{"current_steps": 1, "total_steps": 1218, "loss": 1.7545, "learning_rate": 1.639344262295082e-07, "epoch": 0.0024630541871921183, "percentage": 0.08, "elapsed_time": "0:00:16", "remaining_time": "5:30:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 2, "total_steps": 1218, "loss": 1.6567, "learning_rate": 3.278688524590164e-07, "epoch": 0.0049261083743842365, "percentage": 0.16, "elapsed_time": "0:00:28", "remaining_time": "4:50:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 3, "total_steps": 1218, "loss": 1.6064, "learning_rate": 4.918032786885246e-07, "epoch": 0.007389162561576354, "percentage": 0.25, "elapsed_time": "0:00:38", "remaining_time": "4:23:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 4, "total_steps": 1218, "loss": 1.694, "learning_rate": 6.557377049180328e-07, "epoch": 0.009852216748768473, "percentage": 0.33, "elapsed_time": "0:00:48", "remaining_time": "4:06:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 5, "total_steps": 1218, "loss": 1.674, "learning_rate": 8.196721311475409e-07, "epoch": 0.012315270935960592, "percentage": 0.41, "elapsed_time": "0:00:59", "remaining_time": "4:01:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 6, "total_steps": 1218, "loss": 1.6892, "learning_rate": 9.836065573770493e-07, "epoch": 0.014778325123152709, "percentage": 0.49, "elapsed_time": "0:01:10", "remaining_time": "3:57:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 7, "total_steps": 1218, "loss": 1.65, "learning_rate": 1.1475409836065575e-06, "epoch": 0.017241379310344827, "percentage": 0.57, "elapsed_time": "0:01:20", "remaining_time": "3:53:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 8, "total_steps": 1218, "loss": 1.4504, "learning_rate": 1.3114754098360657e-06, "epoch": 0.019704433497536946, "percentage": 0.66, "elapsed_time": "0:01:35", "remaining_time": "4:00:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 9, "total_steps": 1218, "loss": 1.5861, "learning_rate": 1.4754098360655739e-06, "epoch": 0.022167487684729065, "percentage": 0.74, "elapsed_time": "0:01:45", "remaining_time": "3:56:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 10, "total_steps": 1218, "loss": 1.6732, "learning_rate": 1.6393442622950819e-06, "epoch": 0.024630541871921183, "percentage": 0.82, "elapsed_time": "0:01:58", "remaining_time": "3:58:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 11, "total_steps": 1218, "loss": 1.6, "learning_rate": 1.8032786885245903e-06, "epoch": 0.027093596059113302, "percentage": 0.9, "elapsed_time": "0:02:13", "remaining_time": "4:04:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 12, "total_steps": 1218, "loss": 1.5305, "learning_rate": 1.9672131147540985e-06, "epoch": 0.029556650246305417, "percentage": 0.99, "elapsed_time": "0:02:25", "remaining_time": "4:03:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 13, "total_steps": 1218, "loss": 1.4732, "learning_rate": 2.1311475409836067e-06, "epoch": 0.03201970443349754, "percentage": 1.07, "elapsed_time": "0:02:35", "remaining_time": "3:59:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 14, "total_steps": 1218, "loss": 1.5632, "learning_rate": 2.295081967213115e-06, "epoch": 0.034482758620689655, "percentage": 1.15, "elapsed_time": "0:02:46", "remaining_time": "3:58:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 15, "total_steps": 1218, "loss": 1.5503, "learning_rate": 2.459016393442623e-06, "epoch": 0.03694581280788178, "percentage": 1.23, "elapsed_time": "0:02:56", "remaining_time": "3:55:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 16, "total_steps": 1218, "loss": 1.5676, "learning_rate": 2.6229508196721314e-06, "epoch": 0.03940886699507389, "percentage": 1.31, "elapsed_time": "0:03:07", "remaining_time": "3:55:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 17, "total_steps": 1218, "loss": 1.4395, "learning_rate": 2.786885245901639e-06, "epoch": 0.04187192118226601, "percentage": 1.4, "elapsed_time": "0:03:18", "remaining_time": "3:53:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 18, "total_steps": 1218, "loss": 1.4365, "learning_rate": 2.9508196721311478e-06, "epoch": 0.04433497536945813, "percentage": 1.48, "elapsed_time": "0:03:28", "remaining_time": "3:51:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 19, "total_steps": 1218, "loss": 1.3229, "learning_rate": 3.114754098360656e-06, "epoch": 0.046798029556650245, "percentage": 1.56, "elapsed_time": "0:03:43", "remaining_time": "3:55:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 20, "total_steps": 1218, "loss": 1.4392, "learning_rate": 3.2786885245901638e-06, "epoch": 0.04926108374384237, "percentage": 1.64, "elapsed_time": "0:03:53", "remaining_time": "3:52:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 21, "total_steps": 1218, "loss": 1.4364, "learning_rate": 3.4426229508196724e-06, "epoch": 0.05172413793103448, "percentage": 1.72, "elapsed_time": "0:04:04", "remaining_time": "3:52:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 22, "total_steps": 1218, "loss": 1.3143, "learning_rate": 3.6065573770491806e-06, "epoch": 0.054187192118226604, "percentage": 1.81, "elapsed_time": "0:04:14", "remaining_time": "3:51:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 23, "total_steps": 1218, "loss": 1.213, "learning_rate": 3.7704918032786884e-06, "epoch": 0.05665024630541872, "percentage": 1.89, "elapsed_time": "0:04:26", "remaining_time": "3:50:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 24, "total_steps": 1218, "loss": 1.3925, "learning_rate": 3.934426229508197e-06, "epoch": 0.059113300492610835, "percentage": 1.97, "elapsed_time": "0:04:35", "remaining_time": "3:48:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 25, "total_steps": 1218, "loss": 1.3419, "learning_rate": 4.098360655737705e-06, "epoch": 0.06157635467980296, "percentage": 2.05, "elapsed_time": "0:04:47", "remaining_time": "3:48:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 26, "total_steps": 1218, "loss": 1.3138, "learning_rate": 4.2622950819672135e-06, "epoch": 0.06403940886699508, "percentage": 2.13, "elapsed_time": "0:04:58", "remaining_time": "3:47:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 27, "total_steps": 1218, "loss": 1.2859, "learning_rate": 4.426229508196722e-06, "epoch": 0.0665024630541872, "percentage": 2.22, "elapsed_time": "0:05:08", "remaining_time": "3:46:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 28, "total_steps": 1218, "loss": 1.2653, "learning_rate": 4.59016393442623e-06, "epoch": 0.06896551724137931, "percentage": 2.3, "elapsed_time": "0:05:19", "remaining_time": "3:46:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 29, "total_steps": 1218, "loss": 1.2559, "learning_rate": 4.754098360655738e-06, "epoch": 0.07142857142857142, "percentage": 2.38, "elapsed_time": "0:05:29", "remaining_time": "3:45:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 30, "total_steps": 1218, "loss": 1.2376, "learning_rate": 4.918032786885246e-06, "epoch": 0.07389162561576355, "percentage": 2.46, "elapsed_time": "0:05:40", "remaining_time": "3:44:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 31, "total_steps": 1218, "loss": 1.2772, "learning_rate": 5.0819672131147545e-06, "epoch": 0.07635467980295567, "percentage": 2.55, "elapsed_time": "0:05:50", "remaining_time": "3:43:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 32, "total_steps": 1218, "loss": 1.2745, "learning_rate": 5.245901639344263e-06, "epoch": 0.07881773399014778, "percentage": 2.63, "elapsed_time": "0:06:00", "remaining_time": "3:42:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 33, "total_steps": 1218, "loss": 1.2432, "learning_rate": 5.409836065573772e-06, "epoch": 0.0812807881773399, "percentage": 2.71, "elapsed_time": "0:06:10", "remaining_time": "3:42:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 34, "total_steps": 1218, "loss": 1.1373, "learning_rate": 5.573770491803278e-06, "epoch": 0.08374384236453201, "percentage": 2.79, "elapsed_time": "0:06:20", "remaining_time": "3:40:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 35, "total_steps": 1218, "loss": 1.2228, "learning_rate": 5.737704918032787e-06, "epoch": 0.08620689655172414, "percentage": 2.87, "elapsed_time": "0:06:30", "remaining_time": "3:40:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 36, "total_steps": 1218, "loss": 1.2146, "learning_rate": 5.9016393442622956e-06, "epoch": 0.08866995073891626, "percentage": 2.96, "elapsed_time": "0:06:42", "remaining_time": "3:40:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 37, "total_steps": 1218, "loss": 1.2395, "learning_rate": 6.065573770491804e-06, "epoch": 0.09113300492610837, "percentage": 3.04, "elapsed_time": "0:06:51", "remaining_time": "3:39:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 38, "total_steps": 1218, "loss": 1.2511, "learning_rate": 6.229508196721312e-06, "epoch": 0.09359605911330049, "percentage": 3.12, "elapsed_time": "0:07:03", "remaining_time": "3:39:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 39, "total_steps": 1218, "loss": 1.1572, "learning_rate": 6.393442622950821e-06, "epoch": 0.0960591133004926, "percentage": 3.2, "elapsed_time": "0:07:14", "remaining_time": "3:38:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 40, "total_steps": 1218, "loss": 1.1696, "learning_rate": 6.5573770491803276e-06, "epoch": 0.09852216748768473, "percentage": 3.28, "elapsed_time": "0:07:23", "remaining_time": "3:37:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 41, "total_steps": 1218, "loss": 1.2352, "learning_rate": 6.721311475409837e-06, "epoch": 0.10098522167487685, "percentage": 3.37, "elapsed_time": "0:07:33", "remaining_time": "3:37:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 42, "total_steps": 1218, "loss": 1.2543, "learning_rate": 6.885245901639345e-06, "epoch": 0.10344827586206896, "percentage": 3.45, "elapsed_time": "0:07:44", "remaining_time": "3:36:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 43, "total_steps": 1218, "loss": 1.1574, "learning_rate": 7.049180327868853e-06, "epoch": 0.10591133004926108, "percentage": 3.53, "elapsed_time": "0:07:54", "remaining_time": "3:36:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 44, "total_steps": 1218, "loss": 1.1804, "learning_rate": 7.213114754098361e-06, "epoch": 0.10837438423645321, "percentage": 3.61, "elapsed_time": "0:08:04", "remaining_time": "3:35:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 45, "total_steps": 1218, "loss": 1.1763, "learning_rate": 7.3770491803278695e-06, "epoch": 0.11083743842364532, "percentage": 3.69, "elapsed_time": "0:08:18", "remaining_time": "3:36:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 46, "total_steps": 1218, "loss": 1.1729, "learning_rate": 7.540983606557377e-06, "epoch": 0.11330049261083744, "percentage": 3.78, "elapsed_time": "0:08:28", "remaining_time": "3:35:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 47, "total_steps": 1218, "loss": 1.2131, "learning_rate": 7.704918032786886e-06, "epoch": 0.11576354679802955, "percentage": 3.86, "elapsed_time": "0:08:41", "remaining_time": "3:36:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 48, "total_steps": 1218, "loss": 1.1882, "learning_rate": 7.868852459016394e-06, "epoch": 0.11822660098522167, "percentage": 3.94, "elapsed_time": "0:08:51", "remaining_time": "3:35:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 49, "total_steps": 1218, "loss": 1.3373, "learning_rate": 8.032786885245902e-06, "epoch": 0.1206896551724138, "percentage": 4.02, "elapsed_time": "0:09:01", "remaining_time": "3:35:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 50, "total_steps": 1218, "loss": 1.2286, "learning_rate": 8.19672131147541e-06, "epoch": 0.12315270935960591, "percentage": 4.11, "elapsed_time": "0:09:13", "remaining_time": "3:35:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 51, "total_steps": 1218, "loss": 1.2261, "learning_rate": 8.360655737704919e-06, "epoch": 0.12561576354679804, "percentage": 4.19, "elapsed_time": "0:09:23", "remaining_time": "3:34:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 52, "total_steps": 1218, "loss": 1.0797, "learning_rate": 8.524590163934427e-06, "epoch": 0.12807881773399016, "percentage": 4.27, "elapsed_time": "0:09:35", "remaining_time": "3:34:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 53, "total_steps": 1218, "loss": 1.1637, "learning_rate": 8.688524590163935e-06, "epoch": 0.13054187192118227, "percentage": 4.35, "elapsed_time": "0:09:45", "remaining_time": "3:34:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 54, "total_steps": 1218, "loss": 1.1376, "learning_rate": 8.852459016393443e-06, "epoch": 0.1330049261083744, "percentage": 4.43, "elapsed_time": "0:09:55", "remaining_time": "3:33:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 55, "total_steps": 1218, "loss": 1.2465, "learning_rate": 9.016393442622952e-06, "epoch": 0.1354679802955665, "percentage": 4.52, "elapsed_time": "0:10:06", "remaining_time": "3:33:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 56, "total_steps": 1218, "loss": 1.2961, "learning_rate": 9.18032786885246e-06, "epoch": 0.13793103448275862, "percentage": 4.6, "elapsed_time": "0:10:17", "remaining_time": "3:33:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 57, "total_steps": 1218, "loss": 1.2051, "learning_rate": 9.344262295081968e-06, "epoch": 0.14039408866995073, "percentage": 4.68, "elapsed_time": "0:10:28", "remaining_time": "3:33:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 58, "total_steps": 1218, "loss": 1.1876, "learning_rate": 9.508196721311476e-06, "epoch": 0.14285714285714285, "percentage": 4.76, "elapsed_time": "0:10:37", "remaining_time": "3:32:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 59, "total_steps": 1218, "loss": 1.2107, "learning_rate": 9.672131147540984e-06, "epoch": 0.14532019704433496, "percentage": 4.84, "elapsed_time": "0:10:47", "remaining_time": "3:31:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 60, "total_steps": 1218, "loss": 1.184, "learning_rate": 9.836065573770493e-06, "epoch": 0.1477832512315271, "percentage": 4.93, "elapsed_time": "0:10:56", "remaining_time": "3:31:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 61, "total_steps": 1218, "loss": 1.2428, "learning_rate": 1e-05, "epoch": 0.15024630541871922, "percentage": 5.01, "elapsed_time": "0:11:07", "remaining_time": "3:31:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 62, "total_steps": 1218, "loss": 1.2097, "learning_rate": 1.0163934426229509e-05, "epoch": 0.15270935960591134, "percentage": 5.09, "elapsed_time": "0:11:18", "remaining_time": "3:30:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 63, "total_steps": 1218, "loss": 1.2187, "learning_rate": 1.0327868852459017e-05, "epoch": 0.15517241379310345, "percentage": 5.17, "elapsed_time": "0:11:28", "remaining_time": "3:30:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 64, "total_steps": 1218, "loss": 1.3457, "learning_rate": 1.0491803278688525e-05, "epoch": 0.15763546798029557, "percentage": 5.25, "elapsed_time": "0:11:39", "remaining_time": "3:30:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 65, "total_steps": 1218, "loss": 1.1926, "learning_rate": 1.0655737704918034e-05, "epoch": 0.16009852216748768, "percentage": 5.34, "elapsed_time": "0:11:50", "remaining_time": "3:30:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 66, "total_steps": 1218, "loss": 1.24, "learning_rate": 1.0819672131147544e-05, "epoch": 0.1625615763546798, "percentage": 5.42, "elapsed_time": "0:12:01", "remaining_time": "3:29:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 67, "total_steps": 1218, "loss": 1.166, "learning_rate": 1.0983606557377052e-05, "epoch": 0.16502463054187191, "percentage": 5.5, "elapsed_time": "0:12:11", "remaining_time": "3:29:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 68, "total_steps": 1218, "loss": 1.2541, "learning_rate": 1.1147540983606557e-05, "epoch": 0.16748768472906403, "percentage": 5.58, "elapsed_time": "0:12:22", "remaining_time": "3:29:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 69, "total_steps": 1218, "loss": 1.2344, "learning_rate": 1.1311475409836066e-05, "epoch": 0.16995073891625614, "percentage": 5.67, "elapsed_time": "0:12:32", "remaining_time": "3:28:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 70, "total_steps": 1218, "loss": 1.1888, "learning_rate": 1.1475409836065575e-05, "epoch": 0.1724137931034483, "percentage": 5.75, "elapsed_time": "0:12:51", "remaining_time": "3:30:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 71, "total_steps": 1218, "loss": 1.2256, "learning_rate": 1.1639344262295083e-05, "epoch": 0.1748768472906404, "percentage": 5.83, "elapsed_time": "0:13:01", "remaining_time": "3:30:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 72, "total_steps": 1218, "loss": 1.1419, "learning_rate": 1.1803278688524591e-05, "epoch": 0.17733990147783252, "percentage": 5.91, "elapsed_time": "0:13:12", "remaining_time": "3:30:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 73, "total_steps": 1218, "loss": 1.2626, "learning_rate": 1.19672131147541e-05, "epoch": 0.17980295566502463, "percentage": 5.99, "elapsed_time": "0:13:25", "remaining_time": "3:30:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 74, "total_steps": 1218, "loss": 1.1537, "learning_rate": 1.2131147540983608e-05, "epoch": 0.18226600985221675, "percentage": 6.08, "elapsed_time": "0:13:35", "remaining_time": "3:30:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 75, "total_steps": 1218, "loss": 1.1883, "learning_rate": 1.2295081967213116e-05, "epoch": 0.18472906403940886, "percentage": 6.16, "elapsed_time": "0:13:45", "remaining_time": "3:29:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 76, "total_steps": 1218, "loss": 1.161, "learning_rate": 1.2459016393442624e-05, "epoch": 0.18719211822660098, "percentage": 6.24, "elapsed_time": "0:13:54", "remaining_time": "3:29:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 77, "total_steps": 1218, "loss": 1.2395, "learning_rate": 1.2622950819672132e-05, "epoch": 0.1896551724137931, "percentage": 6.32, "elapsed_time": "0:14:04", "remaining_time": "3:28:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 78, "total_steps": 1218, "loss": 1.2244, "learning_rate": 1.2786885245901642e-05, "epoch": 0.1921182266009852, "percentage": 6.4, "elapsed_time": "0:14:13", "remaining_time": "3:27:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 79, "total_steps": 1218, "loss": 1.2362, "learning_rate": 1.295081967213115e-05, "epoch": 0.19458128078817735, "percentage": 6.49, "elapsed_time": "0:14:23", "remaining_time": "3:27:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 80, "total_steps": 1218, "loss": 1.2797, "learning_rate": 1.3114754098360655e-05, "epoch": 0.19704433497536947, "percentage": 6.57, "elapsed_time": "0:14:33", "remaining_time": "3:26:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 81, "total_steps": 1218, "loss": 1.2826, "learning_rate": 1.3278688524590165e-05, "epoch": 0.19950738916256158, "percentage": 6.65, "elapsed_time": "0:14:42", "remaining_time": "3:26:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 82, "total_steps": 1218, "loss": 1.0685, "learning_rate": 1.3442622950819673e-05, "epoch": 0.2019704433497537, "percentage": 6.73, "elapsed_time": "0:14:53", "remaining_time": "3:26:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 83, "total_steps": 1218, "loss": 1.184, "learning_rate": 1.3606557377049181e-05, "epoch": 0.2044334975369458, "percentage": 6.81, "elapsed_time": "0:15:03", "remaining_time": "3:25:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 84, "total_steps": 1218, "loss": 1.219, "learning_rate": 1.377049180327869e-05, "epoch": 0.20689655172413793, "percentage": 6.9, "elapsed_time": "0:15:14", "remaining_time": "3:25:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 85, "total_steps": 1218, "loss": 1.2491, "learning_rate": 1.3934426229508198e-05, "epoch": 0.20935960591133004, "percentage": 6.98, "elapsed_time": "0:15:24", "remaining_time": "3:25:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 86, "total_steps": 1218, "loss": 1.1326, "learning_rate": 1.4098360655737706e-05, "epoch": 0.21182266009852216, "percentage": 7.06, "elapsed_time": "0:15:34", "remaining_time": "3:25:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 87, "total_steps": 1218, "loss": 1.2039, "learning_rate": 1.4262295081967214e-05, "epoch": 0.21428571428571427, "percentage": 7.14, "elapsed_time": "0:15:45", "remaining_time": "3:24:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 88, "total_steps": 1218, "loss": 1.1613, "learning_rate": 1.4426229508196722e-05, "epoch": 0.21674876847290642, "percentage": 7.22, "elapsed_time": "0:15:55", "remaining_time": "3:24:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 89, "total_steps": 1218, "loss": 1.1717, "learning_rate": 1.459016393442623e-05, "epoch": 0.21921182266009853, "percentage": 7.31, "elapsed_time": "0:16:09", "remaining_time": "3:24:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 90, "total_steps": 1218, "loss": 1.1852, "learning_rate": 1.4754098360655739e-05, "epoch": 0.22167487684729065, "percentage": 7.39, "elapsed_time": "0:16:18", "remaining_time": "3:24:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 91, "total_steps": 1218, "loss": 1.2958, "learning_rate": 1.4918032786885249e-05, "epoch": 0.22413793103448276, "percentage": 7.47, "elapsed_time": "0:16:28", "remaining_time": "3:23:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 92, "total_steps": 1218, "loss": 1.1426, "learning_rate": 1.5081967213114754e-05, "epoch": 0.22660098522167488, "percentage": 7.55, "elapsed_time": "0:16:37", "remaining_time": "3:23:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 93, "total_steps": 1218, "loss": 1.2456, "learning_rate": 1.5245901639344264e-05, "epoch": 0.229064039408867, "percentage": 7.64, "elapsed_time": "0:16:49", "remaining_time": "3:23:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 94, "total_steps": 1218, "loss": 1.0927, "learning_rate": 1.5409836065573772e-05, "epoch": 0.2315270935960591, "percentage": 7.72, "elapsed_time": "0:17:01", "remaining_time": "3:23:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 95, "total_steps": 1218, "loss": 1.1705, "learning_rate": 1.5573770491803278e-05, "epoch": 0.23399014778325122, "percentage": 7.8, "elapsed_time": "0:17:14", "remaining_time": "3:23:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 96, "total_steps": 1218, "loss": 1.3077, "learning_rate": 1.5737704918032788e-05, "epoch": 0.23645320197044334, "percentage": 7.88, "elapsed_time": "0:17:25", "remaining_time": "3:23:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 97, "total_steps": 1218, "loss": 1.2748, "learning_rate": 1.5901639344262295e-05, "epoch": 0.23891625615763548, "percentage": 7.96, "elapsed_time": "0:17:34", "remaining_time": "3:23:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 98, "total_steps": 1218, "loss": 1.2311, "learning_rate": 1.6065573770491805e-05, "epoch": 0.2413793103448276, "percentage": 8.05, "elapsed_time": "0:17:44", "remaining_time": "3:22:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 99, "total_steps": 1218, "loss": 1.2036, "learning_rate": 1.6229508196721314e-05, "epoch": 0.2438423645320197, "percentage": 8.13, "elapsed_time": "0:17:54", "remaining_time": "3:22:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 100, "total_steps": 1218, "loss": 1.193, "learning_rate": 1.639344262295082e-05, "epoch": 0.24630541871921183, "percentage": 8.21, "elapsed_time": "0:18:05", "remaining_time": "3:22:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 101, "total_steps": 1218, "loss": 1.2291, "learning_rate": 1.655737704918033e-05, "epoch": 0.24876847290640394, "percentage": 8.29, "elapsed_time": "0:18:15", "remaining_time": "3:21:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 102, "total_steps": 1218, "loss": 1.1754, "learning_rate": 1.6721311475409837e-05, "epoch": 0.2512315270935961, "percentage": 8.37, "elapsed_time": "0:18:26", "remaining_time": "3:21:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 103, "total_steps": 1218, "loss": 1.1601, "learning_rate": 1.6885245901639347e-05, "epoch": 0.2536945812807882, "percentage": 8.46, "elapsed_time": "0:18:38", "remaining_time": "3:21:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 104, "total_steps": 1218, "loss": 1.1909, "learning_rate": 1.7049180327868854e-05, "epoch": 0.2561576354679803, "percentage": 8.54, "elapsed_time": "0:18:48", "remaining_time": "3:21:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 105, "total_steps": 1218, "loss": 1.1943, "learning_rate": 1.721311475409836e-05, "epoch": 0.25862068965517243, "percentage": 8.62, "elapsed_time": "0:18:58", "remaining_time": "3:21:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 106, "total_steps": 1218, "loss": 1.0855, "learning_rate": 1.737704918032787e-05, "epoch": 0.26108374384236455, "percentage": 8.7, "elapsed_time": "0:19:07", "remaining_time": "3:20:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 107, "total_steps": 1218, "loss": 1.2148, "learning_rate": 1.7540983606557377e-05, "epoch": 0.26354679802955666, "percentage": 8.78, "elapsed_time": "0:19:19", "remaining_time": "3:20:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 108, "total_steps": 1218, "loss": 1.1985, "learning_rate": 1.7704918032786887e-05, "epoch": 0.2660098522167488, "percentage": 8.87, "elapsed_time": "0:19:30", "remaining_time": "3:20:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 109, "total_steps": 1218, "loss": 1.2871, "learning_rate": 1.7868852459016393e-05, "epoch": 0.2684729064039409, "percentage": 8.95, "elapsed_time": "0:19:40", "remaining_time": "3:20:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 110, "total_steps": 1218, "loss": 1.2565, "learning_rate": 1.8032786885245903e-05, "epoch": 0.270935960591133, "percentage": 9.03, "elapsed_time": "0:19:50", "remaining_time": "3:19:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 111, "total_steps": 1218, "loss": 1.1267, "learning_rate": 1.8196721311475413e-05, "epoch": 0.2733990147783251, "percentage": 9.11, "elapsed_time": "0:20:02", "remaining_time": "3:19:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 112, "total_steps": 1218, "loss": 1.2686, "learning_rate": 1.836065573770492e-05, "epoch": 0.27586206896551724, "percentage": 9.2, "elapsed_time": "0:20:13", "remaining_time": "3:19:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 113, "total_steps": 1218, "loss": 1.2142, "learning_rate": 1.852459016393443e-05, "epoch": 0.27832512315270935, "percentage": 9.28, "elapsed_time": "0:20:23", "remaining_time": "3:19:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 114, "total_steps": 1218, "loss": 1.1789, "learning_rate": 1.8688524590163936e-05, "epoch": 0.28078817733990147, "percentage": 9.36, "elapsed_time": "0:20:34", "remaining_time": "3:19:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 115, "total_steps": 1218, "loss": 1.1381, "learning_rate": 1.8852459016393446e-05, "epoch": 0.2832512315270936, "percentage": 9.44, "elapsed_time": "0:20:47", "remaining_time": "3:19:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 116, "total_steps": 1218, "loss": 1.1655, "learning_rate": 1.9016393442622952e-05, "epoch": 0.2857142857142857, "percentage": 9.52, "elapsed_time": "0:20:58", "remaining_time": "3:19:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 117, "total_steps": 1218, "loss": 1.1579, "learning_rate": 1.918032786885246e-05, "epoch": 0.2881773399014778, "percentage": 9.61, "elapsed_time": "0:21:08", "remaining_time": "3:18:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 118, "total_steps": 1218, "loss": 1.1745, "learning_rate": 1.934426229508197e-05, "epoch": 0.29064039408866993, "percentage": 9.69, "elapsed_time": "0:21:20", "remaining_time": "3:18:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 119, "total_steps": 1218, "loss": 1.0881, "learning_rate": 1.9508196721311475e-05, "epoch": 0.29310344827586204, "percentage": 9.77, "elapsed_time": "0:21:30", "remaining_time": "3:18:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 120, "total_steps": 1218, "loss": 1.2475, "learning_rate": 1.9672131147540985e-05, "epoch": 0.2955665024630542, "percentage": 9.85, "elapsed_time": "0:21:40", "remaining_time": "3:18:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 121, "total_steps": 1218, "loss": 1.208, "learning_rate": 1.9836065573770492e-05, "epoch": 0.29802955665024633, "percentage": 9.93, "elapsed_time": "0:21:50", "remaining_time": "3:18:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 122, "total_steps": 1218, "loss": 1.1334, "learning_rate": 2e-05, "epoch": 0.30049261083743845, "percentage": 10.02, "elapsed_time": "0:22:00", "remaining_time": "3:17:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 123, "total_steps": 1218, "loss": 1.1599, "learning_rate": 1.999995891830594e-05, "epoch": 0.30295566502463056, "percentage": 10.1, "elapsed_time": "0:22:10", "remaining_time": "3:17:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 124, "total_steps": 1218, "loss": 1.1884, "learning_rate": 1.9999835673561284e-05, "epoch": 0.3054187192118227, "percentage": 10.18, "elapsed_time": "0:22:21", "remaining_time": "3:17:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 125, "total_steps": 1218, "loss": 1.2117, "learning_rate": 1.9999630266778667e-05, "epoch": 0.3078817733990148, "percentage": 10.26, "elapsed_time": "0:22:33", "remaining_time": "3:17:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 126, "total_steps": 1218, "loss": 1.1938, "learning_rate": 1.9999342699645774e-05, "epoch": 0.3103448275862069, "percentage": 10.34, "elapsed_time": "0:22:43", "remaining_time": "3:17:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 127, "total_steps": 1218, "loss": 1.1861, "learning_rate": 1.9998972974525354e-05, "epoch": 0.312807881773399, "percentage": 10.43, "elapsed_time": "0:22:54", "remaining_time": "3:16:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 128, "total_steps": 1218, "loss": 1.2304, "learning_rate": 1.9998521094455198e-05, "epoch": 0.31527093596059114, "percentage": 10.51, "elapsed_time": "0:23:06", "remaining_time": "3:16:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 129, "total_steps": 1218, "loss": 1.2261, "learning_rate": 1.9997987063148097e-05, "epoch": 0.31773399014778325, "percentage": 10.59, "elapsed_time": "0:23:17", "remaining_time": "3:16:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 130, "total_steps": 1218, "loss": 1.184, "learning_rate": 1.9997370884991842e-05, "epoch": 0.32019704433497537, "percentage": 10.67, "elapsed_time": "0:23:28", "remaining_time": "3:16:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 131, "total_steps": 1218, "loss": 1.2066, "learning_rate": 1.9996672565049158e-05, "epoch": 0.3226600985221675, "percentage": 10.76, "elapsed_time": "0:23:39", "remaining_time": "3:16:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 132, "total_steps": 1218, "loss": 1.195, "learning_rate": 1.9995892109057675e-05, "epoch": 0.3251231527093596, "percentage": 10.84, "elapsed_time": "0:23:50", "remaining_time": "3:16:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 133, "total_steps": 1218, "loss": 1.2068, "learning_rate": 1.9995029523429892e-05, "epoch": 0.3275862068965517, "percentage": 10.92, "elapsed_time": "0:23:59", "remaining_time": "3:15:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 134, "total_steps": 1218, "loss": 1.2182, "learning_rate": 1.99940848152531e-05, "epoch": 0.33004926108374383, "percentage": 11.0, "elapsed_time": "0:24:09", "remaining_time": "3:15:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 135, "total_steps": 1218, "loss": 1.2719, "learning_rate": 1.9993057992289336e-05, "epoch": 0.33251231527093594, "percentage": 11.08, "elapsed_time": "0:24:19", "remaining_time": "3:15:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 136, "total_steps": 1218, "loss": 1.2291, "learning_rate": 1.9991949062975336e-05, "epoch": 0.33497536945812806, "percentage": 11.17, "elapsed_time": "0:24:31", "remaining_time": "3:15:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 137, "total_steps": 1218, "loss": 1.1082, "learning_rate": 1.999075803642243e-05, "epoch": 0.3374384236453202, "percentage": 11.25, "elapsed_time": "0:24:41", "remaining_time": "3:14:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 138, "total_steps": 1218, "loss": 1.2668, "learning_rate": 1.9989484922416503e-05, "epoch": 0.3399014778325123, "percentage": 11.33, "elapsed_time": "0:24:52", "remaining_time": "3:14:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 139, "total_steps": 1218, "loss": 1.1992, "learning_rate": 1.998812973141789e-05, "epoch": 0.34236453201970446, "percentage": 11.41, "elapsed_time": "0:25:01", "remaining_time": "3:14:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 140, "total_steps": 1218, "loss": 1.1272, "learning_rate": 1.9986692474561292e-05, "epoch": 0.3448275862068966, "percentage": 11.49, "elapsed_time": "0:25:12", "remaining_time": "3:14:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 141, "total_steps": 1218, "loss": 1.1604, "learning_rate": 1.9985173163655706e-05, "epoch": 0.3472906403940887, "percentage": 11.58, "elapsed_time": "0:25:24", "remaining_time": "3:14:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 142, "total_steps": 1218, "loss": 1.3596, "learning_rate": 1.9983571811184297e-05, "epoch": 0.3497536945812808, "percentage": 11.66, "elapsed_time": "0:25:35", "remaining_time": "3:13:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 143, "total_steps": 1218, "loss": 1.1783, "learning_rate": 1.998188843030433e-05, "epoch": 0.3522167487684729, "percentage": 11.74, "elapsed_time": "0:25:45", "remaining_time": "3:13:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 144, "total_steps": 1218, "loss": 1.1358, "learning_rate": 1.9980123034847025e-05, "epoch": 0.35467980295566504, "percentage": 11.82, "elapsed_time": "0:25:57", "remaining_time": "3:13:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 145, "total_steps": 1218, "loss": 1.2869, "learning_rate": 1.9978275639317476e-05, "epoch": 0.35714285714285715, "percentage": 11.9, "elapsed_time": "0:26:11", "remaining_time": "3:13:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 146, "total_steps": 1218, "loss": 1.2137, "learning_rate": 1.9976346258894502e-05, "epoch": 0.35960591133004927, "percentage": 11.99, "elapsed_time": "0:26:21", "remaining_time": "3:13:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 147, "total_steps": 1218, "loss": 1.2011, "learning_rate": 1.9974334909430553e-05, "epoch": 0.3620689655172414, "percentage": 12.07, "elapsed_time": "0:26:31", "remaining_time": "3:13:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 148, "total_steps": 1218, "loss": 1.2163, "learning_rate": 1.9972241607451552e-05, "epoch": 0.3645320197044335, "percentage": 12.15, "elapsed_time": "0:26:40", "remaining_time": "3:12:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 149, "total_steps": 1218, "loss": 1.2251, "learning_rate": 1.9970066370156783e-05, "epoch": 0.3669950738916256, "percentage": 12.23, "elapsed_time": "0:26:50", "remaining_time": "3:12:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 150, "total_steps": 1218, "loss": 1.1836, "learning_rate": 1.996780921541873e-05, "epoch": 0.3694581280788177, "percentage": 12.32, "elapsed_time": "0:27:01", "remaining_time": "3:12:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 151, "total_steps": 1218, "loss": 1.2689, "learning_rate": 1.9965470161782942e-05, "epoch": 0.37192118226600984, "percentage": 12.4, "elapsed_time": "0:27:11", "remaining_time": "3:12:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 152, "total_steps": 1218, "loss": 1.1665, "learning_rate": 1.9963049228467875e-05, "epoch": 0.37438423645320196, "percentage": 12.48, "elapsed_time": "0:27:22", "remaining_time": "3:11:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 153, "total_steps": 1218, "loss": 1.2165, "learning_rate": 1.996054643536474e-05, "epoch": 0.3768472906403941, "percentage": 12.56, "elapsed_time": "0:27:33", "remaining_time": "3:11:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 