diff --git "a/trainer_log.jsonl" "b/trainer_log.jsonl" new file mode 100644--- /dev/null +++ "b/trainer_log.jsonl" @@ -0,0 +1,686 @@ +{"current_steps": 5, "total_steps": 33920, "loss": 6.6512, "lr": 1.179245283018868e-08, "epoch": 0.00294811320754717, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "2:20:14", "throughput": 1986.08, "total_tokens": 2464} +{"current_steps": 10, "total_steps": 33920, "loss": 6.3646, "lr": 2.6533018867924528e-08, "epoch": 0.00589622641509434, "percentage": 0.03, "elapsed_time": "0:00:01", "remaining_time": "1:46:39", "throughput": 3543.71, "total_tokens": 6688} +{"current_steps": 15, "total_steps": 33920, "loss": 6.1166, "lr": 4.127358490566038e-08, "epoch": 0.00884433962264151, "percentage": 0.04, "elapsed_time": "0:00:02", "remaining_time": "1:31:58", "throughput": 4089.29, "total_tokens": 9984} +{"current_steps": 20, "total_steps": 33920, "loss": 6.2843, "lr": 5.601415094339623e-08, "epoch": 0.01179245283018868, "percentage": 0.06, "elapsed_time": "0:00:03", "remaining_time": "1:25:28", "throughput": 4420.71, "total_tokens": 13376} +{"current_steps": 25, "total_steps": 33920, "loss": 6.6652, "lr": 7.075471698113208e-08, "epoch": 0.01474056603773585, "percentage": 0.07, "elapsed_time": "0:00:03", "remaining_time": "1:20:29", "throughput": 4734.04, "total_tokens": 16864} +{"current_steps": 30, "total_steps": 33920, "loss": 6.4095, "lr": 8.549528301886793e-08, "epoch": 0.01768867924528302, "percentage": 0.09, "elapsed_time": "0:00:04", "remaining_time": "1:17:13", "throughput": 4758.92, "total_tokens": 19520} +{"current_steps": 35, "total_steps": 33920, "loss": 6.7411, "lr": 1.0023584905660378e-07, "epoch": 0.020636792452830188, "percentage": 0.1, "elapsed_time": "0:00:04", "remaining_time": "1:15:58", "throughput": 4961.69, "total_tokens": 23360} +{"current_steps": 40, "total_steps": 33920, "loss": 6.5525, "lr": 1.1497641509433962e-07, "epoch": 0.02358490566037736, "percentage": 0.12, "elapsed_time": "0:00:05", "remaining_time": "1:14:09", "throughput": 5141.28, "total_tokens": 27008} +{"current_steps": 45, "total_steps": 33920, "loss": 6.4003, "lr": 1.297169811320755e-07, "epoch": 0.02653301886792453, "percentage": 0.13, "elapsed_time": "0:00:05", "remaining_time": "1:12:53", "throughput": 5254.1, "total_tokens": 30528} +{"current_steps": 50, "total_steps": 33920, "loss": 6.3289, "lr": 1.4445754716981135e-07, "epoch": 0.0294811320754717, "percentage": 0.15, "elapsed_time": "0:00:06", "remaining_time": "1:16:51", "throughput": 5495.47, "total_tokens": 37408} +{"current_steps": 55, "total_steps": 33920, "loss": 6.1908, "lr": 1.591981132075472e-07, "epoch": 0.03242924528301887, "percentage": 0.16, "elapsed_time": "0:00:07", "remaining_time": "1:14:51", "throughput": 5501.58, "total_tokens": 40128} +{"current_steps": 60, "total_steps": 33920, "loss": 6.3195, "lr": 1.7393867924528304e-07, "epoch": 0.03537735849056604, "percentage": 0.18, "elapsed_time": "0:00:07", "remaining_time": "1:13:15", "throughput": 5571.45, "total_tokens": 43392} +{"current_steps": 65, "total_steps": 33920, "loss": 6.0541, "lr": 1.886792452830189e-07, "epoch": 0.038325471698113206, "percentage": 0.19, "elapsed_time": "0:00:08", "remaining_time": "1:11:43", "throughput": 5607.76, "total_tokens": 46336} +{"current_steps": 70, "total_steps": 33920, "loss": 6.2879, "lr": 2.0341981132075473e-07, "epoch": 0.041273584905660375, "percentage": 0.21, "elapsed_time": "0:00:08", "remaining_time": "1:10:47", "throughput": 5653.65, "total_tokens": 49664} +{"current_steps": 75, "total_steps": 33920, "loss": 5.5572, "lr": 2.1816037735849058e-07, "epoch": 0.044221698113207544, "percentage": 0.22, "elapsed_time": "0:00:09", "remaining_time": "1:12:29", "throughput": 5764.1, "total_tokens": 55552} +{"current_steps": 80, "total_steps": 33920, "loss": 6.0275, "lr": 2.3290094339622643e-07, "epoch": 0.04716981132075472, "percentage": 0.24, "elapsed_time": "0:00:10", "remaining_time": "1:11:56", "throughput": 5789.26, "total_tokens": 59072} +{"current_steps": 85, "total_steps": 33920, "loss": 6.1802, "lr": 2.476415094339623e-07, "epoch": 0.05011792452830189, "percentage": 0.25, "elapsed_time": "0:00:10", "remaining_time": "1:10:56", "throughput": 5820.68, "total_tokens": 62240} +{"current_steps": 90, "total_steps": 33920, "loss": 6.0592, "lr": 2.6238207547169815e-07, "epoch": 0.05306603773584906, "percentage": 0.27, "elapsed_time": "0:00:11", "remaining_time": "1:10:10", "throughput": 5856.23, "total_tokens": 65600} +{"current_steps": 95, "total_steps": 33920, "loss": 6.2081, "lr": 2.7712264150943397e-07, "epoch": 0.05601415094339623, "percentage": 0.28, "elapsed_time": "0:00:11", "remaining_time": "1:09:14", "throughput": 5860.07, "total_tokens": 68384} +{"current_steps": 100, "total_steps": 33920, "loss": 6.2388, "lr": 2.9186320754716984e-07, "epoch": 0.0589622641509434, "percentage": 0.29, "elapsed_time": "0:00:12", "remaining_time": "1:08:06", "throughput": 5847.9, "total_tokens": 70656} +{"current_steps": 105, "total_steps": 33920, "loss": 5.8466, "lr": 3.0660377358490567e-07, "epoch": 0.061910377358490566, "percentage": 0.31, "elapsed_time": "0:00:12", "remaining_time": "1:07:20", "throughput": 5868.23, "total_tokens": 73632} +{"current_steps": 110, "total_steps": 33920, "loss": 5.5644, "lr": 3.213443396226416e-07, "epoch": 0.06485849056603774, "percentage": 0.32, "elapsed_time": "0:00:13", "remaining_time": "1:07:04", "throughput": 5892.05, "total_tokens": 77152} +{"current_steps": 115, "total_steps": 33920, "loss": 5.4294, "lr": 3.3608490566037736e-07, "epoch": 0.06780660377358491, "percentage": 0.34, "elapsed_time": "0:00:13", "remaining_time": "1:06:30", "throughput": 5900.07, "total_tokens": 80096} +{"current_steps": 120, "total_steps": 33920, "loss": 5.765, "lr": 3.508254716981133e-07, "epoch": 0.07075471698113207, "percentage": 0.35, "elapsed_time": "0:00:14", "remaining_time": "1:06:18", "throughput": 5910.94, "total_tokens": 83488} +{"current_steps": 125, "total_steps": 33920, "loss": 5.5142, "lr": 3.6556603773584905e-07, "epoch": 0.07370283018867925, "percentage": 0.37, "elapsed_time": "0:00:14", "remaining_time": "1:05:45", "throughput": 5924.23, "total_tokens": 86464} +{"current_steps": 130, "total_steps": 33920, "loss": 5.6643, "lr": 3.80306603773585e-07, "epoch": 0.07665094339622641, "percentage": 0.38, "elapsed_time": "0:00:15", "remaining_time": "1:05:28", "throughput": 5954.13, "total_tokens": 89984} +{"current_steps": 135, "total_steps": 33920, "loss": 5.4216, "lr": 3.9504716981132075e-07, "epoch": 0.07959905660377359, "percentage": 0.4, "elapsed_time": "0:00:15", "remaining_time": "1:05:16", "throughput": 5972.96, "total_tokens": 93472} +{"current_steps": 140, "total_steps": 33920, "loss": 5.3138, "lr": 4.097877358490567e-07, "epoch": 0.08254716981132075, "percentage": 0.41, "elapsed_time": "0:00:16", "remaining_time": "1:04:52", "throughput": 5985.76, "total_tokens": 96576} +{"current_steps": 145, "total_steps": 33920, "loss": 5.5152, "lr": 4.2452830188679244e-07, "epoch": 0.08549528301886793, "percentage": 0.43, "elapsed_time": "0:00:16", "remaining_time": "1:04:58", "throughput": 6015.22, "total_tokens": 100672} +{"current_steps": 150, "total_steps": 33920, "loss": 5.4596, "lr": 4.3926886792452837e-07, "epoch": 0.08844339622641509, "percentage": 0.44, "elapsed_time": "0:00:17", "remaining_time": "1:04:35", "throughput": 6017.85, "total_tokens": 103584} +{"current_steps": 155, "total_steps": 33920, "loss": 5.5016, "lr": 4.5400943396226414e-07, "epoch": 0.09139150943396226, "percentage": 0.46, "elapsed_time": "0:00:17", "remaining_time": "1:04:46", "throughput": 6048.14, "total_tokens": 107904} +{"current_steps": 160, "total_steps": 33920, "loss": 5.1658, "lr": 4.6875000000000006e-07, "epoch": 0.09433962264150944, "percentage": 0.47, "elapsed_time": "0:00:18", "remaining_time": "1:04:21", "throughput": 6049.24, "total_tokens": 110720} +{"current_steps": 165, "total_steps": 33920, "loss": 5.3949, "lr": 4.834905660377359e-07, "epoch": 0.0972877358490566, "percentage": 0.49, "elapsed_time": "0:00:18", "remaining_time": "1:04:09", "throughput": 6041.25, "total_tokens": 113664} +{"current_steps": 170, "total_steps": 33920, "loss": 5.1665, "lr": 4.982311320754717e-07, "epoch": 0.10023584905660378, "percentage": 0.5, "elapsed_time": "0:00:19", "remaining_time": "1:04:06", "throughput": 6061.34, "total_tokens": 117440} +{"current_steps": 175, "total_steps": 33920, "loss": 5.0396, "lr": 5.129716981132076e-07, "epoch": 0.10318396226415094, "percentage": 0.52, "elapsed_time": "0:00:19", "remaining_time": "1:03:40", "throughput": 6054.28, "total_tokens": 119968} +{"current_steps": 180, "total_steps": 33920, "loss": 5.1356, "lr": 5.277122641509435e-07, "epoch": 0.10613207547169812, "percentage": 0.53, "elapsed_time": "0:00:20", "remaining_time": "1:03:29", "throughput": 6035.98, "total_tokens": 122656} +{"current_steps": 185, "total_steps": 33920, "loss": 4.5716, "lr": 5.424528301886793e-07, "epoch": 0.10908018867924528, "percentage": 0.55, "elapsed_time": "0:00:20", "remaining_time": "1:03:26", "throughput": 6040.78, "total_tokens": 126112} +{"current_steps": 190, "total_steps": 33920, "loss": 5.1308, "lr": 5.571933962264151e-07, "epoch": 0.11202830188679246, "percentage": 0.56, "elapsed_time": "0:00:21", "remaining_time": "1:03:10", "throughput": 6039.5, "total_tokens": 128960} +{"current_steps": 195, "total_steps": 33920, "loss": 5.0656, "lr": 5.71933962264151e-07, "epoch": 0.11497641509433962, "percentage": 0.57, "elapsed_time": "0:00:21", "remaining_time": "1:02:52", "throughput": 6038.61, "total_tokens": 131712} +{"current_steps": 200, "total_steps": 33920, "loss": 4.3416, "lr": 5.866745283018868e-07, "epoch": 0.1179245283018868, "percentage": 0.59, "elapsed_time": "0:00:22", "remaining_time": "1:02:51", "throughput": 6051.63, "total_tokens": 135360} +{"current_steps": 205, "total_steps": 33920, "loss": 4.1762, "lr": 6.014150943396227e-07, "epoch": 0.12087264150943396, "percentage": 0.6, "elapsed_time": "0:00:22", "remaining_time": "1:02:37", "throughput": 6055.9, "total_tokens": 138368} +{"current_steps": 210, "total_steps": 33920, "loss": 4.3725, "lr": 6.161556603773585e-07, "epoch": 0.12382075471698113, "percentage": 0.62, "elapsed_time": "0:00:23", "remaining_time": "1:02:29", "throughput": 6058.67, "total_tokens": 141536} +{"current_steps": 215, "total_steps": 33920, "loss": 4.0367, "lr": 6.308962264150945e-07, "epoch": 0.1267688679245283, "percentage": 0.63, "elapsed_time": "0:00:23", "remaining_time": "1:02:28", "throughput": 6054.55, "total_tokens": 144768} +{"current_steps": 220, "total_steps": 33920, "loss": 4.4279, "lr": 6.456367924528302e-07, "epoch": 0.12971698113207547, "percentage": 0.65, "elapsed_time": "0:00:24", "remaining_time": "1:02:18", "throughput": 6065.27, "total_tokens": 148032} +{"current_steps": 225, "total_steps": 33920, "loss": 4.2135, "lr": 6.603773584905661e-07, "epoch": 0.13266509433962265, "percentage": 0.66, "elapsed_time": "0:00:24", "remaining_time": "1:02:11", "throughput": 6069.87, "total_tokens": 151264} +{"current_steps": 230, "total_steps": 33920, "loss": 4.2444, "lr": 6.75117924528302e-07, "epoch": 0.13561320754716982, "percentage": 0.68, "elapsed_time": "0:00:25", "remaining_time": "1:01:56", "throughput": 6070.74, "total_tokens": 154048} +{"current_steps": 235, "total_steps": 33920, "loss": 4.2849, "lr": 6.898584905660379e-07, "epoch": 0.13856132075471697, "percentage": 0.69, "elapsed_time": "0:00:25", "remaining_time": "1:01:50", "throughput": 6073.94, "total_tokens": 157216} +{"current_steps": 240, "total_steps": 33920, "loss": 3.7267, "lr": 7.045990566037736e-07, "epoch": 0.14150943396226415, "percentage": 0.71, "elapsed_time": "0:00:26", "remaining_time": "1:01:49", "throughput": 6086.5, "total_tokens": 160896} +{"current_steps": 245, "total_steps": 33920, "loss": 4.1481, "lr": 7.193396226415095e-07, "epoch": 0.14445754716981132, "percentage": 0.72, "elapsed_time": "0:00:27", "remaining_time": "1:02:05", "throughput": 6097.84, "total_tokens": 165280} +{"current_steps": 250, "total_steps": 33920, "loss": 3.8848, "lr": 7.340801886792454e-07, "epoch": 0.1474056603773585, "percentage": 0.74, "elapsed_time": "0:00:27", "remaining_time": "1:02:26", "throughput": 6115.13, "total_tokens": 170112} +{"current_steps": 255, "total_steps": 33920, "loss": 3.49, "lr": 7.488207547169812e-07, "epoch": 0.15035377358490565, "percentage": 0.75, "elapsed_time": "0:00:28", "remaining_time": "1:02:19", "throughput": 6122.57, "total_tokens": 173408} +{"current_steps": 260, "total_steps": 33920, "loss": 3.5115, "lr": 7.63561320754717e-07, "epoch": 0.15330188679245282, "percentage": 0.77, "elapsed_time": "0:00:28", "remaining_time": "1:02:22", "throughput": 6119.84, "total_tokens": 176896} +{"current_steps": 265, "total_steps": 33920, "loss": 3.5608, "lr": 7.783018867924529e-07, "epoch": 0.15625, "percentage": 0.78, "elapsed_time": "0:00:29", "remaining_time": "1:02:15", "throughput": 6117.4, "total_tokens": 179936} +{"current_steps": 270, "total_steps": 33920, "loss": 3.9471, "lr": 7.930424528301888e-07, "epoch": 0.15919811320754718, "percentage": 0.8, "elapsed_time": "0:00:29", "remaining_time": "1:02:18", "throughput": 6130.08, "total_tokens": 183872} +{"current_steps": 275, "total_steps": 33920, "loss": 3.6111, "lr": 8.077830188679246e-07, "epoch": 0.16214622641509435, "percentage": 0.81, "elapsed_time": "0:00:30", "remaining_time": "1:02:22", "throughput": 6132.93, "total_tokens": 187616} +{"current_steps": 280, "total_steps": 33920, "loss": 3.59, "lr": 8.225235849056605e-07, "epoch": 0.1650943396226415, "percentage": 0.83, "elapsed_time": "0:00:31", "remaining_time": "1:02:09", "throughput": 6123.67, "total_tokens": 190080} +{"current_steps": 285, "total_steps": 33920, "loss": 3.2833, "lr": 8.372641509433963e-07, "epoch": 0.16804245283018868, "percentage": 0.84, "elapsed_time": "0:00:31", "remaining_time": "1:02:04", "throughput": 6118.65, "total_tokens": 193088} +{"current_steps": 290, "total_steps": 33920, "loss": 3.7941, "lr": 8.520047169811321e-07, "epoch": 0.17099056603773585, "percentage": 0.85, "elapsed_time": "0:00:32", "remaining_time": "1:02:00", "throughput": 6111.73, "total_tokens": 196064} +{"current_steps": 295, "total_steps": 33920, "loss": 3.9604, "lr": 8.66745283018868e-07, "epoch": 0.17393867924528303, "percentage": 0.87, "elapsed_time": "0:00:32", "remaining_time": "1:01:48", "throughput": 6106.67, "total_tokens": 198688} +{"current_steps": 300, "total_steps": 33920, "loss": 3.6079, "lr": 8.814858490566039e-07, "epoch": 0.17688679245283018, "percentage": 0.88, "elapsed_time": "0:00:33", "remaining_time": "1:01:42", "throughput": 6101.58, "total_tokens": 201568} +{"current_steps": 305, "total_steps": 33920, "loss": 3.4773, "lr": 8.962264150943397e-07, "epoch": 0.17983490566037735, "percentage": 0.9, "elapsed_time": "0:00:33", "remaining_time": "1:01:50", "throughput": 6105.81, "total_tokens": 205568} +{"current_steps": 310, "total_steps": 33920, "loss": 3.1986, "lr": 9.109669811320755e-07, "epoch": 0.18278301886792453, "percentage": 0.91, "elapsed_time": "0:00:34", "remaining_time": "1:01:47", "throughput": 6108.4, "total_tokens": 208864} +{"current_steps": 315, "total_steps": 33920, "loss": 3.4734, "lr": 9.257075471698114e-07, "epoch": 0.1857311320754717, "percentage": 0.93, "elapsed_time": "0:00:34", "remaining_time": "1:01:37", "throughput": 6104.37, "total_tokens": 211584} +{"current_steps": 320, "total_steps": 33920, "loss": 3.3638, "lr": 9.404481132075473e-07, "epoch": 0.18867924528301888, "percentage": 0.94, "elapsed_time": "0:00:35", "remaining_time": "1:01:30", "throughput": 6102.0, "total_tokens": 214464} +{"current_steps": 325, "total_steps": 33920, "loss": 3.0345, "lr": 9.551886792452833e-07, "epoch": 0.19162735849056603, "percentage": 0.96, "elapsed_time": "0:00:35", "remaining_time": "1:01:30", "throughput": 6104.66, "total_tokens": 217920} +{"current_steps": 330, "total_steps": 33920, "loss": 3.2481, "lr": 9.699292452830188e-07, "epoch": 0.1945754716981132, "percentage": 0.97, "elapsed_time": "0:00:36", "remaining_time": "1:01:24", "throughput": 6105.18, "total_tokens": 220992} +{"current_steps": 335, "total_steps": 33920, "loss": 3.1396, "lr": 9.846698113207548e-07, "epoch": 0.19752358490566038, "percentage": 0.99, "elapsed_time": "0:00:36", "remaining_time": "1:01:26", "throughput": 6110.66, "total_tokens": 224704} +{"current_steps": 340, "total_steps": 33920, "loss": 2.7993, "lr": 9.994103773584906e-07, "epoch": 0.20047169811320756, "percentage": 1.0, "elapsed_time": "0:00:37", "remaining_time": "1:01:20", "throughput": 6111.26, "total_tokens": 227712} +{"current_steps": 345, "total_steps": 33920, "loss": 2.8841, "lr": 1.0141509433962265e-06, "epoch": 0.2034198113207547, "percentage": 1.02, "elapsed_time": "0:00:37", "remaining_time": "1:01:10", "throughput": 6104.95, "total_tokens": 230272} +{"current_steps": 350, "total_steps": 33920, "loss": 2.8042, "lr": 1.0288915094339623e-06, "epoch": 0.20636792452830188, "percentage": 1.03, "elapsed_time": "0:00:38", "remaining_time": "1:01:07", "throughput": 6108.59, "total_tokens": 233600} +{"current_steps": 355, "total_steps": 33920, "loss": 2.5032, "lr": 1.043632075471698e-06, "epoch": 0.20931603773584906, "percentage": 1.05, "elapsed_time": "0:00:38", "remaining_time": "1:01:02", "throughput": 6106.95, "total_tokens": 236576} +{"current_steps": 360, "total_steps": 33920, "loss": 2.879, "lr": 1.058372641509434e-06, "epoch": 0.21226415094339623, "percentage": 1.06, "elapsed_time": "0:00:39", "remaining_time": "1:01:16", "throughput": 6112.9, "total_tokens": 241056} +{"current_steps": 365, "total_steps": 33920, "loss": 2.5462, "lr": 1.07311320754717e-06, "epoch": 0.21521226415094338, "percentage": 1.08, "elapsed_time": "0:00:39", "remaining_time": "1:01:09", "throughput": 6107.81, "total_tokens": 243808} +{"current_steps": 370, "total_steps": 33920, "loss": 2.7807, "lr": 1.0878537735849056e-06, "epoch": 0.21816037735849056, "percentage": 1.09, "elapsed_time": "0:00:40", "remaining_time": "1:01:10", "throughput": 6113.97, "total_tokens": 247520} +{"current_steps": 375, "total_steps": 33920, "loss": 2.4202, "lr": 1.1025943396226416e-06, "epoch": 0.22110849056603774, "percentage": 1.11, "elapsed_time": "0:00:41", "remaining_time": "1:01:10", "throughput": 6119.87, "total_tokens": 251104} +{"current_steps": 380, "total_steps": 33920, "loss": 2.231, "lr": 1.1173349056603773e-06, "epoch": 0.2240566037735849, "percentage": 1.12, "elapsed_time": "0:00:41", "remaining_time": "1:01:09", "throughput": 6121.1, "total_tokens": 254464} +{"current_steps": 385, "total_steps": 33920, "loss": 2.5828, "lr": 1.1320754716981133e-06, "epoch": 0.2270047169811321, "percentage": 1.14, "elapsed_time": "0:00:42", "remaining_time": "1:01:03", "throughput": 6118.69, "total_tokens": 257312} +{"current_steps": 390, "total_steps": 33920, "loss": 2.7209, "lr": 1.1468160377358493e-06, "epoch": 0.22995283018867924, "percentage": 1.15, "elapsed_time": "0:00:42", "remaining_time": "1:00:59", "throughput": 6120.19, "total_tokens": 260480} +{"current_steps": 395, "total_steps": 33920, "loss": 2.8036, "lr": 1.1615566037735849e-06, "epoch": 0.2329009433962264, "percentage": 1.16, "elapsed_time": "0:00:43", "remaining_time": "1:01:03", "throughput": 6130.05, "total_tokens": 264608} +{"current_steps": 400, "total_steps": 33920, "loss": 2.8243, "lr": 1.1762971698113208e-06, "epoch": 0.2358490566037736, "percentage": 1.18, "elapsed_time": "0:00:43", "remaining_time": "1:01:01", "throughput": 6133.63, "total_tokens": 268000} +{"current_steps": 405, "total_steps": 33920, "loss": 2.3111, "lr": 1.1910377358490568e-06, "epoch": 0.23879716981132076, "percentage": 1.19, "elapsed_time": "0:00:44", "remaining_time": "1:01:04", "throughput": 6141.38, "total_tokens": 271936} +{"current_steps": 410, "total_steps": 33920, "loss": 2.5572, "lr": 1.2057783018867926e-06, "epoch": 0.2417452830188679, "percentage": 1.21, "elapsed_time": "0:00:44", "remaining_time": "1:00:54", "throughput": 6133.79, "total_tokens": 274272} +{"current_steps": 415, "total_steps": 33920, "loss": 2.0406, "lr": 1.2205188679245284e-06, "epoch": 0.2446933962264151, "percentage": 1.22, "elapsed_time": "0:00:45", "remaining_time": "1:01:13", "throughput": 6144.72, "total_tokens": 279616} +{"current_steps": 420, "total_steps": 33920, "loss": 2.3823, "lr": 1.2352594339622641e-06, "epoch": 0.24764150943396226, "percentage": 1.24, "elapsed_time": "0:00:46", "remaining_time": "1:01:25", "throughput": 6157.39, "total_tokens": 284480} +{"current_steps": 425, "total_steps": 33920, "loss": 2.0924, "lr": 1.25e-06, "epoch": 0.2505896226415094, "percentage": 1.25, "elapsed_time": "0:00:46", "remaining_time": "1:01:25", "throughput": 6160.7, "total_tokens": 288128} +{"current_steps": 430, "total_steps": 33920, "loss": 2.3764, "lr": 1.264740566037736e-06, "epoch": 0.2535377358490566, "percentage": 