train_cb_1757340217 / trainer_log.jsonl
rbelanec's picture
Training in progress, step 570
f589a5e verified
{"current_steps": 5, "total_steps": 570, "loss": 4.343, "lr": 3.5087719298245615e-06, "epoch": 0.08771929824561403, "percentage": 0.88, "elapsed_time": "0:00:03", "remaining_time": "0:05:50", "throughput": 1042.01, "total_tokens": 3232}
{"current_steps": 10, "total_steps": 570, "loss": 2.5468, "lr": 7.894736842105263e-06, "epoch": 0.17543859649122806, "percentage": 1.75, "elapsed_time": "0:00:04", "remaining_time": "0:03:58", "throughput": 1472.14, "total_tokens": 6272}
{"current_steps": 15, "total_steps": 570, "loss": 1.0354, "lr": 1.2280701754385964e-05, "epoch": 0.2631578947368421, "percentage": 2.63, "elapsed_time": "0:00:05", "remaining_time": "0:03:19", "throughput": 1689.21, "total_tokens": 9088}
{"current_steps": 20, "total_steps": 570, "loss": 0.3318, "lr": 1.6666666666666667e-05, "epoch": 0.3508771929824561, "percentage": 3.51, "elapsed_time": "0:00:06", "remaining_time": "0:03:01", "throughput": 1895.91, "total_tokens": 12480}
{"current_steps": 25, "total_steps": 570, "loss": 0.4646, "lr": 2.105263157894737e-05, "epoch": 0.43859649122807015, "percentage": 4.39, "elapsed_time": "0:00:07", "remaining_time": "0:02:47", "throughput": 1981.41, "total_tokens": 15232}
{"current_steps": 29, "total_steps": 570, "eval_loss": 0.21523325145244598, "epoch": 0.5087719298245614, "percentage": 5.09, "elapsed_time": "0:00:09", "remaining_time": "0:02:57", "throughput": 1891.69, "total_tokens": 18048}
{"current_steps": 30, "total_steps": 570, "loss": 0.3198, "lr": 2.5438596491228074e-05, "epoch": 0.5263157894736842, "percentage": 5.26, "elapsed_time": "0:00:11", "remaining_time": "0:03:21", "throughput": 1654.65, "total_tokens": 18496}
{"current_steps": 35, "total_steps": 570, "loss": 0.3082, "lr": 2.9824561403508772e-05, "epoch": 0.6140350877192983, "percentage": 6.14, "elapsed_time": "0:00:12", "remaining_time": "0:03:08", "throughput": 1752.79, "total_tokens": 21632}
{"current_steps": 40, "total_steps": 570, "loss": 0.2133, "lr": 3.421052631578947e-05, "epoch": 0.7017543859649122, "percentage": 7.02, "elapsed_time": "0:00:13", "remaining_time": "0:03:00", "throughput": 1858.05, "total_tokens": 25312}
{"current_steps": 45, "total_steps": 570, "loss": 0.3797, "lr": 3.859649122807018e-05, "epoch": 0.7894736842105263, "percentage": 7.89, "elapsed_time": "0:00:14", "remaining_time": "0:02:53", "throughput": 1950.29, "total_tokens": 29024}
{"current_steps": 50, "total_steps": 570, "loss": 0.2594, "lr": 4.298245614035088e-05, "epoch": 0.8771929824561403, "percentage": 8.77, "elapsed_time": "0:00:16", "remaining_time": "0:02:46", "throughput": 2000.77, "total_tokens": 32096}
{"current_steps": 55, "total_steps": 570, "loss": 0.4224, "lr": 4.736842105263158e-05, "epoch": 0.9649122807017544, "percentage": 9.65, "elapsed_time": "0:00:17", "remaining_time": "0:02:41", "throughput": 2044.05, "total_tokens": 35232}
{"current_steps": 58, "total_steps": 570, "eval_loss": 0.2754163146018982, "epoch": 1.0175438596491229, "percentage": 10.18, "elapsed_time": "0:00:18", "remaining_time": "0:02:45", "throughput": 1932.93, "total_tokens": 36328}
{"current_steps": 60, "total_steps": 570, "loss": 0.2603, "lr": 4.999812487773597e-05, "epoch": 1.0526315789473684, "percentage": 10.53, "elapsed_time": "0:00:21", "remaining_time": "0:02:58", "throughput": 1771.29, "total_tokens": 37288}
{"current_steps": 65, "total_steps": 570, "loss": 0.1991, "lr": 4.997703298253406e-05, "epoch": 1.1403508771929824, "percentage": 11.4, "elapsed_time": "0:00:22", "remaining_time": "0:02:53", "throughput": 1845.18, "total_tokens": 41256}
{"current_steps": 70, "total_steps": 570, "loss": 0.1677, "lr": 4.993252512887069e-05, "epoch": 1.2280701754385965, "percentage": 12.28, "elapsed_time": "0:00:23", "remaining_time": "0:02:48", "throughput": 1895.82, "total_tokens": 44680}
