{ "best_metric": null, "best_model_checkpoint": null, "epoch": 8.91625684392371, "global_step": 640000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 3.8671875e-08, "loss": 5.4939, "step": 500 }, { "epoch": 0.01, "learning_rate": 7.773437500000001e-08, "loss": 5.2319, "step": 1000 }, { "epoch": 0.02, "learning_rate": 1.1679687500000002e-07, "loss": 4.9044, "step": 1500 }, { "epoch": 0.03, "learning_rate": 1.5585937500000003e-07, "loss": 4.6639, "step": 2000 }, { "epoch": 0.03, "learning_rate": 1.9492187500000003e-07, "loss": 4.4707, "step": 2500 }, { "epoch": 0.04, "learning_rate": 2.3398437500000002e-07, "loss": 4.3327, "step": 3000 }, { "epoch": 0.05, "learning_rate": 2.73046875e-07, "loss": 4.2155, "step": 3500 }, { "epoch": 0.06, "learning_rate": 3.12109375e-07, "loss": 4.1126, "step": 4000 }, { "epoch": 0.06, "learning_rate": 3.51171875e-07, "loss": 4.0397, "step": 4500 }, { "epoch": 0.07, "learning_rate": 3.9015625e-07, "loss": 3.9689, "step": 5000 }, { "epoch": 0.08, "learning_rate": 4.2921875e-07, "loss": 3.8489, "step": 5500 }, { "epoch": 0.08, "learning_rate": 4.6828125000000004e-07, "loss": 3.7863, "step": 6000 }, { "epoch": 0.09, "learning_rate": 5.0734375e-07, "loss": 3.7543, "step": 6500 }, { "epoch": 0.1, "learning_rate": 5.46328125e-07, "loss": 3.6828, "step": 7000 }, { "epoch": 0.1, "learning_rate": 5.853906250000001e-07, "loss": 3.6822, "step": 7500 }, { "epoch": 0.11, "learning_rate": 6.244531250000001e-07, "loss": 3.6322, "step": 8000 }, { "epoch": 0.12, "learning_rate": 6.635156250000001e-07, "loss": 3.6357, "step": 8500 }, { "epoch": 0.13, "learning_rate": 7.025000000000002e-07, "loss": 3.6196, "step": 9000 }, { "epoch": 0.13, "learning_rate": 7.415625000000002e-07, "loss": 3.6101, "step": 9500 }, { "epoch": 0.14, "learning_rate": 7.806250000000001e-07, "loss": 3.5769, "step": 10000 }, { "epoch": 0.15, "learning_rate": 8.196875000000001e-07, "loss": 3.567, "step": 10500 }, { "epoch": 0.15, "learning_rate": 8.587500000000001e-07, "loss": 3.558, "step": 11000 }, { "epoch": 0.16, "learning_rate": 8.978125000000001e-07, "loss": 3.519, "step": 11500 }, { "epoch": 0.17, "learning_rate": 9.367968750000001e-07, "loss": 3.5268, "step": 12000 }, { "epoch": 0.17, "learning_rate": 9.75859375e-07, "loss": 3.5111, "step": 12500 }, { "epoch": 0.18, "learning_rate": 1.014921875e-06, "loss": 3.4619, "step": 13000 }, { "epoch": 0.19, "learning_rate": 1.053984375e-06, "loss": 3.4759, "step": 13500 }, { "epoch": 0.2, "learning_rate": 1.093046875e-06, "loss": 3.4815, "step": 14000 }, { "epoch": 0.2, "learning_rate": 1.1321093750000002e-06, "loss": 3.4615, "step": 14500 }, { "epoch": 0.21, "learning_rate": 1.171171875e-06, "loss": 3.4654, "step": 15000 }, { "epoch": 0.22, "learning_rate": 1.2102343750000002e-06, "loss": 3.445, "step": 15500 }, { "epoch": 0.22, "learning_rate": 1.249296875e-06, "loss": 3.4391, "step": 16000 }, { "epoch": 0.23, "learning_rate": 1.2883593750000001e-06, "loss": 3.4293, "step": 16500 }, { "epoch": 0.24, "learning_rate": 1.32734375e-06, "loss": 3.4215, "step": 17000 }, { "epoch": 0.24, "learning_rate": 1.36640625e-06, "loss": 3.423, "step": 17500 }, { "epoch": 0.25, "learning_rate": 1.40546875e-06, "loss": 