1.27, "elapsed_time": "0:00:47", "remaining_time": "1:01:26", "throughput": 6159.31, "total_tokens": 291552} +{"current_steps": 435, "total_steps": 33920, "loss": 2.2371, "lr": 1.2794811320754718e-06, "epoch": 0.25648584905660377, "percentage": 1.28, "elapsed_time": "0:00:47", "remaining_time": "1:01:24", "throughput": 6157.01, "total_tokens": 294688} +{"current_steps": 440, "total_steps": 33920, "loss": 1.9278, "lr": 1.2942216981132078e-06, "epoch": 0.25943396226415094, "percentage": 1.3, "elapsed_time": "0:00:48", "remaining_time": "1:01:15", "throughput": 6148.53, "total_tokens": 296992} +{"current_steps": 445, "total_steps": 33920, "loss": 2.312, "lr": 1.3089622641509436e-06, "epoch": 0.2623820754716981, "percentage": 1.31, "elapsed_time": "0:00:48", "remaining_time": "1:01:09", "throughput": 6144.57, "total_tokens": 299712} +{"current_steps": 450, "total_steps": 33920, "loss": 1.7953, "lr": 1.3237028301886792e-06, "epoch": 0.2653301886792453, "percentage": 1.33, "elapsed_time": "0:00:49", "remaining_time": "1:01:05", "throughput": 6146.45, "total_tokens": 302912} +{"current_steps": 455, "total_steps": 33920, "loss": 2.2464, "lr": 1.3384433962264151e-06, "epoch": 0.26827830188679247, "percentage": 1.34, "elapsed_time": "0:00:49", "remaining_time": "1:01:02", "throughput": 6147.29, "total_tokens": 306112} +{"current_steps": 460, "total_steps": 33920, "loss": 2.2654, "lr": 1.353183962264151e-06, "epoch": 0.27122641509433965, "percentage": 1.36, "elapsed_time": "0:00:50", "remaining_time": "1:00:57", "throughput": 6144.25, "total_tokens": 308928} +{"current_steps": 465, "total_steps": 33920, "loss": 1.6971, "lr": 1.3679245283018869e-06, "epoch": 0.27417452830188677, "percentage": 1.37, "elapsed_time": "0:00:50", "remaining_time": "1:00:51", "throughput": 6141.01, "total_tokens": 311712} +{"current_steps": 470, "total_steps": 33920, "loss": 1.5893, "lr": 1.3826650943396229e-06, "epoch": 0.27712264150943394, "percentage": 1.39, "elapsed_time": "0:00:51", "remaining_time": "1:00:49", "throughput": 6143.75, "total_tokens": 315040} +{"current_steps": 475, "total_steps": 33920, "loss": 1.8189, "lr": 1.3974056603773586e-06, "epoch": 0.2800707547169811, "percentage": 1.4, "elapsed_time": "0:00:51", "remaining_time": "1:00:43", "throughput": 6137.52, "total_tokens": 317568} +{"current_steps": 480, "total_steps": 33920, "loss": 1.4128, "lr": 1.4121462264150946e-06, "epoch": 0.2830188679245283, "percentage": 1.42, "elapsed_time": "0:00:52", "remaining_time": "1:00:37", "throughput": 6139.37, "total_tokens": 320576} +{"current_steps": 485, "total_steps": 33920, "loss": 1.1829, "lr": 1.4268867924528304e-06, "epoch": 0.28596698113207547, "percentage": 1.43, "elapsed_time": "0:00:52", "remaining_time": "1:00:32", "throughput": 6131.06, "total_tokens": 323072} +{"current_steps": 490, "total_steps": 33920, "loss": 1.2505, "lr": 1.4416273584905664e-06, "epoch": 0.28891509433962265, "percentage": 1.44, "elapsed_time": "0:00:53", "remaining_time": "1:00:27", "throughput": 6132.21, "total_tokens": 326080} +{"current_steps": 495, "total_steps": 33920, "loss": 1.3973, "lr": 1.456367924528302e-06, "epoch": 0.2918632075471698, "percentage": 1.46, "elapsed_time": "0:00:53", "remaining_time": "1:00:24", "throughput": 6134.83, "total_tokens": 329312} +{"current_steps": 500, "total_steps": 33920, "loss": 1.1727, "lr": 1.4711084905660377e-06, "epoch": 0.294811320754717, "percentage": 1.47, "elapsed_time": "0:00:54", "remaining_time": "1:00:18", "throughput": 6129.86, "total_tokens": 331872} +{"current_steps": 505, "total_steps": 33920, "loss": 1.1246, "lr": 1.4858490566037737e-06, "epoch": 0.2977594339622642, "percentage": 1.49, "elapsed_time": "0:00:54", "remaining_time": "1:00:16", "throughput": 6132.3, "total_tokens": 335168} +{"current_steps": 510, "total_steps": 33920, "loss": 1.3456, "lr": 1.5005896226415096e-06, "epoch": 0.3007075471698113, "percentage": 1.5, "elapsed_time": "0:00:55", "remaining_time": "1:00:12", "throughput": 6133.78, "total_tokens": 338272} +{"current_steps": 515, "total_steps": 33920, "loss": 1.1066, "lr": 1.5153301886792454e-06, "epoch": 0.30365566037735847, "percentage": 1.52, "elapsed_time": "0:00:55", "remaining_time": "1:00:10", "throughput": 6133.92, "total_tokens": 341472} +{"current_steps": 520, "total_steps": 33920, "loss": 0.9691, "lr": 1.5300707547169814e-06, "epoch": 0.30660377358490565, "percentage": 1.53, "elapsed_time": "0:00:56", "remaining_time": "1:00:13", "throughput": 6135.74, "total_tokens": 345152} +{"current_steps": 525, "total_steps": 33920, "loss": 0.9011, "lr": 1.5448113207547172e-06, "epoch": 0.3095518867924528, "percentage": 1.55, "elapsed_time": "0:00:56", "remaining_time": "1:00:16", "throughput": 6141.69, "total_tokens": 349184} +{"current_steps": 530, "total_steps": 33920, "loss": 1.075, "lr": 1.5595518867924531e-06, "epoch": 0.3125, "percentage": 1.56, "elapsed_time": "0:00:57", "remaining_time": "1:00:13", "throughput": 6140.53, "total_tokens": 352160} +{"current_steps": 535, "total_steps": 33920, "loss": 0.9761, "lr": 1.574292452830189e-06, "epoch": 0.3154481132075472, "percentage": 1.58, "elapsed_time": "0:00:57", "remaining_time": "1:00:16", "throughput": 6143.01, "total_tokens": 356000} +{"current_steps": 540, "total_steps": 33920, "loss": 0.9936, "lr": 1.5890330188679245e-06, "epoch": 0.31839622641509435, "percentage": 1.59, "elapsed_time": "0:00:58", "remaining_time": "1:00:17", "throughput": 6148.99, "total_tokens": 359840} +{"current_steps": 545, "total_steps": 33920, "loss": 1.197, "lr": 1.6037735849056604e-06, "epoch": 0.32134433962264153, "percentage": 1.61, "elapsed_time": "0:00:59", "remaining_time": "1:00:25", "throughput": 6153.3, "total_tokens": 364320} +{"current_steps": 550, "total_steps": 33920, "loss": 0.8054, "lr": 1.6185141509433964e-06, "epoch": 0.3242924528301887, "percentage": 1.62, "elapsed_time": "0:00:59", "remaining_time": "1:00:24", "throughput": 6149.03, "total_tokens": 367328} +{"current_steps": 555, "total_steps": 33920, "loss": 0.7248, "lr": 1.6332547169811322e-06, "epoch": 0.3272405660377358, "percentage": 1.64, "elapsed_time": "0:01:00", "remaining_time": "1:00:25", "throughput": 6145.93, "total_tokens": 370624} +{"current_steps": 560, "total_steps": 33920, "loss": 0.8802, "lr": 1.6479952830188682e-06, "epoch": 0.330188679245283, "percentage": 1.65, "elapsed_time": "0:01:00", "remaining_time": "1:00:27", "throughput": 6147.95, "total_tokens": 374368} +{"current_steps": 565, "total_steps": 33920, "loss": 0.7962, "lr": 1.662735849056604e-06, "epoch": 0.3331367924528302, "percentage": 1.67, "elapsed_time": "0:01:01", "remaining_time": "1:00:26", "throughput": 6144.77, "total_tokens": 377504} +{"current_steps": 570, "total_steps": 33920, "loss": 0.7876, "lr": 1.67747641509434e-06, "epoch": 0.33608490566037735, "percentage": 1.68, "elapsed_time": "0:01:02", "remaining_time": "1:00:28", "throughput": 6137.89, "total_tokens": 380608} +{"current_steps": 575, "total_steps": 33920, "loss": 0.8277, "lr": 1.6922169811320757e-06, "epoch": 0.33903301886792453, "percentage": 1.7, "elapsed_time": "0:01:02", "remaining_time": "1:00:32", "throughput": 6139.32, "total_tokens": 384512} +{"current_steps": 580, "total_steps": 33920, "loss": 0.913, "lr": 1.7069575471698112e-06, "epoch": 0.3419811320754717, "percentage": 1.71, "elapsed_time": "0:01:03", "remaining_time": "1:00:32", "throughput": 6134.19, "total_tokens": 387584} +{"current_steps": 585, "total_steps": 33920, "loss": 0.9092, "lr": 1.7216981132075472e-06, "epoch": 0.3449292452830189, "percentage": 1.72, "elapsed_time": "0:01:03", "remaining_time": "1:00:31", "throughput": 6138.24, "total_tokens": 391232} +{"current_steps": 590, "total_steps": 33920, "loss": 0.9022, "lr": 1.736438679245283e-06, "epoch": 0.34787735849056606, "percentage": 1.74, "elapsed_time": "0:01:04", "remaining_time": "1:00:28", "throughput": 6139.02, "total_tokens": 394336} +{"current_steps": 595, "total_steps": 33920, "loss": 0.831, "lr": 1.751179245283019e-06, "epoch": 0.35082547169811323, "percentage": 1.75, "elapsed_time": "0:01:04", "remaining_time": "1:00:29", "throughput": 6134.77, "total_tokens": 397568} +{"current_steps": 600, "total_steps": 33920, "loss": 0.8677, "lr": 1.765919811320755e-06, "epoch": 0.35377358490566035, "percentage": 1.77, "elapsed_time": "0:01:05", "remaining_time": "1:00:29", "throughput": 6130.18, "total_tokens": 400608} +{"current_steps": 605, "total_steps": 33920, "loss": 0.8183, "lr": 1.7806603773584907e-06, "epoch": 0.35672169811320753, "percentage": 1.78, "elapsed_time": "0:01:06", "remaining_time": "1:00:35", "throughput": 6129.87, "total_tokens": 404736} +{"current_steps": 610, "total_steps": 33920, "loss": 0.7608, "lr": 1.7954009433962267e-06, "epoch": 0.3596698113207547, "percentage": 1.8, "elapsed_time": "0:01:06", "remaining_time": "1:00:35", "throughput": 6125.61, "total_tokens": 407840} +{"current_steps": 615, "total_steps": 33920, "loss": 0.6245, "lr": 1.8101415094339625e-06, "epoch": 0.3626179245283019, "percentage": 1.81, "elapsed_time": "0:01:07", "remaining_time": "1:00:34", "throughput": 6120.61, "total_tokens": 410752} +{"current_steps": 620, "total_steps": 33920, "loss": 0.7243, "lr": 1.8248820754716984e-06, "epoch": 0.36556603773584906, "percentage": 1.83, "elapsed_time": "0:01:07", "remaining_time": "1:00:31", "throughput": 6118.41, "total_tokens": 413728} +{"current_steps": 625, "total_steps": 33920, "loss": 0.9994, "lr": 1.839622641509434e-06, "epoch": 0.36851415094339623, "percentage": 1.84, "elapsed_time": "0:01:08", "remaining_time": "1:00:28", "throughput": 6119.44, "total_tokens": 416864} +{"current_steps": 630, "total_steps": 33920, "loss": 0.7088, "lr": 1.8543632075471698e-06, "epoch": 0.3714622641509434, "percentage": 1.86, "elapsed_time": "0:01:08", "remaining_time": "1:00:25", "throughput": 6119.0, "total_tokens": 419840} +{"current_steps": 635, "total_steps": 33920, "loss": 0.9749, "lr": 1.8691037735849057e-06, "epoch": 0.3744103773584906, "percentage": 1.87, "elapsed_time": "0:01:09", "remaining_time": "1:00:19", "throughput": 6115.51, "total_tokens": 422272} +{"current_steps": 640, "total_steps": 33920, "loss": 0.8456, "lr": 1.8838443396226417e-06, "epoch": 0.37735849056603776, "percentage": 1.89, "elapsed_time": "0:01:09", "remaining_time": "1:00:15", "throughput": 6114.71, "total_tokens": 425184} +{"current_steps": 645, "total_steps": 33920, "loss": 0.7637, "lr": 1.8985849056603775e-06, "epoch": 0.3803066037735849, "percentage": 1.9, "elapsed_time": "0:01:10", "remaining_time": "1:00:12", "throughput": 6115.01, "total_tokens": 428224} +{"current_steps": 650, "total_steps": 33920, "loss": 0.748, "lr": 1.9133254716981133e-06, "epoch": 0.38325471698113206, "percentage": 1.92, "elapsed_time": "0:01:10", "remaining_time": "1:00:08", "throughput": 6114.59, "total_tokens": 431040} +{"current_steps": 655, "total_steps": 33920, "loss": 0.8284, "lr": 1.9280660377358494e-06, "epoch": 0.38620283018867924, "percentage": 1.93, "elapsed_time": "0:01:10", "remaining_time": "1:00:03", "throughput": 6115.05, "total_tokens": 433920} +{"current_steps": 660, "total_steps": 33920, "loss": 0.6951, "lr": 1.9428066037735852e-06, "epoch": 0.3891509433962264, "percentage": 1.95, "elapsed_time": "0:01:11", "remaining_time": "1:00:05", "throughput": 6121.54, "total_tokens": 438016} +{"current_steps": 665, "total_steps": 33920, "loss": 0.6424, "lr": 1.957547169811321e-06, "epoch": 0.3920990566037736, "percentage": 1.96, "elapsed_time": "0:01:12", "remaining_time": "1:00:00", "throughput": 6118.42, "total_tokens": 440576} +{"current_steps": 670, "total_steps": 33920, "loss": 0.6532, "lr": 1.9722877358490568e-06, "epoch": 0.39504716981132076, "percentage": 1.98, "elapsed_time": "0:01:12", "remaining_time": "0:59:58", "throughput": 6120.96, "total_tokens": 443872} +{"current_steps": 675, "total_steps": 33920, "loss": 0.6437, "lr": 1.9870283018867925e-06, "epoch": 0.39799528301886794, "percentage": 1.99, "elapsed_time": "0:01:13", "remaining_time": "0:59:57", "throughput": 6119.16, "total_tokens": 446912} +{"current_steps": 680, "total_steps": 33920, "loss": 0.7485, "lr": 2.0017688679245283e-06, "epoch": 0.4009433962264151, "percentage": 2.0, "elapsed_time": "0:01:13", "remaining_time": "1:00:00", "throughput": 6123.53, "total_tokens": 451072} +{"current_steps": 685, "total_steps": 33920, "loss": 0.7466, "lr": 2.0165094339622645e-06, "epoch": 0.40389150943396224, "percentage": 2.02, "elapsed_time": "0:01:14", "remaining_time": "0:59:55", "throughput": 6120.46, "total_tokens": 453568} +{"current_steps": 690, "total_steps": 33920, "loss": 0.8747, "lr": 2.0312500000000002e-06, "epoch": 0.4068396226415094, "percentage": 2.03, "elapsed_time": "0:01:14", "remaining_time": "0:59:51", "throughput": 6119.44, "total_tokens": 456416} +{"current_steps": 695, "total_steps": 33920, "loss": 0.7353, "lr": 2.045990566037736e-06, "epoch": 0.4097877358490566, "percentage": 2.05, "elapsed_time": "0:01:15", "remaining_time": "0:59:47", "throughput": 6114.67, "total_tokens": 458816} +{"current_steps": 700, "total_steps": 33920, "loss": 0.7846, "lr": 2.0607311320754718e-06, "epoch": 0.41273584905660377, "percentage": 2.06, "elapsed_time": "0:01:15", "remaining_time": "0:59:42", "throughput": 6111.37, "total_tokens": 461344} +{"current_steps": 705, "total_steps": 33920, "loss": 0.5964, "lr": 2.075471698113208e-06, "epoch": 0.41568396226415094, "percentage": 2.08, "elapsed_time": "0:01:15", "remaining_time": "0:59:39", "throughput": 6109.67, "total_tokens": 464192} +{"current_steps": 710, "total_steps": 33920, "loss": 0.638, "lr": 2.0902122641509437e-06, "epoch": 0.4186320754716981, "percentage": 2.09, "elapsed_time": "0:01:16", "remaining_time": "0:59:39", "throughput": 6109.66, "total_tokens": 467520} +{"current_steps": 715, "total_steps": 33920, "loss": 0.7679, "lr": 2.1049528301886795e-06, "epoch": 0.4215801886792453, "percentage": 2.11, "elapsed_time": "0:01:17", "remaining_time": "0:59:39", "throughput": 6114.12, "total_tokens": 471296} +{"current_steps": 720, "total_steps": 33920, "loss": 0.6212, "lr": 2.1196933962264153e-06, "epoch": 0.42452830188679247, "percentage": 2.12, "elapsed_time": "0:01:17", "remaining_time": "0:59:39", "throughput": 6118.26, "total_tokens": 474944} +{"current_steps": 725, "total_steps": 33920, "loss": 0.7064, "lr": 2.134433962264151e-06, "epoch": 0.42747641509433965, "percentage": 2.14, "elapsed_time": "0:01:18", "remaining_time": "0:59:35", "throughput": 6115.98, "total_tokens": 477664} +{"current_steps": 730, "total_steps": 33920, "loss": 0.5702, "lr": 2.149174528301887e-06, "epoch": 0.43042452830188677, "percentage": 2.15, "elapsed_time": "0:01:18", "remaining_time": "0:59:38", "throughput": 6122.5, "total_tokens": 481824} +{"current_steps": 735, "total_steps": 33920, "loss": 0.7767, "lr": 2.163915094339623e-06, "epoch": 0.43337264150943394, "percentage": 2.17, "elapsed_time": "0:01:19", "remaining_time": "0:59:38", "throughput": 6128.26, "total_tokens": 485728} +{"current_steps": 740, "total_steps": 33920, "loss": 0.7257, "lr": 2.1786556603773588e-06, "epoch": 0.4363207547169811, "percentage": 2.18, "elapsed_time": "0:01:19", "remaining_time": "0:59:35", "throughput": 6126.29, "total_tokens": 488480} +{"current_steps": 745, "total_steps": 33920, "loss": 0.54, "lr": 2.1933962264150945e-06, "epoch": 0.4392688679245283, "percentage": 2.2, "elapsed_time": "0:01:20", "remaining_time": "0:59:35", "throughput": 6128.24, "total_tokens": 492032} +{"current_steps": 750, "total_steps": 33920, "loss": 0.6328, "lr": 2.2081367924528303e-06, "epoch": 0.44221698113207547, "percentage": 2.21, "elapsed_time": "0:01:20", "remaining_time": "0:59:30", "throughput": 6124.59, "total_tokens": 494496} +{"current_steps": 755, "total_steps": 33920, "loss": 0.6721, "lr": 2.2228773584905665e-06, "epoch": 0.44516509433962265, "percentage": 2.23, "elapsed_time": "0:01:21", "remaining_time": "0:59:29", "throughput": 6125.54, "total_tokens": 497792} +{"current_steps": 760, "total_steps": 33920, "loss": 0.6328, "lr": 2.237617924528302e-06, "epoch": 0.4481132075471698, "percentage": 2.24, "elapsed_time": "0:01:21", "remaining_time": "0:59:31", "throughput": 6129.42, "total_tokens": 501664} +{"current_steps": 765, "total_steps": 33920, "loss": 0.5973, "lr": 2.252358490566038e-06, "epoch": 0.451061320754717, "percentage": 2.26, "elapsed_time": "0:01:22", "remaining_time": "0:59:29", "throughput": 6129.96, "total_tokens": 504928} +{"current_steps": 770, "total_steps": 33920, "loss": 0.6766, "lr": 2.267099056603774e-06, "epoch": 0.4540094339622642, "percentage": 2.27, "elapsed_time": "0:01:22", "remaining_time": "0:59:28", "throughput": 6127.9, "total_tokens": 507904} +{"current_steps": 775, "total_steps": 33920, "loss": 0.6994, "lr": 2.2818396226415096e-06, "epoch": 0.4569575471698113, "percentage": 2.28, "elapsed_time": "0:01:23", "remaining_time": "0:59:28", "throughput": 6131.26, "total_tokens": 511648} +{"current_steps": 780, "total_steps": 33920, "loss": 0.6119, "lr": 2.2965801886792453e-06, "epoch": 0.45990566037735847, "percentage": 2.3, "elapsed_time": "0:01:24", "remaining_time": "0:59:30", "throughput": 6134.45, "total_tokens": 515488} +{"current_steps": 785, "total_steps": 33920, "loss": 0.5788, "lr": 2.3113207547169815e-06, "epoch": 0.46285377358490565, "percentage": 2.31, "elapsed_time": "0:01:24", "remaining_time": "0:59:27", "throughput": 6135.69, "total_tokens": 518624} +{"current_steps": 790, "total_steps": 33920, "loss": 0.8331, "lr": 2.3260613207547173e-06, "epoch": 0.4658018867924528, "percentage": 2.33, "elapsed_time": "0:01:25", "remaining_time": "0:59:25", "throughput": 6135.68, "total_tokens": 521728} +{"current_steps": 795, "total_steps": 33920, "loss": 0.8239, "lr": 2.340801886792453e-06, "epoch": 0.46875, "percentage": 2.34, "elapsed_time": "0:01:25", "remaining_time": "0:59:25", "throughput": 6137.85, "total_tokens": 525248} +{"current_steps": 800, "total_steps": 33920, "loss": 0.7549, "lr": 2.355542452830189e-06, "epoch": 0.4716981132075472, "percentage": 2.36, "elapsed_time": "0:01:26", "remaining_time": "0:59:24", "throughput": 6139.77, "total_tokens": 528640} +{"current_steps": 805, "total_steps": 33920, "loss": 0.546, "lr": 2.3702830188679246e-06, "epoch": 0.47464622641509435, "percentage": 2.37, "elapsed_time": "0:01:26", "remaining_time": "0:59:23", "throughput": 6138.19, "total_tokens": 531776} +{"current_steps": 810, "total_steps": 33920, "loss": 0.6775, "lr": 2.3850235849056604e-06, "epoch": 0.47759433962264153, "percentage": 2.39, "elapsed_time": "0:01:27", "remaining_time": "0:59:22", "throughput": 6140.34, "total_tokens": 535168} +{"current_steps": 815, "total_steps": 33920, "loss": 0.7604, "lr": 2.3997641509433966e-06, "epoch": 0.4805424528301887, "percentage": 2.4, "elapsed_time": "0:01:27", "remaining_time": "0:59:20", "throughput": 6142.31, "total_tokens": 538432} +{"current_steps": 820, "total_steps": 33920, "loss": 0.8166, "lr": 2.4145047169811323e-06, "epoch": 0.4834905660377358, "percentage": 2.42, "elapsed_time": "0:01:28", "remaining_time": "0:59:17", "throughput": 6140.66, "total_tokens": 541184} +{"current_steps": 825, "total_steps": 33920, "loss": 0.6448, "lr": 2.429245283018868e-06, "epoch": 0.486438679245283, "percentage": 2.43, "elapsed_time": "0:01:28", "remaining_time": "0:59:13", "throughput": 6136.54, "total_tokens": 543552} +{"current_steps": 830, "total_steps": 33920, "loss": 0.5739, "lr": 2.443985849056604e-06, "epoch": 0.4893867924528302, "percentage": 2.45, "elapsed_time": "0:01:29", "remaining_time": "0:59:09", "throughput": 6135.46, "total_tokens": 546272} +{"current_steps": 835, "total_steps": 33920, "loss": 0.6901, "lr": 2.45872641509434e-06, "epoch": 0.49233490566037735, "percentage": 2.46, "elapsed_time": "0:01:29", "remaining_time": "0:59:11", "throughput": 6139.67, "total_tokens": 550336} +{"current_steps": 840, "total_steps": 33920, "loss": 0.6293, "lr": 2.473466981132076e-06, "epoch": 0.49528301886792453, "percentage": 2.48, "elapsed_time": "0:01:30", "remaining_time": "0:59:11", "throughput": 6142.81, "total_tokens": 554048} +{"current_steps": 845, "total_steps": 33920, "loss": 0.836, "lr": 2.4882075471698116e-06, "epoch": 0.4982311320754717, "percentage": 2.49, "elapsed_time": "0:01:30", "remaining_time": "0:59:08", "throughput": 6141.43, "total_tokens": 556704} +{"current_steps": 850, "total_steps": 33920, "loss": 0.6885, "lr": 2.5029481132075474e-06, "epoch": 0.5011792452830188, "percentage": 2.51, "elapsed_time": "0:01:31", "remaining_time": "0:59:09", "throughput": 6137.9, "total_tokens": 559904} +{"current_steps": 855, "total_steps": 33920, "loss": 0.8499, "lr": 2.517688679245283e-06, "epoch": 0.504127358490566, "percentage": 2.52, "elapsed_time": "0:01:31", "remaining_time": "0:59:06", "throughput": 6135.7, "total_tokens": 562752} +{"current_steps": 860, "total_steps": 33920, "loss": 0.9022, "lr": 2.532429245283019e-06, "epoch": 0.5070754716981132, "percentage": 