps": 32, "total_steps": 522, "loss": 0.3774, "accuracy": 0.875, "lr": 1.99090263542778e-05, "epoch": 0.12257601149150107, "percentage": 6.13, "elapsed_time": "0:27:36", "remaining_time": "7:02:43", "throughput": 6371.19, "total_tokens": 10553152} +{"current_steps": 33, "total_steps": 522, "loss": 0.4336, "accuracy": 0.796875, "lr": 1.9900582102622973e-05, "epoch": 0.1264065118506105, "percentage": 6.32, "elapsed_time": "0:28:26", "remaining_time": "7:01:30", "throughput": 6378.55, "total_tokens": 10886464} +{"current_steps": 34, "total_steps": 522, "loss": 0.4272, "accuracy": 0.8203125, "lr": 1.989176509964781e-05, "epoch": 0.1302370122097199, "percentage": 6.51, "elapsed_time": "0:29:17", "remaining_time": "7:00:24", "throughput": 6386.04, "total_tokens": 11222976} +{"current_steps": 35, "total_steps": 522, "loss": 0.3327, "accuracy": 0.8828125, "lr": 1.9882575677307497e-05, "epoch": 0.13406751256882932, "percentage": 6.7, "elapsed_time": "0:30:10", "remaining_time": "6:59:48", "throughput": 6385.26, "total_tokens": 11558912} +{"current_steps": 36, "total_steps": 522, "loss": 0.3958, "accuracy": 0.8515625, "lr": 1.9873014181578588e-05, "epoch": 0.1378980129279387, "percentage": 6.9, "elapsed_time": "0:30:59", "remaining_time": "6:58:27", "throughput": 6385.46, "total_tokens": 11875648} +{"current_steps": 37, "total_steps": 522, "loss": 0.37, "accuracy": 0.84375, "lr": 1.986308097244599e-05, "epoch": 0.1417285132870481, "percentage": 7.09, "elapsed_time": "0:31:48", "remaining_time": "6:56:55", "throughput": 6390.43, "total_tokens": 12195392} +{"current_steps": 38, "total_steps": 522, "loss": 0.3656, "accuracy": 0.8515625, "lr": 1.9852776423889414e-05, "epoch": 0.14555901364615753, "percentage": 7.28, "elapsed_time": "0:32:40", "remaining_time": "6:56:10", "throughput": 6393.71, "total_tokens": 12534752} +{"current_steps": 39, "total_steps": 522, "loss": 0.3673, "accuracy": 0.8515625, "lr": 1.9842100923869292e-05, "epoch": 0.14938951400526693, "percentage": 7.47, "elapsed_time": "0:33:29", "remaining_time": "6:54:46", "throughput": 6398.35, "total_tokens": 12857440} +{"current_steps": 40, "total_steps": 522, "loss": 0.3274, "accuracy": 0.875, "lr": 1.9831054874312167e-05, "epoch": 0.15322001436437635, "percentage": 7.66, "elapsed_time": "0:34:18", "remaining_time": "6:53:19", "throughput": 6403.14, "total_tokens": 13178048} +{"current_steps": 41, "total_steps": 522, "loss": 0.3362, "accuracy": 0.875, "lr": 1.9819638691095554e-05, "epoch": 0.15705051472348575, "percentage": 7.85, "elapsed_time": "0:35:08", "remaining_time": "6:52:12", "throughput": 6409.36, "total_tokens": 13512032} +{"current_steps": 42, "total_steps": 522, "loss": 0.3002, "accuracy": 0.8671875, "lr": 1.9807852804032306e-05, "epoch": 0.16088101508259517, "percentage": 8.05, "elapsed_time": "0:35:58", "remaining_time": "6:51:05", "throughput": 6416.64, "total_tokens": 13848640} +{"current_steps": 43, "total_steps": 522, "loss": 0.2887, "accuracy": 0.9140625, "lr": 1.9795697656854406e-05, "epoch": 0.16471151544170456, "percentage": 8.24, "elapsed_time": "0:36:46", "remaining_time": "6:49:40", "throughput": 6426.55, "total_tokens": 14180832} +{"current_steps": 44, "total_steps": 522, "loss": 0.2722, "accuracy": 0.8828125, "lr": 1.9783173707196278e-05, "epoch": 0.168542015800814, "percentage": 8.43, "elapsed_time": "0:37:35", "remaining_time": "6:48:23", "throughput": 6429.98, "total_tokens": 14502976} +{"current_steps": 45, "total_steps": 522, "loss": 0.2772, "accuracy": 0.90625, "lr": 1.9770281426577543e-05, "epoch": 0.17237251615992338, "percentage": 8.62, "elapsed_time": "0:38:24", "remaining_time": "6:47:06", "throughput": 6434.41, "total_tokens": 14827616} +{"current_steps": 46, "total_steps": 522, "loss": 0.2868, "accuracy": 0.8984375, "lr": 1.9757021300385288e-05, "epoch": 0.1762030165190328, "percentage": 8.81, "elapsed_time": "0:39:15", "remaining_time": "6:46:14", "throughput": 6438.42, "total_tokens": 15165888} +{"current_steps": 47, "total_steps": 522, "loss": 0.2618, "accuracy": 0.90625, "lr": 1.9743393827855758e-05, "epoch": 0.1800335168781422, "percentage": 9.0, "elapsed_time": "0:40:06", "remaining_time": "6:45:25", "throughput": 6440.57, "total_tokens": 15501984} +{"current_steps": 48, "total_steps": 522, "loss": 0.2642, "accuracy": 0.90625, "lr": 1.9729399522055603e-05, "epoch": 0.18386401723725163, "percentage": 9.2, "elapsed_time": "0:40:55", "remaining_time": "6:44:08", "throughput": 6443.71, "total_tokens": 15822752} +{"current_steps": 49, "total_steps": 522, "loss": 0.2754, "accuracy": 0.8828125, "lr": 1.9715038909862518e-05, "epoch": 0.18769451759636102, "percentage": 9.39, "elapsed_time": "0:41:44", "remaining_time": "6:42:58", "throughput": 6447.03, "total_tokens": 16148160} +{"current_steps": 50, "total_steps": 522, "loss": 0.2395, "accuracy": 0.9375, "lr": 1.9700312531945444e-05, "epoch": 0.19152501795547044, "percentage": 9.58, "elapsed_time": "0:42:34", "remaining_time": "6:41:58", "throughput": 6450.22, "total_tokens": 16479744} +{"current_steps": 51, "total_steps": 522, "loss": 0.2197, "accuracy": 0.9140625, "lr": 1.9685220942744174e-05, "epoch": 0.19535551831457984, "percentage": 9.77, "elapsed_time": "0:43:24", "remaining_time": "6:40:53", "throughput": 6454.83, "total_tokens": 16811456} +{"current_steps": 52, "total_steps": 522, "loss": 0.2882, "accuracy": 0.8671875, "lr": 1.9669764710448523e-05, "epoch": 0.19918601867368926, "percentage": 9.96, "elapsed_time": "0:44:13", "remaining_time": "6:39:44", "throughput": 6459.19, "total_tokens": 17140448} +{"current_steps": 53, "total_steps": 522, "loss": 0.2202, "accuracy": 0.9453125, "lr": 1.9653944416976897e-05, "epoch": 0.20301651903279866, "percentage": 10.15, "elapsed_time": "0:45:02", "remaining_time": "6:38:37", "throughput": 6461.73, "total_tokens": 17465248} +{"current_steps": 54, "total_steps": 522, "loss": 0.2347, "accuracy": 0.921875, "lr": 1.96377606579544e-05, "epoch": 0.20684701939190805, "percentage": 10.34, "elapsed_time": "0:45:52", "remaining_time": "6:37:31", "throughput": 6466.61, "total_tokens": 17796480} +{"current_steps": 55, "total_steps": 522, "loss": 0.2424, "accuracy": 0.8984375, "lr": 1.9621214042690416e-05, "epoch": 0.21067751975101748, "percentage": 10.54, "elapsed_time": "0:46:51", "remaining_time": "6:37:48", "throughput": 6451.98, "total_tokens": 18136896} +{"current_steps": 56, "total_steps": 522, "loss": 0.1977, "accuracy": 0.9296875, "lr": 1.960430519415566e-05, "epoch": 0.21450802011012687, "percentage": 10.73, "elapsed_time": "0:47:41", "remaining_time": "6:36:47", "throughput": 6453.22, "total_tokens": 18462848} +{"current_steps": 57, "total_steps": 522, "loss": 0.1834, "accuracy": 0.9296875, "lr": 1.9587034748958716e-05, "epoch": 0.2183385204692363, "percentage": 10.92, "elapsed_time": "0:48:31", "remaining_time": "6:35:49", "throughput": 6457.18, "total_tokens": 18798400} +{"current_steps": 58, "total_steps": 522, "loss": 0.195, "accuracy": 0.921875, "lr": 1.956940335732209e-05, "epoch": 0.2221690208283457, "percentage": 11.11, "elapsed_time": "0:49:19", "remaining_time": "6:34:38", "throughput": 6457.23, "total_tokens": 19112352} +{"current_steps": 59, "total_steps": 522, "loss": 0.1753, "accuracy": 0.9609375, "lr": 1.955141168305771e-05, "epoch": 0.22599952118745512, "percentage": 11.3, "elapsed_time": "0:50:10", "remaining_time": "6:33:43", "throughput": 6460.06, "total_tokens": 19446560} +{"current_steps": 60, "total_steps": 522, "loss": 0.2073, "accuracy": 0.921875, "lr": 1.9533060403541937e-05, "epoch": 0.2298300215465645, "percentage": 11.49, "elapsed_time": "0:51:00", "remaining_time": "6:32:42", "throughput": 6462.86, "total_tokens": 19776960} +{"current_steps": 61, "total_steps": 522, "loss": 0.2021, "accuracy": 0.953125, "lr": 1.9514350209690085e-05, "epoch": 0.23366052190567393, "percentage": 11.69, "elapsed_time": "0:51:47", "remaining_time": "6:31:26", "throughput": 6463.88, "total_tokens": 20088064} +{"current_steps": 62, "total_steps": 522, "loss": 0.1944, "accuracy": 0.9609375, "lr": 1.949528180593037e-05, "epoch": 0.23749102226478333, "percentage": 11.88, "elapsed_time": "0:52:35", "remaining_time": "6:30:12", "throughput": 6468.34, "total_tokens": 20411904} +{"current_steps": 63, "total_steps": 522, "loss": 0.2268, "accuracy": 0.875, "lr": 1.947585591017741e-05, "epoch": 0.24132152262389275, "percentage": 12.07, "elapsed_time": "0:53:24", "remaining_time": "6:29:08", "throughput": 6471.36, "total_tokens": 20738656} +{"current_steps": 64, "total_steps": 522, "loss": 0.2464, "accuracy": 0.890625, "lr": 1.9456073253805214e-05, "epoch": 0.24515202298300215, "percentage": 12.26, "elapsed_time": "0:54:14", "remaining_time": "6:28:13", "throughput": 6471.41, "total_tokens": 21064192} +{"current_steps": 65, "total_steps": 522, "loss": 0.1719, "accuracy": 0.9375, "lr": 1.9435934581619606e-05, "epoch": 0.24898252334211157, "percentage": 12.45, "elapsed_time": "0:55:04", "remaining_time": "6:27:15", "throughput": 6473.39, "total_tokens": 21393024} +{"current_steps": 66, "total_steps": 522, "loss": 0.1916, "accuracy": 0.9140625, "lr": 1.941544065183021e-05, "epoch": 0.252813023701221, "percentage": 12.64, "elapsed_time": "0:55:54", "remaining_time": "6:26:16", "throughput": 6476.7, "total_tokens": 21726112} +{"current_steps": 67, "total_steps": 522, "loss": 0.219, "accuracy": 0.9140625, "lr": 1.93945922360219e-05, "epoch": 0.25664352406033036, "percentage": 12.84, "elapsed_time": "0:56:43", "remaining_time": "6:25:14", "throughput": 6479.82, "total_tokens": 22054816} +{"current_steps": 68, "total_steps": 522, "loss": 0.1784, "accuracy": 0.9453125, "lr": 1.937339011912575e-05, "epoch": 0.2604740244194398, "percentage": 13.03, "elapsed_time": "0:57:34", "remaining_time": "6:24:21", "throughput": 6480.85, "total_tokens": 22385920} +{"current_steps": 69, "total_steps": 522, "loss": 0.1549, "accuracy": 0.9609375, "lr": 1.9351835099389476e-05, "epoch": 0.2643045247785492, "percentage": 13.22, "elapsed_time": "0:58:25", "remaining_time": "6:23:34", "throughput": 6480.88, "total_tokens": 22719104} +{"current_steps": 70, "total_steps": 522, "loss": 0.142, "accuracy": 0.9609375, "lr": 1.932992798834739e-05, "epoch": 0.26813502513765863, "percentage": 13.41, "elapsed_time": "0:59:26", "remaining_time": "6:23:52", "throughput": 6461.57, "total_tokens": 23048352} +{"current_steps": 71, "total_steps": 522, "loss": 0.1519, "accuracy": 0.953125, "lr": 1.9307669610789837e-05, "epoch": 0.271965525496768, "percentage": 13.6, "elapsed_time": "1:00:16", "remaining_time": "6:22:50", "throughput": 6462.74, "total_tokens": 23370880} +{"current_steps": 72, "total_steps": 522, "loss": 0.176, "accuracy": 0.953125, "lr": 1.928506080473216e-05, "epoch": 0.2757960258558774, "percentage": 13.79, "elapsed_time": "1:01:06", "remaining_time": "6:21:55", "throughput": 6465.07, "total_tokens": 23703872} +{"current_steps": 73, "total_steps": 522, "loss": 0.1715, "accuracy": 0.9453125, "lr": 1.9262102421383115e-05, "epoch": 0.27962652621498685, "percentage": 13.98, "elapsed_time": "1:01:54", "remaining_time": "6:20:49", "throughput": 6466.65, "total_tokens": 24023104} +{"current_steps": 74, "total_steps": 522, "loss": 0.1737, "accuracy": 0.9453125, "lr": 1.9238795325112867e-05, "epoch": 0.2834570265740962, "percentage": 14.18, "elapsed_time": "1:02:46", "remaining_time": "6:20:00", "throughput": 6465.35, "total_tokens": 24348992} +{"current_steps": 75, "total_steps": 522, "loss": 0.1499, "accuracy": 0.9765625, "lr": 1.9215140393420422e-05, "epoch": 0.28728752693320564, "percentage": 14.37, "elapsed_time": "1:03:35", "remaining_time": "6:19:01", "throughput": 6468.58, "total_tokens": 24682176} +{"current_steps": 76, "total_steps": 522, "loss": 0.173, "accuracy": 0.9375, "lr": 1.919113851690058e-05, "epoch": 0.29111802729231506, "percentage": 14.56, "elapsed_time": "1:04:27", "remaining_time": "6:18:14", "throughput": 6469.07, "total_tokens": 25017216} +{"current_steps": 77, "total_steps": 522, "loss": 0.1708, "accuracy": 0.953125, "lr": 1.9166790599210426e-05, "epoch": 0.2949485276514245, "percentage": 14.75, "elapsed_time": "1:05:17", "remaining_time": "6:17:17", "throughput": 6471.82, "total_tokens": 25350144} +{"current_steps": 78, "total_steps": 522, "loss": 0.1405, "accuracy": 0.953125, "lr": 1.914209755703531e-05, "epoch": 0.29877902801053385, "percentage": 14.94, "elapsed_time": "1:06:06", "remaining_time": "6:16:17", "throughput": 6474.86, "total_tokens": 25680960} +{"current_steps": 79, "total_steps": 522, "loss": 0.1933, "accuracy": 0.9296875, "lr": 1.91170603200543e-05, "epoch": 0.3026095283696433, "percentage": 15.13, "elapsed_time": "1:06:55", "remaining_time": "6:15:18", "throughput": 6479.25, "total_tokens": 26018816} +{"current_steps": 80, "total_steps": 522, "loss": 0.1648, "accuracy": 0.9375, "lr": 1.9091679830905225e-05, "epoch": 0.3064400287287527, "percentage": 15.33, "elapsed_time": "1:07:47", "remaining_time": "6:14:33", "throughput": 6481.18, "total_tokens": 26362592} +{"current_steps": 81, "total_steps": 522, "loss": 0.1574, "accuracy": 0.9453125, "lr": 1.9065957045149156e-05, "epoch": 0.3102705290878621, "percentage": 15.52, "elapsed_time": "1:08:36", "remaining_time": "6:13:33", "throughput": 6484.51, "total_tokens": 26694880} +{"current_steps": 82, "total_steps": 522, "loss": 0.1452, "accuracy": 0.9375, "lr": 1.9039892931234434e-05, "epoch": 0.3141010294469715, "percentage": 15.71, "elapsed_time": "1:09:25", "remaining_time": "6:12:31", "throughput": 6486.91, "total_tokens": 27020832} +{"current_steps": 83, "total_steps": 522, "loss": 0.1498, "accuracy": 0.9375, "lr": 1.9013488470460223e-05, "epoch": 0.3179315298060809, "percentage": 15.9, "elapsed_time": "1:10:13", "remaining_time": "6:11:26", "throughput": 6488.31, "total_tokens": 27338752} +{"current_steps": 84, "total_steps": 522, "loss": 0.1532, "accuracy": 0.9296875, "lr": 1.898674465693954e-05, "epoch": 0.32176203016519034, "percentage": 16.09, "elapsed_time": "1:11:04", "remaining_time": "6:10:33", "throughput": 6491.76, "total_tokens": 27681088} +{"current_steps": 85, "total_steps": 522, "loss": 0.134, "accuracy": 0.9375, "lr": 1.895966249756185e-05, "epoch": 0.32559253052429976, "percentage": 16.28, "elapsed_time": "1:11:53", "remaining_time": "6:09:35", "throughput": 6494.2, "total_tokens": 28011136} +{"current_steps": 86, "total_steps": 522, "loss": 0.1787, "accuracy": 0.921875, "lr": 1.8932243011955154e-05, "epoch": 0.32942303088340913, "percentage": 16.48, "elapsed_time": "1:12:42", "remaining_time": "6:08:38", "throughput": 6496.42, "total_tokens": 28343296} +{"current_steps": 87, "total_steps": 522, "loss": 0.1563, "accuracy": 0.9453125, "lr": 1.8904487232447582e-05, "epoch": 0.33325353124251855, "percentage": 16.67, "elapsed_time": "1:13:31", "remaining_time": "6:07:38", "throughput": 6497.93, "total_tokens": 28667424} +{"current_steps": 88, "total_steps": 522, "loss": 0.1347, "accuracy": 0.9375, "lr": 1.8876396204028543e-05, "epoch": 0.337084031601628, "percentage": 16.86, "elapsed_time": "1:14:22", "remaining_time": "6:06:45", "throughput": 6499.22, "total_tokens": 28999776} +{"current_steps": 89, "total_steps": 522, "loss": 0.1542, "accuracy": 0.96875, "lr": 1.884797098430938e-05, "epoch": 0.34091453196073734, "percentage": 17.05, "elapsed_time": "1:15:11", "remaining_time": "6:05:49", "throughput": 6501.42, "total_tokens": 29331456} +{"current_steps": 90, "total_steps": 522, "loss": 0.0792, "accuracy": 0.9921875, "lr": 1.881921264348355e-05, "epoch": 0.34474503231984677, "percentage": 17.24, "elapsed_time": "1:16:02", "remaining_time": "6:04:57", "throughput": 6502.56, "total_tokens": 29664768} +{"current_steps": 91, "total_steps": 522, "loss": 0.1184, "accuracy": 0.96875, "lr": 1.8790122264286336e-05, "epoch": 0.3485755326789562, "percentage": 17.43, "elapsed_time": "1:16:54", "remaining_time": "6:04:14", "throughput": 6504.11, "total_tokens": 30011712} +{"current_steps": 92, "total_steps": 522, "loss": 0.1729, "accuracy": 0.9296875, "lr": 1.8760700941954066e-05, "epoch": 0.3524060330380656, "percentage": 17.62, "elapsed_time": "1:17:44", "remaining_time": "6:03:19", "throughput": 6505.75, "total_tokens": 30343968} +{"current_steps": 93, "total_steps": 522, "loss": 0.1441, "accuracy": 0.9453125, "lr": 1.87309497841829e-05, "epoch": 