3.4263, "step": 18000 }, { "epoch": 0.26, "learning_rate": 1.44453125e-06, "loss": 3.3723, "step": 18500 }, { "epoch": 0.26, "learning_rate": 1.48359375e-06, "loss": 3.3856, "step": 19000 }, { "epoch": 0.27, "learning_rate": 1.5225781250000002e-06, "loss": 3.3836, "step": 19500 }, { "epoch": 0.28, "learning_rate": 1.561640625e-06, "loss": 3.3603, "step": 20000 }, { "epoch": 0.29, "learning_rate": 1.6007031250000002e-06, "loss": 3.3733, "step": 20500 }, { "epoch": 0.29, "learning_rate": 1.639765625e-06, "loss": 3.363, "step": 21000 }, { "epoch": 0.3, "learning_rate": 1.6788281250000002e-06, "loss": 3.3444, "step": 21500 }, { "epoch": 0.31, "learning_rate": 1.7178125000000001e-06, "loss": 3.3773, "step": 22000 }, { "epoch": 0.31, "learning_rate": 1.756875e-06, "loss": 3.345, "step": 22500 }, { "epoch": 0.32, "learning_rate": 1.7959375000000001e-06, "loss": 3.3316, "step": 23000 }, { "epoch": 0.33, "learning_rate": 1.8350000000000002e-06, "loss": 3.3584, "step": 23500 }, { "epoch": 0.33, "learning_rate": 1.873984375e-06, "loss": 3.3291, "step": 24000 }, { "epoch": 0.34, "learning_rate": 1.913046875e-06, "loss": 3.3173, "step": 24500 }, { "epoch": 0.35, "learning_rate": 1.952109375e-06, "loss": 3.3177, "step": 25000 }, { "epoch": 0.36, "learning_rate": 1.991171875e-06, "loss": 3.3234, "step": 25500 }, { "epoch": 0.36, "learning_rate": 2.0301562500000004e-06, "loss": 3.3226, "step": 26000 }, { "epoch": 0.37, "learning_rate": 2.06921875e-06, "loss": 3.3435, "step": 26500 }, { "epoch": 0.38, "learning_rate": 2.10828125e-06, "loss": 3.2945, "step": 27000 }, { "epoch": 0.38, "learning_rate": 2.1473437500000003e-06, "loss": 3.3019, "step": 27500 }, { "epoch": 0.39, "learning_rate": 2.186328125e-06, "loss": 3.2966, "step": 28000 }, { "epoch": 0.4, "learning_rate": 2.225390625e-06, "loss": 3.2959, "step": 28500 }, { "epoch": 0.4, "learning_rate": 2.264453125e-06, "loss": 3.3053, "step": 29000 }, { "epoch": 0.41, "learning_rate": 2.3035156250000003e-06, "loss": 3.3003, "step": 29500 }, { "epoch": 0.42, "learning_rate": 2.342578125e-06, "loss": 3.2698, "step": 30000 }, { "epoch": 0.42, "learning_rate": 2.3815625e-06, "loss": 3.266, "step": 30500 }, { "epoch": 0.43, "learning_rate": 2.4206250000000002e-06, "loss": 3.2624, "step": 31000 }, { "epoch": 0.44, "learning_rate": 2.4596875000000003e-06, "loss": 3.3084, "step": 31500 }, { "epoch": 0.45, "learning_rate": 2.4987500000000004e-06, "loss": 3.2526, "step": 32000 }, { "epoch": 0.45, "learning_rate": 2.5378125000000005e-06, "loss": 3.2417, "step": 32500 }, { "epoch": 0.46, "learning_rate": 2.576875e-06, "loss": 3.2902, "step": 33000 }, { "epoch": 0.47, "learning_rate": 2.6159375000000003e-06, "loss": 3.2761, "step": 33500 }, { "epoch": 0.47, "learning_rate": 2.6550000000000004e-06, "loss": 3.2615, "step": 34000 }, { "epoch": 0.48, "learning_rate": 2.6940625000000005e-06, "loss": 3.2692, "step": 34500 }, { "epoch": 0.49, "learning_rate": 2.733125e-06, "loss": 3.26, "step": 35000 }, { "epoch": 0.49, "learning_rate": 2.7721875000000003e-06, "loss": 3.2465, "step": 35500 }, { "epoch": 0.5, "learning_rate": 2.8112500000000004e-06, "loss": 3.2444, "step": 36000 }, { "epoch": 0.51, "learning_rate": 