{"current_steps": 75, "total_steps": 570, "loss": 0.4142, "lr": 4.986464304284091e-05, "epoch": 1.3157894736842106, "percentage": 13.16, "elapsed_time": "0:00:24", "remaining_time": "0:02:43", "throughput": 1948.85, "total_tokens": 48424}
{"current_steps": 80, "total_steps": 570, "loss": 0.159, "lr": 4.977345036387331e-05, "epoch": 1.4035087719298245, "percentage": 14.04, "elapsed_time": "0:00:26", "remaining_time": "0:02:39", "throughput": 1989.38, "total_tokens": 51880}
{"current_steps": 85, "total_steps": 570, "loss": 0.1384, "lr": 4.965903258506806e-05, "epoch": 1.4912280701754386, "percentage": 14.91, "elapsed_time": "0:00:27", "remaining_time": "0:02:35", "throughput": 2023.45, "total_tokens": 55176}
{"current_steps": 87, "total_steps": 570, "eval_loss": 0.17165084183216095, "epoch": 1.526315789473684, "percentage": 15.26, "elapsed_time": "0:00:28", "remaining_time": "0:02:38", "throughput": 1965.67, "total_tokens": 56168}
{"current_steps": 90, "total_steps": 570, "loss": 0.3064, "lr": 4.952149697304716e-05, "epoch": 1.5789473684210527, "percentage": 15.79, "elapsed_time": "0:00:30", "remaining_time": "0:02:43", "throughput": 1876.16, "total_tokens": 57640}
{"current_steps": 95, "total_steps": 570, "loss": 0.1181, "lr": 4.9360972467392056e-05, "epoch": 1.6666666666666665, "percentage": 16.67, "elapsed_time": "0:00:31", "remaining_time": "0:02:39", "throughput": 1918.21, "total_tokens": 61352}
{"current_steps": 100, "total_steps": 570, "loss": 2.5833, "lr": 4.917760955976277e-05, "epoch": 1.7543859649122808, "percentage": 17.54, "elapsed_time": "0:00:33", "remaining_time": "0:02:35", "throughput": 1945.26, "total_tokens": 64488}
{"current_steps": 105, "total_steps": 570, "loss": 11.5179, "lr": 4.897158015281209e-05, "epoch": 1.8421052631578947, "percentage": 18.42, "elapsed_time": "0:00:34", "remaining_time": "0:02:31", "throughput": 1965.31, "total_tokens": 67400}
{"current_steps": 110, "total_steps": 570, "loss": 6.7916, "lr": 4.874307739902689e-05, "epoch": 1.9298245614035088, "percentage": 19.3, "elapsed_time": "0:00:35", "remaining_time": "0:02:28", "throughput": 1983.72, "total_tokens": 70280}
{"current_steps": 115, "total_steps": 570, "loss": 0.9708, "lr": 4.849231551964771e-05, "epoch": 2.017543859649123, "percentage": 20.18, "elapsed_time": "0:00:36", "remaining_time": "0:02:25", "throughput": 1994.79, "total_tokens": 73184}
{"current_steps": 116, "total_steps": 570, "eval_loss": 0.17644236981868744, "epoch": 2.0350877192982457, "percentage": 20.35, "elapsed_time": "0:00:37", "remaining_time": "0:02:27", "throughput": 1952.24, "total_tokens": 73792}
{"current_steps": 120, "total_steps": 570, "loss": 0.0563, "lr": 4.821952960383649e-05, "epoch": 2.1052631578947367, "percentage": 21.05, "elapsed_time": "0:00:40", "remaining_time": "0:02:30", "throughput": 1897.19, "total_tokens": 76256}
{"current_steps": 125, "total_steps": 570, "loss": 0.3175, "lr": 4.7924975388280524e-05, "epoch": 2.192982456140351, "percentage": 21.93, "elapsed_time": "0:00:41", "remaining_time": "0:02:27", "throughput": 1916.63, "total_tokens": 79200}
{"current_steps": 130, "total_steps": 570, "loss": 0.1314, "lr": 4.760892901743944e-05, "epoch": 2.280701754385965, "percentage": 22.81, "elapsed_time": "0:00:42", "remaining_time": "0:02:23", "throughput": 1936.58, "total_tokens": 82272}
{"current_steps": 135, "total_steps": 570, "loss": 0.1019, "lr": 4.727168678465988e-05, "epoch": 2.3684210526315788, "percentage": 23.68, "elapsed_time": "0:00:43", "remaining_time": "0:02:21", "throughput": 1974.86, "total_tokens": 86624}
{"current_steps": 140, "total_steps": 570, "loss": 0.2033, "lr": 4.6913564854400595e-05, "epoch": 2.456140350877193, "percentage": 24.56, "elapsed_time": "0:00:45", "remaining_time": "0:02:18", "throughput": 1990.14, "total_tokens": 89568}
{"current_steps": 145, "total_steps": 570, "loss": 0.187, "lr": 4.6534898965828405e-05, "epoch": 2.543859649122807, "percentage": 25.44, "elapsed_time": "0:00:46", "remaining_time": "0:02:15", "throughput": 2008.59, "total_tokens": 92768}
