diff --git "a/trainer_log.jsonl" "b/trainer_log.jsonl" new file mode 100644--- /dev/null +++ "b/trainer_log.jsonl" @@ -0,0 +1,703 @@ +{"current_steps": 5, "total_steps": 9520, "loss": 8.3193, "lr": 4.2016806722689076e-08, "epoch": 0.01050420168067227, "percentage": 0.05, "elapsed_time": "0:00:00", "remaining_time": "0:28:44", "throughput": 1553.37, "total_tokens": 1408} +{"current_steps": 10, "total_steps": 9520, "loss": 8.5726, "lr": 9.453781512605043e-08, "epoch": 0.02100840336134454, "percentage": 0.11, "elapsed_time": "0:00:01", "remaining_time": "0:20:55", "throughput": 2083.76, "total_tokens": 2752} +{"current_steps": 15, "total_steps": 9520, "loss": 8.4897, "lr": 1.4705882352941178e-07, "epoch": 0.031512605042016806, "percentage": 0.16, "elapsed_time": "0:00:01", "remaining_time": "0:18:27", "throughput": 2434.39, "total_tokens": 4256} +{"current_steps": 20, "total_steps": 9520, "loss": 8.5659, "lr": 1.995798319327731e-07, "epoch": 0.04201680672268908, "percentage": 0.21, "elapsed_time": "0:00:02", "remaining_time": "0:17:11", "throughput": 2623.25, "total_tokens": 5696} +{"current_steps": 25, "total_steps": 9520, "loss": 8.6861, "lr": 2.5210084033613445e-07, "epoch": 0.052521008403361345, "percentage": 0.26, "elapsed_time": "0:00:02", "remaining_time": "0:16:22", "throughput": 2709.01, "total_tokens": 7008} +{"current_steps": 30, "total_steps": 9520, "loss": 7.8338, "lr": 3.0462184873949583e-07, "epoch": 0.06302521008403361, "percentage": 0.32, "elapsed_time": "0:00:03", "remaining_time": "0:15:58", "throughput": 2840.79, "total_tokens": 8608} +{"current_steps": 35, "total_steps": 9520, "loss": 8.0014, "lr": 3.5714285714285716e-07, "epoch": 0.07352941176470588, "percentage": 0.37, "elapsed_time": "0:00:03", "remaining_time": "0:15:31", "throughput": 2866.39, "total_tokens": 9856} +{"current_steps": 40, "total_steps": 9520, "loss": 7.5824, "lr": 4.0966386554621853e-07, "epoch": 0.08403361344537816, "percentage": 0.42, "elapsed_time": "0:00:03", "remaining_time": "0:15:12", "throughput": 2908.97, "total_tokens": 11200} +{"current_steps": 45, "total_steps": 9520, "loss": 8.1188, "lr": 4.621848739495799e-07, "epoch": 0.09453781512605042, "percentage": 0.47, "elapsed_time": "0:00:04", "remaining_time": "0:14:58", "throughput": 2940.5, "total_tokens": 12544} +{"current_steps": 50, "total_steps": 9520, "loss": 7.2224, "lr": 5.147058823529412e-07, "epoch": 0.10504201680672269, "percentage": 0.53, "elapsed_time": "0:00:04", "remaining_time": "0:14:49", "throughput": 2971.95, "total_tokens": 13952} +{"current_steps": 55, "total_steps": 9520, "loss": 7.3664, "lr": 5.672268907563026e-07, "epoch": 0.11554621848739496, "percentage": 0.58, "elapsed_time": "0:00:05", "remaining_time": "0:14:40", "throughput": 3003.72, "total_tokens": 15360} +{"current_steps": 60, "total_steps": 9520, "loss": 7.2161, "lr": 6.197478991596639e-07, "epoch": 0.12605042016806722, "percentage": 0.63, "elapsed_time": "0:00:05", "remaining_time": "0:14:30", "throughput": 3012.43, "total_tokens": 16640} +{"current_steps": 65, "total_steps": 9520, "loss": 6.5521, "lr": 6.722689075630252e-07, "epoch": 0.13655462184873948, "percentage": 0.68, "elapsed_time": "0:00:05", "remaining_time": "0:14:30", "throughput": 3046.94, "total_tokens": 18240} +{"current_steps": 70, "total_steps": 9520, "loss": 7.1581, "lr": 7.247899159663866e-07, "epoch": 0.14705882352941177, "percentage": 0.74, "elapsed_time": "0:00:06", "remaining_time": "0:14:26", "throughput": 3075.74, "total_tokens": 19744} +{"current_steps": 75, "total_steps": 9520, "loss": 6.2963, "lr": 7.77310924369748e-07, "epoch": 0.15756302521008403, "percentage": 0.79, "elapsed_time": "0:00:06", "remaining_time": "0:14:23", "throughput": 3099.35, "total_tokens": 21248} +{"current_steps": 80, "total_steps": 9520, "loss": 5.8757, "lr": 8.298319327731093e-07, "epoch": 0.16806722689075632, "percentage": 0.84, "elapsed_time": "0:00:07", "remaining_time": "0:14:17", "throughput": 3100.28, "total_tokens": 22528} +{"current_steps": 85, "total_steps": 9520, "loss": 6.2739, "lr": 8.823529411764707e-07, "epoch": 0.17857142857142858, "percentage": 0.89, "elapsed_time": "0:00:07", "remaining_time": "0:14:12", "throughput": 3111.07, "total_tokens": 23904} +{"current_steps": 90, "total_steps": 9520, "loss": 5.1248, "lr": 9.34873949579832e-07, "epoch": 0.18907563025210083, "percentage": 0.95, "elapsed_time": "0:00:08", "remaining_time": "0:14:12", "throughput": 3130.52, "total_tokens": 25472} +{"current_steps": 95, "total_steps": 9520, "loss": 5.3321, "lr": 9.873949579831934e-07, "epoch": 0.19957983193277312, "percentage": 1.0, "elapsed_time": "0:00:08", "remaining_time": "0:14:11", "throughput": 3141.3, "total_tokens": 26976} +{"current_steps": 100, "total_steps": 9520, "loss": 5.4591, "lr": 1.0399159663865548e-06, "epoch": 0.21008403361344538, "percentage": 1.05, "elapsed_time": "0:00:09", "remaining_time": "0:14:09", "throughput": 3159.84, "total_tokens": 28480} +{"current_steps": 105, "total_steps": 9520, "loss": 5.399, "lr": 1.092436974789916e-06, "epoch": 0.22058823529411764, "percentage": 1.1, "elapsed_time": "0:00:09", "remaining_time": "0:14:06", "throughput": 3178.75, "total_tokens": 30016} +{"current_steps": 110, "total_steps": 9520, "loss": 5.2302, "lr": 1.1449579831932775e-06, "epoch": 0.23109243697478993, "percentage": 1.16, "elapsed_time": "0:00:09", "remaining_time": "0:14:03", "throughput": 3180.74, "total_tokens": 31360} +{"current_steps": 115, "total_steps": 9520, "loss": 4.9154, "lr": 1.1974789915966389e-06, "epoch": 0.2415966386554622, "percentage": 1.21, "elapsed_time": "0:00:10", "remaining_time": "0:13:59", "throughput": 3181.11, "total_tokens": 32672} +{"current_steps": 120, "total_steps": 9520, "loss": 4.9132, "lr": 1.25e-06, "epoch": 0.25210084033613445, "percentage": 1.26, "elapsed_time": "0:00:10", "remaining_time": "0:13:58", "throughput": 3194.02, "total_tokens": 34176} +{"current_steps": 125, "total_steps": 9520, "loss": 4.7543, "lr": 1.3025210084033615e-06, "epoch": 0.26260504201680673, "percentage": 1.31, "elapsed_time": "0:00:11", "remaining_time": "0:13:56", "throughput": 3201.7, "total_tokens": 35616} +{"current_steps": 130, "total_steps": 9520, "loss": 4.5839, "lr": 1.3550420168067228e-06, "epoch": 0.27310924369747897, "percentage": 1.37, "elapsed_time": "0:00:11", "remaining_time": "0:13:54", "throughput": 3208.57, "total_tokens": 37056} +{"current_steps": 135, "total_steps": 9520, "loss": 4.2991, "lr": 1.4075630252100842e-06, "epoch": 0.28361344537815125, "percentage": 1.42, "elapsed_time": "0:00:11", "remaining_time": "0:13:51", "throughput": 3209.53, "total_tokens": 38400} +{"current_steps": 140, "total_steps": 9520, "loss": 4.7509, "lr": 1.4600840336134456e-06, "epoch": 0.29411764705882354, "percentage": 1.47, "elapsed_time": "0:00:12", "remaining_time": "0:13:49", "throughput": 3204.3, "total_tokens": 39648} +{"current_steps": 145, "total_steps": 9520, "loss": 4.7383, "lr": 1.5126050420168068e-06, "epoch": 0.30462184873949577, "percentage": 1.52, "elapsed_time": "0:00:12", "remaining_time": "0:13:46", "throughput": 3199.44, "total_tokens": 40896} +{"current_steps": 150, "total_steps": 9520, "loss": 4.1492, "lr": 1.5651260504201683e-06, "epoch": 0.31512605042016806, "percentage": 1.58, "elapsed_time": "0:00:13", "remaining_time": "0:13:44", "throughput": 3203.07, "total_tokens": 42272} +{"current_steps": 155, "total_steps": 9520, "loss": 4.4103, "lr": 1.6176470588235297e-06, "epoch": 0.32563025210084034, "percentage": 1.63, "elapsed_time": "0:00:13", "remaining_time": "0:13:43", "throughput": 3211.35, "total_tokens": 43776} +{"current_steps": 160, "total_steps": 9520, "loss": 4.0582, "lr": 1.6701680672268907e-06, "epoch": 0.33613445378151263, "percentage": 1.68, "elapsed_time": "0:00:14", "remaining_time": "0:13:42", "throughput": 3212.79, "total_tokens": 45152} +{"current_steps": 165, "total_steps": 9520, "loss": 4.1026, "lr": 1.7226890756302521e-06, "epoch": 0.34663865546218486, "percentage": 1.73, "elapsed_time": "0:00:14", "remaining_time": "0:13:43", "throughput": 3229.22, "total_tokens": 46880} +{"current_steps": 170, "total_steps": 9520, "loss": 3.6793, "lr": 1.7752100840336136e-06, "epoch": 0.35714285714285715, "percentage": 1.79, "elapsed_time": "0:00:14", "remaining_time": "0:13:43", "throughput": 3230.45, "total_tokens": 48352} +{"current_steps": 175, "total_steps": 9520, "loss": 3.741, "lr": 1.8277310924369748e-06, "epoch": 0.36764705882352944, "percentage": 1.84, "elapsed_time": "0:00:15", "remaining_time": "0:13:42", "throughput": 3234.5, "total_tokens": 49792} +{"current_steps": 180, "total_steps": 9520, "loss": 3.7427, "lr": 1.8802521008403362e-06, "epoch": 0.37815126050420167, "percentage": 1.89, "elapsed_time": "0:00:15", "remaining_time": "0:13:40", "throughput": 3236.9, "total_tokens": 51200} +{"current_steps": 185, "total_steps": 9520, "loss": 3.8821, "lr": 1.932773109243698e-06, "epoch": 0.38865546218487396, "percentage": 1.94, "elapsed_time": "0:00:16", "remaining_time": "0:13:39", "throughput": 3239.54, "total_tokens": 52608} +{"current_steps": 190, "total_steps": 9520, "loss": 3.8664, "lr": 1.985294117647059e-06, "epoch": 0.39915966386554624, "percentage": 2.0, "elapsed_time": "0:00:16", "remaining_time": "0:13:38", "throughput": 3247.7, "total_tokens": 54112} +{"current_steps": 195, "total_steps": 9520, "loss": 3.7029, "lr": 2.0378151260504203e-06, "epoch": 0.4096638655462185, "percentage": 2.05, "elapsed_time": "0:00:17", "remaining_time": "0:13:36", "throughput": 3248.17, "total_tokens": 55488} +{"current_steps": 200, "total_steps": 9520, "loss": 3.5746, "lr": 2.090336134453782e-06, "epoch": 0.42016806722689076, "percentage": 2.1, "elapsed_time": "0:00:17", "remaining_time": "0:13:36", "throughput": 3254.38, "total_tokens": 56992} +{"current_steps": 205, "total_steps": 9520, "loss": 3.4557, "lr": 2.1428571428571427e-06, "epoch": 0.43067226890756305, "percentage": 2.15, "elapsed_time": "0:00:17", "remaining_time": "0:13:34", "throughput": 3256.36, "total_tokens": 58400} +{"current_steps": 210, "total_steps": 9520, "loss": 3.5647, "lr": 2.1953781512605044e-06, "epoch": 0.4411764705882353, "percentage": 2.21, "elapsed_time": "0:00:18", "remaining_time": "0:13:33", "throughput": 3253.63, "total_tokens": 59712} +{"current_steps": 215, "total_steps": 9520, "loss": 3.0567, "lr": 2.2478991596638656e-06, "epoch": 0.45168067226890757, "percentage": 2.26, "elapsed_time": "0:00:18", "remaining_time": "0:13:32", "throughput": 3257.06, "total_tokens": 61152} +{"current_steps": 220, "total_steps": 9520, "loss": 2.9979, "lr": 2.300420168067227e-06, "epoch": 0.46218487394957986, "percentage": 2.31, "elapsed_time": "0:00:19", "remaining_time": "0:13:31", "throughput": 3256.5, "total_tokens": 62496} +{"current_steps": 225, "total_steps": 9520, "loss": 2.8802, "lr": 2.3529411764705885e-06, "epoch": 0.4726890756302521, "percentage": 2.36, "elapsed_time": "0:00:19", "remaining_time": "0:13:29", "throughput": 3257.75, "total_tokens": 63872} +{"current_steps": 230, "total_steps": 9520, "loss": 3.2474, "lr": 2.4054621848739497e-06, "epoch": 0.4831932773109244, "percentage": 2.42, "elapsed_time": "0:00:20", "remaining_time": "0:13:29", "throughput": 3260.66, "total_tokens": 65312} +{"current_steps": 235, "total_steps": 9520, "loss": 3.2369, "lr": 2.457983193277311e-06, "epoch": 0.49369747899159666, "percentage": 2.47, "elapsed_time": "0:00:20", "remaining_time": "0:13:28", "throughput": 3264.28, "total_tokens": 66784} +{"current_steps": 240, "total_steps": 9520, "loss": 2.9675, "lr": 2.5105042016806725e-06, "epoch": 0.5042016806722689, "percentage": 2.52, "elapsed_time": "0:00:20", "remaining_time": "0:13:27", "throughput": 3262.47, "total_tokens": 68128} +{"current_steps": 245, "total_steps": 9520, "loss": 2.7497, "lr": 2.5630252100840338e-06, "epoch": 0.5147058823529411, "percentage": 2.57, "elapsed_time": "0:00:21", "remaining_time": "0:13:27", "throughput": 3263.86, "total_tokens": 69632} +{"current_steps": 250, "total_steps": 9520, "loss": 2.6015, "lr": 2.6155462184873954e-06, "epoch": 0.5252100840336135, "percentage": 2.63, "elapsed_time": "0:00:21", "remaining_time": "0:13:28", "throughput": 3273.01, "total_tokens": 71392} +{"current_steps": 255, "total_steps": 9520, "loss": 2.7443, "lr": 2.6680672268907566e-06, "epoch": 0.5357142857142857, "percentage": 2.68, "elapsed_time": "0:00:22", "remaining_time": "0:13:27", "throughput": 3272.22, "total_tokens": 72736} +{"current_steps": 260, "total_steps": 9520, "loss": 3.0076, "lr": 2.720588235294118e-06, "epoch": 0.5462184873949579, "percentage": 2.73, "elapsed_time": "0:00:22", "remaining_time": "0:13:26", "throughput": 3272.35, "total_tokens": 74112} +{"current_steps": 265, "total_steps": 9520, "loss": 2.7083, "lr": 2.7731092436974795e-06, "epoch": 0.5567226890756303, "percentage": 2.78, "elapsed_time": "0:00:23", "remaining_time": "0:13:26", "throughput": 3276.97, "total_tokens": 75712} +{"current_steps": 270, "total_steps": 9520, "loss": 2.764, "lr": 2.8256302521008407e-06, "epoch": 0.5672268907563025, "percentage": 2.84, "elapsed_time": "0:00:23", "remaining_time": "0:13:25", "throughput": 3276.47, "total_tokens": 77056} +{"current_steps": 275, "total_steps": 9520, "loss": 2.7822, "lr": 2.8781512605042015e-06, "epoch": 0.5777310924369747, "percentage": 2.89, "elapsed_time": "0:00:23", "remaining_time": "0:13:25", "throughput": 3277.35, "total_tokens": 78496} +{"current_steps": 280, "total_steps": 9520, "loss": 2.7499, "lr": 2.9306722689075636e-06, "epoch": 0.5882352941176471, "percentage": 2.94, "elapsed_time": "0:00:24", "remaining_time": "0:13:24", "throughput": 3281.87, "total_tokens": 80032} +{"current_steps": 285, "total_steps": 9520, "loss": 2.6492, "lr": 2.9831932773109248e-06, "epoch": 0.5987394957983193, "percentage": 2.99, "elapsed_time": "0:00:24", "remaining_time": "0:13:23", "throughput": 3281.16, "total_tokens": 81376} +{"current_steps": 290, "total_steps": 9520, "loss": 2.4603, "lr": 3.0357142857142856e-06, "epoch": 0.6092436974789915, "percentage": 3.05, "elapsed_time": "0:00:25", "remaining_time": "0:13:22", "throughput": 3280.2, "total_tokens": 82720} +{"current_steps": 295, "total_steps": 9520, "loss": 2.6192, "lr": 3.0882352941176476e-06, "epoch": 0.6197478991596639, "percentage": 3.1, "elapsed_time": "0:00:25", "remaining_time": "0:13:21", "throughput": 3275.08, "total_tokens": 83904} +{"current_steps": 300, "total_steps": 9520, "loss": 2.1917, "lr": 3.1407563025210084e-06, "epoch": 0.6302521008403361, "percentage": 3.15, "elapsed_time": "0:00:26", "remaining_time": "0:13:20", "throughput": 3279.32, "total_tokens": 85408} +{"current_steps": 305, "total_steps": 9520, "loss": 2.6192, "lr": 3.1932773109243696e-06, "epoch": 0.6407563025210085, "percentage": 3.2, "elapsed_time": "0:00:26", "remaining_time": "0:13:20", "throughput": 3278.62, "total_tokens": 86848} +{"current_steps": 310, "total_steps": 9520, "loss": 2.7202, "lr": 3.2457983193277313e-06, "epoch": 0.6512605042016807, "percentage": 3.26, "elapsed_time": "0:00:26", "remaining_time": "0:13:19", "throughput": 3276.16, "total_tokens": 88128} +{"current_steps": 315, "total_steps": 9520, "loss": 2.4684, "lr": 3.2983193277310925e-06, "epoch": 0.6617647058823529, "percentage": 3.31, "elapsed_time": "0:00:27", "remaining_time": "0:13:17", "throughput": 3273.0, "total_tokens": 89376} +{"current_steps": 320, "total_steps": 9520, "loss": 2.2952, "lr": 3.3508403361344537e-06, "epoch": 0.6722689075630253, "percentage": 3.36, "elapsed_time": "0:00:27", "remaining_time": "0:13:17", "throughput": 3276.01, "total_tokens": 90848} +{"current_steps": 325, "total_steps": 9520, "loss": 2.1677, "lr": 3.4033613445378154e-06, "epoch": 0.6827731092436975, "percentage": 3.41, "elapsed_time": "0:00:28", "remaining_time": "0:13:16", "throughput": 3274.91, "total_tokens": 92160} +{"current_steps": 330, "total_steps": 9520, "loss": 2.3793, "lr": 3.4558823529411766e-06, "epoch": 0.6932773109243697, "percentage": 3.47, "elapsed_time": "0:00:28", "remaining_time": "0:13:15", "throughput": 3279.35, "total_tokens": 93696} +{"current_steps": 335, "total_steps": 9520, "loss": 2.2403, "lr": 3.508403361344538e-06, "epoch": 0.7037815126050421, "percentage": 3.52, "elapsed_time": "0:00:29", "remaining_time": "0:13:15", "throughput": 3281.43, "total_tokens": 95264} +{"current_steps": 340, "total_steps": 9520, "loss": 1.8183, "lr": 3.5609243697478995e-06, "epoch": 0.7142857142857143, "percentage": 3.57, "elapsed_time": "0:00:29", "remaining_time": "0:13:15", "throughput": 3280.56, "total_tokens": 96640} +{"current_steps": 345, "total_steps": 9520, "loss": 2.3728, "lr": 3.6134453781512607e-06, "epoch": 0.7247899159663865, "percentage": 3.62, "elapsed_time": "0:00:29", "remaining_time": "0:13:14", "throughput": 3282.3, "total_tokens": 98080} +{"current_steps": 350, "total_steps": 9520, "loss": 2.6734, "lr": 3.665966386554622e-06, "epoch": 0.7352941176470589, "percentage": 3.68, "elapsed_time": "0:00:30", "remaining_time": "0:13:13", "throughput": 3278.07, "total_tokens": 99264} +{"current_steps": 355, "total_steps": 9520, "loss": 2.1072, "lr": 3.7184873949579835e-06, "epoch": 0.7457983193277311, "percentage": 3.73, "elapsed_time": "0:00:30", "remaining_time": "0:13:12", "throughput": 3276.96, "total_tokens": 100608} +{"current_steps": 360, "total_steps": 9520, "loss": 2.2815, "lr": 3.7710084033613448e-06, "epoch": 0.7563025210084033, "percentage": 3.78, "elapsed_time": "0:00:31", "remaining_time": "0:13:12", "throughput": 3282.08, "total_tokens": 102272} +{"current_steps": 365, "total_steps": 9520, "loss": 2.1539, "lr": 3.8235294117647055e-06, "epoch": 0.7668067226890757, "percentage": 3.83, "elapsed_time": "0:00:31", "remaining_time": "0:13:12", "throughput": 3285.77, "total_tokens": 103808} +{"current_steps": 370, "total_steps": 9520, "loss": 1.9189, "lr": 3.876050420168068e-06, "epoch": 0.7773109243697479, "percentage": 3.89, "elapsed_time": "0:00:32", "remaining_time": "0:13:11", "throughput": 3284.31, "total_tokens": 105120} +{"current_steps": 375, "total_steps": 9520, "loss": 1.5952, "lr": 3.928571428571429e-06, "epoch": 0.7878151260504201, "percentage": 3.94, "elapsed_time": "0:00:32", "remaining_time": "0:13:10", "throughput": 3282.92, "total_tokens": 106432} +{"current_steps": 380, "total_steps": 9520, "loss": 2.1422, "lr": 3.98109243697479e-06, "epoch": 0.7983193277310925, "percentage": 3.99, "elapsed_time": "0:00:32", "remaining_time": "0:13:09", "throughput": 3283.42, "total_tokens": 107840} +{"current_steps": 385, "total_steps": 9520, "loss": 2.1212, "lr": 4.033613445378151e-06, "epoch": 0.8088235294117647, "percentage": 4.04, "elapsed_time": "0:00:33", "remaining_time": "0:13:09", "throughput": 3281.19, "total_tokens": 109120} +{"current_steps": 390, "total_steps": 9520, "loss": 2.2613, "lr": 4.0861344537815125e-06, "epoch": 0.819327731092437, "percentage": 4.1, "elapsed_time": "0:00:33", "remaining_time": "0:13:08", "throughput": 3282.48, "total_tokens": 110560} +{"current_steps": 395, "total_steps": 9520, "loss": 2.1994, "lr": 4.138655462184874e-06, "epoch": 0.8298319327731093, "percentage": 4.15, "elapsed_time": "0:00:34", "remaining_time": "0:13:08", "throughput": 3285.2, "total_tokens": 112064} +{"current_steps": 400, "total_steps": 9520, "loss": 1.618, "lr": 4.191176470588236e-06, "epoch": 0.8403361344537815, "percentage": 4.2, "elapsed_time": "0:00:34", "remaining_time": "0:13:07", "throughput": 3285.75, "total_tokens": 113472} +{"current_steps": 405, "total_steps": 9520, "loss": 1.9162, "lr": 4.243697478991597e-06, "epoch": 0.8508403361344538, "percentage": 4.25, "elapsed_time": "0:00:34", "remaining_time": "0:13:06", "throughput": 3287.95, "total_tokens": 114944} +{"current_steps": 410, "total_steps": 9520, "loss": 1.7278, "lr": 4.296218487394958e-06, "epoch": 0.8613445378151261, "percentage": 4.31, "elapsed_time": "0:00:35", "remaining_time": "0:13:06", "throughput": 3288.96, "total_tokens": 116352} +{"current_steps": 415, "total_steps": 9520, "loss": 1.9563, "lr": 4.3487394957983194e-06, "epoch": 0.8718487394957983, "percentage": 4.36, "elapsed_time": "0:00:35", "remaining_time": "0:13:05", "throughput": 3287.76, "total_tokens": 117696} +{"current_steps": 420, "total_steps": 9520, "loss": 1.6436, "lr": 4.401260504201681e-06, "epoch": 0.8823529411764706, "percentage": 4.41, "elapsed_time": "0:00:36", "remaining_time": "0:13:05", "throughput": 3288.13, "total_tokens": 119168} +{"current_steps": 425, "total_steps": 9520, "loss": 1.8651, "lr": 4.453781512605043e-06, "epoch": 0.8928571428571429, "percentage": 4.46, "elapsed_time": "0:00:36", "remaining_time": "0:13:04", "throughput": 3290.42, "total_tokens": 120672} +{"current_steps": 430, "total_steps": 9520, "loss": 1.996, "lr": 4.506302521008404e-06, "epoch": 0.9033613445378151, "percentage": 4.52, "elapsed_time": "0:00:37", "remaining_time": "0:13:04", "throughput": 3289.28, "total_tokens": 122016} +{"current_steps": 435, "total_steps": 9520, "loss": 1.8649, "lr": 4.558823529411765e-06, "epoch": 0.9138655462184874, "percentage": 4.57, "elapsed_time": "0:00:37", "remaining_time": "0:13:03", "throughput": 3289.54, "total_tokens": 123424} +{"current_steps": 440, "total_steps": 9520, "loss": 2.0197, "lr": 4.611344537815126e-06, "epoch": 0.9243697478991597, "percentage": 