154, "total_steps": 1218, "loss": 1.2366, "learning_rate": 1.9957961803037325e-05, "epoch": 0.3793103448275862, "percentage": 12.64, "elapsed_time": "0:27:43", "remaining_time": "3:11:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 155, "total_steps": 1218, "loss": 1.1961, "learning_rate": 1.9955295352721854e-05, "epoch": 0.3817733990147783, "percentage": 12.73, "elapsed_time": "0:27:54", "remaining_time": "3:11:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 156, "total_steps": 1218, "loss": 1.2157, "learning_rate": 1.9952547106326787e-05, "epoch": 0.3842364532019704, "percentage": 12.81, "elapsed_time": "0:28:04", "remaining_time": "3:11:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 157, "total_steps": 1218, "loss": 1.2075, "learning_rate": 1.9949717086432637e-05, "epoch": 0.3866995073891626, "percentage": 12.89, "elapsed_time": "0:28:14", "remaining_time": "3:10:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 158, "total_steps": 1218, "loss": 1.2725, "learning_rate": 1.9946805316291817e-05, "epoch": 0.3891625615763547, "percentage": 12.97, "elapsed_time": "0:28:24", "remaining_time": "3:10:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 159, "total_steps": 1218, "loss": 1.1786, "learning_rate": 1.994381181982841e-05, "epoch": 0.3916256157635468, "percentage": 13.05, "elapsed_time": "0:28:33", "remaining_time": "3:10:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 160, "total_steps": 1218, "loss": 1.2017, "learning_rate": 1.9940736621638e-05, "epoch": 0.39408866995073893, "percentage": 13.14, "elapsed_time": "0:28:45", "remaining_time": "3:10:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 161, "total_steps": 1218, "loss": 1.1513, "learning_rate": 1.993757974698746e-05, "epoch": 0.39655172413793105, "percentage": 13.22, "elapsed_time": "0:28:57", "remaining_time": "3:10:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 162, "total_steps": 1218, "loss": 1.1983, "learning_rate": 1.993434122181474e-05, "epoch": 0.39901477832512317, "percentage": 13.3, "elapsed_time": "0:29:06", "remaining_time": "3:09:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 163, "total_steps": 1218, "loss": 1.1303, "learning_rate": 1.9931021072728658e-05, "epoch": 0.4014778325123153, "percentage": 13.38, "elapsed_time": "0:29:16", "remaining_time": "3:09:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 164, "total_steps": 1218, "loss": 1.1482, "learning_rate": 1.992761932700868e-05, "epoch": 0.4039408866995074, "percentage": 13.46, "elapsed_time": "0:29:28", "remaining_time": "3:09:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 165, "total_steps": 1218, "loss": 1.141, "learning_rate": 1.9924136012604714e-05, "epoch": 0.4064039408866995, "percentage": 13.55, "elapsed_time": "0:29:40", "remaining_time": "3:09:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 166, "total_steps": 1218, "loss": 1.1279, "learning_rate": 1.9920571158136837e-05, "epoch": 0.4088669950738916, "percentage": 13.63, "elapsed_time": "0:29:50", "remaining_time": "3:09:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 167, "total_steps": 1218, "loss": 1.2717, "learning_rate": 1.9916924792895112e-05, "epoch": 0.41133004926108374, "percentage": 13.71, "elapsed_time": "0:30:00", "remaining_time": "3:08:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 168, "total_steps": 1218, "loss": 1.2269, "learning_rate": 1.9913196946839304e-05, "epoch": 0.41379310344827586, "percentage": 13.79, "elapsed_time": "0:30:11", "remaining_time": "3:08:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 169, "total_steps": 1218, "loss": 1.1724, "learning_rate": 1.9909387650598665e-05, "epoch": 0.41625615763546797, "percentage": 13.88, "elapsed_time": "0:30:21", "remaining_time": "3:08:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 170, "total_steps": 1218, "loss": 1.2654, "learning_rate": 1.990549693547166e-05, "epoch": 0.4187192118226601, "percentage": 13.96, "elapsed_time": "0:30:31", "remaining_time": "3:08:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 171, "total_steps": 1218, "loss": 1.1777, "learning_rate": 1.9901524833425724e-05, "epoch": 0.4211822660098522, "percentage": 14.04, "elapsed_time": "0:30:41", "remaining_time": "3:07:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 172, "total_steps": 1218, "loss": 1.2009, "learning_rate": 1.9897471377096992e-05, "epoch": 0.4236453201970443, "percentage": 14.12, "elapsed_time": "0:30:53", "remaining_time": "3:07:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 173, "total_steps": 1218, "loss": 1.2525, "learning_rate": 1.9893336599790034e-05, "epoch": 0.42610837438423643, "percentage": 14.2, "elapsed_time": "0:31:04", "remaining_time": "3:07:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 174, "total_steps": 1218, "loss": 1.2491, "learning_rate": 1.9889120535477584e-05, "epoch": 0.42857142857142855, "percentage": 14.29, "elapsed_time": "0:31:15", "remaining_time": "3:07:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 175, "total_steps": 1218, "loss": 1.0366, "learning_rate": 1.9884823218800255e-05, "epoch": 0.43103448275862066, "percentage": 14.37, "elapsed_time": "0:31:30", "remaining_time": "3:07:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 176, "total_steps": 1218, "loss": 1.209, "learning_rate": 1.9880444685066252e-05, "epoch": 0.43349753694581283, "percentage": 14.45, "elapsed_time": "0:31:41", "remaining_time": "3:07:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 177, "total_steps": 1218, "loss": 1.1439, "learning_rate": 1.9875984970251095e-05, "epoch": 0.43596059113300495, "percentage": 14.53, "elapsed_time": "0:31:52", "remaining_time": "3:07:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 178, "total_steps": 1218, "loss": 1.1447, "learning_rate": 1.987144411099731e-05, "epoch": 0.43842364532019706, "percentage": 14.61, "elapsed_time": "0:32:04", "remaining_time": "3:07:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 179, "total_steps": 1218, "loss": 1.2291, "learning_rate": 1.9866822144614143e-05, "epoch": 0.4408866995073892, "percentage": 14.7, "elapsed_time": "0:32:14", "remaining_time": "3:07:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 180, "total_steps": 1218, "loss": 1.2764, "learning_rate": 1.9862119109077226e-05, "epoch": 0.4433497536945813, "percentage": 14.78, "elapsed_time": "0:32:24", "remaining_time": "3:06:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 181, "total_steps": 1218, "loss": 1.1659, "learning_rate": 1.9857335043028297e-05, "epoch": 0.4458128078817734, "percentage": 14.86, "elapsed_time": "0:32:35", "remaining_time": "3:06:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 182, "total_steps": 1218, "loss": 1.2003, "learning_rate": 1.985246998577486e-05, "epoch": 0.4482758620689655, "percentage": 14.94, "elapsed_time": "0:32:46", "remaining_time": "3:06:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 183, "total_steps": 1218, "loss": 1.1489, "learning_rate": 1.984752397728988e-05, "epoch": 0.45073891625615764, "percentage": 15.02, "elapsed_time": "0:32:56", "remaining_time": "3:06:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 184, "total_steps": 1218, "loss": 1.2502, "learning_rate": 1.984249705821143e-05, "epoch": 0.45320197044334976, "percentage": 15.11, "elapsed_time": "0:33:07", "remaining_time": "3:06:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 185, "total_steps": 1218, "loss": 1.2042, "learning_rate": 1.983738926984239e-05, "epoch": 0.45566502463054187, "percentage": 15.19, "elapsed_time": "0:33:17", "remaining_time": "3:05:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 186, "total_steps": 1218, "loss": 1.2205, "learning_rate": 1.9832200654150077e-05, "epoch": 0.458128078817734, "percentage": 15.27, "elapsed_time": "0:33:27", "remaining_time": "3:05:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 187, "total_steps": 1218, "loss": 1.2431, "learning_rate": 1.9826931253765907e-05, "epoch": 0.4605911330049261, "percentage": 15.35, "elapsed_time": "0:33:37", "remaining_time": "3:05:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 188, "total_steps": 1218, "loss": 1.1479, "learning_rate": 1.9821581111985072e-05, "epoch": 0.4630541871921182, "percentage": 15.44, "elapsed_time": "0:33:48", "remaining_time": "3:05:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 189, "total_steps": 1218, "loss": 1.2477, "learning_rate": 1.9816150272766136e-05, "epoch": 0.46551724137931033, "percentage": 15.52, "elapsed_time": "0:33:58", "remaining_time": "3:04:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 190, "total_steps": 1218, "loss": 1.1717, "learning_rate": 1.981063878073073e-05, "epoch": 0.46798029556650245, "percentage": 15.6, "elapsed_time": "0:34:08", "remaining_time": "3:04:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 191, "total_steps": 1218, "loss": 1.2328, "learning_rate": 1.9805046681163124e-05, "epoch": 0.47044334975369456, "percentage": 15.68, "elapsed_time": "0:34:18", "remaining_time": "3:04:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 192, "total_steps": 1218, "loss": 1.1088, "learning_rate": 1.979937402000991e-05, "epoch": 0.4729064039408867, "percentage": 15.76, "elapsed_time": "0:34:28", "remaining_time": "3:04:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 193, "total_steps": 1218, "loss": 1.1787, "learning_rate": 1.9793620843879594e-05, "epoch": 0.4753694581280788, "percentage": 15.85, "elapsed_time": "0:34:39", "remaining_time": "3:04:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 194, "total_steps": 1218, "loss": 1.211, "learning_rate": 1.9787787200042224e-05, "epoch": 0.47783251231527096, "percentage": 15.93, "elapsed_time": "0:34:48", "remaining_time": "3:03:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 195, "total_steps": 1218, "loss": 1.2036, "learning_rate": 1.9781873136428985e-05, "epoch": 0.4802955665024631, "percentage": 16.01, "elapsed_time": "0:35:00", "remaining_time": "3:03:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 196, "total_steps": 1218, "loss": 1.2282, "learning_rate": 1.977587870163184e-05, "epoch": 0.4827586206896552, "percentage": 16.09, "elapsed_time": "0:35:11", "remaining_time": "3:03:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 197, "total_steps": 1218, "loss": 1.1701, "learning_rate": 1.9769803944903084e-05, "epoch": 0.4852216748768473, "percentage": 16.17, "elapsed_time": "0:35:21", "remaining_time": "3:03:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 198, "total_steps": 1218, "loss": 1.1916, "learning_rate": 1.9763648916154982e-05, "epoch": 0.4876847290640394, "percentage": 16.26, "elapsed_time": "0:35:31", "remaining_time": "3:02:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 199, "total_steps": 1218, "loss": 1.175, "learning_rate": 1.9757413665959337e-05, "epoch": 0.49014778325123154, "percentage": 16.34, "elapsed_time": "0:35:41", "remaining_time": "3:02:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 200, "total_steps": 1218, "loss": 1.1911, "learning_rate": 1.975109824554707e-05, "epoch": 0.49261083743842365, "percentage": 16.42, "elapsed_time": "0:35:51", "remaining_time": "3:02:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 201, "total_steps": 1218, "loss": 1.1619, "learning_rate": 1.9744702706807825e-05, "epoch": 0.49507389162561577, "percentage": 16.5, "elapsed_time": "0:36:01", "remaining_time": "3:02:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 202, "total_steps": 1218, "loss": 1.2238, "learning_rate": 1.973822710228951e-05, "epoch": 0.4975369458128079, "percentage": 16.58, "elapsed_time": "0:36:12", "remaining_time": "3:02:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 203, "total_steps": 1218, "loss": 1.2679, "learning_rate": 1.9731671485197884e-05, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:36:21", "remaining_time": "3:01:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 204, "total_steps": 1218, "loss": 1.2317, "learning_rate": 1.972503590939612e-05, "epoch": 0.5024630541871922, "percentage": 16.75, "elapsed_time": "0:36:31", "remaining_time": "3:01:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 205, "total_steps": 1218, "loss": 1.1789, "learning_rate": 1.971832042940436e-05, "epoch": 0.5049261083743842, "percentage": 16.83, "elapsed_time": "0:36:40", "remaining_time": "3:01:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 206, "total_steps": 1218, "loss": 1.2282, "learning_rate": 1.971152510039926e-05, "epoch": 0.5073891625615764, "percentage": 16.91, "elapsed_time": "0:36:50", "remaining_time": "3:01:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 207, "total_steps": 1218, "loss": 1.1857, "learning_rate": 1.9704649978213545e-05, "epoch": 0.5098522167487685, "percentage": 17.0, "elapsed_time": "0:37:01", "remaining_time": "3:00:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 208, "total_steps": 1218, "loss": 1.0999, "learning_rate": 1.9697695119335547e-05, "epoch": 0.5123152709359606, "percentage": 17.08, "elapsed_time": "0:37:11", "remaining_time": "3:00:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 209, "total_steps": 1218, "loss": 1.2547, "learning_rate": 1.9690660580908746e-05, "epoch": 0.5147783251231527, "percentage": 17.16, "elapsed_time": "0:37:21", "remaining_time": "3:00:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 210, "total_steps": 1218, "loss": 1.2453, "learning_rate": 1.9683546420731292e-05, "epoch": 0.5172413793103449, "percentage": 17.24, "elapsed_time": "0:37:34", "remaining_time": "3:00:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 211, "total_steps": 1218, "loss": 1.2397, "learning_rate": 1.9676352697255535e-05, "epoch": 0.5197044334975369, "percentage": 17.32, "elapsed_time": "0:37:46", "remaining_time": "3:00:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 212, "total_steps": 1218, "loss": 1.1987, "learning_rate": 1.9669079469587548e-05, "epoch": 0.5221674876847291, "percentage": 17.41, "elapsed_time": "0:37:56", "remaining_time": "3:00:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 213, "total_steps": 1218, "loss": 1.2121, "learning_rate": 1.9661726797486625e-05, "epoch": 0.5246305418719212, "percentage": 17.49, "elapsed_time": "0:38:08", "remaining_time": "2:59:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 214, "total_steps": 1218, "loss": 1.2217, "learning_rate": 1.965429474136482e-05, "epoch": 0.5270935960591133, "percentage": 17.57, "elapsed_time": "0:38:19", "remaining_time": "2:59:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 215, "total_steps": 1218, "loss": 1.2421, "learning_rate": 1.964678336228642e-05, "epoch": 0.5295566502463054, "percentage": 17.65, "elapsed_time": "0:38:29", "remaining_time": "2:59:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 216, "total_steps": 1218, "loss": 1.2221, "learning_rate": 1.963919272196746e-05, "epoch": 0.5320197044334976, "percentage": 17.73, "elapsed_time": "0:38:39", "remaining_time": "2:59:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 217, "total_steps": 1218, "loss": 1.2473, "learning_rate": 1.9631522882775217e-05, "epoch": 0.5344827586206896, "percentage": 17.82, "elapsed_time": "0:38:50", "remaining_time": "2:59:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 218, "total_steps": 1218, "loss": 1.2446, "learning_rate": 1.9623773907727682e-05, "epoch": 0.5369458128078818, "percentage": 17.9, "elapsed_time": "0:39:01", "remaining_time": "2:58:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 219, "total_steps": 1218, "loss": 1.224, "learning_rate": 1.9615945860493063e-05, "epoch": 0.5394088669950738, "percentage": 17.98, "elapsed_time": "0:39:10", "remaining_time": "2:58:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 220, "total_steps": 1218, "loss": 1.2218, "learning_rate": 1.9608038805389253e-05, "epoch": 0.541871921182266, "percentage": 18.06, "elapsed_time": "0:39:19", "remaining_time": "2:58:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 221, "total_steps": 1218, "loss": 1.2438, "learning_rate": 1.9600052807383285e-05, "epoch": 0.5443349753694581, "percentage": 18.14, "elapsed_time": "0:39:30", "remaining_time": "2:58:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 222, "total_steps": 1218, "loss": 1.2647, "learning_rate": 1.9591987932090836e-05, "epoch": 0.5467980295566502, "percentage": 18.23, "elapsed_time": "0:39:42", "remaining_time": "2:58:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 223, "total_steps": 1218, "loss": 1.1673, "learning_rate": 1.9583844245775647e-05, "epoch": 0.5492610837438424, "percentage": 18.31, "elapsed_time": "0:39:51", "remaining_time": "2:57:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 224, "total_steps": 1218, "loss": 1.1771, "learning_rate": 1.9575621815349e-05, "epoch": 0.5517241379310345, "percentage": 18.39, "elapsed_time": "0:40:02", "remaining_time": "2:57:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 225, "total_steps": 1218, "loss": 1.2122, "learning_rate": 1.9567320708369178e-05, "epoch": 0.5541871921182266, "percentage": 18.47, "elapsed_time": "0:40:12", "remaining_time": "2:57:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 226, "total_steps": 1218, "loss": 1.0954, "learning_rate": 1.9558940993040885e-05, "epoch": 0.5566502463054187, "percentage": 18.56, "elapsed_time": "0:40:22", "remaining_time": "2:57:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 227, "total_steps": 1218, "loss": 1.2657, "learning_rate": 1.95504827382147e-05, "epoch": 0.5591133004926109, "percentage": 18.64, "elapsed_time": "0:40:36", "remaining_time": "2:57:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 228, "total_steps": 1218, "loss": 1.2246, "learning_rate": 1.954194601338651e-05, "epoch": 0.5615763546798029, "percentage": 18.72, "elapsed_time": "0:40:47", "remaining_time": "2:57:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 229, "total_steps": 1218, "loss": 1.1612, "learning_rate": 1.9533330888696943e-05, "epoch": 0.5640394088669951, "percentage": 18.8, "elapsed_time": "0:40:57", "remaining_time": "2:56:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 230, "total_steps": 1218, "loss": 1.1355, "learning_rate": 1.952463743493078e-05, "epoch": 0.5665024630541872, "percentage": 18.88, "elapsed_time": "0:41:06", "remaining_time": "2:56:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 231, "total_steps": 1218, "loss": 1.1364, "learning_rate": 1.9515865723516375e-05, "epoch": 0.5689655172413793, "percentage": 18.97, "elapsed_time": "0:41:21", "remaining_time": "2:56:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 232, "total_steps": 1218, "loss": 1.2279, "learning_rate": 1.9507015826525096e-05, "epoch": 0.5714285714285714, "percentage": 19.05, "elapsed_time": "0:41:32", "remaining_time": "2:56:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 233, "total_steps": 1218, "loss": 1.22, "learning_rate": 1.9498087816670685e-05, "epoch": 0.5738916256157636, "percentage": 19.13, "elapsed_time": "0:41:42", "remaining_time": "2:56:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 234, "total_steps": 1218, "loss": 1.2364, "learning_rate": 1.9489081767308696e-05, "epoch": 0.5763546798029556, "percentage": 19.21, "elapsed_time": "0:41:53", "remaining_time": "2:56:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 235, "total_steps": 1218, "loss": 1.2269, "learning_rate": 1.9479997752435886e-05, "epoch": 0.5788177339901478, "percentage": 19.29, "elapsed_time": "0:42:03", "remaining_time": "2:55:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 236, "total_steps": 1218, "loss": 1.2456, "learning_rate": 1.9470835846689596e-05, "epoch": 0.5812807881773399, "percentage": 19.38, "elapsed_time": "0:42:13", "remaining_time": "2:55:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 237, "total_steps": 1218, "loss": 1.3204, "learning_rate": 1.946159612534715e-05, "epoch": 0.583743842364532, "percentage": 19.46, "elapsed_time": "0:42:27", "remaining_time": "2:55:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 238, "total_steps": 1218, "loss": 1.1944, "learning_rate": 1.9452278664325227e-05, "epoch": 0.5862068965517241, "percentage": 19.54, "elapsed_time": "0:42:37", "remaining_time": "2:55:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 239, "total_steps": 1218, "loss": 1.1549, "learning_rate": 1.9442883540179243e-05, "epoch": 0.5886699507389163, "percentage": 19.62, "elapsed_time": "0:42:47", "remaining_time": "2:55:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 240, "total_steps": 1218, "loss": 1.1204, "learning_rate": 1.9433410830102724e-05, "epoch": 0.5911330049261084, "percentage": 19.7, "elapsed_time": "0:42:58", "remaining_time": "2:55:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 241, "total_steps": 1218, "loss": 1.2345, "learning_rate": 1.9423860611926667e-05, "epoch": 0.5935960591133005, "percentage": 19.79, "elapsed_time": "0:43:08", "remaining_time": "2:54:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 242, "total_steps": 1218, "loss": 1.1648, "learning_rate": 1.9414232964118893e-05, "epoch": 0.5960591133004927, "percentage": 19.87, "elapsed_time": "0:43:19", "remaining_time": "2:54:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 243, "total_steps": 1218, "loss": 1.2316, "learning_rate": 1.9404527965783423e-05, "epoch": 0.5985221674876847, "percentage": 19.95, "elapsed_time": "0:43:32", "remaining_time": "2:54:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 244, "total_steps": 1218, "loss": 1.2144, "learning_rate": 1.939474569665981e-05, "epoch": 0.6009852216748769, "percentage": 20.03, "elapsed_time": "0:43:45", "remaining_time": "2:54:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 245, "total_steps": 1218, "loss": 1.2159, "learning_rate": 1.9384886237122496e-05, "epoch": 0.603448275862069, "percentage": 20.11, "elapsed_time": "0:43:57", "remaining_time": "2:54:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 246, "total_steps": 1218, "loss": 1.1254, "learning_rate": 1.937494966818014e-05, "epoch": 0.6059113300492611, "percentage": 20.2, "elapsed_time": "0:44:09", "remaining_time": "2:54:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 247, "total_steps": 1218, "loss": 1.1451, "learning_rate": 1.936493607147495e-05, "epoch": 0.6083743842364532, "percentage": 20.28, "elapsed_time": "0:44:19", "remaining_time": "2:54:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 248, "total_steps": 1218, "loss": 1.1092, "learning_rate": 1.9354845529282042e-05, "epoch": 0.6108374384236454, "percentage": 20.36, "elapsed_time": "0:44:28", "remaining_time": "2:53:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 249, "total_steps": 1218, "loss": 1.1736, "learning_rate": 1.9344678124508718e-05, "epoch": 0.6133004926108374, "percentage": 20.44, "elapsed_time": "0:44:40", "remaining_time": "2:53:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 250, "total_steps": 1218, "loss": 1.1853, "learning_rate": 1.933443394069383e-05, "epoch": 0.6157635467980296, "percentage": 20.53, "elapsed_time": "0:44:50", "remaining_time": "2:53:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 251, "total_steps": 1218, "loss": 1.208, "learning_rate": 1.9324113062007056e-05, "epoch": 0.6182266009852216, "percentage": 20.61, "elapsed_time": "0:45:00", "remaining_time": "2:53:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 252, "total_steps": 1218, "loss": 1.1716, "learning_rate": 1.9313715573248238e-05, "epoch": 0.6206896551724138, "percentage": 20.69, "elapsed_time": "0:45:10", "remaining_time": "2:53:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 253, "total_steps": 1218, "loss": 1.1773, "learning_rate": 1.9303241559846664e-05, "epoch": 0.6231527093596059, "percentage": 20.77, "elapsed_time": "0:45:21", "remaining_time": "2:53:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 254, "total_steps": 1218, "loss": 1.2331, "learning_rate": 1.9292691107860374e-05, "epoch": 0.625615763546798, "percentage": 20.85, "elapsed_time": "0:45:30", "remaining_time": "2:52:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 255, "total_steps": 1218, "loss": 1.122, "learning_rate": 1.928206430397546e-05, "epoch": 0.6280788177339901, "percentage": 20.94, "elapsed_time": "0:45:40", "remaining_time": "2:52:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 256, "total_steps": 1218, "loss": 1.1737, "learning_rate": 1.927136123550534e-05, "epoch": 0.6305418719211823, "percentage": 21.02, "elapsed_time": "0:45:49", "remaining_time": "2:52:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 257, "total_steps": 1218, "loss": 1.2649, "learning_rate": 1.9260581990390056e-05, "epoch": 0.6330049261083743, "percentage": 21.1, "elapsed_time": "0:45:59", "remaining_time": "2:51:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 258, "total_steps": 1218, "loss": 1.1599, "learning_rate": 1.9249726657195534e-05, "epoch": 0.6354679802955665, "percentage": 21.18, "elapsed_time": "0:46:09", "remaining_time": "2:51:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 259, "total_steps": 1218, "loss": 1.093, "learning_rate": 1.9238795325112867e-05, "epoch": 0.6379310344827587, "percentage": 21.26, "elapsed_time": "0:46:20", "remaining_time": "2:51:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 260, "total_steps": 1218, "loss": 1.1583, "learning_rate": 1.922778808395759e-05, "epoch": 0.6403940886699507, "percentage": 21.35, "elapsed_time": "0:46:30", "remaining_time": "2:51:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 261, "total_steps": 1218, "loss": 1.1272, "learning_rate": 1.921670502416892e-05, "epoch": 0.6428571428571429, "percentage": 21.43, "elapsed_time": "0:46:42", "remaining_time": "2:51:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 262, "total_steps": 1218, "loss": 1.2681, "learning_rate": 1.9205546236809037e-05, "epoch": 0.645320197044335, "percentage": 21.51, "elapsed_time": "0:46:54", "remaining_time": "2:51:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 263, "total_steps": 1218, "loss": 1.1932, "learning_rate": 1.919431181356231e-05, "epoch": 0.6477832512315271, "percentage": 21.59, "elapsed_time": "0:47:05", "remaining_time": "2:50:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 264, "total_steps": 1218, "loss": 1.1863, "learning_rate": 1.9183001846734573e-05, "epoch": 0.6502463054187192, "percentage": 21.67, "elapsed_time": "0:47:18", "remaining_time": "2:50:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 265, "total_steps": 1218, "loss": 1.2369, "learning_rate": 1.9171616429252345e-05, "epoch": 0.6527093596059114, "percentage": 21.76, "elapsed_time": "0:47:28", "remaining_time": "2:50:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 266, "total_steps": 1218, "loss": 1.1865, "learning_rate": 1.9160155654662075e-05, "epoch": 0.6551724137931034, "percentage": 21.84, "elapsed_time": "0:47:43", "remaining_time": "2:50:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 267, "total_steps": 1218, "loss": 1.1075, "learning_rate": 1.9148619617129364e-05, "epoch": 0.6576354679802956, "percentage": 21.92, "elapsed_time": "0:47:55", "remaining_time": "2:50:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 268, "total_steps": 1218, "loss": 1.1057, "learning_rate": 1.9137008411438213e-05, "epoch": 0.6600985221674877, "percentage": 22.0, "elapsed_time": "0:48:07", "remaining_time": "2:50:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 269, "total_steps": 1218, "loss": 1.1109, "learning_rate": 1.9125322132990215e-05, "epoch": 0.6625615763546798, "percentage": 22.09, "elapsed_time": "0:48:16", "remaining_time": "2:50:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 270, "total_steps": 1218, "loss": 1.1637, "learning_rate": 1.9113560877803798e-05, "epoch": 0.6650246305418719, "percentage": 22.17, "elapsed_time": "0:48:27", "remaining_time": "2:50:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 271, "total_steps": 1218, "loss": 1.1443, "learning_rate": 1.910172474251341e-05, "epoch": 0.6674876847290641, "percentage": 22.25, "elapsed_time": "0:48:41", "remaining_time": "2:50:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 272, "total_steps": 1218, "loss": 1.1825, "learning_rate": 1.9089813824368765e-05, "epoch": 0.6699507389162561, "percentage": 22.33, "elapsed_time": "0:48:51", "remaining_time": "2:49:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 273, "total_steps": 1218, "loss": 1.1977, "learning_rate": 1.907782822123399e-05, "epoch": 0.6724137931034483, "percentage": 22.41, "elapsed_time": "0:49:02", "remaining_time": "2:49:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 274, "total_steps": 1218, "loss": 1.1979, "learning_rate": 1.9065768031586864e-05, "epoch": 0.6748768472906403, "percentage": 22.5, "elapsed_time": "0:49:13", "remaining_time": "2:49:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 275, "total_steps": 1218, "loss": 1.1391, "learning_rate": 1.905363335451799e-05, "epoch": 0.6773399014778325, "percentage": 22.58, "elapsed_time": "0:49:22", "remaining_time": "2:49:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 276, "total_steps": 1218, "loss": 1.2104, "learning_rate": 1.9041424289729994e-05, "epoch": 0.6798029556650246, "percentage": 22.66, "elapsed_time": "0:49:33", "remaining_time": "2:49:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 277, "total_steps": 1218, "loss": 1.1788, "learning_rate": 1.9029140937536676e-05, "epoch": 0.6822660098522167, "percentage": 22.74, "elapsed_time": "0:49:43", "remaining_time": "2:48:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 278, "total_steps": 1218, "loss": 1.2575, "learning_rate": 1.901678339886223e-05, "epoch": 0.6847290640394089, "percentage": 22.82, "elapsed_time": "0:49:54", "remaining_time": "2:48:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 279, "total_steps": 1218, "loss": 1.1017, "learning_rate": 1.9004351775240376e-05, "epoch": 0.687192118226601, "percentage": 22.91, "elapsed_time": "0:50:03", "remaining_time": "2:48:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 280, "total_steps": 1218, "loss": 1.2713, "learning_rate": 1.8991846168813547e-05, "epoch": 0.6896551724137931, "percentage": 22.99, "elapsed_time": "0:50:14", "remaining_time": "2:48:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 281, "total_steps": 1218, "loss": 1.1888, "learning_rate": 1.897926668233204e-05, "epoch": 0.6921182266009852, "percentage": 23.07, "elapsed_time": "0:50:24", "remaining_time": "2:48:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 282, "total_steps": 1218, "loss": 1.2381, "learning_rate": 1.896661341915318e-05, "epoch": 0.6945812807881774, "percentage": 23.15, "elapsed_time": "0:50:35", "remaining_time": "2:47:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 283, "total_steps": 1218, "loss": 1.1747, "learning_rate": 1.8953886483240465e-05, "epoch": 0.6970443349753694, "percentage": 23.23, "elapsed_time": "0:50:46", "remaining_time": "2:47:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 284, "total_steps": 1218, "loss": 1.2231, "learning_rate": 1.8941085979162714e-05, "epoch": 0.6995073891625616, "percentage": 23.32, "elapsed_time": "0:50:56", "remaining_time": "2:47:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 285, "total_steps": 1218, "loss": 1.1037, "learning_rate": 1.8928212012093204e-05, "epoch": 0.7019704433497537, "percentage": 23.4, "elapsed_time": "0:51:07", "remaining_time": "2:47:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 286, "total_steps": 1218, "loss": 1.2211, "learning_rate": 1.891526468780881e-05, "epoch": 0.7044334975369458, "percentage": 23.48, "elapsed_time": "0:51:18", "remaining_time": "2:47:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 287, "total_steps": 1218, "loss": 1.2476, "learning_rate": 1.8902244112689128e-05, "epoch": 0.7068965517241379, "percentage": 23.56, "elapsed_time": "0:51:29", "remaining_time": "2:47:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 288, "total_steps": 1218, "loss": 1.2508, "learning_rate": 1.8889150393715627e-05, "epoch": 0.7093596059113301, "percentage": 23.65, "elapsed_time": "0:51:41", "remaining_time": "2:46:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 289, "total_steps": 1218, "loss": 1.108, "learning_rate": 1.8875983638470732e-05, "epoch": 0.7118226600985221, "percentage": 23.73, "elapsed_time": "0:51:52", "remaining_time": "2:46:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 290, "total_steps": 1218, "loss": 1.2004, "learning_rate": 1.8862743955136966e-05, "epoch": 0.7142857142857143, "percentage": 23.81, "elapsed_time": "0:52:01", "remaining_time": "2:46:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 291, "total_steps": 1218, "loss": 1.0691, "learning_rate": 1.8849431452496053e-05, "epoch": 0.7167487684729064, "percentage": 23.89, "elapsed_time": "0:52:15", "remaining_time": "2:46:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 292, "total_steps": 1218, "loss": 1.1709, "learning_rate": 1.8836046239928025e-05, "epoch": 0.7192118226600985, "percentage": 23.97, "elapsed_time": "0:52:26", "remaining_time": "2:46:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 293, "total_steps": 1218, "loss": 1.2534, "learning_rate": 1.8822588427410324e-05, "epoch": 0.7216748768472906, "percentage": 24.06, "elapsed_time": "0:52:42", "remaining_time": "2:46:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 294, "total_steps": 1218, "loss": 1.1848, "learning_rate": 1.8809058125516894e-05, "epoch": 0.7241379310344828, "percentage": 24.14, "elapsed_time": "0:52:53", "remaining_time": "2:46:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 295, "total_steps": 1218, "loss": 1.2027, "learning_rate": 1.8795455445417286e-05, "epoch": 0.7266009852216748, "percentage": 24.22, "elapsed_time": "0:53:04", "remaining_time": "2:46:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 296, "total_steps": 1218, "loss": 1.1937, "learning_rate": 1.8781780498875727e-05, "epoch": 0.729064039408867, "percentage": 24.3, "elapsed_time": "0:53:15", "remaining_time": "2:45:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 297, "total_steps": 1218, "loss": 1.2581, "learning_rate": 1.8768033398250203e-05, "epoch": 0.7315270935960592, "percentage": 24.38, "elapsed_time": "0:53:24", "remaining_time": "2:45:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 298, "total_steps": 1218, "loss": 1.2148, "learning_rate": 1.8754214256491564e-05, "epoch": 0.7339901477832512, "percentage": 24.47, "elapsed_time": "0:53:38", "remaining_time": "2:45:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 299, "total_steps": 1218, "loss": 1.2825, "learning_rate": 1.874032318714255e-05, "epoch": 0.7364532019704434, "percentage": 24.55, "elapsed_time": "0:53:48", "remaining_time": "2:45:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 300, "total_steps": 1218, "loss": 1.2107, "learning_rate": 1.8726360304336896e-05, "epoch": 0.7389162561576355, "percentage": 24.63, "elapsed_time": "0:53:58", "remaining_time": "2:45:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 301, "total_steps": 1218, "loss": 1.2195, "learning_rate": 1.8712325722798376e-05, "epoch": 0.7413793103448276, "percentage": 24.71, "elapsed_time": "0:54:08", "remaining_time": "2:44:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 302, "total_steps": 1218, "loss": 1.1619, "learning_rate": 1.8698219557839875e-05, "epoch": 0.7438423645320197, "percentage": 24.79, "elapsed_time": "0:54:20", "remaining_time": "2:44:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 303, "total_steps": 1218, "loss": 1.13, "learning_rate": 1.8684041925362412e-05, "epoch": 0.7463054187192119, "percentage": 24.88, "elapsed_time": "0:54:30", "remaining_time": "2:44:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 304, "total_steps": 1218, "loss": 1.1999, "learning_rate": 1.866979294185423e-05, "epoch": 0.7487684729064039, "percentage": 24.96, "elapsed_time": "0:54:43", "remaining_time": "2:44:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 305, "total_steps": 1218, "loss": 1.1627, "learning_rate": 1.8655472724389798e-05, "epoch": 0.7512315270935961, "percentage": 25.04, "elapsed_time": "0:54:53", "remaining_time": "2:44:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 306, "total_steps": 1218, "loss": 1.2837, "learning_rate": 