0.356236533397175, "percentage": 17.82, "elapsed_time": "1:18:34", "remaining_time": "6:02:25", "throughput": 6506.17, "total_tokens": 30670528} +{"current_steps": 94, "total_steps": 522, "loss": 0.1032, "accuracy": 0.9765625, "lr": 1.8700869911087115e-05, "epoch": 0.3600670337562844, "percentage": 18.01, "elapsed_time": "1:19:23", "remaining_time": "6:01:30", "throughput": 6507.97, "total_tokens": 31003104} +{"current_steps": 95, "total_steps": 522, "loss": 0.1198, "accuracy": 0.9609375, "lr": 1.8670462455156928e-05, "epoch": 0.36389753411539383, "percentage": 18.2, "elapsed_time": "1:20:13", "remaining_time": "6:00:37", "throughput": 6509.52, "total_tokens": 31336576} +{"current_steps": 96, "total_steps": 522, "loss": 0.0899, "accuracy": 0.9765625, "lr": 1.863972856121587e-05, "epoch": 0.36772803447450325, "percentage": 18.39, "elapsed_time": "1:21:04", "remaining_time": "5:59:44", "throughput": 6509.58, "total_tokens": 31663232} +{"current_steps": 97, "total_steps": 522, "loss": 0.0887, "accuracy": 0.984375, "lr": 1.8608669386377672e-05, "epoch": 0.3715585348336126, "percentage": 18.58, "elapsed_time": "1:21:53", "remaining_time": "5:58:49", "throughput": 6510.77, "total_tokens": 31992480} +{"current_steps": 98, "total_steps": 522, "loss": 0.1658, "accuracy": 0.9296875, "lr": 1.8577286100002723e-05, "epoch": 0.37538903519272204, "percentage": 18.77, "elapsed_time": "1:22:44", "remaining_time": "5:58:00", "throughput": 6513.16, "total_tokens": 32336256} +{"current_steps": 99, "total_steps": 522, "loss": 0.1089, "accuracy": 0.96875, "lr": 1.8545579883654007e-05, "epoch": 0.37921953555183147, "percentage": 18.97, "elapsed_time": "1:23:34", "remaining_time": "5:57:04", "throughput": 6514.99, "total_tokens": 32667232} +{"current_steps": 100, "total_steps": 522, "loss": 0.0963, "accuracy": 0.9765625, "lr": 1.8513551931052654e-05, "epoch": 0.3830500359109409, "percentage": 19.16, "elapsed_time": "1:24:24", "remaining_time": "5:56:11", "throughput": 6515.72, "total_tokens": 32998496} +{"current_steps": 101, "total_steps": 522, "loss": 0.1315, "accuracy": 0.9609375, "lr": 1.8481203448032975e-05, "epoch": 0.38688053627005026, "percentage": 19.35, "elapsed_time": "1:25:14", "remaining_time": "5:55:19", "throughput": 6515.65, "total_tokens": 33325216} +{"current_steps": 102, "total_steps": 522, "loss": 0.1281, "accuracy": 0.9765625, "lr": 1.8448535652497073e-05, "epoch": 0.3907110366291597, "percentage": 19.54, "elapsed_time": "1:26:03", "remaining_time": "5:54:21", "throughput": 6516.42, "total_tokens": 33648256} +{"current_steps": 103, "total_steps": 522, "loss": 0.1247, "accuracy": 0.953125, "lr": 1.8415549774368987e-05, "epoch": 0.3945415369882691, "percentage": 19.73, "elapsed_time": "1:26:52", "remaining_time": "5:53:23", "throughput": 6517.78, "total_tokens": 33972000} +{"current_steps": 104, "total_steps": 522, "loss": 0.1733, "accuracy": 0.90625, "lr": 1.838224705554838e-05, "epoch": 0.3983720373473785, "percentage": 19.92, "elapsed_time": "1:27:40", "remaining_time": "5:52:24", "throughput": 6519.14, "total_tokens": 34296864} +{"current_steps": 105, "total_steps": 522, "loss": 0.0805, "accuracy": 0.9765625, "lr": 1.83486287498638e-05, "epoch": 0.4022025377064879, "percentage": 20.11, "elapsed_time": "1:28:31", "remaining_time": "5:51:32", "throughput": 6519.82, "total_tokens": 34627136} +{"current_steps": 106, "total_steps": 522, "loss": 0.1143, "accuracy": 0.96875, "lr": 1.8314696123025456e-05, "epoch": 0.4060330380655973, "percentage": 20.31, "elapsed_time": "1:29:21", "remaining_time": "5:50:42", "throughput": 6521.13, "total_tokens": 34964704} +{"current_steps": 107, "total_steps": 522, "loss": 0.1297, "accuracy": 0.9453125, "lr": 1.828045045257756e-05, "epoch": 0.40986353842470674, "percentage": 20.5, "elapsed_time": "1:30:11", "remaining_time": "5:49:47", "throughput": 6523.89, "total_tokens": 35302112} +{"current_steps": 108, "total_steps": 522, "loss": 0.0726, "accuracy": 0.984375, "lr": 1.8245893027850255e-05, "epoch": 0.4136940387838161, "percentage": 20.69, "elapsed_time": "1:31:01", "remaining_time": "5:48:55", "throughput": 6523.75, "total_tokens": 35628288} +{"current_steps": 109, "total_steps": 522, "loss": 0.0803, "accuracy": 0.984375, "lr": 1.821102514991105e-05, "epoch": 0.41752453914292553, "percentage": 20.88, "elapsed_time": "1:31:49", "remaining_time": "5:47:56", "throughput": 6524.87, "total_tokens": 35950016} +{"current_steps": 110, "total_steps": 522, "loss": 0.156, "accuracy": 0.9453125, "lr": 1.817584813151584e-05, "epoch": 0.42135503950203496, "percentage": 21.07, "elapsed_time": "1:32:39", "remaining_time": "5:47:03", "throughput": 6524.79, "total_tokens": 36275488} +{"current_steps": 111, "total_steps": 522, "loss": 0.1377, "accuracy": 0.9609375, "lr": 1.8140363297059488e-05, "epoch": 0.4251855398611444, "percentage": 21.26, "elapsed_time": "1:33:29", "remaining_time": "5:46:09", "throughput": 6526.15, "total_tokens": 36606944} +{"current_steps": 112, "total_steps": 522, "loss": 0.1222, "accuracy": 0.9375, "lr": 1.810457198252595e-05, "epoch": 0.42901604022025375, "percentage": 21.46, "elapsed_time": "1:34:19", "remaining_time": "5:45:17", "throughput": 6527.22, "total_tokens": 36940928} +{"current_steps": 113, "total_steps": 522, "loss": 0.1344, "accuracy": 0.9609375, "lr": 1.8068475535437996e-05, "epoch": 0.43284654057936317, "percentage": 21.65, "elapsed_time": "1:35:08", "remaining_time": "5:44:21", "throughput": 6527.55, "total_tokens": 37261536} +{"current_steps": 114, "total_steps": 522, "loss": 0.0928, "accuracy": 0.984375, "lr": 1.803207531480645e-05, "epoch": 0.4366770409384726, "percentage": 21.84, "elapsed_time": "1:35:57", "remaining_time": "5:43:24", "throughput": 6529.06, "total_tokens": 37588096} +{"current_steps": 115, "total_steps": 522, "loss": 0.1464, "accuracy": 0.9140625, "lr": 1.799537269107905e-05, "epoch": 0.440507541297582, "percentage": 22.03, "elapsed_time": "1:36:45", "remaining_time": "5:42:28", "throughput": 6530.49, "total_tokens": 37916032} +{"current_steps": 116, "total_steps": 522, "loss": 0.1229, "accuracy": 0.9609375, "lr": 1.7958369046088837e-05, "epoch": 0.4443380416566914, "percentage": 22.22, "elapsed_time": "1:37:33", "remaining_time": "5:41:27", "throughput": 6529.63, "total_tokens": 38222208} +{"current_steps": 117, "total_steps": 522, "loss": 0.1136, "accuracy": 0.9609375, "lr": 1.7921065773002127e-05, "epoch": 0.4481685420158008, "percentage": 22.41, "elapsed_time": "1:38:24", "remaining_time": "5:40:38", "throughput": 6530.47, "total_tokens": 38559712} +{"current_steps": 118, "total_steps": 522, "loss": 0.1193, "accuracy": 0.9609375, "lr": 1.7883464276266064e-05, "epoch": 0.45199904237491023, "percentage": 22.61, "elapsed_time": "1:39:14", "remaining_time": "5:39:47", "throughput": 6529.87, "total_tokens": 38883200} +{"current_steps": 119, "total_steps": 522, "loss": 0.0865, "accuracy": 0.9609375, "lr": 1.7845565971555754e-05, "epoch": 0.45582954273401965, "percentage": 22.8, "elapsed_time": "1:40:03", "remaining_time": "5:38:51", "throughput": 6530.82, "total_tokens": 39209280} +{"current_steps": 120, "total_steps": 522, "loss": 0.1415, "accuracy": 0.953125, "lr": 1.7807372285720945e-05, "epoch": 0.459660043093129, "percentage": 22.99, "elapsed_time": "1:40:52", "remaining_time": "5:37:56", "throughput": 6531.61, "total_tokens": 39533312} +{"current_steps": 121, "total_steps": 522, "loss": 0.124, "accuracy": 0.9453125, "lr": 1.7768884656732327e-05, "epoch": 0.46349054345223845, "percentage": 23.18, "elapsed_time": "1:41:42", "remaining_time": "5:37:03", "throughput": 6533.09, "total_tokens": 39867488} +{"current_steps": 122, "total_steps": 522, "loss": 0.0743, "accuracy": 0.9765625, "lr": 1.773010453362737e-05, "epoch": 0.46732104381134787, "percentage": 23.37, "elapsed_time": "1:42:31", "remaining_time": "5:36:09", "throughput": 6533.11, "total_tokens": 40189824} +{"current_steps": 123, "total_steps": 522, "loss": 0.0918, "accuracy": 0.9765625, "lr": 1.7691033376455798e-05, "epoch": 0.4711515441704573, "percentage": 23.56, "elapsed_time": "1:43:20", "remaining_time": "5:35:13", "throughput": 6534.86, "total_tokens": 40518368} +{"current_steps": 124, "total_steps": 522, "loss": 0.085, "accuracy": 0.9765625, "lr": 1.7651672656224592e-05, "epoch": 0.47498204452956666, "percentage": 23.75, "elapsed_time": "1:44:10", "remaining_time": "5:34:23", "throughput": 6537.89, "total_tokens": 40867360} +{"current_steps": 125, "total_steps": 522, "loss": 0.114, "accuracy": 0.953125, "lr": 1.7612023854842618e-05, "epoch": 0.4788125448886761, "percentage": 23.95, "elapsed_time": "1:45:01", "remaining_time": "5:33:32", "throughput": 6538.53, "total_tokens": 41200768} +{"current_steps": 126, "total_steps": 522, "loss": 0.1044, "accuracy": 0.953125, "lr": 1.7572088465064847e-05, "epoch": 0.4826430452477855, "percentage": 24.14, "elapsed_time": "1:45:50", "remaining_time": "5:32:37", "throughput": 6538.83, "total_tokens": 41521728} +{"current_steps": 127, "total_steps": 522, "loss": 0.0513, "accuracy": 1.0, "lr": 1.7531867990436127e-05, "epoch": 0.4864735456068949, "percentage": 24.33, "elapsed_time": "1:46:39", "remaining_time": "5:31:43", "throughput": 6539.31, "total_tokens": 41848032} +{"current_steps": 128, "total_steps": 522, "loss": 0.0888, "accuracy": 0.96875, "lr": 1.7491363945234595e-05, "epoch": 0.4903040459660043, "percentage": 24.52, "elapsed_time": "1:47:29", "remaining_time": "5:30:53", "throughput": 6540.3, "total_tokens": 42184928} +{"current_steps": 129, "total_steps": 522, "loss": 0.0969, "accuracy": 0.96875, "lr": 1.7450577854414662e-05, "epoch": 0.4941345463251137, "percentage": 24.71, "elapsed_time": "1:48:20", "remaining_time": "5:30:04", "throughput": 6540.15, "total_tokens": 42516544} +{"current_steps": 130, "total_steps": 522, "loss": 0.0965, "accuracy": 0.984375, "lr": 1.7409511253549592e-05, "epoch": 0.49796504668422314, "percentage": 24.9, "elapsed_time": "1:49:12", "remaining_time": "5:29:17", "throughput": 6539.91, "total_tokens": 42851168} +{"current_steps": 131, "total_steps": 522, "loss": 0.1093, "accuracy": 0.96875, "lr": 1.73681656887737e-05, "epoch": 0.5017955470433325, "percentage": 25.1, "elapsed_time": "1:50:00", "remaining_time": "5:28:20", "throughput": 6541.31, "total_tokens": 43175584} +{"current_steps": 132, "total_steps": 522, "loss": 0.0904, "accuracy": 0.96875, "lr": 1.7326542716724127e-05, "epoch": 0.505626047402442, "percentage": 25.29, "elapsed_time": "1:50:51", "remaining_time": "5:27:31", "throughput": 6542.58, "total_tokens": 43515872} +{"current_steps": 133, "total_steps": 522, "loss": 0.0952, "accuracy": 0.9609375, "lr": 1.7284643904482254e-05, "epoch": 0.5094565477615514, "percentage": 25.48, "elapsed_time": "1:51:42", "remaining_time": "5:26:44", "throughput": 6542.75, "total_tokens": 43854976} +{"current_steps": 134, "total_steps": 522, "loss": 0.1383, "accuracy": 0.9296875, "lr": 1.7242470829514674e-05, "epoch": 0.5132870481206607, "percentage": 25.67, "elapsed_time": "1:52:33", "remaining_time": "5:25:54", "throughput": 6544.29, "total_tokens": 44195136} +{"current_steps": 135, "total_steps": 522, "loss": 0.1074, "accuracy": 0.953125, "lr": 1.720002507961382e-05, "epoch": 0.5171175484797702, "percentage": 25.86, "elapsed_time": "1:53:22", "remaining_time": "5:24:59", "throughput": 6545.76, "total_tokens": 44525856} +{"current_steps": 136, "total_steps": 522, "loss": 0.0834, "accuracy": 0.9609375, "lr": 1.7157308252838187e-05, "epoch": 0.5209480488388796, "percentage": 26.05, "elapsed_time": "1:54:10", "remaining_time": "5:24:02", "throughput": 6546.07, "total_tokens": 44842336} +{"current_steps": 137, "total_steps": 522, "loss": 0.0874, "accuracy": 0.9765625, "lr": 1.7114321957452166e-05, "epoch": 0.5247785491979889, "percentage": 26.25, "elapsed_time": "1:55:00", "remaining_time": "5:23:13", "throughput": 6547.38, "total_tokens": 45183360} +{"current_steps": 138, "total_steps": 522, "loss": 0.0913, "accuracy": 0.984375, "lr": 1.7071067811865477e-05, "epoch": 0.5286090495570984, "percentage": 26.44, "elapsed_time": "1:55:50", "remaining_time": "5:22:20", "throughput": 6547.75, "total_tokens": 45511040} +{"current_steps": 139, "total_steps": 522, "loss": 0.0683, "accuracy": 0.9921875, "lr": 1.7027547444572254e-05, "epoch": 0.5324395499162078, "percentage": 26.63, "elapsed_time": "1:56:39", "remaining_time": "5:21:27", "throughput": 6549.18, "total_tokens": 45842656} +{"current_steps": 140, "total_steps": 522, "loss": 0.1107, "accuracy": 0.9609375, "lr": 1.6983762494089732e-05, "epoch": 0.5362700502753173, "percentage": 26.82, "elapsed_time": "1:57:30", "remaining_time": "5:20:36", "throughput": 6550.01, "total_tokens": 46178432} +{"current_steps": 141, "total_steps": 522, "loss": 0.099, "accuracy": 0.9609375, "lr": 1.693971460889654e-05, "epoch": 0.5401005506344266, "percentage": 27.01, "elapsed_time": "1:58:18", "remaining_time": "5:19:40", "throughput": 6551.05, "total_tokens": 46500768} +{"current_steps": 142, "total_steps": 522, "loss": 0.0724, "accuracy": 0.9765625, "lr": 1.689540544737067e-05, "epoch": 0.543931050993536, "percentage": 27.2, "elapsed_time": "1:59:07", "remaining_time": "5:18:46", "throughput": 6551.74, "total_tokens": 46827200} +{"current_steps": 143, "total_steps": 522, "loss": 0.0651, "accuracy": 0.984375, "lr": 1.6850836677727005e-05, "epoch": 0.5477615513526455, "percentage": 27.39, "elapsed_time": "1:59:57", "remaining_time": "5:17:54", "throughput": 6552.24, "total_tokens": 47156576} +{"current_steps": 144, "total_steps": 522, "loss": 0.0992, "accuracy": 0.953125, "lr": 1.6806009977954533e-05, "epoch": 0.5515920517117548, "percentage": 27.59, "elapsed_time": "2:00:48", "remaining_time": "5:17:07", "throughput": 6553.33, "total_tokens": 47501920} +{"current_steps": 145, "total_steps": 522, "loss": 0.0882, "accuracy": 0.953125, "lr": 1.676092703575316e-05, "epoch": 0.5554225520708642, "percentage": 27.78, "elapsed_time": "2:01:36", "remaining_time": "5:16:12", "throughput": 6555.13, "total_tokens": 47832384} +{"current_steps": 146, "total_steps": 522, "loss": 0.0836, "accuracy": 0.9765625, "lr": 1.6715589548470187e-05, "epoch": 0.5592530524299737, "percentage": 27.97, "elapsed_time": "2:02:27", "remaining_time": "5:15:22", "throughput": 6556.05, "total_tokens": 48172064} +{"current_steps": 147, "total_steps": 522, "loss": 0.0801, "accuracy": 0.96875, "lr": 1.6669999223036377e-05, "epoch": 0.5630835527890831, "percentage": 28.16, "elapsed_time": "2:04:30", "remaining_time": "5:17:37", "throughput": 6490.9, "total_tokens": 48490304} +{"current_steps": 148, "total_steps": 522, "loss": 0.0507, "accuracy": 0.984375, "lr": 1.662415777590172e-05, "epoch": 0.5669140531481924, "percentage": 28.35, "elapsed_time": "2:05:26", "remaining_time": "5:16:59", "throughput": 6484.8, "total_tokens": 48808128} +{"current_steps": 149, "total_steps": 522, "loss": 0.1075, "accuracy": 0.9609375, "lr": 1.657806693297079e-05, "epoch": 0.5707445535073019, "percentage": 28.54, "elapsed_time": "2:06:16", "remaining_time": "5:16:07", "throughput": 6486.07, "total_tokens": 49144000} +{"current_steps": 150, "total_steps": 522, "loss": 0.0617, "accuracy": 0.9765625, "lr": 1.6531728429537766e-05, "epoch": 0.5745750538664113, "percentage": 28.74, "elapsed_time": "2:07:05", "remaining_time": "5:15:10", "throughput": 6487.43, "total_tokens": 49469216} +{"current_steps": 151, "total_steps": 522, "loss": 0.0908, "accuracy": 0.9765625, "lr": 1.6485144010221126e-05, "epoch": 0.5784055542255208, "percentage": 28.93, "elapsed_time": "2:07:55", "remaining_time": "5:14:17", "throughput": 6488.26, "total_tokens": 49799488} +{"current_steps": 152, "total_steps": 522, "loss": 0.0647, "accuracy": 0.9765625, "lr": 1.6438315428897914e-05, "epoch": 0.5822360545846301, "percentage": 29.12, "elapsed_time": "2:08:46", "remaining_time": "5:13:27", "throughput": 6488.09, "total_tokens": 50129408} +{"current_steps": 153, "total_steps": 522, "loss": 0.0852, "accuracy": 0.9609375, "lr": 1.639124444863776e-05, "epoch": 0.5860665549437395, "percentage": 29.31, "elapsed_time": "2:09:36", "remaining_time": "5:12:34", "throughput": 6488.34, "total_tokens": 50455968} +{"current_steps": 154, "total_steps": 522, "loss": 0.0384, "accuracy": 0.9921875, "lr": 1.6343932841636455e-05, "epoch": 0.589897055302849, "percentage": 