{"current_steps": 145, "total_steps": 570, "eval_loss": 0.19479458034038544, "epoch": 2.543859649122807, "percentage": 25.44, "elapsed_time": "0:00:47", "remaining_time": "0:02:17", "throughput": 1971.16, "total_tokens": 92768}
{"current_steps": 150, "total_steps": 570, "loss": 0.1428, "lr": 4.613604411806285e-05, "epoch": 2.6315789473684212, "percentage": 26.32, "elapsed_time": "0:00:49", "remaining_time": "0:02:19", "throughput": 1926.15, "total_tokens": 96160}
{"current_steps": 155, "total_steps": 570, "loss": 0.4127, "lr": 4.5717374237364665e-05, "epoch": 2.719298245614035, "percentage": 27.19, "elapsed_time": "0:00:51", "remaining_time": "0:02:16", "throughput": 1943.27, "total_tokens": 99328}
{"current_steps": 160, "total_steps": 570, "loss": 0.221, "lr": 4.5279281826580056e-05, "epoch": 2.807017543859649, "percentage": 28.07, "elapsed_time": "0:00:52", "remaining_time": "0:02:13", "throughput": 1958.76, "total_tokens": 102368}
{"current_steps": 165, "total_steps": 570, "loss": 0.1723, "lr": 4.482217759716946e-05, "epoch": 2.8947368421052633, "percentage": 28.95, "elapsed_time": "0:00:53", "remaining_time": "0:02:11", "throughput": 1970.17, "total_tokens": 105184}
{"current_steps": 170, "total_steps": 570, "loss": 0.1273, "lr": 4.434649008416565e-05, "epoch": 2.982456140350877, "percentage": 29.82, "elapsed_time": "0:00:54", "remaining_time": "0:02:08", "throughput": 1985.32, "total_tokens": 108320}
{"current_steps": 174, "total_steps": 570, "eval_loss": 0.15818169713020325, "epoch": 3.0526315789473686, "percentage": 30.53, "elapsed_time": "0:00:56", "remaining_time": "0:02:08", "throughput": 1951.96, "total_tokens": 110064}
{"current_steps": 175, "total_steps": 570, "loss": 0.007, "lr": 4.385266524442241e-05, "epoch": 3.0701754385964914, "percentage": 30.7, "elapsed_time": "0:00:58", "remaining_time": "0:02:11", "throughput": 1900.99, "total_tokens": 110640}
{"current_steps": 180, "total_steps": 570, "loss": 0.0719, "lr": 4.334116603853007e-05, "epoch": 3.1578947368421053, "percentage": 31.58, "elapsed_time": "0:00:59", "remaining_time": "0:02:08", "throughput": 1920.17, "total_tokens": 114128}
{"current_steps": 185, "total_steps": 570, "loss": 0.1197, "lr": 4.2812471996790206e-05, "epoch": 3.245614035087719, "percentage": 32.46, "elapsed_time": "0:01:00", "remaining_time": "0:02:06", "throughput": 1931.66, "total_tokens": 116976}
{"current_steps": 190, "total_steps": 570, "loss": 0.3185, "lr": 4.226707876965611e-05, "epoch": 3.3333333333333335, "percentage": 33.33, "elapsed_time": "0:01:01", "remaining_time": "0:02:03", "throughput": 1951.46, "total_tokens": 120656}
{"current_steps": 195, "total_steps": 570, "loss": 0.0986, "lr": 4.1705497663060767e-05, "epoch": 3.4210526315789473, "percentage": 34.21, "elapsed_time": "0:01:03", "remaining_time": "0:02:01", "throughput": 1972.07, "total_tokens": 124432}
{"current_steps": 200, "total_steps": 570, "loss": 0.0853, "lr": 4.1128255159067665e-05, "epoch": 3.5087719298245617, "percentage": 35.09, "elapsed_time": "0:01:04", "remaining_time": "0:01:58", "throughput": 1986.43, "total_tokens": 127728}
{"current_steps": 203, "total_steps": 570, "eval_loss": 0.15603545308113098, "epoch": 3.56140350877193, "percentage": 35.61, "elapsed_time": "0:01:05", "remaining_time": "0:01:59", "throughput": 1969.6, "total_tokens": 129808}
{"current_steps": 205, "total_steps": 570, "loss": 0.1693, "lr": 4.053589242229412e-05, "epoch": 3.5964912280701755, "percentage": 35.96, "elapsed_time": "0:01:07", "remaining_time": "0:02:00", "throughput": 1931.55, "total_tokens": 131024}
{"current_steps": 210, "total_steps": 570, "loss": 0.0915, "lr": 3.9928964792569655e-05, "epoch": 3.6842105263157894, "percentage": 36.84, "elapsed_time": "0:01:08", "remaining_time": "0:01:58", "throughput": 1942.68, "total_tokens": 134000}
{"current_steps": 215, "total_steps": 570, "loss": 0.1495, "lr": 3.930804126430513e-05, "epoch": 3.7719298245614032, "percentage": 37.72, "elapsed_time": "0:01:10", "remaining_time": "0:01:55", "throughput": 1952.48, "total_tokens": 136880}