4.62, "elapsed_time": "0:00:37", "remaining_time": "0:13:02", "throughput": 3290.16, "total_tokens": 124832} +{"current_steps": 445, "total_steps": 9520, "loss": 1.8274, "lr": 4.663865546218488e-06, "epoch": 0.9348739495798319, "percentage": 4.67, "elapsed_time": "0:00:38", "remaining_time": "0:13:02", "throughput": 3292.03, "total_tokens": 126304} +{"current_steps": 450, "total_steps": 9520, "loss": 1.792, "lr": 4.716386554621849e-06, "epoch": 0.9453781512605042, "percentage": 4.73, "elapsed_time": "0:00:38", "remaining_time": "0:13:01", "throughput": 3293.48, "total_tokens": 127776} +{"current_steps": 455, "total_steps": 9520, "loss": 1.6047, "lr": 4.768907563025211e-06, "epoch": 0.9558823529411765, "percentage": 4.78, "elapsed_time": "0:00:39", "remaining_time": "0:13:01", "throughput": 3293.5, "total_tokens": 129248} +{"current_steps": 460, "total_steps": 9520, "loss": 1.7637, "lr": 4.821428571428572e-06, "epoch": 0.9663865546218487, "percentage": 4.83, "elapsed_time": "0:00:39", "remaining_time": "0:13:01", "throughput": 3293.73, "total_tokens": 130656} +{"current_steps": 465, "total_steps": 9520, "loss": 1.5361, "lr": 4.873949579831933e-06, "epoch": 0.976890756302521, "percentage": 4.88, "elapsed_time": "0:00:40", "remaining_time": "0:13:00", "throughput": 3295.86, "total_tokens": 132160} +{"current_steps": 470, "total_steps": 9520, "loss": 1.2235, "lr": 4.9264705882352945e-06, "epoch": 0.9873949579831933, "percentage": 4.94, "elapsed_time": "0:00:40", "remaining_time": "0:13:00", "throughput": 3296.74, "total_tokens": 133600} +{"current_steps": 475, "total_steps": 9520, "loss": 1.4573, "lr": 4.978991596638656e-06, "epoch": 0.9978991596638656, "percentage": 4.99, "elapsed_time": "0:00:40", "remaining_time": "0:13:00", "throughput": 3298.97, "total_tokens": 135200} +{"current_steps": 480, "total_steps": 9520, "loss": 1.5381, "lr": 5.031512605042017e-06, "epoch": 1.0084033613445378, "percentage": 5.04, "elapsed_time": "0:00:41", "remaining_time": "0:13:01", "throughput": 3289.27, "total_tokens": 136488} +{"current_steps": 485, "total_steps": 9520, "loss": 1.341, "lr": 5.084033613445378e-06, "epoch": 1.01890756302521, "percentage": 5.09, "elapsed_time": "0:00:41", "remaining_time": "0:13:00", "throughput": 3289.21, "total_tokens": 137896} +{"current_steps": 490, "total_steps": 9520, "loss": 1.7435, "lr": 5.136554621848739e-06, "epoch": 1.0294117647058822, "percentage": 5.15, "elapsed_time": "0:00:42", "remaining_time": "0:13:00", "throughput": 3289.39, "total_tokens": 139400} +{"current_steps": 495, "total_steps": 9520, "loss": 1.0458, "lr": 5.1890756302521015e-06, "epoch": 1.0399159663865547, "percentage": 5.2, "elapsed_time": "0:00:42", "remaining_time": "0:13:00", "throughput": 3288.24, "total_tokens": 140712} +{"current_steps": 500, "total_steps": 9520, "loss": 1.4993, "lr": 5.241596638655463e-06, "epoch": 1.050420168067227, "percentage": 5.25, "elapsed_time": "0:00:43", "remaining_time": "0:12:59", "throughput": 3287.12, "total_tokens": 142024} +{"current_steps": 505, "total_steps": 9520, "loss": 1.2277, "lr": 5.294117647058824e-06, "epoch": 1.0609243697478992, "percentage": 5.3, "elapsed_time": "0:00:43", "remaining_time": "0:12:59", "throughput": 3286.76, "total_tokens": 143432} +{"current_steps": 510, "total_steps": 9520, "loss": 1.7111, "lr": 5.346638655462185e-06, "epoch": 1.0714285714285714, "percentage": 5.36, "elapsed_time": "0:00:44", "remaining_time": "0:12:58", "throughput": 3288.75, "total_tokens": 144968} +{"current_steps": 515, "total_steps": 9520, "loss": 1.3116, "lr": 5.399159663865546e-06, "epoch": 1.0819327731092436, "percentage": 5.41, "elapsed_time": "0:00:44", "remaining_time": "0:12:59", "throughput": 3291.83, "total_tokens": 146696} +{"current_steps": 520, "total_steps": 9520, "loss": 1.2399, "lr": 5.4516806722689076e-06, "epoch": 1.092436974789916, "percentage": 5.46, "elapsed_time": "0:00:44", "remaining_time": "0:12:58", "throughput": 3293.43, "total_tokens": 148200} +{"current_steps": 525, "total_steps": 9520, "loss": 1.5416, "lr": 5.50420168067227e-06, "epoch": 1.1029411764705883, "percentage": 5.51, "elapsed_time": "0:00:45", "remaining_time": "0:12:58", "throughput": 3292.03, "total_tokens": 149512} +{"current_steps": 530, "total_steps": 9520, "loss": 1.5101, "lr": 5.556722689075631e-06, "epoch": 1.1134453781512605, "percentage": 5.57, "elapsed_time": "0:00:45", "remaining_time": "0:12:57", "throughput": 3291.52, "total_tokens": 150856} +{"current_steps": 535, "total_steps": 9520, "loss": 1.3363, "lr": 5.609243697478992e-06, "epoch": 1.1239495798319328, "percentage": 5.62, "elapsed_time": "0:00:46", "remaining_time": "0:12:56", "throughput": 3292.6, "total_tokens": 152296} +{"current_steps": 540, "total_steps": 9520, "loss": 1.2832, "lr": 5.661764705882353e-06, "epoch": 1.134453781512605, "percentage": 5.67, "elapsed_time": "0:00:46", "remaining_time": "0:12:56", "throughput": 3292.62, "total_tokens": 153672} +{"current_steps": 545, "total_steps": 9520, "loss": 1.5613, "lr": 5.7142857142857145e-06, "epoch": 1.1449579831932772, "percentage": 5.72, "elapsed_time": "0:00:47", "remaining_time": "0:12:55", "throughput": 3293.11, "total_tokens": 155080} +{"current_steps": 550, "total_steps": 9520, "loss": 1.3824, "lr": 5.766806722689076e-06, "epoch": 1.1554621848739495, "percentage": 5.78, "elapsed_time": "0:00:47", "remaining_time": "0:12:55", "throughput": 3293.78, "total_tokens": 156520} +{"current_steps": 555, "total_steps": 9520, "loss": 1.1673, "lr": 5.819327731092438e-06, "epoch": 1.165966386554622, "percentage": 5.83, "elapsed_time": "0:00:47", "remaining_time": "0:12:54", "throughput": 3292.77, "total_tokens": 157832} +{"current_steps": 560, "total_steps": 9520, "loss": 1.1921, "lr": 5.871848739495799e-06, "epoch": 1.1764705882352942, "percentage": 5.88, "elapsed_time": "0:00:48", "remaining_time": "0:12:54", "throughput": 3292.33, "total_tokens": 159272} +{"current_steps": 565, "total_steps": 9520, "loss": 1.3374, "lr": 5.92436974789916e-06, "epoch": 1.1869747899159664, "percentage": 5.93, "elapsed_time": "0:00:48", "remaining_time": "0:12:53", "throughput": 3293.17, "total_tokens": 160712} +{"current_steps": 570, "total_steps": 9520, "loss": 0.9436, "lr": 5.9768907563025215e-06, "epoch": 1.1974789915966386, "percentage": 5.99, "elapsed_time": "0:00:49", "remaining_time": "0:12:53", "throughput": 3295.48, "total_tokens": 162248} +{"current_steps": 575, "total_steps": 9520, "loss": 1.3086, "lr": 6.029411764705883e-06, "epoch": 1.2079831932773109, "percentage": 6.04, "elapsed_time": "0:00:49", "remaining_time": "0:12:52", "throughput": 3298.34, "total_tokens": 163816} +{"current_steps": 580, "total_steps": 9520, "loss": 1.5598, "lr": 6.081932773109244e-06, "epoch": 1.2184873949579833, "percentage": 6.09, "elapsed_time": "0:00:50", "remaining_time": "0:12:52", "throughput": 3298.11, "total_tokens": 165192} +{"current_steps": 585, "total_steps": 9520, "loss": 0.8155, "lr": 6.134453781512606e-06, "epoch": 1.2289915966386555, "percentage": 6.14, "elapsed_time": "0:00:50", "remaining_time": "0:12:51", "throughput": 3295.53, "total_tokens": 166408} +{"current_steps": 590, "total_steps": 9520, "loss": 1.2001, "lr": 6.186974789915967e-06, "epoch": 1.2394957983193278, "percentage": 6.2, "elapsed_time": "0:00:50", "remaining_time": "0:12:50", "throughput": 3295.53, "total_tokens": 167784} +{"current_steps": 595, "total_steps": 9520, "loss": 0.9491, "lr": 6.239495798319328e-06, "epoch": 1.25, "percentage": 6.25, "elapsed_time": "0:00:51", "remaining_time": "0:12:50", "throughput": 3296.43, "total_tokens": 169224} +{"current_steps": 600, "total_steps": 9520, "loss": 1.1442, "lr": 6.29201680672269e-06, "epoch": 1.2605042016806722, "percentage": 6.3, "elapsed_time": "0:00:51", "remaining_time": "0:12:49", "throughput": 3295.54, "total_tokens": 170504} +{"current_steps": 605, "total_steps": 9520, "loss": 1.6317, "lr": 6.344537815126051e-06, "epoch": 1.2710084033613445, "percentage": 6.36, "elapsed_time": "0:00:52", "remaining_time": "0:12:48", "throughput": 3294.34, "total_tokens": 171784} +{"current_steps": 610, "total_steps": 9520, "loss": 1.103, "lr": 6.397058823529412e-06, "epoch": 1.2815126050420167, "percentage": 6.41, "elapsed_time": "0:00:52", "remaining_time": "0:12:47", "throughput": 3294.79, "total_tokens": 173224} +{"current_steps": 615, "total_steps": 9520, "loss": 1.129, "lr": 6.449579831932774e-06, "epoch": 1.2920168067226891, "percentage": 6.46, "elapsed_time": "0:00:53", "remaining_time": "0:12:47", "throughput": 3294.74, "total_tokens": 174632} +{"current_steps": 620, "total_steps": 9520, "loss": 0.9868, "lr": 6.502100840336135e-06, "epoch": 1.3025210084033614, "percentage": 6.51, "elapsed_time": "0:00:53", "remaining_time": "0:12:47", "throughput": 3295.2, "total_tokens": 176072} +{"current_steps": 625, "total_steps": 9520, "loss": 1.2901, "lr": 6.5546218487394966e-06, "epoch": 1.3130252100840336, "percentage": 6.57, "elapsed_time": "0:00:53", "remaining_time": "0:12:46", "throughput": 3293.38, "total_tokens": 177320} +{"current_steps": 630, "total_steps": 9520, "loss": 1.2166, "lr": 6.607142857142858e-06, "epoch": 1.3235294117647058, "percentage": 6.62, "elapsed_time": "0:00:54", "remaining_time": "0:12:45", "throughput": 3292.62, "total_tokens": 178664} +{"current_steps": 635, "total_steps": 9520, "loss": 0.7785, "lr": 6.659663865546219e-06, "epoch": 1.334033613445378, "percentage": 6.67, "elapsed_time": "0:00:54", "remaining_time": "0:12:45", "throughput": 3295.81, "total_tokens": 180360} +{"current_steps": 640, "total_steps": 9520, "loss": 1.2956, "lr": 6.71218487394958e-06, "epoch": 1.3445378151260505, "percentage": 6.72, "elapsed_time": "0:00:55", "remaining_time": "0:12:45", "throughput": 3297.64, "total_tokens": 181864} +{"current_steps": 645, "total_steps": 9520, "loss": 1.2056, "lr": 6.764705882352942e-06, "epoch": 1.3550420168067228, "percentage": 6.78, "elapsed_time": "0:00:55", "remaining_time": "0:12:44", "throughput": 3296.24, "total_tokens": 183144} +{"current_steps": 650, "total_steps": 9520, "loss": 0.7986, "lr": 6.8172268907563035e-06, "epoch": 1.365546218487395, "percentage": 6.83, "elapsed_time": "0:00:55", "remaining_time": "0:12:44", "throughput": 3298.58, "total_tokens": 184712} +{"current_steps": 655, "total_steps": 9520, "loss": 0.7387, "lr": 6.869747899159665e-06, "epoch": 1.3760504201680672, "percentage": 6.88, "elapsed_time": "0:00:56", "remaining_time": "0:12:43", "throughput": 3298.64, "total_tokens": 186120} +{"current_steps": 660, "total_steps": 9520, "loss": 0.846, "lr": 6.922268907563026e-06, "epoch": 1.3865546218487395, "percentage": 6.93, "elapsed_time": "0:00:56", "remaining_time": "0:12:42", "throughput": 3298.37, "total_tokens": 187464} +{"current_steps": 665, "total_steps": 9520, "loss": 0.8016, "lr": 6.974789915966387e-06, "epoch": 1.3970588235294117, "percentage": 6.99, "elapsed_time": "0:00:57", "remaining_time": "0:12:42", "throughput": 3299.5, "total_tokens": 188936} +{"current_steps": 670, "total_steps": 9520, "loss": 1.0967, "lr": 7.0273109243697475e-06, "epoch": 1.407563025210084, "percentage": 7.04, "elapsed_time": "0:00:57", "remaining_time": "0:12:41", "throughput": 3300.72, "total_tokens": 190408} +{"current_steps": 675, "total_steps": 9520, "loss": 0.9259, "lr": 7.0798319327731104e-06, "epoch": 1.4180672268907564, "percentage": 7.09, "elapsed_time": "0:00:58", "remaining_time": "0:12:41", "throughput": 3301.79, "total_tokens": 191912} +{"current_steps": 680, "total_steps": 9520, "loss": 1.0579, "lr": 7.132352941176472e-06, "epoch": 1.4285714285714286, "percentage": 7.14, "elapsed_time": "0:00:58", "remaining_time": "0:12:41", "throughput": 3302.76, "total_tokens": 193352} +{"current_steps": 685, "total_steps": 9520, "loss": 0.9628, "lr": 7.184873949579833e-06, "epoch": 1.4390756302521008, "percentage": 7.2, "elapsed_time": "0:00:58", "remaining_time": "0:12:40", "throughput": 3301.55, "total_tokens": 194632} +{"current_steps": 690, "total_steps": 9520, "loss": 1.1046, "lr": 7.237394957983194e-06, "epoch": 1.449579831932773, "percentage": 7.25, "elapsed_time": "0:00:59", "remaining_time": "0:12:39", "throughput": 3301.36, "total_tokens": 195976} +{"current_steps": 695, "total_steps": 9520, "loss": 1.0682, "lr": 7.2899159663865545e-06, "epoch": 1.4600840336134453, "percentage": 7.3, "elapsed_time": "0:00:59", "remaining_time": "0:12:39", "throughput": 3302.34, "total_tokens": 197448} +{"current_steps": 700, "total_steps": 9520, "loss": 0.8293, "lr": 7.342436974789916e-06, "epoch": 1.4705882352941178, "percentage": 7.35, "elapsed_time": "0:01:00", "remaining_time": "0:12:38", "throughput": 3303.42, "total_tokens": 198920} +{"current_steps": 705, "total_steps": 9520, "loss": 1.2898, "lr": 7.394957983193279e-06, "epoch": 1.48109243697479, "percentage": 7.41, "elapsed_time": "0:01:00", "remaining_time": "0:12:37", "throughput": 3301.02, "total_tokens": 200104} +{"current_steps": 710, "total_steps": 9520, "loss": 1.115, "lr": 7.44747899159664e-06, "epoch": 1.4915966386554622, "percentage": 7.46, "elapsed_time": "0:01:01", "remaining_time": "0:12:37", "throughput": 3300.35, "total_tokens": 201448} +{"current_steps": 715, "total_steps": 9520, "loss": 1.0378, "lr": 7.500000000000001e-06, "epoch": 1.5021008403361344, "percentage": 7.51, "elapsed_time": "0:01:01", "remaining_time": "0:12:37", "throughput": 3302.06, "total_tokens": 202984} +{"current_steps": 720, "total_steps": 9520, "loss": 0.7563, "lr": 7.552521008403361e-06, "epoch": 1.5126050420168067, "percentage": 7.56, "elapsed_time": "0:01:01", "remaining_time": "0:12:36", "throughput": 3303.02, "total_tokens": 204488} +{"current_steps": 725, "total_steps": 9520, "loss": 0.6461, "lr": 7.605042016806723e-06, "epoch": 1.523109243697479, "percentage": 7.62, "elapsed_time": "0:01:02", "remaining_time": "0:12:36", "throughput": 3304.19, "total_tokens": 205992} +{"current_steps": 730, "total_steps": 9520, "loss": 0.7846, "lr": 7.657563025210086e-06, "epoch": 1.5336134453781511, "percentage": 7.67, "elapsed_time": "0:01:02", "remaining_time": "0:12:35", "throughput": 3305.24, "total_tokens": 207464} +{"current_steps": 735, "total_steps": 9520, "loss": 1.1403, "lr": 7.710084033613446e-06, "epoch": 1.5441176470588234, "percentage": 7.72, "elapsed_time": "0:01:03", "remaining_time": "0:12:35", "throughput": 3304.31, "total_tokens": 208776} +{"current_steps": 740, "total_steps": 9520, "loss": 1.0664, "lr": 7.762605042016808e-06, "epoch": 1.5546218487394958, "percentage": 7.77, "elapsed_time": "0:01:03", "remaining_time": "0:12:34", "throughput": 3304.68, "total_tokens": 210216} +{"current_steps": 745, "total_steps": 9520, "loss": 1.0257, "lr": 7.815126050420168e-06, "epoch": 1.565126050420168, "percentage": 7.83, "elapsed_time": "0:01:04", "remaining_time": "0:12:34", "throughput": 3305.74, "total_tokens": 211784} +{"current_steps": 750, "total_steps": 9520, "loss": 1.0869, "lr": 7.86764705882353e-06, "epoch": 1.5756302521008403, "percentage": 7.88, "elapsed_time": "0:01:04", "remaining_time": "0:12:34", "throughput": 3305.22, "total_tokens": 213128} +{"current_steps": 755, "total_steps": 9520, "loss": 0.8459, "lr": 7.92016806722689e-06, "epoch": 1.5861344537815127, "percentage": 7.93, "elapsed_time": "0:01:04", "remaining_time": "0:12:33", "throughput": 3305.29, "total_tokens": 214632} +{"current_steps": 760, "total_steps": 9520, "loss": 0.9526, "lr": 7.972689075630253e-06, "epoch": 1.596638655462185, "percentage": 7.98, "elapsed_time": "0:01:05", "remaining_time": "0:12:33", "throughput": 3308.11, "total_tokens": 216264} +{"current_steps": 765, "total_steps": 9520, "loss": 0.7956, "lr": 8.025210084033615e-06, "epoch": 1.6071428571428572, "percentage": 8.04, "elapsed_time": "0:01:05", "remaining_time": "0:12:33", "throughput": 3308.12, "total_tokens": 217768} +{"current_steps": 770, "total_steps": 9520, "loss": 1.0577, "lr": 8.077731092436975e-06, "epoch": 1.6176470588235294, "percentage": 8.09, "elapsed_time": "0:01:06", "remaining_time": "0:12:33", "throughput": 3308.48, "total_tokens": 219304} +{"current_steps": 775, "total_steps": 9520, "loss": 1.2273, "lr": 8.130252100840337e-06, "epoch": 1.6281512605042017, "percentage": 8.14, "elapsed_time": "0:01:06", "remaining_time": "0:12:32", "throughput": 3308.78, "total_tokens": 220744} +{"current_steps": 780, "total_steps": 9520, "loss": 1.0537, "lr": 8.182773109243698e-06, "epoch": 1.638655462184874, "percentage": 8.19, "elapsed_time": "0:01:07", "remaining_time": "0:12:32", "throughput": 3307.91, "total_tokens": 222152} +{"current_steps": 785, "total_steps": 9520, "loss": 1.0563, "lr": 8.23529411764706e-06, "epoch": 1.6491596638655461, "percentage": 8.25, "elapsed_time": "0:01:07", "remaining_time": "0:12:31", "throughput": 3308.23, "total_tokens": 223560} +{"current_steps": 790, "total_steps": 9520, "loss": 0.8504, "lr": 8.287815126050422e-06, "epoch": 1.6596638655462184, "percentage": 8.3, "elapsed_time": "0:01:08", "remaining_time": "0:12:31", "throughput": 3309.46, "total_tokens": 225064} +{"current_steps": 795, "total_steps": 9520, "loss": 0.9866, "lr": 8.340336134453782e-06, "epoch": 1.6701680672268906, "percentage": 8.35, "elapsed_time": "0:01:08", "remaining_time": "0:12:30", "throughput": 3308.62, "total_tokens": 226376} +{"current_steps": 800, "total_steps": 9520, "loss": 0.8524, "lr": 8.392857142857144e-06, "epoch": 1.680672268907563, "percentage": 8.4, "elapsed_time": "0:01:08", "remaining_time": "0:12:30", "throughput": 3309.4, "total_tokens": 227912} +{"current_steps": 805, "total_steps": 9520, "loss": 0.7794, "lr": 8.445378151260505e-06, "epoch": 1.6911764705882353, "percentage": 8.46, "elapsed_time": "0:01:09", "remaining_time": "0:12:30", "throughput": 3308.8, "total_tokens": 229256} +{"current_steps": 810, "total_steps": 9520, "loss": 0.7698, "lr": 8.497899159663867e-06, "epoch": 1.7016806722689075, "percentage": 8.51, "elapsed_time": "0:01:09", "remaining_time": "0:12:29", "throughput": 3309.27, "total_tokens": 230728} +{"current_steps": 815, "total_steps": 9520, "loss": 1.0511, "lr": 8.550420168067227e-06, "epoch": 1.71218487394958, "percentage": 8.56, "elapsed_time": "0:01:10", "remaining_time": "0:12:29", "throughput": 3308.77, "total_tokens": 232072} +{"current_steps": 820, "total_steps": 9520, "loss": 0.7867, "lr": 8.60294117647059e-06, "epoch": 1.7226890756302522, "percentage": 8.61, "elapsed_time": "0:01:10", "remaining_time": "0:12:29", "throughput": 3309.09, "total_tokens": 233608} +{"current_steps": 825, "total_steps": 9520, "loss": 0.7483, "lr": 8.655462184873951e-06, "epoch": 1.7331932773109244, "percentage": 8.67, "elapsed_time": "0:01:11", "remaining_time": "0:12:28", "throughput": 3310.07, "total_tokens": 235080} +{"current_steps": 830, "total_steps": 9520, "loss": 1.1374, "lr": 8.707983193277312e-06, "epoch": 1.7436974789915967, "percentage": 8.72, "elapsed_time": "0:01:11", "remaining_time": "0:12:28", "throughput": 3309.7, "total_tokens": 236456} +{"current_steps": 835, "total_steps": 9520, "loss": 0.915, "lr": 8.760504201680674e-06, "epoch": 1.754201680672269, "percentage": 8.77, "elapsed_time": "0:01:11", "remaining_time": "0:12:27", "throughput": 3310.59, "total_tokens": 237928} +{"current_steps": 840, "total_steps": 9520, "loss": 0.8464, "lr": 8.813025210084034e-06, "epoch": 1.7647058823529411, "percentage": 8.82, "elapsed_time": "0:01:12", "remaining_time": "0:12:27", "throughput": 3312.45, "total_tokens": 239496} +{"current_steps": 845, "total_steps": 9520, "loss": 0.6857, "lr": 8.865546218487396e-06, "epoch": 1.7752100840336134, "percentage": 8.88, "elapsed_time": "0:01:12", "remaining_time": "0:12:26", "throughput": 3310.55, "total_tokens": 240680} +{"current_steps": 850, "total_steps": 9520, "loss": 0.836, "lr": 8.918067226890758e-06, "epoch": 1.7857142857142856, "percentage": 8.93, "elapsed_time": "0:01:13", "remaining_time": "0:12:25", "throughput": 3309.25, "total_tokens": 241928} +{"current_steps": 855, "total_steps": 9520, "loss": 0.6141, "lr": 8.970588235294119e-06, "epoch": 1.7962184873949578, "percentage": 8.98, "elapsed_time": "0:01:13", "remaining_time": "0:12:25", "throughput": 3311.26, "total_tokens": 243528} +{"current_steps": 860, "total_steps": 9520, "loss": 0.8642, "lr": 9.02310924369748e-06, "epoch": 1.8067226890756303, "percentage": 9.03, "elapsed_time": "0:01:13", "remaining_time": "0:12:24", "throughput": 3310.27, "total_tokens": 244808} +{"current_steps": 865, "total_steps": 9520, "loss": 1.0107, "lr": 9.075630252100841e-06, "epoch": 1.8172268907563025, "percentage": 9.09, "elapsed_time": "0:01:14", "remaining_time": "0:12:24", "throughput": 3310.7, "total_tokens": 246280} +{"current_steps": 870, "total_steps": 9520, "loss": 1.007, "lr": 9.128151260504201e-06, "epoch": 1.8277310924369747, "percentage": 9.14, "elapsed_time": "0:01:14", "remaining_time": "0:12:23", "throughput": 3312.6, "total_tokens": 247880} +{"current_steps": 875, "total_steps": 9520, "loss": 0.8465, "lr": 9.180672268907563e-06, "epoch": 1.8382352941176472, "percentage": 9.19, "elapsed_time": "0:01:15", "remaining_time": "0:12:23", "throughput": 3313.88, "total_tokens": 249384} +{"current_steps": 880, "total_steps": 9520, "loss": 0.5949, "lr": 9.233193277310925e-06, "epoch": 1.8487394957983194, "percentage": 9.24, "elapsed_time": "0:01:15", "remaining_time": "0:12:23", "throughput": 