29.5, "elapsed_time": "2:10:24", "remaining_time": "5:11:36", "throughput": 6488.86, "total_tokens": 50770496} +{"current_steps": 155, "total_steps": 522, "loss": 0.1084, "accuracy": 0.953125, "lr": 1.6296382389149273e-05, "epoch": 0.5937275556619583, "percentage": 29.69, "elapsed_time": "2:11:15", "remaining_time": "5:10:48", "throughput": 6489.02, "total_tokens": 51106624} +{"current_steps": 156, "total_steps": 522, "loss": 0.0808, "accuracy": 0.96875, "lr": 1.6248594881423866e-05, "epoch": 0.5975580560210677, "percentage": 29.89, "elapsed_time": "2:12:07", "remaining_time": "5:09:58", "throughput": 6489.08, "total_tokens": 51440256} +{"current_steps": 157, "total_steps": 522, "loss": 0.0811, "accuracy": 0.96875, "lr": 1.6200572117632892e-05, "epoch": 0.6013885563801772, "percentage": 30.08, "elapsed_time": "2:12:56", "remaining_time": "5:09:04", "throughput": 6489.71, "total_tokens": 51767552} +{"current_steps": 158, "total_steps": 522, "loss": 0.0552, "accuracy": 0.984375, "lr": 1.615231590580627e-05, "epoch": 0.6052190567392866, "percentage": 30.27, "elapsed_time": "2:13:45", "remaining_time": "5:08:09", "throughput": 6491.08, "total_tokens": 52094208} +{"current_steps": 159, "total_steps": 522, "loss": 0.0476, "accuracy": 0.9921875, "lr": 1.6103828062763095e-05, "epoch": 0.609049557098396, "percentage": 30.46, "elapsed_time": "2:14:35", "remaining_time": "5:07:16", "throughput": 6492.82, "total_tokens": 52431584} +{"current_steps": 160, "total_steps": 522, "loss": 0.0607, "accuracy": 0.984375, "lr": 1.605511041404326e-05, "epoch": 0.6128800574575054, "percentage": 30.65, "elapsed_time": "2:15:24", "remaining_time": "5:06:21", "throughput": 6493.86, "total_tokens": 52759680} +{"current_steps": 161, "total_steps": 522, "loss": 0.0878, "accuracy": 0.9609375, "lr": 1.6006164793838693e-05, "epoch": 0.6167105578166148, "percentage": 30.84, "elapsed_time": "2:16:13", "remaining_time": "5:05:27", "throughput": 6495.31, "total_tokens": 53090880} +{"current_steps": 162, "total_steps": 522, "loss": 0.064, "accuracy": 0.9765625, "lr": 1.5956993044924334e-05, "epoch": 0.6205410581757242, "percentage": 31.03, "elapsed_time": "2:17:11", "remaining_time": "5:04:51", "throughput": 6489.68, "total_tokens": 53418208} +{"current_steps": 163, "total_steps": 522, "loss": 0.0851, "accuracy": 0.9609375, "lr": 1.5907597018588746e-05, "epoch": 0.6243715585348336, "percentage": 31.23, "elapsed_time": "2:17:58", "remaining_time": "5:03:53", "throughput": 6491.12, "total_tokens": 53739520} +{"current_steps": 164, "total_steps": 522, "loss": 0.0936, "accuracy": 0.953125, "lr": 1.585797857456439e-05, "epoch": 0.628202058893943, "percentage": 31.42, "elapsed_time": "2:18:49", "remaining_time": "5:03:03", "throughput": 6491.32, "total_tokens": 54071936} +{"current_steps": 165, "total_steps": 522, "loss": 0.0891, "accuracy": 0.96875, "lr": 1.5808139580957647e-05, "epoch": 0.6320325592530525, "percentage": 31.61, "elapsed_time": "2:19:38", "remaining_time": "5:02:07", "throughput": 6491.79, "total_tokens": 54390368} +{"current_steps": 166, "total_steps": 522, "loss": 0.1092, "accuracy": 0.9453125, "lr": 1.5758081914178457e-05, "epoch": 0.6358630596121618, "percentage": 31.8, "elapsed_time": "2:20:27", "remaining_time": "5:01:12", "throughput": 6492.91, "total_tokens": 54716928} +{"current_steps": 167, "total_steps": 522, "loss": 0.0476, "accuracy": 0.9921875, "lr": 1.5707807458869675e-05, "epoch": 0.6396935599712712, "percentage": 31.99, "elapsed_time": "2:21:16", "remaining_time": "5:00:18", "throughput": 6493.64, "total_tokens": 55043456} +{"current_steps": 168, "total_steps": 522, "loss": 0.074, "accuracy": 0.9765625, "lr": 1.5657318107836133e-05, "epoch": 0.6435240603303807, "percentage": 32.18, "elapsed_time": "2:22:05", "remaining_time": "4:59:24", "throughput": 6494.62, "total_tokens": 55370368} +{"current_steps": 169, "total_steps": 522, "loss": 0.0451, "accuracy": 0.984375, "lr": 1.560661576197336e-05, "epoch": 0.64735456068949, "percentage": 32.38, "elapsed_time": "2:22:55", "remaining_time": "4:58:32", "throughput": 6495.69, "total_tokens": 55703360} +{"current_steps": 170, "total_steps": 522, "loss": 0.0652, "accuracy": 0.9765625, "lr": 1.5555702330196024e-05, "epoch": 0.6511850610485995, "percentage": 32.57, "elapsed_time": "2:23:45", "remaining_time": "4:57:39", "throughput": 6496.52, "total_tokens": 56034752} +{"current_steps": 171, "total_steps": 522, "loss": 0.0392, "accuracy": 1.0, "lr": 1.550457972936605e-05, "epoch": 0.6550155614077089, "percentage": 32.76, "elapsed_time": "2:24:34", "remaining_time": "4:56:45", "throughput": 6496.82, "total_tokens": 56355040} +{"current_steps": 172, "total_steps": 522, "loss": 0.1087, "accuracy": 0.953125, "lr": 1.5453249884220466e-05, "epoch": 0.6588460617668183, "percentage": 32.95, "elapsed_time": "2:25:22", "remaining_time": "4:55:50", "throughput": 6497.4, "total_tokens": 56676128} +{"current_steps": 173, "total_steps": 522, "loss": 0.0688, "accuracy": 0.984375, "lr": 1.540171472729893e-05, "epoch": 0.6626765621259277, "percentage": 33.14, "elapsed_time": "2:26:11", "remaining_time": "4:54:54", "throughput": 6498.95, "total_tokens": 57004672} +{"current_steps": 174, "total_steps": 522, "loss": 0.0475, "accuracy": 0.9921875, "lr": 1.5349976198870974e-05, "epoch": 0.6665070624850371, "percentage": 33.33, "elapsed_time": "2:27:01", "remaining_time": "4:54:02", "throughput": 6498.88, "total_tokens": 57329792} +{"current_steps": 175, "total_steps": 522, "loss": 0.0648, "accuracy": 0.96875, "lr": 1.529803624686295e-05, "epoch": 0.6703375628441465, "percentage": 33.52, "elapsed_time": "2:27:52", "remaining_time": "4:53:12", "throughput": 6499.52, "total_tokens": 57664768} +{"current_steps": 176, "total_steps": 522, "loss": 0.0709, "accuracy": 0.9765625, "lr": 1.5245896826784689e-05, "epoch": 0.674168063203256, "percentage": 33.72, "elapsed_time": "2:28:41", "remaining_time": "4:52:19", "throughput": 6501.07, "total_tokens": 58001760} +{"current_steps": 177, "total_steps": 522, "loss": 0.1017, "accuracy": 0.953125, "lr": 1.5193559901655897e-05, "epoch": 0.6779985635623653, "percentage": 33.91, "elapsed_time": "2:29:32", "remaining_time": "4:51:27", "throughput": 6502.7, "total_tokens": 58342336} +{"current_steps": 178, "total_steps": 522, "loss": 0.0619, "accuracy": 0.984375, "lr": 1.5141027441932217e-05, "epoch": 0.6818290639214747, "percentage": 34.1, "elapsed_time": "2:30:21", "remaining_time": "4:50:34", "throughput": 6503.38, "total_tokens": 58670432} +{"current_steps": 179, "total_steps": 522, "loss": 0.0519, "accuracy": 0.984375, "lr": 1.5088301425431072e-05, "epoch": 0.6856595642805842, "percentage": 34.29, "elapsed_time": "2:31:09", "remaining_time": "4:49:39", "throughput": 6504.4, "total_tokens": 58993472} +{"current_steps": 180, "total_steps": 522, "loss": 0.0704, "accuracy": 0.9765625, "lr": 1.5035383837257178e-05, "epoch": 0.6894900646396935, "percentage": 34.48, "elapsed_time": "2:31:58", "remaining_time": "4:48:45", "throughput": 6505.33, "total_tokens": 59321248} +{"current_steps": 181, "total_steps": 522, "loss": 0.0565, "accuracy": 0.984375, "lr": 1.498227666972782e-05, "epoch": 0.693320564998803, "percentage": 34.67, "elapsed_time": "2:32:48", "remaining_time": "4:47:53", "throughput": 6504.94, "total_tokens": 59640512} +{"current_steps": 182, "total_steps": 522, "loss": 0.0817, "accuracy": 0.96875, "lr": 1.4928981922297842e-05, "epoch": 0.6971510653579124, "percentage": 34.87, "elapsed_time": "2:34:34", "remaining_time": "4:48:45", "throughput": 6465.61, "total_tokens": 59963648} +{"current_steps": 183, "total_steps": 522, "loss": 0.0783, "accuracy": 0.96875, "lr": 1.4875501601484362e-05, "epoch": 0.7009815657170217, "percentage": 35.06, "elapsed_time": "2:35:24", "remaining_time": "4:47:53", "throughput": 6467.22, "total_tokens": 60304064} +{"current_steps": 184, "total_steps": 522, "loss": 0.0733, "accuracy": 0.96875, "lr": 1.482183772079123e-05, "epoch": 0.7048120660761312, "percentage": 35.25, "elapsed_time": "2:36:13", "remaining_time": "4:46:59", "throughput": 6468.11, "total_tokens": 60630784} +{"current_steps": 185, "total_steps": 522, "loss": 0.0669, "accuracy": 0.96875, "lr": 1.4767992300633224e-05, "epoch": 0.7086425664352406, "percentage": 35.44, "elapsed_time": "2:37:02", "remaining_time": "4:46:04", "throughput": 6468.84, "total_tokens": 60955136} +{"current_steps": 186, "total_steps": 522, "loss": 0.091, "accuracy": 0.9765625, "lr": 1.4713967368259981e-05, "epoch": 0.71247306679435, "percentage": 35.63, "elapsed_time": "2:37:52", "remaining_time": "4:45:11", "throughput": 6469.96, "total_tokens": 61287008} +{"current_steps": 187, "total_steps": 522, "loss": 0.0871, "accuracy": 0.9609375, "lr": 1.4659764957679663e-05, "epoch": 0.7163035671534594, "percentage": 35.82, "elapsed_time": "2:38:41", "remaining_time": "4:44:17", "throughput": 6470.63, "total_tokens": 61610560} +{"current_steps": 188, "total_steps": 522, "loss": 0.0876, "accuracy": 0.9765625, "lr": 1.4605387109582401e-05, "epoch": 0.7201340675125688, "percentage": 36.02, "elapsed_time": "2:39:31", "remaining_time": "4:43:24", "throughput": 6471.75, "total_tokens": 61944384} +{"current_steps": 189, "total_steps": 522, "loss": 0.0526, "accuracy": 0.9921875, "lr": 1.455083587126344e-05, "epoch": 0.7239645678716783, "percentage": 36.21, "elapsed_time": "2:40:20", "remaining_time": "4:42:29", "throughput": 6472.56, "total_tokens": 62267712} +{"current_steps": 190, "total_steps": 522, "loss": 0.1032, "accuracy": 0.984375, "lr": 1.4496113296546068e-05, "epoch": 0.7277950682307877, "percentage": 36.4, "elapsed_time": "2:41:08", "remaining_time": "4:41:34", "throughput": 6473.96, "total_tokens": 62595584} +{"current_steps": 191, "total_steps": 522, "loss": 0.0334, "accuracy": 1.0, "lr": 1.4441221445704294e-05, "epoch": 0.731625568589897, "percentage": 36.59, "elapsed_time": "2:41:58", "remaining_time": "4:40:42", "throughput": 6474.32, "total_tokens": 62921344} +{"current_steps": 192, "total_steps": 522, "loss": 0.0724, "accuracy": 0.984375, "lr": 1.4386162385385279e-05, "epoch": 0.7354560689490065, "percentage": 36.78, "elapsed_time": "2:42:46", "remaining_time": "4:39:46", "throughput": 6474.14, "total_tokens": 63231200} +{"current_steps": 193, "total_steps": 522, "loss": 0.0563, "accuracy": 0.9921875, "lr": 1.433093818853152e-05, "epoch": 0.7392865693081159, "percentage": 36.97, "elapsed_time": "2:43:38", "remaining_time": "4:38:56", "throughput": 6474.89, "total_tokens": 63570592} +{"current_steps": 194, "total_steps": 522, "loss": 0.0592, "accuracy": 0.9921875, "lr": 1.4275550934302822e-05, "epoch": 0.7431170696672252, "percentage": 37.16, "elapsed_time": "2:44:27", "remaining_time": "4:38:03", "throughput": 6475.11, "total_tokens": 63894464} +{"current_steps": 195, "total_steps": 522, "loss": 0.0676, "accuracy": 0.9765625, "lr": 1.4220002707998e-05, "epoch": 0.7469475700263347, "percentage": 37.36, "elapsed_time": "2:45:18", "remaining_time": "4:37:11", "throughput": 6475.78, "total_tokens": 64227200} +{"current_steps": 196, "total_steps": 522, "loss": 0.0188, "accuracy": 1.0, "lr": 1.4164295600976375e-05, "epoch": 0.7507780703854441, "percentage": 37.55, "elapsed_time": "2:46:07", "remaining_time": "4:36:19", "throughput": 6477.38, "total_tokens": 64565504} +{"current_steps": 197, "total_steps": 522, "loss": 0.121, "accuracy": 0.953125, "lr": 1.410843171057904e-05, "epoch": 0.7546085707445535, "percentage": 37.74, "elapsed_time": "2:46:59", "remaining_time": "4:35:29", "throughput": 6478.71, "total_tokens": 64911392} +{"current_steps": 198, "total_steps": 522, "loss": 0.0567, "accuracy": 0.9765625, "lr": 1.4052413140049898e-05, "epoch": 0.7584390711036629, "percentage": 37.93, "elapsed_time": "2:47:49", "remaining_time": "4:34:37", "throughput": 6479.93, "total_tokens": 65249856} +{"current_steps": 199, "total_steps": 522, "loss": 0.054, "accuracy": 1.0, "lr": 1.399624199845647e-05, "epoch": 0.7622695714627723, "percentage": 38.12, "elapsed_time": "2:48:39", "remaining_time": "4:33:45", "throughput": 6479.69, "total_tokens": 65572384} +{"current_steps": 200, "total_steps": 522, "loss": 0.0364, "accuracy": 1.0, "lr": 1.3939920400610483e-05, "epoch": 0.7661000718218818, "percentage": 38.31, "elapsed_time": "2:49:30", "remaining_time": "4:32:54", "throughput": 6479.96, "total_tokens": 65904512} +{"current_steps": 201, "total_steps": 522, "loss": 0.0697, "accuracy": 0.984375, "lr": 1.3883450466988264e-05, "epoch": 0.7699305721809911, "percentage": 38.51, "elapsed_time": "2:50:21", "remaining_time": "4:32:03", "throughput": 6480.6, "total_tokens": 66239552} +{"current_steps": 202, "total_steps": 522, "loss": 0.0349, "accuracy": 0.9921875, "lr": 1.3826834323650899e-05, "epoch": 0.7737610725401005, "percentage": 38.7, "elapsed_time": "2:51:11", "remaining_time": "4:31:11", "throughput": 6481.18, "total_tokens": 66571296} +{"current_steps": 203, "total_steps": 522, "loss": 0.0654, "accuracy": 0.984375, "lr": 1.3770074102164184e-05, "epoch": 0.77759157289921, "percentage": 38.89, "elapsed_time": "2:52:03", "remaining_time": "4:30:21", "throughput": 6481.55, "total_tokens": 66909408} +{"current_steps": 204, "total_steps": 522, "loss": 0.0455, "accuracy": 0.9921875, "lr": 1.3713171939518378e-05, "epoch": 0.7814220732583194, "percentage": 39.08, "elapsed_time": "2:52:51", "remaining_time": "4:29:27", "throughput": 6481.68, "total_tokens": 67225952} +{"current_steps": 205, "total_steps": 522, "loss": 0.051, "accuracy": 0.9921875, "lr": 1.365612997804774e-05, "epoch": 0.7852525736174287, "percentage": 39.27, "elapsed_time": "2:53:42", "remaining_time": "4:28:36", "throughput": 6483.38, "total_tokens": 67570528} +{"current_steps": 206, "total_steps": 522, "loss": 0.0726, "accuracy": 0.96875, "lr": 1.3598950365349884e-05, "epoch": 0.7890830739765382, "percentage": 39.46, "elapsed_time": "2:54:30", "remaining_time": "4:27:41", "throughput": 6484.38, "total_tokens": 67896000} +{"current_steps": 207, "total_steps": 522, "loss": 0.0955, "accuracy": 0.953125, "lr": 1.3541635254204906e-05, "epoch": 0.7929135743356476, "percentage": 39.66, "elapsed_time": "2:55:28", "remaining_time": "4:27:01", "throughput": 6480.25, "total_tokens": 68227488} +{"current_steps": 208, "total_steps": 522, "loss": 0.0521, "accuracy": 0.96875, "lr": 1.3484186802494346e-05, "epoch": 0.796744074694757, "percentage": 39.85, "elapsed_time": "2:56:19", "remaining_time": "4:26:11", "throughput": 6481.14, "total_tokens": 68567584} +{"current_steps": 209, "total_steps": 522, "loss": 0.0754, "accuracy": 0.9765625, "lr": 1.3426607173119945e-05, "epoch": 0.8005745750538664, "percentage": 40.04, "elapsed_time": "2:57:08", "remaining_time": "4:25:17", "throughput": 6482.11, "total_tokens": 68895840} +{"current_steps": 210, "total_steps": 522, "loss": 0.0735, "accuracy": 0.9609375, "lr": 1.3368898533922202e-05, "epoch": 0.8044050754129758, "percentage": 40.23, "elapsed_time": "2:58:04", "remaining_time": "4:24:34", "throughput": 6479.24, "total_tokens": 69229696} +{"current_steps": 211, "total_steps": 522, "loss": 0.0477, "accuracy": 0.984375, "lr": 1.3311063057598765e-05, "epoch": 0.8082355757720853, "percentage": 40.42, "elapsed_time": "2:58:55", "remaining_time": "4:23:43", "throughput": 6479.78, "total_tokens": 69564640} +{"current_steps": 212, "total_steps": 522, "loss": 0.0906, "accuracy": 0.96875, "lr": 1.3253102921622632e-05, "epoch": 0.8120660761311946, "percentage": 40.61, "elapsed_time": "2:59:46", "remaining_time": "4:22:52", "throughput": 6481.17, "total_tokens": 69908864} +{"current_steps": 213, "total_steps": 522, "loss": 0.0585, "accuracy": 0.984375, "lr": 1.3195020308160157e-05, "epoch": 0.815896576490304, "percentage": 40.8, "elapsed_time": "3:00:35", "remaining_time": "4:21:58", "throughput": 6481.32, "total_tokens": 70225312} +{"current_steps": 214, "total_steps": 522, "loss": 0.0615, "accuracy": 0.984375, "lr": 1.3136817403988918e-05, "epoch": 0.8197270768494135, "percentage": 41.0, "elapsed_time": "3:01:25", "remaining_time": "4:21:07", "throughput": 6482.58, "total_tokens": 70567520} +{"current_steps": 215, "total_steps": 522, "loss": 0.0424, "accuracy": 0.9921875, "lr": 1.307849640041535e-05, "epoch": 0.8235575772085229, "percentage": 41.19, "elapsed_time": "3:02:16", "remaining_time": "4:20:16", "throughput": 