{"current_steps": 220, "total_steps": 570, "loss": 0.6616, "lr": 3.867370395306068e-05, "epoch": 3.8596491228070176, "percentage": 38.6, "elapsed_time": "0:01:11", "remaining_time": "0:01:53", "throughput": 1963.49, "total_tokens": 139952}
{"current_steps": 225, "total_steps": 570, "loss": 0.2736, "lr": 3.8026547549812665e-05, "epoch": 3.9473684210526314, "percentage": 39.47, "elapsed_time": "0:01:12", "remaining_time": "0:01:51", "throughput": 1978.09, "total_tokens": 143408}
{"current_steps": 230, "total_steps": 570, "loss": 0.5225, "lr": 3.736717876343106e-05, "epoch": 4.035087719298246, "percentage": 40.35, "elapsed_time": "0:01:13", "remaining_time": "0:01:48", "throughput": 1981.47, "total_tokens": 146088}
{"current_steps": 232, "total_steps": 570, "eval_loss": 0.20426368713378906, "epoch": 4.0701754385964914, "percentage": 40.7, "elapsed_time": "0:01:15", "remaining_time": "0:01:49", "throughput": 1961.62, "total_tokens": 147240}
{"current_steps": 235, "total_steps": 570, "loss": 0.1719, "lr": 3.66962157518902e-05, "epoch": 4.12280701754386, "percentage": 41.23, "elapsed_time": "0:01:17", "remaining_time": "0:01:50", "throughput": 1932.67, "total_tokens": 149288}
{"current_steps": 240, "total_steps": 570, "loss": 0.2108, "lr": 3.601428754274584e-05, "epoch": 4.2105263157894735, "percentage": 42.11, "elapsed_time": "0:01:18", "remaining_time": "0:01:47", "throughput": 1941.55, "total_tokens": 152200}
{"current_steps": 245, "total_steps": 570, "loss": 0.1066, "lr": 3.532203344342212e-05, "epoch": 4.298245614035087, "percentage": 42.98, "elapsed_time": "0:01:19", "remaining_time": "0:01:45", "throughput": 1954.46, "total_tokens": 155560}
{"current_steps": 250, "total_steps": 570, "loss": 0.063, "lr": 3.4620102441861143e-05, "epoch": 4.385964912280702, "percentage": 43.86, "elapsed_time": "0:01:20", "remaining_time": "0:01:43", "throughput": 1965.31, "total_tokens": 158760}
{"current_steps": 255, "total_steps": 570, "loss": 0.0025, "lr": 3.390915259809696e-05, "epoch": 4.473684210526316, "percentage": 44.74, "elapsed_time": "0:01:21", "remaining_time": "0:01:41", "throughput": 1971.36, "total_tokens": 161384}
{"current_steps": 260, "total_steps": 570, "loss": 0.0862, "lr": 3.318985042732461e-05, "epoch": 4.56140350877193, "percentage": 45.61, "elapsed_time": "0:01:22", "remaining_time": "0:01:38", "throughput": 1976.93, "total_tokens": 163976}
{"current_steps": 261, "total_steps": 570, "eval_loss": 0.20135438442230225, "epoch": 4.578947368421053, "percentage": 45.79, "elapsed_time": "0:01:24", "remaining_time": "0:01:39", "throughput": 1959.13, "total_tokens": 164744}
{"current_steps": 265, "total_steps": 570, "loss": 0.0197, "lr": 3.246287027504237e-05, "epoch": 4.649122807017544, "percentage": 46.49, "elapsed_time": "0:01:26", "remaining_time": "0:01:39", "throughput": 1937.21, "total_tokens": 167368}
{"current_steps": 270, "total_steps": 570, "loss": 0.248, "lr": 3.172889368485311e-05, "epoch": 4.7368421052631575, "percentage": 47.37, "elapsed_time": "0:01:27", "remaining_time": "0:01:37", "throughput": 1953.11, "total_tokens": 171240}
{"current_steps": 275, "total_steps": 570, "loss": 0.0868, "lr": 3.0988608759517475e-05, "epoch": 4.824561403508772, "percentage": 48.25, "elapsed_time": "0:01:28", "remaining_time": "0:01:35", "throughput": 1965.21, "total_tokens": 174728}
{"current_steps": 280, "total_steps": 570, "loss": 0.0955, "lr": 3.0242709515857758e-05, "epoch": 4.912280701754386, "percentage": 49.12, "elapsed_time": "0:01:30", "remaining_time": "0:01:33", "throughput": 1977.16, "total_tokens": 178216}
{"current_steps": 285, "total_steps": 570, "loss": 0.116, "lr": 2.949189523411747e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:01:31", "remaining_time": "0:01:31", "throughput": 1981.11, "total_tokens": 180696}
{"current_steps": 290, "total_steps": 570, "loss": 0.0088, "lr": 2.8736869802386364e-05, "epoch": 5.087719298245614, "percentage": 50.88, "elapsed_time": "0:01:32", "remaining_time": "0:01:29", "throughput": 1991.99, "total_tokens": 184440}