1.864108139062888e-05, "epoch": 0.7536945812807881, "percentage": 25.12, "elapsed_time": "0:55:03", "remaining_time": "2:44:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 307, "total_steps": 1218, "loss": 1.1429, "learning_rate": 1.8626619058815546e-05, "epoch": 0.7561576354679803, "percentage": 25.21, "elapsed_time": "0:55:14", "remaining_time": "2:43:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 308, "total_steps": 1218, "loss": 1.1501, "learning_rate": 1.8612085847777215e-05, "epoch": 0.7586206896551724, "percentage": 25.29, "elapsed_time": "0:55:24", "remaining_time": "2:43:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 309, "total_steps": 1218, "loss": 1.1497, "learning_rate": 1.859748187692367e-05, "epoch": 0.7610837438423645, "percentage": 25.37, "elapsed_time": "0:55:35", "remaining_time": "2:43:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 310, "total_steps": 1218, "loss": 1.2505, "learning_rate": 1.858280726624609e-05, "epoch": 0.7635467980295566, "percentage": 25.45, "elapsed_time": "0:55:45", "remaining_time": "2:43:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 311, "total_steps": 1218, "loss": 1.173, "learning_rate": 1.8568062136316047e-05, "epoch": 0.7660098522167488, "percentage": 25.53, "elapsed_time": "0:55:56", "remaining_time": "2:43:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 312, "total_steps": 1218, "loss": 1.3101, "learning_rate": 1.855324660828452e-05, "epoch": 0.7684729064039408, "percentage": 25.62, "elapsed_time": "0:56:06", "remaining_time": "2:42:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 313, "total_steps": 1218, "loss": 1.1491, "learning_rate": 1.853836080388091e-05, "epoch": 0.770935960591133, "percentage": 25.7, "elapsed_time": "0:56:16", "remaining_time": "2:42:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 314, "total_steps": 1218, "loss": 1.1573, "learning_rate": 1.8523404845412028e-05, "epoch": 0.7733990147783252, "percentage": 25.78, "elapsed_time": "0:56:26", "remaining_time": "2:42:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 315, "total_steps": 1218, "loss": 1.1812, "learning_rate": 1.8508378855761097e-05, "epoch": 0.7758620689655172, "percentage": 25.86, "elapsed_time": "0:56:36", "remaining_time": "2:42:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 316, "total_steps": 1218, "loss": 1.1803, "learning_rate": 1.849328295838674e-05, "epoch": 0.7783251231527094, "percentage": 25.94, "elapsed_time": "0:56:46", "remaining_time": "2:42:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 317, "total_steps": 1218, "loss": 1.1608, "learning_rate": 1.8478117277321967e-05, "epoch": 0.7807881773399015, "percentage": 26.03, "elapsed_time": "0:56:56", "remaining_time": "2:41:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 318, "total_steps": 1218, "loss": 1.2806, "learning_rate": 1.8462881937173144e-05, "epoch": 0.7832512315270936, "percentage": 26.11, "elapsed_time": "0:57:06", "remaining_time": "2:41:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 319, "total_steps": 1218, "loss": 1.2105, "learning_rate": 1.844757706311899e-05, "epoch": 0.7857142857142857, "percentage": 26.19, "elapsed_time": "0:57:16", "remaining_time": "2:41:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 320, "total_steps": 1218, "loss": 1.2321, "learning_rate": 1.8432202780909542e-05, "epoch": 0.7881773399014779, "percentage": 26.27, "elapsed_time": "0:57:26", "remaining_time": "2:41:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 321, "total_steps": 1218, "loss": 1.2735, "learning_rate": 1.8416759216865104e-05, "epoch": 0.7906403940886699, "percentage": 26.35, "elapsed_time": "0:57:36", "remaining_time": "2:40:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 322, "total_steps": 1218, "loss": 1.0759, "learning_rate": 1.8401246497875238e-05, "epoch": 0.7931034482758621, "percentage": 26.44, "elapsed_time": "0:57:47", "remaining_time": "2:40:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 323, "total_steps": 1218, "loss": 1.0708, "learning_rate": 1.838566475139769e-05, "epoch": 0.7955665024630542, "percentage": 26.52, "elapsed_time": "0:57:56", "remaining_time": "2:40:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 324, "total_steps": 1218, "loss": 1.1107, "learning_rate": 1.8370014105457378e-05, "epoch": 0.7980295566502463, "percentage": 26.6, "elapsed_time": "0:58:08", "remaining_time": "2:40:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 325, "total_steps": 1218, "loss": 1.3381, "learning_rate": 1.8354294688645303e-05, "epoch": 0.8004926108374384, "percentage": 26.68, "elapsed_time": "0:58:18", "remaining_time": "2:40:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 326, "total_steps": 1218, "loss": 1.1409, "learning_rate": 1.8338506630117527e-05, "epoch": 0.8029556650246306, "percentage": 26.77, "elapsed_time": "0:58:28", "remaining_time": "2:40:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 327, "total_steps": 1218, "loss": 1.123, "learning_rate": 1.8322650059594087e-05, "epoch": 0.8054187192118226, "percentage": 26.85, "elapsed_time": "0:58:38", "remaining_time": "2:39:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 328, "total_steps": 1218, "loss": 1.2287, "learning_rate": 1.8306725107357933e-05, "epoch": 0.8078817733990148, "percentage": 26.93, "elapsed_time": "0:58:48", "remaining_time": "2:39:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 329, "total_steps": 1218, "loss": 1.1696, "learning_rate": 1.8290731904253874e-05, "epoch": 0.8103448275862069, "percentage": 27.01, "elapsed_time": "0:58:59", "remaining_time": "2:39:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 330, "total_steps": 1218, "loss": 1.1477, "learning_rate": 1.827467058168748e-05, "epoch": 0.812807881773399, "percentage": 27.09, "elapsed_time": "0:59:09", "remaining_time": "2:39:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 331, "total_steps": 1218, "loss": 1.1542, "learning_rate": 1.8258541271624025e-05, "epoch": 0.8152709359605911, "percentage": 27.18, "elapsed_time": "0:59:23", "remaining_time": "2:39:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 332, "total_steps": 1218, "loss": 1.0486, "learning_rate": 1.824234410658738e-05, "epoch": 0.8177339901477833, "percentage": 27.26, "elapsed_time": "0:59:34", "remaining_time": "2:38:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 333, "total_steps": 1218, "loss": 1.1863, "learning_rate": 1.8226079219658944e-05, "epoch": 0.8201970443349754, "percentage": 27.34, "elapsed_time": "0:59:45", "remaining_time": "2:38:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 334, "total_steps": 1218, "loss": 1.0729, "learning_rate": 1.8209746744476538e-05, "epoch": 0.8226600985221675, "percentage": 27.42, "elapsed_time": "0:59:56", "remaining_time": "2:38:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 335, "total_steps": 1218, "loss": 1.1819, "learning_rate": 1.819334681523331e-05, "epoch": 0.8251231527093597, "percentage": 27.5, "elapsed_time": "1:00:06", "remaining_time": "2:38:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 336, "total_steps": 1218, "loss": 1.1346, "learning_rate": 1.817687956667664e-05, "epoch": 0.8275862068965517, "percentage": 27.59, "elapsed_time": "1:00:18", "remaining_time": "2:38:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 337, "total_steps": 1218, "loss": 1.2799, "learning_rate": 1.816034513410702e-05, "epoch": 0.8300492610837439, "percentage": 27.67, "elapsed_time": "1:00:29", "remaining_time": "2:38:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 338, "total_steps": 1218, "loss": 1.1781, "learning_rate": 1.8143743653376944e-05, "epoch": 0.8325123152709359, "percentage": 27.75, "elapsed_time": "1:00:39", "remaining_time": "2:37:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 339, "total_steps": 1218, "loss": 1.3102, "learning_rate": 1.8127075260889807e-05, "epoch": 0.8349753694581281, "percentage": 27.83, "elapsed_time": "1:00:48", "remaining_time": "2:37:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 340, "total_steps": 1218, "loss": 1.1121, "learning_rate": 1.811034009359877e-05, "epoch": 0.8374384236453202, "percentage": 27.91, "elapsed_time": "1:00:59", "remaining_time": "2:37:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 341, "total_steps": 1218, "loss": 1.145, "learning_rate": 1.8093538289005635e-05, "epoch": 0.8399014778325123, "percentage": 28.0, "elapsed_time": "1:01:10", "remaining_time": "2:37:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 342, "total_steps": 1218, "loss": 1.1959, "learning_rate": 1.8076669985159726e-05, "epoch": 0.8423645320197044, "percentage": 28.08, "elapsed_time": "1:01:22", "remaining_time": "2:37:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 343, "total_steps": 1218, "loss": 1.2083, "learning_rate": 1.8059735320656738e-05, "epoch": 0.8448275862068966, "percentage": 28.16, "elapsed_time": "1:01:32", "remaining_time": "2:36:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 344, "total_steps": 1218, "loss": 1.1454, "learning_rate": 1.8042734434637615e-05, "epoch": 0.8472906403940886, "percentage": 28.24, "elapsed_time": "1:01:44", "remaining_time": "2:36:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 345, "total_steps": 1218, "loss": 1.2648, "learning_rate": 1.8025667466787395e-05, "epoch": 0.8497536945812808, "percentage": 28.33, "elapsed_time": "1:01:58", "remaining_time": "2:36:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 346, "total_steps": 1218, "loss": 1.2206, "learning_rate": 1.8008534557334064e-05, "epoch": 0.8522167487684729, "percentage": 28.41, "elapsed_time": "1:02:08", "remaining_time": "2:36:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 347, "total_steps": 1218, "loss": 1.1613, "learning_rate": 1.799133584704742e-05, "epoch": 0.854679802955665, "percentage": 28.49, "elapsed_time": "1:02:20", "remaining_time": "2:36:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 348, "total_steps": 1218, "loss": 1.2371, "learning_rate": 1.7974071477237887e-05, "epoch": 0.8571428571428571, "percentage": 28.57, "elapsed_time": "1:02:31", "remaining_time": "2:36:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 349, "total_steps": 1218, "loss": 1.2587, "learning_rate": 1.7956741589755383e-05, "epoch": 0.8596059113300493, "percentage": 28.65, "elapsed_time": "1:02:41", "remaining_time": "2:36:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 350, "total_steps": 1218, "loss": 1.1528, "learning_rate": 1.7939346326988127e-05, "epoch": 0.8620689655172413, "percentage": 28.74, "elapsed_time": "1:02:51", "remaining_time": "2:35:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 351, "total_steps": 1218, "loss": 1.1786, "learning_rate": 1.7921885831861497e-05, "epoch": 0.8645320197044335, "percentage": 28.82, "elapsed_time": "1:03:00", "remaining_time": "2:35:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 352, "total_steps": 1218, "loss": 1.1392, "learning_rate": 1.7904360247836838e-05, "epoch": 0.8669950738916257, "percentage": 28.9, "elapsed_time": "1:03:11", "remaining_time": "2:35:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 353, "total_steps": 1218, "loss": 1.1595, "learning_rate": 1.788676971891028e-05, "epoch": 0.8694581280788177, "percentage": 28.98, "elapsed_time": "1:03:21", "remaining_time": "2:35:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 354, "total_steps": 1218, "loss": 1.2797, "learning_rate": 1.7869114389611574e-05, "epoch": 0.8719211822660099, "percentage": 29.06, "elapsed_time": "1:03:32", "remaining_time": "2:35:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 355, "total_steps": 1218, "loss": 1.1745, "learning_rate": 1.7851394405002885e-05, "epoch": 0.874384236453202, "percentage": 29.15, "elapsed_time": "1:03:45", "remaining_time": "2:35:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 356, "total_steps": 1218, "loss": 1.2188, "learning_rate": 1.7833609910677613e-05, "epoch": 0.8768472906403941, "percentage": 29.23, "elapsed_time": "1:03:57", "remaining_time": "2:34:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 357, "total_steps": 1218, "loss": 1.1681, "learning_rate": 1.781576105275919e-05, "epoch": 0.8793103448275862, "percentage": 29.31, "elapsed_time": "1:04:10", "remaining_time": "2:34:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 358, "total_steps": 1218, "loss": 1.2138, "learning_rate": 1.7797847977899873e-05, "epoch": 0.8817733990147784, "percentage": 29.39, "elapsed_time": "1:04:20", "remaining_time": "2:34:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 359, "total_steps": 1218, "loss": 1.2463, "learning_rate": 1.777987083327956e-05, "epoch": 0.8842364532019704, "percentage": 29.47, "elapsed_time": "1:04:30", "remaining_time": "2:34:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 360, "total_steps": 1218, "loss": 1.2148, "learning_rate": 1.7761829766604556e-05, "epoch": 0.8866995073891626, "percentage": 29.56, "elapsed_time": "1:04:40", "remaining_time": "2:34:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 361, "total_steps": 1218, "loss": 1.1402, "learning_rate": 1.7743724926106387e-05, "epoch": 0.8891625615763546, "percentage": 29.64, "elapsed_time": "1:04:50", "remaining_time": "2:33:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 362, "total_steps": 1218, "loss": 1.1199, "learning_rate": 1.7725556460540553e-05, "epoch": 0.8916256157635468, "percentage": 29.72, "elapsed_time": "1:05:01", "remaining_time": "2:33:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 363, "total_steps": 1218, "loss": 1.1245, "learning_rate": 1.770732451918532e-05, "epoch": 0.8940886699507389, "percentage": 29.8, "elapsed_time": "1:05:11", "remaining_time": "2:33:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 364, "total_steps": 1218, "loss": 1.2386, "learning_rate": 1.7689029251840492e-05, "epoch": 0.896551724137931, "percentage": 29.89, "elapsed_time": "1:05:21", "remaining_time": "2:33:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 365, "total_steps": 1218, "loss": 1.1207, "learning_rate": 1.7670670808826193e-05, "epoch": 0.8990147783251231, "percentage": 29.97, "elapsed_time": "1:05:31", "remaining_time": "2:33:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 366, "total_steps": 1218, "loss": 1.1442, "learning_rate": 1.7652249340981608e-05, "epoch": 0.9014778325123153, "percentage": 30.05, "elapsed_time": "1:05:43", "remaining_time": "2:33:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 367, "total_steps": 1218, "loss": 1.2465, "learning_rate": 1.7633764999663753e-05, "epoch": 0.9039408866995073, "percentage": 30.13, "elapsed_time": "1:05:53", "remaining_time": "2:32:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 368, "total_steps": 1218, "loss": 1.2322, "learning_rate": 1.7615217936746246e-05, "epoch": 0.9064039408866995, "percentage": 30.21, "elapsed_time": "1:06:03", "remaining_time": "2:32:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 369, "total_steps": 1218, "loss": 1.1621, "learning_rate": 1.7596608304618037e-05, "epoch": 0.9088669950738916, "percentage": 30.3, "elapsed_time": "1:06:12", "remaining_time": "2:32:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 370, "total_steps": 1218, "loss": 1.1752, "learning_rate": 1.757793625618217e-05, "epoch": 0.9113300492610837, "percentage": 30.38, "elapsed_time": "1:06:25", "remaining_time": "2:32:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 371, "total_steps": 1218, "loss": 1.1167, "learning_rate": 1.7559201944854515e-05, "epoch": 0.9137931034482759, "percentage": 30.46, "elapsed_time": "1:06:38", "remaining_time": "2:32:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 372, "total_steps": 1218, "loss": 1.1254, "learning_rate": 1.7540405524562533e-05, "epoch": 0.916256157635468, "percentage": 30.54, "elapsed_time": "1:06:49", "remaining_time": "2:31:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 373, "total_steps": 1218, "loss": 1.1664, "learning_rate": 1.752154714974397e-05, "epoch": 0.9187192118226601, "percentage": 30.62, "elapsed_time": "1:06:59", "remaining_time": "2:31:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 374, "total_steps": 1218, "loss": 1.1247, "learning_rate": 1.750262697534563e-05, "epoch": 0.9211822660098522, "percentage": 30.71, "elapsed_time": "1:07:10", "remaining_time": "2:31:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 375, "total_steps": 1218, "loss": 1.2152, "learning_rate": 1.748364515682207e-05, "epoch": 0.9236453201970444, "percentage": 30.79, "elapsed_time": "1:07:19", "remaining_time": "2:31:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 376, "total_steps": 1218, "loss": 1.199, "learning_rate": 1.7464601850134353e-05, "epoch": 0.9261083743842364, "percentage": 30.87, "elapsed_time": "1:07:29", "remaining_time": "2:31:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 377, "total_steps": 1218, "loss": 1.1952, "learning_rate": 1.744549721174873e-05, "epoch": 0.9285714285714286, "percentage": 30.95, "elapsed_time": "1:07:39", "remaining_time": "2:30:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 378, "total_steps": 1218, "loss": 1.1492, "learning_rate": 1.742633139863538e-05, "epoch": 0.9310344827586207, "percentage": 31.03, "elapsed_time": "1:07:50", "remaining_time": "2:30:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 379, "total_steps": 1218, "loss": 1.2148, "learning_rate": 1.740710456826713e-05, "epoch": 0.9334975369458128, "percentage": 31.12, "elapsed_time": "1:08:02", "remaining_time": "2:30:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 380, "total_steps": 1218, "loss": 1.2196, "learning_rate": 1.738781687861812e-05, "epoch": 0.9359605911330049, "percentage": 31.2, "elapsed_time": "1:08:11", "remaining_time": "2:30:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 381, "total_steps": 1218, "loss": 1.1854, "learning_rate": 1.7368468488162547e-05, "epoch": 0.9384236453201971, "percentage": 31.28, "elapsed_time": "1:08:25", "remaining_time": "2:30:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 382, "total_steps": 1218, "loss": 1.2045, "learning_rate": 1.7349059555873348e-05, "epoch": 0.9408866995073891, "percentage": 31.36, "elapsed_time": "1:08:35", "remaining_time": "2:30:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 383, "total_steps": 1218, "loss": 1.1462, "learning_rate": 1.732959024122088e-05, "epoch": 0.9433497536945813, "percentage": 31.44, "elapsed_time": "1:08:46", "remaining_time": "2:29:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 384, "total_steps": 1218, "loss": 1.2479, "learning_rate": 1.731006070417163e-05, "epoch": 0.9458128078817734, "percentage": 31.53, "elapsed_time": "1:08:55", "remaining_time": "2:29:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 385, "total_steps": 1218, "loss": 1.1074, "learning_rate": 1.7290471105186893e-05, "epoch": 0.9482758620689655, "percentage": 31.61, "elapsed_time": "1:09:07", "remaining_time": "2:29:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 386, "total_steps": 1218, "loss": 1.1831, "learning_rate": 1.7270821605221448e-05, "epoch": 0.9507389162561576, "percentage": 31.69, "elapsed_time": "1:09:17", "remaining_time": "2:29:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 387, "total_steps": 1218, "loss": 1.0715, "learning_rate": 1.725111236572225e-05, "epoch": 0.9532019704433498, "percentage": 31.77, "elapsed_time": "1:09:28", "remaining_time": "2:29:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 388, "total_steps": 1218, "loss": 1.1789, "learning_rate": 1.7231343548627085e-05, "epoch": 0.9556650246305419, "percentage": 31.86, "elapsed_time": "1:09:39", "remaining_time": "2:29:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 389, "total_steps": 1218, "loss": 1.1998, "learning_rate": 1.7211515316363252e-05, "epoch": 0.958128078817734, "percentage": 31.94, "elapsed_time": "1:09:49", "remaining_time": "2:28:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 390, "total_steps": 1218, "loss": 1.1184, "learning_rate": 1.7191627831846226e-05, "epoch": 0.9605911330049262, "percentage": 32.02, "elapsed_time": "1:09:58", "remaining_time": "2:28:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 391, "total_steps": 1218, "loss": 1.2642, "learning_rate": 1.7171681258478316e-05, "epoch": 0.9630541871921182, "percentage": 32.1, "elapsed_time": "1:10:10", "remaining_time": "2:28:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 392, "total_steps": 1218, "loss": 1.1768, "learning_rate": 1.7151675760147325e-05, "epoch": 0.9655172413793104, "percentage": 32.18, "elapsed_time": "1:10:20", "remaining_time": "2:28:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 393, "total_steps": 1218, "loss": 1.077, "learning_rate": 1.7131611501225215e-05, "epoch": 0.9679802955665024, "percentage": 32.27, "elapsed_time": "1:10:30", "remaining_time": "2:28:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 394, "total_steps": 1218, "loss": 1.0983, "learning_rate": 1.7111488646566728e-05, "epoch": 0.9704433497536946, "percentage": 32.35, "elapsed_time": "1:10:40", "remaining_time": "2:27:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 395, "total_steps": 1218, "loss": 1.161, "learning_rate": 1.7091307361508057e-05, "epoch": 0.9729064039408867, "percentage": 32.43, "elapsed_time": "1:10:51", "remaining_time": "2:27:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 396, "total_steps": 1218, "loss": 1.2167, "learning_rate": 1.7071067811865477e-05, "epoch": 0.9753694581280788, "percentage": 32.51, "elapsed_time": "1:11:01", "remaining_time": "2:27:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 397, "total_steps": 1218, "loss": 1.1345, "learning_rate": 1.7050770163933985e-05, "epoch": 0.9778325123152709, "percentage": 32.59, "elapsed_time": "1:11:13", "remaining_time": "2:27:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 398, "total_steps": 1218, "loss": 1.1951, "learning_rate": 1.7030414584485938e-05, "epoch": 0.9802955665024631, "percentage": 32.68, "elapsed_time": "1:11:23", "remaining_time": "2:27:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 399, "total_steps": 1218, "loss": 1.1806, "learning_rate": 1.701000124076967e-05, "epoch": 0.9827586206896551, "percentage": 32.76, "elapsed_time": "1:11:34", "remaining_time": "2:26:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 400, "total_steps": 1218, "loss": 1.2236, "learning_rate": 1.6989530300508126e-05, "epoch": 0.9852216748768473, "percentage": 32.84, "elapsed_time": "1:11:44", "remaining_time": "2:26:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 401, "total_steps": 1218, "loss": 1.2562, "learning_rate": 1.6969001931897492e-05, "epoch": 0.9876847290640394, "percentage": 32.92, "elapsed_time": "1:11:53", "remaining_time": "2:26:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 402, "total_steps": 1218, "loss": 1.1348, "learning_rate": 1.6948416303605796e-05, "epoch": 0.9901477832512315, "percentage": 33.0, "elapsed_time": "1:12:04", "remaining_time": "2:26:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 403, "total_steps": 1218, "loss": 1.1724, "learning_rate": 1.692777358477154e-05, "epoch": 0.9926108374384236, "percentage": 33.09, "elapsed_time": "1:12:15", "remaining_time": "2:26:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 404, "total_steps": 1218, "loss": 1.172, "learning_rate": 1.690707394500229e-05, "epoch": 0.9950738916256158, "percentage": 33.17, "elapsed_time": "1:12:25", "remaining_time": "2:25:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 405, "total_steps": 1218, "loss": 1.26, "learning_rate": 1.6886317554373304e-05, "epoch": 0.9975369458128078, "percentage": 33.25, "elapsed_time": "1:12:35", "remaining_time": "2:25:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 406, "total_steps": 1218, "loss": 1.2232, "learning_rate": 1.6865504583426117e-05, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:12:44", "remaining_time": "2:25:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 406, "total_steps": 1218, "eval_loss": 1.1330950260162354, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:12:46", "remaining_time": "2:25:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 407, "total_steps": 1218, "loss": 0.8731, "learning_rate": 1.684463520316715e-05, "epoch": 1.0024630541871922, "percentage": 33.42, "elapsed_time": "1:12:58", "remaining_time": "2:25:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 408, "total_steps": 1218, "loss": 0.8808, "learning_rate": 1.6823709585066308e-05, "epoch": 1.0049261083743843, "percentage": 33.5, "elapsed_time": "1:13:08", "remaining_time": "2:25:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 409, "total_steps": 1218, "loss": 0.7646, "learning_rate": 1.6802727901055555e-05, "epoch": 1.0073891625615763, "percentage": 33.58, "elapsed_time": "1:13:18", "remaining_time": "2:25:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 410, "total_steps": 1218, "loss": 0.8189, "learning_rate": 1.6781690323527512e-05, "epoch": 1.0098522167487685, "percentage": 33.66, "elapsed_time": "1:13:29", "remaining_time": "2:24:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 411, "total_steps": 1218, "loss": 0.8166, "learning_rate": 1.6760597025334046e-05, "epoch": 1.0123152709359606, "percentage": 33.74, "elapsed_time": "1:13:40", "remaining_time": "2:24:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 412, "total_steps": 1218, "loss": 0.8595, "learning_rate": 1.6739448179784846e-05, "epoch": 1.0147783251231528, "percentage": 33.83, "elapsed_time": "1:13:50", "remaining_time": "2:24:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 413, "total_steps": 1218, "loss": 0.7923, "learning_rate": 1.6718243960645984e-05, "epoch": 1.0172413793103448, "percentage": 33.91, "elapsed_time": "1:14:00", "remaining_time": "2:24:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 414, "total_steps": 1218, "loss": 0.8729, "learning_rate": 1.669698454213852e-05, "epoch": 1.019704433497537, "percentage": 33.99, "elapsed_time": "1:14:10", "remaining_time": "2:24:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 415, "total_steps": 1218, "loss": 0.7861, "learning_rate": 1.6675670098937034e-05, "epoch": 1.022167487684729, "percentage": 34.07, "elapsed_time": "1:14:20", "remaining_time": "2:23:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 416, "total_steps": 1218, "loss": 0.7735, "learning_rate": 1.665430080616821e-05, "epoch": 1.0246305418719213, "percentage": 34.15, "elapsed_time": "1:14:31", "remaining_time": "2:23:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 417, "total_steps": 1218, "loss": 0.8035, "learning_rate": 1.66328768394094e-05, "epoch": 1.0270935960591132, "percentage": 34.24, "elapsed_time": "1:14:41", "remaining_time": "2:23:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 418, "total_steps": 1218, "loss": 0.7913, "learning_rate": 1.6611398374687172e-05, "epoch": 1.0295566502463054, "percentage": 34.32, "elapsed_time": "1:14:52", "remaining_time": "2:23:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 419, "total_steps": 1218, "loss": 0.8104, "learning_rate": 1.6589865588475872e-05, "epoch": 1.0320197044334976, "percentage": 34.4, "elapsed_time": "1:15:03", "remaining_time": "2:23:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 420, "total_steps": 1218, "loss": 0.8342, "learning_rate": 1.6568278657696166e-05, "epoch": 1.0344827586206897, "percentage": 34.48, "elapsed_time": "1:15:13", "remaining_time": "2:22:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 421, "total_steps": 1218, "loss": 0.8619, "learning_rate": 1.6546637759713588e-05, "epoch": 1.0369458128078817, "percentage": 34.56, "elapsed_time": "1:15:23", "remaining_time": "2:22:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 422, "total_steps": 1218, "loss": 0.9003, "learning_rate": 1.6524943072337094e-05, "epoch": 1.0394088669950738, "percentage": 34.65, "elapsed_time": "1:15:35", "remaining_time": "2:22:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 423, "total_steps": 1218, "loss": 0.7633, "learning_rate": 1.6503194773817583e-05, "epoch": 1.041871921182266, "percentage": 34.73, "elapsed_time": "1:15:45", "remaining_time": "2:22:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 424, "total_steps": 1218, "loss": 0.814, "learning_rate": 1.6481393042846442e-05, "epoch": 1.0443349753694582, "percentage": 34.81, "elapsed_time": "1:15:54", "remaining_time": "2:22:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 425, "total_steps": 1218, "loss": 0.7668, "learning_rate": 1.6459538058554088e-05, "epoch": 1.0467980295566504, "percentage": 34.89, "elapsed_time": "1:16:05", "remaining_time": "2:21:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 426, "total_steps": 1218, "loss": 0.8318, "learning_rate": 1.6437630000508466e-05, "epoch": 1.0492610837438423, "percentage": 34.98, "elapsed_time": "1:16:15", "remaining_time": "2:21:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 427, "total_steps": 1218, "loss": 0.8044, "learning_rate": 1.6415669048713608e-05, "epoch": 1.0517241379310345, "percentage": 35.06, "elapsed_time": "1:16:26", "remaining_time": "2:21:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 428, "total_steps": 1218, "loss": 0.904, "learning_rate": 1.6393655383608132e-05, "epoch": 1.0541871921182266, "percentage": 35.14, "elapsed_time": "1:16:36", "remaining_time": "2:21:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 429, "total_steps": 1218, "loss": 0.7863, "learning_rate": 1.6371589186063778e-05, "epoch": 1.0566502463054188, "percentage": 35.22, "elapsed_time": "1:16:46", "remaining_time": "2:21:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 430, "total_steps": 1218, "loss": 0.8245, "learning_rate": 1.634947063738389e-05, "epoch": 1.0591133004926108, "percentage": 35.3, "elapsed_time": "1:16:57", "remaining_time": "2:21:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 431, "total_steps": 1218, "loss": 0.8468, "learning_rate": 1.6327299919301967e-05, "epoch": 1.061576354679803, "percentage": 35.39, "elapsed_time": "1:17:08", "remaining_time": "2:20:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 432, "total_steps": 1218, "loss": 0.7999, "learning_rate": 1.630507721398013e-05, "epoch": 1.064039408866995, "percentage": 35.47, "elapsed_time": "1:17:17", "remaining_time": "2:20:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 433, "total_steps": 1218, "loss": 0.6685, "learning_rate": 1.6282802704007668e-05, "epoch": 1.0665024630541873, "percentage": 35.55, "elapsed_time": "1:17:29", "remaining_time": "2:20:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 434, "total_steps": 1218, "loss": 0.8646, "learning_rate": 1.6260476572399494e-05, "epoch": 1.0689655172413792, "percentage": 35.63, "elapsed_time": "1:17:41", "remaining_time": "2:20:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 435, "total_steps": 1218, "loss": 0.8254, "learning_rate": 1.6238099002594672e-05, "epoch": 1.0714285714285714, "percentage": 35.71, "elapsed_time": "1:17:53", "remaining_time": "2:20:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 436, "total_steps": 1218, "loss": 0.7006, "learning_rate": 1.6215670178454893e-05, "epoch": 1.0738916256157636, "percentage": 35.8, "elapsed_time": "1:18:06", "remaining_time": "2:20:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 437, "total_steps": 1218, "loss": 0.7703, "learning_rate": 1.6193190284262982e-05, "epoch": 1.0763546798029557, "percentage": 35.88, "elapsed_time": "1:18:16", "remaining_time": "2:19:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 438, "total_steps": 1218, "loss": 0.8022, "learning_rate": 1.6170659504721365e-05, "epoch": 1.0788177339901477, "percentage": 35.96, "elapsed_time": "1:18:25", "remaining_time": "2:19:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 439, "total_steps": 1218, "loss": 0.8705, "learning_rate": 1.6148078024950553e-05, "epoch": 1.0812807881773399, "percentage": 36.04, "elapsed_time": "1:18:36", "remaining_time": "2:19:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 440, "total_steps": 1218, "loss": 0.7861, "learning_rate": 1.6125446030487642e-05, "epoch": 1.083743842364532, "percentage": 36.12, "elapsed_time": "1:18:46", "remaining_time": "2:19:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 441, "total_steps": 1218, "loss": 0.7969, "learning_rate": 1.610276370728477e-05, "epoch": 1.0862068965517242, "percentage": 36.21, "elapsed_time": "1:18:56", "remaining_time": "2:19:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 442, "total_steps": 1218, "loss": 0.7967, "learning_rate": 1.608003124170758e-05, "epoch": 1.0886699507389164, "percentage": 36.29, "elapsed_time": "1:19:06", "remaining_time": "2:18:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 443, "total_steps": 1218, "loss": 0.8096, "learning_rate": 1.6057248820533712e-05, "epoch": 1.0911330049261083, "percentage": 36.37, "elapsed_time": "1:19:16", "remaining_time": "2:18:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 444, "total_steps": 1218, "loss": 0.7719, "learning_rate": 1.6034416630951265e-05, "epoch": 1.0935960591133005, "percentage": 36.45, "elapsed_time": "1:19:26", "remaining_time": "2:18:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 445, "total_steps": 1218, "loss": 0.8161, "learning_rate": 1.6011534860557238e-05, "epoch": 1.0960591133004927, "percentage": 36.54, "elapsed_time": "1:19:37", "remaining_time": "2:18:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 446, "total_steps": 1218, "loss": 0.7658, "learning_rate": 1.598860369735601e-05, "epoch": 1.0985221674876848, "percentage": 36.62, "elapsed_time": "1:19:48", "remaining_time": "2:18:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 447, "total_steps": 1218, "loss": 0.7895, "learning_rate": 1.5965623329757795e-05, "epoch": 1.1009852216748768, "percentage": 36.7, "elapsed_time": "1:19:59", "remaining_time": "2:17:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 448, "total_steps": 1218, "loss": 0.8342, "learning_rate": 1.594259394657707e-05, "epoch": 1.103448275862069, "percentage": 36.78, "elapsed_time": "1:20:09", "remaining_time": "2:17:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 449, "total_steps": 1218, "loss": 0.8278, "learning_rate": 1.5919515737031052e-05, "epoch": 1.1059113300492611, "percentage": 36.86, "elapsed_time": "1:20:19", "remaining_time": "2:17:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 450, "total_steps": 1218, "loss": 0.7734, "learning_rate": 1.589638889073813e-05, "epoch": 1.1083743842364533, "percentage": 36.95, "elapsed_time": "1:20:30", "remaining_time": "2:17:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 451, "total_steps": 1218, "loss": 0.8156, "learning_rate": 1.587321359771631e-05, "epoch": 1.1108374384236452, "percentage": 37.03, "elapsed_time": "1:20:44", "remaining_time": "2:17:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 452, "total_steps": 1218, "loss": 0.8087, "learning_rate": 1.584999004838165e-05, "epoch": 1.1133004926108374, "percentage": 37.11, "elapsed_time": "1:20:57", "remaining_time": "2:17:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 453, "total_steps": 1218, "loss": 0.7927, "learning_rate": 1.58267184335467e-05, "epoch": 1.1157635467980296, "percentage": 37.19, "elapsed_time": "1:21:07", "remaining_time": "2:17:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 454, "total_steps": 1218, "loss": 0.8278, "learning_rate": 1.5803398944418934e-05, "epoch": 1.1182266009852218, "percentage": 37.27, "elapsed_time": "1:21:18", "remaining_time": "2:16:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 455, "total_steps": 1218, "loss": 0.867, "learning_rate": 1.5780031772599174e-05, "epoch": 1.1206896551724137, "percentage": 37.36, "elapsed_time": "1:21:29", "remaining_time": "2:16:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 456, "total_steps": 1218, "loss": 0.8528, "learning_rate": 1.5756617110080023e-05, "epoch": 1.1231527093596059, "percentage": 37.44, "elapsed_time": "1:21:40", "remaining_time": "2:16:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 457, "total_steps": 1218, "loss": 0.7861, "learning_rate": 1.573315514924428e-05, "epoch": 1.125615763546798, "percentage": 37.52, "elapsed_time": "1:21:50", "remaining_time": "2:16:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 