6482.83, "total_tokens": 70901728} +{"current_steps": 216, "total_steps": 522, "loss": 0.0473, "accuracy": 0.9921875, "lr": 1.3020059493192283e-05, "epoch": 0.8273880775676322, "percentage": 41.38, "elapsed_time": "3:03:06", "remaining_time": "4:19:24", "throughput": 6483.31, "total_tokens": 71229504} +{"current_steps": 217, "total_steps": 522, "loss": 0.0753, "accuracy": 0.9765625, "lr": 1.296150888243624e-05, "epoch": 0.8312185779267417, "percentage": 41.57, "elapsed_time": "3:03:56", "remaining_time": "4:18:32", "throughput": 6483.47, "total_tokens": 71554720} +{"current_steps": 218, "total_steps": 522, "loss": 0.0771, "accuracy": 0.9765625, "lr": 1.2902846772544625e-05, "epoch": 0.8350490782858511, "percentage": 41.76, "elapsed_time": "3:04:45", "remaining_time": "4:17:39", "throughput": 6484.48, "total_tokens": 71885408} +{"current_steps": 219, "total_steps": 522, "loss": 0.0798, "accuracy": 0.9765625, "lr": 1.2844075372112718e-05, "epoch": 0.8388795786449605, "percentage": 41.95, "elapsed_time": "3:05:34", "remaining_time": "4:16:45", "throughput": 6486.08, "total_tokens": 72221248} +{"current_steps": 220, "total_steps": 522, "loss": 0.0485, "accuracy": 0.9921875, "lr": 1.2785196893850532e-05, "epoch": 0.8427100790040699, "percentage": 42.15, "elapsed_time": "3:06:25", "remaining_time": "4:15:54", "throughput": 6486.18, "total_tokens": 72548736} +{"current_steps": 221, "total_steps": 522, "loss": 0.0641, "accuracy": 0.96875, "lr": 1.2726213554499491e-05, "epoch": 0.8465405793631793, "percentage": 42.34, "elapsed_time": "3:07:13", "remaining_time": "4:15:00", "throughput": 6486.87, "total_tokens": 72872864} +{"current_steps": 222, "total_steps": 522, "loss": 0.0598, "accuracy": 0.96875, "lr": 1.2667127574748985e-05, "epoch": 0.8503710797222888, "percentage": 42.53, "elapsed_time": "3:08:03", "remaining_time": "4:14:07", "throughput": 6487.14, "total_tokens": 73196896} +{"current_steps": 223, "total_steps": 522, "loss": 0.0427, "accuracy": 0.9921875, "lr": 1.2607941179152756e-05, "epoch": 0.8542015800813981, "percentage": 42.72, "elapsed_time": "3:08:53", "remaining_time": "4:13:16", "throughput": 6487.88, "total_tokens": 73533536} +{"current_steps": 224, "total_steps": 522, "loss": 0.0342, "accuracy": 0.9921875, "lr": 1.2548656596045147e-05, "epoch": 0.8580320804405075, "percentage": 42.91, "elapsed_time": "3:09:41", "remaining_time": "4:12:21", "throughput": 6489.11, "total_tokens": 73857184} +{"current_steps": 225, "total_steps": 522, "loss": 0.043, "accuracy": 0.9921875, "lr": 1.2489276057457205e-05, "epoch": 0.861862580799617, "percentage": 43.1, "elapsed_time": "3:10:31", "remaining_time": "4:11:30", "throughput": 6489.9, "total_tokens": 74191872} +{"current_steps": 226, "total_steps": 522, "loss": 0.0519, "accuracy": 0.984375, "lr": 1.242980179903264e-05, "epoch": 0.8656930811587263, "percentage": 43.3, "elapsed_time": "3:11:21", "remaining_time": "4:10:38", "throughput": 6489.91, "total_tokens": 74516224} +{"current_steps": 227, "total_steps": 522, "loss": 0.058, "accuracy": 0.984375, "lr": 1.2370236059943674e-05, "epoch": 0.8695235815178358, "percentage": 43.49, "elapsed_time": "3:12:12", "remaining_time": "4:09:47", "throughput": 6489.55, "total_tokens": 74841280} +{"current_steps": 228, "total_steps": 522, "loss": 0.0781, "accuracy": 0.96875, "lr": 1.2310581082806713e-05, "epoch": 0.8733540818769452, "percentage": 43.68, "elapsed_time": "3:13:03", "remaining_time": "4:08:55", "throughput": 6490.0, "total_tokens": 75173696} +{"current_steps": 229, "total_steps": 522, "loss": 0.0447, "accuracy": 0.9921875, "lr": 1.2250839113597928e-05, "epoch": 0.8771845822360546, "percentage": 43.87, "elapsed_time": "3:13:49", "remaining_time": "4:07:59", "throughput": 6490.47, "total_tokens": 75480896} +{"current_steps": 230, "total_steps": 522, "loss": 0.0417, "accuracy": 0.9921875, "lr": 1.2191012401568698e-05, "epoch": 0.881015082595164, "percentage": 44.06, "elapsed_time": "3:14:39", "remaining_time": "4:07:07", "throughput": 6491.23, "total_tokens": 75812608} +{"current_steps": 231, "total_steps": 522, "loss": 0.0535, "accuracy": 0.9765625, "lr": 1.2131103199160913e-05, "epoch": 0.8848455829542734, "percentage": 44.25, "elapsed_time": "3:15:29", "remaining_time": "4:06:16", "throughput": 6491.45, "total_tokens": 76142400} +{"current_steps": 232, "total_steps": 522, "loss": 0.0463, "accuracy": 0.984375, "lr": 1.2071113761922187e-05, "epoch": 0.8886760833133828, "percentage": 44.44, "elapsed_time": "3:16:20", "remaining_time": "4:05:26", "throughput": 6492.69, "total_tokens": 76489376} +{"current_steps": 233, "total_steps": 522, "loss": 0.0358, "accuracy": 0.9921875, "lr": 1.2011046348420921e-05, "epoch": 0.8925065836724922, "percentage": 44.64, "elapsed_time": "3:17:09", "remaining_time": "4:04:33", "throughput": 6493.53, "total_tokens": 76818304} +{"current_steps": 234, "total_steps": 522, "loss": 0.0726, "accuracy": 0.9765625, "lr": 1.1950903220161286e-05, "epoch": 0.8963370840316016, "percentage": 44.83, "elapsed_time": "3:17:59", "remaining_time": "4:03:41", "throughput": 6494.81, "total_tokens": 77158272} +{"current_steps": 235, "total_steps": 522, "loss": 0.079, "accuracy": 0.96875, "lr": 1.1890686641498064e-05, "epoch": 0.900167584390711, "percentage": 45.02, "elapsed_time": "3:18:49", "remaining_time": "4:02:49", "throughput": 6495.19, "total_tokens": 77483360} +{"current_steps": 236, "total_steps": 522, "loss": 0.0488, "accuracy": 0.9921875, "lr": 1.1830398879551412e-05, "epoch": 0.9039980847498205, "percentage": 45.21, "elapsed_time": "3:19:40", "remaining_time": "4:01:58", "throughput": 6495.59, "total_tokens": 77818944} +{"current_steps": 237, "total_steps": 522, "loss": 0.0913, "accuracy": 0.96875, "lr": 1.177004220412149e-05, "epoch": 0.9078285851089298, "percentage": 45.4, "elapsed_time": "3:20:29", "remaining_time": "4:01:05", "throughput": 6496.24, "total_tokens": 78145344} +{"current_steps": 238, "total_steps": 522, "loss": 0.0529, "accuracy": 0.9765625, "lr": 1.1709618887603013e-05, "epoch": 0.9116590854680393, "percentage": 45.59, "elapsed_time": "3:21:18", "remaining_time": "4:00:13", "throughput": 6497.94, "total_tokens": 78488160} +{"current_steps": 239, "total_steps": 522, "loss": 0.0568, "accuracy": 0.9765625, "lr": 1.1649131204899702e-05, "epoch": 0.9154895858271487, "percentage": 45.79, "elapsed_time": "3:22:07", "remaining_time": "3:59:20", "throughput": 6499.31, "total_tokens": 78819968} +{"current_steps": 240, "total_steps": 522, "loss": 0.0574, "accuracy": 0.984375, "lr": 1.1588581433338614e-05, "epoch": 0.919320086186258, "percentage": 45.98, "elapsed_time": "3:22:57", "remaining_time": "3:58:28", "throughput": 6499.33, "total_tokens": 79143136} +{"current_steps": 241, "total_steps": 522, "loss": 0.0927, "accuracy": 0.96875, "lr": 1.1527971852584434e-05, "epoch": 0.9231505865453675, "percentage": 46.17, "elapsed_time": "3:23:47", "remaining_time": "3:57:37", "throughput": 6500.12, "total_tokens": 79482752} +{"current_steps": 242, "total_steps": 522, "loss": 0.047, "accuracy": 0.984375, "lr": 1.1467304744553618e-05, "epoch": 0.9269810869044769, "percentage": 46.36, "elapsed_time": "3:24:39", "remaining_time": "3:56:47", "throughput": 6500.02, "total_tokens": 79813888} +{"current_steps": 243, "total_steps": 522, "loss": 0.0475, "accuracy": 0.984375, "lr": 1.1406582393328493e-05, "epoch": 0.9308115872635863, "percentage": 46.55, "elapsed_time": "3:25:28", "remaining_time": "3:55:54", "throughput": 6500.93, "total_tokens": 80145696} +{"current_steps": 244, "total_steps": 522, "loss": 0.0439, "accuracy": 0.9921875, "lr": 1.1345807085071263e-05, "epoch": 0.9346420876226957, "percentage": 46.74, "elapsed_time": "3:26:18", "remaining_time": "3:55:02", "throughput": 6501.05, "total_tokens": 80471072} +{"current_steps": 245, "total_steps": 522, "loss": 0.0314, "accuracy": 0.9921875, "lr": 1.1284981107937933e-05, "epoch": 0.9384725879818051, "percentage": 46.93, "elapsed_time": "3:27:10", "remaining_time": "3:54:13", "throughput": 6498.69, "total_tokens": 80780224} +{"current_steps": 246, "total_steps": 522, "loss": 0.0276, "accuracy": 1.0, "lr": 1.1224106751992164e-05, "epoch": 0.9423030883409146, "percentage": 47.13, "elapsed_time": "3:27:59", "remaining_time": "3:53:21", "throughput": 6498.76, "total_tokens": 81102880} +{"current_steps": 247, "total_steps": 522, "loss": 0.0225, "accuracy": 1.0, "lr": 1.116318630911905e-05, "epoch": 0.946133588700024, "percentage": 47.32, "elapsed_time": "3:28:50", "remaining_time": "3:52:30", "throughput": 6499.14, "total_tokens": 81435296} +{"current_steps": 248, "total_steps": 522, "loss": 0.0724, "accuracy": 0.96875, "lr": 1.1102222072938832e-05, "epoch": 0.9499640890591333, "percentage": 47.51, "elapsed_time": "3:29:40", "remaining_time": "3:51:39", "throughput": 6500.18, "total_tokens": 81773952} +{"current_steps": 249, "total_steps": 522, "loss": 0.0524, "accuracy": 0.984375, "lr": 1.1041216338720548e-05, "epoch": 0.9537945894182428, "percentage": 47.7, "elapsed_time": "3:30:32", "remaining_time": "3:50:50", "throughput": 6501.18, "total_tokens": 82128992} +{"current_steps": 250, "total_steps": 522, "loss": 0.1022, "accuracy": 0.96875, "lr": 1.098017140329561e-05, "epoch": 0.9576250897773522, "percentage": 47.89, "elapsed_time": "3:31:23", "remaining_time": "3:49:59", "throughput": 6501.33, "total_tokens": 82458624} +{"current_steps": 251, "total_steps": 522, "loss": 0.0704, "accuracy": 0.9765625, "lr": 1.0919089564971328e-05, "epoch": 0.9614555901364615, "percentage": 48.08, "elapsed_time": "3:32:12", "remaining_time": "3:49:07", "throughput": 6502.2, "total_tokens": 82790912} +{"current_steps": 252, "total_steps": 522, "loss": 0.029, "accuracy": 0.9921875, "lr": 1.0857973123444401e-05, "epoch": 0.965286090495571, "percentage": 48.28, "elapsed_time": "3:33:02", "remaining_time": "3:48:15", "throughput": 6502.44, "total_tokens": 83119392} +{"current_steps": 253, "total_steps": 522, "loss": 0.066, "accuracy": 0.984375, "lr": 1.0796824379714301e-05, "epoch": 0.9691165908546804, "percentage": 48.47, "elapsed_time": "3:33:52", "remaining_time": "3:47:23", "throughput": 6503.11, "total_tokens": 83449888} +{"current_steps": 254, "total_steps": 522, "loss": 0.0716, "accuracy": 0.984375, "lr": 1.0735645635996676e-05, "epoch": 0.9729470912137897, "percentage": 48.66, "elapsed_time": "3:34:45", "remaining_time": "3:46:35", "throughput": 6502.73, "total_tokens": 83792608} +{"current_steps": 255, "total_steps": 522, "loss": 0.0613, "accuracy": 0.984375, "lr": 1.067443919563664e-05, "epoch": 0.9767775915728992, "percentage": 48.85, "elapsed_time": "3:35:35", "remaining_time": "3:45:44", "throughput": 6502.99, "total_tokens": 84118304} +{"current_steps": 256, "total_steps": 522, "loss": 0.0284, "accuracy": 0.9921875, "lr": 1.0613207363022086e-05, "epoch": 0.9806080919320086, "percentage": 49.04, "elapsed_time": "3:36:24", "remaining_time": "3:44:51", "throughput": 6503.37, "total_tokens": 84443392} +{"current_steps": 257, "total_steps": 522, "loss": 0.0571, "accuracy": 0.984375, "lr": 1.0551952443496902e-05, "epoch": 0.9844385922911181, "percentage": 49.23, "elapsed_time": "3:37:15", "remaining_time": "3:44:01", "throughput": 6504.41, "total_tokens": 84790656} +{"current_steps": 258, "total_steps": 522, "loss": 0.0607, "accuracy": 0.9765625, "lr": 1.0490676743274181e-05, "epoch": 0.9882690926502274, "percentage": 49.43, "elapsed_time": "3:38:06", "remaining_time": "3:43:10", "throughput": 6505.74, "total_tokens": 85136640} +{"current_steps": 259, "total_steps": 522, "loss": 0.0497, "accuracy": 0.9765625, "lr": 1.042938256934941e-05, "epoch": 0.9920995930093368, "percentage": 49.62, "elapsed_time": "3:38:57", "remaining_time": "3:42:20", "throughput": 6506.03, "total_tokens": 85474048} +{"current_steps": 260, "total_steps": 522, "loss": 0.0568, "accuracy": 0.984375, "lr": 1.036807222941359e-05, "epoch": 0.9959300933684463, "percentage": 49.81, "elapsed_time": "3:39:46", "remaining_time": "3:41:27", "throughput": 6506.5, "total_tokens": 85797408} +{"current_steps": 261, "total_steps": 522, "loss": 0.0328, "accuracy": 1.0, "lr": 1.0306748031766367e-05, "epoch": 0.9997605937275557, "percentage": 50.0, "elapsed_time": "3:40:49", "remaining_time": "3:40:49", "throughput": 6500.64, "total_tokens": 86127744} +{"current_steps": 262, "total_steps": 522, "loss": 0.0049, "accuracy": 1.0, "lr": 1.0245412285229124e-05, "epoch": 1.0, "percentage": 50.19, "elapsed_time": "3:40:52", "remaining_time": "3:39:11", "throughput": 6500.83, "total_tokens": 86150848} +{"current_steps": 263, "total_steps": 522, "loss": 0.0297, "accuracy": 1.0, "lr": 1.018406729905805e-05, "epoch": 1.0038305003591095, "percentage": 50.38, "elapsed_time": "3:41:41", "remaining_time": "3:38:18", "throughput": 6501.05, "total_tokens": 86470976} +{"current_steps": 264, "total_steps": 522, "loss": 0.0394, "accuracy": 0.9921875, "lr": 1.01227153828572e-05, "epoch": 1.0076610007182187, "percentage": 50.57, "elapsed_time": "3:42:35", "remaining_time": "3:37:32", "throughput": 6499.18, "total_tokens": 86801472} +{"current_steps": 265, "total_steps": 522, "loss": 0.0317, "accuracy": 1.0, "lr": 1.0061358846491548e-05, "epoch": 1.0114915010773282, "percentage": 50.77, "elapsed_time": "3:43:25", "remaining_time": "3:36:41", "throughput": 6500.09, "total_tokens": 87139392} +{"current_steps": 266, "total_steps": 522, "loss": 0.0234, "accuracy": 1.0, "lr": 1e-05, "epoch": 1.0153220014364377, "percentage": 50.96, "elapsed_time": "3:44:15", "remaining_time": "3:35:49", "throughput": 6500.6, "total_tokens": 87465760} +{"current_steps": 267, "total_steps": 522, "loss": 0.0273, "accuracy": 0.9921875, "lr": 9.938641153508457e-06, "epoch": 1.019152501795547, "percentage": 51.15, "elapsed_time": "3:45:07", "remaining_time": "3:34:59", "throughput": 6501.04, "total_tokens": 87809856} +{"current_steps": 268, "total_steps": 522, "loss": 0.0203, "accuracy": 1.0, "lr": 9.877284617142802e-06, "epoch": 1.0229830021546564, "percentage": 51.34, "elapsed_time": "3:45:56", "remaining_time": "3:34:08", "throughput": 6500.67, "total_tokens": 88126560} +{"current_steps": 269, "total_steps": 522, "loss": 0.0378, "accuracy": 0.9921875, "lr": 9.815932700941954e-06, "epoch": 1.026813502513766, "percentage": 51.53, "elapsed_time": "3:46:46", "remaining_time": "3:33:17", "throughput": 6501.78, "total_tokens": 88466752} +{"current_steps": 270, "total_steps": 522, "loss": 0.0339, "accuracy": 0.9921875, "lr": 9.75458771477088e-06, "epoch": 1.0306440028728752, "percentage": 51.72, "elapsed_time": "3:47:36", "remaining_time": "3:32:25", "throughput": 6502.1, "total_tokens": 88794112} +{"current_steps": 271, "total_steps": 522, "loss": 0.0321, "accuracy": 1.0, "lr": 9.693251968233637e-06, "epoch": 1.0344745032319846, "percentage": 51.92, "elapsed_time": "3:48:26", "remaining_time": "3:31:34", "throughput": 6501.89, "total_tokens": 89116480} +{"current_steps": 272, "total_steps": 522, "loss": 0.0315, "accuracy": 1.0, "lr": 9.631927770586412e-06, "epoch": 1.0383050035910941, "percentage": 52.11, "elapsed_time": "3:49:16", "remaining_time": "3:30:44", "throughput": 6502.97, "total_tokens": 89460896} +{"current_steps": 273, "total_steps": 522, "loss": 0.0381, "accuracy": 0.984375, "lr": 9.570617430650593e-06, "epoch": 1.0421355039502036, "percentage": 52.3, "elapsed_time": "3:50:05", "remaining_time": "3:29:52", "throughput": 6502.9, "total_tokens": 89776992} +{"current_steps": 274, "total_steps": 522, "loss": 0.0352, "accuracy": 0.9921875, "lr": 9.50932325672582e-06, "epoch": 1.0459660043093129, "percentage": 52.49, "elapsed_time": "3:50:54", "remaining_time": "3:29:00", "throughput": 6502.87, "total_tokens": 90095776} +{"current_steps": 275, "total_steps": 522, "loss": 0.0304, "accuracy": 1.0, "lr": 9.448047556503101e-06, "epoch": 1.0497965046684223, "percentage": 52.68, "elapsed_time": "3:51:45", "remaining_time": "3:28:09", "throughput": 6503.31, "total_tokens": 90429888} +{"current_steps": 276, "total_steps": 522, "loss": 0.0317, "accuracy": 1.0, "lr": 9.386792636977915e-06, "epoch": 1.0536270050275318, "percentage": 52.87, "elapsed_time": "3:52:35", "remaining_time": "3:27:18", "throughput": 6503.82, "total_tokens": 90763872} +{"current_steps": 277, "total_steps": 522, "loss": 0.0544, "accuracy": 