3315.67, "total_tokens": 251080} +{"current_steps": 885, "total_steps": 9520, "loss": 0.9508, "lr": 9.285714285714288e-06, "epoch": 1.8592436974789917, "percentage": 9.3, "elapsed_time": "0:01:16", "remaining_time": "0:12:22", "throughput": 3313.67, "total_tokens": 252264} +{"current_steps": 890, "total_steps": 9520, "loss": 0.8137, "lr": 9.338235294117648e-06, "epoch": 1.8697478991596639, "percentage": 9.35, "elapsed_time": "0:01:16", "remaining_time": "0:12:22", "throughput": 3312.71, "total_tokens": 253544} +{"current_steps": 895, "total_steps": 9520, "loss": 0.693, "lr": 9.390756302521008e-06, "epoch": 1.8802521008403361, "percentage": 9.4, "elapsed_time": "0:01:16", "remaining_time": "0:12:21", "throughput": 3312.87, "total_tokens": 254952} +{"current_steps": 900, "total_steps": 9520, "loss": 0.9885, "lr": 9.44327731092437e-06, "epoch": 1.8907563025210083, "percentage": 9.45, "elapsed_time": "0:01:17", "remaining_time": "0:12:21", "throughput": 3313.18, "total_tokens": 256392} +{"current_steps": 905, "total_steps": 9520, "loss": 0.8788, "lr": 9.49579831932773e-06, "epoch": 1.9012605042016806, "percentage": 9.51, "elapsed_time": "0:01:17", "remaining_time": "0:12:20", "throughput": 3313.31, "total_tokens": 257800} +{"current_steps": 910, "total_steps": 9520, "loss": 0.7795, "lr": 9.548319327731095e-06, "epoch": 1.9117647058823528, "percentage": 9.56, "elapsed_time": "0:01:18", "remaining_time": "0:12:20", "throughput": 3315.83, "total_tokens": 259464} +{"current_steps": 915, "total_steps": 9520, "loss": 0.8074, "lr": 9.600840336134455e-06, "epoch": 1.9222689075630253, "percentage": 9.61, "elapsed_time": "0:01:18", "remaining_time": "0:12:19", "throughput": 3315.09, "total_tokens": 260776} +{"current_steps": 920, "total_steps": 9520, "loss": 1.147, "lr": 9.653361344537815e-06, "epoch": 1.9327731092436975, "percentage": 9.66, "elapsed_time": "0:01:19", "remaining_time": "0:12:19", "throughput": 3315.37, "total_tokens": 262184} +{"current_steps": 925, "total_steps": 9520, "loss": 0.8055, "lr": 9.705882352941177e-06, "epoch": 1.9432773109243697, "percentage": 9.72, "elapsed_time": "0:01:19", "remaining_time": "0:12:18", "throughput": 3315.19, "total_tokens": 263656} +{"current_steps": 930, "total_steps": 9520, "loss": 0.8621, "lr": 9.758403361344538e-06, "epoch": 1.9537815126050422, "percentage": 9.77, "elapsed_time": "0:01:19", "remaining_time": "0:12:18", "throughput": 3315.03, "total_tokens": 265000} +{"current_steps": 935, "total_steps": 9520, "loss": 0.9219, "lr": 9.8109243697479e-06, "epoch": 1.9642857142857144, "percentage": 9.82, "elapsed_time": "0:01:20", "remaining_time": "0:12:17", "throughput": 3315.01, "total_tokens": 266376} +{"current_steps": 940, "total_steps": 9520, "loss": 0.8703, "lr": 9.863445378151262e-06, "epoch": 1.9747899159663866, "percentage": 9.87, "elapsed_time": "0:01:20", "remaining_time": "0:12:17", "throughput": 3315.08, "total_tokens": 267784} +{"current_steps": 945, "total_steps": 9520, "loss": 0.9329, "lr": 9.915966386554622e-06, "epoch": 1.9852941176470589, "percentage": 9.93, "elapsed_time": "0:01:21", "remaining_time": "0:12:16", "throughput": 3316.5, "total_tokens": 269352} +{"current_steps": 950, "total_steps": 9520, "loss": 0.7178, "lr": 9.968487394957984e-06, "epoch": 1.995798319327731, "percentage": 9.98, "elapsed_time": "0:01:21", "remaining_time": "0:12:16", "throughput": 3317.32, "total_tokens": 270824} +{"current_steps": 952, "total_steps": 9520, "eval_loss": 0.8225295543670654, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:01:26", "remaining_time": "0:12:58", "throughput": 3135.58, "total_tokens": 271336} +{"current_steps": 955, "total_steps": 9520, "loss": 0.7912, "lr": 9.999998655561904e-06, "epoch": 2.0063025210084033, "percentage": 10.03, "elapsed_time": "0:01:28", "remaining_time": "0:13:10", "throughput": 3089.97, "total_tokens": 272232} +{"current_steps": 960, "total_steps": 9520, "loss": 0.7381, "lr": 9.999983530641623e-06, "epoch": 2.0168067226890756, "percentage": 10.08, "elapsed_time": "0:01:28", "remaining_time": "0:13:09", "throughput": 3091.45, "total_tokens": 273768} +{"current_steps": 965, "total_steps": 9520, "loss": 0.6616, "lr": 9.999951600304445e-06, "epoch": 2.027310924369748, "percentage": 10.14, "elapsed_time": "0:01:28", "remaining_time": "0:13:08", "throughput": 3092.36, "total_tokens": 275144} +{"current_steps": 970, "total_steps": 9520, "loss": 0.5863, "lr": 9.999902864657691e-06, "epoch": 2.03781512605042, "percentage": 10.19, "elapsed_time": "0:01:29", "remaining_time": "0:13:08", "throughput": 3093.15, "total_tokens": 276616} +{"current_steps": 975, "total_steps": 9520, "loss": 0.8854, "lr": 9.99983732386517e-06, "epoch": 2.0483193277310923, "percentage": 10.24, "elapsed_time": "0:01:29", "remaining_time": "0:13:07", "throughput": 3093.22, "total_tokens": 277928} +{"current_steps": 980, "total_steps": 9520, "loss": 0.9939, "lr": 9.999754978147162e-06, "epoch": 2.0588235294117645, "percentage": 10.29, "elapsed_time": "0:01:30", "remaining_time": "0:13:06", "throughput": 3094.6, "total_tokens": 279400} +{"current_steps": 985, "total_steps": 9520, "loss": 0.8543, "lr": 9.999655827780448e-06, "epoch": 2.069327731092437, "percentage": 10.35, "elapsed_time": "0:01:30", "remaining_time": "0:13:06", "throughput": 3095.77, "total_tokens": 280840} +{"current_steps": 990, "total_steps": 9520, "loss": 0.6364, "lr": 9.999539873098279e-06, "epoch": 2.0798319327731094, "percentage": 10.4, "elapsed_time": "0:01:31", "remaining_time": "0:13:05", "throughput": 3097.28, "total_tokens": 282312} +{"current_steps": 995, "total_steps": 9520, "loss": 0.8392, "lr": 9.999407114490384e-06, "epoch": 2.0903361344537816, "percentage": 10.45, "elapsed_time": "0:01:31", "remaining_time": "0:13:04", "throughput": 3097.36, "total_tokens": 283592} +{"current_steps": 1000, "total_steps": 9520, "loss": 0.7416, "lr": 9.999257552402986e-06, "epoch": 2.100840336134454, "percentage": 10.5, "elapsed_time": "0:01:32", "remaining_time": "0:13:04", "throughput": 3099.72, "total_tokens": 285256} +{"current_steps": 1005, "total_steps": 9520, "loss": 0.8704, "lr": 9.999091187338773e-06, "epoch": 2.111344537815126, "percentage": 10.56, "elapsed_time": "0:01:32", "remaining_time": "0:13:03", "throughput": 3101.62, "total_tokens": 286760} +{"current_steps": 1010, "total_steps": 9520, "loss": 0.7469, "lr": 9.99890801985691e-06, "epoch": 2.1218487394957983, "percentage": 10.61, "elapsed_time": "0:01:32", "remaining_time": "0:13:02", "throughput": 3103.34, "total_tokens": 288264} +{"current_steps": 1015, "total_steps": 9520, "loss": 0.8542, "lr": 9.998708050573047e-06, "epoch": 2.1323529411764706, "percentage": 10.66, "elapsed_time": "0:01:33", "remaining_time": "0:13:01", "throughput": 3103.47, "total_tokens": 289576} +{"current_steps": 1020, "total_steps": 9520, "loss": 0.659, "lr": 9.998491280159298e-06, "epoch": 2.142857142857143, "percentage": 10.71, "elapsed_time": "0:01:33", "remaining_time": "0:13:01", "throughput": 3104.74, "total_tokens": 291016} +{"current_steps": 1025, "total_steps": 9520, "loss": 0.6269, "lr": 9.998257709344246e-06, "epoch": 2.153361344537815, "percentage": 10.77, "elapsed_time": "0:01:34", "remaining_time": "0:13:00", "throughput": 3105.63, "total_tokens": 292456} +{"current_steps": 1030, "total_steps": 9520, "loss": 0.6126, "lr": 9.998007338912945e-06, "epoch": 2.1638655462184873, "percentage": 10.82, "elapsed_time": "0:01:34", "remaining_time": "0:12:59", "throughput": 3107.47, "total_tokens": 293960} +{"current_steps": 1035, "total_steps": 9520, "loss": 0.5465, "lr": 9.997740169706915e-06, "epoch": 2.1743697478991595, "percentage": 10.87, "elapsed_time": "0:01:35", "remaining_time": "0:12:59", "throughput": 3108.68, "total_tokens": 295432} +{"current_steps": 1040, "total_steps": 9520, "loss": 0.9037, "lr": 9.997456202624138e-06, "epoch": 2.184873949579832, "percentage": 10.92, "elapsed_time": "0:01:35", "remaining_time": "0:12:58", "throughput": 3108.9, "total_tokens": 296744} +{"current_steps": 1045, "total_steps": 9520, "loss": 0.7326, "lr": 9.997155438619052e-06, "epoch": 2.1953781512605044, "percentage": 10.98, "elapsed_time": "0:01:35", "remaining_time": "0:12:57", "throughput": 3111.14, "total_tokens": 298408} +{"current_steps": 1050, "total_steps": 9520, "loss": 0.6177, "lr": 9.996837878702554e-06, "epoch": 2.2058823529411766, "percentage": 11.03, "elapsed_time": "0:01:36", "remaining_time": "0:12:57", "throughput": 3112.82, "total_tokens": 299912} +{"current_steps": 1055, "total_steps": 9520, "loss": 0.8846, "lr": 9.996503523941994e-06, "epoch": 2.216386554621849, "percentage": 11.08, "elapsed_time": "0:01:36", "remaining_time": "0:12:56", "throughput": 3112.98, "total_tokens": 301224} +{"current_steps": 1060, "total_steps": 9520, "loss": 0.6859, "lr": 9.996152375461169e-06, "epoch": 2.226890756302521, "percentage": 11.13, "elapsed_time": "0:01:37", "remaining_time": "0:12:55", "throughput": 3114.03, "total_tokens": 302664} +{"current_steps": 1065, "total_steps": 9520, "loss": 0.604, "lr": 9.99578443444032e-06, "epoch": 2.2373949579831933, "percentage": 11.19, "elapsed_time": "0:01:37", "remaining_time": "0:12:55", "throughput": 3115.72, "total_tokens": 304200} +{"current_steps": 1070, "total_steps": 9520, "loss": 0.7814, "lr": 9.995399702116135e-06, "epoch": 2.2478991596638656, "percentage": 11.24, "elapsed_time": "0:01:38", "remaining_time": "0:12:54", "throughput": 3115.99, "total_tokens": 305512} +{"current_steps": 1075, "total_steps": 9520, "loss": 0.6872, "lr": 9.994998179781735e-06, "epoch": 2.258403361344538, "percentage": 11.29, "elapsed_time": "0:01:38", "remaining_time": "0:12:53", "throughput": 3116.02, "total_tokens": 306824} +{"current_steps": 1080, "total_steps": 9520, "loss": 0.83, "lr": 9.994579868786673e-06, "epoch": 2.26890756302521, "percentage": 11.34, "elapsed_time": "0:01:38", "remaining_time": "0:12:52", "throughput": 3117.18, "total_tokens": 308296} +{"current_steps": 1085, "total_steps": 9520, "loss": 0.6883, "lr": 9.994144770536933e-06, "epoch": 2.2794117647058822, "percentage": 11.4, "elapsed_time": "0:01:39", "remaining_time": "0:12:52", "throughput": 3118.5, "total_tokens": 309768} +{"current_steps": 1090, "total_steps": 9520, "loss": 0.6386, "lr": 9.993692886494918e-06, "epoch": 2.2899159663865545, "percentage": 11.45, "elapsed_time": "0:01:39", "remaining_time": "0:12:51", "throughput": 3119.27, "total_tokens": 311176} +{"current_steps": 1095, "total_steps": 9520, "loss": 0.7877, "lr": 9.99322421817946e-06, "epoch": 2.3004201680672267, "percentage": 11.5, "elapsed_time": "0:01:40", "remaining_time": "0:12:50", "throughput": 3120.4, "total_tokens": 312616} +{"current_steps": 1100, "total_steps": 9520, "loss": 0.8653, "lr": 9.992738767165791e-06, "epoch": 2.310924369747899, "percentage": 11.55, "elapsed_time": "0:01:40", "remaining_time": "0:12:50", "throughput": 3120.5, "total_tokens": 313928} +{"current_steps": 1105, "total_steps": 9520, "loss": 0.9052, "lr": 9.992236535085562e-06, "epoch": 2.3214285714285716, "percentage": 11.61, "elapsed_time": "0:01:41", "remaining_time": "0:12:49", "throughput": 3121.28, "total_tokens": 315432} +{"current_steps": 1110, "total_steps": 9520, "loss": 1.1934, "lr": 9.991717523626818e-06, "epoch": 2.331932773109244, "percentage": 11.66, "elapsed_time": "0:01:41", "remaining_time": "0:12:48", "throughput": 3120.63, "total_tokens": 316616} +{"current_steps": 1115, "total_steps": 9520, "loss": 0.876, "lr": 9.99118173453401e-06, "epoch": 2.342436974789916, "percentage": 11.71, "elapsed_time": "0:01:41", "remaining_time": "0:12:48", "throughput": 3122.07, "total_tokens": 318120} +{"current_steps": 1120, "total_steps": 9520, "loss": 0.6402, "lr": 9.990629169607973e-06, "epoch": 2.3529411764705883, "percentage": 11.76, "elapsed_time": "0:01:42", "remaining_time": "0:12:47", "throughput": 3122.44, "total_tokens": 319464} +{"current_steps": 1125, "total_steps": 9520, "loss": 0.9573, "lr": 9.99005983070593e-06, "epoch": 2.3634453781512605, "percentage": 11.82, "elapsed_time": "0:01:42", "remaining_time": "0:12:46", "throughput": 3123.63, "total_tokens": 320936} +{"current_steps": 1130, "total_steps": 9520, "loss": 0.7046, "lr": 9.989473719741484e-06, "epoch": 2.3739495798319328, "percentage": 11.87, "elapsed_time": "0:01:43", "remaining_time": "0:12:45", "throughput": 3124.24, "total_tokens": 322280} +{"current_steps": 1135, "total_steps": 9520, "loss": 0.77, "lr": 9.98887083868461e-06, "epoch": 2.384453781512605, "percentage": 11.92, "elapsed_time": "0:01:43", "remaining_time": "0:12:45", "throughput": 3123.96, "total_tokens": 323528} +{"current_steps": 1140, "total_steps": 9520, "loss": 0.6968, "lr": 9.988251189561645e-06, "epoch": 2.3949579831932772, "percentage": 11.97, "elapsed_time": "0:01:44", "remaining_time": "0:12:44", "throughput": 3125.77, "total_tokens": 325160} +{"current_steps": 1145, "total_steps": 9520, "loss": 0.7069, "lr": 9.98761477445529e-06, "epoch": 2.4054621848739495, "percentage": 12.03, "elapsed_time": "0:01:44", "remaining_time": "0:12:43", "throughput": 3126.48, "total_tokens": 326536} +{"current_steps": 1150, "total_steps": 9520, "loss": 0.8317, "lr": 9.986961595504599e-06, "epoch": 2.4159663865546217, "percentage": 12.08, "elapsed_time": "0:01:44", "remaining_time": "0:12:43", "throughput": 3127.43, "total_tokens": 327976} +{"current_steps": 1155, "total_steps": 9520, "loss": 0.7959, "lr": 9.986291654904963e-06, "epoch": 2.426470588235294, "percentage": 12.13, "elapsed_time": "0:01:45", "remaining_time": "0:12:42", "throughput": 3127.77, "total_tokens": 329320} +{"current_steps": 1160, "total_steps": 9520, "loss": 0.6316, "lr": 9.98560495490812e-06, "epoch": 2.4369747899159666, "percentage": 12.18, "elapsed_time": "0:01:45", "remaining_time": "0:12:41", "throughput": 3127.32, "total_tokens": 330568} +{"current_steps": 1165, "total_steps": 9520, "loss": 1.0333, "lr": 9.984901497822132e-06, "epoch": 2.447478991596639, "percentage": 12.24, "elapsed_time": "0:01:46", "remaining_time": "0:12:41", "throughput": 3128.4, "total_tokens": 332008} +{"current_steps": 1170, "total_steps": 9520, "loss": 0.8512, "lr": 9.984181286011383e-06, "epoch": 2.457983193277311, "percentage": 12.29, "elapsed_time": "0:01:46", "remaining_time": "0:12:40", "throughput": 3129.57, "total_tokens": 333480} +{"current_steps": 1175, "total_steps": 9520, "loss": 0.6767, "lr": 9.983444321896576e-06, "epoch": 2.4684873949579833, "percentage": 12.34, "elapsed_time": "0:01:46", "remaining_time": "0:12:39", "throughput": 3129.76, "total_tokens": 334792} +{"current_steps": 1180, "total_steps": 9520, "loss": 0.6785, "lr": 9.982690607954714e-06, "epoch": 2.4789915966386555, "percentage": 12.39, "elapsed_time": "0:01:47", "remaining_time": "0:12:39", "throughput": 3130.95, "total_tokens": 336264} +{"current_steps": 1185, "total_steps": 9520, "loss": 1.0082, "lr": 9.981920146719101e-06, "epoch": 2.4894957983193278, "percentage": 12.45, "elapsed_time": "0:01:47", "remaining_time": "0:12:38", "throughput": 3130.66, "total_tokens": 337512} +{"current_steps": 1190, "total_steps": 9520, "loss": 1.0516, "lr": 9.981132940779334e-06, "epoch": 2.5, "percentage": 12.5, "elapsed_time": "0:01:48", "remaining_time": "0:12:37", "throughput": 3130.61, "total_tokens": 338792} +{"current_steps": 1195, "total_steps": 9520, "loss": 0.691, "lr": 9.980328992781283e-06, "epoch": 2.5105042016806722, "percentage": 12.55, "elapsed_time": "0:01:48", "remaining_time": "0:12:36", "throughput": 3131.33, "total_tokens": 340200} +{"current_steps": 1200, "total_steps": 9520, "loss": 0.5913, "lr": 9.979508305427094e-06, "epoch": 2.5210084033613445, "percentage": 12.61, "elapsed_time": "0:01:49", "remaining_time": "0:12:36", "throughput": 3132.06, "total_tokens": 341608} +{"current_steps": 1205, "total_steps": 9520, "loss": 0.5374, "lr": 9.978670881475173e-06, "epoch": 2.5315126050420167, "percentage": 12.66, "elapsed_time": "0:01:49", "remaining_time": "0:12:35", "throughput": 3133.38, "total_tokens": 343112} +{"current_steps": 1210, "total_steps": 9520, "loss": 0.7236, "lr": 9.977816723740183e-06, "epoch": 2.542016806722689, "percentage": 12.71, "elapsed_time": "0:01:49", "remaining_time": "0:12:35", "throughput": 3134.28, "total_tokens": 344584} +{"current_steps": 1215, "total_steps": 9520, "loss": 1.0432, "lr": 9.976945835093031e-06, "epoch": 2.552521008403361, "percentage": 12.76, "elapsed_time": "0:01:50", "remaining_time": "0:12:34", "throughput": 3135.52, "total_tokens": 346152} +{"current_steps": 1220, "total_steps": 9520, "loss": 0.5061, "lr": 9.97605821846085e-06, "epoch": 2.5630252100840334, "percentage": 12.82, "elapsed_time": "0:01:50", "remaining_time": "0:12:33", "throughput": 3136.19, "total_tokens": 347560} +{"current_steps": 1225, "total_steps": 9520, "loss": 0.7926, "lr": 9.975153876827008e-06, "epoch": 2.5735294117647056, "percentage": 12.87, "elapsed_time": "0:01:51", "remaining_time": "0:12:33", "throughput": 3137.21, "total_tokens": 349032} +{"current_steps": 1230, "total_steps": 9520, "loss": 0.7142, "lr": 9.974232813231082e-06, "epoch": 2.5840336134453783, "percentage": 12.92, "elapsed_time": "0:01:51", "remaining_time": "0:12:32", "throughput": 3136.61, "total_tokens": 350248} +{"current_steps": 1235, "total_steps": 9520, "loss": 0.465, "lr": 9.97329503076885e-06, "epoch": 2.5945378151260505, "percentage": 12.97, "elapsed_time": "0:01:52", "remaining_time": "0:12:31", "throughput": 3136.61, "total_tokens": 351528} +{"current_steps": 1240, "total_steps": 9520, "loss": 0.8307, "lr": 9.972340532592295e-06, "epoch": 2.6050420168067228, "percentage": 13.03, "elapsed_time": "0:01:52", "remaining_time": "0:12:31", "throughput": 3135.97, "total_tokens": 352712} +{"current_steps": 1245, "total_steps": 9520, "loss": 0.4542, "lr": 9.971369321909567e-06, "epoch": 2.615546218487395, "percentage": 13.08, "elapsed_time": "0:01:52", "remaining_time": "0:12:30", "throughput": 3137.76, "total_tokens": 354280} +{"current_steps": 1250, "total_steps": 9520, "loss": 0.7323, "lr": 9.970381401985003e-06, "epoch": 2.6260504201680672, "percentage": 13.13, "elapsed_time": "0:01:53", "remaining_time": "0:12:29", "throughput": 3138.38, "total_tokens": 355752} +{"current_steps": 1255, "total_steps": 9520, "loss": 0.7884, "lr": 9.969376776139094e-06, "epoch": 2.6365546218487395, "percentage": 13.18, "elapsed_time": "0:01:53", "remaining_time": "0:12:29", "throughput": 3138.71, "total_tokens": 357096} +{"current_steps": 1260, "total_steps": 9520, "loss": 0.6776, "lr": 9.96835544774848e-06, "epoch": 2.6470588235294117, "percentage": 13.24, "elapsed_time": "0:01:54", "remaining_time": "0:12:28", "throughput": 3139.18, "total_tokens": 358472} +{"current_steps": 1265, "total_steps": 9520, "loss": 0.7429, "lr": 9.967317420245944e-06, "epoch": 2.657563025210084, "percentage": 13.29, "elapsed_time": "0:01:54", "remaining_time": "0:12:27", "throughput": 3139.97, "total_tokens": 359912} +{"current_steps": 1270, "total_steps": 9520, "loss": 0.8313, "lr": 9.966262697120393e-06, "epoch": 2.668067226890756, "percentage": 13.34, "elapsed_time": "0:01:55", "remaining_time": "0:12:27", "throughput": 3141.0, "total_tokens": 361352} +{"current_steps": 1275, "total_steps": 9520, "loss": 0.4918, "lr": 9.965191281916852e-06, "epoch": 2.678571428571429, "percentage": 13.39, "elapsed_time": "0:01:55", "remaining_time": "0:12:26", "throughput": 3142.28, "total_tokens": 362856} +{"current_steps": 1280, "total_steps": 9520, "loss": 0.8158, "lr": 9.96410317823645e-06, "epoch": 2.689075630252101, "percentage": 13.45, "elapsed_time": "0:01:55", "remaining_time": "0:12:26", "throughput": 3142.81, "total_tokens": 364328} +{"current_steps": 1285, "total_steps": 9520, "loss": 0.9629, "lr": 9.962998389736407e-06, "epoch": 2.6995798319327733, "percentage": 13.5, "elapsed_time": "0:01:56", "remaining_time": "0:12:25", "throughput": 3143.18, "total_tokens": 365704} +{"current_steps": 1290, "total_steps": 9520, "loss": 0.7716, "lr": 9.961876920130017e-06, "epoch": 2.7100840336134455, "percentage": 13.55, "elapsed_time": "0:01:56", "remaining_time": "0:12:24", "throughput": 3143.85, "total_tokens": 367112} +{"current_steps": 1295, "total_steps": 9520, "loss": 0.7444, "lr": 9.960738773186648e-06, "epoch": 2.7205882352941178, "percentage": 13.6, "elapsed_time": "0:01:57", "remaining_time": "0:12:24", "throughput": 3144.15, "total_tokens": 368456} +{"current_steps": 1300, "total_steps": 9520, "loss": 0.6622, "lr": 9.95958395273172e-06, "epoch": 2.73109243697479, "percentage": 13.66, "elapsed_time": "0:01:57", "remaining_time": "0:12:23", "throughput": 3145.8, "total_tokens": 370120} +{"current_steps": 1305, "total_steps": 9520, "loss": 0.6814, "lr": 9.958412462646691e-06, "epoch": 2.741596638655462, "percentage": 13.71, "elapsed_time": "0:01:58", "remaining_time": "0:12:23", "throughput": 3145.97, "total_tokens": 371432} +{"current_steps": 1310, "total_steps": 9520, "loss": 0.8022, "lr": 9.957224306869053e-06, "epoch": 2.7521008403361344, "percentage": 13.76, "elapsed_time": "0:01:58", "remaining_time": "0:12:22", "throughput": 3145.38, "total_tokens": 372648} +{"current_steps": 1315, "total_steps": 9520, "loss": 0.6509, "lr": 9.956019489392307e-06, "epoch": 2.7626050420168067, "percentage": 13.81, "elapsed_time": "0:01:58", "remaining_time": "0:12:21", "throughput": 