458, "total_steps": 1218, "loss": 0.8233, "learning_rate": 1.570964608286336e-05, "epoch": 1.1280788177339902, "percentage": 37.6, "elapsed_time": "1:22:01", "remaining_time": "2:16:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 459, "total_steps": 1218, "loss": 0.8448, "learning_rate": 1.5686090104095726e-05, "epoch": 1.1305418719211824, "percentage": 37.68, "elapsed_time": "1:22:12", "remaining_time": "2:15:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 460, "total_steps": 1218, "loss": 0.8085, "learning_rate": 1.5662487406485273e-05, "epoch": 1.1330049261083743, "percentage": 37.77, "elapsed_time": "1:22:25", "remaining_time": "2:15:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 461, "total_steps": 1218, "loss": 0.8649, "learning_rate": 1.5638838183959768e-05, "epoch": 1.1354679802955665, "percentage": 37.85, "elapsed_time": "1:22:35", "remaining_time": "2:15:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 462, "total_steps": 1218, "loss": 0.8016, "learning_rate": 1.561514263082923e-05, "epoch": 1.1379310344827587, "percentage": 37.93, "elapsed_time": "1:22:48", "remaining_time": "2:15:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 463, "total_steps": 1218, "loss": 0.7641, "learning_rate": 1.5591400941784354e-05, "epoch": 1.1403940886699506, "percentage": 38.01, "elapsed_time": "1:22:58", "remaining_time": "2:15:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 464, "total_steps": 1218, "loss": 0.8657, "learning_rate": 1.5567613311894908e-05, "epoch": 1.1428571428571428, "percentage": 38.1, "elapsed_time": "1:23:09", "remaining_time": "2:15:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 465, "total_steps": 1218, "loss": 0.7574, "learning_rate": 1.554377993660811e-05, "epoch": 1.145320197044335, "percentage": 38.18, "elapsed_time": "1:23:20", "remaining_time": "2:14:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 466, "total_steps": 1218, "loss": 0.8259, "learning_rate": 1.5519901011747046e-05, "epoch": 1.1477832512315271, "percentage": 38.26, "elapsed_time": "1:23:30", "remaining_time": "2:14:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 467, "total_steps": 1218, "loss": 0.8162, "learning_rate": 1.5495976733509058e-05, "epoch": 1.1502463054187193, "percentage": 38.34, "elapsed_time": "1:23:41", "remaining_time": "2:14:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 468, "total_steps": 1218, "loss": 0.8298, "learning_rate": 1.5472007298464117e-05, "epoch": 1.1527093596059113, "percentage": 38.42, "elapsed_time": "1:23:52", "remaining_time": "2:14:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 469, "total_steps": 1218, "loss": 0.8599, "learning_rate": 1.544799290355323e-05, "epoch": 1.1551724137931034, "percentage": 38.51, "elapsed_time": "1:24:02", "remaining_time": "2:14:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 470, "total_steps": 1218, "loss": 0.8812, "learning_rate": 1.5423933746086793e-05, "epoch": 1.1576354679802956, "percentage": 38.59, "elapsed_time": "1:24:12", "remaining_time": "2:14:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 471, "total_steps": 1218, "loss": 0.8279, "learning_rate": 1.5399830023743004e-05, "epoch": 1.1600985221674878, "percentage": 38.67, "elapsed_time": "1:24:23", "remaining_time": "2:13:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 472, "total_steps": 1218, "loss": 0.8202, "learning_rate": 1.5375681934566203e-05, "epoch": 1.1625615763546797, "percentage": 38.75, "elapsed_time": "1:24:34", "remaining_time": "2:13:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 473, "total_steps": 1218, "loss": 0.8314, "learning_rate": 1.5351489676965283e-05, "epoch": 1.1650246305418719, "percentage": 38.83, "elapsed_time": "1:24:45", "remaining_time": "2:13:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 474, "total_steps": 1218, "loss": 0.815, "learning_rate": 1.532725344971202e-05, "epoch": 1.167487684729064, "percentage": 38.92, "elapsed_time": "1:24:55", "remaining_time": "2:13:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 475, "total_steps": 1218, "loss": 0.7647, "learning_rate": 1.5302973451939472e-05, "epoch": 1.1699507389162562, "percentage": 39.0, "elapsed_time": "1:25:08", "remaining_time": "2:13:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 476, "total_steps": 1218, "loss": 0.8097, "learning_rate": 1.527864988314033e-05, "epoch": 1.1724137931034484, "percentage": 39.08, "elapsed_time": "1:25:19", "remaining_time": "2:12:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 477, "total_steps": 1218, "loss": 0.8599, "learning_rate": 1.525428294316527e-05, "epoch": 1.1748768472906403, "percentage": 39.16, "elapsed_time": "1:25:28", "remaining_time": "2:12:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 478, "total_steps": 1218, "loss": 0.7931, "learning_rate": 1.5229872832221336e-05, "epoch": 1.1773399014778325, "percentage": 39.24, "elapsed_time": "1:25:39", "remaining_time": "2:12:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 479, "total_steps": 1218, "loss": 0.8038, "learning_rate": 1.5205419750870261e-05, "epoch": 1.1798029556650247, "percentage": 39.33, "elapsed_time": "1:25:48", "remaining_time": "2:12:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 480, "total_steps": 1218, "loss": 0.7815, "learning_rate": 1.5180923900026847e-05, "epoch": 1.1822660098522166, "percentage": 39.41, "elapsed_time": "1:25:58", "remaining_time": "2:12:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 481, "total_steps": 1218, "loss": 0.8219, "learning_rate": 1.5156385480957312e-05, "epoch": 1.1847290640394088, "percentage": 39.49, "elapsed_time": "1:26:08", "remaining_time": "2:11:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 482, "total_steps": 1218, "loss": 0.8542, "learning_rate": 1.5131804695277612e-05, "epoch": 1.187192118226601, "percentage": 39.57, "elapsed_time": "1:26:18", "remaining_time": "2:11:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 483, "total_steps": 1218, "loss": 0.8084, "learning_rate": 1.5107181744951818e-05, "epoch": 1.1896551724137931, "percentage": 39.66, "elapsed_time": "1:26:29", "remaining_time": "2:11:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 484, "total_steps": 1218, "loss": 0.7713, "learning_rate": 1.5082516832290424e-05, "epoch": 1.1921182266009853, "percentage": 39.74, "elapsed_time": "1:26:39", "remaining_time": "2:11:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 485, "total_steps": 1218, "loss": 0.8367, "learning_rate": 1.5057810159948715e-05, "epoch": 1.1945812807881773, "percentage": 39.82, "elapsed_time": "1:26:49", "remaining_time": "2:11:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 486, "total_steps": 1218, "loss": 0.8871, "learning_rate": 1.5033061930925081e-05, "epoch": 1.1970443349753694, "percentage": 39.9, "elapsed_time": "1:26:58", "remaining_time": "2:10:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 487, "total_steps": 1218, "loss": 0.8107, "learning_rate": 1.5008272348559359e-05, "epoch": 1.1995073891625616, "percentage": 39.98, "elapsed_time": "1:27:10", "remaining_time": "2:10:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 488, "total_steps": 1218, "loss": 0.7747, "learning_rate": 1.4983441616531152e-05, "epoch": 1.2019704433497538, "percentage": 40.07, "elapsed_time": "1:27:22", "remaining_time": "2:10:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 489, "total_steps": 1218, "loss": 0.8162, "learning_rate": 1.4958569938858169e-05, "epoch": 1.2044334975369457, "percentage": 40.15, "elapsed_time": "1:27:32", "remaining_time": "2:10:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 490, "total_steps": 1218, "loss": 0.7758, "learning_rate": 1.4933657519894542e-05, "epoch": 1.206896551724138, "percentage": 40.23, "elapsed_time": "1:27:44", "remaining_time": "2:10:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 491, "total_steps": 1218, "loss": 0.8396, "learning_rate": 1.4908704564329144e-05, "epoch": 1.20935960591133, "percentage": 40.31, "elapsed_time": "1:27:54", "remaining_time": "2:10:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 492, "total_steps": 1218, "loss": 0.758, "learning_rate": 1.4883711277183917e-05, "epoch": 1.2118226600985222, "percentage": 40.39, "elapsed_time": "1:28:04", "remaining_time": "2:09:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 493, "total_steps": 1218, "loss": 0.7743, "learning_rate": 1.485867786381217e-05, "epoch": 1.2142857142857142, "percentage": 40.48, "elapsed_time": "1:28:16", "remaining_time": "2:09:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 494, "total_steps": 1218, "loss": 0.7754, "learning_rate": 1.483360452989691e-05, "epoch": 1.2167487684729064, "percentage": 40.56, "elapsed_time": "1:28:28", "remaining_time": "2:09:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 495, "total_steps": 1218, "loss": 0.7712, "learning_rate": 1.4808491481449146e-05, "epoch": 1.2192118226600985, "percentage": 40.64, "elapsed_time": "1:28:40", "remaining_time": "2:09:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 496, "total_steps": 1218, "loss": 0.7303, "learning_rate": 1.4783338924806191e-05, "epoch": 1.2216748768472907, "percentage": 40.72, "elapsed_time": "1:28:50", "remaining_time": "2:09:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 497, "total_steps": 1218, "loss": 0.8276, "learning_rate": 1.4758147066629975e-05, "epoch": 1.2241379310344827, "percentage": 40.8, "elapsed_time": "1:29:01", "remaining_time": "2:09:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 498, "total_steps": 1218, "loss": 0.823, "learning_rate": 1.4732916113905336e-05, "epoch": 1.2266009852216748, "percentage": 40.89, "elapsed_time": "1:29:13", "remaining_time": "2:08:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 499, "total_steps": 1218, "loss": 0.8354, "learning_rate": 1.4707646273938335e-05, "epoch": 1.229064039408867, "percentage": 40.97, "elapsed_time": "1:29:24", "remaining_time": "2:08:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 500, "total_steps": 1218, "loss": 0.789, "learning_rate": 1.4682337754354534e-05, "epoch": 1.2315270935960592, "percentage": 41.05, "elapsed_time": "1:29:34", "remaining_time": "2:08:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 501, "total_steps": 1218, "loss": 0.7952, "learning_rate": 1.465699076309731e-05, "epoch": 1.2339901477832513, "percentage": 41.13, "elapsed_time": "1:29:46", "remaining_time": "2:08:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 502, "total_steps": 1218, "loss": 0.7599, "learning_rate": 1.4631605508426124e-05, "epoch": 1.2364532019704433, "percentage": 41.22, "elapsed_time": "1:29:57", "remaining_time": "2:08:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 503, "total_steps": 1218, "loss": 0.7587, "learning_rate": 1.4606182198914835e-05, "epoch": 1.2389162561576355, "percentage": 41.3, "elapsed_time": "1:30:07", "remaining_time": "2:08:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 504, "total_steps": 1218, "loss": 0.8503, "learning_rate": 1.4580721043449968e-05, "epoch": 1.2413793103448276, "percentage": 41.38, "elapsed_time": "1:30:17", "remaining_time": "2:07:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 505, "total_steps": 1218, "loss": 0.8142, "learning_rate": 1.4555222251228997e-05, "epoch": 1.2438423645320198, "percentage": 41.46, "elapsed_time": "1:30:26", "remaining_time": "2:07:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 506, "total_steps": 1218, "loss": 0.7871, "learning_rate": 1.4529686031758642e-05, "epoch": 1.2463054187192117, "percentage": 41.54, "elapsed_time": "1:30:36", "remaining_time": "2:07:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 507, "total_steps": 1218, "loss": 0.7957, "learning_rate": 1.450411259485314e-05, "epoch": 1.248768472906404, "percentage": 41.63, "elapsed_time": "1:30:48", "remaining_time": "2:07:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 508, "total_steps": 1218, "loss": 0.8492, "learning_rate": 1.4478502150632503e-05, "epoch": 1.251231527093596, "percentage": 41.71, "elapsed_time": "1:30:57", "remaining_time": "2:07:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 509, "total_steps": 1218, "loss": 0.7768, "learning_rate": 1.4452854909520824e-05, "epoch": 1.2536945812807883, "percentage": 41.79, "elapsed_time": "1:31:07", "remaining_time": "2:06:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 510, "total_steps": 1218, "loss": 0.8251, "learning_rate": 1.4427171082244523e-05, "epoch": 1.2561576354679804, "percentage": 41.87, "elapsed_time": "1:31:18", "remaining_time": "2:06:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 511, "total_steps": 1218, "loss": 0.8213, "learning_rate": 1.4401450879830628e-05, "epoch": 1.2586206896551724, "percentage": 41.95, "elapsed_time": "1:31:35", "remaining_time": "2:06:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 512, "total_steps": 1218, "loss": 0.7067, "learning_rate": 1.4375694513605037e-05, "epoch": 1.2610837438423645, "percentage": 42.04, "elapsed_time": "1:31:47", "remaining_time": "2:06:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 513, "total_steps": 1218, "loss": 0.8232, "learning_rate": 1.4349902195190777e-05, "epoch": 1.2635467980295567, "percentage": 42.12, "elapsed_time": "1:31:57", "remaining_time": "2:06:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 514, "total_steps": 1218, "loss": 0.7975, "learning_rate": 1.4324074136506283e-05, "epoch": 1.2660098522167487, "percentage": 42.2, "elapsed_time": "1:32:07", "remaining_time": "2:06:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 515, "total_steps": 1218, "loss": 0.9027, "learning_rate": 1.429821054976363e-05, "epoch": 1.2684729064039408, "percentage": 42.28, "elapsed_time": "1:32:19", "remaining_time": "2:06:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 516, "total_steps": 1218, "loss": 0.7706, "learning_rate": 1.427231164746681e-05, "epoch": 1.270935960591133, "percentage": 42.36, "elapsed_time": "1:32:29", "remaining_time": "2:05:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 517, "total_steps": 1218, "loss": 0.7563, "learning_rate": 1.424637764240998e-05, "epoch": 1.2733990147783252, "percentage": 42.45, "elapsed_time": "1:32:39", "remaining_time": "2:05:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 518, "total_steps": 1218, "loss": 0.7796, "learning_rate": 1.4220408747675714e-05, "epoch": 1.2758620689655173, "percentage": 42.53, "elapsed_time": "1:32:49", "remaining_time": "2:05:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 519, "total_steps": 1218, "loss": 0.8419, "learning_rate": 1.419440517663325e-05, "epoch": 1.2783251231527093, "percentage": 42.61, "elapsed_time": "1:33:01", "remaining_time": "2:05:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 520, "total_steps": 1218, "loss": 0.8188, "learning_rate": 1.4168367142936736e-05, "epoch": 1.2807881773399015, "percentage": 42.69, "elapsed_time": "1:33:11", "remaining_time": "2:05:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 521, "total_steps": 1218, "loss": 0.7833, "learning_rate": 1.4142294860523475e-05, "epoch": 1.2832512315270936, "percentage": 42.78, "elapsed_time": "1:33:22", "remaining_time": "2:04:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 522, "total_steps": 1218, "loss": 0.7456, "learning_rate": 1.4116188543612182e-05, "epoch": 1.2857142857142856, "percentage": 42.86, "elapsed_time": "1:33:32", "remaining_time": "2:04:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 523, "total_steps": 1218, "loss": 0.8879, "learning_rate": 1.4090048406701196e-05, "epoch": 1.2881773399014778, "percentage": 42.94, "elapsed_time": "1:33:41", "remaining_time": "2:04:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 524, "total_steps": 1218, "loss": 0.7817, "learning_rate": 1.4063874664566734e-05, "epoch": 1.29064039408867, "percentage": 43.02, "elapsed_time": "1:33:51", "remaining_time": "2:04:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 525, "total_steps": 1218, "loss": 0.8403, "learning_rate": 1.4037667532261143e-05, "epoch": 1.293103448275862, "percentage": 43.1, "elapsed_time": "1:34:01", "remaining_time": "2:04:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 526, "total_steps": 1218, "loss": 0.7812, "learning_rate": 1.4011427225111091e-05, "epoch": 1.2955665024630543, "percentage": 43.19, "elapsed_time": "1:34:12", "remaining_time": "2:03:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 527, "total_steps": 1218, "loss": 0.8574, "learning_rate": 1.3985153958715833e-05, "epoch": 1.2980295566502464, "percentage": 43.27, "elapsed_time": "1:34:21", "remaining_time": "2:03:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 528, "total_steps": 1218, "loss": 0.7913, "learning_rate": 1.3958847948945428e-05, "epoch": 1.3004926108374384, "percentage": 43.35, "elapsed_time": "1:34:32", "remaining_time": "2:03:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 529, "total_steps": 1218, "loss": 0.8953, "learning_rate": 1.3932509411938969e-05, "epoch": 1.3029556650246306, "percentage": 43.43, "elapsed_time": "1:34:43", "remaining_time": "2:03:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 530, "total_steps": 1218, "loss": 0.7397, "learning_rate": 1.3906138564102794e-05, "epoch": 1.3054187192118227, "percentage": 43.51, "elapsed_time": "1:34:52", "remaining_time": "2:03:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 531, "total_steps": 1218, "loss": 0.8169, "learning_rate": 1.387973562210873e-05, "epoch": 1.3078817733990147, "percentage": 43.6, "elapsed_time": "1:35:01", "remaining_time": "2:02:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 532, "total_steps": 1218, "loss": 0.7616, "learning_rate": 1.3853300802892285e-05, "epoch": 1.3103448275862069, "percentage": 43.68, "elapsed_time": "1:35:11", "remaining_time": "2:02:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 533, "total_steps": 1218, "loss": 0.8159, "learning_rate": 1.3826834323650899e-05, "epoch": 1.312807881773399, "percentage": 43.76, "elapsed_time": "1:35:22", "remaining_time": "2:02:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 534, "total_steps": 1218, "loss": 0.7579, "learning_rate": 1.380033640184213e-05, "epoch": 1.3152709359605912, "percentage": 43.84, "elapsed_time": "1:35:33", "remaining_time": "2:02:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 535, "total_steps": 1218, "loss": 0.7243, "learning_rate": 1.3773807255181877e-05, "epoch": 1.3177339901477834, "percentage": 43.92, "elapsed_time": "1:35:43", "remaining_time": "2:02:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 536, "total_steps": 1218, "loss": 0.8649, "learning_rate": 1.3747247101642605e-05, "epoch": 1.3201970443349753, "percentage": 44.01, "elapsed_time": "1:35:56", "remaining_time": "2:02:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 537, "total_steps": 1218, "loss": 0.8011, "learning_rate": 1.3720656159451528e-05, "epoch": 1.3226600985221675, "percentage": 44.09, "elapsed_time": "1:36:07", "remaining_time": "2:01:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 538, "total_steps": 1218, "loss": 0.9275, "learning_rate": 1.369403464708884e-05, "epoch": 1.3251231527093597, "percentage": 44.17, "elapsed_time": "1:36:17", "remaining_time": "2:01:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 539, "total_steps": 1218, "loss": 0.7761, "learning_rate": 1.3667382783285903e-05, "epoch": 1.3275862068965516, "percentage": 44.25, "elapsed_time": "1:36:27", "remaining_time": "2:01:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 540, "total_steps": 1218, "loss": 0.7895, "learning_rate": 1.3640700787023465e-05, "epoch": 1.3300492610837438, "percentage": 44.33, "elapsed_time": "1:36:37", "remaining_time": "2:01:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 541, "total_steps": 1218, "loss": 0.8894, "learning_rate": 1.3613988877529844e-05, "epoch": 1.332512315270936, "percentage": 44.42, "elapsed_time": "1:36:47", "remaining_time": "2:01:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 542, "total_steps": 1218, "loss": 0.748, "learning_rate": 1.358724727427914e-05, "epoch": 1.3349753694581281, "percentage": 44.5, "elapsed_time": "1:36:57", "remaining_time": "2:00:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 543, "total_steps": 1218, "loss": 0.8096, "learning_rate": 1.3560476196989422e-05, "epoch": 1.3374384236453203, "percentage": 44.58, "elapsed_time": "1:37:08", "remaining_time": "2:00:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 544, "total_steps": 1218, "loss": 0.8036, "learning_rate": 1.3533675865620937e-05, "epoch": 1.3399014778325122, "percentage": 44.66, "elapsed_time": "1:37:20", "remaining_time": "2:00:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 545, "total_steps": 1218, "loss": 0.8674, "learning_rate": 1.3506846500374285e-05, "epoch": 1.3423645320197044, "percentage": 44.75, "elapsed_time": "1:37:30", "remaining_time": "2:00:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 546, "total_steps": 1218, "loss": 0.7865, "learning_rate": 1.3479988321688619e-05, "epoch": 1.3448275862068966, "percentage": 44.83, "elapsed_time": "1:37:40", "remaining_time": "2:00:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 547, "total_steps": 1218, "loss": 0.7725, "learning_rate": 1.345310155023984e-05, "epoch": 1.3472906403940887, "percentage": 44.91, "elapsed_time": "1:37:49", "remaining_time": "1:59:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 548, "total_steps": 1218, "loss": 0.7894, "learning_rate": 1.3426186406938769e-05, "epoch": 1.3497536945812807, "percentage": 44.99, "elapsed_time": "1:37:58", "remaining_time": "1:59:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 549, "total_steps": 1218, "loss": 0.8477, "learning_rate": 1.3399243112929341e-05, "epoch": 1.3522167487684729, "percentage": 45.07, "elapsed_time": "1:38:09", "remaining_time": "1:59:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 550, "total_steps": 1218, "loss": 0.7782, "learning_rate": 1.337227188958679e-05, "epoch": 1.354679802955665, "percentage": 45.16, "elapsed_time": "1:38:19", "remaining_time": "1:59:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 551, "total_steps": 1218, "loss": 0.8363, "learning_rate": 1.3345272958515825e-05, "epoch": 1.3571428571428572, "percentage": 45.24, "elapsed_time": "1:38:28", "remaining_time": "1:59:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 552, "total_steps": 1218, "loss": 0.7989, "learning_rate": 1.3318246541548812e-05, "epoch": 1.3596059113300494, "percentage": 45.32, "elapsed_time": "1:38:38", "remaining_time": "1:59:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 553, "total_steps": 1218, "loss": 0.8045, "learning_rate": 1.3291192860743951e-05, "epoch": 1.3620689655172413, "percentage": 45.4, "elapsed_time": "1:38:49", "remaining_time": "1:58:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 554, "total_steps": 1218, "loss": 0.812, "learning_rate": 1.3264112138383445e-05, "epoch": 1.3645320197044335, "percentage": 45.48, "elapsed_time": "1:39:03", "remaining_time": "1:58:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 555, "total_steps": 1218, "loss": 0.7654, "learning_rate": 1.3237004596971687e-05, "epoch": 1.3669950738916257, "percentage": 45.57, "elapsed_time": "1:39:14", "remaining_time": "1:58:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 556, "total_steps": 1218, "loss": 0.8295, "learning_rate": 1.3209870459233422e-05, "epoch": 1.3694581280788176, "percentage": 45.65, "elapsed_time": "1:39:24", "remaining_time": "1:58:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 557, "total_steps": 1218, "loss": 0.832, "learning_rate": 1.3182709948111921e-05, "epoch": 1.3719211822660098, "percentage": 45.73, "elapsed_time": "1:39:37", "remaining_time": "1:58:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 558, "total_steps": 1218, "loss": 0.8343, "learning_rate": 1.315552328676714e-05, "epoch": 1.374384236453202, "percentage": 45.81, "elapsed_time": "1:39:47", "remaining_time": "1:58:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 559, "total_steps": 1218, "loss": 0.8219, "learning_rate": 1.3128310698573904e-05, "epoch": 1.3768472906403941, "percentage": 45.89, "elapsed_time": "1:39:57", "remaining_time": "1:57:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 560, "total_steps": 1218, "loss": 0.8296, "learning_rate": 1.3101072407120056e-05, "epoch": 1.3793103448275863, "percentage": 45.98, "elapsed_time": "1:40:07", "remaining_time": "1:57:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 561, "total_steps": 1218, "loss": 0.8171, "learning_rate": 1.3073808636204628e-05, "epoch": 1.3817733990147782, "percentage": 46.06, "elapsed_time": "1:40:18", "remaining_time": "1:57:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 562, "total_steps": 1218, "loss": 0.7874, "learning_rate": 1.3046519609836002e-05, "epoch": 1.3842364532019704, "percentage": 46.14, "elapsed_time": "1:40:29", "remaining_time": "1:57:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 563, "total_steps": 1218, "loss": 0.7417, "learning_rate": 1.3019205552230058e-05, "epoch": 1.3866995073891626, "percentage": 46.22, "elapsed_time": "1:40:39", "remaining_time": "1:57:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 564, "total_steps": 1218, "loss": 0.8319, "learning_rate": 1.2991866687808355e-05, "epoch": 1.3891625615763548, "percentage": 46.31, "elapsed_time": "1:40:49", "remaining_time": "1:56:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 565, "total_steps": 1218, "loss": 0.7734, "learning_rate": 1.2964503241196258e-05, "epoch": 1.3916256157635467, "percentage": 46.39, "elapsed_time": "1:40:59", "remaining_time": "1:56:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 566, "total_steps": 1218, "loss": 0.7528, "learning_rate": 1.2937115437221119e-05, "epoch": 1.3940886699507389, "percentage": 46.47, "elapsed_time": "1:41:10", "remaining_time": "1:56:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 567, "total_steps": 1218, "loss": 0.8612, "learning_rate": 1.290970350091042e-05, "epoch": 1.396551724137931, "percentage": 46.55, "elapsed_time": "1:41:24", "remaining_time": "1:56:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 568, "total_steps": 1218, "loss": 0.8118, "learning_rate": 1.2882267657489908e-05, "epoch": 1.3990147783251232, "percentage": 46.63, "elapsed_time": "1:41:37", "remaining_time": "1:56:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 569, "total_steps": 1218, "loss": 0.7544, "learning_rate": 1.2854808132381778e-05, "epoch": 1.4014778325123154, "percentage": 46.72, "elapsed_time": "1:41:47", "remaining_time": "1:56:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 570, "total_steps": 1218, "loss": 0.9057, "learning_rate": 1.2827325151202783e-05, "epoch": 1.4039408866995073, "percentage": 46.8, "elapsed_time": "1:41:58", "remaining_time": "1:55:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 571, "total_steps": 1218, "loss": 0.8084, "learning_rate": 1.2799818939762411e-05, "epoch": 1.4064039408866995, "percentage": 46.88, "elapsed_time": "1:42:08", "remaining_time": "1:55:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 572, "total_steps": 1218, "loss": 0.8076, "learning_rate": 1.2772289724061015e-05, "epoch": 1.4088669950738917, "percentage": 46.96, "elapsed_time": "1:42:21", "remaining_time": "1:55:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 573, "total_steps": 1218, "loss": 0.8122, "learning_rate": 1.2744737730287961e-05, "epoch": 1.4113300492610836, "percentage": 47.04, "elapsed_time": "1:42:31", "remaining_time": "1:55:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 574, "total_steps": 1218, "loss": 0.7615, "learning_rate": 1.2717163184819761e-05, "epoch": 1.4137931034482758, "percentage": 47.13, "elapsed_time": "1:42:41", "remaining_time": "1:55:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 575, "total_steps": 1218, "loss": 0.8374, "learning_rate": 1.2689566314218229e-05, "epoch": 1.416256157635468, "percentage": 47.21, "elapsed_time": "1:42:52", "remaining_time": "1:55:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 576, "total_steps": 1218, "loss": 0.7963, "learning_rate": 1.2661947345228593e-05, "epoch": 1.4187192118226601, "percentage": 47.29, "elapsed_time": "1:43:01", "remaining_time": "1:54:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 577, "total_steps": 1218, "loss": 0.8145, "learning_rate": 1.2634306504777669e-05, "epoch": 1.4211822660098523, "percentage": 47.37, "elapsed_time": "1:43:12", "remaining_time": "1:54:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 578, "total_steps": 1218, "loss": 0.803, "learning_rate": 1.2606644019971967e-05, "epoch": 1.4236453201970443, "percentage": 47.45, "elapsed_time": "1:43:22", "remaining_time": "1:54:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 579, "total_steps": 1218, "loss": 0.8445, "learning_rate": 1.257896011809583e-05, "epoch": 1.4261083743842364, "percentage": 47.54, "elapsed_time": "1:43:31", "remaining_time": "1:54:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 580, "total_steps": 1218, "loss": 0.7574, "learning_rate": 1.255125502660958e-05, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "1:43:41", "remaining_time": "1:54:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 581, "total_steps": 1218, "loss": 0.76, "learning_rate": 1.2523528973147631e-05, "epoch": 1.4310344827586206, "percentage": 47.7, "elapsed_time": "1:43:52", "remaining_time": "1:53:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 582, "total_steps": 1218, "loss": 0.8747, "learning_rate": 1.2495782185516638e-05, "epoch": 1.4334975369458127, "percentage": 47.78, "elapsed_time": "1:44:03", "remaining_time": "1:53:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 583, "total_steps": 1218, "loss": 0.8049, "learning_rate": 1.2468014891693603e-05, "epoch": 1.435960591133005, "percentage": 47.87, "elapsed_time": "1:44:16", "remaining_time": "1:53:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 584, "total_steps": 1218, "loss": 0.8206, "learning_rate": 1.2440227319824024e-05, "epoch": 1.438423645320197, "percentage": 47.95, "elapsed_time": "1:44:27", "remaining_time": "1:53:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 585, "total_steps": 1218, "loss": 0.8058, "learning_rate": 1.2412419698220002e-05, "epoch": 1.4408866995073892, "percentage": 48.03, "elapsed_time": "1:44:37", "remaining_time": "1:53:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 586, "total_steps": 1218, "loss": 0.7911, "learning_rate": 1.2384592255358385e-05, "epoch": 1.4433497536945814, "percentage": 48.11, "elapsed_time": "1:44:47", "remaining_time": "1:53:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 587, "total_steps": 1218, "loss": 0.8202, "learning_rate": 1.2356745219878865e-05, "epoch": 1.4458128078817734, "percentage": 48.19, "elapsed_time": "1:44:58", "remaining_time": "1:52:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 588, "total_steps": 1218, "loss": 0.7612, "learning_rate": 1.2328878820582122e-05, "epoch": 1.4482758620689655, "percentage": 48.28, "elapsed_time": "1:45:08", "remaining_time": "1:52:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 589, "total_steps": 1218, "loss": 0.7667, "learning_rate": 1.2300993286427937e-05, "epoch": 1.4507389162561577, "percentage": 48.36, "elapsed_time": "1:45:18", "remaining_time": "1:52:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 590, "total_steps": 1218, "loss": 0.8296, "learning_rate": 1.2273088846533303e-05, "epoch": 1.4532019704433496, "percentage": 48.44, "elapsed_time": "1:45:29", "remaining_time": "1:52:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 591, "total_steps": 1218, "loss": 0.7107, "learning_rate": 1.2245165730170556e-05, "epoch": 1.4556650246305418, "percentage": 48.52, "elapsed_time": "1:45:41", "remaining_time": "1:52:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 592, "total_steps": 1218, "loss": 0.8011, "learning_rate": 1.2217224166765478e-05, "epoch": 1.458128078817734, "percentage": 48.6, "elapsed_time": "1:45:53", "remaining_time": "1:51:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 593, "total_steps": 1218, "loss": 0.8479, "learning_rate": 1.2189264385895422e-05, "epoch": 1.4605911330049262, "percentage": 48.69, "elapsed_time": "1:46:05", "remaining_time": "1:51:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 594, "total_steps": 1218, "loss": 0.8192, "learning_rate": 1.216128661728742e-05, "epoch": 1.4630541871921183, "percentage": 48.77, "elapsed_time": "1:46:16", "remaining_time": "1:51:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 595, "total_steps": 1218, "loss": 0.8309, "learning_rate": 1.2133291090816298e-05, "epoch": 1.4655172413793103, "percentage": 48.85, "elapsed_time": "1:46:26", "remaining_time": "1:51:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 596, "total_steps": 1218, "loss": 0.7888, "learning_rate": 1.2105278036502787e-05, "epoch": 1.4679802955665024, "percentage": 48.93, "elapsed_time": "1:46:39", "remaining_time": "1:51:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 597, "total_steps": 1218, "loss": 0.8222, "learning_rate": 1.207724768451164e-05, "epoch": 1.4704433497536946, "percentage": 49.01, "elapsed_time": "1:46:50", "remaining_time": "1:51:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 598, "total_steps": 1218, "loss": 0.8208, "learning_rate": 1.204920026514971e-05, "epoch": 1.4729064039408866, "percentage": 49.1, "elapsed_time": "1:47:01", "remaining_time": "1:50:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 599, "total_steps": 1218, "loss": 0.759, "learning_rate": 1.202113600886411e-05, "epoch": 1.4753694581280787, "percentage": 49.18, "elapsed_time": "1:47:12", "remaining_time": "1:50:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 600, "total_steps": 1218, "loss": 0.8169, "learning_rate": 1.1993055146240273e-05, "epoch": 1.477832512315271, "percentage": 49.26, "elapsed_time": "1:47:22", "remaining_time": "1:50:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 601, "total_steps": 1218, "loss": 0.7543, "learning_rate": 1.1964957908000084e-05, "epoch": 1.480295566502463, "percentage": 49.34, "elapsed_time": "1:47:31", "remaining_time": "1:50:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 602, "total_steps": 1218, "loss": 0.864, "learning_rate": 1.1936844524999966e-05, "epoch": 1.4827586206896552, "percentage": 49.43, "elapsed_time": "1:47:43", "remaining_time": "1:50:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 603, "total_steps": 1218, "loss": 0.8488, "learning_rate": 1.1908715228229007e-05, "epoch": 1.4852216748768474, "percentage": 49.51, "elapsed_time": "1:47:53", "remaining_time": "1:50:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 604, "total_steps": 1218, "loss": 0.8228, "learning_rate": 1.1880570248807033e-05, "epoch": 1.4876847290640394, "percentage": 49.59, "elapsed_time": "1:48:02", "remaining_time": "1:49:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 605, "total_steps": 1218, "loss": 0.7722, "learning_rate": 1.1852409817982732e-05, "epoch": 1.4901477832512315, "percentage": 49.67, "elapsed_time": "1:48:12", "remaining_time": "1:49:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 606, "total_steps": 1218, "loss": 0.8303, "learning_rate": 1.1824234167131748e-05, "epoch": 1.4926108374384237, "percentage": 49.75, "elapsed_time": "1:48:23", "remaining_time": "1:49:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 607, "total_steps": 1218, "loss": 0.8247, "learning_rate": 1.1796043527754775e-05, "epoch": 1.4950738916256157, "percentage": 49.84, "elapsed_time": "1:48:33", "remaining_time": "1:49:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 608, "total_steps": 1218, "loss": 0.8317, "learning_rate": 1.1767838131475654e-05, "epoch": 1.4975369458128078, "percentage": 49.92, "elapsed_time": "1:48:43", "remaining_time": "1:49:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 609, "total_steps": 1218, "loss": 0.8387, "learning_rate": 1.1739618210039476e-05, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "1:48:55", "remaining_time": "1:48:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 610, "total_steps": 1218, "loss": 0.8095, "learning_rate": 1.171138399531068e-05, "epoch": 