2.850234375e-06, "loss": 3.2418, "step": 36500 }, { "epoch": 0.52, "learning_rate": 2.889296875e-06, "loss": 3.2282, "step": 37000 }, { "epoch": 0.52, "learning_rate": 2.928359375e-06, "loss": 3.2487, "step": 37500 }, { "epoch": 0.53, "learning_rate": 2.967421875e-06, "loss": 3.2399, "step": 38000 }, { "epoch": 0.54, "learning_rate": 3.006484375e-06, "loss": 3.233, "step": 38500 }, { "epoch": 0.54, "learning_rate": 3.045546875e-06, "loss": 3.21, "step": 39000 }, { "epoch": 0.55, "learning_rate": 3.084609375e-06, "loss": 3.236, "step": 39500 }, { "epoch": 0.56, "learning_rate": 3.123671875e-06, "loss": 3.2359, "step": 40000 }, { "epoch": 0.56, "learning_rate": 3.162734375e-06, "loss": 3.2307, "step": 40500 }, { "epoch": 0.57, "learning_rate": 3.2017187500000002e-06, "loss": 3.2041, "step": 41000 }, { "epoch": 0.58, "learning_rate": 3.2407812500000003e-06, "loss": 3.2368, "step": 41500 }, { "epoch": 0.59, "learning_rate": 3.27984375e-06, "loss": 3.2156, "step": 42000 }, { "epoch": 0.59, "learning_rate": 3.31890625e-06, "loss": 3.2106, "step": 42500 }, { "epoch": 0.6, "learning_rate": 3.3579687500000002e-06, "loss": 3.2076, "step": 43000 }, { "epoch": 0.61, "learning_rate": 3.3970312500000003e-06, "loss": 3.2039, "step": 43500 }, { "epoch": 0.61, "learning_rate": 3.4360937500000004e-06, "loss": 3.2019, "step": 44000 }, { "epoch": 0.62, "learning_rate": 3.47515625e-06, "loss": 3.2138, "step": 44500 }, { "epoch": 0.63, "learning_rate": 3.5140625e-06, "loss": 3.1833, "step": 45000 }, { "epoch": 0.63, "learning_rate": 3.553125e-06, "loss": 3.2035, "step": 45500 }, { "epoch": 0.64, "learning_rate": 3.5921875e-06, "loss": 3.2006, "step": 46000 }, { "epoch": 0.65, "learning_rate": 3.63125e-06, "loss": 3.2059, "step": 46500 }, { "epoch": 0.65, "learning_rate": 3.6703125e-06, "loss": 3.1993, "step": 47000 }, { "epoch": 0.66, "learning_rate": 3.709375e-06, "loss": 3.2051, "step": 47500 }, { "epoch": 0.67, "learning_rate": 3.7484375e-06, "loss": 3.1814, "step": 48000 }, { "epoch": 0.68, "learning_rate": 3.7875e-06, "loss": 3.171, "step": 48500 }, { "epoch": 0.68, "learning_rate": 3.8265625e-06, "loss": 3.1862, "step": 49000 }, { "epoch": 0.69, "learning_rate": 3.865625e-06, "loss": 3.1927, "step": 49500 }, { "epoch": 0.7, "learning_rate": 3.9046875e-06, "loss": 3.1795, "step": 50000 }, { "epoch": 0.7, "learning_rate": 3.943671875000001e-06, "loss": 3.1788, "step": 50500 }, { "epoch": 0.71, "learning_rate": 3.982734375e-06, "loss": 3.1672, "step": 51000 }, { "epoch": 0.72, "learning_rate": 4.021796875e-06, "loss": 3.1824, "step": 51500 }, { "epoch": 0.72, "learning_rate": 4.060859375e-06, "loss": 3.1694, "step": 52000 }, { "epoch": 0.73, "learning_rate": 4.099921875e-06, "loss": 3.1756, "step": 52500 }, { "epoch": 0.74, "learning_rate": 4.138984375e-06, "loss": 3.1813, "step": 53000 }, { "epoch": 0.75, "learning_rate": 4.178046875e-06, "loss": 3.1725, "step": 53500 }, { "epoch": 0.75, "learning_rate": 4.2171093750000005e-06, "loss": 3.1677, "step": 54000 }, { "epoch": 0.76, "learning_rate": 4.25609375e-06, "loss": 3.1436, "step": 54500 }, { "epoch": 0.77, "learning_rate": 4.295078125e-06, "loss": 3.1474, "step": 55000 }, { "epoch": 