{"current_steps": 290, "total_steps": 570, "eval_loss": 0.17873549461364746, "epoch": 5.087719298245614, "percentage": 50.88, "elapsed_time": "0:01:33", "remaining_time": "0:01:30", "throughput": 1973.1, "total_tokens": 184440}
{"current_steps": 295, "total_steps": 570, "loss": 0.1308, "lr": 2.797834105670559e-05, "epoch": 5.175438596491228, "percentage": 51.75, "elapsed_time": "0:01:36", "remaining_time": "0:01:29", "throughput": 1941.29, "total_tokens": 186968}
{"current_steps": 300, "total_steps": 570, "loss": 0.205, "lr": 2.7217020117471793e-05, "epoch": 5.2631578947368425, "percentage": 52.63, "elapsed_time": "0:01:37", "remaining_time": "0:01:27", "throughput": 1954.69, "total_tokens": 190808}
{"current_steps": 305, "total_steps": 570, "loss": 0.0673, "lr": 2.6453620722761896e-05, "epoch": 5.350877192982456, "percentage": 53.51, "elapsed_time": "0:01:38", "remaining_time": "0:01:25", "throughput": 1964.64, "total_tokens": 194168}
{"current_steps": 310, "total_steps": 570, "loss": 0.0757, "lr": 2.5688858559204053e-05, "epoch": 5.43859649122807, "percentage": 54.39, "elapsed_time": "0:01:39", "remaining_time": "0:01:23", "throughput": 1971.91, "total_tokens": 197176}
{"current_steps": 315, "total_steps": 570, "loss": 0.0051, "lr": 2.492345059102164e-05, "epoch": 5.526315789473684, "percentage": 55.26, "elapsed_time": "0:01:41", "remaining_time": "0:01:21", "throughput": 1977.88, "total_tokens": 199992}
{"current_steps": 319, "total_steps": 570, "eval_loss": 0.1657482236623764, "epoch": 5.5964912280701755, "percentage": 55.96, "elapsed_time": "0:01:42", "remaining_time": "0:01:20", "throughput": 1967.19, "total_tokens": 202456}
{"current_steps": 320, "total_steps": 570, "loss": 0.0647, "lr": 2.4158114387879616e-05, "epoch": 5.614035087719298, "percentage": 56.14, "elapsed_time": "0:01:44", "remaining_time": "0:01:21", "throughput": 1940.19, "total_tokens": 203096}
{"current_steps": 325, "total_steps": 570, "loss": 0.0284, "lr": 2.3393567452163252e-05, "epoch": 5.701754385964913, "percentage": 57.02, "elapsed_time": "0:01:45", "remaining_time": "0:01:19", "throughput": 1950.71, "total_tokens": 206616}
{"current_steps": 330, "total_steps": 570, "loss": 0.1285, "lr": 2.2630526546319914e-05, "epoch": 5.7894736842105265, "percentage": 57.89, "elapsed_time": "0:01:47", "remaining_time": "0:01:17", "throughput": 1960.26, "total_tokens": 210040}
{"current_steps": 335, "total_steps": 570, "loss": 0.1406, "lr": 2.186970702089457e-05, "epoch": 5.87719298245614, "percentage": 58.77, "elapsed_time": "0:01:48", "remaining_time": "0:01:15", "throughput": 1966.49, "total_tokens": 212952}
{"current_steps": 340, "total_steps": 570, "loss": 0.0007, "lr": 2.111182214388893e-05, "epoch": 5.964912280701754, "percentage": 59.65, "elapsed_time": "0:01:49", "remaining_time": "0:01:14", "throughput": 1975.13, "total_tokens": 216248}
{"current_steps": 345, "total_steps": 570, "loss": 0.001, "lr": 2.0357582432072957e-05, "epoch": 6.052631578947368, "percentage": 60.53, "elapsed_time": "0:01:50", "remaining_time": "0:01:12", "throughput": 1975.92, "total_tokens": 218656}
{"current_steps": 348, "total_steps": 570, "eval_loss": 0.18492062389850616, "epoch": 6.105263157894737, "percentage": 61.05, "elapsed_time": "0:01:52", "remaining_time": "0:01:11", "throughput": 1963.24, "total_tokens": 220288}
{"current_steps": 350, "total_steps": 570, "loss": 0.0848, "lr": 1.9607694984875754e-05, "epoch": 6.140350877192983, "percentage": 61.4, "elapsed_time": "0:01:54", "remaining_time": "0:01:11", "throughput": 1943.8, "total_tokens": 221760}
{"current_steps": 355, "total_steps": 570, "loss": 0.1592, "lr": 1.8862862821480025e-05, "epoch": 6.228070175438597, "percentage": 62.28, "elapsed_time": "0:01:55", "remaining_time": "0:01:09", "throughput": 1949.64, "total_tokens": 224672}