2.54, "elapsed_time": "0:01:32", "remaining_time": "0:59:04", "throughput": 6135.83, "total_tokens": 565792} +{"current_steps": 865, "total_steps": 33920, "loss": 0.7125, "lr": 2.547169811320755e-06, "epoch": 0.5100235849056604, "percentage": 2.55, "elapsed_time": "0:01:32", "remaining_time": "0:59:03", "throughput": 6137.47, "total_tokens": 569056} +{"current_steps": 870, "total_steps": 33920, "loss": 0.6445, "lr": 2.561910377358491e-06, "epoch": 0.5129716981132075, "percentage": 2.56, "elapsed_time": "0:01:33", "remaining_time": "0:59:01", "throughput": 6137.57, "total_tokens": 572224} +{"current_steps": 875, "total_steps": 33920, "loss": 0.6508, "lr": 2.5766509433962266e-06, "epoch": 0.5159198113207547, "percentage": 2.58, "elapsed_time": "0:01:33", "remaining_time": "0:59:05", "throughput": 6141.49, "total_tokens": 576512} +{"current_steps": 880, "total_steps": 33920, "loss": 0.6344, "lr": 2.5913915094339624e-06, "epoch": 0.5188679245283019, "percentage": 2.59, "elapsed_time": "0:01:34", "remaining_time": "0:59:02", "throughput": 6142.39, "total_tokens": 579616} +{"current_steps": 885, "total_steps": 33920, "loss": 0.8628, "lr": 2.6061320754716986e-06, "epoch": 0.5218160377358491, "percentage": 2.61, "elapsed_time": "0:01:34", "remaining_time": "0:59:01", "throughput": 6142.57, "total_tokens": 582784} +{"current_steps": 890, "total_steps": 33920, "loss": 0.7733, "lr": 2.6208726415094343e-06, "epoch": 0.5247641509433962, "percentage": 2.62, "elapsed_time": "0:01:35", "remaining_time": "0:58:59", "throughput": 6142.14, "total_tokens": 585760} +{"current_steps": 895, "total_steps": 33920, "loss": 0.7089, "lr": 2.63561320754717e-06, "epoch": 0.5277122641509434, "percentage": 2.64, "elapsed_time": "0:01:35", "remaining_time": "0:58:56", "throughput": 6141.27, "total_tokens": 588672} +{"current_steps": 900, "total_steps": 33920, "loss": 0.6357, "lr": 2.650353773584906e-06, "epoch": 0.5306603773584906, "percentage": 2.65, "elapsed_time": "0:01:36", "remaining_time": "0:58:54", "throughput": 6140.74, "total_tokens": 591520} +{"current_steps": 905, "total_steps": 33920, "loss": 0.5284, "lr": 2.665094339622642e-06, "epoch": 0.5336084905660378, "percentage": 2.67, "elapsed_time": "0:01:36", "remaining_time": "0:58:51", "throughput": 6141.32, "total_tokens": 594560} +{"current_steps": 910, "total_steps": 33920, "loss": 0.6356, "lr": 2.679834905660378e-06, "epoch": 0.5365566037735849, "percentage": 2.68, "elapsed_time": "0:01:37", "remaining_time": "0:59:07", "throughput": 6147.94, "total_tokens": 601184} +{"current_steps": 915, "total_steps": 33920, "loss": 0.6077, "lr": 2.694575471698113e-06, "epoch": 0.5395047169811321, "percentage": 2.7, "elapsed_time": "0:01:38", "remaining_time": "0:59:05", "throughput": 6147.82, "total_tokens": 604224} +{"current_steps": 920, "total_steps": 33920, "loss": 0.5682, "lr": 2.709316037735849e-06, "epoch": 0.5424528301886793, "percentage": 2.71, "elapsed_time": "0:01:38", "remaining_time": "0:59:05", "throughput": 6150.35, "total_tokens": 607904} +{"current_steps": 925, "total_steps": 33920, "loss": 0.6481, "lr": 2.724056603773585e-06, "epoch": 0.5454009433962265, "percentage": 2.73, "elapsed_time": "0:01:39", "remaining_time": "0:59:03", "throughput": 6148.72, "total_tokens": 610784} +{"current_steps": 930, "total_steps": 33920, "loss": 0.6293, "lr": 2.738797169811321e-06, "epoch": 0.5483490566037735, "percentage": 2.74, "elapsed_time": "0:01:39", "remaining_time": "0:59:02", "throughput": 6150.07, "total_tokens": 614112} +{"current_steps": 935, "total_steps": 33920, "loss": 0.6597, "lr": 2.7535377358490567e-06, "epoch": 0.5512971698113207, "percentage": 2.76, "elapsed_time": "0:01:40", "remaining_time": "0:59:02", "throughput": 6153.16, "total_tokens": 617792} +{"current_steps": 940, "total_steps": 33920, "loss": 0.7425, "lr": 2.7682783018867925e-06, "epoch": 0.5542452830188679, "percentage": 2.77, "elapsed_time": "0:01:40", "remaining_time": "0:58:58", "throughput": 6150.71, "total_tokens": 620416} +{"current_steps": 945, "total_steps": 33920, "loss": 0.6228, "lr": 2.7830188679245286e-06, "epoch": 0.5571933962264151, "percentage": 2.79, "elapsed_time": "0:01:41", "remaining_time": "0:58:55", "throughput": 6148.48, "total_tokens": 623040} +{"current_steps": 950, "total_steps": 33920, "loss": 0.5043, "lr": 2.7977594339622644e-06, "epoch": 0.5601415094339622, "percentage": 2.8, "elapsed_time": "0:01:41", "remaining_time": "0:58:56", "throughput": 6152.39, "total_tokens": 626976} +{"current_steps": 955, "total_steps": 33920, "loss": 0.6673, "lr": 2.8125e-06, "epoch": 0.5630896226415094, "percentage": 2.82, "elapsed_time": "0:01:42", "remaining_time": "0:58:55", "throughput": 6153.25, "total_tokens": 630176} +{"current_steps": 960, "total_steps": 33920, "loss": 0.708, "lr": 2.827240566037736e-06, "epoch": 0.5660377358490566, "percentage": 2.83, "elapsed_time": "0:01:42", "remaining_time": "0:58:53", "throughput": 6153.94, "total_tokens": 633408} +{"current_steps": 965, "total_steps": 33920, "loss": 0.5939, "lr": 2.841981132075472e-06, "epoch": 0.5689858490566038, "percentage": 2.84, "elapsed_time": "0:01:43", "remaining_time": "0:58:50", "throughput": 6152.65, "total_tokens": 636000} +{"current_steps": 970, "total_steps": 33920, "loss": 0.6315, "lr": 2.856721698113208e-06, "epoch": 0.5719339622641509, "percentage": 2.86, "elapsed_time": "0:01:43", "remaining_time": "0:58:51", "throughput": 6156.22, "total_tokens": 640000} +{"current_steps": 975, "total_steps": 33920, "loss": 0.6974, "lr": 2.8714622641509437e-06, "epoch": 0.5748820754716981, "percentage": 2.87, "elapsed_time": "0:01:44", "remaining_time": "0:58:49", "throughput": 6155.7, "total_tokens": 643072} +{"current_steps": 980, "total_steps": 33920, "loss": 0.8485, "lr": 2.8862028301886794e-06, "epoch": 0.5778301886792453, "percentage": 2.89, "elapsed_time": "0:01:44", "remaining_time": "0:58:47", "throughput": 6154.17, "total_tokens": 645824} +{"current_steps": 985, "total_steps": 33920, "loss": 0.768, "lr": 2.9009433962264156e-06, "epoch": 0.5807783018867925, "percentage": 2.9, "elapsed_time": "0:01:45", "remaining_time": "0:58:50", "throughput": 6159.01, "total_tokens": 650240} +{"current_steps": 990, "total_steps": 33920, "loss": 0.5173, "lr": 2.9156839622641514e-06, "epoch": 0.5837264150943396, "percentage": 2.92, "elapsed_time": "0:01:46", "remaining_time": "0:58:47", "throughput": 6156.85, "total_tokens": 652960} +{"current_steps": 995, "total_steps": 33920, "loss": 0.6091, "lr": 2.930424528301887e-06, "epoch": 0.5866745283018868, "percentage": 2.93, "elapsed_time": "0:01:46", "remaining_time": "0:58:46", "throughput": 6155.27, "total_tokens": 655968} +{"current_steps": 1000, "total_steps": 33920, "loss": 0.5206, "lr": 2.9451650943396225e-06, "epoch": 0.589622641509434, "percentage": 2.95, "elapsed_time": "0:01:47", "remaining_time": "0:58:44", "throughput": 6153.5, "total_tokens": 658752} +{"current_steps": 1005, "total_steps": 33920, "loss": 0.7423, "lr": 2.9599056603773587e-06, "epoch": 0.5925707547169812, "percentage": 2.96, "elapsed_time": "0:01:47", "remaining_time": "0:58:43", "throughput": 6155.56, "total_tokens": 662176} +{"current_steps": 1010, "total_steps": 33920, "loss": 0.5009, "lr": 2.9746462264150945e-06, "epoch": 0.5955188679245284, "percentage": 2.98, "elapsed_time": "0:01:48", "remaining_time": "0:58:43", "throughput": 6156.59, "total_tokens": 665760} +{"current_steps": 1015, "total_steps": 33920, "loss": 0.6489, "lr": 2.9893867924528302e-06, "epoch": 0.5984669811320755, "percentage": 2.99, "elapsed_time": "0:01:48", "remaining_time": "0:58:41", "throughput": 6157.29, "total_tokens": 668832} +{"current_steps": 1020, "total_steps": 33920, "loss": 0.7294, "lr": 3.004127358490566e-06, "epoch": 0.6014150943396226, "percentage": 3.01, "elapsed_time": "0:01:49", "remaining_time": "0:58:39", "throughput": 6157.67, "total_tokens": 671936} +{"current_steps": 1025, "total_steps": 33920, "loss": 0.6161, "lr": 3.018867924528302e-06, "epoch": 0.6043632075471698, "percentage": 3.02, "elapsed_time": "0:01:49", "remaining_time": "0:58:39", "throughput": 6157.26, "total_tokens": 675264} +{"current_steps": 1030, "total_steps": 33920, "loss": 0.5463, "lr": 3.033608490566038e-06, "epoch": 0.6073113207547169, "percentage": 3.04, "elapsed_time": "0:01:50", "remaining_time": "0:58:39", "throughput": 6157.55, "total_tokens": 678624} +{"current_steps": 1035, "total_steps": 33920, "loss": 0.6682, "lr": 3.0483490566037737e-06, "epoch": 0.6102594339622641, "percentage": 3.05, "elapsed_time": "0:01:50", "remaining_time": "0:58:43", "throughput": 6161.96, "total_tokens": 683264} +{"current_steps": 1040, "total_steps": 33920, "loss": 0.5731, "lr": 3.0630896226415095e-06, "epoch": 0.6132075471698113, "percentage": 3.07, "elapsed_time": "0:01:51", "remaining_time": "0:58:46", "throughput": 6164.15, "total_tokens": 687552} +{"current_steps": 1045, "total_steps": 33920, "loss": 0.4943, "lr": 3.0778301886792457e-06, "epoch": 0.6161556603773585, "percentage": 3.08, "elapsed_time": "0:01:52", "remaining_time": "0:58:43", "throughput": 6162.37, "total_tokens": 690208} +{"current_steps": 1050, "total_steps": 33920, "loss": 0.644, "lr": 3.0925707547169815e-06, "epoch": 0.6191037735849056, "percentage": 3.1, "elapsed_time": "0:01:52", "remaining_time": "0:58:43", "throughput": 6162.61, "total_tokens": 693600} +{"current_steps": 1055, "total_steps": 33920, "loss": 0.6085, "lr": 3.1073113207547172e-06, "epoch": 0.6220518867924528, "percentage": 3.11, "elapsed_time": "0:01:53", "remaining_time": "0:58:41", "throughput": 6157.76, "total_tokens": 696160} +{"current_steps": 1060, "total_steps": 33920, "loss": 0.6682, "lr": 3.122051886792453e-06, "epoch": 0.625, "percentage": 3.12, "elapsed_time": "0:01:53", "remaining_time": "0:58:44", "throughput": 6160.4, "total_tokens": 700384} +{"current_steps": 1065, "total_steps": 33920, "loss": 0.521, "lr": 3.136792452830189e-06, "epoch": 0.6279481132075472, "percentage": 3.14, "elapsed_time": "0:01:54", "remaining_time": "0:58:42", "throughput": 6160.79, "total_tokens": 703552} +{"current_steps": 1070, "total_steps": 33920, "loss": 0.5971, "lr": 3.151533018867925e-06, "epoch": 0.6308962264150944, "percentage": 3.15, "elapsed_time": "0:01:54", "remaining_time": "0:58:44", "throughput": 6162.46, "total_tokens": 707360} +{"current_steps": 1075, "total_steps": 33920, "loss": 0.5919, "lr": 3.1662735849056607e-06, "epoch": 0.6338443396226415, "percentage": 3.17, "elapsed_time": "0:01:55", "remaining_time": "0:58:44", "throughput": 6165.6, "total_tokens": 711232} +{"current_steps": 1080, "total_steps": 33920, "loss": 0.6113, "lr": 3.181014150943397e-06, "epoch": 0.6367924528301887, "percentage": 3.18, "elapsed_time": "0:01:55", "remaining_time": "0:58:41", "throughput": 6164.24, "total_tokens": 713984} +{"current_steps": 1085, "total_steps": 33920, "loss": 0.6166, "lr": 3.1957547169811327e-06, "epoch": 0.6397405660377359, "percentage": 3.2, "elapsed_time": "0:01:56", "remaining_time": "0:58:40", "throughput": 6164.21, "total_tokens": 717024} +{"current_steps": 1090, "total_steps": 33920, "loss": 0.5285, "lr": 3.210495283018868e-06, "epoch": 0.6426886792452831, "percentage": 3.21, "elapsed_time": "0:01:56", "remaining_time": "0:58:39", "throughput": 6166.65, "total_tokens": 720672} +{"current_steps": 1095, "total_steps": 33920, "loss": 0.6873, "lr": 3.225235849056604e-06, "epoch": 0.6456367924528302, "percentage": 3.23, "elapsed_time": "0:01:57", "remaining_time": "0:58:42", "throughput": 6169.86, "total_tokens": 724960} +{"current_steps": 1100, "total_steps": 33920, "loss": 0.6268, "lr": 3.2399764150943396e-06, "epoch": 0.6485849056603774, "percentage": 3.24, "elapsed_time": "0:01:57", "remaining_time": "0:58:39", "throughput": 6168.26, "total_tokens": 727616} +{"current_steps": 1105, "total_steps": 33920, "loss": 0.6578, "lr": 3.2547169811320758e-06, "epoch": 0.6515330188679245, "percentage": 3.26, "elapsed_time": "0:01:58", "remaining_time": "0:58:36", "throughput": 6166.36, "total_tokens": 730144} +{"current_steps": 1110, "total_steps": 33920, "loss": 0.4531, "lr": 3.2694575471698115e-06, "epoch": 0.6544811320754716, "percentage": 3.27, "elapsed_time": "0:01:58", "remaining_time": "0:58:36", "throughput": 6166.6, "total_tokens": 733696} +{"current_steps": 1115, "total_steps": 33920, "loss": 0.6455, "lr": 3.2841981132075473e-06, "epoch": 0.6574292452830188, "percentage": 3.29, "elapsed_time": "0:01:59", "remaining_time": "0:58:36", "throughput": 6167.28, "total_tokens": 737120} +{"current_steps": 1120, "total_steps": 33920, "loss": 0.5823, "lr": 3.298938679245283e-06, "epoch": 0.660377358490566, "percentage": 3.3, "elapsed_time": "0:02:00", "remaining_time": "0:58:36", "throughput": 6167.87, "total_tokens": 740512} +{"current_steps": 1125, "total_steps": 33920, "loss": 0.6032, "lr": 3.3136792452830192e-06, "epoch": 0.6633254716981132, "percentage": 3.32, "elapsed_time": "0:02:00", "remaining_time": "0:58:35", "throughput": 6168.75, "total_tokens": 743936} +{"current_steps": 1130, "total_steps": 33920, "loss": 0.5163, "lr": 3.328419811320755e-06, "epoch": 0.6662735849056604, "percentage": 3.33, "elapsed_time": "0:02:01", "remaining_time": "0:58:32", "throughput": 6164.85, "total_tokens": 746176} +{"current_steps": 1135, "total_steps": 33920, "loss": 0.5427, "lr": 3.3431603773584908e-06, "epoch": 0.6692216981132075, "percentage": 3.35, "elapsed_time": "0:02:01", "remaining_time": "0:58:30", "throughput": 6166.42, "total_tokens": 749504} +{"current_steps": 1140, "total_steps": 33920, "loss": 0.5874, "lr": 3.3579009433962266e-06, "epoch": 0.6721698113207547, "percentage": 3.36, "elapsed_time": "0:02:02", "remaining_time": "0:58:29", "throughput": 6166.94, "total_tokens": 752672} +{"current_steps": 1145, "total_steps": 33920, "loss": 0.6977, "lr": 3.3726415094339627e-06, "epoch": 0.6751179245283019, "percentage": 3.38, "elapsed_time": "0:02:02", "remaining_time": "0:58:27", "throughput": 6163.82, "total_tokens": 755296} +{"current_steps": 1150, "total_steps": 33920, "loss": 0.7821, "lr": 3.3873820754716985e-06, "epoch": 0.6780660377358491, "percentage": 3.39, "elapsed_time": "0:02:03", "remaining_time": "0:58:25", "throughput": 6162.06, "total_tokens": 758048} +{"current_steps": 1155, "total_steps": 33920, "loss": 0.6409, "lr": 3.4021226415094343e-06, "epoch": 0.6810141509433962, "percentage": 3.41, "elapsed_time": "0:02:03", "remaining_time": "0:58:23", "throughput": 6161.45, "total_tokens": 761024} +{"current_steps": 1160, "total_steps": 33920, "loss": 0.6653, "lr": 3.4168632075471705e-06, "epoch": 0.6839622641509434, "percentage": 3.42, "elapsed_time": "0:02:03", "remaining_time": "0:58:21", "throughput": 6161.0, "total_tokens": 763808} +{"current_steps": 1165, "total_steps": 33920, "loss": 0.5945, "lr": 3.4316037735849062e-06, "epoch": 0.6869103773584906, "percentage": 3.43, "elapsed_time": "0:02:04", "remaining_time": "0:58:19", "throughput": 6161.13, "total_tokens": 766912} +{"current_steps": 1170, "total_steps": 33920, "loss": 0.7233, "lr": 3.446344339622642e-06, "epoch": 0.6898584905660378, "percentage": 3.45, "elapsed_time": "0:02:05", "remaining_time": "0:58:21", "throughput": 6161.87, "total_tokens": 770880} +{"current_steps": 1175, "total_steps": 33920, "loss": 0.5657, "lr": 3.4610849056603778e-06, "epoch": 0.6928066037735849, "percentage": 3.46, "elapsed_time": "0:02:05", "remaining_time": "0:58:21", "throughput": 6162.85, "total_tokens": 774432} +{"current_steps": 1180, "total_steps": 33920, "loss": 0.6825, "lr": 3.475825471698113e-06, "epoch": 0.6957547169811321, "percentage": 3.48, "elapsed_time": "0:02:06", "remaining_time": "0:58:21", "throughput": 6164.64, "total_tokens": 777920} +{"current_steps": 1185, "total_steps": 33920, "loss": 0.6523, "lr": 3.4905660377358493e-06, "epoch": 0.6987028301886793, "percentage": 3.49, "elapsed_time": "0:02:06", "remaining_time": "0:58:19", "throughput": 6161.74, "total_tokens": 780640} +{"current_steps": 1190, "total_steps": 33920, "loss": 0.593, "lr": 3.505306603773585e-06, "epoch": 0.7016509433962265, "percentage": 3.51, "elapsed_time": "0:02:07", "remaining_time": "0:58:16", "throughput": 6159.95, "total_tokens": 783072} +{"current_steps": 1195, "total_steps": 33920, "loss": 0.4876, "lr": 3.520047169811321e-06, "epoch": 0.7045990566037735, "percentage": 3.52, "elapsed_time": "0:02:07", "remaining_time": "0:58:17", "throughput": 6162.16, "total_tokens": 786944} +{"current_steps": 1200, "total_steps": 33920, "loss": 0.619, "lr": 3.5347877358490566e-06, "epoch": 0.7075471698113207, "percentage": 3.54, "elapsed_time": "0:02:08", "remaining_time": "0:58:20", "throughput": 6166.89, "total_tokens": 791680} +{"current_steps": 1205, "total_steps": 33920, "loss": 0.6129, "lr": 3.549528301886793e-06, "epoch": 0.7104952830188679, "percentage": 3.55, "elapsed_time": "0:02:08", "remaining_time": "0:58:19", "throughput": 6166.44, "total_tokens": 794912} +{"current_steps": 1210, "total_steps": 33920, "loss": 0.5696, "lr": 3.5642688679245286e-06, "epoch": 0.7134433962264151, "percentage": 3.57, "elapsed_time": "0:02:09", "remaining_time": "0:58:18", "throughput": 6164.73, "total_tokens": 797728} +{"current_steps": 1215, "total_steps": 33920, "loss": 0.4925, "lr": 3.5790094339622643e-06, "epoch": 0.7163915094339622, "percentage": 3.58, "elapsed_time": "0:02:09", "remaining_time": "0:58:18", "throughput": 6167.31, "total_tokens": 801632} +{"current_steps": 1220, "total_steps": 33920, "loss": 0.6959, "lr": 3.59375e-06, "epoch": 0.7193396226415094, "percentage": 3.6, "elapsed_time": "0:02:10", "remaining_time": "0:58:16", "throughput": 6167.6, "total_tokens": 804640} +{"current_steps": 1225, "total_steps": 33920, "loss": 0.6877, "lr": 3.6084905660377363e-06, "epoch": 0.7222877358490566, "percentage": 3.61, "elapsed_time": "0:02:10", "remaining_time": "0:58:13", "throughput": 6164.77, "total_tokens": 807008} +{"current_steps": 1230, "total_steps": 33920, "loss": 0.6237, "lr": 3.623231132075472e-06, "epoch": 0.7252358490566038, "percentage": 3.63, "elapsed_time": "0:02:11", "remaining_time": "0:58:12", "throughput": 6165.27, "total_tokens": 810176} +{"current_steps": 1235, "total_steps": 33920, "loss": 0.7286, "lr": 3.637971698113208e-06, "epoch": 0.7281839622641509, "percentage": 3.64, "elapsed_time": "0:02:11", "remaining_time": "0:58:11", "throughput": 6165.77, "total_tokens": 813440} +{"current_steps": 1240, "total_steps": 33920, "loss": 0.4679, "lr": 3.652712264150944e-06, "epoch": 0.7311320754716981, "percentage": 3.66, "elapsed_time": "0:02:12", "remaining_time": "0:58:13", "throughput": 6168.73, "total_tokens": 817728} +{"current_steps": 1245, "total_steps": 33920, "loss": 0.5281, "lr": 3.66745283018868e-06, "epoch": 0.7340801886792453, "percentage": 3.67, "elapsed_time": "0:02:13", "remaining_time": "0:58:11", "throughput": 6168.78, "total_tokens": 820768} +{"current_steps": 1250, "total_steps": 33920, "loss": 0.5894, "lr": 3.6821933962264156e-06, "epoch": 0.7370283018867925, "percentage": 3.69, "elapsed_time": "0:02:13", "remaining_time": "0:58:09", "throughput": 6167.37, "total_tokens": 823392} +{"current_steps": 1255, "total_steps": 33920, "loss": 0.6526, "lr": 3.6969339622641513e-06, "epoch": 0.7399764150943396, "percentage": 3.7, "elapsed_time": "0:02:13", "remaining_time": "0:58:06", "throughput": 6165.43, "total_tokens": 825856} +{"current_steps": 1260, "total_steps": 33920, "loss": 0.6207, "lr": 3.7116745283018875e-06, "epoch": 0.7429245283018868, "percentage": 3.71, "elapsed_time": "0:02:14", "remaining_time": "0:58:04", "throughput": 6165.73, "total_tokens": 828960} +{"current_steps": 1265, "total_steps": 33920, "loss": 0.6705, "lr": 3.726415094339623e-06, "epoch": 0.745872641509434, "percentage": 3.73, "elapsed_time": "0:02:14", "remaining_time": "0:58:04", "throughput": 6166.83, "total_tokens": 832352} +{"current_steps": 1270, "total_steps": 33920, "loss": 0.3802, "lr": 3.7411556603773586e-06, "epoch": 0.7488207547169812, "percentage": 3.74, "elapsed_time": "0:02:15", "remaining_time": "0:58:07", "throughput": 6169.9, "total_tokens": 837056} +{"current_steps": 1275, "total_steps": 33920, "loss": 0.6304, "lr": 3.7558962264150944e-06, "epoch": 0.7517688679245284, "percentage": 3.76, "elapsed_time": "0:02:16", "remaining_time": "0:58:08", "throughput": 6172.41, "total_tokens": 841056} +{"current_steps": 1280, "total_steps": 33920, "loss": 0.7641, "lr": 3.77063679245283e-06, "epoch": 0.7547169811320755, "percentage": 3.77, "elapsed_time": "0:02:16", "remaining_time": "0:58:05", "throughput": 6168.52, "total_tokens": 843232} +{"current_steps": 1285, "total_steps": 33920, "loss": 0.6184, "lr": 3.7853773584905664e-06, "epoch": 0.7576650943396226, "percentage": 3.79, "elapsed_time": "0:02:17", "remaining_time": "0:58:07", "throughput": 6169.85, "total_tokens": 847264} +{"current_steps": 1290, "total_steps": 33920, "loss": 0.5735, "lr": 3.800117924528302e-06, "epoch": 