0.77, "learning_rate": 4.334140625e-06, "loss": 3.1435, "step": 55500 }, { "epoch": 0.78, "learning_rate": 4.373203125e-06, "loss": 3.1423, "step": 56000 }, { "epoch": 0.79, "learning_rate": 4.412265625e-06, "loss": 3.1462, "step": 56500 }, { "epoch": 0.79, "learning_rate": 4.45125e-06, "loss": 3.1284, "step": 57000 }, { "epoch": 0.8, "learning_rate": 4.4903125e-06, "loss": 3.136, "step": 57500 }, { "epoch": 0.81, "learning_rate": 4.529375e-06, "loss": 3.143, "step": 58000 }, { "epoch": 0.82, "learning_rate": 4.5684375e-06, "loss": 3.1339, "step": 58500 }, { "epoch": 0.82, "learning_rate": 4.6075e-06, "loss": 3.1646, "step": 59000 }, { "epoch": 0.83, "learning_rate": 4.6465625000000005e-06, "loss": 3.1391, "step": 59500 }, { "epoch": 0.84, "learning_rate": 4.6856250000000006e-06, "loss": 3.1341, "step": 60000 }, { "epoch": 0.84, "learning_rate": 4.724687500000001e-06, "loss": 3.142, "step": 60500 }, { "epoch": 0.85, "learning_rate": 4.76375e-06, "loss": 3.1404, "step": 61000 }, { "epoch": 0.86, "learning_rate": 4.8028125e-06, "loss": 3.1536, "step": 61500 }, { "epoch": 0.86, "learning_rate": 4.841875e-06, "loss": 3.1432, "step": 62000 }, { "epoch": 0.87, "learning_rate": 4.88078125e-06, "loss": 3.1422, "step": 62500 }, { "epoch": 0.88, "learning_rate": 4.91984375e-06, "loss": 3.1566, "step": 63000 }, { "epoch": 0.88, "learning_rate": 4.9589062500000005e-06, "loss": 3.1406, "step": 63500 }, { "epoch": 0.89, "learning_rate": 4.99796875e-06, "loss": 3.1497, "step": 64000 }, { "epoch": 0.9, "learning_rate": 4.995967708333334e-06, "loss": 3.129, "step": 64500 }, { "epoch": 0.91, "learning_rate": 4.991714236111112e-06, "loss": 3.1202, "step": 65000 }, { "epoch": 0.91, "learning_rate": 4.987460763888889e-06, "loss": 3.109, "step": 65500 }, { "epoch": 0.92, "learning_rate": 4.983207291666667e-06, "loss": 3.1332, "step": 66000 }, { "epoch": 0.93, "learning_rate": 4.9789538194444445e-06, "loss": 3.1237, "step": 66500 }, { "epoch": 0.93, "learning_rate": 4.9747088541666666e-06, "loss": 3.1173, "step": 67000 }, { "epoch": 0.94, "learning_rate": 4.970455381944445e-06, "loss": 3.1363, "step": 67500 }, { "epoch": 0.95, "learning_rate": 4.966201909722223e-06, "loss": 3.086, "step": 68000 }, { "epoch": 0.95, "learning_rate": 4.9619484375e-06, "loss": 3.1094, "step": 68500 }, { "epoch": 0.96, "learning_rate": 4.957694965277778e-06, "loss": 3.1297, "step": 69000 }, { "epoch": 0.97, "learning_rate": 4.953450000000001e-06, "loss": 3.1028, "step": 69500 }, { "epoch": 0.98, "learning_rate": 4.9491965277777785e-06, "loss": 3.1004, "step": 70000 }, { "epoch": 0.98, "learning_rate": 4.944943055555556e-06, "loss": 3.1037, "step": 70500 }, { "epoch": 0.99, "learning_rate": 4.940689583333334e-06, "loss": 3.1285, "step": 71000 }, { "epoch": 1.0, "learning_rate": 4.936436111111111e-06, "loss": 3.1002, "step": 71500 }, { "epoch": 1.0, "learning_rate": 4.932191145833334e-06, "loss": 3.1432, "step": 72000 }, { "epoch": 1.01, "learning_rate": 4.927937673611112e-06, "loss": 3.0873, "step": 72500 }, { "epoch": 1.02, "learning_rate": 4.9236842013888895e-06, "loss": 3.0851, "step": 73000 }, { "epoch": 1.02, "learning_rate": 4.919430729166667e-06, "loss": 3.0814, "step": 