{"current_steps": 360, "total_steps": 570, "loss": 0.0056, "lr": 1.8123784221741964e-05, "epoch": 6.315789473684211, "percentage": 63.16, "elapsed_time": "0:01:56", "remaining_time": "0:01:07", "throughput": 1957.52, "total_tokens": 227872}
{"current_steps": 365, "total_steps": 570, "loss": 0.0781, "lr": 1.73911520715541e-05, "epoch": 6.4035087719298245, "percentage": 64.04, "elapsed_time": "0:01:57", "remaining_time": "0:01:05", "throughput": 1962.02, "total_tokens": 230528}
{"current_steps": 370, "total_steps": 570, "loss": 0.0196, "lr": 1.666565321326512e-05, "epoch": 6.491228070175438, "percentage": 64.91, "elapsed_time": "0:01:58", "remaining_time": "0:01:04", "throughput": 1975.95, "total_tokens": 234880}
{"current_steps": 375, "total_steps": 570, "loss": 0.1069, "lr": 1.5947967801765345e-05, "epoch": 6.578947368421053, "percentage": 65.79, "elapsed_time": "0:02:00", "remaining_time": "0:01:02", "throughput": 1981.53, "total_tokens": 237792}
{"current_steps": 377, "total_steps": 570, "eval_loss": 0.19179189205169678, "epoch": 6.614035087719298, "percentage": 66.14, "elapsed_time": "0:02:01", "remaining_time": "0:01:02", "throughput": 1970.77, "total_tokens": 239200}
{"current_steps": 380, "total_steps": 570, "loss": 0.001, "lr": 1.5238768666841907e-05, "epoch": 6.666666666666667, "percentage": 66.67, "elapsed_time": "0:02:03", "remaining_time": "0:01:01", "throughput": 1950.44, "total_tokens": 240736}
{"current_steps": 385, "total_steps": 570, "loss": 0.0007, "lr": 1.4538720682400969e-05, "epoch": 6.754385964912281, "percentage": 67.54, "elapsed_time": "0:02:04", "remaining_time": "0:00:59", "throughput": 1956.26, "total_tokens": 243744}
{"current_steps": 390, "total_steps": 570, "loss": 0.2587, "lr": 1.3848480143148839e-05, "epoch": 6.842105263157895, "percentage": 68.42, "elapsed_time": "0:02:05", "remaining_time": "0:00:58", "throughput": 1963.45, "total_tokens": 247008}
{"current_steps": 395, "total_steps": 570, "loss": 0.121, "lr": 1.3168694149315796e-05, "epoch": 6.9298245614035086, "percentage": 69.3, "elapsed_time": "0:02:06", "remaining_time": "0:00:56", "throughput": 1969.04, "total_tokens": 249984}
{"current_steps": 400, "total_steps": 570, "loss": 0.0046, "lr": 1.2500000000000006e-05, "epoch": 7.017543859649122, "percentage": 70.18, "elapsed_time": "0:02:08", "remaining_time": "0:00:54", "throughput": 1972.73, "total_tokens": 252936}
{"current_steps": 405, "total_steps": 570, "loss": 0.0181, "lr": 1.1843024595699805e-05, "epoch": 7.105263157894737, "percentage": 71.05, "elapsed_time": "0:02:09", "remaining_time": "0:00:52", "throughput": 1978.14, "total_tokens": 255880}
{"current_steps": 406, "total_steps": 570, "eval_loss": 0.19443254172801971, "epoch": 7.12280701754386, "percentage": 71.23, "elapsed_time": "0:02:10", "remaining_time": "0:00:52", "throughput": 1964.88, "total_tokens": 256296}
{"current_steps": 410, "total_steps": 570, "loss": 0.002, "lr": 1.1198383850594758e-05, "epoch": 7.192982456140351, "percentage": 71.93, "elapsed_time": "0:02:12", "remaining_time": "0:00:51", "throughput": 1951.14, "total_tokens": 259240}
{"current_steps": 415, "total_steps": 570, "loss": 0.023, "lr": 1.0566682115126344e-05, "epoch": 7.280701754385965, "percentage": 72.81, "elapsed_time": "0:02:14", "remaining_time": "0:00:50", "throughput": 1958.77, "total_tokens": 262632}
{"current_steps": 420, "total_steps": 570, "loss": 0.0249, "lr": 9.948511609419675e-06, "epoch": 7.368421052631579, "percentage": 73.68, "elapsed_time": "0:02:15", "remaining_time": "0:00:48", "throughput": 1964.69, "total_tokens": 265704}
{"current_steps": 425, "total_steps": 570, "loss": 0.0025, "lr": 9.344451868077353e-06, "epoch": 7.456140350877193, "percentage": 74.56, "elapsed_time": "0:02:16", "remaining_time": "0:00:46", "throughput": 1973.93, "total_tokens": 269480}
{"current_steps": 430, "total_steps": 570, "loss": 0.0007, "lr": 8.755069196866014e-06, "epoch": 7.543859649122807, "percentage": 75.44, "elapsed_time": "0:02:17", "remaining_time": "0:00:44", "throughput": 1979.87, "total_tokens": 272648}