0.7606132075471698, "percentage": 3.8, "elapsed_time": "0:02:17", "remaining_time": "0:58:08", "throughput": 6172.09, "total_tokens": 851296} +{"current_steps": 1295, "total_steps": 33920, "loss": 0.5515, "lr": 3.814858490566038e-06, "epoch": 0.7635613207547169, "percentage": 3.82, "elapsed_time": "0:02:18", "remaining_time": "0:58:07", "throughput": 6172.02, "total_tokens": 854336} +{"current_steps": 1300, "total_steps": 33920, "loss": 0.5659, "lr": 3.829599056603774e-06, "epoch": 0.7665094339622641, "percentage": 3.83, "elapsed_time": "0:02:18", "remaining_time": "0:58:04", "throughput": 6169.03, "total_tokens": 856704} +{"current_steps": 1305, "total_steps": 33920, "loss": 0.7062, "lr": 3.8443396226415094e-06, "epoch": 0.7694575471698113, "percentage": 3.85, "elapsed_time": "0:02:19", "remaining_time": "0:58:03", "throughput": 6169.6, "total_tokens": 860000} +{"current_steps": 1310, "total_steps": 33920, "loss": 0.5802, "lr": 3.859080188679246e-06, "epoch": 0.7724056603773585, "percentage": 3.86, "elapsed_time": "0:02:20", "remaining_time": "0:58:05", "throughput": 6172.41, "total_tokens": 864160} +{"current_steps": 1315, "total_steps": 33920, "loss": 0.8713, "lr": 3.873820754716982e-06, "epoch": 0.7753537735849056, "percentage": 3.88, "elapsed_time": "0:02:20", "remaining_time": "0:58:02", "throughput": 6171.44, "total_tokens": 866848} +{"current_steps": 1320, "total_steps": 33920, "loss": 0.7524, "lr": 3.888561320754717e-06, "epoch": 0.7783018867924528, "percentage": 3.89, "elapsed_time": "0:02:21", "remaining_time": "0:58:02", "throughput": 6171.23, "total_tokens": 870176} +{"current_steps": 1325, "total_steps": 33920, "loss": 0.6063, "lr": 3.903301886792453e-06, "epoch": 0.78125, "percentage": 3.91, "elapsed_time": "0:02:21", "remaining_time": "0:58:05", "throughput": 6175.38, "total_tokens": 874976} +{"current_steps": 1330, "total_steps": 33920, "loss": 0.6285, "lr": 3.9180424528301895e-06, "epoch": 0.7841981132075472, "percentage": 3.92, "elapsed_time": "0:02:22", "remaining_time": "0:58:04", "throughput": 6174.6, "total_tokens": 878112} +{"current_steps": 1335, "total_steps": 33920, "loss": 0.5765, "lr": 3.932783018867925e-06, "epoch": 0.7871462264150944, "percentage": 3.94, "elapsed_time": "0:02:22", "remaining_time": "0:58:03", "throughput": 6174.79, "total_tokens": 881248} +{"current_steps": 1340, "total_steps": 33920, "loss": 0.5969, "lr": 3.947523584905661e-06, "epoch": 0.7900943396226415, "percentage": 3.95, "elapsed_time": "0:02:23", "remaining_time": "0:58:01", "throughput": 6173.75, "total_tokens": 884096} +{"current_steps": 1345, "total_steps": 33920, "loss": 0.532, "lr": 3.962264150943396e-06, "epoch": 0.7930424528301887, "percentage": 3.97, "elapsed_time": "0:02:23", "remaining_time": "0:57:59", "throughput": 6172.4, "total_tokens": 886816} +{"current_steps": 1350, "total_steps": 33920, "loss": 0.6226, "lr": 3.977004716981133e-06, "epoch": 0.7959905660377359, "percentage": 3.98, "elapsed_time": "0:02:24", "remaining_time": "0:57:58", "throughput": 6172.38, "total_tokens": 889952} +{"current_steps": 1355, "total_steps": 33920, "loss": 0.5009, "lr": 3.991745283018868e-06, "epoch": 0.7989386792452831, "percentage": 3.99, "elapsed_time": "0:02:24", "remaining_time": "0:57:56", "throughput": 6170.34, "total_tokens": 892480} +{"current_steps": 1360, "total_steps": 33920, "loss": 0.4451, "lr": 4.006485849056604e-06, "epoch": 0.8018867924528302, "percentage": 4.01, "elapsed_time": "0:02:25", "remaining_time": "0:57:54", "throughput": 6169.68, "total_tokens": 895296} +{"current_steps": 1365, "total_steps": 33920, "loss": 0.5416, "lr": 4.0212264150943395e-06, "epoch": 0.8048349056603774, "percentage": 4.02, "elapsed_time": "0:02:25", "remaining_time": "0:57:54", "throughput": 6170.12, "total_tokens": 898752} +{"current_steps": 1370, "total_steps": 33920, "loss": 0.4249, "lr": 4.035966981132076e-06, "epoch": 0.8077830188679245, "percentage": 4.04, "elapsed_time": "0:02:26", "remaining_time": "0:57:52", "throughput": 6168.59, "total_tokens": 901600} +{"current_steps": 1375, "total_steps": 33920, "loss": 0.5514, "lr": 4.050707547169812e-06, "epoch": 0.8107311320754716, "percentage": 4.05, "elapsed_time": "0:02:26", "remaining_time": "0:57:50", "throughput": 6167.64, "total_tokens": 904384} +{"current_steps": 1380, "total_steps": 33920, "loss": 0.8923, "lr": 4.065448113207547e-06, "epoch": 0.8136792452830188, "percentage": 4.07, "elapsed_time": "0:02:27", "remaining_time": "0:57:49", "throughput": 6165.94, "total_tokens": 907264} +{"current_steps": 1385, "total_steps": 33920, "loss": 0.5869, "lr": 4.080188679245283e-06, "epoch": 0.816627358490566, "percentage": 4.08, "elapsed_time": "0:02:27", "remaining_time": "0:57:47", "throughput": 6163.39, "total_tokens": 909760} +{"current_steps": 1390, "total_steps": 33920, "loss": 0.5282, "lr": 4.094929245283019e-06, "epoch": 0.8195754716981132, "percentage": 4.1, "elapsed_time": "0:02:28", "remaining_time": "0:57:45", "throughput": 6163.57, "total_tokens": 912736} +{"current_steps": 1395, "total_steps": 33920, "loss": 0.4604, "lr": 4.109669811320755e-06, "epoch": 0.8225235849056604, "percentage": 4.11, "elapsed_time": "0:02:28", "remaining_time": "0:57:45", "throughput": 6164.44, "total_tokens": 916384} +{"current_steps": 1400, "total_steps": 33920, "loss": 0.7879, "lr": 4.124410377358491e-06, "epoch": 0.8254716981132075, "percentage": 4.13, "elapsed_time": "0:02:29", "remaining_time": "0:57:45", "throughput": 6165.25, "total_tokens": 919744} +{"current_steps": 1405, "total_steps": 33920, "loss": 0.5083, "lr": 4.1391509433962265e-06, "epoch": 0.8284198113207547, "percentage": 4.14, "elapsed_time": "0:02:29", "remaining_time": "0:57:42", "throughput": 6164.19, "total_tokens": 922368} +{"current_steps": 1410, "total_steps": 33920, "loss": 0.5873, "lr": 4.153891509433963e-06, "epoch": 0.8313679245283019, "percentage": 4.16, "elapsed_time": "0:02:30", "remaining_time": "0:57:41", "throughput": 6163.08, "total_tokens": 925152} +{"current_steps": 1415, "total_steps": 33920, "loss": 0.8659, "lr": 4.168632075471699e-06, "epoch": 0.8343160377358491, "percentage": 4.17, "elapsed_time": "0:02:30", "remaining_time": "0:57:38", "throughput": 6160.69, "total_tokens": 927648} +{"current_steps": 1420, "total_steps": 33920, "loss": 0.5608, "lr": 4.183372641509434e-06, "epoch": 0.8372641509433962, "percentage": 4.19, "elapsed_time": "0:02:31", "remaining_time": "0:57:36", "throughput": 6159.67, "total_tokens": 930304} +{"current_steps": 1425, "total_steps": 33920, "loss": 0.4737, "lr": 4.19811320754717e-06, "epoch": 0.8402122641509434, "percentage": 4.2, "elapsed_time": "0:02:31", "remaining_time": "0:57:35", "throughput": 6160.05, "total_tokens": 933536} +{"current_steps": 1430, "total_steps": 33920, "loss": 0.4669, "lr": 4.212853773584907e-06, "epoch": 0.8431603773584906, "percentage": 4.22, "elapsed_time": "0:02:32", "remaining_time": "0:57:36", "throughput": 6162.04, "total_tokens": 937504} +{"current_steps": 1435, "total_steps": 33920, "loss": 0.8449, "lr": 4.227594339622642e-06, "epoch": 0.8461084905660378, "percentage": 4.23, "elapsed_time": "0:02:32", "remaining_time": "0:57:34", "throughput": 6160.48, "total_tokens": 940128} +{"current_steps": 1440, "total_steps": 33920, "loss": 0.5917, "lr": 4.242334905660378e-06, "epoch": 0.8490566037735849, "percentage": 4.25, "elapsed_time": "0:02:33", "remaining_time": "0:57:34", "throughput": 6159.78, "total_tokens": 943488} +{"current_steps": 1445, "total_steps": 33920, "loss": 0.6725, "lr": 4.2570754716981135e-06, "epoch": 0.8520047169811321, "percentage": 4.26, "elapsed_time": "0:02:33", "remaining_time": "0:57:32", "throughput": 6158.09, "total_tokens": 946016} +{"current_steps": 1450, "total_steps": 33920, "loss": 0.3664, "lr": 4.271816037735849e-06, "epoch": 0.8549528301886793, "percentage": 4.27, "elapsed_time": "0:02:34", "remaining_time": "0:57:30", "throughput": 6156.52, "total_tokens": 948672} +{"current_steps": 1455, "total_steps": 33920, "loss": 0.5968, "lr": 4.286556603773585e-06, "epoch": 0.8579009433962265, "percentage": 4.29, "elapsed_time": "0:02:34", "remaining_time": "0:57:29", "throughput": 6155.3, "total_tokens": 951520} +{"current_steps": 1460, "total_steps": 33920, "loss": 0.5468, "lr": 4.301297169811321e-06, "epoch": 0.8608490566037735, "percentage": 4.3, "elapsed_time": "0:02:35", "remaining_time": "0:57:28", "throughput": 6154.9, "total_tokens": 954592} +{"current_steps": 1465, "total_steps": 33920, "loss": 0.4686, "lr": 4.3160377358490565e-06, "epoch": 0.8637971698113207, "percentage": 4.32, "elapsed_time": "0:02:35", "remaining_time": "0:57:26", "throughput": 6155.12, "total_tokens": 957696} +{"current_steps": 1470, "total_steps": 33920, "loss": 0.6987, "lr": 4.330778301886793e-06, "epoch": 0.8667452830188679, "percentage": 4.33, "elapsed_time": "0:02:36", "remaining_time": "0:57:25", "throughput": 6155.5, "total_tokens": 960832} +{"current_steps": 1475, "total_steps": 33920, "loss": 0.7999, "lr": 4.345518867924529e-06, "epoch": 0.8696933962264151, "percentage": 4.35, "elapsed_time": "0:02:36", "remaining_time": "0:57:27", "throughput": 6154.6, "total_tokens": 964608} +{"current_steps": 1480, "total_steps": 33920, "loss": 0.5806, "lr": 4.360259433962264e-06, "epoch": 0.8726415094339622, "percentage": 4.36, "elapsed_time": "0:02:37", "remaining_time": "0:57:27", "throughput": 6149.75, "total_tokens": 967360} +{"current_steps": 1485, "total_steps": 33920, "loss": 0.5511, "lr": 4.3750000000000005e-06, "epoch": 0.8755896226415094, "percentage": 4.38, "elapsed_time": "0:02:37", "remaining_time": "0:57:28", "throughput": 6146.7, "total_tokens": 970432} +{"current_steps": 1490, "total_steps": 33920, "loss": 0.9184, "lr": 4.389740566037737e-06, "epoch": 0.8785377358490566, "percentage": 4.39, "elapsed_time": "0:02:38", "remaining_time": "0:57:28", "throughput": 6147.27, "total_tokens": 973920} +{"current_steps": 1495, "total_steps": 33920, "loss": 0.5495, "lr": 4.404481132075472e-06, "epoch": 0.8814858490566038, "percentage": 4.41, "elapsed_time": "0:02:38", "remaining_time": "0:57:27", "throughput": 6146.68, "total_tokens": 977152} +{"current_steps": 1500, "total_steps": 33920, "loss": 0.6504, "lr": 4.419221698113208e-06, "epoch": 0.8844339622641509, "percentage": 4.42, "elapsed_time": "0:02:39", "remaining_time": "0:57:25", "throughput": 6145.58, "total_tokens": 979712} +{"current_steps": 1505, "total_steps": 33920, "loss": 0.6059, "lr": 4.4339622641509435e-06, "epoch": 0.8873820754716981, "percentage": 4.44, "elapsed_time": "0:02:39", "remaining_time": "0:57:23", "throughput": 6145.73, "total_tokens": 982592} +{"current_steps": 1510, "total_steps": 33920, "loss": 0.5089, "lr": 4.44870283018868e-06, "epoch": 0.8903301886792453, "percentage": 4.45, "elapsed_time": "0:02:40", "remaining_time": "0:57:21", "throughput": 6144.24, "total_tokens": 985056} +{"current_steps": 1515, "total_steps": 33920, "loss": 0.4899, "lr": 4.463443396226416e-06, "epoch": 0.8932783018867925, "percentage": 4.47, "elapsed_time": "0:02:40", "remaining_time": "0:57:19", "throughput": 6144.17, "total_tokens": 987904} +{"current_steps": 1520, "total_steps": 33920, "loss": 0.4878, "lr": 4.478183962264151e-06, "epoch": 0.8962264150943396, "percentage": 4.48, "elapsed_time": "0:02:41", "remaining_time": "0:57:17", "throughput": 6144.13, "total_tokens": 990752} +{"current_steps": 1525, "total_steps": 33920, "loss": 0.5886, "lr": 4.4929245283018875e-06, "epoch": 0.8991745283018868, "percentage": 4.5, "elapsed_time": "0:02:41", "remaining_time": "0:57:14", "throughput": 6144.14, "total_tokens": 993344} +{"current_steps": 1530, "total_steps": 33920, "loss": 0.5017, "lr": 4.507665094339623e-06, "epoch": 0.902122641509434, "percentage": 4.51, "elapsed_time": "0:02:42", "remaining_time": "0:57:13", "throughput": 6145.73, "total_tokens": 996896} +{"current_steps": 1535, "total_steps": 33920, "loss": 0.4948, "lr": 4.522405660377359e-06, "epoch": 0.9050707547169812, "percentage": 4.53, "elapsed_time": "0:02:42", "remaining_time": "0:57:14", "throughput": 6147.47, "total_tokens": 1000672} +{"current_steps": 1540, "total_steps": 33920, "loss": 0.4765, "lr": 4.537146226415094e-06, "epoch": 0.9080188679245284, "percentage": 4.54, "elapsed_time": "0:02:43", "remaining_time": "0:57:13", "throughput": 6147.93, "total_tokens": 1003808} +{"current_steps": 1545, "total_steps": 33920, "loss": 0.5747, "lr": 4.5518867924528305e-06, "epoch": 0.9109669811320755, "percentage": 4.55, "elapsed_time": "0:02:43", "remaining_time": "0:57:11", "throughput": 6148.16, "total_tokens": 1006720} +{"current_steps": 1550, "total_steps": 33920, "loss": 0.5044, "lr": 4.566627358490566e-06, "epoch": 0.9139150943396226, "percentage": 4.57, "elapsed_time": "0:02:44", "remaining_time": "0:57:09", "throughput": 6149.23, "total_tokens": 1009888} +{"current_steps": 1555, "total_steps": 33920, "loss": 0.5392, "lr": 4.581367924528302e-06, "epoch": 0.9168632075471698, "percentage": 4.58, "elapsed_time": "0:02:44", "remaining_time": "0:57:07", "throughput": 6148.7, "total_tokens": 1012544} +{"current_steps": 1560, "total_steps": 33920, "loss": 0.4825, "lr": 4.596108490566038e-06, "epoch": 0.9198113207547169, "percentage": 4.6, "elapsed_time": "0:02:45", "remaining_time": "0:57:05", "throughput": 6148.12, "total_tokens": 1015232} +{"current_steps": 1565, "total_steps": 33920, "loss": 0.5498, "lr": 4.610849056603774e-06, "epoch": 0.9227594339622641, "percentage": 4.61, "elapsed_time": "0:02:45", "remaining_time": "0:57:04", "throughput": 6148.17, "total_tokens": 1018496} +{"current_steps": 1570, "total_steps": 33920, "loss": 0.6881, "lr": 4.62558962264151e-06, "epoch": 0.9257075471698113, "percentage": 4.63, "elapsed_time": "0:02:46", "remaining_time": "0:57:05", "throughput": 6150.36, "total_tokens": 1022432} +{"current_steps": 1575, "total_steps": 33920, "loss": 0.6306, "lr": 4.640330188679246e-06, "epoch": 0.9286556603773585, "percentage": 4.64, "elapsed_time": "0:02:46", "remaining_time": "0:57:05", "throughput": 6149.74, "total_tokens": 1025760} +{"current_steps": 1580, "total_steps": 33920, "loss": 0.6061, "lr": 4.655070754716981e-06, "epoch": 0.9316037735849056, "percentage": 4.66, "elapsed_time": "0:02:47", "remaining_time": "0:57:08", "throughput": 6151.32, "total_tokens": 1030400} +{"current_steps": 1585, "total_steps": 33920, "loss": 0.4505, "lr": 4.6698113207547175e-06, "epoch": 0.9345518867924528, "percentage": 4.67, "elapsed_time": "0:02:48", "remaining_time": "0:57:08", "throughput": 6148.26, "total_tokens": 1033152} +{"current_steps": 1590, "total_steps": 33920, "loss": 0.5413, "lr": 4.684551886792454e-06, "epoch": 0.9375, "percentage": 4.69, "elapsed_time": "0:02:48", "remaining_time": "0:57:08", "throughput": 6149.15, "total_tokens": 1036896} +{"current_steps": 1595, "total_steps": 33920, "loss": 0.5893, "lr": 4.699292452830189e-06, "epoch": 0.9404481132075472, "percentage": 4.7, "elapsed_time": "0:02:49", "remaining_time": "0:57:08", "throughput": 6149.35, "total_tokens": 1040224} +{"current_steps": 1600, "total_steps": 33920, "loss": 0.491, "lr": 4.714033018867925e-06, "epoch": 0.9433962264150944, "percentage": 4.72, "elapsed_time": "0:02:49", "remaining_time": "0:57:07", "throughput": 6147.36, "total_tokens": 1042976} +{"current_steps": 1605, "total_steps": 33920, "loss": 0.4469, "lr": 4.728773584905661e-06, "epoch": 0.9463443396226415, "percentage": 4.73, "elapsed_time": "0:02:50", "remaining_time": "0:57:07", "throughput": 6145.19, "total_tokens": 1046112} +{"current_steps": 1610, "total_steps": 33920, "loss": 0.5851, "lr": 4.743514150943397e-06, "epoch": 0.9492924528301887, "percentage": 4.75, "elapsed_time": "0:02:50", "remaining_time": "0:57:07", "throughput": 6143.36, "total_tokens": 1049152} +{"current_steps": 1615, "total_steps": 33920, "loss": 0.4134, "lr": 4.758254716981133e-06, "epoch": 0.9522405660377359, "percentage": 4.76, "elapsed_time": "0:02:51", "remaining_time": "0:57:06", "throughput": 6141.85, "total_tokens": 1051968} +{"current_steps": 1620, "total_steps": 33920, "loss": 0.5304, "lr": 4.772995283018868e-06, "epoch": 0.9551886792452831, "percentage": 4.78, "elapsed_time": "0:02:52", "remaining_time": "0:57:17", "throughput": 6144.64, "total_tokens": 1059424} +{"current_steps": 1625, "total_steps": 33920, "loss": 0.6092, "lr": 4.787735849056604e-06, "epoch": 0.9581367924528302, "percentage": 4.79, "elapsed_time": "0:02:52", "remaining_time": "0:57:16", "throughput": 6143.13, "total_tokens": 1062240} +{"current_steps": 1630, "total_steps": 33920, "loss": 0.5283, "lr": 4.80247641509434e-06, "epoch": 0.9610849056603774, "percentage": 4.81, "elapsed_time": "0:02:53", "remaining_time": "0:57:17", "throughput": 6142.69, "total_tokens": 1065792} +{"current_steps": 1635, "total_steps": 33920, "loss": 0.6121, "lr": 4.817216981132076e-06, "epoch": 0.9640330188679245, "percentage": 4.82, "elapsed_time": "0:02:54", "remaining_time": "0:57:17", "throughput": 6142.27, "total_tokens": 1069280} +{"current_steps": 1640, "total_steps": 33920, "loss": 0.5424, "lr": 4.831957547169811e-06, "epoch": 0.9669811320754716, "percentage": 4.83, "elapsed_time": "0:02:54", "remaining_time": "0:57:16", "throughput": 6139.43, "total_tokens": 1071936} +{"current_steps": 1645, "total_steps": 33920, "loss": 0.6563, "lr": 4.8466981132075476e-06, "epoch": 0.9699292452830188, "percentage": 4.85, "elapsed_time": "0:02:55", "remaining_time": "0:57:15", "throughput": 6138.18, "total_tokens": 1074944} +{"current_steps": 1650, "total_steps": 33920, "loss": 0.5446, "lr": 4.861438679245283e-06, "epoch": 0.972877358490566, "percentage": 4.86, "elapsed_time": "0:02:55", "remaining_time": "0:57:16", "throughput": 6136.94, "total_tokens": 1078368} +{"current_steps": 1655, "total_steps": 33920, "loss": 0.5517, "lr": 4.876179245283019e-06, "epoch": 0.9758254716981132, "percentage": 4.88, "elapsed_time": "0:02:56", "remaining_time": "0:57:16", "throughput": 6134.72, "total_tokens": 1081312} +{"current_steps": 1660, "total_steps": 33920, "loss": 0.8125, "lr": 4.890919811320755e-06, "epoch": 0.9787735849056604, "percentage": 4.89, "elapsed_time": "0:02:57", "remaining_time": "0:57:27", "throughput": 6137.13, "total_tokens": 1088704} +{"current_steps": 1665, "total_steps": 33920, "loss": 0.637, "lr": 4.905660377358491e-06, "epoch": 0.9817216981132075, "percentage": 4.91, "elapsed_time": "0:02:57", "remaining_time": "0:57:27", "throughput": 6137.93, "total_tokens": 1092352} +{"current_steps": 1670, "total_steps": 33920, "loss": 0.6539, "lr": 4.920400943396227e-06, "epoch": 0.9846698113207547, "percentage": 4.92, "elapsed_time": "0:02:58", "remaining_time": "0:57:26", "throughput": 6134.07, "total_tokens": 1094880} +{"current_steps": 1675, "total_steps": 33920, "loss": 0.5469, "lr": 4.935141509433963e-06, "epoch": 0.9876179245283019, "percentage": 4.94, "elapsed_time": "0:02:59", "remaining_time": "0:57:26", "throughput": 6134.23, "total_tokens": 1098176} +{"current_steps": 1680, "total_steps": 33920, "loss": 0.5497, "lr": 4.949882075471698e-06, "epoch": 0.9905660377358491, "percentage": 4.95, "elapsed_time": "0:02:59", "remaining_time": "0:57:26", "throughput": 6132.56, "total_tokens": 1101440} +{"current_steps": 1685, "total_steps": 33920, "loss": 0.7427, "lr": 4.9646226415094346e-06, "epoch": 0.9935141509433962, "percentage": 4.97, "elapsed_time": "0:03:00", "remaining_time": "0:57:27", "throughput": 6130.62, "total_tokens": 1104736} +{"current_steps": 1690, "total_steps": 33920, "loss": 0.4693, "lr": 4.979363207547171e-06, "epoch": 0.9964622641509434, "percentage": 4.98, "elapsed_time": "0:03:00", "remaining_time": "0:57:26", "throughput": 6127.45, "total_tokens": 1107328} +{"current_steps": 1695, "total_steps": 33920, "loss": 0.4854, "lr": 4.994103773584906e-06, "epoch": 0.9994103773584906, "percentage": 5.0, "elapsed_time": "0:03:01", "remaining_time": "0:57:26", "throughput": 6126.02, "total_tokens": 1110528} +{"current_steps": 1700, "total_steps": 33920, "loss": 0.566, "lr": 5.0088443396226414e-06, "epoch": 1.0023584905660377, "percentage": 5.01, "elapsed_time": "0:03:02", "remaining_time": "0:57:34", "throughput": 6108.89, "total_tokens": 1113400} +{"current_steps": 1705, "total_steps": 33920, "loss": 0.5185, "lr": 5.023584905660378e-06, "epoch": 1.005306603773585, "percentage": 5.03, "elapsed_time": "0:03:02", "remaining_time": "0:57:34", "throughput": 6109.49, "total_tokens": 1117144} +{"current_steps": 1710, "total_steps": 33920, "loss": 0.6226, "lr": 5.038325471698113e-06, "epoch": 1.008254716981132, "percentage": 5.04, "elapsed_time": "0:03:03", "remaining_time": "0:57:34", "throughput": 6107.41, "total_tokens": 1120216} +{"current_steps": 1715, "total_steps": 33920, "loss": 0.5095, "lr": 5.05306603773585e-06, "epoch": 1.0112028301886793, "percentage": 5.06, "elapsed_time": "0:03:03", "remaining_time": "0:57:34", "throughput": 6104.58, "total_tokens": 1122904} +{"current_steps": 1720, "total_steps": 33920, "loss": 