1.5024630541871922, "percentage": 50.08, "elapsed_time": "1:49:58", "remaining_time": "1:49:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 611, "total_steps": 1218, "loss": 0.7528, "learning_rate": 1.1683135719271143e-05, "epoch": 1.5049261083743843, "percentage": 50.16, "elapsed_time": "1:50:08", "remaining_time": "1:49:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 612, "total_steps": 1218, "loss": 0.708, "learning_rate": 1.1654873614018266e-05, "epoch": 1.5073891625615765, "percentage": 50.25, "elapsed_time": "1:50:18", "remaining_time": "1:49:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 613, "total_steps": 1218, "loss": 0.8625, "learning_rate": 1.1626597911763085e-05, "epoch": 1.5098522167487685, "percentage": 50.33, "elapsed_time": "1:50:29", "remaining_time": "1:49:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 614, "total_steps": 1218, "loss": 0.777, "learning_rate": 1.1598308844828348e-05, "epoch": 1.5123152709359606, "percentage": 50.41, "elapsed_time": "1:50:40", "remaining_time": "1:48:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 615, "total_steps": 1218, "loss": 0.7645, "learning_rate": 1.1570006645646614e-05, "epoch": 1.5147783251231526, "percentage": 50.49, "elapsed_time": "1:50:51", "remaining_time": "1:48:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 616, "total_steps": 1218, "loss": 0.7522, "learning_rate": 1.1541691546758343e-05, "epoch": 1.5172413793103448, "percentage": 50.57, "elapsed_time": "1:51:02", "remaining_time": "1:48:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 617, "total_steps": 1218, "loss": 0.7629, "learning_rate": 1.1513363780809974e-05, "epoch": 1.519704433497537, "percentage": 50.66, "elapsed_time": "1:51:13", "remaining_time": "1:48:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 618, "total_steps": 1218, "loss": 0.8078, "learning_rate": 1.1485023580552039e-05, "epoch": 1.522167487684729, "percentage": 50.74, "elapsed_time": "1:51:23", "remaining_time": "1:48:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 619, "total_steps": 1218, "loss": 0.8732, "learning_rate": 1.145667117883722e-05, "epoch": 1.5246305418719213, "percentage": 50.82, "elapsed_time": "1:51:42", "remaining_time": "1:48:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 620, "total_steps": 1218, "loss": 0.8185, "learning_rate": 1.1428306808618456e-05, "epoch": 1.5270935960591134, "percentage": 50.9, "elapsed_time": "1:51:54", "remaining_time": "1:47:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 621, "total_steps": 1218, "loss": 0.756, "learning_rate": 1.1399930702947025e-05, "epoch": 1.5295566502463054, "percentage": 50.99, "elapsed_time": "1:52:03", "remaining_time": "1:47:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 622, "total_steps": 1218, "loss": 0.7755, "learning_rate": 1.1371543094970624e-05, "epoch": 1.5320197044334976, "percentage": 51.07, "elapsed_time": "1:52:14", "remaining_time": "1:47:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 623, "total_steps": 1218, "loss": 0.8264, "learning_rate": 1.1343144217931457e-05, "epoch": 1.5344827586206895, "percentage": 51.15, "elapsed_time": "1:52:24", "remaining_time": "1:47:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 624, "total_steps": 1218, "loss": 0.832, "learning_rate": 1.131473430516432e-05, "epoch": 1.5369458128078817, "percentage": 51.23, "elapsed_time": "1:52:34", "remaining_time": "1:47:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 625, "total_steps": 1218, "loss": 0.7755, "learning_rate": 1.1286313590094686e-05, "epoch": 1.5394088669950738, "percentage": 51.31, "elapsed_time": "1:52:46", "remaining_time": "1:47:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 626, "total_steps": 1218, "loss": 0.8177, "learning_rate": 1.1257882306236776e-05, "epoch": 1.541871921182266, "percentage": 51.4, "elapsed_time": "1:52:57", "remaining_time": "1:46:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 627, "total_steps": 1218, "loss": 0.8898, "learning_rate": 1.1229440687191649e-05, "epoch": 1.5443349753694582, "percentage": 51.48, "elapsed_time": "1:53:07", "remaining_time": "1:46:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 628, "total_steps": 1218, "loss": 0.7424, "learning_rate": 1.1200988966645286e-05, "epoch": 1.5467980295566504, "percentage": 51.56, "elapsed_time": "1:53:20", "remaining_time": "1:46:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 629, "total_steps": 1218, "loss": 0.8885, "learning_rate": 1.1172527378366664e-05, "epoch": 1.5492610837438425, "percentage": 51.64, "elapsed_time": "1:53:30", "remaining_time": "1:46:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 630, "total_steps": 1218, "loss": 0.8056, "learning_rate": 1.1144056156205834e-05, "epoch": 1.5517241379310345, "percentage": 51.72, "elapsed_time": "1:53:40", "remaining_time": "1:46:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 631, "total_steps": 1218, "loss": 0.812, "learning_rate": 1.1115575534092003e-05, "epoch": 1.5541871921182266, "percentage": 51.81, "elapsed_time": "1:53:51", "remaining_time": "1:45:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 632, "total_steps": 1218, "loss": 0.7681, "learning_rate": 1.1087085746031612e-05, "epoch": 1.5566502463054186, "percentage": 51.89, "elapsed_time": "1:54:03", "remaining_time": "1:45:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 633, "total_steps": 1218, "loss": 0.7321, "learning_rate": 1.1058587026106413e-05, "epoch": 1.5591133004926108, "percentage": 51.97, "elapsed_time": "1:54:13", "remaining_time": "1:45:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 634, "total_steps": 1218, "loss": 0.7562, "learning_rate": 1.1030079608471544e-05, "epoch": 1.561576354679803, "percentage": 52.05, "elapsed_time": "1:54:23", "remaining_time": "1:45:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 635, "total_steps": 1218, "loss": 0.6928, "learning_rate": 1.1001563727353611e-05, "epoch": 1.564039408866995, "percentage": 52.13, "elapsed_time": "1:54:38", "remaining_time": "1:45:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 636, "total_steps": 1218, "loss": 0.8037, "learning_rate": 1.0973039617048748e-05, "epoch": 1.5665024630541873, "percentage": 52.22, "elapsed_time": "1:54:49", "remaining_time": "1:45:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 637, "total_steps": 1218, "loss": 0.7353, "learning_rate": 1.0944507511920715e-05, "epoch": 1.5689655172413794, "percentage": 52.3, "elapsed_time": "1:55:00", "remaining_time": "1:44:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 638, "total_steps": 1218, "loss": 0.7519, "learning_rate": 1.091596764639895e-05, "epoch": 1.5714285714285714, "percentage": 52.38, "elapsed_time": "1:55:10", "remaining_time": "1:44:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 639, "total_steps": 1218, "loss": 0.7385, "learning_rate": 1.0887420254976661e-05, "epoch": 1.5738916256157636, "percentage": 52.46, "elapsed_time": "1:55:24", "remaining_time": "1:44:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 640, "total_steps": 1218, "loss": 0.8075, "learning_rate": 1.0858865572208892e-05, "epoch": 1.5763546798029555, "percentage": 52.55, "elapsed_time": "1:55:36", "remaining_time": "1:44:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 641, "total_steps": 1218, "loss": 0.8216, "learning_rate": 1.0830303832710584e-05, "epoch": 1.5788177339901477, "percentage": 52.63, "elapsed_time": "1:55:48", "remaining_time": "1:44:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 642, "total_steps": 1218, "loss": 0.8193, "learning_rate": 1.080173527115467e-05, "epoch": 1.5812807881773399, "percentage": 52.71, "elapsed_time": "1:55:58", "remaining_time": "1:44:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 643, "total_steps": 1218, "loss": 0.7992, "learning_rate": 1.0773160122270127e-05, "epoch": 1.583743842364532, "percentage": 52.79, "elapsed_time": "1:56:08", "remaining_time": "1:43:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 644, "total_steps": 1218, "loss": 0.7955, "learning_rate": 1.0744578620840065e-05, "epoch": 1.5862068965517242, "percentage": 52.87, "elapsed_time": "1:56:19", "remaining_time": "1:43:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 645, "total_steps": 1218, "loss": 0.8444, "learning_rate": 1.071599100169978e-05, "epoch": 1.5886699507389164, "percentage": 52.96, "elapsed_time": "1:56:29", "remaining_time": "1:43:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 646, "total_steps": 1218, "loss": 0.8145, "learning_rate": 1.0687397499734842e-05, "epoch": 1.5911330049261085, "percentage": 53.04, "elapsed_time": "1:56:39", "remaining_time": "1:43:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 647, "total_steps": 1218, "loss": 0.7826, "learning_rate": 1.0658798349879144e-05, "epoch": 1.5935960591133005, "percentage": 53.12, "elapsed_time": "1:56:50", "remaining_time": "1:43:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 648, "total_steps": 1218, "loss": 0.7337, "learning_rate": 1.0630193787112994e-05, "epoch": 1.5960591133004927, "percentage": 53.2, "elapsed_time": "1:57:00", "remaining_time": "1:42:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 649, "total_steps": 1218, "loss": 0.8309, "learning_rate": 1.0601584046461173e-05, "epoch": 1.5985221674876846, "percentage": 53.28, "elapsed_time": "1:57:09", "remaining_time": "1:42:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 650, "total_steps": 1218, "loss": 0.7868, "learning_rate": 1.0572969362991e-05, "epoch": 1.6009852216748768, "percentage": 53.37, "elapsed_time": "1:57:19", "remaining_time": "1:42:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 651, "total_steps": 1218, "loss": 0.7627, "learning_rate": 1.0544349971810413e-05, "epoch": 1.603448275862069, "percentage": 53.45, "elapsed_time": "1:57:29", "remaining_time": "1:42:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 652, "total_steps": 1218, "loss": 0.8094, "learning_rate": 1.0515726108066025e-05, "epoch": 1.6059113300492611, "percentage": 53.53, "elapsed_time": "1:57:40", "remaining_time": "1:42:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 653, "total_steps": 1218, "loss": 0.724, "learning_rate": 1.0487098006941197e-05, "epoch": 1.6083743842364533, "percentage": 53.61, "elapsed_time": "1:57:50", "remaining_time": "1:41:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 654, "total_steps": 1218, "loss": 0.8228, "learning_rate": 1.0458465903654107e-05, "epoch": 1.6108374384236455, "percentage": 53.69, "elapsed_time": "1:58:01", "remaining_time": "1:41:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 655, "total_steps": 1218, "loss": 0.776, "learning_rate": 1.0429830033455821e-05, "epoch": 1.6133004926108374, "percentage": 53.78, "elapsed_time": "1:58:12", "remaining_time": "1:41:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 656, "total_steps": 1218, "loss": 0.7745, "learning_rate": 1.0401190631628348e-05, "epoch": 1.6157635467980296, "percentage": 53.86, "elapsed_time": "1:58:23", "remaining_time": "1:41:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 657, "total_steps": 1218, "loss": 0.8509, "learning_rate": 1.037254793348272e-05, "epoch": 1.6182266009852215, "percentage": 53.94, "elapsed_time": "1:58:35", "remaining_time": "1:41:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 658, "total_steps": 1218, "loss": 0.7648, "learning_rate": 1.034390217435704e-05, "epoch": 1.6206896551724137, "percentage": 54.02, "elapsed_time": "1:58:45", "remaining_time": "1:41:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 659, "total_steps": 1218, "loss": 0.7229, "learning_rate": 1.031525358961458e-05, "epoch": 1.6231527093596059, "percentage": 54.11, "elapsed_time": "1:58:55", "remaining_time": "1:40:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 660, "total_steps": 1218, "loss": 0.7521, "learning_rate": 1.0286602414641818e-05, "epoch": 1.625615763546798, "percentage": 54.19, "elapsed_time": "1:59:05", "remaining_time": "1:40:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 661, "total_steps": 1218, "loss": 0.787, "learning_rate": 1.0257948884846507e-05, "epoch": 1.6280788177339902, "percentage": 54.27, "elapsed_time": "1:59:20", "remaining_time": "1:40:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 662, "total_steps": 1218, "loss": 0.7752, "learning_rate": 1.0229293235655768e-05, "epoch": 1.6305418719211824, "percentage": 54.35, "elapsed_time": "1:59:31", "remaining_time": "1:40:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 663, "total_steps": 1218, "loss": 0.7768, "learning_rate": 1.0200635702514115e-05, "epoch": 1.6330049261083743, "percentage": 54.43, "elapsed_time": "1:59:44", "remaining_time": "1:40:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 664, "total_steps": 1218, "loss": 0.7752, "learning_rate": 1.0171976520881552e-05, "epoch": 1.6354679802955665, "percentage": 54.52, "elapsed_time": "1:59:54", "remaining_time": "1:40:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 665, "total_steps": 1218, "loss": 0.861, "learning_rate": 1.0143315926231625e-05, "epoch": 1.6379310344827587, "percentage": 54.6, "elapsed_time": "2:00:09", "remaining_time": "1:39:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 666, "total_steps": 1218, "loss": 0.8735, "learning_rate": 1.011465415404949e-05, "epoch": 1.6403940886699506, "percentage": 54.68, "elapsed_time": "2:00:20", "remaining_time": "1:39:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 667, "total_steps": 1218, "loss": 0.8135, "learning_rate": 1.0085991439829981e-05, "epoch": 1.6428571428571428, "percentage": 54.76, "elapsed_time": "2:00:30", "remaining_time": "1:39:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 668, "total_steps": 1218, "loss": 0.8085, "learning_rate": 1.005732801907567e-05, "epoch": 1.645320197044335, "percentage": 54.84, "elapsed_time": "2:00:41", "remaining_time": "1:39:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 669, "total_steps": 1218, "loss": 0.8169, "learning_rate": 1.0028664127294924e-05, "epoch": 1.6477832512315271, "percentage": 54.93, "elapsed_time": "2:00:51", "remaining_time": "1:39:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 670, "total_steps": 1218, "loss": 0.7487, "learning_rate": 1e-05, "epoch": 1.6502463054187193, "percentage": 55.01, "elapsed_time": "2:01:01", "remaining_time": "1:38:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 671, "total_steps": 1218, "loss": 0.816, "learning_rate": 9.971335872705076e-06, "epoch": 1.6527093596059115, "percentage": 55.09, "elapsed_time": "2:01:12", "remaining_time": "1:38:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 672, "total_steps": 1218, "loss": 0.8639, "learning_rate": 9.942671980924336e-06, "epoch": 1.6551724137931034, "percentage": 55.17, "elapsed_time": "2:01:23", "remaining_time": "1:38:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 673, "total_steps": 1218, "loss": 0.7564, "learning_rate": 9.91400856017002e-06, "epoch": 1.6576354679802956, "percentage": 55.25, "elapsed_time": "2:01:33", "remaining_time": "1:38:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 674, "total_steps": 1218, "loss": 0.7742, "learning_rate": 9.88534584595051e-06, "epoch": 1.6600985221674875, "percentage": 55.34, "elapsed_time": "2:01:43", "remaining_time": "1:38:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 675, "total_steps": 1218, "loss": 0.7488, "learning_rate": 9.856684073768378e-06, "epoch": 1.6625615763546797, "percentage": 55.42, "elapsed_time": "2:01:53", "remaining_time": "1:38:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 676, "total_steps": 1218, "loss": 0.8409, "learning_rate": 9.82802347911845e-06, "epoch": 1.6650246305418719, "percentage": 55.5, "elapsed_time": "2:02:05", "remaining_time": "1:37:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 677, "total_steps": 1218, "loss": 0.802, "learning_rate": 9.799364297485889e-06, "epoch": 1.667487684729064, "percentage": 55.58, "elapsed_time": "2:02:15", "remaining_time": "1:37:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 678, "total_steps": 1218, "loss": 0.787, "learning_rate": 9.770706764344235e-06, "epoch": 1.6699507389162562, "percentage": 55.67, "elapsed_time": "2:02:24", "remaining_time": "1:37:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 679, "total_steps": 1218, "loss": 0.8629, "learning_rate": 9.742051115153494e-06, "epoch": 1.6724137931034484, "percentage": 55.75, "elapsed_time": "2:02:34", "remaining_time": "1:37:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 680, "total_steps": 1218, "loss": 0.8705, "learning_rate": 9.713397585358189e-06, "epoch": 1.6748768472906403, "percentage": 55.83, "elapsed_time": "2:02:45", "remaining_time": "1:37:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 681, "total_steps": 1218, "loss": 0.7341, "learning_rate": 9.684746410385423e-06, "epoch": 1.6773399014778325, "percentage": 55.91, "elapsed_time": "2:02:55", "remaining_time": "1:36:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 682, "total_steps": 1218, "loss": 0.8532, "learning_rate": 9.65609782564296e-06, "epoch": 1.6798029556650245, "percentage": 55.99, "elapsed_time": "2:03:05", "remaining_time": "1:36:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 683, "total_steps": 1218, "loss": 0.8299, "learning_rate": 9.627452066517287e-06, "epoch": 1.6822660098522166, "percentage": 56.08, "elapsed_time": "2:03:15", "remaining_time": "1:36:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 684, "total_steps": 1218, "loss": 0.8729, "learning_rate": 9.598809368371656e-06, "epoch": 1.6847290640394088, "percentage": 56.16, "elapsed_time": "2:03:27", "remaining_time": "1:36:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 685, "total_steps": 1218, "loss": 0.8646, "learning_rate": 9.57016996654418e-06, "epoch": 1.687192118226601, "percentage": 56.24, "elapsed_time": "2:03:41", "remaining_time": "1:36:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 686, "total_steps": 1218, "loss": 0.8558, "learning_rate": 9.541534096345896e-06, "epoch": 1.6896551724137931, "percentage": 56.32, "elapsed_time": "2:03:52", "remaining_time": "1:36:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 687, "total_steps": 1218, "loss": 0.8423, "learning_rate": 9.512901993058806e-06, "epoch": 1.6921182266009853, "percentage": 56.4, "elapsed_time": "2:04:07", "remaining_time": "1:35:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 688, "total_steps": 1218, "loss": 0.8183, "learning_rate": 9.484273891933982e-06, "epoch": 1.6945812807881775, "percentage": 56.49, "elapsed_time": "2:04:19", "remaining_time": "1:35:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 689, "total_steps": 1218, "loss": 0.7902, "learning_rate": 9.45565002818959e-06, "epoch": 1.6970443349753694, "percentage": 56.57, "elapsed_time": "2:04:29", "remaining_time": "1:35:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 690, "total_steps": 1218, "loss": 0.8244, "learning_rate": 9.427030637009002e-06, "epoch": 1.6995073891625616, "percentage": 56.65, "elapsed_time": "2:04:39", "remaining_time": "1:35:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 691, "total_steps": 1218, "loss": 0.7736, "learning_rate": 9.398415953538832e-06, "epoch": 1.7019704433497536, "percentage": 56.73, "elapsed_time": "2:04:52", "remaining_time": "1:35:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 692, "total_steps": 1218, "loss": 0.8151, "learning_rate": 9.369806212887008e-06, "epoch": 1.7044334975369457, "percentage": 56.81, "elapsed_time": "2:05:02", "remaining_time": "1:35:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 693, "total_steps": 1218, "loss": 0.7932, "learning_rate": 9.341201650120857e-06, "epoch": 1.706896551724138, "percentage": 56.9, "elapsed_time": "2:05:12", "remaining_time": "1:34:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 694, "total_steps": 1218, "loss": 0.7487, "learning_rate": 9.312602500265162e-06, "epoch": 1.70935960591133, "percentage": 56.98, "elapsed_time": "2:05:23", "remaining_time": "1:34:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 695, "total_steps": 1218, "loss": 0.8448, "learning_rate": 9.284008998300221e-06, "epoch": 1.7118226600985222, "percentage": 57.06, "elapsed_time": "2:05:34", "remaining_time": "1:34:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 696, "total_steps": 1218, "loss": 0.7532, "learning_rate": 9.255421379159935e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "2:05:44", "remaining_time": "1:34:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 697, "total_steps": 1218, "loss": 0.7648, "learning_rate": 9.226839877729875e-06, "epoch": 1.7167487684729064, "percentage": 57.22, "elapsed_time": "2:05:53", "remaining_time": "1:34:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 698, "total_steps": 1218, "loss": 0.7629, "learning_rate": 9.198264728845332e-06, "epoch": 1.7192118226600985, "percentage": 57.31, "elapsed_time": "2:06:04", "remaining_time": "1:33:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 699, "total_steps": 1218, "loss": 0.7358, "learning_rate": 9.16969616728942e-06, "epoch": 1.7216748768472905, "percentage": 57.39, "elapsed_time": "2:06:14", "remaining_time": "1:33:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 700, "total_steps": 1218, "loss": 0.8003, "learning_rate": 9.14113442779111e-06, "epoch": 1.7241379310344827, "percentage": 57.47, "elapsed_time": "2:06:24", "remaining_time": "1:33:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 701, "total_steps": 1218, "loss": 0.8707, "learning_rate": 9.112579745023339e-06, "epoch": 1.7266009852216748, "percentage": 57.55, "elapsed_time": "2:06:34", "remaining_time": "1:33:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 702, "total_steps": 1218, "loss": 0.8248, "learning_rate": 9.084032353601053e-06, "epoch": 1.729064039408867, "percentage": 57.64, "elapsed_time": "2:06:49", "remaining_time": "1:33:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 703, "total_steps": 1218, "loss": 0.7968, "learning_rate": 9.055492488079288e-06, "epoch": 1.7315270935960592, "percentage": 57.72, "elapsed_time": "2:06:59", "remaining_time": "1:33:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 704, "total_steps": 1218, "loss": 0.8412, "learning_rate": 9.026960382951253e-06, "epoch": 1.7339901477832513, "percentage": 57.8, "elapsed_time": "2:07:10", "remaining_time": "1:32:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 705, "total_steps": 1218, "loss": 0.8316, "learning_rate": 8.998436272646394e-06, "epoch": 1.7364532019704435, "percentage": 57.88, "elapsed_time": "2:07:22", "remaining_time": "1:32:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 706, "total_steps": 1218, "loss": 0.8217, "learning_rate": 8.969920391528459e-06, "epoch": 1.7389162561576355, "percentage": 57.96, "elapsed_time": "2:07:32", "remaining_time": "1:32:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 707, "total_steps": 1218, "loss": 0.8701, "learning_rate": 8.941412973893594e-06, "epoch": 1.7413793103448276, "percentage": 58.05, "elapsed_time": "2:07:43", "remaining_time": "1:32:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 708, "total_steps": 1218, "loss": 0.8012, "learning_rate": 8.912914253968391e-06, "epoch": 1.7438423645320196, "percentage": 58.13, "elapsed_time": "2:07:54", "remaining_time": "1:32:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 709, "total_steps": 1218, "loss": 0.8607, "learning_rate": 8.884424465907999e-06, "epoch": 1.7463054187192117, "percentage": 58.21, "elapsed_time": "2:08:05", "remaining_time": "1:31:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 710, "total_steps": 1218, "loss": 0.9043, "learning_rate": 8.855943843794171e-06, "epoch": 1.748768472906404, "percentage": 58.29, "elapsed_time": "2:08:15", "remaining_time": "1:31:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 711, "total_steps": 1218, "loss": 0.8844, "learning_rate": 8.827472621633338e-06, "epoch": 1.751231527093596, "percentage": 58.37, "elapsed_time": "2:08:27", "remaining_time": "1:31:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 712, "total_steps": 1218, "loss": 0.7509, "learning_rate": 8.799011033354716e-06, "epoch": 1.7536945812807883, "percentage": 58.46, "elapsed_time": "2:08:38", "remaining_time": "1:31:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 713, "total_steps": 1218, "loss": 0.7192, "learning_rate": 8.770559312808356e-06, "epoch": 1.7561576354679804, "percentage": 58.54, "elapsed_time": "2:08:48", "remaining_time": "1:31:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 714, "total_steps": 1218, "loss": 0.7903, "learning_rate": 8.742117693763229e-06, "epoch": 1.7586206896551724, "percentage": 58.62, "elapsed_time": "2:08:58", "remaining_time": "1:31:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 715, "total_steps": 1218, "loss": 0.8037, "learning_rate": 8.713686409905314e-06, "epoch": 1.7610837438423645, "percentage": 58.7, "elapsed_time": "2:09:08", "remaining_time": "1:30:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 716, "total_steps": 1218, "loss": 0.7899, "learning_rate": 8.685265694835681e-06, "epoch": 1.7635467980295565, "percentage": 58.78, "elapsed_time": "2:09:19", "remaining_time": "1:30:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 717, "total_steps": 1218, "loss": 0.8248, "learning_rate": 8.656855782068546e-06, "epoch": 1.7660098522167487, "percentage": 58.87, "elapsed_time": "2:09:31", "remaining_time": "1:30:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 718, "total_steps": 1218, "loss": 0.7503, "learning_rate": 8.628456905029383e-06, "epoch": 1.7684729064039408, "percentage": 58.95, "elapsed_time": "2:09:41", "remaining_time": "1:30:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 719, "total_steps": 1218, "loss": 0.8082, "learning_rate": 8.600069297052978e-06, "epoch": 1.770935960591133, "percentage": 59.03, "elapsed_time": "2:09:51", "remaining_time": "1:30:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 720, "total_steps": 1218, "loss": 0.8413, "learning_rate": 8.571693191381545e-06, "epoch": 1.7733990147783252, "percentage": 59.11, "elapsed_time": "2:10:01", "remaining_time": "1:29:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 721, "total_steps": 1218, "loss": 0.805, "learning_rate": 8.543328821162784e-06, "epoch": 1.7758620689655173, "percentage": 59.2, "elapsed_time": "2:10:11", "remaining_time": "1:29:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 722, "total_steps": 1218, "loss": 0.8134, "learning_rate": 8.514976419447963e-06, "epoch": 1.7783251231527095, "percentage": 59.28, "elapsed_time": "2:10:22", "remaining_time": "1:29:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 723, "total_steps": 1218, "loss": 0.7808, "learning_rate": 8.486636219190027e-06, "epoch": 1.7807881773399015, "percentage": 59.36, "elapsed_time": "2:10:33", "remaining_time": "1:29:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 724, "total_steps": 1218, "loss": 0.8469, "learning_rate": 8.458308453241664e-06, "epoch": 1.7832512315270936, "percentage": 59.44, "elapsed_time": "2:10:42", "remaining_time": "1:29:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 725, "total_steps": 1218, "loss": 0.7705, "learning_rate": 8.429993354353389e-06, "epoch": 1.7857142857142856, "percentage": 59.52, "elapsed_time": "2:10:52", "remaining_time": "1:28:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 726, "total_steps": 1218, "loss": 0.7969, "learning_rate": 8.401691155171654e-06, "epoch": 1.7881773399014778, "percentage": 59.61, "elapsed_time": "2:11:02", "remaining_time": "1:28:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 727, "total_steps": 1218, "loss": 0.8231, "learning_rate": 8.373402088236919e-06, "epoch": 1.79064039408867, "percentage": 59.69, "elapsed_time": "2:11:13", "remaining_time": "1:28:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 728, "total_steps": 1218, "loss": 0.7968, "learning_rate": 8.345126385981737e-06, "epoch": 1.793103448275862, "percentage": 59.77, "elapsed_time": "2:11:23", "remaining_time": "1:28:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 729, "total_steps": 1218, "loss": 0.8681, "learning_rate": 8.316864280728862e-06, "epoch": 1.7955665024630543, "percentage": 59.85, "elapsed_time": "2:11:34", "remaining_time": "1:28:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 730, "total_steps": 1218, "loss": 0.7903, "learning_rate": 8.288616004689321e-06, "epoch": 1.7980295566502464, "percentage": 59.93, "elapsed_time": "2:11:44", "remaining_time": "1:28:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 731, "total_steps": 1218, "loss": 0.7438, "learning_rate": 8.260381789960524e-06, "epoch": 1.8004926108374384, "percentage": 60.02, "elapsed_time": "2:11:54", "remaining_time": "1:27:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 732, "total_steps": 1218, "loss": 0.7472, "learning_rate": 8.23216186852435e-06, "epoch": 1.8029556650246306, "percentage": 60.1, "elapsed_time": "2:12:05", "remaining_time": "1:27:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 733, "total_steps": 1218, "loss": 0.8197, "learning_rate": 8.203956472245226e-06, "epoch": 1.8054187192118225, "percentage": 60.18, "elapsed_time": "2:12:15", "remaining_time": "1:27:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 734, "total_steps": 1218, "loss": 0.8366, "learning_rate": 8.175765832868252e-06, "epoch": 1.8078817733990147, "percentage": 60.26, "elapsed_time": "2:12:25", "remaining_time": "1:27:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 735, "total_steps": 1218, "loss": 0.7067, "learning_rate": 8.147590182017271e-06, "epoch": 1.8103448275862069, "percentage": 60.34, "elapsed_time": "2:12:34", "remaining_time": "1:27:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 736, "total_steps": 1218, "loss": 0.7683, "learning_rate": 8.119429751192972e-06, "epoch": 1.812807881773399, "percentage": 60.43, "elapsed_time": "2:12:44", "remaining_time": "1:26:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 737, "total_steps": 1218, "loss": 0.787, "learning_rate": 8.091284771770995e-06, "epoch": 1.8152709359605912, "percentage": 60.51, "elapsed_time": "2:12:57", "remaining_time": "1:26:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 738, "total_steps": 1218, "loss": 0.8227, "learning_rate": 8.063155475000037e-06, "epoch": 1.8177339901477834, "percentage": 60.59, "elapsed_time": "2:13:08", "remaining_time": "1:26:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 739, "total_steps": 1218, "loss": 0.8029, "learning_rate": 8.035042091999921e-06, "epoch": 1.8201970443349755, "percentage": 60.67, "elapsed_time": "2:13:18", "remaining_time": "1:26:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 740, "total_steps": 1218, "loss": 0.8681, "learning_rate": 8.006944853759732e-06, "epoch": 1.8226600985221675, "percentage": 60.76, "elapsed_time": "2:13:29", "remaining_time": "1:26:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 741, "total_steps": 1218, "loss": 0.679, "learning_rate": 7.978863991135894e-06, "epoch": 1.8251231527093597, "percentage": 60.84, "elapsed_time": "2:13:40", "remaining_time": "1:26:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 742, "total_steps": 1218, "loss": 0.7532, "learning_rate": 7.950799734850292e-06, "epoch": 1.8275862068965516, "percentage": 60.92, "elapsed_time": "2:13:50", "remaining_time": "1:25:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 743, "total_steps": 1218, "loss": 0.7974, "learning_rate": 7.922752315488367e-06, "epoch": 1.8300492610837438, "percentage": 61.0, "elapsed_time": "2:13:59", "remaining_time": "1:25:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 744, "total_steps": 1218, "loss": 0.8542, "learning_rate": 7.894721963497214e-06, "epoch": 1.832512315270936, "percentage": 61.08, "elapsed_time": "2:14:10", "remaining_time": "1:25:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 745, "total_steps": 1218, "loss": 0.8112, "learning_rate": 7.866708909183702e-06, "epoch": 1.8349753694581281, "percentage": 61.17, "elapsed_time": "2:14:20", "remaining_time": "1:25:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 746, "total_steps": 1218, "loss": 0.7813, "learning_rate": 7.838713382712583e-06, "epoch": 1.8374384236453203, "percentage": 61.25, "elapsed_time": "2:14:31", "remaining_time": "1:25:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 747, "total_steps": 1218, "loss": 0.8036, "learning_rate": 7.810735614104581e-06, "epoch": 1.8399014778325125, "percentage": 61.33, "elapsed_time": "2:14:41", "remaining_time": "1:24:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 748, "total_steps": 1218, "loss": 0.7841, "learning_rate": 7.782775833234522e-06, "epoch": 1.8423645320197044, "percentage": 61.41, "elapsed_time": "2:14:51", "remaining_time": "1:24:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 749, "total_steps": 1218, "loss": 0.7876, "learning_rate": 7.754834269829447e-06, "epoch": 1.8448275862068966, "percentage": 61.49, "elapsed_time": "2:15:02", "remaining_time": "1:24:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 750, "total_steps": 1218, "loss": 0.7662, "learning_rate": 7.726911153466699e-06, "epoch": 1.8472906403940885, "percentage": 61.58, "elapsed_time": "2:15:12", "remaining_time": "1:24:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 751, "total_steps": 1218, "loss": 0.7129, "learning_rate": 7.699006713572068e-06, "epoch": 1.8497536945812807, "percentage": 61.66, "elapsed_time": "2:15:23", "remaining_time": "1:24:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 752, "total_steps": 1218, "loss": 0.8317, "learning_rate": 7.67112117941788e-06, "epoch": 1.8522167487684729, "percentage": 61.74, "elapsed_time": "2:15:33", "remaining_time": "1:24:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 753, "total_steps": 1218, "loss": 0.8999, "learning_rate": 7.643254780121137e-06, "epoch": 1.854679802955665, "percentage": 61.82, "elapsed_time": "2:15:44", "remaining_time": "1:23:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 754, "total_steps": 1218, "loss": 0.8214, "learning_rate": 7.615407744641618e-06, "epoch": 1.8571428571428572, "percentage": 61.9, "elapsed_time": "2:15:55", "remaining_time": "1:23:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 755, "total_steps": 1218, "loss": 0.7333, "learning_rate": 7.58758030178e-06, "epoch": 1.8596059113300494, "percentage": 61.99, "elapsed_time": "2:16:05", "remaining_time": "1:23:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 756, "total_steps": 1218, "loss": 0.8637, "learning_rate": 7.559772680175979e-06, "epoch": 1.8620689655172413, "percentage": 62.07, "elapsed_time": "2:16:17", "remaining_time": "1:23:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 757, "total_steps": 1218, "loss": 0.8286, "learning_rate": 7.531985108306401e-06, "epoch": 1.8645320197044335, "percentage": 62.15, "elapsed_time": "2:16:28", "remaining_time": "1:23:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 758, "total_steps": 1218, "loss": 0.7792, "learning_rate": 7.504217814483364e-06, "epoch": 1.8669950738916257, "percentage": 62.23, "elapsed_time": "2:16:38", "remaining_time": "1:22:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 759, "total_steps": 1218, "loss": 0.7377, "learning_rate": 7.476471026852368e-06, "epoch": 1.8694581280788176, "percentage": 62.32, "elapsed_time": "2:16:48", "remaining_time": "1:22:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 760, "total_steps": 1218, "loss": 0.8641, "learning_rate": 7.448744973390423e-06, "epoch": 1.8719211822660098, "percentage": 62.4, "elapsed_time": "2:17:00", "remaining_time": "1:22:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 761, "total_steps": 1218, "loss": 0.8076, "learning_rate": 7.42103988190417e-06, "epoch": 1.874384236453202, "percentage": 62.48, "elapsed_time": "2:17:10", "remaining_time": "1:22:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 762, "total_steps": 1218, "loss": 0.8, "learning_rate": 7.393355980028039e-06, "epoch": 1.8768472906403941, "percentage": 62.56, "elapsed_time": "2:17:20", "remaining_time": "1:22:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 763, "total_steps": 1218, "loss": 0.8062, "learning_rate": 