0.984375, "lr": 9.325560804363361e-06, "epoch": 1.057457505386641, "percentage": 53.07, "elapsed_time": "3:53:24", "remaining_time": "3:26:26", "throughput": 6505.14, "total_tokens": 91101920} +{"current_steps": 278, "total_steps": 522, "loss": 0.0196, "accuracy": 1.0, "lr": 9.264354364003327e-06, "epoch": 1.0612880057457506, "percentage": 53.26, "elapsed_time": "3:54:13", "remaining_time": "3:25:35", "throughput": 6506.44, "total_tokens": 91441408} +{"current_steps": 279, "total_steps": 522, "loss": 0.0268, "accuracy": 1.0, "lr": 9.2031756202857e-06, "epoch": 1.06511850610486, "percentage": 53.45, "elapsed_time": "3:55:03", "remaining_time": "3:24:43", "throughput": 6506.3, "total_tokens": 91758592} +{"current_steps": 280, "total_steps": 522, "loss": 0.0197, "accuracy": 1.0, "lr": 9.142026876555602e-06, "epoch": 1.0689490064639693, "percentage": 53.64, "elapsed_time": "3:55:52", "remaining_time": "3:23:51", "throughput": 6507.2, "total_tokens": 92090016} +{"current_steps": 281, "total_steps": 522, "loss": 0.0304, "accuracy": 0.9921875, "lr": 9.080910435028675e-06, "epoch": 1.0727795068230788, "percentage": 53.83, "elapsed_time": "3:56:39", "remaining_time": "3:22:58", "throughput": 6507.9, "total_tokens": 92410560} +{"current_steps": 282, "total_steps": 522, "loss": 0.0152, "accuracy": 1.0, "lr": 9.019828596704394e-06, "epoch": 1.0766100071821882, "percentage": 54.02, "elapsed_time": "3:57:29", "remaining_time": "3:22:07", "throughput": 6508.13, "total_tokens": 92740160} +{"current_steps": 283, "total_steps": 522, "loss": 0.0405, "accuracy": 0.984375, "lr": 8.958783661279454e-06, "epoch": 1.0804405075412975, "percentage": 54.21, "elapsed_time": "3:58:19", "remaining_time": "3:21:15", "throughput": 6508.71, "total_tokens": 93068864} +{"current_steps": 284, "total_steps": 522, "loss": 0.0414, "accuracy": 0.984375, "lr": 8.89777792706117e-06, "epoch": 1.084271007900407, "percentage": 54.41, "elapsed_time": "3:59:08", "remaining_time": "3:20:24", "throughput": 6509.26, "total_tokens": 93401184} +{"current_steps": 285, "total_steps": 522, "loss": 0.0394, "accuracy": 0.9921875, "lr": 8.836813690880953e-06, "epoch": 1.0881015082595165, "percentage": 54.6, "elapsed_time": "3:59:59", "remaining_time": "3:19:34", "throughput": 6509.73, "total_tokens": 93738176} +{"current_steps": 286, "total_steps": 522, "loss": 0.0222, "accuracy": 1.0, "lr": 8.77589324800784e-06, "epoch": 1.0919320086186257, "percentage": 54.79, "elapsed_time": "4:00:48", "remaining_time": "3:18:42", "throughput": 6510.2, "total_tokens": 94064352} +{"current_steps": 287, "total_steps": 522, "loss": 0.0334, "accuracy": 0.9921875, "lr": 8.715018892062069e-06, "epoch": 1.0957625089777352, "percentage": 54.98, "elapsed_time": "4:01:38", "remaining_time": "3:17:51", "throughput": 6510.45, "total_tokens": 94393056} +{"current_steps": 288, "total_steps": 522, "loss": 0.0344, "accuracy": 0.9921875, "lr": 8.654192914928739e-06, "epoch": 1.0995930093368447, "percentage": 55.17, "elapsed_time": "4:02:28", "remaining_time": "3:17:00", "throughput": 6510.98, "total_tokens": 94724640} +{"current_steps": 289, "total_steps": 522, "loss": 0.0213, "accuracy": 1.0, "lr": 8.593417606671509e-06, "epoch": 1.103423509695954, "percentage": 55.36, "elapsed_time": "4:03:18", "remaining_time": "3:16:09", "throughput": 6510.66, "total_tokens": 95043040} +{"current_steps": 290, "total_steps": 522, "loss": 0.0277, "accuracy": 1.0, "lr": 8.532695255446384e-06, "epoch": 1.1072540100550634, "percentage": 55.56, "elapsed_time": "4:04:07", "remaining_time": "3:15:17", "throughput": 6510.95, "total_tokens": 95368288} +{"current_steps": 291, "total_steps": 522, "loss": 0.0358, "accuracy": 0.984375, "lr": 8.472028147415567e-06, "epoch": 1.1110845104141729, "percentage": 55.75, "elapsed_time": "4:04:55", "remaining_time": "3:14:25", "throughput": 6510.49, "total_tokens": 95672320} +{"current_steps": 292, "total_steps": 522, "loss": 0.0207, "accuracy": 1.0, "lr": 8.411418566661387e-06, "epoch": 1.1149150107732821, "percentage": 55.94, "elapsed_time": "4:05:48", "remaining_time": "3:13:36", "throughput": 6507.85, "total_tokens": 95980992} +{"current_steps": 293, "total_steps": 522, "loss": 0.0142, "accuracy": 1.0, "lr": 8.350868795100301e-06, "epoch": 1.1187455111323916, "percentage": 56.13, "elapsed_time": "4:06:41", "remaining_time": "3:12:48", "throughput": 6507.72, "total_tokens": 96324896} +{"current_steps": 294, "total_steps": 522, "loss": 0.0237, "accuracy": 1.0, "lr": 8.290381112396989e-06, "epoch": 1.122576011491501, "percentage": 56.32, "elapsed_time": "4:07:30", "remaining_time": "3:11:56", "throughput": 6507.39, "total_tokens": 96640032} +{"current_steps": 295, "total_steps": 522, "loss": 0.0252, "accuracy": 1.0, "lr": 8.229957795878513e-06, "epoch": 1.1264065118506106, "percentage": 56.51, "elapsed_time": "4:08:20", "remaining_time": "3:11:05", "throughput": 6507.87, "total_tokens": 96968160} +{"current_steps": 296, "total_steps": 522, "loss": 0.0207, "accuracy": 1.0, "lr": 8.169601120448592e-06, "epoch": 1.1302370122097198, "percentage": 56.7, "elapsed_time": "4:09:09", "remaining_time": "3:10:14", "throughput": 6507.83, "total_tokens": 97288096} +{"current_steps": 297, "total_steps": 522, "loss": 0.0684, "accuracy": 0.96875, "lr": 8.109313358501939e-06, "epoch": 1.1340675125688293, "percentage": 56.9, "elapsed_time": "4:09:59", "remaining_time": "3:09:23", "throughput": 6508.28, "total_tokens": 97618816} +{"current_steps": 298, "total_steps": 522, "loss": 0.0196, "accuracy": 0.9921875, "lr": 8.04909677983872e-06, "epoch": 1.1378980129279388, "percentage": 57.09, "elapsed_time": "4:10:48", "remaining_time": "3:08:31", "throughput": 6508.57, "total_tokens": 97946400} +{"current_steps": 299, "total_steps": 522, "loss": 0.0593, "accuracy": 0.9765625, "lr": 7.988953651579082e-06, "epoch": 1.141728513287048, "percentage": 57.28, "elapsed_time": "4:11:39", "remaining_time": "3:07:41", "throughput": 6508.32, "total_tokens": 98273472} +{"current_steps": 300, "total_steps": 522, "loss": 0.0354, "accuracy": 0.984375, "lr": 7.928886238077817e-06, "epoch": 1.1455590136461575, "percentage": 57.47, "elapsed_time": "4:12:33", "remaining_time": "3:06:53", "throughput": 6506.78, "total_tokens": 98599360} +{"current_steps": 301, "total_steps": 522, "loss": 0.0193, "accuracy": 0.9921875, "lr": 7.868896800839088e-06, "epoch": 1.149389514005267, "percentage": 57.66, "elapsed_time": "4:13:22", "remaining_time": "3:06:01", "throughput": 6507.65, "total_tokens": 98930080} +{"current_steps": 302, "total_steps": 522, "loss": 0.0142, "accuracy": 1.0, "lr": 7.808987598431303e-06, "epoch": 1.1532200143643763, "percentage": 57.85, "elapsed_time": "4:14:11", "remaining_time": "3:05:10", "throughput": 6507.95, "total_tokens": 99256576} +{"current_steps": 303, "total_steps": 522, "loss": 0.0282, "accuracy": 1.0, "lr": 7.749160886402074e-06, "epoch": 1.1570505147234857, "percentage": 58.05, "elapsed_time": "4:15:02", "remaining_time": "3:04:20", "throughput": 6508.55, "total_tokens": 99595808} +{"current_steps": 304, "total_steps": 522, "loss": 0.0221, "accuracy": 1.0, "lr": 7.68941891719329e-06, "epoch": 1.1608810150825952, "percentage": 58.24, "elapsed_time": "4:15:51", "remaining_time": "3:03:28", "throughput": 6508.64, "total_tokens": 99917760} +{"current_steps": 305, "total_steps": 522, "loss": 0.0426, "accuracy": 0.984375, "lr": 7.629763940056328e-06, "epoch": 1.1647115154417045, "percentage": 58.43, "elapsed_time": "4:16:41", "remaining_time": "3:02:37", "throughput": 6508.71, "total_tokens": 100242176} +{"current_steps": 306, "total_steps": 522, "loss": 0.0208, "accuracy": 1.0, "lr": 7.570198200967363e-06, "epoch": 1.168542015800814, "percentage": 58.62, "elapsed_time": "4:17:29", "remaining_time": "3:01:45", "throughput": 6509.07, "total_tokens": 100560000} +{"current_steps": 307, "total_steps": 522, "loss": 0.0362, "accuracy": 0.9921875, "lr": 7.510723942542799e-06, "epoch": 1.1723725161599234, "percentage": 58.81, "elapsed_time": "4:18:19", "remaining_time": "3:00:54", "throughput": 6510.07, "total_tokens": 100902592} +{"current_steps": 308, "total_steps": 522, "loss": 0.0168, "accuracy": 1.0, "lr": 7.451343403954856e-06, "epoch": 1.176203016519033, "percentage": 59.0, "elapsed_time": "4:19:11", "remaining_time": "3:00:04", "throughput": 6510.18, "total_tokens": 101239840} +{"current_steps": 309, "total_steps": 522, "loss": 0.0324, "accuracy": 1.0, "lr": 7.392058820847246e-06, "epoch": 1.1800335168781422, "percentage": 59.2, "elapsed_time": "4:20:00", "remaining_time": "2:59:14", "throughput": 6510.12, "total_tokens": 101563744} +{"current_steps": 310, "total_steps": 522, "loss": 0.0216, "accuracy": 0.9921875, "lr": 7.332872425251017e-06, "epoch": 1.1838640172372517, "percentage": 59.39, "elapsed_time": "4:20:51", "remaining_time": "2:58:23", "throughput": 6510.39, "total_tokens": 101898880} +{"current_steps": 311, "total_steps": 522, "loss": 0.0226, "accuracy": 1.0, "lr": 7.273786445500512e-06, "epoch": 1.187694517596361, "percentage": 59.58, "elapsed_time": "4:21:42", "remaining_time": "2:57:33", "throughput": 6510.33, "total_tokens": 102231360} +{"current_steps": 312, "total_steps": 522, "loss": 0.0399, "accuracy": 0.9921875, "lr": 7.214803106149471e-06, "epoch": 1.1915250179554704, "percentage": 59.77, "elapsed_time": "4:22:33", "remaining_time": "2:56:43", "throughput": 6511.35, "total_tokens": 102574176} +{"current_steps": 313, "total_steps": 522, "loss": 0.0139, "accuracy": 1.0, "lr": 7.155924627887283e-06, "epoch": 1.1953555183145799, "percentage": 59.96, "elapsed_time": "4:23:22", "remaining_time": "2:55:52", "throughput": 6511.7, "total_tokens": 102903424} +{"current_steps": 314, "total_steps": 522, "loss": 0.016, "accuracy": 1.0, "lr": 7.097153227455379e-06, "epoch": 1.1991860186736893, "percentage": 60.15, "elapsed_time": "4:24:12", "remaining_time": "2:55:01", "throughput": 6512.52, "total_tokens": 103240992} +{"current_steps": 315, "total_steps": 522, "loss": 0.0328, "accuracy": 0.9921875, "lr": 7.038491117563762e-06, "epoch": 1.2030165190327986, "percentage": 60.34, "elapsed_time": "4:25:03", "remaining_time": "2:54:10", "throughput": 6512.95, "total_tokens": 103578240} +{"current_steps": 316, "total_steps": 522, "loss": 0.0371, "accuracy": 0.9765625, "lr": 6.97994050680772e-06, "epoch": 1.206847019391908, "percentage": 60.54, "elapsed_time": "4:25:53", "remaining_time": "2:53:19", "throughput": 6513.2, "total_tokens": 103907424} +{"current_steps": 317, "total_steps": 522, "loss": 0.0376, "accuracy": 0.984375, "lr": 6.9215035995846515e-06, "epoch": 1.2106775197510176, "percentage": 60.73, "elapsed_time": "4:26:43", "remaining_time": "2:52:29", "throughput": 6512.82, "total_tokens": 104225696} +{"current_steps": 318, "total_steps": 522, "loss": 0.0131, "accuracy": 1.0, "lr": 6.8631825960110866e-06, "epoch": 1.2145080201101268, "percentage": 60.92, "elapsed_time": "4:27:34", "remaining_time": "2:51:39", "throughput": 6513.13, "total_tokens": 104567264} +{"current_steps": 319, "total_steps": 522, "loss": 0.0135, "accuracy": 1.0, "lr": 6.8049796918398435e-06, "epoch": 1.2183385204692363, "percentage": 61.11, "elapsed_time": "4:28:23", "remaining_time": "2:50:47", "throughput": 6512.94, "total_tokens": 104878656} +{"current_steps": 320, "total_steps": 522, "loss": 0.0273, "accuracy": 0.9921875, "lr": 6.746897078377372e-06, "epoch": 1.2221690208283458, "percentage": 61.3, "elapsed_time": "4:29:13", "remaining_time": "2:49:56", "throughput": 6513.14, "total_tokens": 105210048} +{"current_steps": 321, "total_steps": 522, "loss": 0.0329, "accuracy": 0.984375, "lr": 6.688936942401237e-06, "epoch": 1.225999521187455, "percentage": 61.49, "elapsed_time": "4:30:03", "remaining_time": "2:49:06", "throughput": 6513.9, "total_tokens": 105549728} +{"current_steps": 322, "total_steps": 522, "loss": 0.0229, "accuracy": 1.0, "lr": 6.631101466077801e-06, "epoch": 1.2298300215465645, "percentage": 61.69, "elapsed_time": "4:30:55", "remaining_time": "2:48:16", "throughput": 6514.77, "total_tokens": 105897600} +{"current_steps": 323, "total_steps": 522, "loss": 0.0304, "accuracy": 0.984375, "lr": 6.573392826880058e-06, "epoch": 1.233660521905674, "percentage": 61.88, "elapsed_time": "4:31:46", "remaining_time": "2:47:26", "throughput": 6514.94, "total_tokens": 106232672} +{"current_steps": 324, "total_steps": 522, "loss": 0.0265, "accuracy": 0.9921875, "lr": 6.515813197505656e-06, "epoch": 1.2374910222647832, "percentage": 62.07, "elapsed_time": "4:32:34", "remaining_time": "2:46:34", "throughput": 6515.06, "total_tokens": 106552192} +{"current_steps": 325, "total_steps": 522, "loss": 0.0331, "accuracy": 1.0, "lr": 6.458364745795096e-06, "epoch": 1.2413215226238927, "percentage": 62.26, "elapsed_time": "4:33:23", "remaining_time": "2:45:42", "throughput": 6514.9, "total_tokens": 106865248} +{"current_steps": 326, "total_steps": 522, "loss": 0.02, "accuracy": 1.0, "lr": 6.401049634650119e-06, "epoch": 1.2451520229830022, "percentage": 62.45, "elapsed_time": "4:34:13", "remaining_time": "2:44:52", "throughput": 6514.64, "total_tokens": 107189984} +{"current_steps": 327, "total_steps": 522, "loss": 0.0352, "accuracy": 0.984375, "lr": 6.343870021952262e-06, "epoch": 1.2489825233421117, "percentage": 62.64, "elapsed_time": "4:35:04", "remaining_time": "2:44:02", "throughput": 6515.28, "total_tokens": 107530208} +{"current_steps": 328, "total_steps": 522, "loss": 0.0252, "accuracy": 0.9921875, "lr": 6.286828060481626e-06, "epoch": 1.252813023701221, "percentage": 62.84, "elapsed_time": "4:35:54", "remaining_time": "2:43:11", "throughput": 6515.74, "total_tokens": 107866464} +{"current_steps": 329, "total_steps": 522, "loss": 0.015, "accuracy": 1.0, "lr": 6.229925897835818e-06, "epoch": 1.2566435240603304, "percentage": 63.03, "elapsed_time": "4:36:44", "remaining_time": "2:42:20", "throughput": 6515.81, "total_tokens": 108193216} +{"current_steps": 330, "total_steps": 522, "loss": 0.0222, "accuracy": 1.0, "lr": 6.173165676349103e-06, "epoch": 1.2604740244194397, "percentage": 63.22, "elapsed_time": "4:37:34", "remaining_time": "2:41:30", "throughput": 6516.25, "total_tokens": 108526592} +{"current_steps": 331, "total_steps": 522, "loss": 0.0544, "accuracy": 0.96875, "lr": 6.116549533011739e-06, "epoch": 1.2643045247785492, "percentage": 63.41, "elapsed_time": "4:38:24", "remaining_time": "2:40:39", "throughput": 6516.33, "total_tokens": 108854496} +{"current_steps": 332, "total_steps": 522, "loss": 0.0311, "accuracy": 0.984375, "lr": 6.060079599389521e-06, "epoch": 1.2681350251376586, "percentage": 63.6, "elapsed_time": "4:39:16", "remaining_time": "2:39:49", "throughput": 6516.96, "total_tokens": 109201216} +{"current_steps": 333, "total_steps": 522, "loss": 0.0427, "accuracy": 0.984375, "lr": 6.003758001543534e-06, "epoch": 1.2719655254967681, "percentage": 63.79, "elapsed_time": "4:40:07", "remaining_time": "2:38:59", "throughput": 6517.43, "total_tokens": 109544960} +{"current_steps": 334, "total_steps": 522, "loss": 0.0396, "accuracy": 0.9921875, "lr": 5.947586859950103e-06, "epoch": 1.2757960258558774, "percentage": 63.98, "elapsed_time": "4:40:58", "remaining_time": "2:38:09", "throughput": 6517.03, "total_tokens": 109868192} +{"current_steps": 335, "total_steps": 522, "loss": 0.0283, "accuracy": 0.984375, "lr": 5.891568289420963e-06, "epoch": 1.2796265262149868, "percentage": 64.18, "elapsed_time": "4:41:48", "remaining_time": "2:37:18", "throughput": 6517.59, "total_tokens": 110200832} +{"current_steps": 336, "total_steps": 522, "loss": 0.0329, "accuracy": 0.9921875, "lr": 5.835704399023631e-06, "epoch": 1.283457026574096, "percentage": 64.37, "elapsed_time": "4:42:37", "remaining_time": "2:36:27", "throughput": 6517.74, "total_tokens": 110526496} +{"current_steps": 337, "total_steps": 522, "loss": 0.0188, "accuracy": 1.0, "lr": 5.7799972920020046e-06, "epoch": 1.2872875269332056, "percentage": 64.56, "elapsed_time": "4:43:26", "remaining_time": "2:35:36", "throughput": 6518.04, "total_tokens": 110851200} +{"current_steps": 338, "total_steps": 522, "loss": 0.0224, "accuracy": 0.984375, "lr": 5.724449065697182e-06, "epoch": 1.291118027292315, "percentage": 64.75, "elapsed_time": "4:44:16", "remaining_time": "2:34:45", "throughput": 6518.38, "total_tokens": 111182784} +{"current_steps": 