0.4493, "lr": 5.067806603773585e-06, "epoch": 1.0141509433962264, "percentage": 5.07, "elapsed_time": "0:03:04", "remaining_time": "0:57:34", "throughput": 6105.0, "total_tokens": 1126552} +{"current_steps": 1725, "total_steps": 33920, "loss": 0.4396, "lr": 5.0825471698113216e-06, "epoch": 1.0170990566037736, "percentage": 5.09, "elapsed_time": "0:03:05", "remaining_time": "0:57:36", "throughput": 6102.64, "total_tokens": 1130040} +{"current_steps": 1730, "total_steps": 33920, "loss": 0.5636, "lr": 5.097287735849057e-06, "epoch": 1.0200471698113207, "percentage": 5.1, "elapsed_time": "0:03:05", "remaining_time": "0:57:36", "throughput": 6103.99, "total_tokens": 1133752} +{"current_steps": 1735, "total_steps": 33920, "loss": 0.6907, "lr": 5.112028301886793e-06, "epoch": 1.022995283018868, "percentage": 5.11, "elapsed_time": "0:03:06", "remaining_time": "0:57:35", "throughput": 6097.48, "total_tokens": 1135928} +{"current_steps": 1740, "total_steps": 33920, "loss": 0.566, "lr": 5.1267688679245284e-06, "epoch": 1.025943396226415, "percentage": 5.13, "elapsed_time": "0:03:06", "remaining_time": "0:57:35", "throughput": 6094.95, "total_tokens": 1138712} +{"current_steps": 1745, "total_steps": 33920, "loss": 0.5239, "lr": 5.1415094339622655e-06, "epoch": 1.0288915094339623, "percentage": 5.14, "elapsed_time": "0:03:07", "remaining_time": "0:57:34", "throughput": 6093.56, "total_tokens": 1141752} +{"current_steps": 1750, "total_steps": 33920, "loss": 0.4853, "lr": 5.156250000000001e-06, "epoch": 1.0318396226415094, "percentage": 5.16, "elapsed_time": "0:03:07", "remaining_time": "0:57:34", "throughput": 6092.37, "total_tokens": 1144952} +{"current_steps": 1755, "total_steps": 33920, "loss": 0.534, "lr": 5.170990566037736e-06, "epoch": 1.0347877358490567, "percentage": 5.17, "elapsed_time": "0:03:08", "remaining_time": "0:57:33", "throughput": 6088.46, "total_tokens": 1147416} +{"current_steps": 1760, "total_steps": 33920, "loss": 0.6777, "lr": 5.185731132075472e-06, "epoch": 1.0377358490566038, "percentage": 5.19, "elapsed_time": "0:03:09", "remaining_time": "0:57:34", "throughput": 6088.28, "total_tokens": 1150840} +{"current_steps": 1765, "total_steps": 33920, "loss": 0.5138, "lr": 5.200471698113208e-06, "epoch": 1.040683962264151, "percentage": 5.2, "elapsed_time": "0:03:09", "remaining_time": "0:57:32", "throughput": 6086.4, "total_tokens": 1153592} +{"current_steps": 1770, "total_steps": 33920, "loss": 0.4222, "lr": 5.215212264150944e-06, "epoch": 1.0436320754716981, "percentage": 5.22, "elapsed_time": "0:03:10", "remaining_time": "0:57:33", "throughput": 6084.02, "total_tokens": 1156888} +{"current_steps": 1775, "total_steps": 33920, "loss": 0.5446, "lr": 5.229952830188679e-06, "epoch": 1.0465801886792452, "percentage": 5.23, "elapsed_time": "0:03:10", "remaining_time": "0:57:33", "throughput": 6082.91, "total_tokens": 1159992} +{"current_steps": 1780, "total_steps": 33920, "loss": 0.6806, "lr": 5.2446933962264154e-06, "epoch": 1.0495283018867925, "percentage": 5.25, "elapsed_time": "0:03:11", "remaining_time": "0:57:33", "throughput": 6081.38, "total_tokens": 1163224} +{"current_steps": 1785, "total_steps": 33920, "loss": 0.6864, "lr": 5.259433962264151e-06, "epoch": 1.0524764150943395, "percentage": 5.26, "elapsed_time": "0:03:11", "remaining_time": "0:57:33", "throughput": 6081.89, "total_tokens": 1166744} +{"current_steps": 1790, "total_steps": 33920, "loss": 0.475, "lr": 5.274174528301888e-06, "epoch": 1.0554245283018868, "percentage": 5.28, "elapsed_time": "0:03:12", "remaining_time": "0:57:35", "throughput": 6083.44, "total_tokens": 1171224} +{"current_steps": 1795, "total_steps": 33920, "loss": 0.4934, "lr": 5.288915094339623e-06, "epoch": 1.0583726415094339, "percentage": 5.29, "elapsed_time": "0:03:13", "remaining_time": "0:57:36", "throughput": 6085.08, "total_tokens": 1175096} +{"current_steps": 1800, "total_steps": 33920, "loss": 0.4973, "lr": 5.303655660377359e-06, "epoch": 1.0613207547169812, "percentage": 5.31, "elapsed_time": "0:03:13", "remaining_time": "0:57:35", "throughput": 6084.58, "total_tokens": 1178296} +{"current_steps": 1805, "total_steps": 33920, "loss": 0.5081, "lr": 5.318396226415095e-06, "epoch": 1.0642688679245282, "percentage": 5.32, "elapsed_time": "0:03:14", "remaining_time": "0:57:35", "throughput": 6081.63, "total_tokens": 1181176} +{"current_steps": 1810, "total_steps": 33920, "loss": 0.6466, "lr": 5.333136792452831e-06, "epoch": 1.0672169811320755, "percentage": 5.34, "elapsed_time": "0:03:15", "remaining_time": "0:57:45", "throughput": 6083.56, "total_tokens": 1188376} +{"current_steps": 1815, "total_steps": 33920, "loss": 0.5493, "lr": 5.347877358490566e-06, "epoch": 1.0701650943396226, "percentage": 5.35, "elapsed_time": "0:03:16", "remaining_time": "0:57:47", "throughput": 6082.63, "total_tokens": 1192344} +{"current_steps": 1820, "total_steps": 33920, "loss": 0.6354, "lr": 5.362617924528302e-06, "epoch": 1.0731132075471699, "percentage": 5.37, "elapsed_time": "0:03:16", "remaining_time": "0:57:46", "throughput": 6081.64, "total_tokens": 1195416} +{"current_steps": 1825, "total_steps": 33920, "loss": 0.6096, "lr": 5.377358490566038e-06, "epoch": 1.076061320754717, "percentage": 5.38, "elapsed_time": "0:03:17", "remaining_time": "0:57:46", "throughput": 6082.45, "total_tokens": 1198936} +{"current_steps": 1830, "total_steps": 33920, "loss": 0.7194, "lr": 5.392099056603775e-06, "epoch": 1.0790094339622642, "percentage": 5.4, "elapsed_time": "0:03:17", "remaining_time": "0:57:46", "throughput": 6079.68, "total_tokens": 1201688} +{"current_steps": 1835, "total_steps": 33920, "loss": 0.456, "lr": 5.40683962264151e-06, "epoch": 1.0819575471698113, "percentage": 5.41, "elapsed_time": "0:03:18", "remaining_time": "0:57:45", "throughput": 6078.17, "total_tokens": 1204760} +{"current_steps": 1840, "total_steps": 33920, "loss": 0.5533, "lr": 5.4215801886792455e-06, "epoch": 1.0849056603773586, "percentage": 5.42, "elapsed_time": "0:03:18", "remaining_time": "0:57:45", "throughput": 6075.07, "total_tokens": 1207416} +{"current_steps": 1845, "total_steps": 33920, "loss": 0.8037, "lr": 5.436320754716982e-06, "epoch": 1.0878537735849056, "percentage": 5.44, "elapsed_time": "0:03:19", "remaining_time": "0:57:44", "throughput": 6072.91, "total_tokens": 1210296} +{"current_steps": 1850, "total_steps": 33920, "loss": 0.6276, "lr": 5.451061320754717e-06, "epoch": 1.0908018867924527, "percentage": 5.45, "elapsed_time": "0:03:19", "remaining_time": "0:57:44", "throughput": 6070.53, "total_tokens": 1213304} +{"current_steps": 1855, "total_steps": 33920, "loss": 0.6061, "lr": 5.465801886792453e-06, "epoch": 1.09375, "percentage": 5.47, "elapsed_time": "0:03:20", "remaining_time": "0:57:45", "throughput": 6069.15, "total_tokens": 1216728} +{"current_steps": 1860, "total_steps": 33920, "loss": 0.4811, "lr": 5.4805424528301886e-06, "epoch": 1.0966981132075473, "percentage": 5.48, "elapsed_time": "0:03:21", "remaining_time": "0:57:46", "throughput": 6068.58, "total_tokens": 1220312} +{"current_steps": 1865, "total_steps": 33920, "loss": 0.618, "lr": 5.495283018867925e-06, "epoch": 1.0996462264150944, "percentage": 5.5, "elapsed_time": "0:03:21", "remaining_time": "0:57:46", "throughput": 6068.77, "total_tokens": 1224152} +{"current_steps": 1870, "total_steps": 33920, "loss": 0.5742, "lr": 5.51002358490566e-06, "epoch": 1.1025943396226414, "percentage": 5.51, "elapsed_time": "0:03:22", "remaining_time": "0:57:45", "throughput": 6065.32, "total_tokens": 1226488} +{"current_steps": 1875, "total_steps": 33920, "loss": 0.6429, "lr": 5.524764150943397e-06, "epoch": 1.1055424528301887, "percentage": 5.53, "elapsed_time": "0:03:22", "remaining_time": "0:57:46", "throughput": 6064.62, "total_tokens": 1229912} +{"current_steps": 1880, "total_steps": 33920, "loss": 0.591, "lr": 5.5395047169811325e-06, "epoch": 1.1084905660377358, "percentage": 5.54, "elapsed_time": "0:03:23", "remaining_time": "0:57:45", "throughput": 6065.25, "total_tokens": 1233400} +{"current_steps": 1885, "total_steps": 33920, "loss": 0.4804, "lr": 5.554245283018869e-06, "epoch": 1.111438679245283, "percentage": 5.56, "elapsed_time": "0:03:23", "remaining_time": "0:57:44", "throughput": 6061.84, "total_tokens": 1235832} +{"current_steps": 1890, "total_steps": 33920, "loss": 0.5569, "lr": 5.568985849056604e-06, "epoch": 1.1143867924528301, "percentage": 5.57, "elapsed_time": "0:03:24", "remaining_time": "0:57:44", "throughput": 6059.84, "total_tokens": 1238712} +{"current_steps": 1895, "total_steps": 33920, "loss": 0.523, "lr": 5.58372641509434e-06, "epoch": 1.1173349056603774, "percentage": 5.59, "elapsed_time": "0:03:24", "remaining_time": "0:57:44", "throughput": 6058.78, "total_tokens": 1241912} +{"current_steps": 1900, "total_steps": 33920, "loss": 0.563, "lr": 5.5984669811320755e-06, "epoch": 1.1202830188679245, "percentage": 5.6, "elapsed_time": "0:03:25", "remaining_time": "0:57:43", "throughput": 6057.91, "total_tokens": 1244984} +{"current_steps": 1905, "total_steps": 33920, "loss": 0.552, "lr": 5.613207547169813e-06, "epoch": 1.1232311320754718, "percentage": 5.62, "elapsed_time": "0:03:26", "remaining_time": "0:57:44", "throughput": 6059.38, "total_tokens": 1249080} +{"current_steps": 1910, "total_steps": 33920, "loss": 0.568, "lr": 5.627948113207548e-06, "epoch": 1.1261792452830188, "percentage": 5.63, "elapsed_time": "0:03:26", "remaining_time": "0:57:43", "throughput": 6058.98, "total_tokens": 1252184} +{"current_steps": 1915, "total_steps": 33920, "loss": 0.5306, "lr": 5.642688679245284e-06, "epoch": 1.1291273584905661, "percentage": 5.65, "elapsed_time": "0:03:27", "remaining_time": "0:57:43", "throughput": 6059.78, "total_tokens": 1255832} +{"current_steps": 1920, "total_steps": 33920, "loss": 0.4954, "lr": 5.6574292452830195e-06, "epoch": 1.1320754716981132, "percentage": 5.66, "elapsed_time": "0:03:27", "remaining_time": "0:57:44", "throughput": 6061.79, "total_tokens": 1260216} +{"current_steps": 1925, "total_steps": 33920, "loss": 0.4754, "lr": 5.672169811320756e-06, "epoch": 1.1350235849056605, "percentage": 5.68, "elapsed_time": "0:03:28", "remaining_time": "0:57:45", "throughput": 6062.45, "total_tokens": 1263928} +{"current_steps": 1930, "total_steps": 33920, "loss": 0.4583, "lr": 5.686910377358491e-06, "epoch": 1.1379716981132075, "percentage": 5.69, "elapsed_time": "0:03:29", "remaining_time": "0:57:45", "throughput": 6063.42, "total_tokens": 1267800} +{"current_steps": 1935, "total_steps": 33920, "loss": 0.4293, "lr": 5.701650943396226e-06, "epoch": 1.1409198113207548, "percentage": 5.7, "elapsed_time": "0:03:29", "remaining_time": "0:57:44", "throughput": 6062.25, "total_tokens": 1270712} +{"current_steps": 1940, "total_steps": 33920, "loss": 0.5493, "lr": 5.7163915094339625e-06, "epoch": 1.1438679245283019, "percentage": 5.72, "elapsed_time": "0:03:30", "remaining_time": "0:57:45", "throughput": 6060.53, "total_tokens": 1274008} +{"current_steps": 1945, "total_steps": 33920, "loss": 0.548, "lr": 5.731132075471698e-06, "epoch": 1.146816037735849, "percentage": 5.73, "elapsed_time": "0:03:30", "remaining_time": "0:57:44", "throughput": 6055.76, "total_tokens": 1276152} +{"current_steps": 1950, "total_steps": 33920, "loss": 0.5027, "lr": 5.745872641509435e-06, "epoch": 1.1497641509433962, "percentage": 5.75, "elapsed_time": "0:03:31", "remaining_time": "0:57:43", "throughput": 6054.59, "total_tokens": 1279064} +{"current_steps": 1955, "total_steps": 33920, "loss": 0.5612, "lr": 5.76061320754717e-06, "epoch": 1.1527122641509433, "percentage": 5.76, "elapsed_time": "0:03:31", "remaining_time": "0:57:43", "throughput": 6053.82, "total_tokens": 1282264} +{"current_steps": 1960, "total_steps": 33920, "loss": 0.5651, "lr": 5.7753537735849065e-06, "epoch": 1.1556603773584906, "percentage": 5.78, "elapsed_time": "0:03:32", "remaining_time": "0:57:43", "throughput": 6053.63, "total_tokens": 1285816} +{"current_steps": 1965, "total_steps": 33920, "loss": 0.4506, "lr": 5.790094339622642e-06, "epoch": 1.1586084905660377, "percentage": 5.79, "elapsed_time": "0:03:32", "remaining_time": "0:57:42", "throughput": 6050.72, "total_tokens": 1288280} +{"current_steps": 1970, "total_steps": 33920, "loss": 0.6233, "lr": 5.804834905660378e-06, "epoch": 1.161556603773585, "percentage": 5.81, "elapsed_time": "0:03:33", "remaining_time": "0:57:41", "throughput": 6050.03, "total_tokens": 1291256} +{"current_steps": 1975, "total_steps": 33920, "loss": 0.4851, "lr": 5.819575471698113e-06, "epoch": 1.164504716981132, "percentage": 5.82, "elapsed_time": "0:03:33", "remaining_time": "0:57:41", "throughput": 6047.62, "total_tokens": 1294072} +{"current_steps": 1980, "total_steps": 33920, "loss": 0.8181, "lr": 5.8343160377358495e-06, "epoch": 1.1674528301886793, "percentage": 5.84, "elapsed_time": "0:03:34", "remaining_time": "0:57:42", "throughput": 6049.07, "total_tokens": 1298488} +{"current_steps": 1985, "total_steps": 33920, "loss": 0.4212, "lr": 5.849056603773585e-06, "epoch": 1.1704009433962264, "percentage": 5.85, "elapsed_time": "0:03:35", "remaining_time": "0:57:42", "throughput": 6048.66, "total_tokens": 1301912} +{"current_steps": 1990, "total_steps": 33920, "loss": 0.4772, "lr": 5.863797169811322e-06, "epoch": 1.1733490566037736, "percentage": 5.87, "elapsed_time": "0:03:35", "remaining_time": "0:57:41", "throughput": 6045.32, "total_tokens": 1304312} +{"current_steps": 1995, "total_steps": 33920, "loss": 0.553, "lr": 5.878537735849057e-06, "epoch": 1.1762971698113207, "percentage": 5.88, "elapsed_time": "0:03:36", "remaining_time": "0:57:41", "throughput": 6045.83, "total_tokens": 1307736} +{"current_steps": 2000, "total_steps": 33920, "loss": 0.5978, "lr": 5.8932783018867934e-06, "epoch": 1.179245283018868, "percentage": 5.9, "elapsed_time": "0:03:36", "remaining_time": "0:57:41", "throughput": 6044.73, "total_tokens": 1310904} +{"current_steps": 2005, "total_steps": 33920, "loss": 0.457, "lr": 5.908018867924529e-06, "epoch": 1.182193396226415, "percentage": 5.91, "elapsed_time": "0:03:37", "remaining_time": "0:57:40", "throughput": 6041.28, "total_tokens": 1313208} +{"current_steps": 2010, "total_steps": 33920, "loss": 0.5635, "lr": 5.922759433962265e-06, "epoch": 1.1851415094339623, "percentage": 5.93, "elapsed_time": "0:03:37", "remaining_time": "0:57:40", "throughput": 6041.4, "total_tokens": 1316888} +{"current_steps": 2015, "total_steps": 33920, "loss": 0.4905, "lr": 5.9375e-06, "epoch": 1.1880896226415094, "percentage": 5.94, "elapsed_time": "0:03:38", "remaining_time": "0:57:40", "throughput": 6040.47, "total_tokens": 1320120} +{"current_steps": 2020, "total_steps": 33920, "loss": 0.4259, "lr": 5.952240566037736e-06, "epoch": 1.1910377358490567, "percentage": 5.96, "elapsed_time": "0:03:39", "remaining_time": "0:57:46", "throughput": 6041.23, "total_tokens": 1326168} +{"current_steps": 2025, "total_steps": 33920, "loss": 0.5077, "lr": 5.966981132075472e-06, "epoch": 1.1939858490566038, "percentage": 5.97, "elapsed_time": "0:03:40", "remaining_time": "0:57:46", "throughput": 6039.74, "total_tokens": 1329144} +{"current_steps": 2030, "total_steps": 33920, "loss": 0.4891, "lr": 5.981721698113207e-06, "epoch": 1.196933962264151, "percentage": 5.98, "elapsed_time": "0:03:40", "remaining_time": "0:57:45", "throughput": 6037.27, "total_tokens": 1331896} +{"current_steps": 2035, "total_steps": 33920, "loss": 0.6328, "lr": 5.996462264150944e-06, "epoch": 1.1998820754716981, "percentage": 6.0, "elapsed_time": "0:03:41", "remaining_time": "0:57:45", "throughput": 6035.76, "total_tokens": 1335160} +{"current_steps": 2040, "total_steps": 33920, "loss": 0.594, "lr": 6.01120283018868e-06, "epoch": 1.2028301886792452, "percentage": 6.01, "elapsed_time": "0:03:41", "remaining_time": "0:57:45", "throughput": 6033.54, "total_tokens": 1337848} +{"current_steps": 2045, "total_steps": 33920, "loss": 0.5915, "lr": 6.025943396226416e-06, "epoch": 1.2057783018867925, "percentage": 6.03, "elapsed_time": "0:03:42", "remaining_time": "0:57:46", "throughput": 6032.57, "total_tokens": 1341464} +{"current_steps": 2050, "total_steps": 33920, "loss": 0.6467, "lr": 6.040683962264151e-06, "epoch": 1.2087264150943395, "percentage": 6.04, "elapsed_time": "0:03:42", "remaining_time": "0:57:45", "throughput": 6031.39, "total_tokens": 1344440} +{"current_steps": 2055, "total_steps": 33920, "loss": 0.6749, "lr": 6.055424528301887e-06, "epoch": 1.2116745283018868, "percentage": 6.06, "elapsed_time": "0:03:43", "remaining_time": "0:57:44", "throughput": 6028.82, "total_tokens": 1347064} +{"current_steps": 2060, "total_steps": 33920, "loss": 0.5188, "lr": 6.070165094339623e-06, "epoch": 1.2146226415094339, "percentage": 6.07, "elapsed_time": "0:03:43", "remaining_time": "0:57:43", "throughput": 6025.78, "total_tokens": 1349528} +{"current_steps": 2065, "total_steps": 33920, "loss": 0.5857, "lr": 6.08490566037736e-06, "epoch": 1.2175707547169812, "percentage": 6.09, "elapsed_time": "0:03:44", "remaining_time": "0:57:43", "throughput": 6024.22, "total_tokens": 1352760} +{"current_steps": 2070, "total_steps": 33920, "loss": 0.5042, "lr": 6.099646226415095e-06, "epoch": 1.2205188679245282, "percentage": 6.1, "elapsed_time": "0:03:45", "remaining_time": "0:57:43", "throughput": 6022.42, "total_tokens": 1355512} +{"current_steps": 2075, "total_steps": 33920, "loss": 0.5658, "lr": 6.114386792452831e-06, "epoch": 1.2234669811320755, "percentage": 6.12, "elapsed_time": "0:03:45", "remaining_time": "0:57:42", "throughput": 6020.61, "total_tokens": 1358328} +{"current_steps": 2080, "total_steps": 33920, "loss": 0.5727, "lr": 6.129127358490567e-06, "epoch": 1.2264150943396226, "percentage": 6.13, "elapsed_time": "0:03:46", "remaining_time": "0:57:41", "throughput": 6021.31, "total_tokens": 1361784} +{"current_steps": 2085, "total_steps": 33920, "loss": 0.5784, "lr": 6.143867924528303e-06, "epoch": 1.2293632075471699, "percentage": 6.15, "elapsed_time": "0:03:46", "remaining_time": "0:57:41", "throughput": 6019.42, "total_tokens": 1364568} +{"current_steps": 2090, "total_steps": 33920, "loss": 0.4572, "lr": 6.158608490566038e-06, "epoch": 1.232311320754717, "percentage": 6.16, "elapsed_time": "0:03:47", "remaining_time": "0:57:40", "throughput": 6018.03, "total_tokens": 1367384} +{"current_steps": 2095, "total_steps": 33920, "loss": 0.5664, "lr": 6.173349056603774e-06, "epoch": 1.2352594339622642, "percentage": 6.18, "elapsed_time": "0:03:47", "remaining_time": "0:57:40", "throughput": 6018.52, "total_tokens": 1370936} +{"current_steps": 2100, "total_steps": 33920, "loss": 0.5463, "lr": 6.18808962264151e-06, "epoch": 1.2382075471698113, "percentage": 6.19, "elapsed_time": "0:03:48", "remaining_time": "0:57:40", "throughput": 6017.99, "total_tokens": 1374392} +{"current_steps": 2105, "total_steps": 33920, "loss": 0.6779, "lr": 6.202830188679245e-06, "epoch": 1.2411556603773586, "percentage": 6.21, "elapsed_time": "0:03:48", "remaining_time": "0:57:39", "throughput": 6017.9, "total_tokens": 1377656} +{"current_steps": 2110, "total_steps": 33920, "loss": 0.4946, "lr": 6.217570754716982e-06, "epoch": 1.2441037735849056, "percentage": 6.22, "elapsed_time": "0:03:49", "remaining_time": "0:57:39", "throughput": 6016.9, "total_tokens": 1380792} +{"current_steps": 2115, "total_steps": 33920, "loss": 0.3988, "lr": 6.232311320754717e-06, "epoch": 1.2470518867924527, "percentage": 6.24, "elapsed_time": "0:03:50", "remaining_time": "0:57:39", "throughput": 6016.42, "total_tokens": 1384184} +{"current_steps": 2120, "total_steps": 33920, "loss": 0.5362, "lr": 6.2470518867924536e-06, "epoch": 1.25, "percentage": 6.25, "elapsed_time": "0:03:50", "remaining_time": "0:57:41", "throughput": 6018.81, "total_tokens": 1388824} +{"current_steps": 2125, "total_steps": 33920, "loss": 0.6328, "lr": 6.261792452830189e-06, "epoch": 1.2529481132075473, "percentage": 6.26, "elapsed_time": "0:03:51", "remaining_time": "0:57:41", "throughput": 6020.65, "total_tokens": 1392728} +{"current_steps": 2130, "total_steps": 33920, "loss": 0.4704, "lr": 6.276533018867925e-06, "epoch": 1.2558962264150944, "percentage": 6.28, "elapsed_time": "0:03:52", "remaining_time": "0:57:42", "throughput": 6021.48, "total_tokens": 1397016} +{"current_steps": 2135, "total_steps": 33920, "loss": 0.5167, "lr": 6.2912735849056604e-06, "epoch": 1.2588443396226414, "percentage": 6.29, "elapsed_time": "0:03:52", "remaining_time": "0:57:43", "throughput": 6021.18, "total_tokens": 1400824} +{"current_steps": 2140, "total_steps": 33920, "loss": 0.516, "lr": 6.306014150943397e-06, "epoch": 1.2617924528301887, "percentage": 6.31, "elapsed_time": "0:03:53", "remaining_time": "0:57:43", "throughput": 6022.95, "total_tokens": 1404856} +{"current_steps": 2145, "total_steps": 33920, "loss": 0.6553, "lr": 6.320754716981132e-06, "epoch": 1.2647405660377358, "percentage": 6.32, "elapsed_time": "0:03:53", "remaining_time": "0:57:43", "throughput": 