3146.35, "total_tokens": 374120} +{"current_steps": 1320, "total_steps": 9520, "loss": 0.7939, "lr": 9.954798014265962e-06, "epoch": 2.773109243697479, "percentage": 13.87, "elapsed_time": "0:01:59", "remaining_time": "0:12:21", "throughput": 3146.66, "total_tokens": 375464} +{"current_steps": 1325, "total_steps": 9520, "loss": 0.7633, "lr": 9.953559885595508e-06, "epoch": 2.783613445378151, "percentage": 13.92, "elapsed_time": "0:01:59", "remaining_time": "0:12:20", "throughput": 3148.15, "total_tokens": 377000} +{"current_steps": 1330, "total_steps": 9520, "loss": 0.6867, "lr": 9.952305107542413e-06, "epoch": 2.7941176470588234, "percentage": 13.97, "elapsed_time": "0:02:00", "remaining_time": "0:12:20", "throughput": 3149.69, "total_tokens": 378536} +{"current_steps": 1335, "total_steps": 9520, "loss": 0.5498, "lr": 9.951033684324105e-06, "epoch": 2.8046218487394956, "percentage": 14.02, "elapsed_time": "0:02:00", "remaining_time": "0:12:19", "throughput": 3151.16, "total_tokens": 380072} +{"current_steps": 1340, "total_steps": 9520, "loss": 0.5406, "lr": 9.949745620213959e-06, "epoch": 2.815126050420168, "percentage": 14.08, "elapsed_time": "0:02:01", "remaining_time": "0:12:18", "throughput": 3151.49, "total_tokens": 381448} +{"current_steps": 1345, "total_steps": 9520, "loss": 0.7152, "lr": 9.948440919541277e-06, "epoch": 2.82563025210084, "percentage": 14.13, "elapsed_time": "0:02:01", "remaining_time": "0:12:18", "throughput": 3152.12, "total_tokens": 382952} +{"current_steps": 1350, "total_steps": 9520, "loss": 0.568, "lr": 9.947119586691284e-06, "epoch": 2.8361344537815127, "percentage": 14.18, "elapsed_time": "0:02:01", "remaining_time": "0:12:17", "throughput": 3153.24, "total_tokens": 384456} +{"current_steps": 1355, "total_steps": 9520, "loss": 0.9315, "lr": 9.945781626105101e-06, "epoch": 2.846638655462185, "percentage": 14.23, "elapsed_time": "0:02:02", "remaining_time": "0:12:17", "throughput": 3153.86, "total_tokens": 385864} +{"current_steps": 1360, "total_steps": 9520, "loss": 0.8121, "lr": 9.944427042279746e-06, "epoch": 2.857142857142857, "percentage": 14.29, "elapsed_time": "0:02:02", "remaining_time": "0:12:16", "throughput": 3155.05, "total_tokens": 387368} +{"current_steps": 1365, "total_steps": 9520, "loss": 0.5485, "lr": 9.943055839768096e-06, "epoch": 2.8676470588235294, "percentage": 14.34, "elapsed_time": "0:02:03", "remaining_time": "0:12:16", "throughput": 3155.28, "total_tokens": 388712} +{"current_steps": 1370, "total_steps": 9520, "loss": 0.5689, "lr": 9.941668023178898e-06, "epoch": 2.8781512605042017, "percentage": 14.39, "elapsed_time": "0:02:03", "remaining_time": "0:12:15", "throughput": 3155.89, "total_tokens": 390120} +{"current_steps": 1375, "total_steps": 9520, "loss": 0.8119, "lr": 9.940263597176731e-06, "epoch": 2.888655462184874, "percentage": 14.44, "elapsed_time": "0:02:04", "remaining_time": "0:12:14", "throughput": 3156.73, "total_tokens": 391560} +{"current_steps": 1380, "total_steps": 9520, "loss": 0.5375, "lr": 9.938842566482005e-06, "epoch": 2.899159663865546, "percentage": 14.5, "elapsed_time": "0:02:04", "remaining_time": "0:12:14", "throughput": 3157.28, "total_tokens": 393064} +{"current_steps": 1385, "total_steps": 9520, "loss": 0.6339, "lr": 9.937404935870938e-06, "epoch": 2.9096638655462184, "percentage": 14.55, "elapsed_time": "0:02:04", "remaining_time": "0:12:14", "throughput": 3158.95, "total_tokens": 394760} +{"current_steps": 1390, "total_steps": 9520, "loss": 0.6296, "lr": 9.935950710175541e-06, "epoch": 2.9201680672268906, "percentage": 14.6, "elapsed_time": "0:02:05", "remaining_time": "0:12:13", "throughput": 3160.85, "total_tokens": 396488} +{"current_steps": 1395, "total_steps": 9520, "loss": 0.5129, "lr": 9.934479894283607e-06, "epoch": 2.9306722689075633, "percentage": 14.65, "elapsed_time": "0:02:05", "remaining_time": "0:12:13", "throughput": 3161.56, "total_tokens": 397960} +{"current_steps": 1400, "total_steps": 9520, "loss": 0.63, "lr": 9.932992493138685e-06, "epoch": 2.9411764705882355, "percentage": 14.71, "elapsed_time": "0:02:06", "remaining_time": "0:12:12", "throughput": 3162.36, "total_tokens": 399400} +{"current_steps": 1405, "total_steps": 9520, "loss": 0.7323, "lr": 9.931488511740071e-06, "epoch": 2.9516806722689077, "percentage": 14.76, "elapsed_time": "0:02:06", "remaining_time": "0:12:11", "throughput": 3163.24, "total_tokens": 400872} +{"current_steps": 1410, "total_steps": 9520, "loss": 0.8074, "lr": 9.929967955142787e-06, "epoch": 2.96218487394958, "percentage": 14.81, "elapsed_time": "0:02:07", "remaining_time": "0:12:11", "throughput": 3163.26, "total_tokens": 402184} +{"current_steps": 1415, "total_steps": 9520, "loss": 0.5726, "lr": 9.92843082845757e-06, "epoch": 2.972689075630252, "percentage": 14.86, "elapsed_time": "0:02:07", "remaining_time": "0:12:10", "throughput": 3164.38, "total_tokens": 403816} +{"current_steps": 1420, "total_steps": 9520, "loss": 0.5433, "lr": 9.926877136850848e-06, "epoch": 2.9831932773109244, "percentage": 14.92, "elapsed_time": "0:02:08", "remaining_time": "0:12:10", "throughput": 3164.29, "total_tokens": 405128} +{"current_steps": 1425, "total_steps": 9520, "loss": 0.5695, "lr": 9.925306885544723e-06, "epoch": 2.9936974789915967, "percentage": 14.97, "elapsed_time": "0:02:08", "remaining_time": "0:12:09", "throughput": 3164.85, "total_tokens": 406536} +{"current_steps": 1430, "total_steps": 9520, "loss": 0.5355, "lr": 9.923720079816959e-06, "epoch": 3.004201680672269, "percentage": 15.02, "elapsed_time": "0:02:08", "remaining_time": "0:12:09", "throughput": 3163.62, "total_tokens": 408080} +{"current_steps": 1435, "total_steps": 9520, "loss": 0.7244, "lr": 9.922116725000961e-06, "epoch": 3.014705882352941, "percentage": 15.07, "elapsed_time": "0:02:09", "remaining_time": "0:12:09", "throughput": 3164.13, "total_tokens": 409488} +{"current_steps": 1440, "total_steps": 9520, "loss": 0.6073, "lr": 9.920496826485754e-06, "epoch": 3.0252100840336134, "percentage": 15.13, "elapsed_time": "0:02:09", "remaining_time": "0:12:08", "throughput": 3163.84, "total_tokens": 410768} +{"current_steps": 1445, "total_steps": 9520, "loss": 0.659, "lr": 9.918860389715973e-06, "epoch": 3.0357142857142856, "percentage": 15.18, "elapsed_time": "0:02:10", "remaining_time": "0:12:07", "throughput": 3164.82, "total_tokens": 412272} +{"current_steps": 1450, "total_steps": 9520, "loss": 0.6157, "lr": 9.917207420191832e-06, "epoch": 3.046218487394958, "percentage": 15.23, "elapsed_time": "0:02:10", "remaining_time": "0:12:07", "throughput": 3165.05, "total_tokens": 413616} +{"current_steps": 1455, "total_steps": 9520, "loss": 0.6262, "lr": 9.91553792346912e-06, "epoch": 3.05672268907563, "percentage": 15.28, "elapsed_time": "0:02:11", "remaining_time": "0:12:06", "throughput": 3165.83, "total_tokens": 415088} +{"current_steps": 1460, "total_steps": 9520, "loss": 0.876, "lr": 9.913851905159175e-06, "epoch": 3.0672268907563027, "percentage": 15.34, "elapsed_time": "0:02:11", "remaining_time": "0:12:06", "throughput": 3165.78, "total_tokens": 416400} +{"current_steps": 1465, "total_steps": 9520, "loss": 0.5197, "lr": 9.91214937092886e-06, "epoch": 3.077731092436975, "percentage": 15.39, "elapsed_time": "0:02:11", "remaining_time": "0:12:05", "throughput": 3166.57, "total_tokens": 417872} +{"current_steps": 1470, "total_steps": 9520, "loss": 0.6085, "lr": 9.910430326500557e-06, "epoch": 3.088235294117647, "percentage": 15.44, "elapsed_time": "0:02:12", "remaining_time": "0:12:04", "throughput": 3167.0, "total_tokens": 419280} +{"current_steps": 1475, "total_steps": 9520, "loss": 0.5534, "lr": 9.908694777652137e-06, "epoch": 3.0987394957983194, "percentage": 15.49, "elapsed_time": "0:02:12", "remaining_time": "0:12:04", "throughput": 3168.13, "total_tokens": 420912} +{"current_steps": 1480, "total_steps": 9520, "loss": 0.373, "lr": 9.90694273021694e-06, "epoch": 3.1092436974789917, "percentage": 15.55, "elapsed_time": "0:02:13", "remaining_time": "0:12:04", "throughput": 3168.72, "total_tokens": 422352} +{"current_steps": 1485, "total_steps": 9520, "loss": 0.3456, "lr": 9.905174190083763e-06, "epoch": 3.119747899159664, "percentage": 15.6, "elapsed_time": "0:02:13", "remaining_time": "0:12:03", "throughput": 3170.1, "total_tokens": 423920} +{"current_steps": 1490, "total_steps": 9520, "loss": 0.4936, "lr": 9.903389163196839e-06, "epoch": 3.130252100840336, "percentage": 15.65, "elapsed_time": "0:02:14", "remaining_time": "0:12:02", "throughput": 3170.36, "total_tokens": 425296} +{"current_steps": 1495, "total_steps": 9520, "loss": 0.5672, "lr": 9.901587655555813e-06, "epoch": 3.1407563025210083, "percentage": 15.7, "elapsed_time": "0:02:14", "remaining_time": "0:12:02", "throughput": 3170.49, "total_tokens": 426640} +{"current_steps": 1500, "total_steps": 9520, "loss": 0.4082, "lr": 9.899769673215718e-06, "epoch": 3.1512605042016806, "percentage": 15.76, "elapsed_time": "0:02:15", "remaining_time": "0:12:01", "throughput": 3172.08, "total_tokens": 428240} +{"current_steps": 1505, "total_steps": 9520, "loss": 0.4878, "lr": 9.897935222286968e-06, "epoch": 3.161764705882353, "percentage": 15.81, "elapsed_time": "0:02:15", "remaining_time": "0:12:01", "throughput": 3172.22, "total_tokens": 429616} +{"current_steps": 1510, "total_steps": 9520, "loss": 0.7247, "lr": 9.896084308935325e-06, "epoch": 3.172268907563025, "percentage": 15.86, "elapsed_time": "0:02:15", "remaining_time": "0:12:00", "throughput": 3172.85, "total_tokens": 431056} +{"current_steps": 1515, "total_steps": 9520, "loss": 0.7961, "lr": 9.894216939381883e-06, "epoch": 3.1827731092436973, "percentage": 15.91, "elapsed_time": "0:02:16", "remaining_time": "0:12:00", "throughput": 3173.56, "total_tokens": 432688} +{"current_steps": 1520, "total_steps": 9520, "loss": 0.5972, "lr": 9.892333119903045e-06, "epoch": 3.19327731092437, "percentage": 15.97, "elapsed_time": "0:02:16", "remaining_time": "0:11:59", "throughput": 3174.63, "total_tokens": 434192} +{"current_steps": 1525, "total_steps": 9520, "loss": 0.6593, "lr": 9.890432856830512e-06, "epoch": 3.203781512605042, "percentage": 16.02, "elapsed_time": "0:02:17", "remaining_time": "0:11:59", "throughput": 3176.08, "total_tokens": 435856} +{"current_steps": 1530, "total_steps": 9520, "loss": 0.7264, "lr": 9.888516156551242e-06, "epoch": 3.2142857142857144, "percentage": 16.07, "elapsed_time": "0:02:17", "remaining_time": "0:11:58", "throughput": 3175.74, "total_tokens": 437104} +{"current_steps": 1535, "total_steps": 9520, "loss": 0.9411, "lr": 9.88658302550745e-06, "epoch": 3.2247899159663866, "percentage": 16.12, "elapsed_time": "0:02:18", "remaining_time": "0:11:58", "throughput": 3175.68, "total_tokens": 438416} +{"current_steps": 1540, "total_steps": 9520, "loss": 0.6643, "lr": 9.88463347019657e-06, "epoch": 3.235294117647059, "percentage": 16.18, "elapsed_time": "0:02:18", "remaining_time": "0:11:57", "throughput": 3176.14, "total_tokens": 439824} +{"current_steps": 1545, "total_steps": 9520, "loss": 0.486, "lr": 9.88266749717124e-06, "epoch": 3.245798319327731, "percentage": 16.23, "elapsed_time": "0:02:18", "remaining_time": "0:11:56", "throughput": 3176.47, "total_tokens": 441200} +{"current_steps": 1550, "total_steps": 9520, "loss": 0.4714, "lr": 9.880685113039285e-06, "epoch": 3.2563025210084033, "percentage": 16.28, "elapsed_time": "0:02:19", "remaining_time": "0:11:56", "throughput": 3177.37, "total_tokens": 442704} +{"current_steps": 1555, "total_steps": 9520, "loss": 0.5835, "lr": 9.878686324463683e-06, "epoch": 3.2668067226890756, "percentage": 16.33, "elapsed_time": "0:02:19", "remaining_time": "0:11:55", "throughput": 3177.3, "total_tokens": 444016} +{"current_steps": 1560, "total_steps": 9520, "loss": 0.6075, "lr": 9.87667113816255e-06, "epoch": 3.277310924369748, "percentage": 16.39, "elapsed_time": "0:02:20", "remaining_time": "0:11:55", "throughput": 3177.69, "total_tokens": 445424} +{"current_steps": 1565, "total_steps": 9520, "loss": 0.5256, "lr": 9.874639560909118e-06, "epoch": 3.28781512605042, "percentage": 16.44, "elapsed_time": "0:02:20", "remaining_time": "0:11:54", "throughput": 3178.08, "total_tokens": 446832} +{"current_steps": 1570, "total_steps": 9520, "loss": 0.7135, "lr": 9.872591599531714e-06, "epoch": 3.2983193277310923, "percentage": 16.49, "elapsed_time": "0:02:21", "remaining_time": "0:11:54", "throughput": 3178.42, "total_tokens": 448208} +{"current_steps": 1575, "total_steps": 9520, "loss": 0.9803, "lr": 9.870527260913722e-06, "epoch": 3.3088235294117645, "percentage": 16.54, "elapsed_time": "0:02:21", "remaining_time": "0:11:53", "throughput": 3178.65, "total_tokens": 449584} +{"current_steps": 1580, "total_steps": 9520, "loss": 0.5901, "lr": 9.868446551993587e-06, "epoch": 3.3193277310924367, "percentage": 16.6, "elapsed_time": "0:02:21", "remaining_time": "0:11:52", "throughput": 3178.7, "total_tokens": 450928} +{"current_steps": 1585, "total_steps": 9520, "loss": 0.7006, "lr": 9.866349479764764e-06, "epoch": 3.3298319327731094, "percentage": 16.65, "elapsed_time": "0:02:22", "remaining_time": "0:11:52", "throughput": 3179.01, "total_tokens": 452336} +{"current_steps": 1590, "total_steps": 9520, "loss": 0.7198, "lr": 9.864236051275708e-06, "epoch": 3.3403361344537816, "percentage": 16.7, "elapsed_time": "0:02:22", "remaining_time": "0:11:51", "throughput": 3179.57, "total_tokens": 453776} +{"current_steps": 1595, "total_steps": 9520, "loss": 0.4367, "lr": 9.862106273629858e-06, "epoch": 3.350840336134454, "percentage": 16.75, "elapsed_time": "0:02:23", "remaining_time": "0:11:51", "throughput": 3179.32, "total_tokens": 455056} +{"current_steps": 1600, "total_steps": 9520, "loss": 0.8113, "lr": 9.859960153985597e-06, "epoch": 3.361344537815126, "percentage": 16.81, "elapsed_time": "0:02:23", "remaining_time": "0:11:50", "throughput": 3180.08, "total_tokens": 456592} +{"current_steps": 1605, "total_steps": 9520, "loss": 0.7023, "lr": 9.857797699556231e-06, "epoch": 3.3718487394957983, "percentage": 16.86, "elapsed_time": "0:02:24", "remaining_time": "0:11:50", "throughput": 3180.06, "total_tokens": 457936} +{"current_steps": 1610, "total_steps": 9520, "loss": 0.4152, "lr": 9.855618917609977e-06, "epoch": 3.3823529411764706, "percentage": 16.91, "elapsed_time": "0:02:24", "remaining_time": "0:11:49", "throughput": 3180.77, "total_tokens": 459408} +{"current_steps": 1615, "total_steps": 9520, "loss": 0.5997, "lr": 9.853423815469927e-06, "epoch": 3.392857142857143, "percentage": 16.96, "elapsed_time": "0:02:24", "remaining_time": "0:11:48", "throughput": 3180.8, "total_tokens": 460720} +{"current_steps": 1620, "total_steps": 9520, "loss": 0.4958, "lr": 9.851212400514026e-06, "epoch": 3.403361344537815, "percentage": 17.02, "elapsed_time": "0:02:25", "remaining_time": "0:11:48", "throughput": 3181.87, "total_tokens": 462256} +{"current_steps": 1625, "total_steps": 9520, "loss": 0.4633, "lr": 9.848984680175049e-06, "epoch": 3.4138655462184873, "percentage": 17.07, "elapsed_time": "0:02:25", "remaining_time": "0:11:47", "throughput": 3182.69, "total_tokens": 463760} +{"current_steps": 1630, "total_steps": 9520, "loss": 0.4956, "lr": 9.846740661940573e-06, "epoch": 3.4243697478991595, "percentage": 17.12, "elapsed_time": "0:02:26", "remaining_time": "0:11:47", "throughput": 3183.79, "total_tokens": 465296} +{"current_steps": 1635, "total_steps": 9520, "loss": 0.4979, "lr": 9.844480353352956e-06, "epoch": 3.434873949579832, "percentage": 17.17, "elapsed_time": "0:02:26", "remaining_time": "0:11:46", "throughput": 3184.99, "total_tokens": 466864} +{"current_steps": 1640, "total_steps": 9520, "loss": 0.5458, "lr": 9.842203762009308e-06, "epoch": 3.4453781512605044, "percentage": 17.23, "elapsed_time": "0:02:26", "remaining_time": "0:11:46", "throughput": 3184.79, "total_tokens": 468144} +{"current_steps": 1645, "total_steps": 9520, "loss": 0.7218, "lr": 9.83991089556147e-06, "epoch": 3.4558823529411766, "percentage": 17.28, "elapsed_time": "0:02:27", "remaining_time": "0:11:45", "throughput": 3184.79, "total_tokens": 469488} +{"current_steps": 1650, "total_steps": 9520, "loss": 0.6427, "lr": 9.837601761715982e-06, "epoch": 3.466386554621849, "percentage": 17.33, "elapsed_time": "0:02:27", "remaining_time": "0:11:45", "throughput": 3184.44, "total_tokens": 470736} +{"current_steps": 1655, "total_steps": 9520, "loss": 0.8182, "lr": 9.835276368234058e-06, "epoch": 3.476890756302521, "percentage": 17.38, "elapsed_time": "0:02:28", "remaining_time": "0:11:44", "throughput": 3184.31, "total_tokens": 472048} +{"current_steps": 1660, "total_steps": 9520, "loss": 0.671, "lr": 9.832934722931568e-06, "epoch": 3.4873949579831933, "percentage": 17.44, "elapsed_time": "0:02:28", "remaining_time": "0:11:43", "throughput": 3185.07, "total_tokens": 473520} +{"current_steps": 1665, "total_steps": 9520, "loss": 0.7296, "lr": 9.830576833679005e-06, "epoch": 3.4978991596638656, "percentage": 17.49, "elapsed_time": "0:02:29", "remaining_time": "0:11:43", "throughput": 3185.61, "total_tokens": 474960} +{"current_steps": 1670, "total_steps": 9520, "loss": 0.7519, "lr": 9.82820270840145e-06, "epoch": 3.508403361344538, "percentage": 17.54, "elapsed_time": "0:02:29", "remaining_time": "0:11:42", "throughput": 3186.05, "total_tokens": 476368} +{"current_steps": 1675, "total_steps": 9520, "loss": 0.6403, "lr": 9.82581235507857e-06, "epoch": 3.51890756302521, "percentage": 17.59, "elapsed_time": "0:02:29", "remaining_time": "0:11:42", "throughput": 3186.57, "total_tokens": 477904} +{"current_steps": 1680, "total_steps": 9520, "loss": 0.5647, "lr": 9.823405781744564e-06, "epoch": 3.5294117647058822, "percentage": 17.65, "elapsed_time": "0:02:30", "remaining_time": "0:11:41", "throughput": 3187.32, "total_tokens": 479408} +{"current_steps": 1685, "total_steps": 9520, "loss": 0.6685, "lr": 9.820982996488154e-06, "epoch": 3.5399159663865545, "percentage": 17.7, "elapsed_time": "0:02:30", "remaining_time": "0:11:41", "throughput": 3187.07, "total_tokens": 480688} +{"current_steps": 1690, "total_steps": 9520, "loss": 0.5511, "lr": 9.818544007452551e-06, "epoch": 3.5504201680672267, "percentage": 17.75, "elapsed_time": "0:02:31", "remaining_time": "0:11:40", "throughput": 3188.46, "total_tokens": 482288} +{"current_steps": 1695, "total_steps": 9520, "loss": 0.801, "lr": 9.816088822835423e-06, "epoch": 3.560924369747899, "percentage": 17.8, "elapsed_time": "0:02:31", "remaining_time": "0:11:40", "throughput": 3188.89, "total_tokens": 483728} +{"current_steps": 1700, "total_steps": 9520, "loss": 0.5462, "lr": 9.813617450888884e-06, "epoch": 3.571428571428571, "percentage": 17.86, "elapsed_time": "0:02:32", "remaining_time": "0:11:40", "throughput": 3189.68, "total_tokens": 485424} +{"current_steps": 1705, "total_steps": 9520, "loss": 0.6379, "lr": 9.811129899919443e-06, "epoch": 3.581932773109244, "percentage": 17.91, "elapsed_time": "0:02:32", "remaining_time": "0:11:39", "throughput": 3190.4, "total_tokens": 486896} +{"current_steps": 1710, "total_steps": 9520, "loss": 0.6541, "lr": 9.808626178287995e-06, "epoch": 3.592436974789916, "percentage": 17.96, "elapsed_time": "0:02:33", "remaining_time": "0:11:38", "throughput": 3191.19, "total_tokens": 488368} +{"current_steps": 1715, "total_steps": 9520, "loss": 0.7043, "lr": 9.806106294409788e-06, "epoch": 3.6029411764705883, "percentage": 18.01, "elapsed_time": "0:02:33", "remaining_time": "0:11:38", "throughput": 3191.49, "total_tokens": 489744} +{"current_steps": 1720, "total_steps": 9520, "loss": 0.8486, "lr": 9.803570256754387e-06, "epoch": 3.6134453781512605, "percentage": 18.07, "elapsed_time": "0:02:33", "remaining_time": "0:11:37", "throughput": 3191.48, "total_tokens": 491088} +{"current_steps": 1725, "total_steps": 9520, "loss": 0.5395, "lr": 9.801018073845653e-06, "epoch": 3.6239495798319328, "percentage": 18.12, "elapsed_time": "0:02:34", "remaining_time": "0:11:37", "throughput": 3191.19, "total_tokens": 492336} +{"current_steps": 1730, "total_steps": 9520, "loss": 0.3808, "lr": 9.798449754261716e-06, "epoch": 3.634453781512605, "percentage": 18.17, "elapsed_time": "0:02:34", "remaining_time": "0:11:36", "throughput": 3191.3, "total_tokens": 493712} +{"current_steps": 1735, "total_steps": 9520, "loss": 0.5792, "lr": 9.795865306634939e-06, "epoch": 3.6449579831932772, "percentage": 18.22, "elapsed_time": "0:02:35", "remaining_time": "0:11:36", "throughput": 3191.87, "total_tokens": 495184} +{"current_steps": 1740, "total_steps": 9520, "loss": 0.627, "lr": 9.793264739651897e-06, "epoch": 3.6554621848739495, "percentage": 18.28, "elapsed_time": "0:02:35", "remaining_time": "0:11:35", "throughput": 3192.5, "total_tokens": 496656} +{"current_steps": 1745, "total_steps": 9520, "loss": 0.7332, "lr": 9.790648062053341e-06, "epoch": 3.6659663865546217, "percentage": 18.33, "elapsed_time": "0:02:36", "remaining_time": "0:11:35", "throughput": 3192.9, "total_tokens": 498160} +{"current_steps": 1750, "total_steps": 9520, "loss": 0.9125, "lr": 9.788015282634169e-06, "epoch": 3.6764705882352944, "percentage": 18.38, "elapsed_time": "0:02:36", "remaining_time": "0:11:34", "throughput": 3193.08, "total_tokens": 499536} +{"current_steps": 1755, "total_steps": 9520, "loss": 1.1271, "lr": 9.785366410243403e-06, "epoch": 