73500 }, { "epoch": 1.03, "learning_rate": 4.915177256944445e-06, "loss": 3.0963, "step": 74000 }, { "epoch": 1.04, "learning_rate": 4.910923784722222e-06, "loss": 3.0701, "step": 74500 }, { "epoch": 1.04, "learning_rate": 4.9066788194444444e-06, "loss": 3.0736, "step": 75000 }, { "epoch": 1.05, "learning_rate": 4.902425347222223e-06, "loss": 3.1015, "step": 75500 }, { "epoch": 1.06, "learning_rate": 4.8981718750000005e-06, "loss": 3.0794, "step": 76000 }, { "epoch": 1.07, "learning_rate": 4.893918402777778e-06, "loss": 3.0744, "step": 76500 }, { "epoch": 1.07, "learning_rate": 4.889664930555556e-06, "loss": 3.103, "step": 77000 }, { "epoch": 1.08, "learning_rate": 4.885428472222223e-06, "loss": 3.0727, "step": 77500 }, { "epoch": 1.09, "learning_rate": 4.881175000000001e-06, "loss": 3.0918, "step": 78000 }, { "epoch": 1.09, "learning_rate": 4.876921527777778e-06, "loss": 3.0509, "step": 78500 }, { "epoch": 1.1, "learning_rate": 4.8726765625000004e-06, "loss": 3.0727, "step": 79000 }, { "epoch": 1.11, "learning_rate": 4.868423090277778e-06, "loss": 3.0902, "step": 79500 }, { "epoch": 1.11, "learning_rate": 4.864169618055556e-06, "loss": 3.0614, "step": 80000 }, { "epoch": 1.12, "learning_rate": 4.859916145833333e-06, "loss": 3.0629, "step": 80500 }, { "epoch": 1.13, "learning_rate": 4.855662673611111e-06, "loss": 3.057, "step": 81000 }, { "epoch": 1.14, "learning_rate": 4.851426215277778e-06, "loss": 3.0859, "step": 81500 }, { "epoch": 1.14, "learning_rate": 4.847172743055556e-06, "loss": 3.0461, "step": 82000 }, { "epoch": 1.15, "learning_rate": 4.8429192708333335e-06, "loss": 3.0678, "step": 82500 }, { "epoch": 1.16, "learning_rate": 4.838665798611112e-06, "loss": 3.0757, "step": 83000 }, { "epoch": 1.16, "learning_rate": 4.83441232638889e-06, "loss": 3.0351, "step": 83500 }, { "epoch": 1.17, "learning_rate": 4.830158854166667e-06, "loss": 3.0538, "step": 84000 }, { "epoch": 1.18, "learning_rate": 4.825905381944445e-06, "loss": 3.0898, "step": 84500 }, { "epoch": 1.18, "learning_rate": 4.8216519097222225e-06, "loss": 3.0555, "step": 85000 }, { "epoch": 1.19, "learning_rate": 4.8173984375e-06, "loss": 3.0672, "step": 85500 }, { "epoch": 1.2, "learning_rate": 4.813144965277779e-06, "loss": 3.0675, "step": 86000 }, { "epoch": 1.21, "learning_rate": 4.808891493055556e-06, "loss": 3.0551, "step": 86500 }, { "epoch": 1.21, "learning_rate": 4.804638020833334e-06, "loss": 3.0556, "step": 87000 }, { "epoch": 1.22, "learning_rate": 4.8003845486111115e-06, "loss": 3.0694, "step": 87500 }, { "epoch": 1.23, "learning_rate": 4.796131076388889e-06, "loss": 3.0639, "step": 88000 }, { "epoch": 1.23, "learning_rate": 4.791877604166667e-06, "loss": 3.0825, "step": 88500 }, { "epoch": 1.24, "learning_rate": 4.787624131944444e-06, "loss": 3.064, "step": 89000 }, { "epoch": 1.25, "learning_rate": 4.783370659722222e-06, "loss": 3.0471, "step": 89500 }, { "epoch": 1.25, "learning_rate": 4.7791171875000005e-06, "loss": 3.0531, "step": 90000 }, { "epoch": 1.26, "learning_rate": 4.774863715277778e-06, "loss": 3.0496, "step": 90500 }, { "epoch": 1.27, "learning_rate": 4.77061875e-06, "loss": 3.0453, "step": 91000 }, { "epoch": 1.27, "learning_rate": 