{"current_steps": 435, "total_steps": 570, "loss": 0.0004, "lr": 8.180916141804906e-06, "epoch": 7.631578947368421, "percentage": 76.32, "elapsed_time": "0:02:18", "remaining_time": "0:00:43", "throughput": 1985.37, "total_tokens": 275688}
{"current_steps": 435, "total_steps": 570, "eval_loss": 0.19701550900936127, "epoch": 7.631578947368421, "percentage": 76.32, "elapsed_time": "0:02:19", "remaining_time": "0:00:43", "throughput": 1972.79, "total_tokens": 275688}
{"current_steps": 440, "total_steps": 570, "loss": 0.0267, "lr": 7.622530971154199e-06, "epoch": 7.719298245614035, "percentage": 77.19, "elapsed_time": "0:02:22", "remaining_time": "0:00:42", "throughput": 1958.62, "total_tokens": 279400}
{"current_steps": 445, "total_steps": 570, "loss": 0.0149, "lr": 7.080437170788723e-06, "epoch": 7.807017543859649, "percentage": 78.07, "elapsed_time": "0:02:23", "remaining_time": "0:00:40", "throughput": 1964.37, "total_tokens": 282504}
{"current_steps": 450, "total_steps": 570, "loss": 0.2894, "lr": 6.555142953430158e-06, "epoch": 7.894736842105263, "percentage": 78.95, "elapsed_time": "0:02:24", "remaining_time": "0:00:38", "throughput": 1969.25, "total_tokens": 285448}
{"current_steps": 455, "total_steps": 570, "loss": 0.0011, "lr": 6.0471407821978135e-06, "epoch": 7.982456140350877, "percentage": 79.82, "elapsed_time": "0:02:26", "remaining_time": "0:00:36", "throughput": 1975.42, "total_tokens": 288680}
{"current_steps": 460, "total_steps": 570, "loss": 0.0886, "lr": 5.556906908924655e-06, "epoch": 8.070175438596491, "percentage": 80.7, "elapsed_time": "0:02:27", "remaining_time": "0:00:35", "throughput": 1978.95, "total_tokens": 291728}
{"current_steps": 464, "total_steps": 570, "eval_loss": 0.19679372012615204, "epoch": 8.140350877192983, "percentage": 81.4, "elapsed_time": "0:02:29", "remaining_time": "0:00:34", "throughput": 1973.22, "total_tokens": 294608}
{"current_steps": 465, "total_steps": 570, "loss": 0.0011, "lr": 5.084900927671393e-06, "epoch": 8.157894736842104, "percentage": 81.58, "elapsed_time": "0:02:30", "remaining_time": "0:00:34", "throughput": 1956.07, "total_tokens": 295216}
{"current_steps": 470, "total_steps": 570, "loss": 0.0006, "lr": 4.631565343857239e-06, "epoch": 8.24561403508772, "percentage": 82.46, "elapsed_time": "0:02:31", "remaining_time": "0:00:32", "throughput": 1957.94, "total_tokens": 297552}
{"current_steps": 475, "total_steps": 570, "loss": 0.0081, "lr": 4.19732515941125e-06, "epoch": 8.333333333333334, "percentage": 83.33, "elapsed_time": "0:02:33", "remaining_time": "0:00:30", "throughput": 1963.35, "total_tokens": 300688}
{"current_steps": 480, "total_steps": 570, "loss": 0.0005, "lr": 3.7825874743331907e-06, "epoch": 8.421052631578947, "percentage": 84.21, "elapsed_time": "0:02:34", "remaining_time": "0:00:28", "throughput": 1968.04, "total_tokens": 303664}
{"current_steps": 485, "total_steps": 570, "loss": 0.0189, "lr": 3.3877411050374424e-06, "epoch": 8.508771929824562, "percentage": 85.09, "elapsed_time": "0:02:35", "remaining_time": "0:00:27", "throughput": 1974.6, "total_tokens": 307120}
{"current_steps": 490, "total_steps": 570, "loss": 0.1007, "lr": 3.013156219837776e-06, "epoch": 8.596491228070175, "percentage": 85.96, "elapsed_time": "0:02:36", "remaining_time": "0:00:25", "throughput": 1980.25, "total_tokens": 310352}
{"current_steps": 493, "total_steps": 570, "eval_loss": 0.2059914618730545, "epoch": 8.649122807017545, "percentage": 86.49, "elapsed_time": "0:02:38", "remaining_time": "0:00:24", "throughput": 1971.91, "total_tokens": 312144}
{"current_steps": 495, "total_steps": 570, "loss": 0.0008, "lr": 2.659183991914696e-06, "epoch": 8.68421052631579, "percentage": 86.84, "elapsed_time": "0:02:40", "remaining_time": "0:00:24", "throughput": 1956.34, "total_tokens": 313328}
{"current_steps": 500, "total_steps": 570, "loss": 0.0806, "lr": 2.326156270090735e-06, "epoch": 8.771929824561404, "percentage": 87.72, "elapsed_time": "0:02:41", "remaining_time": "0:00:22", "throughput": 1962.56, "total_tokens": 316688}