339, "total_steps": 522, "loss": 0.0143, "accuracy": 1.0, "lr": 5.669061811468481e-06, "epoch": 1.2949485276514245, "percentage": 64.94, "elapsed_time": "4:45:07", "remaining_time": "2:33:54", "throughput": 6518.43, "total_tokens": 111512768} +{"current_steps": 340, "total_steps": 522, "loss": 0.0265, "accuracy": 0.9921875, "lr": 5.613837614614726e-06, "epoch": 1.2987790280105338, "percentage": 65.13, "elapsed_time": "4:45:57", "remaining_time": "2:33:04", "throughput": 6518.37, "total_tokens": 111839008} +{"current_steps": 341, "total_steps": 522, "loss": 0.0324, "accuracy": 0.9921875, "lr": 5.558778554295709e-06, "epoch": 1.3026095283696433, "percentage": 65.33, "elapsed_time": "4:46:48", "remaining_time": "2:32:14", "throughput": 6518.37, "total_tokens": 112173056} +{"current_steps": 342, "total_steps": 522, "loss": 0.049, "accuracy": 0.984375, "lr": 5.503886703453933e-06, "epoch": 1.3064400287287528, "percentage": 65.52, "elapsed_time": "4:47:38", "remaining_time": "2:31:23", "throughput": 6519.09, "total_tokens": 112509504} +{"current_steps": 343, "total_steps": 522, "loss": 0.0202, "accuracy": 1.0, "lr": 5.4491641287365635e-06, "epoch": 1.310270529087862, "percentage": 65.71, "elapsed_time": "4:48:29", "remaining_time": "2:30:33", "throughput": 6520.06, "total_tokens": 112856896} +{"current_steps": 344, "total_steps": 522, "loss": 0.0358, "accuracy": 0.9921875, "lr": 5.3946128904176e-06, "epoch": 1.3141010294469715, "percentage": 65.9, "elapsed_time": "4:49:19", "remaining_time": "2:29:42", "throughput": 6520.38, "total_tokens": 113191488} +{"current_steps": 345, "total_steps": 522, "loss": 0.0168, "accuracy": 1.0, "lr": 5.340235042320341e-06, "epoch": 1.317931529806081, "percentage": 66.09, "elapsed_time": "4:50:10", "remaining_time": "2:28:52", "throughput": 6519.93, "total_tokens": 113514048} +{"current_steps": 346, "total_steps": 522, "loss": 0.017, "accuracy": 0.9921875, "lr": 5.286032631740023e-06, "epoch": 1.3217620301651904, "percentage": 66.28, "elapsed_time": "4:51:00", "remaining_time": "2:28:01", "throughput": 6519.69, "total_tokens": 113838464} +{"current_steps": 347, "total_steps": 522, "loss": 0.0326, "accuracy": 0.9921875, "lr": 5.2320076993667815e-06, "epoch": 1.3255925305242997, "percentage": 66.48, "elapsed_time": "4:51:52", "remaining_time": "2:27:11", "throughput": 6519.85, "total_tokens": 114176736} +{"current_steps": 348, "total_steps": 522, "loss": 0.0427, "accuracy": 0.984375, "lr": 5.178162279208774e-06, "epoch": 1.3294230308834092, "percentage": 66.67, "elapsed_time": "4:52:41", "remaining_time": "2:26:20", "throughput": 6520.28, "total_tokens": 114506016} +{"current_steps": 349, "total_steps": 522, "loss": 0.0328, "accuracy": 0.9921875, "lr": 5.1244983985156425e-06, "epoch": 1.3332535312425184, "percentage": 66.86, "elapsed_time": "4:53:35", "remaining_time": "2:25:32", "throughput": 6518.61, "total_tokens": 114830528} +{"current_steps": 350, "total_steps": 522, "loss": 0.0293, "accuracy": 1.0, "lr": 5.071018077702161e-06, "epoch": 1.337084031601628, "percentage": 67.05, "elapsed_time": "4:54:26", "remaining_time": "2:24:41", "throughput": 6518.39, "total_tokens": 115154272} +{"current_steps": 351, "total_steps": 522, "loss": 0.0162, "accuracy": 1.0, "lr": 5.017723330272184e-06, "epoch": 1.3409145319607374, "percentage": 67.24, "elapsed_time": "4:55:15", "remaining_time": "2:23:50", "throughput": 6518.67, "total_tokens": 115482144} +{"current_steps": 352, "total_steps": 522, "loss": 0.0235, "accuracy": 0.9921875, "lr": 4.964616162742826e-06, "epoch": 1.3447450323198469, "percentage": 67.43, "elapsed_time": "4:56:07", "remaining_time": "2:23:00", "throughput": 6518.76, "total_tokens": 115822272} +{"current_steps": 353, "total_steps": 522, "loss": 0.0171, "accuracy": 1.0, "lr": 4.911698574568929e-06, "epoch": 1.3485755326789561, "percentage": 67.62, "elapsed_time": "4:57:01", "remaining_time": "2:22:12", "throughput": 6517.0, "total_tokens": 116145504} +{"current_steps": 354, "total_steps": 522, "loss": 0.0231, "accuracy": 0.9921875, "lr": 4.858972558067784e-06, "epoch": 1.3524060330380656, "percentage": 67.82, "elapsed_time": "4:57:57", "remaining_time": "2:21:24", "throughput": 6515.12, "total_tokens": 116474016} +{"current_steps": 355, "total_steps": 522, "loss": 0.026, "accuracy": 0.9921875, "lr": 4.8064400983441036e-06, "epoch": 1.3562365333971749, "percentage": 68.01, "elapsed_time": "4:58:46", "remaining_time": "2:20:33", "throughput": 6515.21, "total_tokens": 116797696} +{"current_steps": 356, "total_steps": 522, "loss": 0.032, "accuracy": 0.9921875, "lr": 4.754103173215313e-06, "epoch": 1.3600670337562843, "percentage": 68.2, "elapsed_time": "4:59:38", "remaining_time": "2:19:43", "throughput": 6515.7, "total_tokens": 117143072} +{"current_steps": 357, "total_steps": 522, "loss": 0.0435, "accuracy": 0.984375, "lr": 4.7019637531370535e-06, "epoch": 1.3638975341153938, "percentage": 68.39, "elapsed_time": "5:00:29", "remaining_time": "2:18:53", "throughput": 6516.48, "total_tokens": 117491008} +{"current_steps": 358, "total_steps": 522, "loss": 0.0273, "accuracy": 1.0, "lr": 4.65002380112903e-06, "epoch": 1.3677280344745033, "percentage": 68.58, "elapsed_time": "5:01:18", "remaining_time": "2:18:01", "throughput": 6516.81, "total_tokens": 117813952} +{"current_steps": 359, "total_steps": 522, "loss": 0.0153, "accuracy": 1.0, "lr": 4.598285272701072e-06, "epoch": 1.3715585348336126, "percentage": 68.77, "elapsed_time": "5:02:07", "remaining_time": "2:17:10", "throughput": 6517.41, "total_tokens": 118146592} +{"current_steps": 360, "total_steps": 522, "loss": 0.04, "accuracy": 0.9921875, "lr": 4.546750115779538e-06, "epoch": 1.375389035192722, "percentage": 68.97, "elapsed_time": "5:02:58", "remaining_time": "2:16:20", "throughput": 6517.15, "total_tokens": 118470272} +{"current_steps": 361, "total_steps": 522, "loss": 0.0323, "accuracy": 1.0, "lr": 4.495420270633954e-06, "epoch": 1.3792195355518315, "percentage": 69.16, "elapsed_time": "5:03:49", "remaining_time": "2:15:30", "throughput": 6517.59, "total_tokens": 118812064} +{"current_steps": 362, "total_steps": 522, "loss": 0.0598, "accuracy": 0.9765625, "lr": 4.444297669803981e-06, "epoch": 1.3830500359109408, "percentage": 69.35, "elapsed_time": "5:04:39", "remaining_time": "2:14:39", "throughput": 6517.62, "total_tokens": 119137728} +{"current_steps": 363, "total_steps": 522, "loss": 0.0313, "accuracy": 0.984375, "lr": 4.393384238026641e-06, "epoch": 1.3868805362700503, "percentage": 69.54, "elapsed_time": "5:05:30", "remaining_time": "2:13:49", "throughput": 6518.2, "total_tokens": 119481760} +{"current_steps": 364, "total_steps": 522, "loss": 0.0212, "accuracy": 1.0, "lr": 4.342681892163868e-06, "epoch": 1.3907110366291597, "percentage": 69.73, "elapsed_time": "5:06:21", "remaining_time": "2:12:58", "throughput": 6518.48, "total_tokens": 119816544} +{"current_steps": 365, "total_steps": 522, "loss": 0.0147, "accuracy": 1.0, "lr": 4.292192541130329e-06, "epoch": 1.3945415369882692, "percentage": 69.92, "elapsed_time": "5:07:11", "remaining_time": "2:12:08", "throughput": 6518.35, "total_tokens": 120142976} +{"current_steps": 366, "total_steps": 522, "loss": 0.0191, "accuracy": 1.0, "lr": 4.241918085821547e-06, "epoch": 1.3983720373473785, "percentage": 70.11, "elapsed_time": "5:08:03", "remaining_time": "2:11:18", "throughput": 6519.23, "total_tokens": 120496384} +{"current_steps": 367, "total_steps": 522, "loss": 0.0294, "accuracy": 0.984375, "lr": 4.191860419042356e-06, "epoch": 1.402202537706488, "percentage": 70.31, "elapsed_time": "5:08:52", "remaining_time": "2:10:26", "throughput": 6519.76, "total_tokens": 120825632} +{"current_steps": 368, "total_steps": 522, "loss": 0.0185, "accuracy": 1.0, "lr": 4.142021425435612e-06, "epoch": 1.4060330380655972, "percentage": 70.5, "elapsed_time": "5:09:43", "remaining_time": "2:09:36", "throughput": 6520.14, "total_tokens": 121165152} +{"current_steps": 369, "total_steps": 522, "loss": 0.062, "accuracy": 0.9765625, "lr": 4.09240298141126e-06, "epoch": 1.4098635384247067, "percentage": 70.69, "elapsed_time": "5:10:33", "remaining_time": "2:08:46", "throughput": 6520.11, "total_tokens": 121494080} +{"current_steps": 370, "total_steps": 522, "loss": 0.0261, "accuracy": 0.9921875, "lr": 4.043006955075667e-06, "epoch": 1.4136940387838162, "percentage": 70.88, "elapsed_time": "5:11:23", "remaining_time": "2:07:55", "throughput": 6520.57, "total_tokens": 121829184} +{"current_steps": 371, "total_steps": 522, "loss": 0.0431, "accuracy": 0.9765625, "lr": 3.993835206161313e-06, "epoch": 1.4175245391429256, "percentage": 71.07, "elapsed_time": "5:12:14", "remaining_time": "2:07:04", "throughput": 6521.03, "total_tokens": 122165280} +{"current_steps": 372, "total_steps": 522, "loss": 0.068, "accuracy": 0.9765625, "lr": 3.944889585956746e-06, "epoch": 1.421355039502035, "percentage": 71.26, "elapsed_time": "5:13:04", "remaining_time": "2:06:14", "throughput": 6521.37, "total_tokens": 122499680} +{"current_steps": 373, "total_steps": 522, "loss": 0.0305, "accuracy": 0.9921875, "lr": 3.896171937236904e-06, "epoch": 1.4251855398611444, "percentage": 71.46, "elapsed_time": "5:13:53", "remaining_time": "2:05:23", "throughput": 6522.37, "total_tokens": 122841312} +{"current_steps": 374, "total_steps": 522, "loss": 0.0275, "accuracy": 1.0, "lr": 3.847684094193733e-06, "epoch": 1.4290160402202536, "percentage": 71.65, "elapsed_time": "5:14:43", "remaining_time": "2:04:32", "throughput": 6522.59, "total_tokens": 123169600} +{"current_steps": 375, "total_steps": 522, "loss": 0.0235, "accuracy": 1.0, "lr": 3.7994278823671084e-06, "epoch": 1.4328465405793631, "percentage": 71.84, "elapsed_time": "5:15:32", "remaining_time": "2:03:41", "throughput": 6522.61, "total_tokens": 123486976} +{"current_steps": 376, "total_steps": 522, "loss": 0.0275, "accuracy": 1.0, "lr": 3.751405118576138e-06, "epoch": 1.4366770409384726, "percentage": 72.03, "elapsed_time": "5:16:27", "remaining_time": "2:02:52", "throughput": 6521.06, "total_tokens": 123817504} +{"current_steps": 377, "total_steps": 522, "loss": 0.0202, "accuracy": 1.0, "lr": 3.7036176108507295e-06, "epoch": 1.440507541297582, "percentage": 72.22, "elapsed_time": "5:17:17", "remaining_time": "2:02:02", "throughput": 6522.0, "total_tokens": 124161760} +{"current_steps": 378, "total_steps": 522, "loss": 0.029, "accuracy": 0.9921875, "lr": 3.6560671583635467e-06, "epoch": 1.4443380416566913, "percentage": 72.41, "elapsed_time": "5:18:08", "remaining_time": "2:01:11", "throughput": 6522.03, "total_tokens": 124495872} +{"current_steps": 379, "total_steps": 522, "loss": 0.031, "accuracy": 0.984375, "lr": 3.608755551362243e-06, "epoch": 1.4481685420158008, "percentage": 72.61, "elapsed_time": "5:18:57", "remaining_time": "2:00:20", "throughput": 6522.07, "total_tokens": 124816192} +{"current_steps": 380, "total_steps": 522, "loss": 0.0138, "accuracy": 1.0, "lr": 3.5616845711020876e-06, "epoch": 1.4519990423749103, "percentage": 72.8, "elapsed_time": "5:19:47", "remaining_time": "1:59:29", "throughput": 6522.69, "total_tokens": 125151904} +{"current_steps": 381, "total_steps": 522, "loss": 0.0158, "accuracy": 1.0, "lr": 3.514855989778876e-06, "epoch": 1.4558295427340195, "percentage": 72.99, "elapsed_time": "5:20:37", "remaining_time": "1:58:39", "throughput": 6523.28, "total_tokens": 125488480} +{"current_steps": 382, "total_steps": 522, "loss": 0.0133, "accuracy": 1.0, "lr": 3.468271570462235e-06, "epoch": 1.459660043093129, "percentage": 73.18, "elapsed_time": "5:21:28", "remaining_time": "1:57:48", "throughput": 6523.67, "total_tokens": 125830016} +{"current_steps": 383, "total_steps": 522, "loss": 0.0229, "accuracy": 1.0, "lr": 3.4219330670292137e-06, "epoch": 1.4634905434522385, "percentage": 73.37, "elapsed_time": "5:22:16", "remaining_time": "1:56:57", "throughput": 6523.84, "total_tokens": 126146784} +{"current_steps": 384, "total_steps": 522, "loss": 0.0217, "accuracy": 1.0, "lr": 3.3758422240982814e-06, "epoch": 1.467321043811348, "percentage": 73.56, "elapsed_time": "5:23:06", "remaining_time": "1:56:06", "throughput": 6524.13, "total_tokens": 126478176} +{"current_steps": 385, "total_steps": 522, "loss": 0.0208, "accuracy": 1.0, "lr": 3.3300007769636268e-06, "epoch": 1.4711515441704572, "percentage": 73.75, "elapsed_time": "5:23:56", "remaining_time": "1:55:16", "throughput": 6523.91, "total_tokens": 126804992} +{"current_steps": 386, "total_steps": 522, "loss": 0.0294, "accuracy": 0.984375, "lr": 3.284410451529816e-06, "epoch": 1.4749820445295667, "percentage": 73.95, "elapsed_time": "5:24:45", "remaining_time": "1:54:25", "throughput": 6524.15, "total_tokens": 127127552} +{"current_steps": 387, "total_steps": 522, "loss": 0.0379, "accuracy": 0.9765625, "lr": 3.239072964246842e-06, "epoch": 1.478812544888676, "percentage": 74.14, "elapsed_time": "5:25:36", "remaining_time": "1:53:34", "throughput": 6524.03, "total_tokens": 127454624} +{"current_steps": 388, "total_steps": 522, "loss": 0.012, "accuracy": 1.0, "lr": 3.19399002204547e-06, "epoch": 1.4826430452477855, "percentage": 74.33, "elapsed_time": "5:26:24", "remaining_time": "1:52:43", "throughput": 6524.33, "total_tokens": 127777664} +{"current_steps": 389, "total_steps": 522, "loss": 0.0492, "accuracy": 0.9765625, "lr": 3.149163322272998e-06, "epoch": 1.486473545606895, "percentage": 74.52, "elapsed_time": "5:27:16", "remaining_time": "1:51:53", "throughput": 6524.35, "total_tokens": 128114400} +{"current_steps": 390, "total_steps": 522, "loss": 0.05, "accuracy": 0.984375, "lr": 3.1045945526293307e-06, "epoch": 1.4903040459660044, "percentage": 74.71, "elapsed_time": "5:28:05", "remaining_time": "1:51:02", "throughput": 6525.07, "total_tokens": 128449920} +{"current_steps": 391, "total_steps": 522, "loss": 0.029, "accuracy": 0.9921875, "lr": 3.0602853911034623e-06, "epoch": 1.4941345463251137, "percentage": 74.9, "elapsed_time": "5:28:55", "remaining_time": "1:50:12", "throughput": 6525.14, "total_tokens": 128773984} +{"current_steps": 392, "total_steps": 522, "loss": 0.0183, "accuracy": 1.0, "lr": 3.016237505910272e-06, "epoch": 1.4979650466842231, "percentage": 75.1, "elapsed_time": "5:29:46", "remaining_time": "1:49:21", "throughput": 6524.62, "total_tokens": 129096640} +{"current_steps": 393, "total_steps": 522, "loss": 0.0362, "accuracy": 0.9921875, "lr": 2.9724525554277494e-06, "epoch": 1.5017955470433324, "percentage": 75.29, "elapsed_time": "5:30:35", "remaining_time": "1:48:30", "throughput": 6524.77, "total_tokens": 129422848} +{"current_steps": 394, "total_steps": 522, "loss": 0.0095, "accuracy": 1.0, "lr": 2.9289321881345257e-06, "epoch": 1.5056260474024419, "percentage": 75.48, "elapsed_time": "5:31:27", "remaining_time": "1:47:40", "throughput": 6524.67, "total_tokens": 129759776} +{"current_steps": 395, "total_steps": 522, "loss": 0.0573, "accuracy": 0.9765625, "lr": 2.8856780425478346e-06, "epoch": 1.5094565477615514, "percentage": 75.67, "elapsed_time": "5:32:18", "remaining_time": "1:46:50", "throughput": 6524.6, "total_tokens": 130088320} +{"current_steps": 396, "total_steps": 522, "loss": 0.0123, "accuracy": 1.0, "lr": 2.8426917471618144e-06, "epoch": 1.5132870481206608, "percentage": 75.86, "elapsed_time": "5:33:08", "remaining_time": "1:45:59", "throughput": 6524.51, "total_tokens": 130413568} +{"current_steps": 397, "total_steps": 522, "loss": 0.0404, "accuracy": 0.984375, "lr": 2.799974920386184e-06, "epoch": 1.5171175484797703, "percentage": 76.05, "elapsed_time": "5:33:57", "remaining_time": "1:45:09", "throughput": 6525.17, "total_tokens": 130750496} +{"current_steps": 398, "total_steps": 522, "loss": 0.0225, "accuracy": 0.9921875, "lr": 2.7575291704853325e-06, "epoch": 1.5209480488388796, "percentage": 76.25, "elapsed_time": "5:34:48", "remaining_time": "1:44:18", "throughput": 6525.3, "total_tokens": 131082080} +{"current_steps": 399, "total_steps": 522, "loss": 0.0198, "accuracy": 1.0, "lr": 2.7153560955177484e-06, "epoch": 1.5247785491979888, "percentage": 76.44, "elapsed_time": "5:35:36", "remaining_time": "1:43:27", "throughput": 6525.68, "total_tokens": 131404768} +{"current_steps": 400, "total_steps": 522, "loss": 0.0149, "accuracy": 1.0, "lr": 2.673457283275873e-06, "epoch": 1.5286090495570983, "percentage": 