4.766365277777779e-06, "loss": 3.0416, "step": 91500 }, { "epoch": 1.28, "learning_rate": 4.762111805555556e-06, "loss": 3.044, "step": 92000 }, { "epoch": 1.29, "learning_rate": 4.757858333333334e-06, "loss": 3.0538, "step": 92500 }, { "epoch": 1.3, "learning_rate": 4.7536048611111115e-06, "loss": 3.0415, "step": 93000 }, { "epoch": 1.3, "learning_rate": 4.749351388888889e-06, "loss": 3.0388, "step": 93500 }, { "epoch": 1.31, "learning_rate": 4.745106423611111e-06, "loss": 3.0478, "step": 94000 }, { "epoch": 1.32, "learning_rate": 4.74085295138889e-06, "loss": 3.0314, "step": 94500 }, { "epoch": 1.32, "learning_rate": 4.736599479166667e-06, "loss": 3.068, "step": 95000 }, { "epoch": 1.33, "learning_rate": 4.732346006944445e-06, "loss": 3.0356, "step": 95500 }, { "epoch": 1.34, "learning_rate": 4.7280925347222226e-06, "loss": 3.0355, "step": 96000 }, { "epoch": 1.34, "learning_rate": 4.7238390625e-06, "loss": 3.0213, "step": 96500 }, { "epoch": 1.35, "learning_rate": 4.719585590277778e-06, "loss": 3.0633, "step": 97000 }, { "epoch": 1.36, "learning_rate": 4.7153321180555554e-06, "loss": 3.0378, "step": 97500 }, { "epoch": 1.37, "learning_rate": 4.711087152777778e-06, "loss": 3.0534, "step": 98000 }, { "epoch": 1.37, "learning_rate": 4.706833680555556e-06, "loss": 3.0416, "step": 98500 }, { "epoch": 1.38, "learning_rate": 4.702588715277778e-06, "loss": 3.0167, "step": 99000 }, { "epoch": 1.39, "learning_rate": 4.6983352430555565e-06, "loss": 3.0271, "step": 99500 }, { "epoch": 1.39, "learning_rate": 4.694081770833334e-06, "loss": 3.0401, "step": 100000 }, { "epoch": 1.39, "eval_gen_len": 19.9936, "eval_loss": 2.870497703552246, "eval_rouge1": 0.2979, "eval_rouge2": 0.1743, "eval_rougeL": 0.2516, "eval_rougeLsum": 0.283, "eval_runtime": 897.9111, "eval_samples_per_second": 14.888, "eval_steps_per_second": 3.722, "step": 100000 }, { "epoch": 1.4, "learning_rate": 4.689828298611112e-06, "loss": 3.0068, "step": 100500 }, { "epoch": 1.41, "learning_rate": 4.685574826388889e-06, "loss": 3.0365, "step": 101000 }, { "epoch": 1.41, "learning_rate": 4.681321354166667e-06, "loss": 3.0628, "step": 101500 }, { "epoch": 1.42, "learning_rate": 4.6770848958333335e-06, "loss": 3.079, "step": 102000 }, { "epoch": 1.43, "learning_rate": 4.672831423611111e-06, "loss": 3.0425, "step": 102500 }, { "epoch": 1.43, "learning_rate": 4.668577951388889e-06, "loss": 3.0297, "step": 103000 }, { "epoch": 1.44, "learning_rate": 4.664324479166667e-06, "loss": 3.017, "step": 103500 }, { "epoch": 1.45, "learning_rate": 4.660071006944445e-06, "loss": 3.0374, "step": 104000 }, { "epoch": 1.46, "learning_rate": 4.6558175347222225e-06, "loss": 3.0665, "step": 104500 }, { "epoch": 1.46, "learning_rate": 4.6515640625e-06, "loss": 3.0246, "step": 105000 }, { "epoch": 1.47, "learning_rate": 4.647310590277778e-06, "loss": 3.0423, "step": 105500 }, { "epoch": 1.48, "learning_rate": 4.643057118055556e-06, "loss": 3.0181, "step": 106000 }, { "epoch": 1.48, "learning_rate": 4.638803645833334e-06, "loss": 3.0335, "step": 106500 }, { "epoch": 1.49, "learning_rate": 4.6345501736111115e-06, "loss": 3.0345, "step": 107000 }, { "epoch": 1.5, "learning_rate": 4.630296701388889e-06, "loss": 