{"current_steps": 505, "total_steps": 570, "loss": 0.0125, "lr": 2.0143852677223075e-06, "epoch": 8.859649122807017, "percentage": 88.6, "elapsed_time": "0:02:42", "remaining_time": "0:00:20", "throughput": 1966.29, "total_tokens": 319472}
{"current_steps": 510, "total_steps": 570, "loss": 0.001, "lr": 1.7241632699998123e-06, "epoch": 8.947368421052632, "percentage": 89.47, "elapsed_time": "0:02:43", "remaining_time": "0:00:19", "throughput": 1972.7, "total_tokens": 322896}
{"current_steps": 515, "total_steps": 570, "loss": 0.0007, "lr": 1.4557623599303903e-06, "epoch": 9.035087719298245, "percentage": 90.35, "elapsed_time": "0:02:44", "remaining_time": "0:00:17", "throughput": 1973.35, "total_tokens": 325320}
{"current_steps": 520, "total_steps": 570, "loss": 0.0083, "lr": 1.2094341632602064e-06, "epoch": 9.12280701754386, "percentage": 91.23, "elapsed_time": "0:02:46", "remaining_time": "0:00:15", "throughput": 1980.12, "total_tokens": 328936}
{"current_steps": 522, "total_steps": 570, "eval_loss": 0.21111197769641876, "epoch": 9.157894736842104, "percentage": 91.58, "elapsed_time": "0:02:47", "remaining_time": "0:00:15", "throughput": 1971.55, "total_tokens": 330152}
{"current_steps": 525, "total_steps": 570, "loss": 0.0021, "lr": 9.85409612575411e-07, "epoch": 9.210526315789474, "percentage": 92.11, "elapsed_time": "0:02:49", "remaining_time": "0:00:14", "throughput": 1955.82, "total_tokens": 331944}
{"current_steps": 530, "total_steps": 570, "loss": 0.001, "lr": 7.838987308029427e-07, "epoch": 9.298245614035087, "percentage": 92.98, "elapsed_time": "0:02:50", "remaining_time": "0:00:12", "throughput": 1960.32, "total_tokens": 334952}
{"current_steps": 535, "total_steps": 570, "loss": 0.0005, "lr": 6.050904343141095e-07, "epoch": 9.385964912280702, "percentage": 93.86, "elapsed_time": "0:02:52", "remaining_time": "0:00:11", "throughput": 1964.76, "total_tokens": 337992}
{"current_steps": 540, "total_steps": 570, "loss": 0.112, "lr": 4.491523558155714e-07, "epoch": 9.473684210526315, "percentage": 94.74, "elapsed_time": "0:02:53", "remaining_time": "0:00:09", "throughput": 1966.75, "total_tokens": 340456}
{"current_steps": 545, "total_steps": 570, "loss": 0.0043, "lr": 3.162306871937387e-07, "epoch": 9.56140350877193, "percentage": 95.61, "elapsed_time": "0:02:54", "remaining_time": "0:00:08", "throughput": 1974.48, "total_tokens": 344360}
{"current_steps": 550, "total_steps": 570, "loss": 0.0012, "lr": 2.064500424599436e-07, "epoch": 9.649122807017545, "percentage": 96.49, "elapsed_time": "0:02:55", "remaining_time": "0:00:06", "throughput": 1978.69, "total_tokens": 347368}
{"current_steps": 551, "total_steps": 570, "eval_loss": 0.2125496119260788, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:56", "remaining_time": "0:00:06", "throughput": 1969.61, "total_tokens": 347976}
{"current_steps": 555, "total_steps": 570, "loss": 0.0152, "lr": 1.1991334092484318e-07, "epoch": 9.736842105263158, "percentage": 97.37, "elapsed_time": "0:02:59", "remaining_time": "0:00:04", "throughput": 1958.17, "total_tokens": 350664}
{"current_steps": 560, "total_steps": 570, "loss": 0.0029, "lr": 5.6701710711626334e-08, "epoch": 9.824561403508772, "percentage": 98.25, "elapsed_time": "0:03:00", "remaining_time": "0:00:03", "throughput": 1962.89, "total_tokens": 353832}
{"current_steps": 565, "total_steps": 570, "loss": 0.0016, "lr": 1.6874412698408836e-08, "epoch": 9.912280701754385, "percentage": 99.12, "elapsed_time": "0:03:01", "remaining_time": "0:00:01", "throughput": 1966.94, "total_tokens": 356872}
{"current_steps": 570, "total_steps": 570, "loss": 0.0013, "lr": 4.687849611939576e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:02", "remaining_time": "0:00:00", "throughput": 1970.27, "total_tokens": 359688}
{"current_steps": 570, "total_steps": 570, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:03", "remaining_time": "0:00:00", "throughput": 1955.66, "total_tokens": 359688}