7.365693495222333e-06, "epoch": 1.8793103448275863, "percentage": 62.64, "elapsed_time": "2:17:30", "remaining_time": "1:22:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 764, "total_steps": 1218, "loss": 0.8897, "learning_rate": 7.338052654771407e-06, "epoch": 1.8817733990147785, "percentage": 62.73, "elapsed_time": "2:17:40", "remaining_time": "1:21:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 765, "total_steps": 1218, "loss": 0.8515, "learning_rate": 7.310433685781777e-06, "epoch": 1.8842364532019704, "percentage": 62.81, "elapsed_time": "2:17:51", "remaining_time": "1:21:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 766, "total_steps": 1218, "loss": 0.7439, "learning_rate": 7.282836815180241e-06, "epoch": 1.8866995073891626, "percentage": 62.89, "elapsed_time": "2:18:03", "remaining_time": "1:21:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 767, "total_steps": 1218, "loss": 0.7721, "learning_rate": 7.25526226971204e-06, "epoch": 1.8891625615763545, "percentage": 62.97, "elapsed_time": "2:18:12", "remaining_time": "1:21:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 768, "total_steps": 1218, "loss": 0.7644, "learning_rate": 7.227710275938987e-06, "epoch": 1.8916256157635467, "percentage": 63.05, "elapsed_time": "2:18:23", "remaining_time": "1:21:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 769, "total_steps": 1218, "loss": 0.8303, "learning_rate": 7.200181060237591e-06, "epoch": 1.8940886699507389, "percentage": 63.14, "elapsed_time": "2:18:33", "remaining_time": "1:20:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 770, "total_steps": 1218, "loss": 0.8328, "learning_rate": 7.172674848797218e-06, "epoch": 1.896551724137931, "percentage": 63.22, "elapsed_time": "2:18:43", "remaining_time": "1:20:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 771, "total_steps": 1218, "loss": 0.9782, "learning_rate": 7.1451918676182265e-06, "epoch": 1.8990147783251232, "percentage": 63.3, "elapsed_time": "2:18:54", "remaining_time": "1:20:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 772, "total_steps": 1218, "loss": 0.8212, "learning_rate": 7.117732342510093e-06, "epoch": 1.9014778325123154, "percentage": 63.38, "elapsed_time": "2:19:04", "remaining_time": "1:20:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 773, "total_steps": 1218, "loss": 0.8024, "learning_rate": 7.090296499089586e-06, "epoch": 1.9039408866995073, "percentage": 63.46, "elapsed_time": "2:19:14", "remaining_time": "1:20:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 774, "total_steps": 1218, "loss": 0.8012, "learning_rate": 7.062884562778883e-06, "epoch": 1.9064039408866995, "percentage": 63.55, "elapsed_time": "2:19:25", "remaining_time": "1:19:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 775, "total_steps": 1218, "loss": 0.7983, "learning_rate": 7.035496758803744e-06, "epoch": 1.9088669950738915, "percentage": 63.63, "elapsed_time": "2:19:36", "remaining_time": "1:19:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 776, "total_steps": 1218, "loss": 0.7521, "learning_rate": 7.008133312191649e-06, "epoch": 1.9113300492610836, "percentage": 63.71, "elapsed_time": "2:19:49", "remaining_time": "1:19:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 777, "total_steps": 1218, "loss": 0.8037, "learning_rate": 6.980794447769945e-06, "epoch": 1.9137931034482758, "percentage": 63.79, "elapsed_time": "2:20:00", "remaining_time": "1:19:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 778, "total_steps": 1218, "loss": 0.7388, "learning_rate": 6.953480390164001e-06, "epoch": 1.916256157635468, "percentage": 63.88, "elapsed_time": "2:20:10", "remaining_time": "1:19:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 779, "total_steps": 1218, "loss": 0.7452, "learning_rate": 6.926191363795375e-06, "epoch": 1.9187192118226601, "percentage": 63.96, "elapsed_time": "2:20:20", "remaining_time": "1:19:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 780, "total_steps": 1218, "loss": 0.7688, "learning_rate": 6.898927592879945e-06, "epoch": 1.9211822660098523, "percentage": 64.04, "elapsed_time": "2:20:30", "remaining_time": "1:18:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 781, "total_steps": 1218, "loss": 0.8282, "learning_rate": 6.871689301426101e-06, "epoch": 1.9236453201970445, "percentage": 64.12, "elapsed_time": "2:20:41", "remaining_time": "1:18:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 782, "total_steps": 1218, "loss": 0.7317, "learning_rate": 6.844476713232863e-06, "epoch": 1.9261083743842364, "percentage": 64.2, "elapsed_time": "2:20:51", "remaining_time": "1:18:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 783, "total_steps": 1218, "loss": 0.7313, "learning_rate": 6.817290051888084e-06, "epoch": 1.9285714285714286, "percentage": 64.29, "elapsed_time": "2:21:05", "remaining_time": "1:18:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 784, "total_steps": 1218, "loss": 0.6905, "learning_rate": 6.790129540766581e-06, "epoch": 1.9310344827586206, "percentage": 64.37, "elapsed_time": "2:21:20", "remaining_time": "1:18:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 785, "total_steps": 1218, "loss": 0.8612, "learning_rate": 6.762995403028315e-06, "epoch": 1.9334975369458127, "percentage": 64.45, "elapsed_time": "2:21:30", "remaining_time": "1:18:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 786, "total_steps": 1218, "loss": 0.8631, "learning_rate": 6.735887861616555e-06, "epoch": 1.935960591133005, "percentage": 64.53, "elapsed_time": "2:21:41", "remaining_time": "1:17:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 787, "total_steps": 1218, "loss": 0.7995, "learning_rate": 6.708807139256053e-06, "epoch": 1.938423645320197, "percentage": 64.61, "elapsed_time": "2:21:51", "remaining_time": "1:17:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 788, "total_steps": 1218, "loss": 0.776, "learning_rate": 6.68175345845119e-06, "epoch": 1.9408866995073892, "percentage": 64.7, "elapsed_time": "2:22:02", "remaining_time": "1:17:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 789, "total_steps": 1218, "loss": 0.8262, "learning_rate": 6.654727041484174e-06, "epoch": 1.9433497536945814, "percentage": 64.78, "elapsed_time": "2:22:12", "remaining_time": "1:17:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 790, "total_steps": 1218, "loss": 0.7318, "learning_rate": 6.627728110413214e-06, "epoch": 1.9458128078817734, "percentage": 64.86, "elapsed_time": "2:22:24", "remaining_time": "1:17:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 791, "total_steps": 1218, "loss": 0.7791, "learning_rate": 6.600756887070661e-06, "epoch": 1.9482758620689655, "percentage": 64.94, "elapsed_time": "2:22:34", "remaining_time": "1:16:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 792, "total_steps": 1218, "loss": 0.7846, "learning_rate": 6.5738135930612355e-06, "epoch": 1.9507389162561575, "percentage": 65.02, "elapsed_time": "2:22:45", "remaining_time": "1:16:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 793, "total_steps": 1218, "loss": 0.7578, "learning_rate": 6.546898449760162e-06, "epoch": 1.9532019704433496, "percentage": 65.11, "elapsed_time": "2:22:57", "remaining_time": "1:16:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 794, "total_steps": 1218, "loss": 0.8526, "learning_rate": 6.520011678311382e-06, "epoch": 1.9556650246305418, "percentage": 65.19, "elapsed_time": "2:23:06", "remaining_time": "1:16:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 795, "total_steps": 1218, "loss": 0.7402, "learning_rate": 6.493153499625719e-06, "epoch": 1.958128078817734, "percentage": 65.27, "elapsed_time": "2:23:16", "remaining_time": "1:16:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 796, "total_steps": 1218, "loss": 0.8348, "learning_rate": 6.466324134379066e-06, "epoch": 1.9605911330049262, "percentage": 65.35, "elapsed_time": "2:23:27", "remaining_time": "1:16:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 797, "total_steps": 1218, "loss": 0.8478, "learning_rate": 6.4395238030105786e-06, "epoch": 1.9630541871921183, "percentage": 65.44, "elapsed_time": "2:23:37", "remaining_time": "1:15:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 798, "total_steps": 1218, "loss": 0.7572, "learning_rate": 6.412752725720864e-06, "epoch": 1.9655172413793105, "percentage": 65.52, "elapsed_time": "2:23:48", "remaining_time": "1:15:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 799, "total_steps": 1218, "loss": 0.8267, "learning_rate": 6.386011122470159e-06, "epoch": 1.9679802955665024, "percentage": 65.6, "elapsed_time": "2:23:58", "remaining_time": "1:15:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 800, "total_steps": 1218, "loss": 0.7496, "learning_rate": 6.359299212976535e-06, "epoch": 1.9704433497536946, "percentage": 65.68, "elapsed_time": "2:24:09", "remaining_time": "1:15:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 801, "total_steps": 1218, "loss": 0.8067, "learning_rate": 6.332617216714099e-06, "epoch": 1.9729064039408866, "percentage": 65.76, "elapsed_time": "2:24:20", "remaining_time": "1:15:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 802, "total_steps": 1218, "loss": 0.7763, "learning_rate": 6.305965352911162e-06, "epoch": 1.9753694581280787, "percentage": 65.85, "elapsed_time": "2:24:30", "remaining_time": "1:14:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 803, "total_steps": 1218, "loss": 0.7879, "learning_rate": 6.279343840548475e-06, "epoch": 1.977832512315271, "percentage": 65.93, "elapsed_time": "2:24:40", "remaining_time": "1:14:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 804, "total_steps": 1218, "loss": 0.7964, "learning_rate": 6.252752898357397e-06, "epoch": 1.980295566502463, "percentage": 66.01, "elapsed_time": "2:24:49", "remaining_time": "1:14:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 805, "total_steps": 1218, "loss": 0.7987, "learning_rate": 6.226192744818125e-06, "epoch": 1.9827586206896552, "percentage": 66.09, "elapsed_time": "2:25:00", "remaining_time": "1:14:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 806, "total_steps": 1218, "loss": 0.7586, "learning_rate": 6.1996635981578755e-06, "epoch": 1.9852216748768474, "percentage": 66.17, "elapsed_time": "2:25:11", "remaining_time": "1:14:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 807, "total_steps": 1218, "loss": 0.8053, "learning_rate": 6.173165676349103e-06, "epoch": 1.9876847290640394, "percentage": 66.26, "elapsed_time": "2:25:24", "remaining_time": "1:14:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 808, "total_steps": 1218, "loss": 0.8085, "learning_rate": 6.146699197107715e-06, "epoch": 1.9901477832512315, "percentage": 66.34, "elapsed_time": "2:25:35", "remaining_time": "1:13:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 809, "total_steps": 1218, "loss": 0.7358, "learning_rate": 6.1202643778912755e-06, "epoch": 1.9926108374384235, "percentage": 66.42, "elapsed_time": "2:25:44", "remaining_time": "1:13:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 810, "total_steps": 1218, "loss": 0.7534, "learning_rate": 6.093861435897208e-06, "epoch": 1.9950738916256157, "percentage": 66.5, "elapsed_time": "2:25:55", "remaining_time": "1:13:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 811, "total_steps": 1218, "loss": 0.835, "learning_rate": 6.067490588061034e-06, "epoch": 1.9975369458128078, "percentage": 66.58, "elapsed_time": "2:26:07", "remaining_time": "1:13:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 812, "total_steps": 1218, "loss": 0.7618, "learning_rate": 6.041152051054575e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:26:19", "remaining_time": "1:13:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 812, "total_steps": 1218, "eval_loss": 1.1783102750778198, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:26:20", "remaining_time": "1:13:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 813, "total_steps": 1218, "loss": 0.4776, "learning_rate": 6.014846041284168e-06, "epoch": 2.002463054187192, "percentage": 66.75, "elapsed_time": "2:26:33", "remaining_time": "1:13:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 814, "total_steps": 1218, "loss": 0.5285, "learning_rate": 5.988572774888913e-06, "epoch": 2.0049261083743843, "percentage": 66.83, "elapsed_time": "2:26:42", "remaining_time": "1:12:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 815, "total_steps": 1218, "loss": 0.5086, "learning_rate": 5.962332467738858e-06, "epoch": 2.0073891625615765, "percentage": 66.91, "elapsed_time": "2:26:53", "remaining_time": "1:12:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 816, "total_steps": 1218, "loss": 0.5012, "learning_rate": 5.936125335433265e-06, "epoch": 2.0098522167487687, "percentage": 67.0, "elapsed_time": "2:27:02", "remaining_time": "1:12:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 817, "total_steps": 1218, "loss": 0.5097, "learning_rate": 5.909951593298811e-06, "epoch": 2.0123152709359604, "percentage": 67.08, "elapsed_time": "2:27:12", "remaining_time": "1:12:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 818, "total_steps": 1218, "loss": 0.47, "learning_rate": 5.883811456387821e-06, "epoch": 2.0147783251231526, "percentage": 67.16, "elapsed_time": "2:27:23", "remaining_time": "1:12:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 819, "total_steps": 1218, "loss": 0.4102, "learning_rate": 5.857705139476525e-06, "epoch": 2.0172413793103448, "percentage": 67.24, "elapsed_time": "2:27:34", "remaining_time": "1:11:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 820, "total_steps": 1218, "loss": 0.5274, "learning_rate": 5.831632857063271e-06, "epoch": 2.019704433497537, "percentage": 67.32, "elapsed_time": "2:27:45", "remaining_time": "1:11:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 821, "total_steps": 1218, "loss": 0.4378, "learning_rate": 5.805594823366751e-06, "epoch": 2.022167487684729, "percentage": 67.41, "elapsed_time": "2:27:57", "remaining_time": "1:11:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 822, "total_steps": 1218, "loss": 0.4807, "learning_rate": 5.779591252324286e-06, "epoch": 2.0246305418719213, "percentage": 67.49, "elapsed_time": "2:28:09", "remaining_time": "1:11:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 823, "total_steps": 1218, "loss": 0.4289, "learning_rate": 5.753622357590021e-06, "epoch": 2.0270935960591134, "percentage": 67.57, "elapsed_time": "2:28:19", "remaining_time": "1:11:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 824, "total_steps": 1218, "loss": 0.4917, "learning_rate": 5.7276883525331915e-06, "epoch": 2.0295566502463056, "percentage": 67.65, "elapsed_time": "2:28:28", "remaining_time": "1:10:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 825, "total_steps": 1218, "loss": 0.4341, "learning_rate": 5.701789450236377e-06, "epoch": 2.0320197044334973, "percentage": 67.73, "elapsed_time": "2:28:41", "remaining_time": "1:10:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 826, "total_steps": 1218, "loss": 0.4152, "learning_rate": 5.675925863493721e-06, "epoch": 2.0344827586206895, "percentage": 67.82, "elapsed_time": "2:28:51", "remaining_time": "1:10:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 827, "total_steps": 1218, "loss": 0.4969, "learning_rate": 5.650097804809224e-06, "epoch": 2.0369458128078817, "percentage": 67.9, "elapsed_time": "2:29:02", "remaining_time": "1:10:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 828, "total_steps": 1218, "loss": 0.4731, "learning_rate": 5.6243054863949675e-06, "epoch": 2.039408866995074, "percentage": 67.98, "elapsed_time": "2:29:17", "remaining_time": "1:10:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 829, "total_steps": 1218, "loss": 0.4922, "learning_rate": 5.598549120169376e-06, "epoch": 2.041871921182266, "percentage": 68.06, "elapsed_time": "2:29:27", "remaining_time": "1:10:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 830, "total_steps": 1218, "loss": 0.478, "learning_rate": 5.5728289177554805e-06, "epoch": 2.044334975369458, "percentage": 68.14, "elapsed_time": "2:29:38", "remaining_time": "1:09:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 831, "total_steps": 1218, "loss": 0.4711, "learning_rate": 5.54714509047918e-06, "epoch": 2.0467980295566504, "percentage": 68.23, "elapsed_time": "2:29:57", "remaining_time": "1:09:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 832, "total_steps": 1218, "loss": 0.4489, "learning_rate": 5.521497849367501e-06, "epoch": 2.0492610837438425, "percentage": 68.31, "elapsed_time": "2:30:08", "remaining_time": "1:09:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 833, "total_steps": 1218, "loss": 0.4616, "learning_rate": 5.49588740514686e-06, "epoch": 2.0517241379310347, "percentage": 68.39, "elapsed_time": "2:30:21", "remaining_time": "1:09:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 834, "total_steps": 1218, "loss": 0.4909, "learning_rate": 5.4703139682413585e-06, "epoch": 2.0541871921182264, "percentage": 68.47, "elapsed_time": "2:30:31", "remaining_time": "1:09:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 835, "total_steps": 1218, "loss": 0.4631, "learning_rate": 5.444777748771006e-06, "epoch": 2.0566502463054186, "percentage": 68.56, "elapsed_time": "2:30:44", "remaining_time": "1:09:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 836, "total_steps": 1218, "loss": 0.4235, "learning_rate": 5.419278956550037e-06, "epoch": 2.0591133004926108, "percentage": 68.64, "elapsed_time": "2:30:53", "remaining_time": "1:08:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 837, "total_steps": 1218, "loss": 0.449, "learning_rate": 5.393817801085168e-06, "epoch": 2.061576354679803, "percentage": 68.72, "elapsed_time": "2:31:03", "remaining_time": "1:08:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 838, "total_steps": 1218, "loss": 0.4041, "learning_rate": 5.368394491573876e-06, "epoch": 2.064039408866995, "percentage": 68.8, "elapsed_time": "2:31:13", "remaining_time": "1:08:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 839, "total_steps": 1218, "loss": 0.4219, "learning_rate": 5.343009236902696e-06, "epoch": 2.0665024630541873, "percentage": 68.88, "elapsed_time": "2:31:24", "remaining_time": "1:08:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 840, "total_steps": 1218, "loss": 0.4486, "learning_rate": 5.31766224564547e-06, "epoch": 2.0689655172413794, "percentage": 68.97, "elapsed_time": "2:31:34", "remaining_time": "1:08:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 841, "total_steps": 1218, "loss": 0.4448, "learning_rate": 5.292353726061665e-06, "epoch": 2.0714285714285716, "percentage": 69.05, "elapsed_time": "2:31:45", "remaining_time": "1:08:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 842, "total_steps": 1218, "loss": 0.4167, "learning_rate": 5.267083886094668e-06, "epoch": 2.0738916256157633, "percentage": 69.13, "elapsed_time": "2:31:55", "remaining_time": "1:07:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 843, "total_steps": 1218, "loss": 0.4192, "learning_rate": 5.241852933370026e-06, "epoch": 2.0763546798029555, "percentage": 69.21, "elapsed_time": "2:32:07", "remaining_time": "1:07:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 844, "total_steps": 1218, "loss": 0.4773, "learning_rate": 5.216661075193814e-06, "epoch": 2.0788177339901477, "percentage": 69.29, "elapsed_time": "2:32:17", "remaining_time": "1:07:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 845, "total_steps": 1218, "loss": 0.4553, "learning_rate": 5.191508518550856e-06, "epoch": 2.08128078817734, "percentage": 69.38, "elapsed_time": "2:32:28", "remaining_time": "1:07:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 846, "total_steps": 1218, "loss": 0.4155, "learning_rate": 5.166395470103092e-06, "epoch": 2.083743842364532, "percentage": 69.46, "elapsed_time": "2:32:38", "remaining_time": "1:07:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 847, "total_steps": 1218, "loss": 0.424, "learning_rate": 5.141322136187837e-06, "epoch": 2.086206896551724, "percentage": 69.54, "elapsed_time": "2:32:48", "remaining_time": "1:06:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 848, "total_steps": 1218, "loss": 0.4565, "learning_rate": 5.116288722816087e-06, "epoch": 2.0886699507389164, "percentage": 69.62, "elapsed_time": "2:32:59", "remaining_time": "1:06:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 849, "total_steps": 1218, "loss": 0.4058, "learning_rate": 5.091295435670856e-06, "epoch": 2.0911330049261085, "percentage": 69.7, "elapsed_time": "2:33:08", "remaining_time": "1:06:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 850, "total_steps": 1218, "loss": 0.4387, "learning_rate": 5.06634248010546e-06, "epoch": 2.0935960591133007, "percentage": 69.79, "elapsed_time": "2:33:18", "remaining_time": "1:06:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 851, "total_steps": 1218, "loss": 0.3873, "learning_rate": 5.041430061141833e-06, "epoch": 2.0960591133004924, "percentage": 69.87, "elapsed_time": "2:33:27", "remaining_time": "1:06:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 852, "total_steps": 1218, "loss": 0.4427, "learning_rate": 5.016558383468851e-06, "epoch": 2.0985221674876846, "percentage": 69.95, "elapsed_time": "2:33:38", "remaining_time": "1:06:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 853, "total_steps": 1218, "loss": 0.4925, "learning_rate": 4.991727651440644e-06, "epoch": 2.100985221674877, "percentage": 70.03, "elapsed_time": "2:33:48", "remaining_time": "1:05:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 854, "total_steps": 1218, "loss": 0.4299, "learning_rate": 4.9669380690749215e-06, "epoch": 2.103448275862069, "percentage": 70.11, "elapsed_time": "2:33:58", "remaining_time": "1:05:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 855, "total_steps": 1218, "loss": 0.4626, "learning_rate": 4.942189840051288e-06, "epoch": 2.105911330049261, "percentage": 70.2, "elapsed_time": "2:34:08", "remaining_time": "1:05:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 856, "total_steps": 1218, "loss": 0.3961, "learning_rate": 4.91748316770958e-06, "epoch": 2.1083743842364533, "percentage": 70.28, "elapsed_time": "2:34:18", "remaining_time": "1:05:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 857, "total_steps": 1218, "loss": 0.3805, "learning_rate": 4.892818255048188e-06, "epoch": 2.1108374384236455, "percentage": 70.36, "elapsed_time": "2:34:29", "remaining_time": "1:05:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 858, "total_steps": 1218, "loss": 0.4653, "learning_rate": 4.868195304722391e-06, "epoch": 2.1133004926108376, "percentage": 70.44, "elapsed_time": "2:34:39", "remaining_time": "1:04:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 859, "total_steps": 1218, "loss": 0.453, "learning_rate": 4.843614519042693e-06, "epoch": 2.1157635467980294, "percentage": 70.53, "elapsed_time": "2:34:50", "remaining_time": "1:04:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 860, "total_steps": 1218, "loss": 0.4783, "learning_rate": 4.819076099973152e-06, "epoch": 2.1182266009852215, "percentage": 70.61, "elapsed_time": "2:34:59", "remaining_time": "1:04:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 861, "total_steps": 1218, "loss": 0.4386, "learning_rate": 4.794580249129745e-06, "epoch": 2.1206896551724137, "percentage": 70.69, "elapsed_time": "2:35:09", "remaining_time": "1:04:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 862, "total_steps": 1218, "loss": 0.4535, "learning_rate": 4.77012716777867e-06, "epoch": 2.123152709359606, "percentage": 70.77, "elapsed_time": "2:35:20", "remaining_time": "1:04:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 863, "total_steps": 1218, "loss": 0.4784, "learning_rate": 4.745717056834729e-06, "epoch": 2.125615763546798, "percentage": 70.85, "elapsed_time": "2:35:29", "remaining_time": "1:03:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 864, "total_steps": 1218, "loss": 0.4758, "learning_rate": 4.721350116859675e-06, "epoch": 2.12807881773399, "percentage": 70.94, "elapsed_time": "2:35:44", "remaining_time": "1:03:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 865, "total_steps": 1218, "loss": 0.3942, "learning_rate": 4.697026548060528e-06, "epoch": 2.1305418719211824, "percentage": 71.02, "elapsed_time": "2:35:54", "remaining_time": "1:03:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 866, "total_steps": 1218, "loss": 0.3992, "learning_rate": 4.672746550287985e-06, "epoch": 2.1330049261083746, "percentage": 71.1, "elapsed_time": "2:36:04", "remaining_time": "1:03:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 867, "total_steps": 1218, "loss": 0.4385, "learning_rate": 4.64851032303472e-06, "epoch": 2.1354679802955667, "percentage": 71.18, "elapsed_time": "2:36:14", "remaining_time": "1:03:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 868, "total_steps": 1218, "loss": 0.4356, "learning_rate": 4.6243180654337975e-06, "epoch": 2.1379310344827585, "percentage": 71.26, "elapsed_time": "2:36:26", "remaining_time": "1:03:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 869, "total_steps": 1218, "loss": 0.4192, "learning_rate": 4.600169976257003e-06, "epoch": 2.1403940886699506, "percentage": 71.35, "elapsed_time": "2:36:40", "remaining_time": "1:02:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 870, "total_steps": 1218, "loss": 0.4245, "learning_rate": 4.576066253913209e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "2:36:50", "remaining_time": "1:02:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 871, "total_steps": 1218, "loss": 0.4587, "learning_rate": 4.5520070964467736e-06, "epoch": 2.145320197044335, "percentage": 71.51, "elapsed_time": "2:37:01", "remaining_time": "1:02:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 872, "total_steps": 1218, "loss": 0.4481, "learning_rate": 4.527992701535884e-06, "epoch": 2.147783251231527, "percentage": 71.59, "elapsed_time": "2:37:11", "remaining_time": "1:02:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 873, "total_steps": 1218, "loss": 0.4682, "learning_rate": 4.504023266490945e-06, "epoch": 2.1502463054187193, "percentage": 71.67, "elapsed_time": "2:37:22", "remaining_time": "1:02:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 874, "total_steps": 1218, "loss": 0.4532, "learning_rate": 4.480098988252958e-06, "epoch": 2.1527093596059115, "percentage": 71.76, "elapsed_time": "2:37:31", "remaining_time": "1:02:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 875, "total_steps": 1218, "loss": 0.4634, "learning_rate": 4.456220063391895e-06, "epoch": 2.1551724137931036, "percentage": 71.84, "elapsed_time": "2:37:41", "remaining_time": "1:01:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 876, "total_steps": 1218, "loss": 0.4549, "learning_rate": 4.432386688105095e-06, "epoch": 2.1576354679802954, "percentage": 71.92, "elapsed_time": "2:37:51", "remaining_time": "1:01:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 877, "total_steps": 1218, "loss": 0.4421, "learning_rate": 4.4085990582156455e-06, "epoch": 2.1600985221674875, "percentage": 72.0, "elapsed_time": "2:38:00", "remaining_time": "1:01:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 878, "total_steps": 1218, "loss": 0.4011, "learning_rate": 4.384857369170772e-06, "epoch": 2.1625615763546797, "percentage": 72.09, "elapsed_time": "2:38:11", "remaining_time": "1:01:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 879, "total_steps": 1218, "loss": 0.4414, "learning_rate": 4.361161816040234e-06, "epoch": 2.165024630541872, "percentage": 72.17, "elapsed_time": "2:38:22", "remaining_time": "1:01:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 880, "total_steps": 1218, "loss": 0.4815, "learning_rate": 4.337512593514729e-06, "epoch": 2.167487684729064, "percentage": 72.25, "elapsed_time": "2:38:33", "remaining_time": "1:00:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 881, "total_steps": 1218, "loss": 0.4426, "learning_rate": 4.313909895904278e-06, "epoch": 2.1699507389162562, "percentage": 72.33, "elapsed_time": "2:38:42", "remaining_time": "1:00:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 882, "total_steps": 1218, "loss": 0.4536, "learning_rate": 4.290353917136639e-06, "epoch": 2.1724137931034484, "percentage": 72.41, "elapsed_time": "2:38:54", "remaining_time": "1:00:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 883, "total_steps": 1218, "loss": 0.4312, "learning_rate": 4.2668448507557256e-06, "epoch": 2.1748768472906406, "percentage": 72.5, "elapsed_time": "2:39:04", "remaining_time": "1:00:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 884, "total_steps": 1218, "loss": 0.4473, "learning_rate": 4.243382889919981e-06, "epoch": 2.1773399014778327, "percentage": 72.58, "elapsed_time": "2:39:14", "remaining_time": "1:00:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 885, "total_steps": 1218, "loss": 0.4038, "learning_rate": 4.219968227400826e-06, "epoch": 2.1798029556650245, "percentage": 72.66, "elapsed_time": "2:39:24", "remaining_time": "0:59:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 886, "total_steps": 1218, "loss": 0.3835, "learning_rate": 4.1966010555810696e-06, "epoch": 2.1822660098522166, "percentage": 72.74, "elapsed_time": "2:39:35", "remaining_time": "0:59:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 887, "total_steps": 1218, "loss": 0.4761, "learning_rate": 4.173281566453301e-06, "epoch": 2.184729064039409, "percentage": 72.82, "elapsed_time": "2:39:45", "remaining_time": "0:59:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 888, "total_steps": 1218, "loss": 0.4116, "learning_rate": 4.1500099516183555e-06, "epoch": 2.187192118226601, "percentage": 72.91, "elapsed_time": "2:39:56", "remaining_time": "0:59:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 889, "total_steps": 1218, "loss": 0.4547, "learning_rate": 4.126786402283692e-06, "epoch": 2.189655172413793, "percentage": 72.99, "elapsed_time": "2:40:08", "remaining_time": "0:59:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 890, "total_steps": 1218, "loss": 0.4199, "learning_rate": 4.1036111092618725e-06, "epoch": 2.1921182266009853, "percentage": 73.07, "elapsed_time": "2:40:18", "remaining_time": "0:59:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 891, "total_steps": 1218, "loss": 0.4075, "learning_rate": 4.080484262968955e-06, "epoch": 2.1945812807881775, "percentage": 73.15, "elapsed_time": "2:40:29", "remaining_time": "0:58:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 892, "total_steps": 1218, "loss": 0.4569, "learning_rate": 4.057406053422933e-06, "epoch": 2.1970443349753697, "percentage": 73.23, "elapsed_time": "2:40:39", "remaining_time": "0:58:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 893, "total_steps": 1218, "loss": 0.4554, "learning_rate": 4.0343766702422075e-06, "epoch": 2.1995073891625614, "percentage": 73.32, "elapsed_time": "2:40:49", "remaining_time": "0:58:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 894, "total_steps": 1218, "loss": 0.4341, "learning_rate": 4.011396302643989e-06, "epoch": 2.2019704433497536, "percentage": 73.4, "elapsed_time": "2:41:01", "remaining_time": "0:58:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 895, "total_steps": 1218, "loss": 0.4505, "learning_rate": 3.9884651394427635e-06, "epoch": 2.2044334975369457, "percentage": 73.48, "elapsed_time": "2:41:11", "remaining_time": "0:58:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 896, "total_steps": 1218, "loss": 0.4403, "learning_rate": 3.965583369048737e-06, "epoch": 2.206896551724138, "percentage": 73.56, "elapsed_time": "2:41:20", "remaining_time": "0:57:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 897, "total_steps": 1218, "loss": 0.4696, "learning_rate": 3.94275117946629e-06, "epoch": 2.20935960591133, "percentage": 73.65, "elapsed_time": "2:41:32", "remaining_time": "0:57:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 898, "total_steps": 1218, "loss": 0.4799, "learning_rate": 3.919968758292425e-06, "epoch": 2.2118226600985222, "percentage": 73.73, "elapsed_time": "2:41:42", "remaining_time": "0:57:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 899, "total_steps": 1218, "loss": 0.4113, "learning_rate": 3.897236292715235e-06, "epoch": 2.2142857142857144, "percentage": 73.81, "elapsed_time": "2:41:52", "remaining_time": "0:57:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 900, "total_steps": 1218, "loss": 0.3738, "learning_rate": 3.874553969512358e-06, "epoch": 2.2167487684729066, "percentage": 73.89, "elapsed_time": "2:42:01", "remaining_time": "0:57:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 901, "total_steps": 1218, "loss": 0.4744, "learning_rate": 3.851921975049448e-06, "epoch": 2.2192118226600988, "percentage": 73.97, "elapsed_time": "2:42:13", "remaining_time": "0:57:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 902, "total_steps": 1218, "loss": 0.4334, "learning_rate": 3.82934049527864e-06, "epoch": 2.2216748768472905, "percentage": 74.06, "elapsed_time": "2:42:22", "remaining_time": "0:56:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 903, "total_steps": 1218, "loss": 0.4198, "learning_rate": 3.8068097157370198e-06, "epoch": 2.2241379310344827, "percentage": 74.14, "elapsed_time": "2:42:32", "remaining_time": "0:56:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 904, "total_steps": 1218, "loss": 0.493, "learning_rate": 3.784329821545105e-06, "epoch": 2.226600985221675, "percentage": 74.22, "elapsed_time": "2:42:42", "remaining_time": "0:56:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 905, "total_steps": 1218, "loss": 0.4261, "learning_rate": 3.761900997405332e-06, "epoch": 2.229064039408867, "percentage": 74.3, "elapsed_time": "2:42:54", "remaining_time": "0:56:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 906, "total_steps": 1218, "loss": 0.4882, "learning_rate": 3.739523427600509e-06, "epoch": 2.231527093596059, "percentage": 74.38, "elapsed_time": "2:43:05", "remaining_time": "0:56:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 907, "total_steps": 1218, "loss": 0.389, "learning_rate": 3.7171972959923306e-06, "epoch": 2.2339901477832513, "percentage": 74.47, "elapsed_time": "2:43:15", "remaining_time": "0:55:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 908, "total_steps": 1218, "loss": 0.4413, "learning_rate": 3.6949227860198712e-06, "epoch": 2.2364532019704435, "percentage": 74.55, "elapsed_time": "2:43:24", "remaining_time": "0:55:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 909, "total_steps": 1218, "loss": 0.4373, "learning_rate": 3.672700080698035e-06, "epoch": 2.2389162561576357, "percentage": 74.63, "elapsed_time": "2:43:34", "remaining_time": "0:55:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 910, "total_steps": 1218, "loss": 0.4235, "learning_rate": 3.650529362616113e-06, "epoch": 2.2413793103448274, "percentage": 74.71, "elapsed_time": "2:43:45", "remaining_time": "0:55:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 911, "total_steps": 1218, "loss": 0.4315, "learning_rate": 3.628410813936224e-06, "epoch": 2.2438423645320196, "percentage": 74.79, "elapsed_time": "2:43:56", "remaining_time": "0:55:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 912, "total_steps": 1218, "loss": 0.4366, "learning_rate": 3.606344616391867e-06, "epoch": 2.2463054187192117, "percentage": 74.88, "elapsed_time": "2:44:06", "remaining_time": "0:55:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 913, "total_steps": 1218, "loss": 0.3895, "learning_rate": 3.584330951286398e-06, "epoch": 2.248768472906404, "percentage": 74.96, "elapsed_time": "2:44:15", "remaining_time": "0:54:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 914, "total_steps": 1218, "loss": 0.3745, "learning_rate": 3.5623699994915363e-06, "epoch": 2.251231527093596, "percentage": 75.04, "elapsed_time": "2:44:28", "remaining_time": "0:54:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 915, "total_steps": 1218, "loss": 0.4634, "learning_rate": 3.540461941445915e-06, "epoch": 2.2536945812807883, "percentage": 