3.6869747899159666, "percentage": 18.43, "elapsed_time": "0:02:36", "remaining_time": "0:11:34", "throughput": 3192.83, "total_tokens": 500816} +{"current_steps": 1760, "total_steps": 9520, "loss": 0.5326, "lr": 9.782701453784154e-06, "epoch": 3.697478991596639, "percentage": 18.49, "elapsed_time": "0:02:37", "remaining_time": "0:11:33", "throughput": 3193.16, "total_tokens": 502224} +{"current_steps": 1765, "total_steps": 9520, "loss": 0.6745, "lr": 9.78002042221359e-06, "epoch": 3.707983193277311, "percentage": 18.54, "elapsed_time": "0:02:37", "remaining_time": "0:11:32", "throughput": 3193.05, "total_tokens": 503536} +{"current_steps": 1770, "total_steps": 9520, "loss": 0.6194, "lr": 9.777323324542912e-06, "epoch": 3.7184873949579833, "percentage": 18.59, "elapsed_time": "0:02:38", "remaining_time": "0:11:32", "throughput": 3192.82, "total_tokens": 504816} +{"current_steps": 1775, "total_steps": 9520, "loss": 0.7066, "lr": 9.774610169837321e-06, "epoch": 3.7289915966386555, "percentage": 18.64, "elapsed_time": "0:02:38", "remaining_time": "0:11:31", "throughput": 3192.12, "total_tokens": 506000} +{"current_steps": 1780, "total_steps": 9520, "loss": 0.5521, "lr": 9.771880967215988e-06, "epoch": 3.7394957983193278, "percentage": 18.7, "elapsed_time": "0:02:38", "remaining_time": "0:11:31", "throughput": 3192.09, "total_tokens": 507344} +{"current_steps": 1785, "total_steps": 9520, "loss": 0.3498, "lr": 9.769135725852016e-06, "epoch": 3.75, "percentage": 18.75, "elapsed_time": "0:02:39", "remaining_time": "0:11:30", "throughput": 3193.41, "total_tokens": 509040} +{"current_steps": 1790, "total_steps": 9520, "loss": 0.7338, "lr": 9.766374454972425e-06, "epoch": 3.7605042016806722, "percentage": 18.8, "elapsed_time": "0:02:39", "remaining_time": "0:11:30", "throughput": 3193.29, "total_tokens": 510352} +{"current_steps": 1795, "total_steps": 9520, "loss": 0.7874, "lr": 9.763597163858104e-06, "epoch": 3.7710084033613445, "percentage": 18.86, "elapsed_time": "0:02:40", "remaining_time": "0:11:29", "throughput": 3194.44, "total_tokens": 511920} +{"current_steps": 1800, "total_steps": 9520, "loss": 0.6188, "lr": 9.760803861843796e-06, "epoch": 3.7815126050420167, "percentage": 18.91, "elapsed_time": "0:02:40", "remaining_time": "0:11:29", "throughput": 3195.43, "total_tokens": 513552} +{"current_steps": 1805, "total_steps": 9520, "loss": 0.747, "lr": 9.757994558318044e-06, "epoch": 3.792016806722689, "percentage": 18.96, "elapsed_time": "0:02:41", "remaining_time": "0:11:28", "throughput": 3196.58, "total_tokens": 515152} +{"current_steps": 1810, "total_steps": 9520, "loss": 0.7476, "lr": 9.755169262723192e-06, "epoch": 3.802521008403361, "percentage": 19.01, "elapsed_time": "0:02:41", "remaining_time": "0:11:28", "throughput": 3197.11, "total_tokens": 516592} +{"current_steps": 1815, "total_steps": 9520, "loss": 0.5387, "lr": 9.75232798455532e-06, "epoch": 3.8130252100840334, "percentage": 19.07, "elapsed_time": "0:02:42", "remaining_time": "0:11:27", "throughput": 3198.07, "total_tokens": 518224} +{"current_steps": 1820, "total_steps": 9520, "loss": 0.7656, "lr": 9.749470733364231e-06, "epoch": 3.8235294117647056, "percentage": 19.12, "elapsed_time": "0:02:42", "remaining_time": "0:11:27", "throughput": 3198.36, "total_tokens": 519632} +{"current_steps": 1825, "total_steps": 9520, "loss": 0.595, "lr": 9.746597518753419e-06, "epoch": 3.8340336134453783, "percentage": 19.17, "elapsed_time": "0:02:42", "remaining_time": "0:11:26", "throughput": 3198.38, "total_tokens": 520976} +{"current_steps": 1830, "total_steps": 9520, "loss": 0.6958, "lr": 9.74370835038003e-06, "epoch": 3.8445378151260505, "percentage": 19.22, "elapsed_time": "0:02:43", "remaining_time": "0:11:26", "throughput": 3198.13, "total_tokens": 522256} +{"current_steps": 1835, "total_steps": 9520, "loss": 0.49, "lr": 9.74080323795483e-06, "epoch": 3.8550420168067228, "percentage": 19.28, "elapsed_time": "0:02:43", "remaining_time": "0:11:25", "throughput": 3198.23, "total_tokens": 523600} +{"current_steps": 1840, "total_steps": 9520, "loss": 0.6245, "lr": 9.737882191242178e-06, "epoch": 3.865546218487395, "percentage": 19.33, "elapsed_time": "0:02:44", "remaining_time": "0:11:25", "throughput": 3199.35, "total_tokens": 525360} +{"current_steps": 1845, "total_steps": 9520, "loss": 0.5574, "lr": 9.734945220059985e-06, "epoch": 3.8760504201680672, "percentage": 19.38, "elapsed_time": "0:02:44", "remaining_time": "0:11:24", "throughput": 3200.44, "total_tokens": 526928} +{"current_steps": 1850, "total_steps": 9520, "loss": 0.5085, "lr": 9.731992334279693e-06, "epoch": 3.8865546218487395, "percentage": 19.43, "elapsed_time": "0:02:45", "remaining_time": "0:11:24", "throughput": 3200.41, "total_tokens": 528272} +{"current_steps": 1855, "total_steps": 9520, "loss": 0.6374, "lr": 9.729023543826225e-06, "epoch": 3.8970588235294117, "percentage": 19.49, "elapsed_time": "0:02:45", "remaining_time": "0:11:23", "throughput": 3200.04, "total_tokens": 529552} +{"current_steps": 1860, "total_steps": 9520, "loss": 0.4175, "lr": 9.72603885867797e-06, "epoch": 3.907563025210084, "percentage": 19.54, "elapsed_time": "0:02:45", "remaining_time": "0:11:23", "throughput": 3200.99, "total_tokens": 531088} +{"current_steps": 1865, "total_steps": 9520, "loss": 0.6363, "lr": 9.723038288866738e-06, "epoch": 3.918067226890756, "percentage": 19.59, "elapsed_time": "0:02:46", "remaining_time": "0:11:22", "throughput": 3201.68, "total_tokens": 532592} +{"current_steps": 1870, "total_steps": 9520, "loss": 0.9405, "lr": 9.720021844477722e-06, "epoch": 3.928571428571429, "percentage": 19.64, "elapsed_time": "0:02:46", "remaining_time": "0:11:22", "throughput": 3201.04, "total_tokens": 533776} +{"current_steps": 1875, "total_steps": 9520, "loss": 0.4715, "lr": 9.716989535649479e-06, "epoch": 3.939075630252101, "percentage": 19.7, "elapsed_time": "0:02:47", "remaining_time": "0:11:21", "throughput": 3201.2, "total_tokens": 535152} +{"current_steps": 1880, "total_steps": 9520, "loss": 0.6058, "lr": 9.713941372573887e-06, "epoch": 3.9495798319327733, "percentage": 19.75, "elapsed_time": "0:02:47", "remaining_time": "0:11:21", "throughput": 3202.13, "total_tokens": 536720} +{"current_steps": 1885, "total_steps": 9520, "loss": 0.6182, "lr": 9.710877365496107e-06, "epoch": 3.9600840336134455, "percentage": 19.8, "elapsed_time": "0:02:48", "remaining_time": "0:11:20", "throughput": 3202.3, "total_tokens": 538128} +{"current_steps": 1890, "total_steps": 9520, "loss": 0.5895, "lr": 9.70779752471456e-06, "epoch": 3.9705882352941178, "percentage": 19.85, "elapsed_time": "0:02:48", "remaining_time": "0:11:20", "throughput": 3203.25, "total_tokens": 539696} +{"current_steps": 1895, "total_steps": 9520, "loss": 0.7647, "lr": 9.704701860580878e-06, "epoch": 3.98109243697479, "percentage": 19.91, "elapsed_time": "0:02:48", "remaining_time": "0:11:19", "throughput": 3204.05, "total_tokens": 541232} +{"current_steps": 1900, "total_steps": 9520, "loss": 0.5327, "lr": 9.701590383499884e-06, "epoch": 3.991596638655462, "percentage": 19.96, "elapsed_time": "0:02:49", "remaining_time": "0:11:19", "throughput": 3204.71, "total_tokens": 542704} +{"current_steps": 1904, "total_steps": 9520, "eval_loss": 0.7194890975952148, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:02:54", "remaining_time": "0:11:37", "throughput": 3118.54, "total_tokens": 544016} +{"current_steps": 1905, "total_steps": 9520, "loss": 0.5012, "lr": 9.698463103929542e-06, "epoch": 4.0021008403361344, "percentage": 20.01, "elapsed_time": "0:02:55", "remaining_time": "0:11:41", "throughput": 3099.72, "total_tokens": 544336} +{"current_steps": 1910, "total_steps": 9520, "loss": 0.5092, "lr": 9.69532003238094e-06, "epoch": 4.012605042016807, "percentage": 20.06, "elapsed_time": "0:02:56", "remaining_time": "0:11:41", "throughput": 3100.05, "total_tokens": 545712} +{"current_steps": 1915, "total_steps": 9520, "loss": 0.4745, "lr": 9.692161179418231e-06, "epoch": 4.023109243697479, "percentage": 20.12, "elapsed_time": "0:02:56", "remaining_time": "0:11:40", "throughput": 3101.83, "total_tokens": 547408} +{"current_steps": 1920, "total_steps": 9520, "loss": 0.6354, "lr": 9.688986555658624e-06, "epoch": 4.033613445378151, "percentage": 20.17, "elapsed_time": "0:02:56", "remaining_time": "0:11:40", "throughput": 3101.97, "total_tokens": 548720} +{"current_steps": 1925, "total_steps": 9520, "loss": 0.4008, "lr": 9.685796171772327e-06, "epoch": 4.044117647058823, "percentage": 20.22, "elapsed_time": "0:02:57", "remaining_time": "0:11:39", "throughput": 3102.36, "total_tokens": 550096} +{"current_steps": 1930, "total_steps": 9520, "loss": 0.5886, "lr": 9.682590038482523e-06, "epoch": 4.054621848739496, "percentage": 20.27, "elapsed_time": "0:02:57", "remaining_time": "0:11:38", "throughput": 3102.49, "total_tokens": 551440} +{"current_steps": 1935, "total_steps": 9520, "loss": 0.5262, "lr": 9.679368166565328e-06, "epoch": 4.065126050420168, "percentage": 20.33, "elapsed_time": "0:02:58", "remaining_time": "0:11:38", "throughput": 3103.24, "total_tokens": 552912} +{"current_steps": 1940, "total_steps": 9520, "loss": 0.4274, "lr": 9.676130566849757e-06, "epoch": 4.07563025210084, "percentage": 20.38, "elapsed_time": "0:02:58", "remaining_time": "0:11:37", "throughput": 3103.82, "total_tokens": 554352} +{"current_steps": 1945, "total_steps": 9520, "loss": 0.5517, "lr": 9.672877250217689e-06, "epoch": 4.086134453781512, "percentage": 20.43, "elapsed_time": "0:02:59", "remaining_time": "0:11:37", "throughput": 3104.52, "total_tokens": 555888} +{"current_steps": 1950, "total_steps": 9520, "loss": 0.3873, "lr": 9.669608227603828e-06, "epoch": 4.0966386554621845, "percentage": 20.48, "elapsed_time": "0:02:59", "remaining_time": "0:11:36", "throughput": 3104.37, "total_tokens": 557136} +{"current_steps": 1955, "total_steps": 9520, "loss": 0.6945, "lr": 9.666323509995668e-06, "epoch": 4.107142857142857, "percentage": 20.54, "elapsed_time": "0:02:59", "remaining_time": "0:11:36", "throughput": 3104.33, "total_tokens": 558448} +{"current_steps": 1960, "total_steps": 9520, "loss": 0.3603, "lr": 9.663023108433456e-06, "epoch": 4.117647058823529, "percentage": 20.59, "elapsed_time": "0:03:00", "remaining_time": "0:11:35", "throughput": 3105.52, "total_tokens": 560048} +{"current_steps": 1965, "total_steps": 9520, "loss": 0.7235, "lr": 9.659707034010152e-06, "epoch": 4.128151260504202, "percentage": 20.64, "elapsed_time": "0:03:00", "remaining_time": "0:11:34", "throughput": 3105.71, "total_tokens": 561360} +{"current_steps": 1970, "total_steps": 9520, "loss": 0.63, "lr": 9.656375297871397e-06, "epoch": 4.138655462184874, "percentage": 20.69, "elapsed_time": "0:03:01", "remaining_time": "0:11:34", "throughput": 3106.56, "total_tokens": 562864} +{"current_steps": 1975, "total_steps": 9520, "loss": 0.4473, "lr": 9.653027911215469e-06, "epoch": 4.149159663865547, "percentage": 20.75, "elapsed_time": "0:03:01", "remaining_time": "0:11:33", "throughput": 3106.8, "total_tokens": 564208} +{"current_steps": 1980, "total_steps": 9520, "loss": 0.6224, "lr": 9.649664885293253e-06, "epoch": 4.159663865546219, "percentage": 20.8, "elapsed_time": "0:03:02", "remaining_time": "0:11:33", "throughput": 3106.81, "total_tokens": 565488} +{"current_steps": 1985, "total_steps": 9520, "loss": 0.5538, "lr": 9.646286231408194e-06, "epoch": 4.170168067226891, "percentage": 20.85, "elapsed_time": "0:03:02", "remaining_time": "0:11:32", "throughput": 3106.59, "total_tokens": 566736} +{"current_steps": 1990, "total_steps": 9520, "loss": 0.5378, "lr": 9.642891960916269e-06, "epoch": 4.180672268907563, "percentage": 20.9, "elapsed_time": "0:03:02", "remaining_time": "0:11:31", "throughput": 3107.31, "total_tokens": 568208} +{"current_steps": 1995, "total_steps": 9520, "loss": 0.6885, "lr": 9.63948208522594e-06, "epoch": 4.1911764705882355, "percentage": 20.96, "elapsed_time": "0:03:03", "remaining_time": "0:11:31", "throughput": 3107.25, "total_tokens": 569456} +{"current_steps": 2000, "total_steps": 9520, "loss": 0.8022, "lr": 9.636056615798123e-06, "epoch": 4.201680672268908, "percentage": 21.01, "elapsed_time": "0:03:03", "remaining_time": "0:11:30", "throughput": 3107.49, "total_tokens": 570768} +{"current_steps": 2005, "total_steps": 9520, "loss": 0.4994, "lr": 9.632615564146145e-06, "epoch": 4.21218487394958, "percentage": 21.06, "elapsed_time": "0:03:04", "remaining_time": "0:11:29", "throughput": 3107.49, "total_tokens": 572048} +{"current_steps": 2010, "total_steps": 9520, "loss": 0.7248, "lr": 9.629158941835701e-06, "epoch": 4.222689075630252, "percentage": 21.11, "elapsed_time": "0:03:04", "remaining_time": "0:11:29", "throughput": 3107.2, "total_tokens": 573264} +{"current_steps": 2015, "total_steps": 9520, "loss": 0.6588, "lr": 9.62568676048483e-06, "epoch": 4.233193277310924, "percentage": 21.17, "elapsed_time": "0:03:04", "remaining_time": "0:11:28", "throughput": 3108.21, "total_tokens": 574800} +{"current_steps": 2020, "total_steps": 9520, "loss": 0.4938, "lr": 9.622199031763859e-06, "epoch": 4.243697478991597, "percentage": 21.22, "elapsed_time": "0:03:05", "remaining_time": "0:11:28", "throughput": 3108.98, "total_tokens": 576272} +{"current_steps": 2025, "total_steps": 9520, "loss": 0.4822, "lr": 9.618695767395377e-06, "epoch": 4.254201680672269, "percentage": 21.27, "elapsed_time": "0:03:05", "remaining_time": "0:11:27", "throughput": 3109.27, "total_tokens": 577648} +{"current_steps": 2030, "total_steps": 9520, "loss": 0.5201, "lr": 9.61517697915418e-06, "epoch": 4.264705882352941, "percentage": 21.32, "elapsed_time": "0:03:06", "remaining_time": "0:11:27", "throughput": 3109.94, "total_tokens": 579120} +{"current_steps": 2035, "total_steps": 9520, "loss": 0.7125, "lr": 9.611642678867252e-06, "epoch": 4.275210084033613, "percentage": 21.38, "elapsed_time": "0:03:06", "remaining_time": "0:11:26", "throughput": 3109.82, "total_tokens": 580400} +{"current_steps": 2040, "total_steps": 9520, "loss": 0.603, "lr": 9.60809287841371e-06, "epoch": 4.285714285714286, "percentage": 21.43, "elapsed_time": "0:03:07", "remaining_time": "0:11:26", "throughput": 3110.72, "total_tokens": 582032} +{"current_steps": 2045, "total_steps": 9520, "loss": 0.6288, "lr": 9.60452758972477e-06, "epoch": 4.296218487394958, "percentage": 21.48, "elapsed_time": "0:03:07", "remaining_time": "0:11:25", "throughput": 3111.18, "total_tokens": 583440} +{"current_steps": 2050, "total_steps": 9520, "loss": 0.4753, "lr": 9.6009468247837e-06, "epoch": 4.30672268907563, "percentage": 21.53, "elapsed_time": "0:03:07", "remaining_time": "0:11:24", "throughput": 3112.29, "total_tokens": 585008} +{"current_steps": 2055, "total_steps": 9520, "loss": 0.5581, "lr": 9.59735059562579e-06, "epoch": 4.317226890756302, "percentage": 21.59, "elapsed_time": "0:03:08", "remaining_time": "0:11:24", "throughput": 3112.47, "total_tokens": 586352} +{"current_steps": 2060, "total_steps": 9520, "loss": 0.414, "lr": 9.593738914338309e-06, "epoch": 4.3277310924369745, "percentage": 21.64, "elapsed_time": "0:03:08", "remaining_time": "0:11:23", "throughput": 3112.78, "total_tokens": 587728} +{"current_steps": 2065, "total_steps": 9520, "loss": 0.6876, "lr": 9.590111793060457e-06, "epoch": 4.338235294117647, "percentage": 21.69, "elapsed_time": "0:03:09", "remaining_time": "0:11:23", "throughput": 3114.11, "total_tokens": 589360} +{"current_steps": 2070, "total_steps": 9520, "loss": 0.5088, "lr": 9.58646924398333e-06, "epoch": 4.348739495798319, "percentage": 21.74, "elapsed_time": "0:03:09", "remaining_time": "0:11:22", "throughput": 3114.76, "total_tokens": 590832} +{"current_steps": 2075, "total_steps": 9520, "loss": 0.5272, "lr": 9.582811279349881e-06, "epoch": 4.359243697478991, "percentage": 21.8, "elapsed_time": "0:03:10", "remaining_time": "0:11:22", "throughput": 3115.01, "total_tokens": 592176} +{"current_steps": 2080, "total_steps": 9520, "loss": 0.572, "lr": 9.579137911454876e-06, "epoch": 4.369747899159664, "percentage": 21.85, "elapsed_time": "0:03:10", "remaining_time": "0:11:21", "throughput": 3115.35, "total_tokens": 593552} +{"current_steps": 2085, "total_steps": 9520, "loss": 0.4454, "lr": 9.575449152644848e-06, "epoch": 4.380252100840336, "percentage": 21.9, "elapsed_time": "0:03:10", "remaining_time": "0:11:20", "throughput": 3115.78, "total_tokens": 595024} +{"current_steps": 2090, "total_steps": 9520, "loss": 0.5367, "lr": 9.571745015318066e-06, "epoch": 4.390756302521009, "percentage": 21.95, "elapsed_time": "0:03:11", "remaining_time": "0:11:20", "throughput": 3116.71, "total_tokens": 596528} +{"current_steps": 2095, "total_steps": 9520, "loss": 0.6565, "lr": 9.568025511924486e-06, "epoch": 4.401260504201681, "percentage": 22.01, "elapsed_time": "0:03:11", "remaining_time": "0:11:19", "throughput": 3117.31, "total_tokens": 598064} +{"current_steps": 2100, "total_steps": 9520, "loss": 0.5155, "lr": 9.564290654965706e-06, "epoch": 4.411764705882353, "percentage": 22.06, "elapsed_time": "0:03:12", "remaining_time": "0:11:19", "throughput": 3118.39, "total_tokens": 599632} +{"current_steps": 2105, "total_steps": 9520, "loss": 0.7462, "lr": 9.56054045699494e-06, "epoch": 4.4222689075630255, "percentage": 22.11, "elapsed_time": "0:03:12", "remaining_time": "0:11:18", "throughput": 3118.54, "total_tokens": 600944} +{"current_steps": 2110, "total_steps": 9520, "loss": 0.7216, "lr": 9.556774930616953e-06, "epoch": 4.432773109243698, "percentage": 22.16, "elapsed_time": "0:03:13", "remaining_time": "0:11:18", "throughput": 3118.7, "total_tokens": 602384} +{"current_steps": 2115, "total_steps": 9520, "loss": 0.5022, "lr": 9.552994088488033e-06, "epoch": 4.44327731092437, "percentage": 22.22, "elapsed_time": "0:03:13", "remaining_time": "0:11:17", "throughput": 3119.84, "total_tokens": 603952} +{"current_steps": 2120, "total_steps": 9520, "loss": 0.5227, "lr": 9.549197943315952e-06, "epoch": 4.453781512605042, "percentage": 22.27, "elapsed_time": "0:03:14", "remaining_time": "0:11:17", "throughput": 3120.72, "total_tokens": 605456} +{"current_steps": 2125, "total_steps": 9520, "loss": 0.4908, "lr": 9.54538650785991e-06, "epoch": 4.464285714285714, "percentage": 22.32, "elapsed_time": "0:03:14", "remaining_time": "0:11:16", "throughput": 3121.42, "total_tokens": 606928} +{"current_steps": 2130, "total_steps": 9520, "loss": 0.3494, "lr": 9.541559794930502e-06, "epoch": 4.474789915966387, "percentage": 22.37, "elapsed_time": "0:03:14", "remaining_time": "0:11:16", "throughput": 3122.64, "total_tokens": 608528} +{"current_steps": 2135, "total_steps": 9520, "loss": 0.3836, "lr": 9.537717817389672e-06, "epoch": 4.485294117647059, "percentage": 22.43, "elapsed_time": "0:03:15", "remaining_time": "0:11:15", "throughput": 3122.82, "total_tokens": 609872} +{"current_steps": 2140, "total_steps": 9520, "loss": 0.467, "lr": 9.53386058815067e-06, "epoch": 4.495798319327731, "percentage": 22.48, "elapsed_time": "0:03:15", "remaining_time": "0:11:14", "throughput": 3123.14, "total_tokens": 611248} +{"current_steps": 2145, "total_steps": 9520, "loss": 0.6478, "lr": 9.529988120178006e-06, "epoch": 4.506302521008403, "percentage": 22.53, "elapsed_time": "0:03:16", "remaining_time": "0:11:14", "throughput": 3123.34, "total_tokens": 612592} +{"current_steps": 2150, "total_steps": 9520, "loss": 0.5066, "lr": 9.52610042648741e-06, "epoch": 4.516806722689076, "percentage": 22.58, "elapsed_time": "0:03:16", "remaining_time": "0:11:13", "throughput": 3124.36, "total_tokens": 614128} +{"current_steps": 2155, "total_steps": 9520, "loss": 0.6678, "lr": 9.522197520145791e-06, "epoch": 4.527310924369748, "percentage": 22.64, "elapsed_time": "0:03:16", "remaining_time": "0:11:13", "throughput": 3124.59, "total_tokens": 615504} +{"current_steps": 2160, "total_steps": 9520, "loss": 0.5644, "lr": 9.518279414271184e-06, "epoch": 4.53781512605042, "percentage": 22.69, "elapsed_time": "0:03:17", "remaining_time": "0:11:12", "throughput": 3125.0, "total_tokens": 616912} +{"current_steps": 2165, "total_steps": 9520, "loss": 1.0491, "lr": 9.514346122032713e-06, "epoch": 4.548319327731092, "percentage": 22.74, "elapsed_time": "0:03:17", "remaining_time": "0:11:12", "throughput": 3125.07, "total_tokens": 618320} +{"current_steps": 2170, "total_steps": 9520, "loss": 0.5375, "lr": 9.510397656650544e-06, "epoch": 4.5588235294117645, "percentage": 22.79, "elapsed_time": "0:03:18", "remaining_time": "0:11:11", "throughput": 3125.51, "total_tokens": 619728} +{"current_steps": 2175, "total_steps": 9520, "loss": 0.6125, "lr": 9.506434031395843e-06, "epoch": 4.569327731092437, "percentage": 22.85, "elapsed_time": "0:03:18", "remaining_time": "0:11:11", "throughput": 3126.08, "total_tokens": 621200} +{"current_steps": 2180, "total_steps": 9520, "loss": 0.6038, "lr": 9.502455259590729e-06, "epoch": 4.579831932773109, "percentage": 22.9, "elapsed_time": "0:03:19", "remaining_time": "0:11:10", "throughput": 3126.96, "total_tokens": 622736} +{"current_steps": 2185, "total_steps": 9520, "loss": 0.703, "lr": 9.498461354608228e-06, "epoch": 4.590336134453781, "percentage": 22.95, "elapsed_time": "0:03:19", "remaining_time": "0:11:09", "throughput": 3127.18, "total_tokens": 624112} +{"current_steps": 2190, "total_steps": 9520, "loss": 0.8168, "lr": 9.494452329872234e-06, "epoch": 