3.0378, "step": 107500 }, { "epoch": 1.5, "learning_rate": 4.626051736111112e-06, "loss": 3.033, "step": 108000 }, { "epoch": 1.51, "learning_rate": 4.62179826388889e-06, "loss": 3.0395, "step": 108500 }, { "epoch": 1.52, "learning_rate": 4.617544791666667e-06, "loss": 3.0256, "step": 109000 }, { "epoch": 1.53, "learning_rate": 4.613291319444445e-06, "loss": 3.0061, "step": 109500 }, { "epoch": 1.53, "learning_rate": 4.6090378472222225e-06, "loss": 3.0321, "step": 110000 }, { "epoch": 1.54, "learning_rate": 4.604784375e-06, "loss": 3.0228, "step": 110500 }, { "epoch": 1.55, "learning_rate": 4.600530902777778e-06, "loss": 3.0108, "step": 111000 }, { "epoch": 1.55, "learning_rate": 4.596277430555555e-06, "loss": 3.0147, "step": 111500 }, { "epoch": 1.56, "learning_rate": 4.592032465277778e-06, "loss": 3.0105, "step": 112000 }, { "epoch": 1.57, "learning_rate": 4.5877875e-06, "loss": 3.0213, "step": 112500 }, { "epoch": 1.57, "learning_rate": 4.583534027777778e-06, "loss": 3.0243, "step": 113000 }, { "epoch": 1.58, "learning_rate": 4.579280555555556e-06, "loss": 3.0116, "step": 113500 }, { "epoch": 1.59, "learning_rate": 4.575027083333334e-06, "loss": 2.9976, "step": 114000 }, { "epoch": 1.6, "learning_rate": 4.570782118055556e-06, "loss": 3.0147, "step": 114500 }, { "epoch": 1.6, "learning_rate": 4.566528645833334e-06, "loss": 3.0202, "step": 115000 }, { "epoch": 1.61, "learning_rate": 4.562275173611111e-06, "loss": 3.0112, "step": 115500 }, { "epoch": 1.62, "learning_rate": 4.558021701388889e-06, "loss": 3.0115, "step": 116000 }, { "epoch": 1.62, "learning_rate": 4.553768229166667e-06, "loss": 3.03, "step": 116500 }, { "epoch": 1.63, "learning_rate": 4.549523263888889e-06, "loss": 3.0344, "step": 117000 }, { "epoch": 1.64, "learning_rate": 4.545278298611112e-06, "loss": 3.0194, "step": 117500 }, { "epoch": 1.64, "learning_rate": 4.541024826388889e-06, "loss": 3.023, "step": 118000 }, { "epoch": 1.65, "learning_rate": 4.536771354166667e-06, "loss": 3.017, "step": 118500 }, { "epoch": 1.66, "learning_rate": 4.5325178819444445e-06, "loss": 3.0292, "step": 119000 }, { "epoch": 1.66, "learning_rate": 4.528264409722223e-06, "loss": 3.0245, "step": 119500 }, { "epoch": 1.67, "learning_rate": 4.5240109375000006e-06, "loss": 3.0291, "step": 120000 }, { "epoch": 1.68, "learning_rate": 4.519765972222223e-06, "loss": 3.028, "step": 120500 }, { "epoch": 1.69, "learning_rate": 4.5155125e-06, "loss": 3.0066, "step": 121000 }, { "epoch": 1.69, "learning_rate": 4.511259027777779e-06, "loss": 3.0181, "step": 121500 }, { "epoch": 1.7, "learning_rate": 4.507005555555556e-06, "loss": 3.0025, "step": 122000 }, { "epoch": 1.71, "learning_rate": 4.502752083333334e-06, "loss": 3.016, "step": 122500 }, { "epoch": 1.71, "learning_rate": 4.498498611111112e-06, "loss": 2.994, "step": 123000 }, { "epoch": 1.72, "learning_rate": 4.494245138888889e-06, "loss": 3.0244, "step": 123500 }, { "epoch": 1.73, "learning_rate": 4.489991666666667e-06, "loss": 2.9984, "step": 124000 }, { "epoch": 1.73, "learning_rate": 4.4857381944444445e-06, "loss": 3.0111, "step": 124500 }, { "epoch": 1.74, "learning_rate": 4.4814932291666665e-06, "loss": 3.015, "step": 125000 }, { "epoch": 