75.12, "elapsed_time": "2:44:38", "remaining_time": "0:54:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 916, "total_steps": 1218, "loss": 0.4446, "learning_rate": 3.5186069571535575e-06, "epoch": 2.2561576354679804, "percentage": 75.21, "elapsed_time": "2:44:48", "remaining_time": "0:54:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 917, "total_steps": 1218, "loss": 0.424, "learning_rate": 3.4968052261824194e-06, "epoch": 2.2586206896551726, "percentage": 75.29, "elapsed_time": "2:44:58", "remaining_time": "0:54:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 918, "total_steps": 1218, "loss": 0.4747, "learning_rate": 3.475056927662912e-06, "epoch": 2.2610837438423648, "percentage": 75.37, "elapsed_time": "2:45:08", "remaining_time": "0:53:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 919, "total_steps": 1218, "loss": 0.428, "learning_rate": 3.453362240286414e-06, "epoch": 2.2635467980295565, "percentage": 75.45, "elapsed_time": "2:45:19", "remaining_time": "0:53:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 920, "total_steps": 1218, "loss": 0.5345, "learning_rate": 3.4317213423038386e-06, "epoch": 2.2660098522167487, "percentage": 75.53, "elapsed_time": "2:45:30", "remaining_time": "0:53:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 921, "total_steps": 1218, "loss": 0.4026, "learning_rate": 3.410134411524133e-06, "epoch": 2.268472906403941, "percentage": 75.62, "elapsed_time": "2:45:40", "remaining_time": "0:53:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 922, "total_steps": 1218, "loss": 0.5103, "learning_rate": 3.388601625312833e-06, "epoch": 2.270935960591133, "percentage": 75.7, "elapsed_time": "2:45:51", "remaining_time": "0:53:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 923, "total_steps": 1218, "loss": 0.436, "learning_rate": 3.3671231605906052e-06, "epoch": 2.273399014778325, "percentage": 75.78, "elapsed_time": "2:46:01", "remaining_time": "0:53:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 924, "total_steps": 1218, "loss": 0.4255, "learning_rate": 3.345699193831795e-06, "epoch": 2.2758620689655173, "percentage": 75.86, "elapsed_time": "2:46:12", "remaining_time": "0:52:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 925, "total_steps": 1218, "loss": 0.4303, "learning_rate": 3.3243299010629706e-06, "epoch": 2.2783251231527095, "percentage": 75.94, "elapsed_time": "2:46:23", "remaining_time": "0:52:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 926, "total_steps": 1218, "loss": 0.47, "learning_rate": 3.3030154578614783e-06, "epoch": 2.2807881773399012, "percentage": 76.03, "elapsed_time": "2:46:33", "remaining_time": "0:52:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 927, "total_steps": 1218, "loss": 0.4362, "learning_rate": 3.281756039354016e-06, "epoch": 2.2832512315270934, "percentage": 76.11, "elapsed_time": "2:46:44", "remaining_time": "0:52:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 928, "total_steps": 1218, "loss": 0.4473, "learning_rate": 3.2605518202151577e-06, "epoch": 2.2857142857142856, "percentage": 76.19, "elapsed_time": "2:46:53", "remaining_time": "0:52:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 929, "total_steps": 1218, "loss": 0.4715, "learning_rate": 3.239402974665956e-06, "epoch": 2.2881773399014778, "percentage": 76.27, "elapsed_time": "2:47:04", "remaining_time": "0:51:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 930, "total_steps": 1218, "loss": 0.4558, "learning_rate": 3.218309676472492e-06, "epoch": 2.29064039408867, "percentage": 76.35, "elapsed_time": "2:47:14", "remaining_time": "0:51:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 931, "total_steps": 1218, "loss": 0.3997, "learning_rate": 3.1972720989444473e-06, "epoch": 2.293103448275862, "percentage": 76.44, "elapsed_time": "2:47:26", "remaining_time": "0:51:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 932, "total_steps": 1218, "loss": 0.4496, "learning_rate": 3.1762904149336947e-06, "epoch": 2.2955665024630543, "percentage": 76.52, "elapsed_time": "2:47:36", "remaining_time": "0:51:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 933, "total_steps": 1218, "loss": 0.3912, "learning_rate": 3.155364796832848e-06, "epoch": 2.2980295566502464, "percentage": 76.6, "elapsed_time": "2:47:47", "remaining_time": "0:51:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 934, "total_steps": 1218, "loss": 0.4628, "learning_rate": 3.134495416573884e-06, "epoch": 2.3004926108374386, "percentage": 76.68, "elapsed_time": "2:47:58", "remaining_time": "0:51:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 935, "total_steps": 1218, "loss": 0.4348, "learning_rate": 3.113682445626701e-06, "epoch": 2.302955665024631, "percentage": 76.77, "elapsed_time": "2:48:07", "remaining_time": "0:50:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 936, "total_steps": 1218, "loss": 0.4316, "learning_rate": 3.0929260549977116e-06, "epoch": 2.3054187192118225, "percentage": 76.85, "elapsed_time": "2:48:17", "remaining_time": "0:50:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 937, "total_steps": 1218, "loss": 0.4577, "learning_rate": 3.072226415228463e-06, "epoch": 2.3078817733990147, "percentage": 76.93, "elapsed_time": "2:48:29", "remaining_time": "0:50:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 938, "total_steps": 1218, "loss": 0.4152, "learning_rate": 3.0515836963942056e-06, "epoch": 2.310344827586207, "percentage": 77.01, "elapsed_time": "2:48:39", "remaining_time": "0:50:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 939, "total_steps": 1218, "loss": 0.5112, "learning_rate": 3.030998068102512e-06, "epoch": 2.312807881773399, "percentage": 77.09, "elapsed_time": "2:48:49", "remaining_time": "0:50:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 940, "total_steps": 1218, "loss": 0.4346, "learning_rate": 3.01046969949188e-06, "epoch": 2.315270935960591, "percentage": 77.18, "elapsed_time": "2:48:59", "remaining_time": "0:49:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 941, "total_steps": 1218, "loss": 0.4312, "learning_rate": 2.989998759230335e-06, "epoch": 2.3177339901477834, "percentage": 77.26, "elapsed_time": "2:49:10", "remaining_time": "0:49:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 942, "total_steps": 1218, "loss": 0.4377, "learning_rate": 2.9695854155140648e-06, "epoch": 2.3201970443349755, "percentage": 77.34, "elapsed_time": "2:49:22", "remaining_time": "0:49:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 943, "total_steps": 1218, "loss": 0.418, "learning_rate": 2.9492298360660164e-06, "epoch": 2.3226600985221673, "percentage": 77.42, "elapsed_time": "2:49:32", "remaining_time": "0:49:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 944, "total_steps": 1218, "loss": 0.4423, "learning_rate": 2.9289321881345257e-06, "epoch": 2.3251231527093594, "percentage": 77.5, "elapsed_time": "2:49:44", "remaining_time": "0:49:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 945, "total_steps": 1218, "loss": 0.433, "learning_rate": 2.9086926384919457e-06, "epoch": 2.3275862068965516, "percentage": 77.59, "elapsed_time": "2:49:55", "remaining_time": "0:49:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 946, "total_steps": 1218, "loss": 0.3646, "learning_rate": 2.8885113534332742e-06, "epoch": 2.3300492610837438, "percentage": 77.67, "elapsed_time": "2:50:05", "remaining_time": "0:48:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 947, "total_steps": 1218, "loss": 0.4518, "learning_rate": 2.868388498774787e-06, "epoch": 2.332512315270936, "percentage": 77.75, "elapsed_time": "2:50:15", "remaining_time": "0:48:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 948, "total_steps": 1218, "loss": 0.444, "learning_rate": 2.8483242398526723e-06, "epoch": 2.334975369458128, "percentage": 77.83, "elapsed_time": "2:50:26", "remaining_time": "0:48:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 949, "total_steps": 1218, "loss": 0.4333, "learning_rate": 2.8283187415216882e-06, "epoch": 2.3374384236453203, "percentage": 77.91, "elapsed_time": "2:50:37", "remaining_time": "0:48:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 950, "total_steps": 1218, "loss": 0.5254, "learning_rate": 2.80837216815378e-06, "epoch": 2.3399014778325125, "percentage": 78.0, "elapsed_time": "2:50:47", "remaining_time": "0:48:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 951, "total_steps": 1218, "loss": 0.4129, "learning_rate": 2.788484683636753e-06, "epoch": 2.3423645320197046, "percentage": 78.08, "elapsed_time": "2:50:56", "remaining_time": "0:47:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 952, "total_steps": 1218, "loss": 0.4638, "learning_rate": 2.7686564513729198e-06, "epoch": 2.344827586206897, "percentage": 78.16, "elapsed_time": "2:51:07", "remaining_time": "0:47:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 953, "total_steps": 1218, "loss": 0.449, "learning_rate": 2.7488876342777505e-06, "epoch": 2.3472906403940885, "percentage": 78.24, "elapsed_time": "2:51:17", "remaining_time": "0:47:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 954, "total_steps": 1218, "loss": 0.4624, "learning_rate": 2.7291783947785544e-06, "epoch": 2.3497536945812807, "percentage": 78.33, "elapsed_time": "2:51:29", "remaining_time": "0:47:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 955, "total_steps": 1218, "loss": 0.4315, "learning_rate": 2.7095288948131114e-06, "epoch": 2.352216748768473, "percentage": 78.41, "elapsed_time": "2:51:38", "remaining_time": "0:47:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 956, "total_steps": 1218, "loss": 0.417, "learning_rate": 2.689939295828371e-06, "epoch": 2.354679802955665, "percentage": 78.49, "elapsed_time": "2:51:50", "remaining_time": "0:47:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 957, "total_steps": 1218, "loss": 0.4108, "learning_rate": 2.6704097587791245e-06, "epoch": 2.357142857142857, "percentage": 78.57, "elapsed_time": "2:52:00", "remaining_time": "0:46:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 958, "total_steps": 1218, "loss": 0.4266, "learning_rate": 2.650940444126654e-06, "epoch": 2.3596059113300494, "percentage": 78.65, "elapsed_time": "2:52:09", "remaining_time": "0:46:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 959, "total_steps": 1218, "loss": 0.4102, "learning_rate": 2.6315315118374528e-06, "epoch": 2.3620689655172415, "percentage": 78.74, "elapsed_time": "2:52:20", "remaining_time": "0:46:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 960, "total_steps": 1218, "loss": 0.4094, "learning_rate": 2.6121831213818825e-06, "epoch": 2.3645320197044333, "percentage": 78.82, "elapsed_time": "2:52:30", "remaining_time": "0:46:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 961, "total_steps": 1218, "loss": 0.4476, "learning_rate": 2.5928954317328735e-06, "epoch": 2.3669950738916254, "percentage": 78.9, "elapsed_time": "2:52:41", "remaining_time": "0:46:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 962, "total_steps": 1218, "loss": 0.4543, "learning_rate": 2.5736686013646226e-06, "epoch": 2.3694581280788176, "percentage": 78.98, "elapsed_time": "2:52:51", "remaining_time": "0:46:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 963, "total_steps": 1218, "loss": 0.4183, "learning_rate": 2.5545027882512742e-06, "epoch": 2.37192118226601, "percentage": 79.06, "elapsed_time": "2:53:03", "remaining_time": "0:45:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 964, "total_steps": 1218, "loss": 0.4184, "learning_rate": 2.535398149865651e-06, "epoch": 2.374384236453202, "percentage": 79.15, "elapsed_time": "2:53:13", "remaining_time": "0:45:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 965, "total_steps": 1218, "loss": 0.4735, "learning_rate": 2.5163548431779306e-06, "epoch": 2.376847290640394, "percentage": 79.23, "elapsed_time": "2:53:23", "remaining_time": "0:45:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 966, "total_steps": 1218, "loss": 0.5079, "learning_rate": 2.4973730246543736e-06, "epoch": 2.3793103448275863, "percentage": 79.31, "elapsed_time": "2:53:33", "remaining_time": "0:45:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 967, "total_steps": 1218, "loss": 0.524, "learning_rate": 2.4784528502560334e-06, "epoch": 2.3817733990147785, "percentage": 79.39, "elapsed_time": "2:53:47", "remaining_time": "0:45:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 968, "total_steps": 1218, "loss": 0.4884, "learning_rate": 2.4595944754374723e-06, "epoch": 2.3842364532019706, "percentage": 79.47, "elapsed_time": "2:53:57", "remaining_time": "0:44:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 969, "total_steps": 1218, "loss": 0.427, "learning_rate": 2.440798055145487e-06, "epoch": 2.386699507389163, "percentage": 79.56, "elapsed_time": "2:54:09", "remaining_time": "0:44:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 970, "total_steps": 1218, "loss": 0.4765, "learning_rate": 2.422063743817832e-06, "epoch": 2.3891625615763545, "percentage": 79.64, "elapsed_time": "2:54:20", "remaining_time": "0:44:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 971, "total_steps": 1218, "loss": 0.4608, "learning_rate": 2.403391695381966e-06, "epoch": 2.3916256157635467, "percentage": 79.72, "elapsed_time": "2:54:31", "remaining_time": "0:44:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 972, "total_steps": 1218, "loss": 0.426, "learning_rate": 2.3847820632537565e-06, "epoch": 2.394088669950739, "percentage": 79.8, "elapsed_time": "2:54:42", "remaining_time": "0:44:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 973, "total_steps": 1218, "loss": 0.4371, "learning_rate": 2.36623500033625e-06, "epoch": 2.396551724137931, "percentage": 79.89, "elapsed_time": "2:54:53", "remaining_time": "0:44:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 974, "total_steps": 1218, "loss": 0.437, "learning_rate": 2.347750659018397e-06, "epoch": 2.399014778325123, "percentage": 79.97, "elapsed_time": "2:55:04", "remaining_time": "0:43:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 975, "total_steps": 1218, "loss": 0.3933, "learning_rate": 2.329329191173808e-06, "epoch": 2.4014778325123154, "percentage": 80.05, "elapsed_time": "2:55:14", "remaining_time": "0:43:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 976, "total_steps": 1218, "loss": 0.4169, "learning_rate": 2.3109707481595113e-06, "epoch": 2.4039408866995076, "percentage": 80.13, "elapsed_time": "2:55:28", "remaining_time": "0:43:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 977, "total_steps": 1218, "loss": 0.3997, "learning_rate": 2.2926754808146865e-06, "epoch": 2.4064039408866993, "percentage": 80.21, "elapsed_time": "2:55:37", "remaining_time": "0:43:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 978, "total_steps": 1218, "loss": 0.476, "learning_rate": 2.27444353945945e-06, "epoch": 2.4088669950738915, "percentage": 80.3, "elapsed_time": "2:55:47", "remaining_time": "0:43:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 979, "total_steps": 1218, "loss": 0.4577, "learning_rate": 2.2562750738936155e-06, "epoch": 2.4113300492610836, "percentage": 80.38, "elapsed_time": "2:55:58", "remaining_time": "0:42:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 980, "total_steps": 1218, "loss": 0.4663, "learning_rate": 2.2381702333954436e-06, "epoch": 2.413793103448276, "percentage": 80.46, "elapsed_time": "2:56:08", "remaining_time": "0:42:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 981, "total_steps": 1218, "loss": 0.4068, "learning_rate": 2.2201291667204463e-06, "epoch": 2.416256157635468, "percentage": 80.54, "elapsed_time": "2:56:20", "remaining_time": "0:42:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 982, "total_steps": 1218, "loss": 0.4121, "learning_rate": 2.2021520221001304e-06, "epoch": 2.41871921182266, "percentage": 80.62, "elapsed_time": "2:56:32", "remaining_time": "0:42:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 983, "total_steps": 1218, "loss": 0.4159, "learning_rate": 2.1842389472408133e-06, "epoch": 2.4211822660098523, "percentage": 80.71, "elapsed_time": "2:56:42", "remaining_time": "0:42:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 984, "total_steps": 1218, "loss": 0.4554, "learning_rate": 2.16639008932239e-06, "epoch": 2.4236453201970445, "percentage": 80.79, "elapsed_time": "2:56:52", "remaining_time": "0:42:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 985, "total_steps": 1218, "loss": 0.4607, "learning_rate": 2.148605594997115e-06, "epoch": 2.4261083743842367, "percentage": 80.87, "elapsed_time": "2:57:02", "remaining_time": "0:41:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 986, "total_steps": 1218, "loss": 0.4611, "learning_rate": 2.130885610388428e-06, "epoch": 2.4285714285714284, "percentage": 80.95, "elapsed_time": "2:57:12", "remaining_time": "0:41:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 987, "total_steps": 1218, "loss": 0.5082, "learning_rate": 2.113230281089722e-06, "epoch": 2.4310344827586206, "percentage": 81.03, "elapsed_time": "2:57:23", "remaining_time": "0:41:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 988, "total_steps": 1218, "loss": 0.3851, "learning_rate": 2.0956397521631666e-06, "epoch": 2.4334975369458127, "percentage": 81.12, "elapsed_time": "2:57:33", "remaining_time": "0:41:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 989, "total_steps": 1218, "loss": 0.4593, "learning_rate": 2.0781141681385053e-06, "epoch": 2.435960591133005, "percentage": 81.2, "elapsed_time": "2:57:45", "remaining_time": "0:41:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 990, "total_steps": 1218, "loss": 0.4188, "learning_rate": 2.0606536730118767e-06, "epoch": 2.438423645320197, "percentage": 81.28, "elapsed_time": "2:57:55", "remaining_time": "0:40:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 991, "total_steps": 1218, "loss": 0.4046, "learning_rate": 2.043258410244622e-06, "epoch": 2.4408866995073892, "percentage": 81.36, "elapsed_time": "2:58:06", "remaining_time": "0:40:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 992, "total_steps": 1218, "loss": 0.3752, "learning_rate": 2.0259285227621152e-06, "epoch": 2.4433497536945814, "percentage": 81.44, "elapsed_time": "2:58:16", "remaining_time": "0:40:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 993, "total_steps": 1218, "loss": 0.4352, "learning_rate": 2.008664152952583e-06, "epoch": 2.4458128078817736, "percentage": 81.53, "elapsed_time": "2:58:25", "remaining_time": "0:40:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 994, "total_steps": 1218, "loss": 0.5227, "learning_rate": 1.9914654426659374e-06, "epoch": 2.4482758620689653, "percentage": 81.61, "elapsed_time": "2:58:35", "remaining_time": "0:40:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 995, "total_steps": 1218, "loss": 0.4376, "learning_rate": 1.974332533212611e-06, "epoch": 2.4507389162561575, "percentage": 81.69, "elapsed_time": "2:58:48", "remaining_time": "0:40:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 996, "total_steps": 1218, "loss": 0.3917, "learning_rate": 1.9572655653623884e-06, "epoch": 2.4532019704433496, "percentage": 81.77, "elapsed_time": "2:59:02", "remaining_time": "0:39:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 997, "total_steps": 1218, "loss": 0.4496, "learning_rate": 1.9402646793432624e-06, "epoch": 2.455665024630542, "percentage": 81.86, "elapsed_time": "2:59:13", "remaining_time": "0:39:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 998, "total_steps": 1218, "loss": 0.4432, "learning_rate": 1.9233300148402767e-06, "epoch": 2.458128078817734, "percentage": 81.94, "elapsed_time": "2:59:23", "remaining_time": "0:39:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 999, "total_steps": 1218, "loss": 0.4588, "learning_rate": 1.9064617109943662e-06, "epoch": 2.460591133004926, "percentage": 82.02, "elapsed_time": "2:59:33", "remaining_time": "0:39:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1000, "total_steps": 1218, "loss": 0.4167, "learning_rate": 1.88965990640123e-06, "epoch": 2.4630541871921183, "percentage": 82.1, "elapsed_time": "2:59:44", "remaining_time": "0:39:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1001, "total_steps": 1218, "loss": 0.4513, "learning_rate": 1.8729247391101958e-06, "epoch": 2.4655172413793105, "percentage": 82.18, "elapsed_time": "2:59:54", "remaining_time": "0:39:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1002, "total_steps": 1218, "loss": 0.4873, "learning_rate": 1.8562563466230577e-06, "epoch": 2.4679802955665027, "percentage": 82.27, "elapsed_time": "3:00:08", "remaining_time": "0:38:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1003, "total_steps": 1218, "loss": 0.4649, "learning_rate": 1.8396548658929858e-06, "epoch": 2.4704433497536944, "percentage": 82.35, "elapsed_time": "3:00:19", "remaining_time": "0:38:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1004, "total_steps": 1218, "loss": 0.464, "learning_rate": 1.823120433323361e-06, "epoch": 2.4729064039408866, "percentage": 82.43, "elapsed_time": "3:00:30", "remaining_time": "0:38:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1005, "total_steps": 1218, "loss": 0.4926, "learning_rate": 1.8066531847666891e-06, "epoch": 2.4753694581280787, "percentage": 82.51, "elapsed_time": "3:00:40", "remaining_time": "0:38:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1006, "total_steps": 1218, "loss": 0.3811, "learning_rate": 1.7902532555234653e-06, "epoch": 2.477832512315271, "percentage": 82.59, "elapsed_time": "3:00:51", "remaining_time": "0:38:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1007, "total_steps": 1218, "loss": 0.461, "learning_rate": 1.7739207803410575e-06, "epoch": 2.480295566502463, "percentage": 82.68, "elapsed_time": "3:01:01", "remaining_time": "0:37:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1008, "total_steps": 1218, "loss": 0.4722, "learning_rate": 1.757655893412622e-06, "epoch": 2.4827586206896552, "percentage": 82.76, "elapsed_time": "3:01:13", "remaining_time": "0:37:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1009, "total_steps": 1218, "loss": 0.4164, "learning_rate": 1.7414587283759776e-06, "epoch": 2.4852216748768474, "percentage": 82.84, "elapsed_time": "3:01:23", "remaining_time": "0:37:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1010, "total_steps": 1218, "loss": 0.3919, "learning_rate": 1.7253294183125223e-06, "epoch": 2.4876847290640396, "percentage": 82.92, "elapsed_time": "3:01:33", "remaining_time": "0:37:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1011, "total_steps": 1218, "loss": 0.4028, "learning_rate": 1.7092680957461294e-06, "epoch": 2.4901477832512313, "percentage": 83.0, "elapsed_time": "3:01:43", "remaining_time": "0:37:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1012, "total_steps": 1218, "loss": 0.3992, "learning_rate": 1.6932748926420695e-06, "epoch": 2.4926108374384235, "percentage": 83.09, "elapsed_time": "3:01:53", "remaining_time": "0:37:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1013, "total_steps": 1218, "loss": 0.4728, "learning_rate": 1.6773499404059157e-06, "epoch": 2.4950738916256157, "percentage": 83.17, "elapsed_time": "3:02:03", "remaining_time": "0:36:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1014, "total_steps": 1218, "loss": 0.4247, "learning_rate": 1.661493369882473e-06, "epoch": 2.497536945812808, "percentage": 83.25, "elapsed_time": "3:02:13", "remaining_time": "0:36:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1015, "total_steps": 1218, "loss": 0.4547, "learning_rate": 1.6457053113546972e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "3:02:22", "remaining_time": "0:36:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1016, "total_steps": 1218, "loss": 0.4518, "learning_rate": 1.6299858945426251e-06, "epoch": 2.502463054187192, "percentage": 83.42, "elapsed_time": "3:02:32", "remaining_time": "0:36:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1017, "total_steps": 1218, "loss": 0.402, "learning_rate": 1.6143352486023113e-06, "epoch": 2.5049261083743843, "percentage": 83.5, "elapsed_time": "3:02:44", "remaining_time": "0:36:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1018, "total_steps": 1218, "loss": 0.4676, "learning_rate": 1.5987535021247668e-06, "epoch": 2.5073891625615765, "percentage": 83.58, "elapsed_time": "3:02:54", "remaining_time": "0:35:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1019, "total_steps": 1218, "loss": 0.4373, "learning_rate": 1.583240783134896e-06, "epoch": 2.5098522167487687, "percentage": 83.66, "elapsed_time": "3:03:06", "remaining_time": "0:35:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1020, "total_steps": 1218, "loss": 0.4437, "learning_rate": 1.5677972190904623e-06, "epoch": 2.512315270935961, "percentage": 83.74, "elapsed_time": "3:03:18", "remaining_time": "0:35:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1021, "total_steps": 1218, "loss": 0.4564, "learning_rate": 1.5524229368810129e-06, "epoch": 2.5147783251231526, "percentage": 83.83, "elapsed_time": "3:03:29", "remaining_time": "0:35:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1022, "total_steps": 1218, "loss": 0.3984, "learning_rate": 1.537118062826859e-06, "epoch": 2.5172413793103448, "percentage": 83.91, "elapsed_time": "3:03:38", "remaining_time": "0:35:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1023, "total_steps": 1218, "loss": 0.4528, "learning_rate": 1.5218827226780397e-06, "epoch": 2.519704433497537, "percentage": 83.99, "elapsed_time": "3:03:51", "remaining_time": "0:35:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1024, "total_steps": 1218, "loss": 0.4476, "learning_rate": 1.5067170416132603e-06, "epoch": 2.522167487684729, "percentage": 84.07, "elapsed_time": "3:04:05", "remaining_time": "0:34:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1025, "total_steps": 1218, "loss": 0.4145, "learning_rate": 1.491621144238905e-06, "epoch": 2.5246305418719213, "percentage": 84.15, "elapsed_time": "3:04:14", "remaining_time": "0:34:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1026, "total_steps": 1218, "loss": 0.502, "learning_rate": 1.4765951545879732e-06, "epoch": 2.5270935960591134, "percentage": 84.24, "elapsed_time": "3:04:25", "remaining_time": "0:34:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1027, "total_steps": 1218, "loss": 0.4445, "learning_rate": 1.4616391961190924e-06, "epoch": 2.529556650246305, "percentage": 84.32, "elapsed_time": "3:04:35", "remaining_time": "0:34:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1028, "total_steps": 1218, "loss": 0.3828, "learning_rate": 1.4467533917154842e-06, "epoch": 2.5320197044334973, "percentage": 84.4, "elapsed_time": "3:04:46", "remaining_time": "0:34:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1029, "total_steps": 1218, "loss": 0.4262, "learning_rate": 1.4319378636839554e-06, "epoch": 2.5344827586206895, "percentage": 84.48, "elapsed_time": "3:04:57", "remaining_time": "0:33:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1030, "total_steps": 1218, "loss": 0.4686, "learning_rate": 1.4171927337539103e-06, "epoch": 2.5369458128078817, "percentage": 84.56, "elapsed_time": "3:05:07", "remaining_time": "0:33:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1031, "total_steps": 1218, "loss": 0.4173, "learning_rate": 1.4025181230763307e-06, "epoch": 2.539408866995074, "percentage": 84.65, "elapsed_time": "3:05:18", "remaining_time": "0:33:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1032, "total_steps": 1218, "loss": 0.4374, "learning_rate": 1.3879141522227878e-06, "epoch": 2.541871921182266, "percentage": 84.73, "elapsed_time": "3:05:30", "remaining_time": "0:33:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1033, "total_steps": 1218, "loss": 0.414, "learning_rate": 1.3733809411844567e-06, "epoch": 2.544334975369458, "percentage": 84.81, "elapsed_time": "3:05:40", "remaining_time": "0:33:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1034, "total_steps": 1218, "loss": 0.3916, "learning_rate": 1.3589186093711227e-06, "epoch": 2.5467980295566504, "percentage": 84.89, "elapsed_time": "3:05:52", "remaining_time": "0:33:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1035, "total_steps": 1218, "loss": 0.4363, "learning_rate": 1.3445272756102023e-06, "epoch": 2.5492610837438425, "percentage": 84.98, "elapsed_time": "3:06:03", "remaining_time": "0:32:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1036, "total_steps": 1218, "loss": 0.5321, "learning_rate": 1.3302070581457716e-06, "epoch": 2.5517241379310347, "percentage": 85.06, "elapsed_time": "3:06:13", "remaining_time": "0:32:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1037, "total_steps": 1218, "loss": 0.4289, "learning_rate": 1.3159580746375887e-06, "epoch": 2.554187192118227, "percentage": 85.14, "elapsed_time": "3:06:22", "remaining_time": "0:32:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1038, "total_steps": 1218, "loss": 0.4328, "learning_rate": 1.3017804421601298e-06, "epoch": 2.5566502463054186, "percentage": 85.22, "elapsed_time": "3:06:32", "remaining_time": "0:32:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1039, "total_steps": 1218, "loss": 0.4165, "learning_rate": 1.287674277201626e-06, "epoch": 2.5591133004926108, "percentage": 85.3, "elapsed_time": "3:06:45", "remaining_time": "0:32:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1040, "total_steps": 1218, "loss": 0.3953, "learning_rate": 1.273639695663108e-06, "epoch": 2.561576354679803, "percentage": 85.39, "elapsed_time": "3:06:54", "remaining_time": "0:31:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1041, "total_steps": 1218, "loss": 0.4622, "learning_rate": 1.2596768128574522e-06, "epoch": 2.564039408866995, "percentage": 85.47, "elapsed_time": "3:07:06", "remaining_time": "0:31:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1042, "total_steps": 1218, "loss": 0.3547, "learning_rate": 1.245785743508441e-06, "epoch": 2.5665024630541873, "percentage": 85.55, "elapsed_time": "3:07:16", "remaining_time": "0:31:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1043, "total_steps": 1218, "loss": 0.4452, "learning_rate": 1.2319666017497977e-06, "epoch": 2.5689655172413794, "percentage": 85.63, "elapsed_time": "3:07:25", "remaining_time": "0:31:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1044, "total_steps": 1218, "loss": 0.4428, "learning_rate": 1.2182195011242747e-06, "epoch": 2.571428571428571, "percentage": 85.71, "elapsed_time": "3:07:36", "remaining_time": "0:31:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1045, "total_steps": 1218, "loss": 0.4107, "learning_rate": 1.2045445545827162e-06, "epoch": 2.5738916256157633, "percentage": 85.8, "elapsed_time": "3:07:50", "remaining_time": "0:31:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1046, "total_steps": 1218, "loss": 0.3926, "learning_rate": 1.1909418744831048e-06, "epoch": 2.5763546798029555, "percentage": 85.88, "elapsed_time": "3:07:59", "remaining_time": "0:30:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1047, "total_steps": 1218, "loss": 0.4602, "learning_rate": 1.1774115725896806e-06, "epoch": 2.5788177339901477, "percentage": 85.96, "elapsed_time": "3:08:09", "remaining_time": "0:30:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1048, "total_steps": 1218, "loss": 0.4226, "learning_rate": 1.1639537600719764e-06, "epoch": 2.58128078817734, "percentage": 86.04, "elapsed_time": "3:08:19", "remaining_time": "0:30:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1049, "total_steps": 1218, "loss": 0.3708, "learning_rate": 1.1505685475039486e-06, "epoch": 2.583743842364532, "percentage": 86.12, "elapsed_time": "3:08:33", "remaining_time": "0:30:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1050, "total_steps": 1218, "loss": 0.4363, "learning_rate": 1.1372560448630377e-06, "epoch": 2.586206896551724, "percentage": 86.21, "elapsed_time": "3:08:43", "remaining_time": "0:30:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1051, "total_steps": 1218, "loss": 0.4795, "learning_rate": 1.12401636152927e-06, "epoch": 2.5886699507389164, "percentage": 86.29, "elapsed_time": "3:08:53", "remaining_time": "0:30:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1052, "total_steps": 1218, "loss": 0.4076, "learning_rate": 1.1108496062843743e-06, "epoch": 2.5911330049261085, "percentage": 86.37, "elapsed_time": "3:09:04", "remaining_time": "0:29:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1053, "total_steps": 1218, "loss": 0.4183, "learning_rate": 1.0977558873108717e-06, "epoch": 2.5935960591133007, "percentage": 86.45, "elapsed_time": "3:09:15", "remaining_time": "0:29:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1054, "total_steps": 1218, "loss": 0.4331, "learning_rate": 1.0847353121911952e-06, "epoch": 2.596059113300493, "percentage": 86.54, "elapsed_time": "3:09:25", "remaining_time": "0:29:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1055, "total_steps": 1218, "loss": 0.4091, "learning_rate": 1.0717879879068004e-06, "epoch": 2.5985221674876846, "percentage": 86.62, "elapsed_time": "3:09:35", "remaining_time": "0:29:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1056, "total_steps": 1218, "loss": 0.4089, "learning_rate": 1.0589140208372872e-06, "epoch": 2.600985221674877, "percentage": 86.7, "elapsed_time": "3:09:46", "remaining_time": "0:29:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1057, "total_steps": 1218, "loss": 0.4146, "learning_rate": 1.0461135167595348e-06, "epoch": 2.603448275862069, "percentage": 86.78, "elapsed_time": "3:09:56", "remaining_time": "0:28:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1058, "total_steps": 1218, "loss": 0.4389, "learning_rate": 1.0333865808468203e-06, "epoch": 2.605911330049261, "percentage": 86.86, "elapsed_time": "3:10:07", "remaining_time": "0:28:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1059, "total_steps": 1218, "loss": 0.4566, "learning_rate": 1.0207333176679624e-06, "epoch": 2.6083743842364533, "percentage": 86.95, "elapsed_time": "3:10:17", "remaining_time": "0:28:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1060, "total_steps": 1218, "loss": 0.432, "learning_rate": 1.008153831186457e-06, "epoch": 2.6108374384236455, "percentage": 87.03, "elapsed_time": "3:10:28", "remaining_time": "0:28:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1061, "total_steps": 1218, "loss": 0.4596, "learning_rate": 9.956482247596266e-07, "epoch": 2.613300492610837, "percentage": 87.11, "elapsed_time": "3:10:38", "remaining_time": "0:28:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1062, "total_steps": 1218, "loss": 0.4649, "learning_rate": 9.83216601137773e-07, "epoch": 2.6157635467980294, "percentage": 87.19, "elapsed_time": "3:10:48", "remaining_time": "0:28:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1063, "total_steps": 1218, "loss": 0.4364, "learning_rate": 9.70859062463324e-07, "epoch": 2.6182266009852215, "percentage": 87.27, "elapsed_time": "3:10:58", "remaining_time": "0:27:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1064, "total_steps": 1218, "loss": 0.4847, "learning_rate": 9.58575710270011e-07, "epoch": 2.6206896551724137, "percentage": 87.36, "elapsed_time": "3:11:09", "remaining_time": "0:27:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1065, "total_steps": 1218, "loss": 0.437, "learning_rate": 9.463666454820119e-07, "epoch": 2.623152709359606, "percentage": 87.44, "elapsed_time": "3:11:20", "remaining_time": "0:27:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1066, "total_steps": 1218, "loss": 0.4438, "learning_rate": 9.342319684131396e-07, "epoch": 2.625615763546798, "percentage": 87.52, "elapsed_time": "3:11:30", "remaining_time": "0:27:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1067, "total_steps": 1218, "loss": 0.4192, "learning_rate": 9.221717787660145e-07, "epoch": 2.62807881773399, "percentage": 87.6, "elapsed_time": "3:11:40", "remaining_time": "0:27:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1068, "total_steps": 1218, "loss": 0.4463, "learning_rate": 