4.600840336134453, "percentage": 23.0, "elapsed_time": "0:03:20", "remaining_time": "0:11:09", "throughput": 3127.72, "total_tokens": 625552} +{"current_steps": 2195, "total_steps": 9520, "loss": 0.5358, "lr": 9.490428198857457e-06, "epoch": 4.6113445378151265, "percentage": 23.06, "elapsed_time": "0:03:20", "remaining_time": "0:11:08", "throughput": 3127.47, "total_tokens": 626768} +{"current_steps": 2200, "total_steps": 9520, "loss": 0.5927, "lr": 9.48638897508938e-06, "epoch": 4.621848739495798, "percentage": 23.11, "elapsed_time": "0:03:20", "remaining_time": "0:11:08", "throughput": 3127.89, "total_tokens": 628272} +{"current_steps": 2205, "total_steps": 9520, "loss": 0.4881, "lr": 9.48233467214422e-06, "epoch": 4.632352941176471, "percentage": 23.16, "elapsed_time": "0:03:21", "remaining_time": "0:11:07", "throughput": 3128.4, "total_tokens": 629712} +{"current_steps": 2210, "total_steps": 9520, "loss": 0.7895, "lr": 9.478265303648867e-06, "epoch": 4.642857142857143, "percentage": 23.21, "elapsed_time": "0:03:21", "remaining_time": "0:11:07", "throughput": 3128.35, "total_tokens": 630992} +{"current_steps": 2215, "total_steps": 9520, "loss": 0.6594, "lr": 9.474180883280857e-06, "epoch": 4.6533613445378155, "percentage": 23.27, "elapsed_time": "0:03:22", "remaining_time": "0:11:06", "throughput": 3128.23, "total_tokens": 632240} +{"current_steps": 2220, "total_steps": 9520, "loss": 0.5851, "lr": 9.47008142476831e-06, "epoch": 4.663865546218488, "percentage": 23.32, "elapsed_time": "0:03:22", "remaining_time": "0:11:05", "throughput": 3128.43, "total_tokens": 633584} +{"current_steps": 2225, "total_steps": 9520, "loss": 0.4914, "lr": 9.465966941889893e-06, "epoch": 4.67436974789916, "percentage": 23.37, "elapsed_time": "0:03:22", "remaining_time": "0:11:05", "throughput": 3128.79, "total_tokens": 634992} +{"current_steps": 2230, "total_steps": 9520, "loss": 0.494, "lr": 9.461837448474771e-06, "epoch": 4.684873949579832, "percentage": 23.42, "elapsed_time": "0:03:23", "remaining_time": "0:11:05", "throughput": 3129.24, "total_tokens": 636592} +{"current_steps": 2235, "total_steps": 9520, "loss": 0.6041, "lr": 9.457692958402566e-06, "epoch": 4.695378151260504, "percentage": 23.48, "elapsed_time": "0:03:23", "remaining_time": "0:11:04", "throughput": 3129.71, "total_tokens": 638000} +{"current_steps": 2240, "total_steps": 9520, "loss": 0.6682, "lr": 9.453533485603296e-06, "epoch": 4.705882352941177, "percentage": 23.53, "elapsed_time": "0:03:24", "remaining_time": "0:11:03", "throughput": 3130.07, "total_tokens": 639408} +{"current_steps": 2245, "total_steps": 9520, "loss": 0.5418, "lr": 9.449359044057344e-06, "epoch": 4.716386554621849, "percentage": 23.58, "elapsed_time": "0:03:24", "remaining_time": "0:11:03", "throughput": 3130.09, "total_tokens": 640688} +{"current_steps": 2250, "total_steps": 9520, "loss": 0.5575, "lr": 9.445169647795402e-06, "epoch": 4.726890756302521, "percentage": 23.63, "elapsed_time": "0:03:25", "remaining_time": "0:11:02", "throughput": 3130.39, "total_tokens": 642096} +{"current_steps": 2255, "total_steps": 9520, "loss": 0.3732, "lr": 9.440965310898425e-06, "epoch": 4.737394957983193, "percentage": 23.69, "elapsed_time": "0:03:25", "remaining_time": "0:11:02", "throughput": 3131.07, "total_tokens": 643568} +{"current_steps": 2260, "total_steps": 9520, "loss": 0.5282, "lr": 9.436746047497589e-06, "epoch": 4.7478991596638656, "percentage": 23.74, "elapsed_time": "0:03:25", "remaining_time": "0:11:01", "throughput": 3131.91, "total_tokens": 645104} +{"current_steps": 2265, "total_steps": 9520, "loss": 0.3717, "lr": 9.432511871774234e-06, "epoch": 4.758403361344538, "percentage": 23.79, "elapsed_time": "0:03:26", "remaining_time": "0:11:01", "throughput": 3132.86, "total_tokens": 646768} +{"current_steps": 2270, "total_steps": 9520, "loss": 0.5848, "lr": 9.428262797959828e-06, "epoch": 4.76890756302521, "percentage": 23.84, "elapsed_time": "0:03:26", "remaining_time": "0:11:00", "throughput": 3133.17, "total_tokens": 648144} +{"current_steps": 2275, "total_steps": 9520, "loss": 0.6559, "lr": 9.423998840335906e-06, "epoch": 4.779411764705882, "percentage": 23.9, "elapsed_time": "0:03:27", "remaining_time": "0:11:00", "throughput": 3133.69, "total_tokens": 649584} +{"current_steps": 2280, "total_steps": 9520, "loss": 0.4543, "lr": 9.419720013234035e-06, "epoch": 4.7899159663865545, "percentage": 23.95, "elapsed_time": "0:03:27", "remaining_time": "0:10:59", "throughput": 3133.94, "total_tokens": 650992} +{"current_steps": 2285, "total_steps": 9520, "loss": 0.5518, "lr": 9.415426331035754e-06, "epoch": 4.800420168067227, "percentage": 24.0, "elapsed_time": "0:03:28", "remaining_time": "0:10:59", "throughput": 3134.41, "total_tokens": 652432} +{"current_steps": 2290, "total_steps": 9520, "loss": 0.3992, "lr": 9.411117808172536e-06, "epoch": 4.810924369747899, "percentage": 24.05, "elapsed_time": "0:03:28", "remaining_time": "0:10:58", "throughput": 3135.48, "total_tokens": 654032} +{"current_steps": 2295, "total_steps": 9520, "loss": 0.5391, "lr": 9.406794459125735e-06, "epoch": 4.821428571428571, "percentage": 24.11, "elapsed_time": "0:03:29", "remaining_time": "0:10:58", "throughput": 3135.66, "total_tokens": 655472} +{"current_steps": 2300, "total_steps": 9520, "loss": 0.4813, "lr": 9.402456298426534e-06, "epoch": 4.831932773109243, "percentage": 24.16, "elapsed_time": "0:03:29", "remaining_time": "0:10:57", "throughput": 3135.79, "total_tokens": 656816} +{"current_steps": 2305, "total_steps": 9520, "loss": 0.477, "lr": 9.3981033406559e-06, "epoch": 4.842436974789916, "percentage": 24.21, "elapsed_time": "0:03:29", "remaining_time": "0:10:56", "throughput": 3135.92, "total_tokens": 658160} +{"current_steps": 2310, "total_steps": 9520, "loss": 0.5902, "lr": 9.393735600444536e-06, "epoch": 4.852941176470588, "percentage": 24.26, "elapsed_time": "0:03:30", "remaining_time": "0:10:56", "throughput": 3136.8, "total_tokens": 659824} +{"current_steps": 2315, "total_steps": 9520, "loss": 0.5025, "lr": 9.38935309247283e-06, "epoch": 4.86344537815126, "percentage": 24.32, "elapsed_time": "0:03:30", "remaining_time": "0:10:56", "throughput": 3137.27, "total_tokens": 661328} +{"current_steps": 2320, "total_steps": 9520, "loss": 0.9927, "lr": 9.384955831470805e-06, "epoch": 4.873949579831933, "percentage": 24.37, "elapsed_time": "0:03:31", "remaining_time": "0:10:55", "throughput": 3137.41, "total_tokens": 662672} +{"current_steps": 2325, "total_steps": 9520, "loss": 0.3892, "lr": 9.380543832218069e-06, "epoch": 4.884453781512605, "percentage": 24.42, "elapsed_time": "0:03:31", "remaining_time": "0:10:54", "throughput": 3138.38, "total_tokens": 664240} +{"current_steps": 2330, "total_steps": 9520, "loss": 0.7993, "lr": 9.376117109543769e-06, "epoch": 4.894957983193278, "percentage": 24.47, "elapsed_time": "0:03:32", "remaining_time": "0:10:54", "throughput": 3138.76, "total_tokens": 665648} +{"current_steps": 2335, "total_steps": 9520, "loss": 0.7316, "lr": 9.37167567832654e-06, "epoch": 4.90546218487395, "percentage": 24.53, "elapsed_time": "0:03:32", "remaining_time": "0:10:53", "throughput": 3139.43, "total_tokens": 667120} +{"current_steps": 2340, "total_steps": 9520, "loss": 0.4148, "lr": 9.36721955349445e-06, "epoch": 4.915966386554622, "percentage": 24.58, "elapsed_time": "0:03:32", "remaining_time": "0:10:53", "throughput": 3140.02, "total_tokens": 668592} +{"current_steps": 2345, "total_steps": 9520, "loss": 0.8296, "lr": 9.362748750024953e-06, "epoch": 4.926470588235294, "percentage": 24.63, "elapsed_time": "0:03:33", "remaining_time": "0:10:52", "throughput": 3140.03, "total_tokens": 669904} +{"current_steps": 2350, "total_steps": 9520, "loss": 0.7261, "lr": 9.358263282944846e-06, "epoch": 4.936974789915967, "percentage": 24.68, "elapsed_time": "0:03:33", "remaining_time": "0:10:52", "throughput": 3139.75, "total_tokens": 671120} +{"current_steps": 2355, "total_steps": 9520, "loss": 0.5822, "lr": 9.353763167330206e-06, "epoch": 4.947478991596639, "percentage": 24.74, "elapsed_time": "0:03:34", "remaining_time": "0:10:51", "throughput": 3140.46, "total_tokens": 672720} +{"current_steps": 2360, "total_steps": 9520, "loss": 0.4699, "lr": 9.349248418306347e-06, "epoch": 4.957983193277311, "percentage": 24.79, "elapsed_time": "0:03:34", "remaining_time": "0:10:51", "throughput": 3140.69, "total_tokens": 674096} +{"current_steps": 2365, "total_steps": 9520, "loss": 0.3303, "lr": 9.344719051047766e-06, "epoch": 4.968487394957983, "percentage": 24.84, "elapsed_time": "0:03:35", "remaining_time": "0:10:50", "throughput": 3140.5, "total_tokens": 675344} +{"current_steps": 2370, "total_steps": 9520, "loss": 0.5144, "lr": 9.340175080778096e-06, "epoch": 4.9789915966386555, "percentage": 24.89, "elapsed_time": "0:03:35", "remaining_time": "0:10:50", "throughput": 3140.58, "total_tokens": 676656} +{"current_steps": 2375, "total_steps": 9520, "loss": 0.5648, "lr": 9.335616522770046e-06, "epoch": 4.989495798319328, "percentage": 24.95, "elapsed_time": "0:03:35", "remaining_time": "0:10:49", "throughput": 3141.4, "total_tokens": 678288} +{"current_steps": 2380, "total_steps": 9520, "loss": 0.7983, "lr": 9.331043392345365e-06, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:03:36", "remaining_time": "0:10:49", "throughput": 3141.12, "total_tokens": 679688} +{"current_steps": 2385, "total_steps": 9520, "loss": 0.4836, "lr": 9.326455704874772e-06, "epoch": 5.010504201680672, "percentage": 25.05, "elapsed_time": "0:03:36", "remaining_time": "0:10:48", "throughput": 3140.56, "total_tokens": 681160} +{"current_steps": 2390, "total_steps": 9520, "loss": 0.6424, "lr": 9.321853475777921e-06, "epoch": 5.0210084033613445, "percentage": 25.11, "elapsed_time": "0:03:37", "remaining_time": "0:10:48", "throughput": 3140.63, "total_tokens": 682504} +{"current_steps": 2395, "total_steps": 9520, "loss": 0.4202, "lr": 9.317236720523338e-06, "epoch": 5.031512605042017, "percentage": 25.16, "elapsed_time": "0:03:37", "remaining_time": "0:10:47", "throughput": 3141.1, "total_tokens": 683976} +{"current_steps": 2400, "total_steps": 9520, "loss": 0.5347, "lr": 9.312605454628373e-06, "epoch": 5.042016806722689, "percentage": 25.21, "elapsed_time": "0:03:38", "remaining_time": "0:10:47", "throughput": 3141.15, "total_tokens": 685288} +{"current_steps": 2405, "total_steps": 9520, "loss": 0.6284, "lr": 9.307959693659149e-06, "epoch": 5.052521008403361, "percentage": 25.26, "elapsed_time": "0:03:38", "remaining_time": "0:10:46", "throughput": 3141.65, "total_tokens": 686760} +{"current_steps": 2410, "total_steps": 9520, "loss": 0.6021, "lr": 9.303299453230505e-06, "epoch": 5.063025210084033, "percentage": 25.32, "elapsed_time": "0:03:39", "remaining_time": "0:10:46", "throughput": 3142.57, "total_tokens": 688328} +{"current_steps": 2415, "total_steps": 9520, "loss": 0.5997, "lr": 9.298624749005953e-06, "epoch": 5.073529411764706, "percentage": 25.37, "elapsed_time": "0:03:39", "remaining_time": "0:10:45", "throughput": 3143.04, "total_tokens": 689768} +{"current_steps": 2420, "total_steps": 9520, "loss": 0.6352, "lr": 9.293935596697611e-06, "epoch": 5.084033613445378, "percentage": 25.42, "elapsed_time": "0:03:39", "remaining_time": "0:10:45", "throughput": 3143.02, "total_tokens": 691048} +{"current_steps": 2425, "total_steps": 9520, "loss": 0.3752, "lr": 9.289232012066166e-06, "epoch": 5.09453781512605, "percentage": 25.47, "elapsed_time": "0:03:40", "remaining_time": "0:10:44", "throughput": 3143.43, "total_tokens": 692488} +{"current_steps": 2430, "total_steps": 9520, "loss": 0.5944, "lr": 9.28451401092081e-06, "epoch": 5.105042016806722, "percentage": 25.53, "elapsed_time": "0:03:40", "remaining_time": "0:10:43", "throughput": 3143.43, "total_tokens": 693768} +{"current_steps": 2435, "total_steps": 9520, "loss": 0.6689, "lr": 9.279781609119189e-06, "epoch": 5.1155462184873945, "percentage": 25.58, "elapsed_time": "0:03:41", "remaining_time": "0:10:43", "throughput": 3143.34, "total_tokens": 695016} +{"current_steps": 2440, "total_steps": 9520, "loss": 0.3506, "lr": 9.275034822567354e-06, "epoch": 5.126050420168067, "percentage": 25.63, "elapsed_time": "0:03:41", "remaining_time": "0:10:42", "throughput": 3143.31, "total_tokens": 696328} +{"current_steps": 2445, "total_steps": 9520, "loss": 0.6503, "lr": 9.2702736672197e-06, "epoch": 5.13655462184874, "percentage": 25.68, "elapsed_time": "0:03:41", "remaining_time": "0:10:42", "throughput": 3143.48, "total_tokens": 697768} +{"current_steps": 2450, "total_steps": 9520, "loss": 0.5864, "lr": 9.265498159078924e-06, "epoch": 5.147058823529412, "percentage": 25.74, "elapsed_time": "0:03:42", "remaining_time": "0:10:41", "throughput": 3144.06, "total_tokens": 699240} +{"current_steps": 2455, "total_steps": 9520, "loss": 0.4777, "lr": 9.260708314195958e-06, "epoch": 5.157563025210084, "percentage": 25.79, "elapsed_time": "0:03:42", "remaining_time": "0:10:41", "throughput": 3144.52, "total_tokens": 700680} +{"current_steps": 2460, "total_steps": 9520, "loss": 0.5454, "lr": 9.255904148669922e-06, "epoch": 5.168067226890757, "percentage": 25.84, "elapsed_time": "0:03:43", "remaining_time": "0:10:40", "throughput": 3144.83, "total_tokens": 702088} +{"current_steps": 2465, "total_steps": 9520, "loss": 0.5276, "lr": 9.251085678648072e-06, "epoch": 5.178571428571429, "percentage": 25.89, "elapsed_time": "0:03:43", "remaining_time": "0:10:40", "throughput": 3144.87, "total_tokens": 703368} +{"current_steps": 2470, "total_steps": 9520, "loss": 0.4832, "lr": 9.246252920325738e-06, "epoch": 5.189075630252101, "percentage": 25.95, "elapsed_time": "0:03:44", "remaining_time": "0:10:39", "throughput": 3144.79, "total_tokens": 704680} +{"current_steps": 2475, "total_steps": 9520, "loss": 0.4773, "lr": 9.24140588994628e-06, "epoch": 5.199579831932773, "percentage": 26.0, "elapsed_time": "0:03:44", "remaining_time": "0:10:39", "throughput": 3144.63, "total_tokens": 706024} +{"current_steps": 2480, "total_steps": 9520, "loss": 0.5651, "lr": 9.236544603801025e-06, "epoch": 5.2100840336134455, "percentage": 26.05, "elapsed_time": "0:03:44", "remaining_time": "0:10:38", "throughput": 3144.87, "total_tokens": 707400} +{"current_steps": 2485, "total_steps": 9520, "loss": 0.5449, "lr": 9.231669078229212e-06, "epoch": 5.220588235294118, "percentage": 26.1, "elapsed_time": "0:03:45", "remaining_time": "0:10:38", "throughput": 3145.34, "total_tokens": 708936} +{"current_steps": 2490, "total_steps": 9520, "loss": 0.6819, "lr": 9.226779329617947e-06, "epoch": 5.23109243697479, "percentage": 26.16, "elapsed_time": "0:03:45", "remaining_time": "0:10:37", "throughput": 3145.62, "total_tokens": 710312} +{"current_steps": 2495, "total_steps": 9520, "loss": 0.4663, "lr": 9.221875374402134e-06, "epoch": 5.241596638655462, "percentage": 26.21, "elapsed_time": "0:03:46", "remaining_time": "0:10:37", "throughput": 3146.48, "total_tokens": 711944} +{"current_steps": 2500, "total_steps": 9520, "loss": 0.721, "lr": 9.21695722906443e-06, "epoch": 5.2521008403361344, "percentage": 26.26, "elapsed_time": "0:03:46", "remaining_time": "0:10:36", "throughput": 3146.6, "total_tokens": 713320} +{"current_steps": 2505, "total_steps": 9520, "loss": 0.4608, "lr": 9.212024910135186e-06, "epoch": 5.262605042016807, "percentage": 26.31, "elapsed_time": "0:03:47", "remaining_time": "0:10:36", "throughput": 3146.91, "total_tokens": 714728} +{"current_steps": 2510, "total_steps": 9520, "loss": 0.5441, "lr": 9.20707843419239e-06, "epoch": 5.273109243697479, "percentage": 26.37, "elapsed_time": "0:03:47", "remaining_time": "0:10:35", "throughput": 3146.87, "total_tokens": 716008} +{"current_steps": 2515, "total_steps": 9520, "loss": 0.491, "lr": 9.202117817861621e-06, "epoch": 5.283613445378151, "percentage": 26.42, "elapsed_time": "0:03:47", "remaining_time": "0:10:34", "throughput": 3147.41, "total_tokens": 717480} +{"current_steps": 2520, "total_steps": 9520, "loss": 0.404, "lr": 9.197143077815973e-06, "epoch": 5.294117647058823, "percentage": 26.47, "elapsed_time": "0:03:48", "remaining_time": "0:10:34", "throughput": 3147.66, "total_tokens": 718856} +{"current_steps": 2525, "total_steps": 9520, "loss": 0.4646, "lr": 9.192154230776021e-06, "epoch": 5.304621848739496, "percentage": 26.52, "elapsed_time": "0:03:48", "remaining_time": "0:10:33", "throughput": 3147.98, "total_tokens": 720264} +{"current_steps": 2530, "total_steps": 9520, "loss": 0.3298, "lr": 9.187151293509745e-06, "epoch": 5.315126050420168, "percentage": 26.58, "elapsed_time": "0:03:49", "remaining_time": "0:10:33", "throughput": 3148.08, "total_tokens": 721576} +{"current_steps": 2535, "total_steps": 9520, "loss": 0.3891, "lr": 9.182134282832498e-06, "epoch": 5.32563025210084, "percentage": 26.63, "elapsed_time": "0:03:49", "remaining_time": "0:10:32", "throughput": 3148.72, "total_tokens": 723080} +{"current_steps": 2540, "total_steps": 9520, "loss": 0.4033, "lr": 9.177103215606921e-06, "epoch": 5.336134453781512, "percentage": 26.68, "elapsed_time": "0:03:50", "remaining_time": "0:10:32", "throughput": 3148.98, "total_tokens": 724456} +{"current_steps": 2545, "total_steps": 9520, "loss": 0.5278, "lr": 9.172058108742908e-06, "epoch": 5.3466386554621845, "percentage": 26.73, "elapsed_time": "0:03:50", "remaining_time": "0:10:31", "throughput": 3149.69, "total_tokens": 725992} +{"current_steps": 2550, "total_steps": 9520, "loss": 0.5143, "lr": 9.16699897919754e-06, "epoch": 5.357142857142857, "percentage": 26.79, "elapsed_time": "0:03:50", "remaining_time": "0:10:31", "throughput": 3150.09, "total_tokens": 727432} +{"current_steps": 2555, "total_steps": 9520, "loss": 0.4754, "lr": 9.161925843975027e-06, "epoch": 5.367647058823529, "percentage": 26.84, "elapsed_time": "0:03:51", "remaining_time": "0:10:30", "throughput": 3150.69, "total_tokens": 728936} +{"current_steps": 2560, "total_steps": 9520, "loss": 0.3785, "lr": 9.15683872012666e-06, "epoch": 5.378151260504202, "percentage": 26.89, "elapsed_time": "0:03:51", "remaining_time": "0:10:30", "throughput": 3150.81, "total_tokens": 730280} +{"current_steps": 2565, "total_steps": 9520, "loss": 0.4894, "lr": 9.151737624750738e-06, "epoch": 5.388655462184874, "percentage": 26.94, "elapsed_time": "0:03:52", "remaining_time": "0:10:29", "throughput": 3151.26, "total_tokens": 731752} +{"current_steps": 2570, "total_steps": 9520, "loss": 0.482, "lr": 9.146622574992528e-06, "epoch": 5.399159663865547, "percentage": 27.0, "elapsed_time": "0:03:52", "remaining_time": "0:10:29", "throughput": 3151.66, "total_tokens": 733288} +{"current_steps": 2575, "total_steps": 9520, "loss": 0.6679, "lr": 9.141493588044194e-06, "epoch": 5.409663865546219, "percentage": 27.05, "elapsed_time": "0:03:53", "remaining_time": "0:10:28", "throughput": 3152.07, "total_tokens": 734728} +{"current_steps": 2580, "total_steps": 9520, "loss": 0.4818, "lr": 9.136350681144744e-06, "epoch": 5.420168067226891, "percentage": 27.1, "elapsed_time": "0:03:53", "remaining_time": "0:10:28", "throughput": 3153.2, "total_tokens": 736488} +{"current_steps": 2585, "total_steps": 9520, "loss": 0.5069, "lr": 9.131193871579975e-06, "epoch": 5.430672268907563, "percentage": 27.15, "elapsed_time": "0:03:54", "remaining_time": "0:10:27", "throughput": 3154.15, "total_tokens": 738088} +{"current_steps": 2590, "total_steps": 9520, "loss": 0.6062, "lr": 9.126023176682413e-06, "epoch": 5.4411764705882355, "percentage": 27.21, "elapsed_time": "0:03:54", "remaining_time": "0:10:27", "throughput": 3154.36, "total_tokens": 739464} +{"current_steps": 2595, "total_steps": 9520, "loss": 0.4465, "lr": 9.12083861383125e-06, "epoch": 5.451680672268908, "percentage": 27.26, "elapsed_time": "0:03:54", "remaining_time": "0:10:26", "throughput": 3154.69, "total_tokens": 740968} +{"current_steps": 2600, "total_steps": 9520, "loss": 0.7317, "lr": 9.115640200452289e-06, "epoch": 5.46218487394958, "percentage": 27.31, "elapsed_time": "0:03:55", "remaining_time": "0:10:26", "throughput": 3154.72, "total_tokens": 742312} +{"current_steps": 2605, "total_steps": 9520, "loss": 0.3987, "lr": 9.110427954017891e-06, "epoch": 5.472689075630252, "percentage": 27.36, "elapsed_time": "0:03:55", "remaining_time": "0:10:25", "throughput": 3155.46, "total_tokens": 743848} +{"current_steps": 2610, "total_steps": 9520, "loss": 0.4809, "lr": 9.10520189204691e-06, "epoch": 5.483193277310924, "percentage": 27.42, "elapsed_time": "0:03:56", "remaining_time": "0:10:25", "throughput": 3155.92, "total_tokens": 745384} +{"current_steps": 2615, "total_steps": 9520, "loss": 0.4253, "lr": 9.099962032104634e-06, "epoch": 5.493697478991597, "percentage": 27.47, "elapsed_time": "0:03:56", "remaining_time": "0:10:24", "throughput": 3156.0, "total_tokens": 746728} +{"current_steps": 2620, "total_steps": 9520, "loss": 0.4473, "lr": 9.094708391802725e-06, "epoch": 5.504201680672269, "percentage": 27.52, "elapsed_time": "0:03:57", "remaining_time": "0:10:24", "throughput": 3156.21, "total_tokens": 748200} +{"current_steps": 2625, "total_steps": 9520, "loss": 0.5079, "lr": 9.089440988799164e-06, "epoch": 5.514705882352941, "percentage": 27.57, "elapsed_time": "0:03:57", "remaining_time": "0:10:23", "throughput": 3155.91, "total_tokens": 749416} +{"current_steps": 2630, "total_steps": 9520, "loss": 