6022.1, "total_tokens": 1407864} +{"current_steps": 2150, "total_steps": 33920, "loss": 0.4342, "lr": 6.335495283018869e-06, "epoch": 1.267688679245283, "percentage": 6.34, "elapsed_time": "0:03:54", "remaining_time": "0:57:42", "throughput": 6022.05, "total_tokens": 1411192} +{"current_steps": 2155, "total_steps": 33920, "loss": 0.505, "lr": 6.350235849056604e-06, "epoch": 1.2706367924528301, "percentage": 6.35, "elapsed_time": "0:03:54", "remaining_time": "0:57:41", "throughput": 6021.5, "total_tokens": 1414136} +{"current_steps": 2160, "total_steps": 33920, "loss": 0.5352, "lr": 6.3649764150943406e-06, "epoch": 1.2735849056603774, "percentage": 6.37, "elapsed_time": "0:03:55", "remaining_time": "0:57:41", "throughput": 6020.27, "total_tokens": 1417112} +{"current_steps": 2165, "total_steps": 33920, "loss": 0.5976, "lr": 6.379716981132076e-06, "epoch": 1.2765330188679245, "percentage": 6.38, "elapsed_time": "0:03:55", "remaining_time": "0:57:40", "throughput": 6019.32, "total_tokens": 1419960} +{"current_steps": 2170, "total_steps": 33920, "loss": 0.5058, "lr": 6.394457547169812e-06, "epoch": 1.2794811320754718, "percentage": 6.4, "elapsed_time": "0:03:56", "remaining_time": "0:57:39", "throughput": 6018.32, "total_tokens": 1422968} +{"current_steps": 2175, "total_steps": 33920, "loss": 0.6564, "lr": 6.4091981132075474e-06, "epoch": 1.2824292452830188, "percentage": 6.41, "elapsed_time": "0:03:56", "remaining_time": "0:57:38", "throughput": 6017.93, "total_tokens": 1426072} +{"current_steps": 2180, "total_steps": 33920, "loss": 0.4747, "lr": 6.423938679245284e-06, "epoch": 1.2853773584905661, "percentage": 6.43, "elapsed_time": "0:03:57", "remaining_time": "0:57:37", "throughput": 6016.51, "total_tokens": 1428824} +{"current_steps": 2185, "total_steps": 33920, "loss": 0.5505, "lr": 6.438679245283019e-06, "epoch": 1.2883254716981132, "percentage": 6.44, "elapsed_time": "0:03:58", "remaining_time": "0:57:37", "throughput": 6012.86, "total_tokens": 1431192} +{"current_steps": 2190, "total_steps": 33920, "loss": 0.4477, "lr": 6.453419811320756e-06, "epoch": 1.2912735849056602, "percentage": 6.46, "elapsed_time": "0:03:58", "remaining_time": "0:57:37", "throughput": 6011.79, "total_tokens": 1434456} +{"current_steps": 2195, "total_steps": 33920, "loss": 0.521, "lr": 6.468160377358491e-06, "epoch": 1.2942216981132075, "percentage": 6.47, "elapsed_time": "0:03:59", "remaining_time": "0:57:37", "throughput": 6012.81, "total_tokens": 1438488} +{"current_steps": 2200, "total_steps": 33920, "loss": 0.5384, "lr": 6.482900943396227e-06, "epoch": 1.2971698113207548, "percentage": 6.49, "elapsed_time": "0:03:59", "remaining_time": "0:57:37", "throughput": 6011.38, "total_tokens": 1441592} +{"current_steps": 2205, "total_steps": 33920, "loss": 0.4994, "lr": 6.497641509433963e-06, "epoch": 1.3001179245283019, "percentage": 6.5, "elapsed_time": "0:04:00", "remaining_time": "0:57:39", "throughput": 6010.2, "total_tokens": 1445496} +{"current_steps": 2210, "total_steps": 33920, "loss": 0.6806, "lr": 6.512382075471698e-06, "epoch": 1.303066037735849, "percentage": 6.52, "elapsed_time": "0:04:01", "remaining_time": "0:57:38", "throughput": 6008.15, "total_tokens": 1448088} +{"current_steps": 2215, "total_steps": 33920, "loss": 0.5251, "lr": 6.5271226415094344e-06, "epoch": 1.3060141509433962, "percentage": 6.53, "elapsed_time": "0:04:01", "remaining_time": "0:57:37", "throughput": 6008.31, "total_tokens": 1451352} +{"current_steps": 2220, "total_steps": 33920, "loss": 0.4453, "lr": 6.54186320754717e-06, "epoch": 1.3089622641509435, "percentage": 6.54, "elapsed_time": "0:04:02", "remaining_time": "0:57:37", "throughput": 6007.69, "total_tokens": 1454648} +{"current_steps": 2225, "total_steps": 33920, "loss": 0.4649, "lr": 6.556603773584907e-06, "epoch": 1.3119103773584906, "percentage": 6.56, "elapsed_time": "0:04:02", "remaining_time": "0:57:37", "throughput": 6005.03, "total_tokens": 1457400} +{"current_steps": 2230, "total_steps": 33920, "loss": 0.5183, "lr": 6.571344339622641e-06, "epoch": 1.3148584905660377, "percentage": 6.57, "elapsed_time": "0:04:03", "remaining_time": "0:57:37", "throughput": 6005.58, "total_tokens": 1461016} +{"current_steps": 2235, "total_steps": 33920, "loss": 0.5803, "lr": 6.586084905660378e-06, "epoch": 1.317806603773585, "percentage": 6.59, "elapsed_time": "0:04:03", "remaining_time": "0:57:36", "throughput": 6004.14, "total_tokens": 1463736} +{"current_steps": 2240, "total_steps": 33920, "loss": 0.6249, "lr": 6.600825471698114e-06, "epoch": 1.320754716981132, "percentage": 6.6, "elapsed_time": "0:04:04", "remaining_time": "0:57:35", "throughput": 6003.23, "total_tokens": 1466552} +{"current_steps": 2245, "total_steps": 33920, "loss": 0.4646, "lr": 6.61556603773585e-06, "epoch": 1.3237028301886793, "percentage": 6.62, "elapsed_time": "0:04:04", "remaining_time": "0:57:34", "throughput": 6003.36, "total_tokens": 1469944} +{"current_steps": 2250, "total_steps": 33920, "loss": 0.4562, "lr": 6.630306603773585e-06, "epoch": 1.3266509433962264, "percentage": 6.63, "elapsed_time": "0:04:05", "remaining_time": "0:57:35", "throughput": 6002.73, "total_tokens": 1473816} +{"current_steps": 2255, "total_steps": 33920, "loss": 0.3847, "lr": 6.645047169811321e-06, "epoch": 1.3295990566037736, "percentage": 6.65, "elapsed_time": "0:04:06", "remaining_time": "0:57:35", "throughput": 6002.95, "total_tokens": 1477016} +{"current_steps": 2260, "total_steps": 33920, "loss": 0.5613, "lr": 6.659787735849057e-06, "epoch": 1.3325471698113207, "percentage": 6.66, "elapsed_time": "0:04:06", "remaining_time": "0:57:33", "throughput": 6001.8, "total_tokens": 1479768} +{"current_steps": 2265, "total_steps": 33920, "loss": 0.4635, "lr": 6.674528301886794e-06, "epoch": 1.335495283018868, "percentage": 6.68, "elapsed_time": "0:04:07", "remaining_time": "0:57:33", "throughput": 6001.59, "total_tokens": 1482904} +{"current_steps": 2270, "total_steps": 33920, "loss": 0.4605, "lr": 6.689268867924529e-06, "epoch": 1.338443396226415, "percentage": 6.69, "elapsed_time": "0:04:07", "remaining_time": "0:57:32", "throughput": 6000.23, "total_tokens": 1485752} +{"current_steps": 2275, "total_steps": 33920, "loss": 0.4532, "lr": 6.704009433962265e-06, "epoch": 1.3413915094339623, "percentage": 6.71, "elapsed_time": "0:04:08", "remaining_time": "0:57:32", "throughput": 6000.68, "total_tokens": 1489400} +{"current_steps": 2280, "total_steps": 33920, "loss": 0.4467, "lr": 6.718750000000001e-06, "epoch": 1.3443396226415094, "percentage": 6.72, "elapsed_time": "0:04:08", "remaining_time": "0:57:31", "throughput": 6000.39, "total_tokens": 1492472} +{"current_steps": 2285, "total_steps": 33920, "loss": 0.5131, "lr": 6.733490566037736e-06, "epoch": 1.3472877358490565, "percentage": 6.74, "elapsed_time": "0:04:09", "remaining_time": "0:57:30", "throughput": 5997.84, "total_tokens": 1494872} +{"current_steps": 2290, "total_steps": 33920, "loss": 0.4297, "lr": 6.748231132075472e-06, "epoch": 1.3502358490566038, "percentage": 6.75, "elapsed_time": "0:04:09", "remaining_time": "0:57:30", "throughput": 5998.5, "total_tokens": 1498712} +{"current_steps": 2295, "total_steps": 33920, "loss": 0.4812, "lr": 6.7629716981132076e-06, "epoch": 1.353183962264151, "percentage": 6.77, "elapsed_time": "0:04:10", "remaining_time": "0:57:30", "throughput": 5997.24, "total_tokens": 1501688} +{"current_steps": 2300, "total_steps": 33920, "loss": 0.6799, "lr": 6.777712264150944e-06, "epoch": 1.3561320754716981, "percentage": 6.78, "elapsed_time": "0:04:10", "remaining_time": "0:57:30", "throughput": 5996.95, "total_tokens": 1505208} +{"current_steps": 2305, "total_steps": 33920, "loss": 0.476, "lr": 6.792452830188679e-06, "epoch": 1.3590801886792452, "percentage": 6.8, "elapsed_time": "0:04:11", "remaining_time": "0:57:29", "throughput": 5995.34, "total_tokens": 1508024} +{"current_steps": 2310, "total_steps": 33920, "loss": 0.5381, "lr": 6.807193396226416e-06, "epoch": 1.3620283018867925, "percentage": 6.81, "elapsed_time": "0:04:12", "remaining_time": "0:57:28", "throughput": 5993.44, "total_tokens": 1510616} +{"current_steps": 2315, "total_steps": 33920, "loss": 0.5126, "lr": 6.8219339622641515e-06, "epoch": 1.3649764150943398, "percentage": 6.82, "elapsed_time": "0:04:12", "remaining_time": "0:57:28", "throughput": 5993.38, "total_tokens": 1514104} +{"current_steps": 2320, "total_steps": 33920, "loss": 0.6415, "lr": 6.836674528301888e-06, "epoch": 1.3679245283018868, "percentage": 6.84, "elapsed_time": "0:04:13", "remaining_time": "0:57:28", "throughput": 5992.56, "total_tokens": 1517240} +{"current_steps": 2325, "total_steps": 33920, "loss": 0.4983, "lr": 6.851415094339623e-06, "epoch": 1.3708726415094339, "percentage": 6.85, "elapsed_time": "0:04:13", "remaining_time": "0:57:29", "throughput": 5993.96, "total_tokens": 1521464} +{"current_steps": 2330, "total_steps": 33920, "loss": 0.6036, "lr": 6.866155660377359e-06, "epoch": 1.3738207547169812, "percentage": 6.87, "elapsed_time": "0:04:14", "remaining_time": "0:57:28", "throughput": 5993.27, "total_tokens": 1524536} +{"current_steps": 2335, "total_steps": 33920, "loss": 0.5816, "lr": 6.8808962264150946e-06, "epoch": 1.3767688679245282, "percentage": 6.88, "elapsed_time": "0:04:14", "remaining_time": "0:57:28", "throughput": 5992.28, "total_tokens": 1527608} +{"current_steps": 2340, "total_steps": 33920, "loss": 0.4409, "lr": 6.895636792452831e-06, "epoch": 1.3797169811320755, "percentage": 6.9, "elapsed_time": "0:04:15", "remaining_time": "0:57:28", "throughput": 5990.52, "total_tokens": 1530616} +{"current_steps": 2345, "total_steps": 33920, "loss": 0.5375, "lr": 6.910377358490566e-06, "epoch": 1.3826650943396226, "percentage": 6.91, "elapsed_time": "0:04:16", "remaining_time": "0:57:30", "throughput": 5991.31, "total_tokens": 1535512} +{"current_steps": 2350, "total_steps": 33920, "loss": 0.5482, "lr": 6.925117924528303e-06, "epoch": 1.3856132075471699, "percentage": 6.93, "elapsed_time": "0:04:16", "remaining_time": "0:57:30", "throughput": 5990.38, "total_tokens": 1538456} +{"current_steps": 2355, "total_steps": 33920, "loss": 0.4289, "lr": 6.9398584905660385e-06, "epoch": 1.388561320754717, "percentage": 6.94, "elapsed_time": "0:04:17", "remaining_time": "0:57:29", "throughput": 5990.31, "total_tokens": 1541880} +{"current_steps": 2360, "total_steps": 33920, "loss": 0.5307, "lr": 6.954599056603775e-06, "epoch": 1.3915094339622642, "percentage": 6.96, "elapsed_time": "0:04:17", "remaining_time": "0:57:29", "throughput": 5988.5, "total_tokens": 1544664} +{"current_steps": 2365, "total_steps": 33920, "loss": 0.5082, "lr": 6.96933962264151e-06, "epoch": 1.3944575471698113, "percentage": 6.97, "elapsed_time": "0:04:18", "remaining_time": "0:57:29", "throughput": 5988.48, "total_tokens": 1548120} +{"current_steps": 2370, "total_steps": 33920, "loss": 0.5114, "lr": 6.984080188679245e-06, "epoch": 1.3974056603773586, "percentage": 6.99, "elapsed_time": "0:04:19", "remaining_time": "0:57:28", "throughput": 5987.58, "total_tokens": 1551096} +{"current_steps": 2375, "total_steps": 33920, "loss": 0.539, "lr": 6.9988207547169815e-06, "epoch": 1.4003537735849056, "percentage": 7.0, "elapsed_time": "0:04:19", "remaining_time": "0:57:27", "throughput": 5988.04, "total_tokens": 1554360} +{"current_steps": 2380, "total_steps": 33920, "loss": 0.6404, "lr": 7.013561320754717e-06, "epoch": 1.4033018867924527, "percentage": 7.02, "elapsed_time": "0:04:20", "remaining_time": "0:57:27", "throughput": 5986.43, "total_tokens": 1557240} +{"current_steps": 2385, "total_steps": 33920, "loss": 0.5188, "lr": 7.028301886792454e-06, "epoch": 1.40625, "percentage": 7.03, "elapsed_time": "0:04:20", "remaining_time": "0:57:27", "throughput": 5986.84, "total_tokens": 1560920} +{"current_steps": 2390, "total_steps": 33920, "loss": 0.5962, "lr": 7.043042452830188e-06, "epoch": 1.4091981132075473, "percentage": 7.05, "elapsed_time": "0:04:21", "remaining_time": "0:57:26", "throughput": 5984.41, "total_tokens": 1563288} +{"current_steps": 2395, "total_steps": 33920, "loss": 0.6344, "lr": 7.0577830188679255e-06, "epoch": 1.4121462264150944, "percentage": 7.06, "elapsed_time": "0:04:21", "remaining_time": "0:57:25", "throughput": 5983.27, "total_tokens": 1566296} +{"current_steps": 2400, "total_steps": 33920, "loss": 0.7386, "lr": 7.072523584905661e-06, "epoch": 1.4150943396226414, "percentage": 7.08, "elapsed_time": "0:04:22", "remaining_time": "0:57:25", "throughput": 5983.2, "total_tokens": 1569752} +{"current_steps": 2405, "total_steps": 33920, "loss": 0.6608, "lr": 7.087264150943397e-06, "epoch": 1.4180424528301887, "percentage": 7.09, "elapsed_time": "0:04:22", "remaining_time": "0:57:25", "throughput": 5981.31, "total_tokens": 1572536} +{"current_steps": 2410, "total_steps": 33920, "loss": 0.4359, "lr": 7.102004716981132e-06, "epoch": 1.4209905660377358, "percentage": 7.1, "elapsed_time": "0:04:23", "remaining_time": "0:57:25", "throughput": 5979.36, "total_tokens": 1575704} +{"current_steps": 2415, "total_steps": 33920, "loss": 0.4586, "lr": 7.1167452830188685e-06, "epoch": 1.423938679245283, "percentage": 7.12, "elapsed_time": "0:04:24", "remaining_time": "0:57:24", "throughput": 5978.56, "total_tokens": 1578680} +{"current_steps": 2420, "total_steps": 33920, "loss": 0.4817, "lr": 7.131485849056604e-06, "epoch": 1.4268867924528301, "percentage": 7.13, "elapsed_time": "0:04:24", "remaining_time": "0:57:23", "throughput": 5978.23, "total_tokens": 1581752} +{"current_steps": 2425, "total_steps": 33920, "loss": 0.5478, "lr": 7.146226415094341e-06, "epoch": 1.4298349056603774, "percentage": 7.15, "elapsed_time": "0:04:25", "remaining_time": "0:57:23", "throughput": 5977.61, "total_tokens": 1585016} +{"current_steps": 2430, "total_steps": 33920, "loss": 0.4824, "lr": 7.160966981132076e-06, "epoch": 1.4327830188679245, "percentage": 7.16, "elapsed_time": "0:04:25", "remaining_time": "0:57:23", "throughput": 5977.59, "total_tokens": 1588440} +{"current_steps": 2435, "total_steps": 33920, "loss": 0.4705, "lr": 7.1757075471698125e-06, "epoch": 1.4357311320754718, "percentage": 7.18, "elapsed_time": "0:04:26", "remaining_time": "0:57:22", "throughput": 5975.91, "total_tokens": 1591160} +{"current_steps": 2440, "total_steps": 33920, "loss": 0.5324, "lr": 7.190448113207548e-06, "epoch": 1.4386792452830188, "percentage": 7.19, "elapsed_time": "0:04:26", "remaining_time": "0:57:23", "throughput": 5975.3, "total_tokens": 1594712} +{"current_steps": 2445, "total_steps": 33920, "loss": 0.6095, "lr": 7.205188679245284e-06, "epoch": 1.4416273584905661, "percentage": 7.21, "elapsed_time": "0:04:27", "remaining_time": "0:57:22", "throughput": 5976.25, "total_tokens": 1598168} +{"current_steps": 2450, "total_steps": 33920, "loss": 0.5994, "lr": 7.219929245283019e-06, "epoch": 1.4445754716981132, "percentage": 7.22, "elapsed_time": "0:04:28", "remaining_time": "0:57:22", "throughput": 5976.1, "total_tokens": 1601752} +{"current_steps": 2455, "total_steps": 33920, "loss": 0.4669, "lr": 7.2346698113207555e-06, "epoch": 1.4475235849056602, "percentage": 7.24, "elapsed_time": "0:04:28", "remaining_time": "0:57:21", "throughput": 5973.92, "total_tokens": 1604248} +{"current_steps": 2460, "total_steps": 33920, "loss": 0.6597, "lr": 7.249410377358491e-06, "epoch": 1.4504716981132075, "percentage": 7.25, "elapsed_time": "0:04:29", "remaining_time": "0:57:20", "throughput": 5973.79, "total_tokens": 1607352} +{"current_steps": 2465, "total_steps": 33920, "loss": 0.5316, "lr": 7.264150943396226e-06, "epoch": 1.4534198113207548, "percentage": 7.27, "elapsed_time": "0:04:29", "remaining_time": "0:57:20", "throughput": 5972.94, "total_tokens": 1610264} +{"current_steps": 2470, "total_steps": 33920, "loss": 0.663, "lr": 7.278891509433963e-06, "epoch": 1.4563679245283019, "percentage": 7.28, "elapsed_time": "0:04:30", "remaining_time": "0:57:19", "throughput": 5972.08, "total_tokens": 1613144} +{"current_steps": 2475, "total_steps": 33920, "loss": 0.4705, "lr": 7.293632075471699e-06, "epoch": 1.459316037735849, "percentage": 7.3, "elapsed_time": "0:04:31", "remaining_time": "0:57:23", "throughput": 5975.09, "total_tokens": 1619448} +{"current_steps": 2480, "total_steps": 33920, "loss": 0.509, "lr": 7.308372641509435e-06, "epoch": 1.4622641509433962, "percentage": 7.31, "elapsed_time": "0:04:31", "remaining_time": "0:57:22", "throughput": 5974.79, "total_tokens": 1622520} +{"current_steps": 2485, "total_steps": 33920, "loss": 0.6943, "lr": 7.32311320754717e-06, "epoch": 1.4652122641509435, "percentage": 7.33, "elapsed_time": "0:04:32", "remaining_time": "0:57:22", "throughput": 5974.3, "total_tokens": 1625592} +{"current_steps": 2490, "total_steps": 33920, "loss": 0.5361, "lr": 7.337853773584906e-06, "epoch": 1.4681603773584906, "percentage": 7.34, "elapsed_time": "0:04:32", "remaining_time": "0:57:21", "throughput": 5973.54, "total_tokens": 1628760} +{"current_steps": 2495, "total_steps": 33920, "loss": 0.5753, "lr": 7.352594339622642e-06, "epoch": 1.4711084905660377, "percentage": 7.36, "elapsed_time": "0:04:33", "remaining_time": "0:57:20", "throughput": 5972.65, "total_tokens": 1631576} +{"current_steps": 2500, "total_steps": 33920, "loss": 0.5677, "lr": 7.367334905660378e-06, "epoch": 1.474056603773585, "percentage": 7.37, "elapsed_time": "0:04:33", "remaining_time": "0:57:19", "throughput": 5972.3, "total_tokens": 1634584} +{"current_steps": 2505, "total_steps": 33920, "loss": 0.5057, "lr": 7.382075471698113e-06, "epoch": 1.477004716981132, "percentage": 7.39, "elapsed_time": "0:04:34", "remaining_time": "0:57:18", "throughput": 5971.01, "total_tokens": 1637304} +{"current_steps": 2510, "total_steps": 33920, "loss": 0.8169, "lr": 7.39681603773585e-06, "epoch": 1.4799528301886793, "percentage": 7.4, "elapsed_time": "0:04:34", "remaining_time": "0:57:18", "throughput": 5967.85, "total_tokens": 1639640} +{"current_steps": 2515, "total_steps": 33920, "loss": 0.5261, "lr": 7.411556603773586e-06, "epoch": 1.4829009433962264, "percentage": 7.41, "elapsed_time": "0:04:35", "remaining_time": "0:57:17", "throughput": 5967.68, "total_tokens": 1642840} +{"current_steps": 2520, "total_steps": 33920, "loss": 0.7222, "lr": 7.426297169811322e-06, "epoch": 1.4858490566037736, "percentage": 7.43, "elapsed_time": "0:04:35", "remaining_time": "0:57:17", "throughput": 5969.28, "total_tokens": 1646936} +{"current_steps": 2525, "total_steps": 33920, "loss": 0.7112, "lr": 7.441037735849057e-06, "epoch": 1.4887971698113207, "percentage": 7.44, "elapsed_time": "0:04:36", "remaining_time": "0:57:18", "throughput": 5970.41, "total_tokens": 1651256} +{"current_steps": 2530, "total_steps": 33920, "loss": 0.6471, "lr": 7.455778301886793e-06, "epoch": 1.491745283018868, "percentage": 7.46, "elapsed_time": "0:04:37", "remaining_time": "0:57:17", "throughput": 5970.68, "total_tokens": 1654456} +{"current_steps": 2535, "total_steps": 33920, "loss": 0.4948, "lr": 7.470518867924529e-06, "epoch": 1.494693396226415, "percentage": 7.47, "elapsed_time": "0:04:37", "remaining_time": "0:57:16", "throughput": 5969.49, "total_tokens": 1657176} +{"current_steps": 2540, "total_steps": 33920, "loss": 0.3534, "lr": 7.485259433962266e-06, "epoch": 1.4976415094339623, "percentage": 7.49, "elapsed_time": "0:04:38", "remaining_time": "0:57:15", "throughput": 5966.71, "total_tokens": 1659416} +{"current_steps": 2545, "total_steps": 33920, "loss": 0.4647, "lr": 7.500000000000001e-06, "epoch": 1.5005896226415094, "percentage": 7.5, "elapsed_time": "0:04:38", "remaining_time": "0:57:15", "throughput": 5965.83, "total_tokens": 1662552} +{"current_steps": 2550, "total_steps": 33920, "loss": 0.4586, "lr": 7.5147405660377355e-06, "epoch": 1.5035377358490565, "percentage": 7.52, "elapsed_time": "0:04:39", "remaining_time": "0:57:14", "throughput": 5965.74, "total_tokens": 1665592} +{"current_steps": 2555, "total_steps": 33920, "loss": 0.372, "lr": 7.5294811320754726e-06, "epoch": 1.5064858490566038, "percentage": 7.53, "elapsed_time": "0:04:39", "remaining_time": "0:57:13", "throughput": 5963.44, "total_tokens": 1667992} +{"current_steps": 2560, "total_steps": 33920, "loss": 0.4982, "lr": 7.544221698113208e-06, "epoch": 1.509433962264151, "percentage": 7.55, "elapsed_time": "0:04:40", "remaining_time": "0:57:13", "throughput": 5961.47, "total_tokens": 1670840} +{"current_steps": 2565, "total_steps": 33920, "loss": 0.5543, "lr": 7.558962264150944e-06, "epoch": 1.5123820754716981, "percentage": 7.56, "elapsed_time": "0:04:40", "remaining_time": "0:57:12", "throughput": 5961.23, "total_tokens": 1674008} +{"current_steps": 2570, "total_steps": 33920, "loss": 0.3332, "lr": 7.5737028301886795e-06, "epoch": 1.5153301886792452, "percentage": 7.58, "elapsed_time": "0:04:41", "remaining_time": "0:57:15", "throughput": 5962.29, "total_tokens": 1679192} +{"current_steps": 2575, "total_steps": 33920, "loss": 0.4668, "lr": 7.588443396226416e-06, "epoch": 