9.101861756312369e-07, "epoch": 2.6305418719211824, "percentage": 87.68, "elapsed_time": "3:11:51", "remaining_time": "0:26:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1069, "total_steps": 1218, "loss": 0.3847, "learning_rate": 8.982752574865905e-07, "epoch": 2.6330049261083746, "percentage": 87.77, "elapsed_time": "3:12:05", "remaining_time": "0:26:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1070, "total_steps": 1218, "loss": 0.421, "learning_rate": 8.864391221962065e-07, "epoch": 2.6354679802955667, "percentage": 87.85, "elapsed_time": "3:12:16", "remaining_time": "0:26:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1071, "total_steps": 1218, "loss": 0.446, "learning_rate": 8.746778670097877e-07, "epoch": 2.637931034482759, "percentage": 87.93, "elapsed_time": "3:12:27", "remaining_time": "0:26:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1072, "total_steps": 1218, "loss": 0.4243, "learning_rate": 8.629915885617912e-07, "epoch": 2.6403940886699506, "percentage": 88.01, "elapsed_time": "3:12:37", "remaining_time": "0:26:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1073, "total_steps": 1218, "loss": 0.4255, "learning_rate": 8.513803828706369e-07, "epoch": 2.642857142857143, "percentage": 88.1, "elapsed_time": "3:12:47", "remaining_time": "0:26:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1074, "total_steps": 1218, "loss": 0.4361, "learning_rate": 8.398443453379268e-07, "epoch": 2.645320197044335, "percentage": 88.18, "elapsed_time": "3:12:57", "remaining_time": "0:25:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1075, "total_steps": 1218, "loss": 0.4402, "learning_rate": 8.283835707476551e-07, "epoch": 2.647783251231527, "percentage": 88.26, "elapsed_time": "3:13:09", "remaining_time": "0:25:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1076, "total_steps": 1218, "loss": 0.4523, "learning_rate": 8.169981532654269e-07, "epoch": 2.6502463054187193, "percentage": 88.34, "elapsed_time": "3:13:19", "remaining_time": "0:25:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1077, "total_steps": 1218, "loss": 0.417, "learning_rate": 8.05688186437693e-07, "epoch": 2.6527093596059115, "percentage": 88.42, "elapsed_time": "3:13:30", "remaining_time": "0:25:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1078, "total_steps": 1218, "loss": 0.4122, "learning_rate": 7.944537631909666e-07, "epoch": 2.655172413793103, "percentage": 88.51, "elapsed_time": "3:13:39", "remaining_time": "0:25:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1079, "total_steps": 1218, "loss": 0.4222, "learning_rate": 7.832949758310804e-07, "epoch": 2.6576354679802954, "percentage": 88.59, "elapsed_time": "3:13:49", "remaining_time": "0:24:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1080, "total_steps": 1218, "loss": 0.4552, "learning_rate": 7.722119160424113e-07, "epoch": 2.6600985221674875, "percentage": 88.67, "elapsed_time": "3:14:00", "remaining_time": "0:24:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1081, "total_steps": 1218, "loss": 0.4848, "learning_rate": 7.612046748871327e-07, "epoch": 2.6625615763546797, "percentage": 88.75, "elapsed_time": "3:14:11", "remaining_time": "0:24:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1082, "total_steps": 1218, "loss": 0.4341, "learning_rate": 7.502733428044684e-07, "epoch": 2.665024630541872, "percentage": 88.83, "elapsed_time": "3:14:21", "remaining_time": "0:24:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1083, "total_steps": 1218, "loss": 0.4334, "learning_rate": 7.394180096099457e-07, "epoch": 2.667487684729064, "percentage": 88.92, "elapsed_time": "3:14:31", "remaining_time": "0:24:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1084, "total_steps": 1218, "loss": 0.4485, "learning_rate": 7.286387644946602e-07, "epoch": 2.6699507389162562, "percentage": 89.0, "elapsed_time": "3:14:42", "remaining_time": "0:24:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1085, "total_steps": 1218, "loss": 0.4638, "learning_rate": 7.179356960245409e-07, "epoch": 2.6724137931034484, "percentage": 89.08, "elapsed_time": "3:14:51", "remaining_time": "0:23:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1086, "total_steps": 1218, "loss": 0.4693, "learning_rate": 7.073088921396287e-07, "epoch": 2.6748768472906406, "percentage": 89.16, "elapsed_time": "3:15:02", "remaining_time": "0:23:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1087, "total_steps": 1218, "loss": 0.4967, "learning_rate": 6.9675844015334e-07, "epoch": 2.6773399014778327, "percentage": 89.24, "elapsed_time": "3:15:12", "remaining_time": "0:23:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1088, "total_steps": 1218, "loss": 0.3764, "learning_rate": 6.862844267517643e-07, "epoch": 2.6798029556650245, "percentage": 89.33, "elapsed_time": "3:15:22", "remaining_time": "0:23:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1089, "total_steps": 1218, "loss": 0.3792, "learning_rate": 6.758869379929456e-07, "epoch": 2.6822660098522166, "percentage": 89.41, "elapsed_time": "3:15:31", "remaining_time": "0:23:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1090, "total_steps": 1218, "loss": 0.4379, "learning_rate": 6.655660593061719e-07, "epoch": 2.684729064039409, "percentage": 89.49, "elapsed_time": "3:15:43", "remaining_time": "0:22:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1091, "total_steps": 1218, "loss": 0.457, "learning_rate": 6.553218754912838e-07, "epoch": 2.687192118226601, "percentage": 89.57, "elapsed_time": "3:15:54", "remaining_time": "0:22:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1092, "total_steps": 1218, "loss": 0.4619, "learning_rate": 6.451544707179635e-07, "epoch": 2.689655172413793, "percentage": 89.66, "elapsed_time": "3:16:03", "remaining_time": "0:22:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1093, "total_steps": 1218, "loss": 0.3903, "learning_rate": 6.350639285250515e-07, "epoch": 2.6921182266009853, "percentage": 89.74, "elapsed_time": "3:16:13", "remaining_time": "0:22:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1094, "total_steps": 1218, "loss": 0.4552, "learning_rate": 6.250503318198664e-07, "epoch": 2.6945812807881775, "percentage": 89.82, "elapsed_time": "3:16:24", "remaining_time": "0:22:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1095, "total_steps": 1218, "loss": 0.4698, "learning_rate": 6.151137628775051e-07, "epoch": 2.697044334975369, "percentage": 89.9, "elapsed_time": "3:16:34", "remaining_time": "0:22:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1096, "total_steps": 1218, "loss": 0.3841, "learning_rate": 6.052543033401892e-07, "epoch": 2.6995073891625614, "percentage": 89.98, "elapsed_time": "3:16:44", "remaining_time": "0:21:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1097, "total_steps": 1218, "loss": 0.4281, "learning_rate": 5.954720342165787e-07, "epoch": 2.7019704433497536, "percentage": 90.07, "elapsed_time": "3:16:54", "remaining_time": "0:21:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1098, "total_steps": 1218, "loss": 0.3884, "learning_rate": 5.857670358811096e-07, "epoch": 2.7044334975369457, "percentage": 90.15, "elapsed_time": "3:17:04", "remaining_time": "0:21:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1099, "total_steps": 1218, "loss": 0.4048, "learning_rate": 5.761393880733379e-07, "epoch": 2.706896551724138, "percentage": 90.23, "elapsed_time": "3:17:15", "remaining_time": "0:21:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1100, "total_steps": 1218, "loss": 0.4686, "learning_rate": 5.665891698972769e-07, "epoch": 2.70935960591133, "percentage": 90.31, "elapsed_time": "3:17:25", "remaining_time": "0:21:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1101, "total_steps": 1218, "loss": 0.4772, "learning_rate": 5.571164598207579e-07, "epoch": 2.7118226600985222, "percentage": 90.39, "elapsed_time": "3:17:35", "remaining_time": "0:20:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1102, "total_steps": 1218, "loss": 0.4153, "learning_rate": 5.477213356747746e-07, "epoch": 2.7142857142857144, "percentage": 90.48, "elapsed_time": "3:17:47", "remaining_time": "0:20:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1103, "total_steps": 1218, "loss": 0.4318, "learning_rate": 5.384038746528519e-07, "epoch": 2.7167487684729066, "percentage": 90.56, "elapsed_time": "3:18:01", "remaining_time": "0:20:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1104, "total_steps": 1218, "loss": 0.4073, "learning_rate": 5.291641533104053e-07, "epoch": 2.7192118226600988, "percentage": 90.64, "elapsed_time": "3:18:12", "remaining_time": "0:20:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1105, "total_steps": 1218, "loss": 0.4531, "learning_rate": 5.200022475641154e-07, "epoch": 2.7216748768472905, "percentage": 90.72, "elapsed_time": "3:18:21", "remaining_time": "0:20:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1106, "total_steps": 1218, "loss": 0.4688, "learning_rate": 5.109182326913053e-07, "epoch": 2.7241379310344827, "percentage": 90.8, "elapsed_time": "3:18:32", "remaining_time": "0:20:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1107, "total_steps": 1218, "loss": 0.5167, "learning_rate": 5.019121833293161e-07, "epoch": 2.726600985221675, "percentage": 90.89, "elapsed_time": "3:18:42", "remaining_time": "0:19:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1108, "total_steps": 1218, "loss": 0.3942, "learning_rate": 4.929841734749063e-07, "epoch": 2.729064039408867, "percentage": 90.97, "elapsed_time": "3:18:52", "remaining_time": "0:19:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1109, "total_steps": 1218, "loss": 0.4152, "learning_rate": 4.841342764836243e-07, "epoch": 2.731527093596059, "percentage": 91.05, "elapsed_time": "3:19:02", "remaining_time": "0:19:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1110, "total_steps": 1218, "loss": 0.4611, "learning_rate": 4.7536256506922507e-07, "epoch": 2.7339901477832513, "percentage": 91.13, "elapsed_time": "3:19:11", "remaining_time": "0:19:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1111, "total_steps": 1218, "loss": 0.4948, "learning_rate": 4.666691113030608e-07, "epoch": 2.7364532019704435, "percentage": 91.22, "elapsed_time": "3:19:20", "remaining_time": "0:19:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1112, "total_steps": 1218, "loss": 0.4391, "learning_rate": 4.580539866134914e-07, "epoch": 2.7389162561576352, "percentage": 91.3, "elapsed_time": "3:19:30", "remaining_time": "0:19:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1113, "total_steps": 1218, "loss": 0.4468, "learning_rate": 4.4951726178530387e-07, "epoch": 2.7413793103448274, "percentage": 91.38, "elapsed_time": "3:19:40", "remaining_time": "0:18:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1114, "total_steps": 1218, "loss": 0.4379, "learning_rate": 4.410590069591192e-07, "epoch": 2.7438423645320196, "percentage": 91.46, "elapsed_time": "3:19:52", "remaining_time": "0:18:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1115, "total_steps": 1218, "loss": 0.4403, "learning_rate": 4.3267929163082424e-07, "epoch": 2.7463054187192117, "percentage": 91.54, "elapsed_time": "3:20:06", "remaining_time": "0:18:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1116, "total_steps": 1218, "loss": 0.4513, "learning_rate": 4.2437818465100313e-07, "epoch": 2.748768472906404, "percentage": 91.63, "elapsed_time": "3:20:16", "remaining_time": "0:18:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1117, "total_steps": 1218, "loss": 0.4522, "learning_rate": 4.1615575422435774e-07, "epoch": 2.751231527093596, "percentage": 91.71, "elapsed_time": "3:20:25", "remaining_time": "0:18:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1118, "total_steps": 1218, "loss": 0.4349, "learning_rate": 4.0801206790916815e-07, "epoch": 2.7536945812807883, "percentage": 91.79, "elapsed_time": "3:20:37", "remaining_time": "0:17:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1119, "total_steps": 1218, "loss": 0.4672, "learning_rate": 3.999471926167142e-07, "epoch": 2.7561576354679804, "percentage": 91.87, "elapsed_time": "3:20:47", "remaining_time": "0:17:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1120, "total_steps": 1218, "loss": 0.4231, "learning_rate": 3.919611946107493e-07, "epoch": 2.7586206896551726, "percentage": 91.95, "elapsed_time": "3:20:57", "remaining_time": "0:17:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1121, "total_steps": 1218, "loss": 0.4416, "learning_rate": 3.840541395069375e-07, "epoch": 2.7610837438423648, "percentage": 92.04, "elapsed_time": "3:21:07", "remaining_time": "0:17:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1122, "total_steps": 1218, "loss": 0.4185, "learning_rate": 3.762260922723182e-07, "epoch": 2.7635467980295565, "percentage": 92.12, "elapsed_time": "3:21:17", "remaining_time": "0:17:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1123, "total_steps": 1218, "loss": 0.4903, "learning_rate": 3.6847711722478476e-07, "epoch": 2.7660098522167487, "percentage": 92.2, "elapsed_time": "3:21:28", "remaining_time": "0:17:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1124, "total_steps": 1218, "loss": 0.4746, "learning_rate": 3.6080727803254003e-07, "epoch": 2.768472906403941, "percentage": 92.28, "elapsed_time": "3:21:39", "remaining_time": "0:16:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1125, "total_steps": 1218, "loss": 0.4343, "learning_rate": 3.532166377135815e-07, "epoch": 2.770935960591133, "percentage": 92.36, "elapsed_time": "3:21:48", "remaining_time": "0:16:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1126, "total_steps": 1218, "loss": 0.4489, "learning_rate": 3.457052586351817e-07, "epoch": 2.773399014778325, "percentage": 92.45, "elapsed_time": "3:21:59", "remaining_time": "0:16:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1127, "total_steps": 1218, "loss": 0.4164, "learning_rate": 3.3827320251337613e-07, "epoch": 2.7758620689655173, "percentage": 92.53, "elapsed_time": "3:22:09", "remaining_time": "0:16:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1128, "total_steps": 1218, "loss": 0.4031, "learning_rate": 3.309205304124552e-07, "epoch": 2.7783251231527095, "percentage": 92.61, "elapsed_time": "3:22:18", "remaining_time": "0:16:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1129, "total_steps": 1218, "loss": 0.4656, "learning_rate": 3.2364730274446533e-07, "epoch": 2.7807881773399012, "percentage": 92.69, "elapsed_time": "3:22:29", "remaining_time": "0:15:57", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1130, "total_steps": 1218, "loss": 0.411, "learning_rate": 3.1645357926870957e-07, "epoch": 2.7832512315270934, "percentage": 92.78, "elapsed_time": "3:22:39", "remaining_time": "0:15:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1131, "total_steps": 1218, "loss": 0.4566, "learning_rate": 3.0933941909125573e-07, "epoch": 2.7857142857142856, "percentage": 92.86, "elapsed_time": "3:22:50", "remaining_time": "0:15:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1132, "total_steps": 1218, "loss": 0.4399, "learning_rate": 3.0230488066445465e-07, "epoch": 2.7881773399014778, "percentage": 92.94, "elapsed_time": "3:23:02", "remaining_time": "0:15:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1133, "total_steps": 1218, "loss": 0.4757, "learning_rate": 2.95350021786458e-07, "epoch": 2.79064039408867, "percentage": 93.02, "elapsed_time": "3:23:14", "remaining_time": "0:15:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1134, "total_steps": 1218, "loss": 0.3832, "learning_rate": 2.8847489960074136e-07, "epoch": 2.793103448275862, "percentage": 93.1, "elapsed_time": "3:23:23", "remaining_time": "0:15:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1135, "total_steps": 1218, "loss": 0.4106, "learning_rate": 2.81679570595641e-07, "epoch": 2.7955665024630543, "percentage": 93.19, "elapsed_time": "3:23:33", "remaining_time": "0:14:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1136, "total_steps": 1218, "loss": 0.4553, "learning_rate": 2.7496409060387973e-07, "epoch": 2.7980295566502464, "percentage": 93.27, "elapsed_time": "3:23:43", "remaining_time": "0:14:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1137, "total_steps": 1218, "loss": 0.4475, "learning_rate": 2.683285148021164e-07, "epoch": 2.8004926108374386, "percentage": 93.35, "elapsed_time": "3:23:53", "remaining_time": "0:14:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1138, "total_steps": 1218, "loss": 0.3686, "learning_rate": 2.6177289771049274e-07, "epoch": 2.802955665024631, "percentage": 93.43, "elapsed_time": "3:24:05", "remaining_time": "0:14:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1139, "total_steps": 1218, "loss": 0.4656, "learning_rate": 2.55297293192176e-07, "epoch": 2.8054187192118225, "percentage": 93.51, "elapsed_time": "3:24:15", "remaining_time": "0:14:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1140, "total_steps": 1218, "loss": 0.4349, "learning_rate": 2.489017544529315e-07, "epoch": 2.8078817733990147, "percentage": 93.6, "elapsed_time": "3:24:29", "remaining_time": "0:13:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1141, "total_steps": 1218, "loss": 0.449, "learning_rate": 2.425863340406676e-07, "epoch": 2.810344827586207, "percentage": 93.68, "elapsed_time": "3:24:38", "remaining_time": "0:13:48", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1142, "total_steps": 1218, "loss": 0.424, "learning_rate": 2.3635108384502003e-07, "epoch": 2.812807881773399, "percentage": 93.76, "elapsed_time": "3:24:48", "remaining_time": "0:13:37", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1143, "total_steps": 1218, "loss": 0.4707, "learning_rate": 2.3019605509691957e-07, "epoch": 2.815270935960591, "percentage": 93.84, "elapsed_time": "3:24:59", "remaining_time": "0:13:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1144, "total_steps": 1218, "loss": 0.4608, "learning_rate": 2.2412129836816287e-07, "epoch": 2.8177339901477834, "percentage": 93.92, "elapsed_time": "3:25:11", "remaining_time": "0:13:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1145, "total_steps": 1218, "loss": 0.4626, "learning_rate": 2.181268635710143e-07, "epoch": 2.8201970443349755, "percentage": 94.01, "elapsed_time": "3:25:20", "remaining_time": "0:13:05", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1146, "total_steps": 1218, "loss": 0.4268, "learning_rate": 2.1221279995777833e-07, "epoch": 2.8226600985221673, "percentage": 94.09, "elapsed_time": "3:25:31", "remaining_time": "0:12:54", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1147, "total_steps": 1218, "loss": 0.4504, "learning_rate": 2.0637915612040537e-07, "epoch": 2.8251231527093594, "percentage": 94.17, "elapsed_time": "3:25:41", "remaining_time": "0:12:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1148, "total_steps": 1218, "loss": 0.4328, "learning_rate": 2.0062597999009114e-07, "epoch": 2.8275862068965516, "percentage": 94.25, "elapsed_time": "3:25:50", "remaining_time": "0:12:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1149, "total_steps": 1218, "loss": 0.4492, "learning_rate": 1.9495331883687906e-07, "epoch": 2.8300492610837438, "percentage": 94.33, "elapsed_time": "3:26:01", "remaining_time": "0:12:22", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1150, "total_steps": 1218, "loss": 0.384, "learning_rate": 1.8936121926927508e-07, "epoch": 2.832512315270936, "percentage": 94.42, "elapsed_time": "3:26:11", "remaining_time": "0:12:11", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1151, "total_steps": 1218, "loss": 0.3879, "learning_rate": 1.838497272338635e-07, "epoch": 2.834975369458128, "percentage": 94.5, "elapsed_time": "3:26:22", "remaining_time": "0:12:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1152, "total_steps": 1218, "loss": 0.4503, "learning_rate": 1.7841888801493178e-07, "epoch": 2.8374384236453203, "percentage": 94.58, "elapsed_time": "3:26:32", "remaining_time": "0:11:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1153, "total_steps": 1218, "loss": 0.4363, "learning_rate": 1.7306874623409296e-07, "epoch": 2.8399014778325125, "percentage": 94.66, "elapsed_time": "3:26:42", "remaining_time": "0:11:39", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1154, "total_steps": 1218, "loss": 0.4566, "learning_rate": 1.677993458499272e-07, "epoch": 2.8423645320197046, "percentage": 94.75, "elapsed_time": "3:26:54", "remaining_time": "0:11:28", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1155, "total_steps": 1218, "loss": 0.4284, "learning_rate": 1.6261073015761076e-07, "epoch": 2.844827586206897, "percentage": 94.83, "elapsed_time": "3:27:04", "remaining_time": "0:11:17", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1156, "total_steps": 1218, "loss": 0.4884, "learning_rate": 1.5750294178856872e-07, "epoch": 2.8472906403940885, "percentage": 94.91, "elapsed_time": "3:27:16", "remaining_time": "0:11:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1157, "total_steps": 1218, "loss": 0.456, "learning_rate": 1.5247602271012296e-07, "epoch": 2.8497536945812807, "percentage": 94.99, "elapsed_time": "3:27:26", "remaining_time": "0:10:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1158, "total_steps": 1218, "loss": 0.4098, "learning_rate": 1.4753001422514125e-07, "epoch": 2.852216748768473, "percentage": 95.07, "elapsed_time": "3:27:36", "remaining_time": "0:10:45", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1159, "total_steps": 1218, "loss": 0.4353, "learning_rate": 1.4266495697170536e-07, "epoch": 2.854679802955665, "percentage": 95.16, "elapsed_time": "3:27:53", "remaining_time": "0:10:34", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1160, "total_steps": 1218, "loss": 0.4156, "learning_rate": 1.378808909227769e-07, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "3:28:03", "remaining_time": "0:10:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1161, "total_steps": 1218, "loss": 0.401, "learning_rate": 1.331778553858598e-07, "epoch": 2.8596059113300494, "percentage": 95.32, "elapsed_time": "3:28:13", "remaining_time": "0:10:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1162, "total_steps": 1218, "loss": 0.4166, "learning_rate": 1.2855588900269057e-07, "epoch": 2.862068965517241, "percentage": 95.4, "elapsed_time": "3:28:24", "remaining_time": "0:10:02", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1163, "total_steps": 1218, "loss": 0.4077, "learning_rate": 1.2401502974890735e-07, "epoch": 2.8645320197044333, "percentage": 95.48, "elapsed_time": "3:28:34", "remaining_time": "0:09:51", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1164, "total_steps": 1218, "loss": 0.4428, "learning_rate": 1.1955531493375137e-07, "epoch": 2.8669950738916254, "percentage": 95.57, "elapsed_time": "3:28:45", "remaining_time": "0:09:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1165, "total_steps": 1218, "loss": 0.3542, "learning_rate": 1.1517678119975062e-07, "epoch": 2.8694581280788176, "percentage": 95.65, "elapsed_time": "3:28:56", "remaining_time": "0:09:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1166, "total_steps": 1218, "loss": 0.481, "learning_rate": 1.1087946452241871e-07, "epoch": 2.87192118226601, "percentage": 95.73, "elapsed_time": "3:29:07", "remaining_time": "0:09:19", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1167, "total_steps": 1218, "loss": 0.4654, "learning_rate": 1.0666340020996868e-07, "epoch": 2.874384236453202, "percentage": 95.81, "elapsed_time": "3:29:18", "remaining_time": "0:09:08", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1168, "total_steps": 1218, "loss": 0.4041, "learning_rate": 1.0252862290301092e-07, "epoch": 2.876847290640394, "percentage": 95.89, "elapsed_time": "3:29:29", "remaining_time": "0:08:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1169, "total_steps": 1218, "loss": 0.3943, "learning_rate": 9.847516657427891e-08, "epoch": 2.8793103448275863, "percentage": 95.98, "elapsed_time": "3:29:41", "remaining_time": "0:08:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1170, "total_steps": 1218, "loss": 0.4422, "learning_rate": 9.45030645283418e-08, "epoch": 2.8817733990147785, "percentage": 96.06, "elapsed_time": "3:29:51", "remaining_time": "0:08:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1171, "total_steps": 1218, "loss": 0.4256, "learning_rate": 9.061234940133668e-08, "epoch": 2.8842364532019706, "percentage": 96.14, "elapsed_time": "3:30:01", "remaining_time": "0:08:25", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1172, "total_steps": 1218, "loss": 0.4438, "learning_rate": 8.68030531606967e-08, "epoch": 2.886699507389163, "percentage": 96.22, "elapsed_time": "3:30:11", "remaining_time": "0:08:14", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1173, "total_steps": 1218, "loss": 0.3978, "learning_rate": 8.307520710489015e-08, "epoch": 2.8891625615763545, "percentage": 96.31, "elapsed_time": "3:30:21", "remaining_time": "0:08:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1174, "total_steps": 1218, "loss": 0.4115, "learning_rate": 7.94288418631639e-08, "epoch": 2.8916256157635467, "percentage": 96.39, "elapsed_time": "3:30:32", "remaining_time": "0:07:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1175, "total_steps": 1218, "loss": 0.4698, "learning_rate": 7.586398739528933e-08, "epoch": 2.894088669950739, "percentage": 96.47, "elapsed_time": "3:30:43", "remaining_time": "0:07:42", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1176, "total_steps": 1218, "loss": 0.389, "learning_rate": 7.238067299131901e-08, "epoch": 2.896551724137931, "percentage": 96.55, "elapsed_time": "3:30:54", "remaining_time": "0:07:31", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1177, "total_steps": 1218, "loss": 0.4308, "learning_rate": 6.897892727134592e-08, "epoch": 2.899014778325123, "percentage": 96.63, "elapsed_time": "3:31:08", "remaining_time": "0:07:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1178, "total_steps": 1218, "loss": 0.4117, "learning_rate": 6.565877818526245e-08, "epoch": 2.9014778325123154, "percentage": 96.72, "elapsed_time": "3:31:18", "remaining_time": "0:07:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1179, "total_steps": 1218, "loss": 0.3806, "learning_rate": 6.242025301254062e-08, "epoch": 2.903940886699507, "percentage": 96.8, "elapsed_time": "3:31:32", "remaining_time": "0:06:59", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1180, "total_steps": 1218, "loss": 0.4864, "learning_rate": 5.926337836199891e-08, "epoch": 2.9064039408866993, "percentage": 96.88, "elapsed_time": "3:31:45", "remaining_time": "0:06:49", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1181, "total_steps": 1218, "loss": 0.4078, "learning_rate": 5.6188180171590225e-08, "epoch": 2.9088669950738915, "percentage": 96.96, "elapsed_time": "3:31:55", "remaining_time": "0:06:38", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1182, "total_steps": 1218, "loss": 0.4417, "learning_rate": 5.319468370818537e-08, "epoch": 2.9113300492610836, "percentage": 97.04, "elapsed_time": "3:32:07", "remaining_time": "0:06:27", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1183, "total_steps": 1218, "loss": 0.4235, "learning_rate": 5.028291356736326e-08, "epoch": 2.913793103448276, "percentage": 97.13, "elapsed_time": "3:32:17", "remaining_time": "0:06:16", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1184, "total_steps": 1218, "loss": 0.4148, "learning_rate": 4.7452893673216596e-08, "epoch": 2.916256157635468, "percentage": 97.21, "elapsed_time": "3:32:29", "remaining_time": "0:06:06", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1185, "total_steps": 1218, "loss": 0.497, "learning_rate": 4.470464727814538e-08, "epoch": 2.91871921182266, "percentage": 97.29, "elapsed_time": "3:32:42", "remaining_time": "0:05:55", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1186, "total_steps": 1218, "loss": 0.4583, "learning_rate": 4.203819696267486e-08, "epoch": 2.9211822660098523, "percentage": 97.37, "elapsed_time": "3:32:52", "remaining_time": "0:05:44", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1187, "total_steps": 1218, "loss": 0.4058, "learning_rate": 3.945356463526451e-08, "epoch": 2.9236453201970445, "percentage": 97.45, "elapsed_time": "3:33:07", "remaining_time": "0:05:33", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1188, "total_steps": 1218, "loss": 0.4136, "learning_rate": 3.6950771532126004e-08, "epoch": 2.9261083743842367, "percentage": 97.54, "elapsed_time": "3:33:17", "remaining_time": "0:05:23", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1189, "total_steps": 1218, "loss": 0.4095, "learning_rate": 3.452983821705891e-08, "epoch": 2.928571428571429, "percentage": 97.62, "elapsed_time": "3:33:27", "remaining_time": "0:05:12", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1190, "total_steps": 1218, "loss": 0.4081, "learning_rate": 3.2190784581270786e-08, "epoch": 2.9310344827586206, "percentage": 97.7, "elapsed_time": "3:33:38", "remaining_time": "0:05:01", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1191, "total_steps": 1218, "loss": 0.4549, "learning_rate": 2.993362984321735e-08, "epoch": 2.9334975369458127, "percentage": 97.78, "elapsed_time": "3:33:48", "remaining_time": "0:04:50", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1192, "total_steps": 1218, "loss": 0.3992, "learning_rate": 2.7758392548449253e-08, "epoch": 2.935960591133005, "percentage": 97.87, "elapsed_time": "3:33:59", "remaining_time": "0:04:40", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1193, "total_steps": 1218, "loss": 0.4147, "learning_rate": 2.566509056944999e-08, "epoch": 2.938423645320197, "percentage": 97.95, "elapsed_time": "3:34:09", "remaining_time": "0:04:29", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1194, "total_steps": 1218, "loss": 0.4106, "learning_rate": 2.3653741105499338e-08, "epoch": 2.9408866995073892, "percentage": 98.03, "elapsed_time": "3:34:19", "remaining_time": "0:04:18", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1195, "total_steps": 1218, "loss": 0.4156, "learning_rate": 2.1724360682527925e-08, "epoch": 2.9433497536945814, "percentage": 98.11, "elapsed_time": "3:34:30", "remaining_time": "0:04:07", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1196, "total_steps": 1218, "loss": 0.464, "learning_rate": 1.9876965152975102e-08, "epoch": 2.945812807881773, "percentage": 98.19, "elapsed_time": "3:34:40", "remaining_time": "0:03:56", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1197, "total_steps": 1218, "loss": 0.432, "learning_rate": 1.8111569695672403e-08, "epoch": 2.9482758620689653, "percentage": 98.28, "elapsed_time": "3:34:49", "remaining_time": "0:03:46", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1198, "total_steps": 1218, "loss": 0.4468, "learning_rate": 1.6428188815703627e-08, "epoch": 2.9507389162561575, "percentage": 98.36, "elapsed_time": "3:35:00", "remaining_time": "0:03:35", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1199, "total_steps": 1218, "loss": 0.4274, "learning_rate": 1.4826836344299378e-08, "epoch": 2.9532019704433496, "percentage": 98.44, "elapsed_time": "3:35:11", "remaining_time": "0:03:24", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1200, "total_steps": 1218, "loss": 0.4588, "learning_rate": 1.3307525438711611e-08, "epoch": 2.955665024630542, "percentage": 98.52, "elapsed_time": "3:35:22", "remaining_time": "0:03:13", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1201, "total_steps": 1218, "loss": 0.4493, "learning_rate": 1.187026858211482e-08, "epoch": 2.958128078817734, "percentage": 98.6, "elapsed_time": "3:35:35", "remaining_time": "0:03:03", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1202, "total_steps": 1218, "loss": 0.4329, "learning_rate": 1.0515077583498346e-08, "epoch": 2.960591133004926, "percentage": 98.69, "elapsed_time": "3:35:45", "remaining_time": "0:02:52", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1203, "total_steps": 1218, "loss": 0.4085, "learning_rate": 9.241963577569791e-09, "epoch": 2.9630541871921183, "percentage": 98.77, "elapsed_time": "3:35:54", "remaining_time": "0:02:41", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1204, "total_steps": 1218, "loss": 0.4496, "learning_rate": 8.050937024666195e-09, "epoch": 2.9655172413793105, "percentage": 98.85, "elapsed_time": "3:36:05", "remaining_time": "0:02:30", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1205, "total_steps": 1218, "loss": 0.4102, "learning_rate": 6.942007710665222e-09, "epoch": 2.9679802955665027, "percentage": 98.93, "elapsed_time": "3:36:18", "remaining_time": "0:02:20", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1206, "total_steps": 1218, "loss": 0.4659, "learning_rate": 5.9151847469041125e-09, "epoch": 2.970443349753695, "percentage": 99.01, "elapsed_time": "3:36:28", "remaining_time": "0:02:09", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1207, "total_steps": 1218, "loss": 0.454, "learning_rate": 4.970476570110849e-09, "epoch": 2.9729064039408866, "percentage": 99.1, "elapsed_time": "3:36:38", "remaining_time": "0:01:58", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1208, "total_steps": 1218, "loss": 0.434, "learning_rate": 4.1078909423253325e-09, "epoch": 2.9753694581280787, "percentage": 99.18, "elapsed_time": "3:36:48", "remaining_time": "0:01:47", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1209, "total_steps": 1218, "loss": 0.4034, "learning_rate": 3.327434950846087e-09, "epoch": 2.977832512315271, "percentage": 99.26, "elapsed_time": "3:36:59", "remaining_time": "0:01:36", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1210, "total_steps": 1218, "loss": 0.43, "learning_rate": 2.629115008160321e-09, "epoch": 2.980295566502463, "percentage": 99.34, "elapsed_time": "3:37:11", "remaining_time": "0:01:26", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1211, "total_steps": 1218, "loss": 0.4448, "learning_rate": 2.0129368519050674e-09, "epoch": 2.9827586206896552, "percentage": 99.43, "elapsed_time": "3:37:20", "remaining_time": "0:01:15", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1212, "total_steps": 1218, "loss": 0.3958, "learning_rate": 1.4789055448061195e-09, "epoch": 2.9852216748768474, "percentage": 99.51, "elapsed_time": "3:37:30", "remaining_time": "0:01:04", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1213, "total_steps": 1218, "loss": 0.3828, "learning_rate": 1.027025474648058e-09, "epoch": 2.987684729064039, "percentage": 99.59, "elapsed_time": "3:37:40", "remaining_time": "0:00:53", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1214, "total_steps": 1218, "loss": 0.4129, "learning_rate": 6.573003542276191e-10, "epoch": 2.9901477832512313, "percentage": 99.67, "elapsed_time": "3:37:51", "remaining_time": "0:00:43", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1215, "total_steps": 1218, "loss": 0.4113, "learning_rate": 3.697332213348226e-10, "epoch": 2.9926108374384235, "percentage": 99.75, "elapsed_time": "3:38:01", "remaining_time": "0:00:32", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1216, "total_steps": 1218, "loss": 0.4441, "learning_rate": 1.6432643871633346e-10, "epoch": 2.9950738916256157, "percentage": 99.84, "elapsed_time": "3:38:13", "remaining_time": "0:00:21", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1217, "total_steps": 1218, "loss": 0.4782, "learning_rate": 4.108169406435991e-11, "epoch": 2.997536945812808, "percentage": 99.92, "elapsed_time": "3:38:23", "remaining_time": "0:00:10", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1218, "total_steps": 1218, "loss": 0.4558, "learning_rate": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:38:35", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1218, "total_steps": 1218, "eval_loss": 1.3741660118103027, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:39:40", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} {"current_steps": 1218, "total_steps": 1218, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:39:40", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}