0.5348, "lr": 9.08415984079819e-06, "epoch": 5.525210084033613, "percentage": 27.63, "elapsed_time": "0:03:57", "remaining_time": "0:10:23", "throughput": 3156.12, "total_tokens": 750888} +{"current_steps": 2635, "total_steps": 9520, "loss": 0.62, "lr": 9.07886496555024e-06, "epoch": 5.535714285714286, "percentage": 27.68, "elapsed_time": "0:03:58", "remaining_time": "0:10:22", "throughput": 3156.52, "total_tokens": 752328} +{"current_steps": 2640, "total_steps": 9520, "loss": 0.4965, "lr": 9.073556380851894e-06, "epoch": 5.546218487394958, "percentage": 27.73, "elapsed_time": "0:03:58", "remaining_time": "0:10:22", "throughput": 3156.81, "total_tokens": 753736} +{"current_steps": 2645, "total_steps": 9520, "loss": 0.6409, "lr": 9.0682341045458e-06, "epoch": 5.55672268907563, "percentage": 27.78, "elapsed_time": "0:03:59", "remaining_time": "0:10:21", "throughput": 3157.15, "total_tokens": 755144} +{"current_steps": 2650, "total_steps": 9520, "loss": 0.5209, "lr": 9.062898154520638e-06, "epoch": 5.567226890756302, "percentage": 27.84, "elapsed_time": "0:03:59", "remaining_time": "0:10:21", "throughput": 3157.45, "total_tokens": 756552} +{"current_steps": 2655, "total_steps": 9520, "loss": 0.5304, "lr": 9.057548548711035e-06, "epoch": 5.5777310924369745, "percentage": 27.89, "elapsed_time": "0:04:00", "remaining_time": "0:10:20", "throughput": 3157.48, "total_tokens": 757864} +{"current_steps": 2660, "total_steps": 9520, "loss": 0.6505, "lr": 9.052185305097526e-06, "epoch": 5.588235294117647, "percentage": 27.94, "elapsed_time": "0:04:00", "remaining_time": "0:10:20", "throughput": 3157.72, "total_tokens": 759336} +{"current_steps": 2665, "total_steps": 9520, "loss": 0.7228, "lr": 9.046808441706474e-06, "epoch": 5.598739495798319, "percentage": 27.99, "elapsed_time": "0:04:00", "remaining_time": "0:10:19", "throughput": 3157.99, "total_tokens": 760744} +{"current_steps": 2670, "total_steps": 9520, "loss": 0.5678, "lr": 9.041417976610028e-06, "epoch": 5.609243697478991, "percentage": 28.05, "elapsed_time": "0:04:01", "remaining_time": "0:10:19", "throughput": 3158.27, "total_tokens": 762152} +{"current_steps": 2675, "total_steps": 9520, "loss": 0.3927, "lr": 9.036013927926049e-06, "epoch": 5.619747899159664, "percentage": 28.1, "elapsed_time": "0:04:01", "remaining_time": "0:10:18", "throughput": 3158.74, "total_tokens": 763624} +{"current_steps": 2680, "total_steps": 9520, "loss": 0.6891, "lr": 9.030596313818055e-06, "epoch": 5.630252100840336, "percentage": 28.15, "elapsed_time": "0:04:02", "remaining_time": "0:10:18", "throughput": 3159.05, "total_tokens": 765032} +{"current_steps": 2685, "total_steps": 9520, "loss": 0.6652, "lr": 9.02516515249516e-06, "epoch": 5.640756302521009, "percentage": 28.2, "elapsed_time": "0:04:02", "remaining_time": "0:10:17", "throughput": 3159.24, "total_tokens": 766408} +{"current_steps": 2690, "total_steps": 9520, "loss": 0.624, "lr": 9.01972046221201e-06, "epoch": 5.651260504201681, "percentage": 28.26, "elapsed_time": "0:04:03", "remaining_time": "0:10:17", "throughput": 3159.39, "total_tokens": 767784} +{"current_steps": 2695, "total_steps": 9520, "loss": 0.4825, "lr": 9.014262261268723e-06, "epoch": 5.661764705882353, "percentage": 28.31, "elapsed_time": "0:04:03", "remaining_time": "0:10:16", "throughput": 3160.24, "total_tokens": 769480} +{"current_steps": 2700, "total_steps": 9520, "loss": 0.6625, "lr": 9.008790568010828e-06, "epoch": 5.6722689075630255, "percentage": 28.36, "elapsed_time": "0:04:03", "remaining_time": "0:10:16", "throughput": 3160.96, "total_tokens": 771016} +{"current_steps": 2705, "total_steps": 9520, "loss": 0.5319, "lr": 9.0033054008292e-06, "epoch": 5.682773109243698, "percentage": 28.41, "elapsed_time": "0:04:04", "remaining_time": "0:10:15", "throughput": 3161.96, "total_tokens": 772680} +{"current_steps": 2710, "total_steps": 9520, "loss": 0.5151, "lr": 8.997806778160009e-06, "epoch": 5.69327731092437, "percentage": 28.47, "elapsed_time": "0:04:04", "remaining_time": "0:10:15", "throughput": 3162.21, "total_tokens": 774088} +{"current_steps": 2715, "total_steps": 9520, "loss": 0.5685, "lr": 8.992294718484643e-06, "epoch": 5.703781512605042, "percentage": 28.52, "elapsed_time": "0:04:05", "remaining_time": "0:10:14", "throughput": 3162.28, "total_tokens": 775432} +{"current_steps": 2720, "total_steps": 9520, "loss": 0.4709, "lr": 8.986769240329653e-06, "epoch": 5.714285714285714, "percentage": 28.57, "elapsed_time": "0:04:05", "remaining_time": "0:10:14", "throughput": 3162.66, "total_tokens": 776904} +{"current_steps": 2725, "total_steps": 9520, "loss": 0.4662, "lr": 8.981230362266695e-06, "epoch": 5.724789915966387, "percentage": 28.62, "elapsed_time": "0:04:06", "remaining_time": "0:10:13", "throughput": 3162.69, "total_tokens": 778216} +{"current_steps": 2730, "total_steps": 9520, "loss": 0.6779, "lr": 8.975678102912463e-06, "epoch": 5.735294117647059, "percentage": 28.68, "elapsed_time": "0:04:06", "remaining_time": "0:10:13", "throughput": 3162.71, "total_tokens": 779528} +{"current_steps": 2735, "total_steps": 9520, "loss": 0.5045, "lr": 8.970112480928621e-06, "epoch": 5.745798319327731, "percentage": 28.73, "elapsed_time": "0:04:06", "remaining_time": "0:10:12", "throughput": 3162.84, "total_tokens": 780872} +{"current_steps": 2740, "total_steps": 9520, "loss": 0.5377, "lr": 8.964533515021754e-06, "epoch": 5.756302521008403, "percentage": 28.78, "elapsed_time": "0:04:07", "remaining_time": "0:10:12", "throughput": 3163.53, "total_tokens": 782440} +{"current_steps": 2745, "total_steps": 9520, "loss": 0.5894, "lr": 8.958941223943292e-06, "epoch": 5.766806722689076, "percentage": 28.83, "elapsed_time": "0:04:07", "remaining_time": "0:10:11", "throughput": 3164.23, "total_tokens": 784008} +{"current_steps": 2750, "total_steps": 9520, "loss": 0.3394, "lr": 8.953335626489453e-06, "epoch": 5.777310924369748, "percentage": 28.89, "elapsed_time": "0:04:08", "remaining_time": "0:10:11", "throughput": 3165.22, "total_tokens": 785768} +{"current_steps": 2755, "total_steps": 9520, "loss": 0.4363, "lr": 8.947716741501178e-06, "epoch": 5.78781512605042, "percentage": 28.94, "elapsed_time": "0:04:08", "remaining_time": "0:10:10", "throughput": 3165.54, "total_tokens": 787176} +{"current_steps": 2760, "total_steps": 9520, "loss": 0.6749, "lr": 8.942084587864072e-06, "epoch": 5.798319327731092, "percentage": 28.99, "elapsed_time": "0:04:09", "remaining_time": "0:10:10", "throughput": 3166.03, "total_tokens": 788680} +{"current_steps": 2765, "total_steps": 9520, "loss": 0.3684, "lr": 8.936439184508336e-06, "epoch": 5.8088235294117645, "percentage": 29.04, "elapsed_time": "0:04:09", "remaining_time": "0:10:09", "throughput": 3166.39, "total_tokens": 790120} +{"current_steps": 2770, "total_steps": 9520, "loss": 0.8076, "lr": 8.930780550408704e-06, "epoch": 5.819327731092437, "percentage": 29.1, "elapsed_time": "0:04:09", "remaining_time": "0:10:09", "throughput": 3166.38, "total_tokens": 791432} +{"current_steps": 2775, "total_steps": 9520, "loss": 0.4709, "lr": 8.925108704584378e-06, "epoch": 5.829831932773109, "percentage": 29.15, "elapsed_time": "0:04:10", "remaining_time": "0:10:08", "throughput": 3166.88, "total_tokens": 793000} +{"current_steps": 2780, "total_steps": 9520, "loss": 0.4541, "lr": 8.91942366609897e-06, "epoch": 5.840336134453781, "percentage": 29.2, "elapsed_time": "0:04:10", "remaining_time": "0:10:08", "throughput": 3167.09, "total_tokens": 794408} +{"current_steps": 2785, "total_steps": 9520, "loss": 0.3512, "lr": 8.913725454060427e-06, "epoch": 5.850840336134453, "percentage": 29.25, "elapsed_time": "0:04:11", "remaining_time": "0:10:07", "throughput": 3167.39, "total_tokens": 795848} +{"current_steps": 2790, "total_steps": 9520, "loss": 0.5521, "lr": 8.908014087620983e-06, "epoch": 5.8613445378151265, "percentage": 29.31, "elapsed_time": "0:04:11", "remaining_time": "0:10:07", "throughput": 3167.48, "total_tokens": 797192} +{"current_steps": 2795, "total_steps": 9520, "loss": 0.5864, "lr": 8.902289585977074e-06, "epoch": 5.871848739495798, "percentage": 29.36, "elapsed_time": "0:04:12", "remaining_time": "0:10:06", "throughput": 3167.65, "total_tokens": 798568} +{"current_steps": 2800, "total_steps": 9520, "loss": 0.4442, "lr": 8.896551968369297e-06, "epoch": 5.882352941176471, "percentage": 29.41, "elapsed_time": "0:04:12", "remaining_time": "0:10:06", "throughput": 3167.99, "total_tokens": 800008} +{"current_steps": 2805, "total_steps": 9520, "loss": 0.3384, "lr": 8.890801254082322e-06, "epoch": 5.892857142857143, "percentage": 29.46, "elapsed_time": "0:04:12", "remaining_time": "0:10:05", "throughput": 3168.67, "total_tokens": 801640} +{"current_steps": 2810, "total_steps": 9520, "loss": 0.5883, "lr": 8.885037462444848e-06, "epoch": 5.9033613445378155, "percentage": 29.52, "elapsed_time": "0:04:13", "remaining_time": "0:10:05", "throughput": 3169.03, "total_tokens": 803080} +{"current_steps": 2815, "total_steps": 9520, "loss": 0.3567, "lr": 8.879260612829517e-06, "epoch": 5.913865546218488, "percentage": 29.57, "elapsed_time": "0:04:13", "remaining_time": "0:10:04", "throughput": 3169.43, "total_tokens": 804520} +{"current_steps": 2820, "total_steps": 9520, "loss": 0.6124, "lr": 8.87347072465287e-06, "epoch": 5.92436974789916, "percentage": 29.62, "elapsed_time": "0:04:14", "remaining_time": "0:10:04", "throughput": 3169.51, "total_tokens": 805864} +{"current_steps": 2825, "total_steps": 9520, "loss": 0.3525, "lr": 8.867667817375266e-06, "epoch": 5.934873949579832, "percentage": 29.67, "elapsed_time": "0:04:14", "remaining_time": "0:10:03", "throughput": 3169.87, "total_tokens": 807336} +{"current_steps": 2830, "total_steps": 9520, "loss": 0.3117, "lr": 8.861851910500828e-06, "epoch": 5.945378151260504, "percentage": 29.73, "elapsed_time": "0:04:15", "remaining_time": "0:10:03", "throughput": 3170.07, "total_tokens": 808712} +{"current_steps": 2835, "total_steps": 9520, "loss": 0.5191, "lr": 8.856023023577363e-06, "epoch": 5.955882352941177, "percentage": 29.78, "elapsed_time": "0:04:15", "remaining_time": "0:10:02", "throughput": 3170.39, "total_tokens": 810152} +{"current_steps": 2840, "total_steps": 9520, "loss": 0.4357, "lr": 8.850181176196316e-06, "epoch": 5.966386554621849, "percentage": 29.83, "elapsed_time": "0:04:15", "remaining_time": "0:10:02", "throughput": 3171.04, "total_tokens": 811720} +{"current_steps": 2845, "total_steps": 9520, "loss": 0.4524, "lr": 8.844326387992683e-06, "epoch": 5.976890756302521, "percentage": 29.88, "elapsed_time": "0:04:16", "remaining_time": "0:10:01", "throughput": 3171.2, "total_tokens": 813128} +{"current_steps": 2850, "total_steps": 9520, "loss": 0.6336, "lr": 8.838458678644963e-06, "epoch": 5.987394957983193, "percentage": 29.94, "elapsed_time": "0:04:16", "remaining_time": "0:10:01", "throughput": 3171.56, "total_tokens": 814568} +{"current_steps": 2855, "total_steps": 9520, "loss": 0.3083, "lr": 8.83257806787508e-06, "epoch": 5.9978991596638656, "percentage": 29.99, "elapsed_time": "0:04:17", "remaining_time": "0:10:00", "throughput": 3172.22, "total_tokens": 816104} +{"current_steps": 2856, "total_steps": 9520, "eval_loss": 0.7400283813476562, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "0:04:22", "remaining_time": "0:10:11", "throughput": 3114.54, "total_tokens": 816320} +{"current_steps": 2860, "total_steps": 9520, "loss": 0.2777, "lr": 8.826684575448324e-06, "epoch": 6.008403361344538, "percentage": 30.04, "elapsed_time": "0:04:23", "remaining_time": "0:10:13", "throughput": 3102.95, "total_tokens": 817600} +{"current_steps": 2865, "total_steps": 9520, "loss": 0.462, "lr": 8.82077822117328e-06, "epoch": 6.01890756302521, "percentage": 30.09, "elapsed_time": "0:04:23", "remaining_time": "0:10:13", "throughput": 3103.78, "total_tokens": 819168} +{"current_steps": 2870, "total_steps": 9520, "loss": 0.3276, "lr": 8.814859024901756e-06, "epoch": 6.029411764705882, "percentage": 30.15, "elapsed_time": "0:04:24", "remaining_time": "0:10:12", "throughput": 3104.58, "total_tokens": 820736} +{"current_steps": 2875, "total_steps": 9520, "loss": 0.3219, "lr": 8.808927006528739e-06, "epoch": 6.0399159663865545, "percentage": 30.2, "elapsed_time": "0:04:24", "remaining_time": "0:10:11", "throughput": 3104.89, "total_tokens": 822112} +{"current_steps": 2880, "total_steps": 9520, "loss": 0.5848, "lr": 8.802982185992297e-06, "epoch": 6.050420168067227, "percentage": 30.25, "elapsed_time": "0:04:25", "remaining_time": "0:10:11", "throughput": 3104.98, "total_tokens": 823456} +{"current_steps": 2885, "total_steps": 9520, "loss": 0.5354, "lr": 8.797024583273536e-06, "epoch": 6.060924369747899, "percentage": 30.3, "elapsed_time": "0:04:25", "remaining_time": "0:10:10", "throughput": 3104.97, "total_tokens": 824768} +{"current_steps": 2890, "total_steps": 9520, "loss": 0.4747, "lr": 8.79105421839652e-06, "epoch": 6.071428571428571, "percentage": 30.36, "elapsed_time": "0:04:26", "remaining_time": "0:10:10", "throughput": 3104.95, "total_tokens": 826048} +{"current_steps": 2895, "total_steps": 9520, "loss": 0.612, "lr": 8.785071111428211e-06, "epoch": 6.081932773109243, "percentage": 30.41, "elapsed_time": "0:04:26", "remaining_time": "0:10:09", "throughput": 3105.44, "total_tokens": 827520} +{"current_steps": 2900, "total_steps": 9520, "loss": 0.4334, "lr": 8.779075282478395e-06, "epoch": 6.092436974789916, "percentage": 30.46, "elapsed_time": "0:04:26", "remaining_time": "0:10:09", "throughput": 3105.65, "total_tokens": 828960} +{"current_steps": 2905, "total_steps": 9520, "loss": 0.5131, "lr": 8.77306675169962e-06, "epoch": 6.102941176470588, "percentage": 30.51, "elapsed_time": "0:04:27", "remaining_time": "0:10:08", "throughput": 3106.03, "total_tokens": 830464} +{"current_steps": 2910, "total_steps": 9520, "loss": 0.4119, "lr": 8.767045539287125e-06, "epoch": 6.11344537815126, "percentage": 30.57, "elapsed_time": "0:04:27", "remaining_time": "0:10:08", "throughput": 3106.39, "total_tokens": 831872} +{"current_steps": 2915, "total_steps": 9520, "loss": 0.6755, "lr": 8.761011665478775e-06, "epoch": 6.123949579831933, "percentage": 30.62, "elapsed_time": "0:04:28", "remaining_time": "0:10:07", "throughput": 3106.92, "total_tokens": 833344} +{"current_steps": 2920, "total_steps": 9520, "loss": 0.5107, "lr": 8.754965150554988e-06, "epoch": 6.1344537815126055, "percentage": 30.67, "elapsed_time": "0:04:28", "remaining_time": "0:10:07", "throughput": 3107.13, "total_tokens": 834752} +{"current_steps": 2925, "total_steps": 9520, "loss": 0.3165, "lr": 8.748906014838672e-06, "epoch": 6.144957983193278, "percentage": 30.72, "elapsed_time": "0:04:29", "remaining_time": "0:10:06", "throughput": 3107.52, "total_tokens": 836160} +{"current_steps": 2930, "total_steps": 9520, "loss": 0.4449, "lr": 8.742834278695154e-06, "epoch": 6.15546218487395, "percentage": 30.78, "elapsed_time": "0:04:29", "remaining_time": "0:10:06", "throughput": 3107.89, "total_tokens": 837600} +{"current_steps": 2935, "total_steps": 9520, "loss": 0.2873, "lr": 8.736749962532117e-06, "epoch": 6.165966386554622, "percentage": 30.83, "elapsed_time": "0:04:29", "remaining_time": "0:10:05", "throughput": 3108.03, "total_tokens": 839040} +{"current_steps": 2940, "total_steps": 9520, "loss": 0.6037, "lr": 8.730653086799516e-06, "epoch": 6.176470588235294, "percentage": 30.88, "elapsed_time": "0:04:30", "remaining_time": "0:10:05", "throughput": 3108.23, "total_tokens": 840480} +{"current_steps": 2945, "total_steps": 9520, "loss": 0.4377, "lr": 8.72454367198953e-06, "epoch": 6.186974789915967, "percentage": 30.93, "elapsed_time": "0:04:30", "remaining_time": "0:10:04", "throughput": 3108.43, "total_tokens": 841856} +{"current_steps": 2950, "total_steps": 9520, "loss": 0.5609, "lr": 8.718421738636478e-06, "epoch": 6.197478991596639, "percentage": 30.99, "elapsed_time": "0:04:31", "remaining_time": "0:10:04", "throughput": 3108.61, "total_tokens": 843232} +{"current_steps": 2955, "total_steps": 9520, "loss": 0.5686, "lr": 8.712287307316756e-06, "epoch": 6.207983193277311, "percentage": 31.04, "elapsed_time": "0:04:31", "remaining_time": "0:10:03", "throughput": 3109.17, "total_tokens": 844736} +{"current_steps": 2960, "total_steps": 9520, "loss": 0.6227, "lr": 8.706140398648768e-06, "epoch": 6.218487394957983, "percentage": 31.09, "elapsed_time": "0:04:32", "remaining_time": "0:10:03", "throughput": 3109.49, "total_tokens": 846144} +{"current_steps": 2965, "total_steps": 9520, "loss": 0.3206, "lr": 8.699981033292855e-06, "epoch": 6.2289915966386555, "percentage": 31.14, "elapsed_time": "0:04:32", "remaining_time": "0:10:02", "throughput": 3109.57, "total_tokens": 847456} +{"current_steps": 2970, "total_steps": 9520, "loss": 0.428, "lr": 8.693809231951225e-06, "epoch": 6.239495798319328, "percentage": 31.2, "elapsed_time": "0:04:32", "remaining_time": "0:10:01", "throughput": 3109.55, "total_tokens": 848736} +{"current_steps": 2975, "total_steps": 9520, "loss": 0.2964, "lr": 8.687625015367883e-06, "epoch": 6.25, "percentage": 31.25, "elapsed_time": "0:04:33", "remaining_time": "0:10:01", "throughput": 3109.69, "total_tokens": 850080} +{"current_steps": 2980, "total_steps": 9520, "loss": 0.5581, "lr": 8.68142840432857e-06, "epoch": 6.260504201680672, "percentage": 31.3, "elapsed_time": "0:04:33", "remaining_time": "0:10:00", "throughput": 3110.16, "total_tokens": 851552} +{"current_steps": 2985, "total_steps": 9520, "loss": 0.5393, "lr": 8.675219419660676e-06, "epoch": 6.2710084033613445, "percentage": 31.36, "elapsed_time": "0:04:34", "remaining_time": "0:10:00", "throughput": 3111.33, "total_tokens": 853248} +{"current_steps": 2990, "total_steps": 9520, "loss": 0.5684, "lr": 8.668998082233186e-06, "epoch": 6.281512605042017, "percentage": 31.41, "elapsed_time": "0:04:34", "remaining_time": "0:09:59", "throughput": 3111.91, "total_tokens": 854848} +{"current_steps": 2995, "total_steps": 9520, "loss": 0.4297, "lr": 8.662764412956606e-06, "epoch": 6.292016806722689, "percentage": 31.46, "elapsed_time": "0:04:35", "remaining_time": "0:09:59", "throughput": 3112.13, "total_tokens": 856224} +{"current_steps": 3000, "total_steps": 9520, "loss": 0.4091, "lr": 8.656518432782885e-06, "epoch": 6.302521008403361, "percentage": 31.51, "elapsed_time": "0:04:35", "remaining_time": "0:09:58", "throughput": 3112.79, "total_tokens": 857760} +{"current_steps": 3005, "total_steps": 9520, "loss": 0.5079, "lr": 8.65026016270535e-06, "epoch": 6.313025210084033, "percentage": 31.57, "elapsed_time": "0:04:35", "remaining_time": "0:09:58", "throughput": 3112.68, "total_tokens": 859008} +{"current_steps": 3010, "total_steps": 9520, "loss": 0.4325, "lr": 8.643989623758642e-06, "epoch": 6.323529411764706, "percentage": 31.62, "elapsed_time": "0:04:36", "remaining_time": "0:09:57", "throughput": 3112.94, "total_tokens": 860416} +{"current_steps": 3015, "total_steps": 9520, "loss": 0.3353, "lr": 8.637706837018633e-06, "epoch": 6.334033613445378, "percentage": 31.67, "elapsed_time": "0:04:36", "remaining_time": "0:09:57", "throughput": 3113.17, "total_tokens": 861792} +{"current_steps": 3020, "total_steps": 9520, "loss": 0.575, "lr": 8.631411823602363e-06, "epoch": 6.34453781512605, "percentage": 31.72, "elapsed_time": "0:04:37", "remaining_time": "0:09:56", "throughput": 3113.51, "total_tokens": 863232} +{"current_steps": 3025, "total_steps": 9520, "loss": 0.6374, "lr": 8.625104604667965e-06, "epoch": 6.355042016806722, "percentage": 31.78, "elapsed_time": "0:04:37", "remaining_time": "0:09:56", "throughput": 3113.82, "total_tokens": 864672} +{"current_steps": 3030, "total_steps": 9520, "loss": 0.439, "lr": 8.618785201414598e-06, "epoch": 6.3655462184873945, "percentage": 31.83, "elapsed_time": "0:04:38", "remaining_time": "0:09:55", "throughput": 3114.28, "total_tokens": 866112} +{"current_steps": 3035, "total_steps": 9520, "loss": 0.3025, "lr": 8.612453635082374e-06, "epoch": 6.376050420168067, "percentage": 31.88, "elapsed_time": "0:04:38", "remaining_time": "0:09:55", "throughput": 3114.41, "total_tokens": 867456} +{"current_steps": 3040, "total_steps": 9520, "loss": 0.2758, "lr": 8.606109926952285e-06, "epoch": 6.38655462184874, "percentage": 31.93, "elapsed_time": "0:04:38", "remaining_time": "0:09:54", "throughput": 3114.73, "total_tokens": 868896} +{"current_steps": 3045, "total_steps": 9520, "loss": 0.4266, "lr": 8.599754098346134e-06, "epoch": 6.397058823529412, "percentage": 31.99, "elapsed_time": "0:04:39", "remaining_time": "0:09:54", "throughput": 3115.45, "total_tokens": 870464} +{"current_steps": 3050, "total_steps": 9520, "loss": 0.3117, "lr": 8.59338617062646e-06, "epoch": 6.407563025210084, "percentage": 32.04, "elapsed_time": "0:04:39", "remaining_time": "0:09:53", "throughput": 3115.66, "total_tokens": 871840} +{"current_steps": 3055, "total_steps": 9520, "loss": 0.4861, "lr": 8.587006165196472e-06, "epoch": 6.418067226890757, "percentage": 32.09, "elapsed_time": "0:04:40", "remaining_time": "0:09:53", "throughput": 3115.8, "total_tokens": 873184} +{"current_steps": 3060, "total_steps": 9520, "loss": 0.4744, "lr": 8.580614103499968e-06, "epoch": 6.428571428571429, "percentage": 32.14, "elapsed_time": "0:04:40", "remaining_time": "0:09:52", "throughput": 3116.22, "total_tokens": 874720} +{"current_steps": 3065, "total_steps": 