76.63, "elapsed_time": "5:36:26", "remaining_time": "1:42:36", "throughput": 6525.5, "total_tokens": 131727936} +{"current_steps": 401, "total_steps": 522, "loss": 0.0318, "accuracy": 0.9921875, "lr": 2.6318343112263014e-06, "epoch": 1.5324395499162078, "percentage": 76.82, "elapsed_time": "5:37:16", "remaining_time": "1:41:46", "throughput": 6525.55, "total_tokens": 132056608} +{"current_steps": 402, "total_steps": 522, "loss": 0.0165, "accuracy": 1.0, "lr": 2.5904887464504115e-06, "epoch": 1.5362700502753173, "percentage": 77.01, "elapsed_time": "5:38:07", "remaining_time": "1:40:55", "throughput": 6525.73, "total_tokens": 132391296} +{"current_steps": 403, "total_steps": 522, "loss": 0.0513, "accuracy": 0.984375, "lr": 2.5494221455853407e-06, "epoch": 1.5401005506344267, "percentage": 77.2, "elapsed_time": "5:38:59", "remaining_time": "1:40:05", "throughput": 6525.96, "total_tokens": 132735296} +{"current_steps": 404, "total_steps": 522, "loss": 0.0338, "accuracy": 0.984375, "lr": 2.5086360547654088e-06, "epoch": 1.543931050993536, "percentage": 77.39, "elapsed_time": "5:39:51", "remaining_time": "1:39:15", "throughput": 6525.83, "total_tokens": 133069568} +{"current_steps": 405, "total_steps": 522, "loss": 0.0227, "accuracy": 1.0, "lr": 2.4681320095638763e-06, "epoch": 1.5477615513526455, "percentage": 77.59, "elapsed_time": "5:40:43", "remaining_time": "1:38:25", "throughput": 6525.94, "total_tokens": 133409952} +{"current_steps": 406, "total_steps": 522, "loss": 0.0471, "accuracy": 0.9765625, "lr": 2.4279115349351546e-06, "epoch": 1.5515920517117547, "percentage": 77.78, "elapsed_time": "5:41:34", "remaining_time": "1:37:35", "throughput": 6526.42, "total_tokens": 133752672} +{"current_steps": 407, "total_steps": 522, "loss": 0.0154, "accuracy": 1.0, "lr": 2.3879761451573834e-06, "epoch": 1.5554225520708642, "percentage": 77.97, "elapsed_time": "5:42:23", "remaining_time": "1:36:44", "throughput": 6527.05, "total_tokens": 134090848} +{"current_steps": 408, "total_steps": 522, "loss": 0.0217, "accuracy": 1.0, "lr": 2.3483273437754106e-06, "epoch": 1.5592530524299737, "percentage": 78.16, "elapsed_time": "5:43:12", "remaining_time": "1:35:53", "throughput": 6527.21, "total_tokens": 134410240} +{"current_steps": 409, "total_steps": 522, "loss": 0.0414, "accuracy": 0.984375, "lr": 2.3089666235442055e-06, "epoch": 1.5630835527890832, "percentage": 78.35, "elapsed_time": "5:44:02", "remaining_time": "1:35:03", "throughput": 6527.78, "total_tokens": 134747712} +{"current_steps": 410, "total_steps": 522, "loss": 0.0374, "accuracy": 0.984375, "lr": 2.26989546637263e-06, "epoch": 1.5669140531481924, "percentage": 78.54, "elapsed_time": "5:44:50", "remaining_time": "1:34:12", "throughput": 6527.98, "total_tokens": 135069120} +{"current_steps": 411, "total_steps": 522, "loss": 0.0452, "accuracy": 0.9765625, "lr": 2.231115343267677e-06, "epoch": 1.570744553507302, "percentage": 78.74, "elapsed_time": "5:45:38", "remaining_time": "1:33:21", "throughput": 6528.32, "total_tokens": 135390720} +{"current_steps": 412, "total_steps": 522, "loss": 0.0385, "accuracy": 0.984375, "lr": 2.1926277142790554e-06, "epoch": 1.5745750538664112, "percentage": 78.93, "elapsed_time": "5:46:29", "remaining_time": "1:32:30", "throughput": 6528.32, "total_tokens": 135723456} +{"current_steps": 413, "total_steps": 522, "loss": 0.0118, "accuracy": 1.0, "lr": 2.15443402844425e-06, "epoch": 1.5784055542255206, "percentage": 79.12, "elapsed_time": "5:47:18", "remaining_time": "1:31:39", "throughput": 6528.64, "total_tokens": 136044576} +{"current_steps": 414, "total_steps": 522, "loss": 0.0238, "accuracy": 0.9921875, "lr": 2.116535723733938e-06, "epoch": 1.5822360545846301, "percentage": 79.31, "elapsed_time": "5:48:07", "remaining_time": "1:30:48", "throughput": 6529.12, "total_tokens": 136378048} +{"current_steps": 415, "total_steps": 522, "loss": 0.0221, "accuracy": 0.9921875, "lr": 2.0789342269978785e-06, "epoch": 1.5860665549437396, "percentage": 79.5, "elapsed_time": "5:48:55", "remaining_time": "1:29:57", "throughput": 6529.55, "total_tokens": 136698144} +{"current_steps": 416, "total_steps": 522, "loss": 0.0165, "accuracy": 1.0, "lr": 2.0416309539111656e-06, "epoch": 1.589897055302849, "percentage": 79.69, "elapsed_time": "5:49:46", "remaining_time": "1:29:07", "throughput": 6529.7, "total_tokens": 137033856} +{"current_steps": 417, "total_steps": 522, "loss": 0.0306, "accuracy": 0.9921875, "lr": 2.004627308920949e-06, "epoch": 1.5937275556619583, "percentage": 79.89, "elapsed_time": "5:50:36", "remaining_time": "1:28:17", "throughput": 6530.18, "total_tokens": 137373344} +{"current_steps": 418, "total_steps": 522, "loss": 0.0298, "accuracy": 0.9921875, "lr": 1.967924685193552e-06, "epoch": 1.5975580560210676, "percentage": 80.08, "elapsed_time": "5:51:25", "remaining_time": "1:27:26", "throughput": 6530.67, "total_tokens": 137703808} +{"current_steps": 419, "total_steps": 522, "loss": 0.051, "accuracy": 0.984375, "lr": 1.9315244645620066e-06, "epoch": 1.601388556380177, "percentage": 80.27, "elapsed_time": "5:52:15", "remaining_time": "1:26:35", "throughput": 6530.99, "total_tokens": 138037472} +{"current_steps": 420, "total_steps": 522, "loss": 0.0216, "accuracy": 1.0, "lr": 1.8954280174740536e-06, "epoch": 1.6052190567392866, "percentage": 80.46, "elapsed_time": "5:53:06", "remaining_time": "1:25:45", "throughput": 6531.12, "total_tokens": 138371904} +{"current_steps": 421, "total_steps": 522, "loss": 0.033, "accuracy": 0.9765625, "lr": 1.859636702940516e-06, "epoch": 1.609049557098396, "percentage": 80.65, "elapsed_time": "5:53:54", "remaining_time": "1:24:54", "throughput": 6531.33, "total_tokens": 138686880} +{"current_steps": 422, "total_steps": 522, "loss": 0.0167, "accuracy": 1.0, "lr": 1.8241518684841642e-06, "epoch": 1.6128800574575055, "percentage": 80.84, "elapsed_time": "5:54:43", "remaining_time": "1:24:03", "throughput": 6531.47, "total_tokens": 139010656} +{"current_steps": 423, "total_steps": 522, "loss": 0.0122, "accuracy": 1.0, "lr": 1.7889748500889537e-06, "epoch": 1.6167105578166148, "percentage": 81.03, "elapsed_time": "5:55:33", "remaining_time": "1:23:12", "throughput": 6531.49, "total_tokens": 139338848} +{"current_steps": 424, "total_steps": 522, "loss": 0.0177, "accuracy": 1.0, "lr": 1.7541069721497494e-06, "epoch": 1.6205410581757242, "percentage": 81.23, "elapsed_time": "5:56:23", "remaining_time": "1:22:22", "throughput": 6531.85, "total_tokens": 139674496} +{"current_steps": 425, "total_steps": 522, "loss": 0.0169, "accuracy": 1.0, "lr": 1.7195495474224433e-06, "epoch": 1.6243715585348335, "percentage": 81.42, "elapsed_time": "5:57:12", "remaining_time": "1:21:31", "throughput": 6532.06, "total_tokens": 139998272} +{"current_steps": 426, "total_steps": 522, "loss": 0.0388, "accuracy": 0.9921875, "lr": 1.6853038769745466e-06, "epoch": 1.628202058893943, "percentage": 81.61, "elapsed_time": "5:58:02", "remaining_time": "1:20:41", "throughput": 6532.43, "total_tokens": 140330400} +{"current_steps": 427, "total_steps": 522, "loss": 0.0308, "accuracy": 0.9921875, "lr": 1.6513712501362e-06, "epoch": 1.6320325592530525, "percentage": 81.8, "elapsed_time": "5:58:53", "remaining_time": "1:19:50", "throughput": 6532.06, "total_tokens": 140656416} +{"current_steps": 428, "total_steps": 522, "loss": 0.0426, "accuracy": 0.984375, "lr": 1.6177529444516193e-06, "epoch": 1.635863059612162, "percentage": 81.99, "elapsed_time": "5:59:43", "remaining_time": "1:19:00", "throughput": 6531.82, "total_tokens": 140977472} +{"current_steps": 429, "total_steps": 522, "loss": 0.0115, "accuracy": 1.0, "lr": 1.5844502256310169e-06, "epoch": 1.6396935599712712, "percentage": 82.18, "elapsed_time": "6:00:31", "remaining_time": "1:18:09", "throughput": 6532.18, "total_tokens": 141300224} +{"current_steps": 430, "total_steps": 522, "loss": 0.0276, "accuracy": 0.984375, "lr": 1.551464347502929e-06, "epoch": 1.6435240603303807, "percentage": 82.38, "elapsed_time": "6:01:20", "remaining_time": "1:17:18", "throughput": 6532.55, "total_tokens": 141631616} +{"current_steps": 431, "total_steps": 522, "loss": 0.0277, "accuracy": 0.9921875, "lr": 1.518796551967029e-06, "epoch": 1.64735456068949, "percentage": 82.57, "elapsed_time": "6:02:10", "remaining_time": "1:16:28", "throughput": 6532.27, "total_tokens": 141948576} +{"current_steps": 432, "total_steps": 522, "loss": 0.0403, "accuracy": 0.9921875, "lr": 1.486448068947348e-06, "epoch": 1.6511850610485994, "percentage": 82.76, "elapsed_time": "6:03:00", "remaining_time": "1:15:37", "throughput": 6532.26, "total_tokens": 142276928} +{"current_steps": 433, "total_steps": 522, "loss": 0.0323, "accuracy": 0.9921875, "lr": 1.454420116345996e-06, "epoch": 1.655015561407709, "percentage": 82.95, "elapsed_time": "6:03:50", "remaining_time": "1:14:47", "throughput": 6532.44, "total_tokens": 142609120} +{"current_steps": 434, "total_steps": 522, "loss": 0.0116, "accuracy": 1.0, "lr": 1.4227138999972801e-06, "epoch": 1.6588460617668184, "percentage": 83.14, "elapsed_time": "6:04:40", "remaining_time": "1:13:56", "throughput": 6532.56, "total_tokens": 142934048} +{"current_steps": 435, "total_steps": 522, "loss": 0.0277, "accuracy": 0.984375, "lr": 1.3913306136223292e-06, "epoch": 1.6626765621259278, "percentage": 83.33, "elapsed_time": "6:05:30", "remaining_time": "1:13:06", "throughput": 6532.88, "total_tokens": 143271200} +{"current_steps": 436, "total_steps": 522, "loss": 0.0194, "accuracy": 1.0, "lr": 1.3602714387841332e-06, "epoch": 1.666507062485037, "percentage": 83.52, "elapsed_time": "6:06:22", "remaining_time": "1:12:15", "throughput": 6533.29, "total_tokens": 143614752} +{"current_steps": 437, "total_steps": 522, "loss": 0.0195, "accuracy": 1.0, "lr": 1.3295375448430726e-06, "epoch": 1.6703375628441464, "percentage": 83.72, "elapsed_time": "6:07:11", "remaining_time": "1:11:25", "throughput": 6533.63, "total_tokens": 143946976} +{"current_steps": 438, "total_steps": 522, "loss": 0.0204, "accuracy": 1.0, "lr": 1.2991300889128867e-06, "epoch": 1.6741680632032558, "percentage": 83.91, "elapsed_time": "6:08:00", "remaining_time": "1:10:34", "throughput": 6534.18, "total_tokens": 144278144} +{"current_steps": 439, "total_steps": 522, "loss": 0.0351, "accuracy": 0.984375, "lr": 1.2690502158170992e-06, "epoch": 1.6779985635623653, "percentage": 84.1, "elapsed_time": "6:08:50", "remaining_time": "1:09:44", "throughput": 6534.22, "total_tokens": 144604384} +{"current_steps": 440, "total_steps": 522, "loss": 0.0152, "accuracy": 1.0, "lr": 1.2392990580459351e-06, "epoch": 1.6818290639214748, "percentage": 84.29, "elapsed_time": "6:09:38", "remaining_time": "1:08:53", "throughput": 6534.18, "total_tokens": 144917728} +{"current_steps": 441, "total_steps": 522, "loss": 0.0194, "accuracy": 1.0, "lr": 1.209877735713665e-06, "epoch": 1.6856595642805843, "percentage": 84.48, "elapsed_time": "6:10:26", "remaining_time": "1:08:02", "throughput": 6534.4, "total_tokens": 145238176} +{"current_steps": 442, "total_steps": 522, "loss": 0.0194, "accuracy": 0.9921875, "lr": 1.1807873565164507e-06, "epoch": 1.6894900646396935, "percentage": 84.67, "elapsed_time": "6:11:16", "remaining_time": "1:07:11", "throughput": 6534.5, "total_tokens": 145564160} +{"current_steps": 443, "total_steps": 522, "loss": 0.0283, "accuracy": 0.9921875, "lr": 1.1520290156906222e-06, "epoch": 1.693320564998803, "percentage": 84.87, "elapsed_time": "6:12:03", "remaining_time": "1:06:21", "throughput": 6535.22, "total_tokens": 145891296} +{"current_steps": 444, "total_steps": 522, "loss": 0.0309, "accuracy": 0.9921875, "lr": 1.123603795971462e-06, "epoch": 1.6971510653579123, "percentage": 85.06, "elapsed_time": "6:12:53", "remaining_time": "1:05:30", "throughput": 6535.25, "total_tokens": 146218944} +{"current_steps": 445, "total_steps": 522, "loss": 0.0357, "accuracy": 0.9921875, "lr": 1.0955127675524213e-06, "epoch": 1.7009815657170217, "percentage": 85.25, "elapsed_time": "6:13:44", "remaining_time": "1:04:40", "throughput": 6535.77, "total_tokens": 146564320} +{"current_steps": 446, "total_steps": 522, "loss": 0.0204, "accuracy": 1.0, "lr": 1.0677569880448479e-06, "epoch": 1.7048120660761312, "percentage": 85.44, "elapsed_time": "6:14:36", "remaining_time": "1:03:50", "throughput": 6535.73, "total_tokens": 146901120} +{"current_steps": 447, "total_steps": 522, "loss": 0.0188, "accuracy": 1.0, "lr": 1.040337502438149e-06, "epoch": 1.7086425664352407, "percentage": 85.63, "elapsed_time": "6:15:26", "remaining_time": "1:02:59", "throughput": 6535.71, "total_tokens": 147228736} +{"current_steps": 448, "total_steps": 522, "loss": 0.0211, "accuracy": 1.0, "lr": 1.0132553430604608e-06, "epoch": 1.71247306679435, "percentage": 85.82, "elapsed_time": "6:16:15", "remaining_time": "1:02:09", "throughput": 6535.82, "total_tokens": 147550528} +{"current_steps": 449, "total_steps": 522, "loss": 0.0488, "accuracy": 0.984375, "lr": 9.865115295397808e-07, "epoch": 1.7163035671534594, "percentage": 86.02, "elapsed_time": "6:17:04", "remaining_time": "1:01:18", "throughput": 6536.44, "total_tokens": 147885792} +{"current_steps": 450, "total_steps": 522, "loss": 0.0306, "accuracy": 0.984375, "lr": 9.601070687655667e-07, "epoch": 1.7201340675125687, "percentage": 86.21, "elapsed_time": "6:17:53", "remaining_time": "1:00:27", "throughput": 6536.93, "total_tokens": 148214848} +{"current_steps": 451, "total_steps": 522, "loss": 0.0279, "accuracy": 1.0, "lr": 9.340429548508468e-07, "epoch": 1.7239645678716782, "percentage": 86.4, "elapsed_time": "6:18:42", "remaining_time": "0:59:37", "throughput": 6537.15, "total_tokens": 148543616} +{"current_steps": 452, "total_steps": 522, "loss": 0.0249, "accuracy": 1.0, "lr": 9.083201690947763e-07, "epoch": 1.7277950682307877, "percentage": 86.59, "elapsed_time": "6:19:32", "remaining_time": "0:58:46", "throughput": 6537.29, "total_tokens": 148872672} +{"current_steps": 453, "total_steps": 522, "loss": 0.0223, "accuracy": 0.9921875, "lr": 8.829396799457024e-07, "epoch": 1.7316255685898971, "percentage": 86.78, "elapsed_time": "6:20:21", "remaining_time": "0:57:56", "throughput": 6537.59, "total_tokens": 149199488} +{"current_steps": 454, "total_steps": 522, "loss": 0.0259, "accuracy": 0.9921875, "lr": 8.579024429646932e-07, "epoch": 1.7354560689490066, "percentage": 86.97, "elapsed_time": "6:21:12", "remaining_time": "0:57:05", "throughput": 6537.7, "total_tokens": 149535552} +{"current_steps": 455, "total_steps": 522, "loss": 0.0268, "accuracy": 0.9921875, "lr": 8.332094007895742e-07, "epoch": 1.7392865693081159, "percentage": 87.16, "elapsed_time": "6:22:01", "remaining_time": "0:56:15", "throughput": 6538.0, "total_tokens": 149863552} +{"current_steps": 456, "total_steps": 522, "loss": 0.0178, "accuracy": 1.0, "lr": 8.088614830994223e-07, "epoch": 1.7431170696672251, "percentage": 87.36, "elapsed_time": "6:22:51", "remaining_time": "0:55:24", "throughput": 6538.16, "total_tokens": 150189216} +{"current_steps": 457, "total_steps": 522, "loss": 0.019, "accuracy": 1.0, "lr": 7.848596065795822e-07, "epoch": 1.7469475700263346, "percentage": 87.55, "elapsed_time": "6:23:40", "remaining_time": "0:54:34", "throughput": 6538.46, "total_tokens": 150520128} +{"current_steps": 458, "total_steps": 522, "loss": 0.0262, "accuracy": 0.9921875, "lr": 7.612046748871327e-07, "epoch": 1.750778070385444, "percentage": 87.74, "elapsed_time": "6:24:29", "remaining_time": "0:53:43", "throughput": 6538.73, "total_tokens": 150842400} +{"current_steps": 459, "total_steps": 522, "loss": 0.0136, "accuracy": 1.0, "lr": 7.378975786168862e-07, "epoch": 1.7546085707445536, "percentage": 87.93, "elapsed_time": "6:25:15", "remaining_time": "0:52:52", "throughput": 6538.98, "total_tokens": 151153632} +{"current_steps": 460, "total_steps": 522, "loss": 0.0177, "accuracy": 0.9921875, "lr": 7.149391952678453e-07, "epoch": 1.758439071103663, "percentage": 88.12, "elapsed_time": "6:26:04", "remaining_time": "0:52:02", "throughput": 6539.3, "total_tokens": 151481120} +{"current_steps": 461, "total_steps": 522, "loss": 0.0293, "accuracy": 1.0, "lr": 6.923303892101629e-07, "epoch": 1.7622695714627723, "percentage": 88.31, "elapsed_time": "6:26:54", "remaining_time": "0:51:11", "throughput": 6539.68, "total_tokens": 151812512} +{"current_steps": 