1.5182783018867925, "percentage": 7.59, "elapsed_time": "0:04:42", "remaining_time": "0:57:15", "throughput": 5962.36, "total_tokens": 1682808} +{"current_steps": 2580, "total_steps": 33920, "loss": 0.4815, "lr": 7.603183962264151e-06, "epoch": 1.5212264150943398, "percentage": 7.61, "elapsed_time": "0:04:42", "remaining_time": "0:57:16", "throughput": 5963.97, "total_tokens": 1687352} +{"current_steps": 2585, "total_steps": 33920, "loss": 0.6118, "lr": 7.617924528301888e-06, "epoch": 1.5241745283018868, "percentage": 7.62, "elapsed_time": "0:04:43", "remaining_time": "0:57:15", "throughput": 5961.58, "total_tokens": 1689784} +{"current_steps": 2590, "total_steps": 33920, "loss": 0.6919, "lr": 7.632665094339623e-06, "epoch": 1.5271226415094339, "percentage": 7.64, "elapsed_time": "0:04:44", "remaining_time": "0:57:18", "throughput": 5963.93, "total_tokens": 1695192} +{"current_steps": 2595, "total_steps": 33920, "loss": 0.5491, "lr": 7.64740566037736e-06, "epoch": 1.5300707547169812, "percentage": 7.65, "elapsed_time": "0:04:44", "remaining_time": "0:57:17", "throughput": 5962.81, "total_tokens": 1698168} +{"current_steps": 2600, "total_steps": 33920, "loss": 0.5908, "lr": 7.662146226415095e-06, "epoch": 1.5330188679245285, "percentage": 7.67, "elapsed_time": "0:04:45", "remaining_time": "0:57:17", "throughput": 5962.32, "total_tokens": 1701624} +{"current_steps": 2605, "total_steps": 33920, "loss": 0.5148, "lr": 7.676886792452832e-06, "epoch": 1.5359669811320755, "percentage": 7.68, "elapsed_time": "0:04:45", "remaining_time": "0:57:17", "throughput": 5962.88, "total_tokens": 1705080} +{"current_steps": 2610, "total_steps": 33920, "loss": 0.6323, "lr": 7.691627358490567e-06, "epoch": 1.5389150943396226, "percentage": 7.69, "elapsed_time": "0:04:46", "remaining_time": "0:57:16", "throughput": 5962.49, "total_tokens": 1708280} +{"current_steps": 2615, "total_steps": 33920, "loss": 0.5338, "lr": 7.706367924528303e-06, "epoch": 1.5418632075471699, "percentage": 7.71, "elapsed_time": "0:04:47", "remaining_time": "0:57:17", "throughput": 5961.17, "total_tokens": 1711640} +{"current_steps": 2620, "total_steps": 33920, "loss": 0.4385, "lr": 7.721108490566038e-06, "epoch": 1.544811320754717, "percentage": 7.72, "elapsed_time": "0:04:47", "remaining_time": "0:57:16", "throughput": 5959.23, "total_tokens": 1714360} +{"current_steps": 2625, "total_steps": 33920, "loss": 0.4699, "lr": 7.735849056603775e-06, "epoch": 1.547759433962264, "percentage": 7.74, "elapsed_time": "0:04:48", "remaining_time": "0:57:16", "throughput": 5957.05, "total_tokens": 1717112} +{"current_steps": 2630, "total_steps": 33920, "loss": 0.5202, "lr": 7.75058962264151e-06, "epoch": 1.5507075471698113, "percentage": 7.75, "elapsed_time": "0:04:48", "remaining_time": "0:57:16", "throughput": 5957.58, "total_tokens": 1720664} +{"current_steps": 2635, "total_steps": 33920, "loss": 0.5821, "lr": 7.765330188679246e-06, "epoch": 1.5536556603773586, "percentage": 7.77, "elapsed_time": "0:04:49", "remaining_time": "0:57:15", "throughput": 5956.95, "total_tokens": 1723800} +{"current_steps": 2640, "total_steps": 33920, "loss": 0.821, "lr": 7.780070754716981e-06, "epoch": 1.5566037735849056, "percentage": 7.78, "elapsed_time": "0:04:49", "remaining_time": "0:57:14", "throughput": 5954.64, "total_tokens": 1726296} +{"current_steps": 2645, "total_steps": 33920, "loss": 0.4583, "lr": 7.794811320754716e-06, "epoch": 1.5595518867924527, "percentage": 7.8, "elapsed_time": "0:04:50", "remaining_time": "0:57:16", "throughput": 5954.77, "total_tokens": 1730424} +{"current_steps": 2650, "total_steps": 33920, "loss": 0.544, "lr": 7.809551886792453e-06, "epoch": 1.5625, "percentage": 7.81, "elapsed_time": "0:04:51", "remaining_time": "0:57:15", "throughput": 5953.14, "total_tokens": 1733176} +{"current_steps": 2655, "total_steps": 33920, "loss": 0.5237, "lr": 7.824292452830189e-06, "epoch": 1.5654481132075473, "percentage": 7.83, "elapsed_time": "0:04:51", "remaining_time": "0:57:14", "throughput": 5951.61, "total_tokens": 1735992} +{"current_steps": 2660, "total_steps": 33920, "loss": 0.4386, "lr": 7.839033018867926e-06, "epoch": 1.5683962264150944, "percentage": 7.84, "elapsed_time": "0:04:52", "remaining_time": "0:57:14", "throughput": 5951.5, "total_tokens": 1739096} +{"current_steps": 2665, "total_steps": 33920, "loss": 0.5593, "lr": 7.853773584905661e-06, "epoch": 1.5713443396226414, "percentage": 7.86, "elapsed_time": "0:04:53", "remaining_time": "0:57:21", "throughput": 5953.34, "total_tokens": 1746808} +{"current_steps": 2670, "total_steps": 33920, "loss": 0.5755, "lr": 7.868514150943397e-06, "epoch": 1.5742924528301887, "percentage": 7.87, "elapsed_time": "0:04:54", "remaining_time": "0:57:21", "throughput": 5952.88, "total_tokens": 1750552} +{"current_steps": 2675, "total_steps": 33920, "loss": 0.5568, "lr": 7.883254716981132e-06, "epoch": 1.577240566037736, "percentage": 7.89, "elapsed_time": "0:04:54", "remaining_time": "0:57:20", "throughput": 5951.38, "total_tokens": 1753208} +{"current_steps": 2680, "total_steps": 33920, "loss": 0.4838, "lr": 7.897995283018869e-06, "epoch": 1.580188679245283, "percentage": 7.9, "elapsed_time": "0:04:55", "remaining_time": "0:57:20", "throughput": 5951.12, "total_tokens": 1756728} +{"current_steps": 2685, "total_steps": 33920, "loss": 0.559, "lr": 7.912735849056604e-06, "epoch": 1.5831367924528301, "percentage": 7.92, "elapsed_time": "0:04:55", "remaining_time": "0:57:21", "throughput": 5951.34, "total_tokens": 1760472} +{"current_steps": 2690, "total_steps": 33920, "loss": 0.3578, "lr": 7.927476415094341e-06, "epoch": 1.5860849056603774, "percentage": 7.93, "elapsed_time": "0:04:56", "remaining_time": "0:57:20", "throughput": 5950.54, "total_tokens": 1763608} +{"current_steps": 2695, "total_steps": 33920, "loss": 0.6648, "lr": 7.942216981132077e-06, "epoch": 1.5890330188679245, "percentage": 7.95, "elapsed_time": "0:04:56", "remaining_time": "0:57:20", "throughput": 5949.67, "total_tokens": 1766552} +{"current_steps": 2700, "total_steps": 33920, "loss": 0.4145, "lr": 7.956957547169812e-06, "epoch": 1.5919811320754715, "percentage": 7.96, "elapsed_time": "0:04:57", "remaining_time": "0:57:19", "throughput": 5949.43, "total_tokens": 1769816} +{"current_steps": 2705, "total_steps": 33920, "loss": 0.5028, "lr": 7.971698113207547e-06, "epoch": 1.5949292452830188, "percentage": 7.97, "elapsed_time": "0:04:58", "remaining_time": "0:57:19", "throughput": 5949.0, "total_tokens": 1773016} +{"current_steps": 2710, "total_steps": 33920, "loss": 0.4626, "lr": 7.986438679245284e-06, "epoch": 1.5978773584905661, "percentage": 7.99, "elapsed_time": "0:04:58", "remaining_time": "0:57:18", "throughput": 5947.47, "total_tokens": 1775672} +{"current_steps": 2715, "total_steps": 33920, "loss": 0.5417, "lr": 8.00117924528302e-06, "epoch": 1.6008254716981132, "percentage": 8.0, "elapsed_time": "0:04:59", "remaining_time": "0:57:17", "throughput": 5947.44, "total_tokens": 1778680} +{"current_steps": 2720, "total_steps": 33920, "loss": 0.6327, "lr": 8.015919811320757e-06, "epoch": 1.6037735849056602, "percentage": 8.02, "elapsed_time": "0:04:59", "remaining_time": "0:57:16", "throughput": 5946.23, "total_tokens": 1781528} +{"current_steps": 2725, "total_steps": 33920, "loss": 0.6686, "lr": 8.030660377358492e-06, "epoch": 1.6067216981132075, "percentage": 8.03, "elapsed_time": "0:05:00", "remaining_time": "0:57:16", "throughput": 5946.36, "total_tokens": 1784856} +{"current_steps": 2730, "total_steps": 33920, "loss": 0.46, "lr": 8.045400943396227e-06, "epoch": 1.6096698113207548, "percentage": 8.05, "elapsed_time": "0:05:00", "remaining_time": "0:57:15", "throughput": 5944.27, "total_tokens": 1787384} +{"current_steps": 2735, "total_steps": 33920, "loss": 0.6499, "lr": 8.060141509433963e-06, "epoch": 1.6126179245283019, "percentage": 8.06, "elapsed_time": "0:05:01", "remaining_time": "0:57:15", "throughput": 5943.91, "total_tokens": 1790712} +{"current_steps": 2740, "total_steps": 33920, "loss": 0.5316, "lr": 8.074882075471698e-06, "epoch": 1.615566037735849, "percentage": 8.08, "elapsed_time": "0:05:01", "remaining_time": "0:57:14", "throughput": 5942.72, "total_tokens": 1793400} +{"current_steps": 2745, "total_steps": 33920, "loss": 0.5906, "lr": 8.089622641509435e-06, "epoch": 1.6185141509433962, "percentage": 8.09, "elapsed_time": "0:05:02", "remaining_time": "0:57:14", "throughput": 5942.35, "total_tokens": 1796824} +{"current_steps": 2750, "total_steps": 33920, "loss": 0.5757, "lr": 8.10436320754717e-06, "epoch": 1.6214622641509435, "percentage": 8.11, "elapsed_time": "0:05:02", "remaining_time": "0:57:13", "throughput": 5941.47, "total_tokens": 1799608} +{"current_steps": 2755, "total_steps": 33920, "loss": 0.5158, "lr": 8.119103773584906e-06, "epoch": 1.6244103773584906, "percentage": 8.12, "elapsed_time": "0:05:03", "remaining_time": "0:57:13", "throughput": 5941.24, "total_tokens": 1803192} +{"current_steps": 2760, "total_steps": 33920, "loss": 0.3916, "lr": 8.133844339622641e-06, "epoch": 1.6273584905660377, "percentage": 8.14, "elapsed_time": "0:05:04", "remaining_time": "0:57:13", "throughput": 5941.7, "total_tokens": 1806808} +{"current_steps": 2765, "total_steps": 33920, "loss": 0.4918, "lr": 8.148584905660378e-06, "epoch": 1.630306603773585, "percentage": 8.15, "elapsed_time": "0:05:04", "remaining_time": "0:57:12", "throughput": 5941.73, "total_tokens": 1809816} +{"current_steps": 2770, "total_steps": 33920, "loss": 0.5403, "lr": 8.163325471698114e-06, "epoch": 1.6332547169811322, "percentage": 8.17, "elapsed_time": "0:05:05", "remaining_time": "0:57:11", "throughput": 5940.74, "total_tokens": 1812536} +{"current_steps": 2775, "total_steps": 33920, "loss": 0.4869, "lr": 8.17806603773585e-06, "epoch": 1.6362028301886793, "percentage": 8.18, "elapsed_time": "0:05:05", "remaining_time": "0:57:11", "throughput": 5942.37, "total_tokens": 1816824} +{"current_steps": 2780, "total_steps": 33920, "loss": 0.5422, "lr": 8.192806603773586e-06, "epoch": 1.6391509433962264, "percentage": 8.2, "elapsed_time": "0:05:06", "remaining_time": "0:57:11", "throughput": 5942.26, "total_tokens": 1820312} +{"current_steps": 2785, "total_steps": 33920, "loss": 0.4578, "lr": 8.207547169811321e-06, "epoch": 1.6420990566037736, "percentage": 8.21, "elapsed_time": "0:05:06", "remaining_time": "0:57:11", "throughput": 5940.97, "total_tokens": 1823320} +{"current_steps": 2790, "total_steps": 33920, "loss": 0.5846, "lr": 8.222287735849057e-06, "epoch": 1.6450471698113207, "percentage": 8.23, "elapsed_time": "0:05:07", "remaining_time": "0:57:10", "throughput": 5940.6, "total_tokens": 1826552} +{"current_steps": 2795, "total_steps": 33920, "loss": 0.6512, "lr": 8.237028301886794e-06, "epoch": 1.6479952830188678, "percentage": 8.24, "elapsed_time": "0:05:07", "remaining_time": "0:57:09", "throughput": 5939.96, "total_tokens": 1829432} +{"current_steps": 2800, "total_steps": 33920, "loss": 0.4295, "lr": 8.251768867924529e-06, "epoch": 1.650943396226415, "percentage": 8.25, "elapsed_time": "0:05:08", "remaining_time": "0:57:09", "throughput": 5939.47, "total_tokens": 1832536} +{"current_steps": 2805, "total_steps": 33920, "loss": 0.495, "lr": 8.266509433962266e-06, "epoch": 1.6538915094339623, "percentage": 8.27, "elapsed_time": "0:05:09", "remaining_time": "0:57:09", "throughput": 5940.38, "total_tokens": 1836600} +{"current_steps": 2810, "total_steps": 33920, "loss": 0.5311, "lr": 8.281250000000001e-06, "epoch": 1.6568396226415094, "percentage": 8.28, "elapsed_time": "0:05:09", "remaining_time": "0:57:08", "throughput": 5937.5, "total_tokens": 1838808} +{"current_steps": 2815, "total_steps": 33920, "loss": 0.4286, "lr": 8.295990566037737e-06, "epoch": 1.6597877358490565, "percentage": 8.3, "elapsed_time": "0:05:10", "remaining_time": "0:57:08", "throughput": 5937.73, "total_tokens": 1842232} +{"current_steps": 2820, "total_steps": 33920, "loss": 0.5835, "lr": 8.310731132075472e-06, "epoch": 1.6627358490566038, "percentage": 8.31, "elapsed_time": "0:05:10", "remaining_time": "0:57:08", "throughput": 5938.22, "total_tokens": 1846008} +{"current_steps": 2825, "total_steps": 33920, "loss": 0.6148, "lr": 8.325471698113207e-06, "epoch": 1.665683962264151, "percentage": 8.33, "elapsed_time": "0:05:11", "remaining_time": "0:57:08", "throughput": 5937.62, "total_tokens": 1849272} +{"current_steps": 2830, "total_steps": 33920, "loss": 0.5432, "lr": 8.340212264150944e-06, "epoch": 1.6686320754716981, "percentage": 8.34, "elapsed_time": "0:05:12", "remaining_time": "0:57:07", "throughput": 5937.53, "total_tokens": 1852536} +{"current_steps": 2835, "total_steps": 33920, "loss": 0.4587, "lr": 8.35495283018868e-06, "epoch": 1.6715801886792452, "percentage": 8.36, "elapsed_time": "0:05:12", "remaining_time": "0:57:08", "throughput": 5939.46, "total_tokens": 1857304} +{"current_steps": 2840, "total_steps": 33920, "loss": 0.4895, "lr": 8.369693396226415e-06, "epoch": 1.6745283018867925, "percentage": 8.37, "elapsed_time": "0:05:13", "remaining_time": "0:57:08", "throughput": 5940.92, "total_tokens": 1861400} +{"current_steps": 2845, "total_steps": 33920, "loss": 0.5017, "lr": 8.38443396226415e-06, "epoch": 1.6774764150943398, "percentage": 8.39, "elapsed_time": "0:05:13", "remaining_time": "0:57:08", "throughput": 5940.13, "total_tokens": 1864408} +{"current_steps": 2850, "total_steps": 33920, "loss": 0.4526, "lr": 8.399174528301888e-06, "epoch": 1.6804245283018868, "percentage": 8.4, "elapsed_time": "0:05:14", "remaining_time": "0:57:08", "throughput": 5939.37, "total_tokens": 1867608} +{"current_steps": 2855, "total_steps": 33920, "loss": 0.446, "lr": 8.413915094339623e-06, "epoch": 1.6833726415094339, "percentage": 8.42, "elapsed_time": "0:05:14", "remaining_time": "0:57:07", "throughput": 5937.62, "total_tokens": 1870264} +{"current_steps": 2860, "total_steps": 33920, "loss": 0.4714, "lr": 8.42865566037736e-06, "epoch": 1.6863207547169812, "percentage": 8.43, "elapsed_time": "0:05:15", "remaining_time": "0:57:07", "throughput": 5937.78, "total_tokens": 1873816} +{"current_steps": 2865, "total_steps": 33920, "loss": 0.4416, "lr": 8.443396226415095e-06, "epoch": 1.6892688679245285, "percentage": 8.45, "elapsed_time": "0:05:16", "remaining_time": "0:57:06", "throughput": 5937.56, "total_tokens": 1877112} +{"current_steps": 2870, "total_steps": 33920, "loss": 0.4891, "lr": 8.45813679245283e-06, "epoch": 1.6922169811320755, "percentage": 8.46, "elapsed_time": "0:05:16", "remaining_time": "0:57:06", "throughput": 5937.2, "total_tokens": 1880216} +{"current_steps": 2875, "total_steps": 33920, "loss": 0.5221, "lr": 8.472877358490566e-06, "epoch": 1.6951650943396226, "percentage": 8.48, "elapsed_time": "0:05:17", "remaining_time": "0:57:05", "throughput": 5935.93, "total_tokens": 1883000} +{"current_steps": 2880, "total_steps": 33920, "loss": 0.5907, "lr": 8.487617924528303e-06, "epoch": 1.6981132075471699, "percentage": 8.49, "elapsed_time": "0:05:17", "remaining_time": "0:57:04", "throughput": 5934.82, "total_tokens": 1885752} +{"current_steps": 2885, "total_steps": 33920, "loss": 0.5243, "lr": 8.502358490566038e-06, "epoch": 1.701061320754717, "percentage": 8.51, "elapsed_time": "0:05:18", "remaining_time": "0:57:04", "throughput": 5935.12, "total_tokens": 1889560} +{"current_steps": 2890, "total_steps": 33920, "loss": 0.5486, "lr": 8.517099056603775e-06, "epoch": 1.704009433962264, "percentage": 8.52, "elapsed_time": "0:05:18", "remaining_time": "0:57:04", "throughput": 5935.65, "total_tokens": 1893016} +{"current_steps": 2895, "total_steps": 33920, "loss": 0.4977, "lr": 8.53183962264151e-06, "epoch": 1.7069575471698113, "percentage": 8.53, "elapsed_time": "0:05:19", "remaining_time": "0:57:03", "throughput": 5935.32, "total_tokens": 1895960} +{"current_steps": 2900, "total_steps": 33920, "loss": 0.4906, "lr": 8.546580188679246e-06, "epoch": 1.7099056603773586, "percentage": 8.55, "elapsed_time": "0:05:19", "remaining_time": "0:57:02", "throughput": 5934.5, "total_tokens": 1898968} +{"current_steps": 2905, "total_steps": 33920, "loss": 0.3736, "lr": 8.561320754716981e-06, "epoch": 1.7128537735849056, "percentage": 8.56, "elapsed_time": "0:05:20", "remaining_time": "0:57:02", "throughput": 5934.49, "total_tokens": 1902360} +{"current_steps": 2910, "total_steps": 33920, "loss": 0.5127, "lr": 8.576061320754717e-06, "epoch": 1.7158018867924527, "percentage": 8.58, "elapsed_time": "0:05:21", "remaining_time": "0:57:01", "throughput": 5933.51, "total_tokens": 1905336} +{"current_steps": 2915, "total_steps": 33920, "loss": 0.7356, "lr": 8.590801886792454e-06, "epoch": 1.71875, "percentage": 8.59, "elapsed_time": "0:05:21", "remaining_time": "0:57:01", "throughput": 5933.9, "total_tokens": 1908888} +{"current_steps": 2920, "total_steps": 33920, "loss": 0.5751, "lr": 8.605542452830189e-06, "epoch": 1.7216981132075473, "percentage": 8.61, "elapsed_time": "0:05:22", "remaining_time": "0:57:02", "throughput": 5933.58, "total_tokens": 1912952} +{"current_steps": 2925, "total_steps": 33920, "loss": 0.4145, "lr": 8.620283018867926e-06, "epoch": 1.7246462264150944, "percentage": 8.62, "elapsed_time": "0:05:22", "remaining_time": "0:57:02", "throughput": 5933.37, "total_tokens": 1916312} +{"current_steps": 2930, "total_steps": 33920, "loss": 0.4054, "lr": 8.635023584905662e-06, "epoch": 1.7275943396226414, "percentage": 8.64, "elapsed_time": "0:05:23", "remaining_time": "0:57:01", "throughput": 5933.16, "total_tokens": 1919512} +{"current_steps": 2935, "total_steps": 33920, "loss": 0.4923, "lr": 8.649764150943397e-06, "epoch": 1.7305424528301887, "percentage": 8.65, "elapsed_time": "0:05:24", "remaining_time": "0:57:00", "throughput": 5932.44, "total_tokens": 1922392} +{"current_steps": 2940, "total_steps": 33920, "loss": 0.5374, "lr": 8.664504716981132e-06, "epoch": 1.733490566037736, "percentage": 8.67, "elapsed_time": "0:05:24", "remaining_time": "0:57:00", "throughput": 5931.91, "total_tokens": 1925720} +{"current_steps": 2945, "total_steps": 33920, "loss": 0.5583, "lr": 8.67924528301887e-06, "epoch": 1.736438679245283, "percentage": 8.68, "elapsed_time": "0:05:25", "remaining_time": "0:57:00", "throughput": 5931.09, "total_tokens": 1928600} +{"current_steps": 2950, "total_steps": 33920, "loss": 0.4716, "lr": 8.693985849056605e-06, "epoch": 1.7393867924528301, "percentage": 8.7, "elapsed_time": "0:05:25", "remaining_time": "0:56:59", "throughput": 5930.05, "total_tokens": 1931288} +{"current_steps": 2955, "total_steps": 33920, "loss": 0.6177, "lr": 8.70872641509434e-06, "epoch": 1.7423349056603774, "percentage": 8.71, "elapsed_time": "0:05:26", "remaining_time": "0:56:58", "throughput": 5929.95, "total_tokens": 1934392} +{"current_steps": 2960, "total_steps": 33920, "loss": 0.3822, "lr": 8.723466981132075e-06, "epoch": 1.7452830188679245, "percentage": 8.73, "elapsed_time": "0:05:26", "remaining_time": "0:56:57", "throughput": 5929.17, "total_tokens": 1937304} +{"current_steps": 2965, "total_steps": 33920, "loss": 0.4099, "lr": 8.738207547169812e-06, "epoch": 1.7482311320754715, "percentage": 8.74, "elapsed_time": "0:05:27", "remaining_time": "0:56:56", "throughput": 5929.13, "total_tokens": 1940536} +{"current_steps": 2970, "total_steps": 33920, "loss": 0.5902, "lr": 8.752948113207548e-06, "epoch": 1.7511792452830188, "percentage": 8.76, "elapsed_time": "0:05:27", "remaining_time": "0:56:55", "throughput": 5927.75, "total_tokens": 1943128} +{"current_steps": 2975, "total_steps": 33920, "loss": 0.5142, "lr": 8.767688679245285e-06, "epoch": 1.7541273584905661, "percentage": 8.77, "elapsed_time": "0:05:28", "remaining_time": "0:56:55", "throughput": 5927.65, "total_tokens": 1946136} +{"current_steps": 2980, "total_steps": 33920, "loss": 0.4953, "lr": 8.78242924528302e-06, "epoch": 1.7570754716981132, "percentage": 8.79, "elapsed_time": "0:05:28", "remaining_time": "0:56:54", "throughput": 5925.64, "total_tokens": 1948568} +{"current_steps": 2985, "total_steps": 33920, "loss": 0.7807, "lr": 8.797169811320755e-06, "epoch": 1.7600235849056602, "percentage": 8.8, "elapsed_time": "0:05:29", "remaining_time": "0:56:53", "throughput": 5923.95, "total_tokens": 1951096} +{"current_steps": 2990, "total_steps": 33920, "loss": 0.4057, "lr": 8.81191037735849e-06, "epoch": 1.7629716981132075, "percentage": 8.81, "elapsed_time": "0:05:29", "remaining_time": "0:56:52", "throughput": 5923.39, "total_tokens": 1954264} +{"current_steps": 2995, "total_steps": 33920, "loss": 0.4684, "lr": 8.826650943396226e-06, "epoch": 1.7659198113207548, "percentage": 8.83, "elapsed_time": "0:05:30", "remaining_time": "0:56:52", "throughput": 5923.91, "total_tokens": 1957688} +{"current_steps": 3000, "total_steps": 33920, "loss": 0.637, "lr": 8.841391509433963e-06, "epoch": 1.7688679245283019, "percentage": 8.84, "elapsed_time": "0:05:30", "remaining_time": "0:56:51", "throughput": 5923.38, "total_tokens": 1960600} +{"current_steps": 3005, "total_steps": 