9520, "loss": 0.5119, "lr": 8.57421000702127e-06, "epoch": 6.439075630252101, "percentage": 32.2, "elapsed_time": "0:04:41", "remaining_time": "0:09:52", "throughput": 3116.85, "total_tokens": 876256} +{"current_steps": 3070, "total_steps": 9520, "loss": 0.4525, "lr": 8.567793897285158e-06, "epoch": 6.449579831932773, "percentage": 32.25, "elapsed_time": "0:04:41", "remaining_time": "0:09:51", "throughput": 3117.38, "total_tokens": 877824} +{"current_steps": 3075, "total_steps": 9520, "loss": 0.4444, "lr": 8.561365795856773e-06, "epoch": 6.4600840336134455, "percentage": 32.3, "elapsed_time": "0:04:42", "remaining_time": "0:09:51", "throughput": 3117.72, "total_tokens": 879232} +{"current_steps": 3080, "total_steps": 9520, "loss": 0.354, "lr": 8.55492572434158e-06, "epoch": 6.470588235294118, "percentage": 32.35, "elapsed_time": "0:04:42", "remaining_time": "0:09:50", "throughput": 3118.23, "total_tokens": 880832} +{"current_steps": 3085, "total_steps": 9520, "loss": 0.5997, "lr": 8.548473704385263e-06, "epoch": 6.48109243697479, "percentage": 32.41, "elapsed_time": "0:04:42", "remaining_time": "0:09:50", "throughput": 3118.29, "total_tokens": 882144} +{"current_steps": 3090, "total_steps": 9520, "loss": 0.5082, "lr": 8.54200975767367e-06, "epoch": 6.491596638655462, "percentage": 32.46, "elapsed_time": "0:04:43", "remaining_time": "0:09:49", "throughput": 3118.81, "total_tokens": 883712} +{"current_steps": 3095, "total_steps": 9520, "loss": 0.4775, "lr": 8.535533905932739e-06, "epoch": 6.5021008403361344, "percentage": 32.51, "elapsed_time": "0:04:43", "remaining_time": "0:09:49", "throughput": 3119.08, "total_tokens": 885120} +{"current_steps": 3100, "total_steps": 9520, "loss": 0.3879, "lr": 8.529046170928416e-06, "epoch": 6.512605042016807, "percentage": 32.56, "elapsed_time": "0:04:44", "remaining_time": "0:09:48", "throughput": 3119.35, "total_tokens": 886592} +{"current_steps": 3105, "total_steps": 9520, "loss": 0.5063, "lr": 8.522546574466594e-06, "epoch": 6.523109243697479, "percentage": 32.62, "elapsed_time": "0:04:44", "remaining_time": "0:09:48", "throughput": 3120.23, "total_tokens": 888224} +{"current_steps": 3110, "total_steps": 9520, "loss": 0.4799, "lr": 8.516035138393032e-06, "epoch": 6.533613445378151, "percentage": 32.67, "elapsed_time": "0:04:45", "remaining_time": "0:09:47", "throughput": 3120.61, "total_tokens": 889664} +{"current_steps": 3115, "total_steps": 9520, "loss": 0.4898, "lr": 8.509511884593277e-06, "epoch": 6.544117647058823, "percentage": 32.72, "elapsed_time": "0:04:45", "remaining_time": "0:09:47", "throughput": 3120.7, "total_tokens": 891072} +{"current_steps": 3120, "total_steps": 9520, "loss": 0.4488, "lr": 8.502976834992605e-06, "epoch": 6.554621848739496, "percentage": 32.77, "elapsed_time": "0:04:45", "remaining_time": "0:09:46", "throughput": 3120.84, "total_tokens": 892416} +{"current_steps": 3125, "total_steps": 9520, "loss": 0.4716, "lr": 8.496430011555933e-06, "epoch": 6.565126050420168, "percentage": 32.83, "elapsed_time": "0:04:46", "remaining_time": "0:09:46", "throughput": 3121.08, "total_tokens": 893792} +{"current_steps": 3130, "total_steps": 9520, "loss": 0.4168, "lr": 8.489871436287752e-06, "epoch": 6.57563025210084, "percentage": 32.88, "elapsed_time": "0:04:46", "remaining_time": "0:09:45", "throughput": 3121.69, "total_tokens": 895328} +{"current_steps": 3135, "total_steps": 9520, "loss": 0.3687, "lr": 8.483301131232056e-06, "epoch": 6.586134453781512, "percentage": 32.93, "elapsed_time": "0:04:47", "remaining_time": "0:09:44", "throughput": 3121.81, "total_tokens": 896672} +{"current_steps": 3140, "total_steps": 9520, "loss": 0.4044, "lr": 8.476719118472259e-06, "epoch": 6.5966386554621845, "percentage": 32.98, "elapsed_time": "0:04:47", "remaining_time": "0:09:44", "throughput": 3122.29, "total_tokens": 898144} +{"current_steps": 3145, "total_steps": 9520, "loss": 0.6245, "lr": 8.470125420131126e-06, "epoch": 6.607142857142857, "percentage": 33.04, "elapsed_time": "0:04:48", "remaining_time": "0:09:43", "throughput": 3122.26, "total_tokens": 899424} +{"current_steps": 3150, "total_steps": 9520, "loss": 0.4383, "lr": 8.463520058370701e-06, "epoch": 6.617647058823529, "percentage": 33.09, "elapsed_time": "0:04:48", "remaining_time": "0:09:43", "throughput": 3122.71, "total_tokens": 900928} +{"current_steps": 3155, "total_steps": 9520, "loss": 0.4203, "lr": 8.456903055392233e-06, "epoch": 6.628151260504202, "percentage": 33.14, "elapsed_time": "0:04:48", "remaining_time": "0:09:42", "throughput": 3123.53, "total_tokens": 902528} +{"current_steps": 3160, "total_steps": 9520, "loss": 0.5138, "lr": 8.450274433436088e-06, "epoch": 6.6386554621848735, "percentage": 33.19, "elapsed_time": "0:04:49", "remaining_time": "0:09:42", "throughput": 3123.97, "total_tokens": 903968} +{"current_steps": 3165, "total_steps": 9520, "loss": 0.5726, "lr": 8.443634214781693e-06, "epoch": 6.649159663865547, "percentage": 33.25, "elapsed_time": "0:04:49", "remaining_time": "0:09:41", "throughput": 3124.19, "total_tokens": 905344} +{"current_steps": 3170, "total_steps": 9520, "loss": 0.4212, "lr": 8.43698242174745e-06, "epoch": 6.659663865546219, "percentage": 33.3, "elapsed_time": "0:04:50", "remaining_time": "0:09:41", "throughput": 3124.26, "total_tokens": 906688} +{"current_steps": 3175, "total_steps": 9520, "loss": 0.4933, "lr": 8.430319076690664e-06, "epoch": 6.670168067226891, "percentage": 33.35, "elapsed_time": "0:04:50", "remaining_time": "0:09:40", "throughput": 3124.6, "total_tokens": 908224} +{"current_steps": 3180, "total_steps": 9520, "loss": 0.4687, "lr": 8.423644202007468e-06, "epoch": 6.680672268907563, "percentage": 33.4, "elapsed_time": "0:04:51", "remaining_time": "0:09:40", "throughput": 3124.91, "total_tokens": 909632} +{"current_steps": 3185, "total_steps": 9520, "loss": 0.4666, "lr": 8.416957820132743e-06, "epoch": 6.6911764705882355, "percentage": 33.46, "elapsed_time": "0:04:51", "remaining_time": "0:09:39", "throughput": 3125.59, "total_tokens": 911168} +{"current_steps": 3190, "total_steps": 9520, "loss": 0.3053, "lr": 8.410259953540053e-06, "epoch": 6.701680672268908, "percentage": 33.51, "elapsed_time": "0:04:51", "remaining_time": "0:09:39", "throughput": 3125.79, "total_tokens": 912544} +{"current_steps": 3195, "total_steps": 9520, "loss": 0.3681, "lr": 8.40355062474156e-06, "epoch": 6.71218487394958, "percentage": 33.56, "elapsed_time": "0:04:52", "remaining_time": "0:09:38", "throughput": 3126.36, "total_tokens": 914272} +{"current_steps": 3200, "total_steps": 9520, "loss": 0.4283, "lr": 8.39682985628795e-06, "epoch": 6.722689075630252, "percentage": 33.61, "elapsed_time": "0:04:52", "remaining_time": "0:09:38", "throughput": 3126.35, "total_tokens": 915552} +{"current_steps": 3205, "total_steps": 9520, "loss": 0.4662, "lr": 8.39009767076836e-06, "epoch": 6.733193277310924, "percentage": 33.67, "elapsed_time": "0:04:53", "remaining_time": "0:09:37", "throughput": 3126.17, "total_tokens": 916768} +{"current_steps": 3210, "total_steps": 9520, "loss": 0.4801, "lr": 8.383354090810303e-06, "epoch": 6.743697478991597, "percentage": 33.72, "elapsed_time": "0:04:53", "remaining_time": "0:09:37", "throughput": 3126.56, "total_tokens": 918240} +{"current_steps": 3215, "total_steps": 9520, "loss": 0.2942, "lr": 8.37659913907959e-06, "epoch": 6.754201680672269, "percentage": 33.77, "elapsed_time": "0:04:54", "remaining_time": "0:09:36", "throughput": 3126.47, "total_tokens": 919488} +{"current_steps": 3220, "total_steps": 9520, "loss": 0.4491, "lr": 8.369832838280249e-06, "epoch": 6.764705882352941, "percentage": 33.82, "elapsed_time": "0:04:54", "remaining_time": "0:09:36", "throughput": 3126.37, "total_tokens": 920736} +{"current_steps": 3225, "total_steps": 9520, "loss": 0.5322, "lr": 8.363055211154458e-06, "epoch": 6.775210084033613, "percentage": 33.88, "elapsed_time": "0:04:54", "remaining_time": "0:09:35", "throughput": 3126.99, "total_tokens": 922304} +{"current_steps": 3230, "total_steps": 9520, "loss": 0.6148, "lr": 8.356266280482459e-06, "epoch": 6.785714285714286, "percentage": 33.93, "elapsed_time": "0:04:55", "remaining_time": "0:09:35", "throughput": 3126.83, "total_tokens": 923520} +{"current_steps": 3235, "total_steps": 9520, "loss": 0.6422, "lr": 8.349466069082492e-06, "epoch": 6.796218487394958, "percentage": 33.98, "elapsed_time": "0:04:55", "remaining_time": "0:09:34", "throughput": 3126.89, "total_tokens": 924864} +{"current_steps": 3240, "total_steps": 9520, "loss": 0.4984, "lr": 8.34265459981071e-06, "epoch": 6.80672268907563, "percentage": 34.03, "elapsed_time": "0:04:56", "remaining_time": "0:09:34", "throughput": 3127.03, "total_tokens": 926208} +{"current_steps": 3245, "total_steps": 9520, "loss": 0.5132, "lr": 8.3358318955611e-06, "epoch": 6.817226890756302, "percentage": 34.09, "elapsed_time": "0:04:56", "remaining_time": "0:09:33", "throughput": 3127.62, "total_tokens": 927744} +{"current_steps": 3250, "total_steps": 9520, "loss": 0.4898, "lr": 8.32899797926542e-06, "epoch": 6.8277310924369745, "percentage": 34.14, "elapsed_time": "0:04:57", "remaining_time": "0:09:33", "throughput": 3127.55, "total_tokens": 928992} +{"current_steps": 3255, "total_steps": 9520, "loss": 0.3291, "lr": 8.32215287389311e-06, "epoch": 6.838235294117647, "percentage": 34.19, "elapsed_time": "0:04:57", "remaining_time": "0:09:32", "throughput": 3127.84, "total_tokens": 930496} +{"current_steps": 3260, "total_steps": 9520, "loss": 0.6234, "lr": 8.31529660245121e-06, "epoch": 6.848739495798319, "percentage": 34.24, "elapsed_time": "0:04:57", "remaining_time": "0:09:32", "throughput": 3127.89, "total_tokens": 931808} +{"current_steps": 3265, "total_steps": 9520, "loss": 0.6606, "lr": 8.308429187984298e-06, "epoch": 6.859243697478991, "percentage": 34.3, "elapsed_time": "0:04:58", "remaining_time": "0:09:31", "throughput": 3128.22, "total_tokens": 933248} +{"current_steps": 3270, "total_steps": 9520, "loss": 0.4649, "lr": 8.301550653574403e-06, "epoch": 6.869747899159664, "percentage": 34.35, "elapsed_time": "0:04:58", "remaining_time": "0:09:31", "throughput": 3128.4, "total_tokens": 934624} +{"current_steps": 3275, "total_steps": 9520, "loss": 0.5159, "lr": 8.294661022340931e-06, "epoch": 6.880252100840336, "percentage": 34.4, "elapsed_time": "0:04:59", "remaining_time": "0:09:30", "throughput": 3128.42, "total_tokens": 935904} +{"current_steps": 3280, "total_steps": 9520, "loss": 0.464, "lr": 8.28776031744058e-06, "epoch": 6.890756302521009, "percentage": 34.45, "elapsed_time": "0:04:59", "remaining_time": "0:09:29", "throughput": 3128.52, "total_tokens": 937216} +{"current_steps": 3285, "total_steps": 9520, "loss": 0.6184, "lr": 8.280848562067272e-06, "epoch": 6.901260504201681, "percentage": 34.51, "elapsed_time": "0:04:59", "remaining_time": "0:09:29", "throughput": 3128.79, "total_tokens": 938592} +{"current_steps": 3290, "total_steps": 9520, "loss": 0.3906, "lr": 8.27392577945207e-06, "epoch": 6.911764705882353, "percentage": 34.56, "elapsed_time": "0:05:00", "remaining_time": "0:09:28", "throughput": 3128.8, "total_tokens": 939904} +{"current_steps": 3295, "total_steps": 9520, "loss": 0.3847, "lr": 8.2669919928631e-06, "epoch": 6.9222689075630255, "percentage": 34.61, "elapsed_time": "0:05:00", "remaining_time": "0:09:28", "throughput": 3129.12, "total_tokens": 941344} +{"current_steps": 3300, "total_steps": 9520, "loss": 0.4737, "lr": 8.260047225605475e-06, "epoch": 6.932773109243698, "percentage": 34.66, "elapsed_time": "0:05:01", "remaining_time": "0:09:27", "throughput": 3129.71, "total_tokens": 942880} +{"current_steps": 3305, "total_steps": 9520, "loss": 0.517, "lr": 8.25309150102121e-06, "epoch": 6.94327731092437, "percentage": 34.72, "elapsed_time": "0:05:01", "remaining_time": "0:09:27", "throughput": 3129.91, "total_tokens": 944288} +{"current_steps": 3310, "total_steps": 9520, "loss": 0.2455, "lr": 8.246124842489157e-06, "epoch": 6.953781512605042, "percentage": 34.77, "elapsed_time": "0:05:02", "remaining_time": "0:09:26", "throughput": 3130.1, "total_tokens": 945696} +{"current_steps": 3315, "total_steps": 9520, "loss": 0.5493, "lr": 8.23914727342491e-06, "epoch": 6.964285714285714, "percentage": 34.82, "elapsed_time": "0:05:02", "remaining_time": "0:09:26", "throughput": 3129.86, "total_tokens": 946880} +{"current_steps": 3320, "total_steps": 9520, "loss": 0.4179, "lr": 8.23215881728074e-06, "epoch": 6.974789915966387, "percentage": 34.87, "elapsed_time": "0:05:02", "remaining_time": "0:09:25", "throughput": 3130.21, "total_tokens": 948320} +{"current_steps": 3325, "total_steps": 9520, "loss": 0.6578, "lr": 8.225159497545505e-06, "epoch": 6.985294117647059, "percentage": 34.93, "elapsed_time": "0:05:03", "remaining_time": "0:09:25", "throughput": 3130.41, "total_tokens": 949696} +{"current_steps": 3330, "total_steps": 9520, "loss": 0.4875, "lr": 8.218149337744582e-06, "epoch": 6.995798319327731, "percentage": 34.98, "elapsed_time": "0:05:03", "remaining_time": "0:09:24", "throughput": 3130.5, "total_tokens": 951008} +{"current_steps": 3335, "total_steps": 9520, "loss": 0.7493, "lr": 8.21112836143978e-06, "epoch": 7.006302521008403, "percentage": 35.03, "elapsed_time": "0:05:04", "remaining_time": "0:09:24", "throughput": 3129.61, "total_tokens": 952416} +{"current_steps": 3340, "total_steps": 9520, "loss": 0.3717, "lr": 8.204096592229262e-06, "epoch": 7.016806722689076, "percentage": 35.08, "elapsed_time": "0:05:04", "remaining_time": "0:09:23", "throughput": 3129.84, "total_tokens": 953824} +{"current_steps": 3345, "total_steps": 9520, "loss": 0.3304, "lr": 8.197054053747473e-06, "epoch": 7.027310924369748, "percentage": 35.14, "elapsed_time": "0:05:05", "remaining_time": "0:09:23", "throughput": 3130.13, "total_tokens": 955264} +{"current_steps": 3350, "total_steps": 9520, "loss": 0.3235, "lr": 8.190000769665044e-06, "epoch": 7.03781512605042, "percentage": 35.19, "elapsed_time": "0:05:05", "remaining_time": "0:09:22", "throughput": 3130.34, "total_tokens": 956640} +{"current_steps": 3355, "total_steps": 9520, "loss": 0.4013, "lr": 8.182936763688733e-06, "epoch": 7.048319327731092, "percentage": 35.24, "elapsed_time": "0:05:06", "remaining_time": "0:09:22", "throughput": 3130.61, "total_tokens": 958048} +{"current_steps": 3360, "total_steps": 9520, "loss": 0.3753, "lr": 8.175862059561328e-06, "epoch": 7.0588235294117645, "percentage": 35.29, "elapsed_time": "0:05:06", "remaining_time": "0:09:21", "throughput": 3131.05, "total_tokens": 959520} +{"current_steps": 3365, "total_steps": 9520, "loss": 0.2072, "lr": 8.168776681061583e-06, "epoch": 7.069327731092437, "percentage": 35.35, "elapsed_time": "0:05:06", "remaining_time": "0:09:21", "throughput": 3131.78, "total_tokens": 961184} +{"current_steps": 3370, "total_steps": 9520, "loss": 0.4036, "lr": 8.161680652004118e-06, "epoch": 7.079831932773109, "percentage": 35.4, "elapsed_time": "0:05:07", "remaining_time": "0:09:20", "throughput": 3131.96, "total_tokens": 962560} +{"current_steps": 3375, "total_steps": 9520, "loss": 0.3094, "lr": 8.15457399623936e-06, "epoch": 7.090336134453781, "percentage": 35.45, "elapsed_time": "0:05:07", "remaining_time": "0:09:20", "throughput": 3132.24, "total_tokens": 963968} +{"current_steps": 3380, "total_steps": 9520, "loss": 0.3496, "lr": 8.147456737653452e-06, "epoch": 7.100840336134453, "percentage": 35.5, "elapsed_time": "0:05:08", "remaining_time": "0:09:19", "throughput": 3132.39, "total_tokens": 965408} +{"current_steps": 3385, "total_steps": 9520, "loss": 0.4292, "lr": 8.14032890016817e-06, "epoch": 7.111344537815126, "percentage": 35.56, "elapsed_time": "0:05:08", "remaining_time": "0:09:19", "throughput": 3133.01, "total_tokens": 966944} +{"current_steps": 3390, "total_steps": 9520, "loss": 0.408, "lr": 8.13319050774085e-06, "epoch": 7.121848739495798, "percentage": 35.61, "elapsed_time": "0:05:09", "remaining_time": "0:09:18", "throughput": 3133.02, "total_tokens": 968288} +{"current_steps": 3395, "total_steps": 9520, "loss": 0.5783, "lr": 8.126041584364304e-06, "epoch": 7.132352941176471, "percentage": 35.66, "elapsed_time": "0:05:09", "remaining_time": "0:09:18", "throughput": 3133.24, "total_tokens": 969696} +{"current_steps": 3400, "total_steps": 9520, "loss": 0.4745, "lr": 8.118882154066737e-06, "epoch": 7.142857142857143, "percentage": 35.71, "elapsed_time": "0:05:09", "remaining_time": "0:09:17", "throughput": 3133.57, "total_tokens": 971136} +{"current_steps": 3405, "total_steps": 9520, "loss": 0.5643, "lr": 8.11171224091167e-06, "epoch": 7.1533613445378155, "percentage": 35.77, "elapsed_time": "0:05:10", "remaining_time": "0:09:17", "throughput": 3133.52, "total_tokens": 972416} +{"current_steps": 3410, "total_steps": 9520, "loss": 0.4356, "lr": 8.104531868997858e-06, "epoch": 7.163865546218488, "percentage": 35.82, "elapsed_time": "0:05:10", "remaining_time": "0:09:16", "throughput": 3133.7, "total_tokens": 973792} +{"current_steps": 3415, "total_steps": 9520, "loss": 0.4469, "lr": 8.09734106245921e-06, "epoch": 7.17436974789916, "percentage": 35.87, "elapsed_time": "0:05:11", "remaining_time": "0:09:16", "throughput": 3133.86, "total_tokens": 975168} +{"current_steps": 3420, "total_steps": 9520, "loss": 0.4368, "lr": 8.090139845464709e-06, "epoch": 7.184873949579832, "percentage": 35.92, "elapsed_time": "0:05:11", "remaining_time": "0:09:15", "throughput": 3134.11, "total_tokens": 976576} +{"current_steps": 3425, "total_steps": 9520, "loss": 0.4239, "lr": 8.082928242218323e-06, "epoch": 7.195378151260504, "percentage": 35.98, "elapsed_time": "0:05:12", "remaining_time": "0:09:15", "throughput": 3134.42, "total_tokens": 978016} +{"current_steps": 3430, "total_steps": 9520, "loss": 0.5106, "lr": 8.075706276958928e-06, "epoch": 7.205882352941177, "percentage": 36.03, "elapsed_time": "0:05:12", "remaining_time": "0:09:14", "throughput": 3134.39, "total_tokens": 979328} +{"current_steps": 3435, "total_steps": 9520, "loss": 0.4863, "lr": 8.068473973960238e-06, "epoch": 7.216386554621849, "percentage": 36.08, "elapsed_time": "0:05:12", "remaining_time": "0:09:14", "throughput": 3134.52, "total_tokens": 980704} +{"current_steps": 3440, "total_steps": 9520, "loss": 0.4545, "lr": 8.061231357530701e-06, "epoch": 7.226890756302521, "percentage": 36.13, "elapsed_time": "0:05:13", "remaining_time": "0:09:13", "throughput": 3134.72, "total_tokens": 982112} +{"current_steps": 3445, "total_steps": 9520, "loss": 0.423, "lr": 8.05397845201344e-06, "epoch": 7.237394957983193, "percentage": 36.19, "elapsed_time": "0:05:13", "remaining_time": "0:09:13", "throughput": 3134.8, "total_tokens": 983520} +{"current_steps": 3450, "total_steps": 9520, "loss": 0.3727, "lr": 8.04671528178615e-06, "epoch": 7.2478991596638656, "percentage": 36.24, "elapsed_time": "0:05:14", "remaining_time": "0:09:12", "throughput": 3135.31, "total_tokens": 985056} +{"current_steps": 3455, "total_steps": 9520, "loss": 0.3751, "lr": 8.039441871261037e-06, "epoch": 7.258403361344538, "percentage": 36.29, "elapsed_time": "0:05:14", "remaining_time": "0:09:12", "throughput": 3135.21, "total_tokens": 986304} +{"current_steps": 3460, "total_steps": 9520, "loss": 0.3068, "lr": 8.032158244884719e-06, "epoch": 7.26890756302521, "percentage": 36.34, "elapsed_time": "0:05:15", "remaining_time": "0:09:11", "throughput": 3135.37, "total_tokens": 987712} +{"current_steps": 3465, "total_steps": 9520, "loss": 0.4365, "lr": 8.02486442713815e-06, "epoch": 7.279411764705882, "percentage": 36.4, "elapsed_time": "0:05:15", "remaining_time": "0:09:11", "throughput": 3135.7, "total_tokens": 989184} +{"current_steps": 3470, "total_steps": 9520, "loss": 0.4678, "lr": 8.017560442536542e-06, "epoch": 7.2899159663865545, "percentage": 36.45, "elapsed_time": "0:05:15", "remaining_time": "0:09:10", "throughput": 3134.89, "total_tokens": 990496} +{"current_steps": 3475, "total_steps": 9520, "loss": 0.3586, "lr": 8.010246315629278e-06, "epoch": 7.300420168067227, "percentage": 36.5, "elapsed_time": "0:05:16", "remaining_time": "0:09:10", "throughput": 3134.96, "total_tokens": 991808} +{"current_steps": 3480, "total_steps": 9520, "loss": 0.3026, "lr": 8.002922070999827e-06, "epoch": 7.310924369747899, "percentage": 36.55, "elapsed_time": "0:05:16", "remaining_time": "0:09:09", "throughput": 3135.68, "total_tokens": 993472} +{"current_steps": 3485, "total_steps": 9520, "loss": 0.3154, "lr": 7.99558773326567e-06, "epoch": 7.321428571428571, "percentage": 36.61, "elapsed_time": "0:05:17", "remaining_time": "0:09:09", "throughput": 3136.07, "total_tokens": 995040} +{"current_steps": 3490, "total_steps": 9520, "loss": 0.418, "lr": 7.988243327078208e-06, "epoch": 7.331932773109243, "percentage": 36.66, "elapsed_time": "0:05:17", "remaining_time": "0:09:08", "throughput": 3136.72, "total_tokens": 996608} +{"current_steps": 3495, "total_steps": 9520, "loss": 0.494, "lr": 7.980888877122684e-06, "epoch": 7.342436974789916, "percentage": 36.71, "elapsed_time": "0:05:18", "remaining_time": "0:09:08", "throughput": 3136.99, "total_tokens": 998016} +{"current_steps": 3500, "total_steps": 9520, "loss": 0.3485, "lr": 7.973524408118095e-06, "epoch": 7.352941176470588, "percentage": 36.76, "elapsed_time": "0:05:18", "remaining_time": "0:09:07", "throughput": 3136.8, "total_tokens": 999232}