462, "total_steps": 522, "loss": 0.0318, "accuracy": 0.9921875, "lr": 6.700720116526116e-07, "epoch": 1.7661000718218818, "percentage": 88.51, "elapsed_time": "6:27:43", "remaining_time": "0:50:21", "throughput": 6539.93, "total_tokens": 152140000} +{"current_steps": 463, "total_steps": 522, "loss": 0.0206, "accuracy": 1.0, "lr": 6.481649006105239e-07, "epoch": 1.769930572180991, "percentage": 88.7, "elapsed_time": "6:28:31", "remaining_time": "0:49:30", "throughput": 6540.2, "total_tokens": 152463584} +{"current_steps": 464, "total_steps": 522, "loss": 0.0256, "accuracy": 0.9921875, "lr": 6.266098808742515e-07, "epoch": 1.7737610725401005, "percentage": 88.89, "elapsed_time": "6:29:20", "remaining_time": "0:48:40", "throughput": 6540.57, "total_tokens": 152791584} +{"current_steps": 465, "total_steps": 522, "loss": 0.0178, "accuracy": 1.0, "lr": 6.054077639781009e-07, "epoch": 1.77759157289921, "percentage": 89.08, "elapsed_time": "6:30:10", "remaining_time": "0:47:49", "throughput": 6540.76, "total_tokens": 153119264} +{"current_steps": 466, "total_steps": 522, "loss": 0.046, "accuracy": 0.9765625, "lr": 5.845593481697931e-07, "epoch": 1.7814220732583195, "percentage": 89.27, "elapsed_time": "6:30:57", "remaining_time": "0:46:58", "throughput": 6540.64, "total_tokens": 153430272} +{"current_steps": 467, "total_steps": 522, "loss": 0.0186, "accuracy": 1.0, "lr": 5.640654183803962e-07, "epoch": 1.7852525736174287, "percentage": 89.46, "elapsed_time": "6:31:46", "remaining_time": "0:46:08", "throughput": 6540.81, "total_tokens": 153752128} +{"current_steps": 468, "total_steps": 522, "loss": 0.0117, "accuracy": 1.0, "lr": 5.439267461947884e-07, "epoch": 1.7890830739765382, "percentage": 89.66, "elapsed_time": "6:32:37", "remaining_time": "0:45:18", "throughput": 6541.02, "total_tokens": 154088384} +{"current_steps": 469, "total_steps": 522, "loss": 0.0198, "accuracy": 1.0, "lr": 5.241440898225891e-07, "epoch": 1.7929135743356475, "percentage": 89.85, "elapsed_time": "6:33:26", "remaining_time": "0:44:27", "throughput": 6541.51, "total_tokens": 154422560} +{"current_steps": 470, "total_steps": 522, "loss": 0.0242, "accuracy": 0.9921875, "lr": 5.047181940696333e-07, "epoch": 1.796744074694757, "percentage": 90.04, "elapsed_time": "6:34:16", "remaining_time": "0:43:37", "throughput": 6542.17, "total_tokens": 154766336} +{"current_steps": 471, "total_steps": 522, "loss": 0.0205, "accuracy": 0.9921875, "lr": 4.856497903099167e-07, "epoch": 1.8005745750538664, "percentage": 90.23, "elapsed_time": "6:35:06", "remaining_time": "0:42:46", "throughput": 6542.24, "total_tokens": 155091648} +{"current_steps": 472, "total_steps": 522, "loss": 0.0211, "accuracy": 0.9921875, "lr": 4.6693959645806143e-07, "epoch": 1.804405075412976, "percentage": 90.42, "elapsed_time": "6:35:55", "remaining_time": "0:41:56", "throughput": 6542.53, "total_tokens": 155418336} +{"current_steps": 473, "total_steps": 522, "loss": 0.0218, "accuracy": 0.9921875, "lr": 4.4858831694229334e-07, "epoch": 1.8082355757720854, "percentage": 90.61, "elapsed_time": "6:36:43", "remaining_time": "0:41:05", "throughput": 6542.52, "total_tokens": 155737088} +{"current_steps": 474, "total_steps": 522, "loss": 0.0385, "accuracy": 0.984375, "lr": 4.305966426779118e-07, "epoch": 1.8120660761311946, "percentage": 90.8, "elapsed_time": "6:37:32", "remaining_time": "0:40:15", "throughput": 6542.79, "total_tokens": 156064512} +{"current_steps": 475, "total_steps": 522, "loss": 0.058, "accuracy": 0.984375, "lr": 4.1296525104128513e-07, "epoch": 1.815896576490304, "percentage": 91.0, "elapsed_time": "6:38:21", "remaining_time": "0:39:25", "throughput": 6543.36, "total_tokens": 156397152} +{"current_steps": 476, "total_steps": 522, "loss": 0.032, "accuracy": 0.9921875, "lr": 3.9569480584434217e-07, "epoch": 1.8197270768494134, "percentage": 91.19, "elapsed_time": "6:39:10", "remaining_time": "0:38:34", "throughput": 6544.03, "total_tokens": 156730688} +{"current_steps": 477, "total_steps": 522, "loss": 0.0376, "accuracy": 0.9921875, "lr": 3.787859573095853e-07, "epoch": 1.8235575772085229, "percentage": 91.38, "elapsed_time": "6:39:58", "remaining_time": "0:37:44", "throughput": 6544.26, "total_tokens": 157051776} +{"current_steps": 478, "total_steps": 522, "loss": 0.0275, "accuracy": 0.9921875, "lr": 3.6223934204560165e-07, "epoch": 1.8273880775676323, "percentage": 91.57, "elapsed_time": "6:40:48", "remaining_time": "0:36:53", "throughput": 6544.71, "total_tokens": 157388704} +{"current_steps": 479, "total_steps": 522, "loss": 0.019, "accuracy": 1.0, "lr": 3.4605558302310715e-07, "epoch": 1.8312185779267418, "percentage": 91.76, "elapsed_time": "6:41:37", "remaining_time": "0:36:03", "throughput": 6545.18, "total_tokens": 157725120} +{"current_steps": 480, "total_steps": 522, "loss": 0.0435, "accuracy": 0.984375, "lr": 3.302352895514793e-07, "epoch": 1.835049078285851, "percentage": 91.95, "elapsed_time": "6:42:27", "remaining_time": "0:35:12", "throughput": 6545.37, "total_tokens": 158054944} +{"current_steps": 481, "total_steps": 522, "loss": 0.0168, "accuracy": 1.0, "lr": 3.147790572558262e-07, "epoch": 1.8388795786449605, "percentage": 92.15, "elapsed_time": "6:43:16", "remaining_time": "0:34:22", "throughput": 6545.57, "total_tokens": 158379936} +{"current_steps": 482, "total_steps": 522, "loss": 0.0216, "accuracy": 1.0, "lr": 2.996874680545603e-07, "epoch": 1.8427100790040698, "percentage": 92.34, "elapsed_time": "6:44:04", "remaining_time": "0:33:31", "throughput": 6545.65, "total_tokens": 158694752} +{"current_steps": 483, "total_steps": 522, "loss": 0.0136, "accuracy": 1.0, "lr": 2.849610901374822e-07, "epoch": 1.8465405793631793, "percentage": 92.53, "elapsed_time": "6:44:55", "remaining_time": "0:32:41", "throughput": 6545.72, "total_tokens": 159033856} +{"current_steps": 484, "total_steps": 522, "loss": 0.0147, "accuracy": 1.0, "lr": 2.7060047794439937e-07, "epoch": 1.8503710797222888, "percentage": 92.72, "elapsed_time": "6:45:45", "remaining_time": "0:31:51", "throughput": 6545.9, "total_tokens": 159362944} +{"current_steps": 485, "total_steps": 522, "loss": 0.0225, "accuracy": 1.0, "lr": 2.5660617214424146e-07, "epoch": 1.8542015800813982, "percentage": 92.91, "elapsed_time": "6:46:35", "remaining_time": "0:31:01", "throughput": 6546.03, "total_tokens": 159694496} +{"current_steps": 486, "total_steps": 522, "loss": 0.039, "accuracy": 0.9921875, "lr": 2.4297869961471544e-07, "epoch": 1.8580320804405075, "percentage": 93.1, "elapsed_time": "6:47:27", "remaining_time": "0:30:10", "throughput": 6546.12, "total_tokens": 160038496} +{"current_steps": 487, "total_steps": 522, "loss": 0.0283, "accuracy": 0.9921875, "lr": 2.2971857342245607e-07, "epoch": 1.861862580799617, "percentage": 93.3, "elapsed_time": "6:48:17", "remaining_time": "0:29:20", "throughput": 6546.6, "total_tokens": 160378176} +{"current_steps": 488, "total_steps": 522, "loss": 0.0196, "accuracy": 1.0, "lr": 2.168262928037246e-07, "epoch": 1.8656930811587262, "percentage": 93.49, "elapsed_time": "6:49:07", "remaining_time": "0:28:30", "throughput": 6546.79, "total_tokens": 160710144} +{"current_steps": 489, "total_steps": 522, "loss": 0.0245, "accuracy": 1.0, "lr": 2.0430234314559482e-07, "epoch": 1.8695235815178357, "percentage": 93.68, "elapsed_time": "6:49:57", "remaining_time": "0:27:39", "throughput": 6547.05, "total_tokens": 161039680} +{"current_steps": 490, "total_steps": 522, "loss": 0.0382, "accuracy": 0.9921875, "lr": 1.921471959676957e-07, "epoch": 1.8733540818769452, "percentage": 93.87, "elapsed_time": "6:50:46", "remaining_time": "0:26:49", "throughput": 6547.22, "total_tokens": 161366240} +{"current_steps": 491, "total_steps": 522, "loss": 0.0211, "accuracy": 0.9921875, "lr": 1.8036130890444758e-07, "epoch": 1.8771845822360547, "percentage": 94.06, "elapsed_time": "6:51:34", "remaining_time": "0:25:59", "throughput": 6547.3, "total_tokens": 161682880} +{"current_steps": 492, "total_steps": 522, "loss": 0.0162, "accuracy": 1.0, "lr": 1.6894512568783717e-07, "epoch": 1.8810150825951641, "percentage": 94.25, "elapsed_time": "6:52:22", "remaining_time": "0:25:08", "throughput": 6547.45, "total_tokens": 162003520} +{"current_steps": 493, "total_steps": 522, "loss": 0.0506, "accuracy": 0.984375, "lr": 1.5789907613070977e-07, "epoch": 1.8848455829542734, "percentage": 94.44, "elapsed_time": "6:53:13", "remaining_time": "0:24:18", "throughput": 6547.75, "total_tokens": 162340448} +{"current_steps": 494, "total_steps": 522, "loss": 0.0138, "accuracy": 1.0, "lr": 1.472235761105878e-07, "epoch": 1.8886760833133827, "percentage": 94.64, "elapsed_time": "6:54:02", "remaining_time": "0:23:28", "throughput": 6547.74, "total_tokens": 162661088} +{"current_steps": 495, "total_steps": 522, "loss": 0.0203, "accuracy": 0.9921875, "lr": 1.3691902755401442e-07, "epoch": 1.8925065836724921, "percentage": 94.83, "elapsed_time": "6:54:51", "remaining_time": "0:22:37", "throughput": 6548.17, "total_tokens": 162992512} +{"current_steps": 496, "total_steps": 522, "loss": 0.0212, "accuracy": 1.0, "lr": 1.2698581842141567e-07, "epoch": 1.8963370840316016, "percentage": 95.02, "elapsed_time": "6:55:40", "remaining_time": "0:21:47", "throughput": 6548.56, "total_tokens": 163324864} +{"current_steps": 497, "total_steps": 522, "loss": 0.018, "accuracy": 0.9921875, "lr": 1.1742432269250536e-07, "epoch": 1.900167584390711, "percentage": 95.21, "elapsed_time": "6:56:30", "remaining_time": "0:20:57", "throughput": 6549.1, "total_tokens": 163662144} +{"current_steps": 498, "total_steps": 522, "loss": 0.0114, "accuracy": 1.0, "lr": 1.0823490035218986e-07, "epoch": 1.9039980847498206, "percentage": 95.4, "elapsed_time": "6:57:18", "remaining_time": "0:20:06", "throughput": 6549.51, "total_tokens": 163988064} +{"current_steps": 499, "total_steps": 522, "loss": 0.0214, "accuracy": 1.0, "lr": 9.94178973770299e-08, "epoch": 1.9078285851089298, "percentage": 95.59, "elapsed_time": "6:58:07", "remaining_time": "0:19:16", "throughput": 6550.23, "total_tokens": 164331552} +{"current_steps": 500, "total_steps": 522, "loss": 0.0408, "accuracy": 0.984375, "lr": 9.09736457221999e-08, "epoch": 1.9116590854680393, "percentage": 95.79, "elapsed_time": "6:58:57", "remaining_time": "0:18:26", "throughput": 6550.25, "total_tokens": 164657472} +{"current_steps": 501, "total_steps": 522, "loss": 0.0288, "accuracy": 1.0, "lr": 8.290246330900475e-08, "epoch": 1.9154895858271486, "percentage": 95.98, "elapsed_time": "6:59:46", "remaining_time": "0:17:35", "throughput": 6550.31, "total_tokens": 164976896} +{"current_steps": 502, "total_steps": 522, "loss": 0.0381, "accuracy": 0.9921875, "lr": 7.520465401290033e-08, "epoch": 1.919320086186258, "percentage": 96.17, "elapsed_time": "7:00:35", "remaining_time": "0:16:45", "throughput": 6550.65, "total_tokens": 165307264} +{"current_steps": 503, "total_steps": 522, "loss": 0.0199, "accuracy": 1.0, "lr": 6.788050765205501e-08, "epoch": 1.9231505865453675, "percentage": 96.36, "elapsed_time": "7:01:25", "remaining_time": "0:15:55", "throughput": 6550.93, "total_tokens": 165644416} +{"current_steps": 504, "total_steps": 522, "loss": 0.0407, "accuracy": 0.9765625, "lr": 6.09302999764394e-08, "epoch": 1.926981086904477, "percentage": 96.55, "elapsed_time": "7:02:14", "remaining_time": "0:15:04", "throughput": 6551.41, "total_tokens": 165977312} +{"current_steps": 505, "total_steps": 522, "loss": 0.013, "accuracy": 1.0, "lr": 5.435429265744585e-08, "epoch": 1.9308115872635863, "percentage": 96.74, "elapsed_time": "7:03:09", "remaining_time": "0:14:14", "throughput": 6550.3, "total_tokens": 166309056} +{"current_steps": 506, "total_steps": 522, "loss": 0.0373, "accuracy": 0.984375, "lr": 4.815273327803183e-08, "epoch": 1.9346420876226957, "percentage": 96.93, "elapsed_time": "7:04:01", "remaining_time": "0:13:24", "throughput": 6549.92, "total_tokens": 166639520} +{"current_steps": 507, "total_steps": 522, "loss": 0.0196, "accuracy": 1.0, "lr": 4.232585532340183e-08, "epoch": 1.938472587981805, "percentage": 97.13, "elapsed_time": "7:04:51", "remaining_time": "0:12:34", "throughput": 6550.22, "total_tokens": 166975296} +{"current_steps": 508, "total_steps": 522, "loss": 0.0556, "accuracy": 0.96875, "lr": 3.687387817221999e-08, "epoch": 1.9423030883409145, "percentage": 97.32, "elapsed_time": "7:05:40", "remaining_time": "0:11:43", "throughput": 6550.43, "total_tokens": 167301664} +{"current_steps": 509, "total_steps": 522, "loss": 0.0157, "accuracy": 1.0, "lr": 3.179700708834332e-08, "epoch": 1.946133588700024, "percentage": 97.51, "elapsed_time": "7:06:30", "remaining_time": "0:10:53", "throughput": 6550.7, "total_tokens": 167634208} +{"current_steps": 510, "total_steps": 522, "loss": 0.0187, "accuracy": 1.0, "lr": 2.7095433213097933e-08, "epoch": 1.9499640890591334, "percentage": 97.7, "elapsed_time": "7:07:19", "remaining_time": "0:10:03", "throughput": 6551.12, "total_tokens": 167967168} +{"current_steps": 511, "total_steps": 522, "loss": 0.0442, "accuracy": 0.9921875, "lr": 2.276933355808364e-08, "epoch": 1.953794589418243, "percentage": 97.89, "elapsed_time": "7:08:09", "remaining_time": "0:09:13", "throughput": 6551.43, "total_tokens": 168302656} +{"current_steps": 512, "total_steps": 522, "loss": 0.0336, "accuracy": 0.9765625, "lr": 1.881887099850821e-08, "epoch": 1.9576250897773522, "percentage": 98.08, "elapsed_time": "7:09:00", "remaining_time": "0:08:22", "throughput": 6551.43, "total_tokens": 168639648} +{"current_steps": 513, "total_steps": 522, "loss": 0.0215, "accuracy": 1.0, "lr": 1.524419426705226e-08, "epoch": 1.9614555901364614, "percentage": 98.28, "elapsed_time": "7:09:48", "remaining_time": "0:07:32", "throughput": 6551.93, "total_tokens": 168967520} +{"current_steps": 514, "total_steps": 522, "loss": 0.0333, "accuracy": 0.984375, "lr": 1.2045437948275952e-08, "epoch": 1.965286090495571, "percentage": 98.47, "elapsed_time": "7:10:38", "remaining_time": "0:06:42", "throughput": 6552.19, "total_tokens": 169297856} +{"current_steps": 515, "total_steps": 522, "loss": 0.0483, "accuracy": 0.984375, "lr": 9.222722473546385e-09, "epoch": 1.9691165908546804, "percentage": 98.66, "elapsed_time": "7:11:26", "remaining_time": "0:05:51", "throughput": 6552.36, "total_tokens": 169618464} +{"current_steps": 516, "total_steps": 522, "loss": 0.0467, "accuracy": 0.984375, "lr": 6.776154116504563e-09, "epoch": 1.9729470912137899, "percentage": 98.85, "elapsed_time": "7:12:15", "remaining_time": "0:05:01", "throughput": 6552.66, "total_tokens": 169949120} +{"current_steps": 517, "total_steps": 522, "loss": 0.0224, "accuracy": 1.0, "lr": 4.705824989068575e-09, "epoch": 1.9767775915728993, "percentage": 99.04, "elapsed_time": "7:13:08", "remaining_time": "0:04:11", "throughput": 6553.14, "total_tokens": 170304320} +{"current_steps": 518, "total_steps": 522, "loss": 0.0367, "accuracy": 0.9921875, "lr": 3.0118130379575005e-09, "epoch": 1.9806080919320086, "percentage": 99.23, "elapsed_time": "7:13:58", "remaining_time": "0:03:21", "throughput": 6553.11, "total_tokens": 170634080} +{"current_steps": 519, "total_steps": 522, "loss": 0.0147, "accuracy": 1.0, "lr": 1.6941820417659682e-09, "epoch": 1.984438592291118, "percentage": 99.43, "elapsed_time": "7:14:47", "remaining_time": "0:02:30", "throughput": 6553.21, "total_tokens": 170959328} +{"current_steps": 520, "total_steps": 522, "loss": 0.025, "accuracy": 0.9921875, "lr": 7.529816085549701e-10, "epoch": 1.9882690926502273, "percentage": 99.62, "elapsed_time": "7:15:38", "remaining_time": "0:01:40", "throughput": 6553.27, "total_tokens": 171291360} +{"current_steps": 521, "total_steps": 522, "loss": 0.0177, "accuracy": 1.0, "lr": 1.8824717398890912e-10, "epoch": 1.9920995930093368, "percentage": 99.81, "elapsed_time": "7:16:40", "remaining_time": "0:00:50", "throughput": 6549.43, "total_tokens": 171601152} +{"current_steps": 522, "total_steps": 522, "loss": 0.0211, "accuracy": 1.0, "lr": 0.0, "epoch": 1.9959300933684463, "percentage": 100.0, "elapsed_time": "7:17:29", "remaining_time": "0:00:00", "throughput": 6549.82, "total_tokens": 171931200} +{"current_steps": 522, "total_steps": 522, "epoch": 1.9959300933684463, "percentage": 100.0, "elapsed_time": "7:17:42", "remaining_time": "0:00:00", "throughput": 6546.71, "total_tokens": 171931200}