33920, "loss": 0.537, "lr": 8.856132075471698e-06, "epoch": 1.771816037735849, "percentage": 8.86, "elapsed_time": "0:05:31", "remaining_time": "0:56:51", "throughput": 5923.78, "total_tokens": 1964088} +{"current_steps": 3010, "total_steps": 33920, "loss": 0.6031, "lr": 8.870872641509435e-06, "epoch": 1.7747641509433962, "percentage": 8.87, "elapsed_time": "0:05:32", "remaining_time": "0:56:50", "throughput": 5924.1, "total_tokens": 1967320} +{"current_steps": 3015, "total_steps": 33920, "loss": 0.4097, "lr": 8.88561320754717e-06, "epoch": 1.7777122641509435, "percentage": 8.89, "elapsed_time": "0:05:32", "remaining_time": "0:56:51", "throughput": 5925.2, "total_tokens": 1972152} +{"current_steps": 3020, "total_steps": 33920, "loss": 0.5527, "lr": 8.900353773584906e-06, "epoch": 1.7806603773584906, "percentage": 8.9, "elapsed_time": "0:05:33", "remaining_time": "0:56:51", "throughput": 5925.84, "total_tokens": 1975960} +{"current_steps": 3025, "total_steps": 33920, "loss": 0.391, "lr": 8.915094339622642e-06, "epoch": 1.7836084905660377, "percentage": 8.92, "elapsed_time": "0:05:33", "remaining_time": "0:56:51", "throughput": 5925.93, "total_tokens": 1979256} +{"current_steps": 3030, "total_steps": 33920, "loss": 0.6963, "lr": 8.929834905660379e-06, "epoch": 1.786556603773585, "percentage": 8.93, "elapsed_time": "0:05:34", "remaining_time": "0:56:50", "throughput": 5925.63, "total_tokens": 1982232} +{"current_steps": 3035, "total_steps": 33920, "loss": 0.4936, "lr": 8.944575471698114e-06, "epoch": 1.7895047169811322, "percentage": 8.95, "elapsed_time": "0:05:35", "remaining_time": "0:56:50", "throughput": 5927.53, "total_tokens": 1986808} +{"current_steps": 3040, "total_steps": 33920, "loss": 0.4139, "lr": 8.959316037735851e-06, "epoch": 1.7924528301886793, "percentage": 8.96, "elapsed_time": "0:05:35", "remaining_time": "0:56:49", "throughput": 5925.71, "total_tokens": 1989240} +{"current_steps": 3045, "total_steps": 33920, "loss": 0.5585, "lr": 8.974056603773586e-06, "epoch": 1.7954009433962264, "percentage": 8.98, "elapsed_time": "0:05:36", "remaining_time": "0:56:49", "throughput": 5924.59, "total_tokens": 1991960} +{"current_steps": 3050, "total_steps": 33920, "loss": 0.4733, "lr": 8.988797169811322e-06, "epoch": 1.7983490566037736, "percentage": 8.99, "elapsed_time": "0:05:36", "remaining_time": "0:56:48", "throughput": 5923.47, "total_tokens": 1994584} +{"current_steps": 3055, "total_steps": 33920, "loss": 0.5391, "lr": 9.003537735849057e-06, "epoch": 1.8012971698113207, "percentage": 9.01, "elapsed_time": "0:05:37", "remaining_time": "0:56:47", "throughput": 5924.45, "total_tokens": 1998328} +{"current_steps": 3060, "total_steps": 33920, "loss": 0.7036, "lr": 9.018278301886794e-06, "epoch": 1.8042452830188678, "percentage": 9.02, "elapsed_time": "0:05:37", "remaining_time": "0:56:47", "throughput": 5924.42, "total_tokens": 2001528} +{"current_steps": 3065, "total_steps": 33920, "loss": 0.5111, "lr": 9.03301886792453e-06, "epoch": 1.807193396226415, "percentage": 9.04, "elapsed_time": "0:05:38", "remaining_time": "0:56:46", "throughput": 5924.92, "total_tokens": 2004920} +{"current_steps": 3070, "total_steps": 33920, "loss": 0.4168, "lr": 9.047759433962265e-06, "epoch": 1.8101415094339623, "percentage": 9.05, "elapsed_time": "0:05:38", "remaining_time": "0:56:46", "throughput": 5925.63, "total_tokens": 2008760} +{"current_steps": 3075, "total_steps": 33920, "loss": 0.6961, "lr": 9.0625e-06, "epoch": 1.8130896226415094, "percentage": 9.07, "elapsed_time": "0:05:39", "remaining_time": "0:56:45", "throughput": 5924.45, "total_tokens": 2011448} +{"current_steps": 3080, "total_steps": 33920, "loss": 0.5515, "lr": 9.077240566037735e-06, "epoch": 1.8160377358490565, "percentage": 9.08, "elapsed_time": "0:05:40", "remaining_time": "0:56:45", "throughput": 5924.52, "total_tokens": 2014936} +{"current_steps": 3085, "total_steps": 33920, "loss": 0.7468, "lr": 9.091981132075472e-06, "epoch": 1.8189858490566038, "percentage": 9.09, "elapsed_time": "0:05:40", "remaining_time": "0:56:44", "throughput": 5923.68, "total_tokens": 2017848} +{"current_steps": 3090, "total_steps": 33920, "loss": 0.5752, "lr": 9.106721698113208e-06, "epoch": 1.821933962264151, "percentage": 9.11, "elapsed_time": "0:05:41", "remaining_time": "0:56:44", "throughput": 5924.13, "total_tokens": 2021688} +{"current_steps": 3095, "total_steps": 33920, "loss": 0.8491, "lr": 9.121462264150945e-06, "epoch": 1.8248820754716981, "percentage": 9.12, "elapsed_time": "0:05:41", "remaining_time": "0:56:44", "throughput": 5924.08, "total_tokens": 2024760} +{"current_steps": 3100, "total_steps": 33920, "loss": 0.5528, "lr": 9.13620283018868e-06, "epoch": 1.8278301886792452, "percentage": 9.14, "elapsed_time": "0:05:42", "remaining_time": "0:56:43", "throughput": 5924.14, "total_tokens": 2028152} +{"current_steps": 3105, "total_steps": 33920, "loss": 0.4598, "lr": 9.150943396226416e-06, "epoch": 1.8307783018867925, "percentage": 9.15, "elapsed_time": "0:05:42", "remaining_time": "0:56:43", "throughput": 5922.51, "total_tokens": 2030904} +{"current_steps": 3110, "total_steps": 33920, "loss": 0.5396, "lr": 9.165683962264151e-06, "epoch": 1.8337264150943398, "percentage": 9.17, "elapsed_time": "0:05:43", "remaining_time": "0:56:42", "throughput": 5922.6, "total_tokens": 2034328} +{"current_steps": 3115, "total_steps": 33920, "loss": 0.7763, "lr": 9.180424528301888e-06, "epoch": 1.8366745283018868, "percentage": 9.18, "elapsed_time": "0:05:44", "remaining_time": "0:56:42", "throughput": 5922.31, "total_tokens": 2037560} +{"current_steps": 3120, "total_steps": 33920, "loss": 0.5452, "lr": 9.195165094339623e-06, "epoch": 1.8396226415094339, "percentage": 9.2, "elapsed_time": "0:05:44", "remaining_time": "0:56:42", "throughput": 5922.55, "total_tokens": 2041176} +{"current_steps": 3125, "total_steps": 33920, "loss": 0.4362, "lr": 9.20990566037736e-06, "epoch": 1.8425707547169812, "percentage": 9.21, "elapsed_time": "0:05:45", "remaining_time": "0:56:41", "throughput": 5922.78, "total_tokens": 2044472} +{"current_steps": 3130, "total_steps": 33920, "loss": 0.5232, "lr": 9.224646226415096e-06, "epoch": 1.8455188679245285, "percentage": 9.23, "elapsed_time": "0:05:45", "remaining_time": "0:56:41", "throughput": 5923.01, "total_tokens": 2048088} +{"current_steps": 3135, "total_steps": 33920, "loss": 0.4834, "lr": 9.239386792452831e-06, "epoch": 1.8484669811320755, "percentage": 9.24, "elapsed_time": "0:05:46", "remaining_time": "0:56:40", "throughput": 5922.68, "total_tokens": 2051096} +{"current_steps": 3140, "total_steps": 33920, "loss": 0.4923, "lr": 9.254127358490566e-06, "epoch": 1.8514150943396226, "percentage": 9.26, "elapsed_time": "0:05:46", "remaining_time": "0:56:40", "throughput": 5923.53, "total_tokens": 2054776} +{"current_steps": 3145, "total_steps": 33920, "loss": 0.4875, "lr": 9.268867924528303e-06, "epoch": 1.8543632075471699, "percentage": 9.27, "elapsed_time": "0:05:47", "remaining_time": "0:56:39", "throughput": 5923.34, "total_tokens": 2057784} +{"current_steps": 3150, "total_steps": 33920, "loss": 0.4603, "lr": 9.283608490566039e-06, "epoch": 1.857311320754717, "percentage": 9.29, "elapsed_time": "0:05:47", "remaining_time": "0:56:38", "throughput": 5922.43, "total_tokens": 2060504} +{"current_steps": 3155, "total_steps": 33920, "loss": 0.5476, "lr": 9.298349056603774e-06, "epoch": 1.860259433962264, "percentage": 9.3, "elapsed_time": "0:05:48", "remaining_time": "0:56:38", "throughput": 5921.58, "total_tokens": 2063864} +{"current_steps": 3160, "total_steps": 33920, "loss": 0.5082, "lr": 9.31308962264151e-06, "epoch": 1.8632075471698113, "percentage": 9.32, "elapsed_time": "0:05:49", "remaining_time": "0:56:38", "throughput": 5921.69, "total_tokens": 2067448} +{"current_steps": 3165, "total_steps": 33920, "loss": 0.4582, "lr": 9.327830188679245e-06, "epoch": 1.8661556603773586, "percentage": 9.33, "elapsed_time": "0:05:49", "remaining_time": "0:56:38", "throughput": 5922.14, "total_tokens": 2071480} +{"current_steps": 3170, "total_steps": 33920, "loss": 0.5498, "lr": 9.342570754716982e-06, "epoch": 1.8691037735849056, "percentage": 9.35, "elapsed_time": "0:05:50", "remaining_time": "0:56:38", "throughput": 5921.09, "total_tokens": 2074520} +{"current_steps": 3175, "total_steps": 33920, "loss": 0.3831, "lr": 9.357311320754717e-06, "epoch": 1.8720518867924527, "percentage": 9.36, "elapsed_time": "0:05:50", "remaining_time": "0:56:38", "throughput": 5921.18, "total_tokens": 2077848} +{"current_steps": 3180, "total_steps": 33920, "loss": 0.4085, "lr": 9.372051886792454e-06, "epoch": 1.875, "percentage": 9.38, "elapsed_time": "0:05:51", "remaining_time": "0:56:38", "throughput": 5921.8, "total_tokens": 2082136} +{"current_steps": 3185, "total_steps": 33920, "loss": 0.5789, "lr": 9.38679245283019e-06, "epoch": 1.8779481132075473, "percentage": 9.39, "elapsed_time": "0:05:52", "remaining_time": "0:56:37", "throughput": 5921.09, "total_tokens": 2084888} +{"current_steps": 3190, "total_steps": 33920, "loss": 0.6103, "lr": 9.401533018867925e-06, "epoch": 1.8808962264150944, "percentage": 9.4, "elapsed_time": "0:05:53", "remaining_time": "0:56:41", "throughput": 5921.93, "total_tokens": 2090840} +{"current_steps": 3195, "total_steps": 33920, "loss": 0.4561, "lr": 9.41627358490566e-06, "epoch": 1.8838443396226414, "percentage": 9.42, "elapsed_time": "0:05:53", "remaining_time": "0:56:41", "throughput": 5922.63, "total_tokens": 2094904} +{"current_steps": 3200, "total_steps": 33920, "loss": 0.594, "lr": 9.431014150943397e-06, "epoch": 1.8867924528301887, "percentage": 9.43, "elapsed_time": "0:05:54", "remaining_time": "0:56:40", "throughput": 5921.56, "total_tokens": 2097688} +{"current_steps": 3205, "total_steps": 33920, "loss": 0.5259, "lr": 9.445754716981133e-06, "epoch": 1.889740566037736, "percentage": 9.45, "elapsed_time": "0:05:54", "remaining_time": "0:56:40", "throughput": 5921.71, "total_tokens": 2101176} +{"current_steps": 3210, "total_steps": 33920, "loss": 0.5192, "lr": 9.46049528301887e-06, "epoch": 1.892688679245283, "percentage": 9.46, "elapsed_time": "0:05:55", "remaining_time": "0:56:39", "throughput": 5921.14, "total_tokens": 2103992} +{"current_steps": 3215, "total_steps": 33920, "loss": 0.5128, "lr": 9.475235849056605e-06, "epoch": 1.8956367924528301, "percentage": 9.48, "elapsed_time": "0:05:55", "remaining_time": "0:56:39", "throughput": 5921.44, "total_tokens": 2107896} +{"current_steps": 3220, "total_steps": 33920, "loss": 0.5792, "lr": 9.48997641509434e-06, "epoch": 1.8985849056603774, "percentage": 9.49, "elapsed_time": "0:05:56", "remaining_time": "0:56:39", "throughput": 5922.3, "total_tokens": 2111608} +{"current_steps": 3225, "total_steps": 33920, "loss": 0.5504, "lr": 9.504716981132076e-06, "epoch": 1.9015330188679245, "percentage": 9.51, "elapsed_time": "0:05:57", "remaining_time": "0:56:39", "throughput": 5922.19, "total_tokens": 2115064} +{"current_steps": 3230, "total_steps": 33920, "loss": 0.4051, "lr": 9.519457547169813e-06, "epoch": 1.9044811320754715, "percentage": 9.52, "elapsed_time": "0:05:57", "remaining_time": "0:56:38", "throughput": 5922.0, "total_tokens": 2118040} +{"current_steps": 3235, "total_steps": 33920, "loss": 0.6842, "lr": 9.534198113207548e-06, "epoch": 1.9074292452830188, "percentage": 9.54, "elapsed_time": "0:05:58", "remaining_time": "0:56:37", "throughput": 5920.49, "total_tokens": 2120760} +{"current_steps": 3240, "total_steps": 33920, "loss": 0.5488, "lr": 9.548938679245285e-06, "epoch": 1.9103773584905661, "percentage": 9.55, "elapsed_time": "0:05:58", "remaining_time": "0:56:37", "throughput": 5920.66, "total_tokens": 2124536} +{"current_steps": 3245, "total_steps": 33920, "loss": 0.5862, "lr": 9.56367924528302e-06, "epoch": 1.9133254716981132, "percentage": 9.57, "elapsed_time": "0:05:59", "remaining_time": "0:56:37", "throughput": 5921.08, "total_tokens": 2128184} +{"current_steps": 3250, "total_steps": 33920, "loss": 0.4463, "lr": 9.578419811320756e-06, "epoch": 1.9162735849056602, "percentage": 9.58, "elapsed_time": "0:06:00", "remaining_time": "0:56:37", "throughput": 5922.2, "total_tokens": 2132184} +{"current_steps": 3255, "total_steps": 33920, "loss": 0.4632, "lr": 9.593160377358491e-06, "epoch": 1.9192216981132075, "percentage": 9.6, "elapsed_time": "0:06:00", "remaining_time": "0:56:36", "throughput": 5922.15, "total_tokens": 2135288} +{"current_steps": 3260, "total_steps": 33920, "loss": 0.5715, "lr": 9.607900943396226e-06, "epoch": 1.9221698113207548, "percentage": 9.61, "elapsed_time": "0:06:01", "remaining_time": "0:56:36", "throughput": 5921.77, "total_tokens": 2138616} +{"current_steps": 3265, "total_steps": 33920, "loss": 0.5413, "lr": 9.622641509433963e-06, "epoch": 1.9251179245283019, "percentage": 9.63, "elapsed_time": "0:06:01", "remaining_time": "0:56:36", "throughput": 5921.1, "total_tokens": 2141880} +{"current_steps": 3270, "total_steps": 33920, "loss": 0.4785, "lr": 9.637382075471699e-06, "epoch": 1.928066037735849, "percentage": 9.64, "elapsed_time": "0:06:02", "remaining_time": "0:56:35", "throughput": 5920.21, "total_tokens": 2144664} +{"current_steps": 3275, "total_steps": 33920, "loss": 0.5875, "lr": 9.652122641509434e-06, "epoch": 1.9310141509433962, "percentage": 9.66, "elapsed_time": "0:06:02", "remaining_time": "0:56:35", "throughput": 5920.51, "total_tokens": 2148184} +{"current_steps": 3280, "total_steps": 33920, "loss": 0.5118, "lr": 9.66686320754717e-06, "epoch": 1.9339622641509435, "percentage": 9.67, "elapsed_time": "0:06:03", "remaining_time": "0:56:35", "throughput": 5921.34, "total_tokens": 2152568} +{"current_steps": 3285, "total_steps": 33920, "loss": 0.5098, "lr": 9.681603773584907e-06, "epoch": 1.9369103773584906, "percentage": 9.68, "elapsed_time": "0:06:04", "remaining_time": "0:56:34", "throughput": 5920.73, "total_tokens": 2155384} +{"current_steps": 3290, "total_steps": 33920, "loss": 0.4821, "lr": 9.696344339622642e-06, "epoch": 1.9398584905660377, "percentage": 9.7, "elapsed_time": "0:06:04", "remaining_time": "0:56:34", "throughput": 5921.17, "total_tokens": 2158744} +{"current_steps": 3295, "total_steps": 33920, "loss": 0.4582, "lr": 9.711084905660379e-06, "epoch": 1.942806603773585, "percentage": 9.71, "elapsed_time": "0:06:05", "remaining_time": "0:56:34", "throughput": 5921.06, "total_tokens": 2162200} +{"current_steps": 3300, "total_steps": 33920, "loss": 0.4621, "lr": 9.725825471698114e-06, "epoch": 1.9457547169811322, "percentage": 9.73, "elapsed_time": "0:06:05", "remaining_time": "0:56:33", "throughput": 5919.87, "total_tokens": 2164792} +{"current_steps": 3305, "total_steps": 33920, "loss": 0.4133, "lr": 9.74056603773585e-06, "epoch": 1.9487028301886793, "percentage": 9.74, "elapsed_time": "0:06:06", "remaining_time": "0:56:32", "throughput": 5918.48, "total_tokens": 2167320} +{"current_steps": 3310, "total_steps": 33920, "loss": 0.4264, "lr": 9.755306603773585e-06, "epoch": 1.9516509433962264, "percentage": 9.76, "elapsed_time": "0:06:06", "remaining_time": "0:56:31", "throughput": 5916.98, "total_tokens": 2169784} +{"current_steps": 3315, "total_steps": 33920, "loss": 0.5689, "lr": 9.770047169811322e-06, "epoch": 1.9545990566037736, "percentage": 9.77, "elapsed_time": "0:06:07", "remaining_time": "0:56:30", "throughput": 5917.06, "total_tokens": 2173272} +{"current_steps": 3320, "total_steps": 33920, "loss": 0.6058, "lr": 9.784787735849057e-06, "epoch": 1.9575471698113207, "percentage": 9.79, "elapsed_time": "0:06:07", "remaining_time": "0:56:29", "throughput": 5916.94, "total_tokens": 2176248} +{"current_steps": 3325, "total_steps": 33920, "loss": 0.7947, "lr": 9.799528301886794e-06, "epoch": 1.9604952830188678, "percentage": 9.8, "elapsed_time": "0:06:08", "remaining_time": "0:56:29", "throughput": 5917.06, "total_tokens": 2179704} +{"current_steps": 3330, "total_steps": 33920, "loss": 0.5105, "lr": 9.81426886792453e-06, "epoch": 1.963443396226415, "percentage": 9.82, "elapsed_time": "0:06:09", "remaining_time": "0:56:30", "throughput": 5916.98, "total_tokens": 2183640} +{"current_steps": 3335, "total_steps": 33920, "loss": 0.6292, "lr": 9.829009433962265e-06, "epoch": 1.9663915094339623, "percentage": 9.83, "elapsed_time": "0:06:09", "remaining_time": "0:56:30", "throughput": 5917.41, "total_tokens": 2187480} +{"current_steps": 3340, "total_steps": 33920, "loss": 0.4996, "lr": 9.84375e-06, "epoch": 1.9693396226415094, "percentage": 9.85, "elapsed_time": "0:06:10", "remaining_time": "0:56:29", "throughput": 5917.0, "total_tokens": 2190360} +{"current_steps": 3345, "total_steps": 33920, "loss": 0.6923, "lr": 9.858490566037736e-06, "epoch": 1.9722877358490565, "percentage": 9.86, "elapsed_time": "0:06:10", "remaining_time": "0:56:28", "throughput": 5917.51, "total_tokens": 2193784} +{"current_steps": 3350, "total_steps": 33920, "loss": 0.5737, "lr": 9.873231132075473e-06, "epoch": 1.9752358490566038, "percentage": 9.88, "elapsed_time": "0:06:11", "remaining_time": "0:56:27", "throughput": 5916.23, "total_tokens": 2196472} +{"current_steps": 3355, "total_steps": 33920, "loss": 0.4756, "lr": 9.887971698113208e-06, "epoch": 1.978183962264151, "percentage": 9.89, "elapsed_time": "0:06:11", "remaining_time": "0:56:26", "throughput": 5914.97, "total_tokens": 2199032} +{"current_steps": 3360, "total_steps": 33920, "loss": 0.5122, "lr": 9.902712264150945e-06, "epoch": 1.9811320754716981, "percentage": 9.91, "elapsed_time": "0:06:12", "remaining_time": "0:56:26", "throughput": 5914.21, "total_tokens": 2202200} +{"current_steps": 3365, "total_steps": 33920, "loss": 0.5698, "lr": 9.917452830188679e-06, "epoch": 1.9840801886792452, "percentage": 9.92, "elapsed_time": "0:06:12", "remaining_time": "0:56:26", "throughput": 5914.61, "total_tokens": 2205624} +{"current_steps": 3370, "total_steps": 33920, "loss": 0.4672, "lr": 9.932193396226416e-06, "epoch": 1.9870283018867925, "percentage": 9.94, "elapsed_time": "0:06:13", "remaining_time": "0:56:25", "throughput": 5913.44, "total_tokens": 2208344} +{"current_steps": 3375, "total_steps": 33920, "loss": 0.4384, "lr": 9.946933962264151e-06, "epoch": 1.9899764150943398, "percentage": 9.95, "elapsed_time": "0:06:14", "remaining_time": "0:56:25", "throughput": 5914.26, "total_tokens": 2212280} +{"current_steps": 3380, "total_steps": 33920, "loss": 0.4696, "lr": 9.961674528301888e-06, "epoch": 1.9929245283018868, "percentage": 9.96, "elapsed_time": "0:06:14", "remaining_time": "0:56:24", "throughput": 5913.5, "total_tokens": 2215160} +{"current_steps": 3385, "total_steps": 33920, "loss": 0.5678, "lr": 9.976415094339624e-06, "epoch": 1.9958726415094339, "percentage": 9.98, "elapsed_time": "0:06:15", "remaining_time": "0:56:23", "throughput": 5914.16, "total_tokens": 2218520} +{"current_steps": 3390, "total_steps": 33920, "loss": 0.5308, "lr": 9.991155660377359e-06, "epoch": 1.9988207547169812, "percentage": 9.99, "elapsed_time": "0:06:15", "remaining_time": "0:56:23", "throughput": 5914.62, "total_tokens": 2222232} +{"current_steps": 3392, "total_steps": 33920, "eval_loss": 0.5022701025009155, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:06:35", "remaining_time": "0:59:15", "throughput": 5626.91, "total_tokens": 2222792} +{"current_steps": 3395, "total_steps": 33920, "loss": 0.4309, "lr": 9.999999894098275e-06, "epoch": 2.0017688679245285, "percentage": 10.01, "elapsed_time": "0:06:37", "remaining_time": "0:59:37", "throughput": 5591.57, "total_tokens": 2224712} +{"current_steps": 3400, "total_steps": 33920, "loss": 0.4921, "lr": 9.99999870270391e-06, "epoch": 2.0047169811320753, "percentage": 10.02, "elapsed_time": "0:06:38", "remaining_time": "0:59:36", "throughput": 5590.68, "total_tokens": 2227720} +{"current_steps": 3405, "total_steps": 33920, "loss": 0.4471, "lr": 9.999996187538341e-06, "epoch": 2.0076650943396226, "percentage": 10.04, "elapsed_time": "0:06:39", "remaining_time": "0:59:36", "throughput": 5590.61, "total_tokens": 2230824} +{"current_steps": 3410, "total_steps": 33920, "loss": 0.5188, "lr": 9.999992348602233e-06, "epoch": 2.01061320754717, "percentage": 10.05, "elapsed_time": "0:06:39", "remaining_time": "0:59:34", "throughput": 5588.95, "total_tokens": 2233128} +{"current_steps": 3415, "total_steps": 33920, "loss": 0.4745, "lr": 9.999987185896598e-06, "epoch": 2.013561320754717, "percentage": 10.07, "elapsed_time": "0:06:40", "remaining_time": "0:59:34", "throughput": 5588.52, "total_tokens": 2236136} +{"current_steps": 3420, "total_steps": 33920, "loss": 0.4433, "lr": 9.99998069942281e-06, "epoch": 2.016509433962264, "percentage": 10.08, "elapsed_time": "0:06:40", "remaining_time": "0:59:33", "throughput": 5587.29, "total_tokens": 2238792} +{"current_steps": 3425, "total_steps": 33920, "loss": 0.5118, "lr": 9.999972889182583e-06, "epoch": 2.0194575471698113, "percentage": 10.1, "elapsed_time": "0:06:41", "remaining_time": "0:59:32", "throughput": 5587.82, "total_tokens": 2242344}