1.75, "learning_rate": 4.4772482638888894e-06, "loss": 3.0108, "step": 125500 }, { "epoch": 1.76, "learning_rate": 4.472994791666667e-06, "loss": 2.9978, "step": 126000 }, { "epoch": 1.76, "learning_rate": 4.468741319444445e-06, "loss": 3.0186, "step": 126500 }, { "epoch": 1.77, "learning_rate": 4.464487847222222e-06, "loss": 3.0223, "step": 127000 }, { "epoch": 1.78, "learning_rate": 4.460234375000001e-06, "loss": 3.0114, "step": 127500 }, { "epoch": 1.78, "learning_rate": 4.4559809027777784e-06, "loss": 3.0063, "step": 128000 }, { "epoch": 1.79, "learning_rate": 4.451727430555556e-06, "loss": 3.0093, "step": 128500 }, { "epoch": 1.8, "learning_rate": 4.4474909722222225e-06, "loss": 3.0003, "step": 129000 }, { "epoch": 1.8, "learning_rate": 4.4432375e-06, "loss": 3.0186, "step": 129500 }, { "epoch": 1.81, "learning_rate": 4.438984027777778e-06, "loss": 3.0056, "step": 130000 }, { "epoch": 1.82, "learning_rate": 4.434730555555555e-06, "loss": 3.0065, "step": 130500 }, { "epoch": 1.83, "learning_rate": 4.430477083333334e-06, "loss": 3.0324, "step": 131000 }, { "epoch": 1.83, "learning_rate": 4.4262236111111115e-06, "loss": 2.9988, "step": 131500 }, { "epoch": 1.84, "learning_rate": 4.421970138888889e-06, "loss": 3.0163, "step": 132000 }, { "epoch": 1.85, "learning_rate": 4.417716666666667e-06, "loss": 2.9936, "step": 132500 }, { "epoch": 1.85, "learning_rate": 4.413463194444444e-06, "loss": 3.0139, "step": 133000 }, { "epoch": 1.86, "learning_rate": 4.409209722222222e-06, "loss": 2.982, "step": 133500 }, { "epoch": 1.87, "learning_rate": 4.4049562500000005e-06, "loss": 2.9908, "step": 134000 }, { "epoch": 1.87, "learning_rate": 4.400702777777778e-06, "loss": 3.0003, "step": 134500 }, { "epoch": 1.88, "learning_rate": 4.396449305555556e-06, "loss": 2.9924, "step": 135000 }, { "epoch": 1.89, "learning_rate": 4.392195833333334e-06, "loss": 3.0235, "step": 135500 }, { "epoch": 1.89, "learning_rate": 4.387950868055556e-06, "loss": 2.9979, "step": 136000 }, { "epoch": 1.9, "learning_rate": 4.383697395833334e-06, "loss": 2.9846, "step": 136500 }, { "epoch": 1.91, "learning_rate": 4.3794439236111115e-06, "loss": 2.9916, "step": 137000 }, { "epoch": 1.92, "learning_rate": 4.375190451388889e-06, "loss": 2.996, "step": 137500 }, { "epoch": 1.92, "learning_rate": 4.370945486111111e-06, "loss": 2.9737, "step": 138000 }, { "epoch": 1.93, "learning_rate": 4.366692013888889e-06, "loss": 3.003, "step": 138500 }, { "epoch": 1.94, "learning_rate": 4.3624385416666665e-06, "loss": 2.9837, "step": 139000 }, { "epoch": 1.94, "learning_rate": 4.358185069444445e-06, "loss": 3.0183, "step": 139500 }, { "epoch": 1.95, "learning_rate": 4.353931597222223e-06, "loss": 3.0169, "step": 140000 }, { "epoch": 1.96, "learning_rate": 4.349678125e-06, "loss": 2.9834, "step": 140500 }, { "epoch": 1.96, "learning_rate": 4.345424652777778e-06, "loss": 3.0022, "step": 141000 }, { "epoch": 1.97, "learning_rate": 4.3411711805555555e-06, "loss": 2.9879, "step": 141500 }, { "epoch": 1.98, "learning_rate": 4.336926215277778e-06, "loss": 2.9919, "step": 142000 }, { "epoch": 1.99, "learning_rate": 4.332672743055556e-06, "loss": 2.9892, "step": 142500 }, { "epoch": 1.99, "learning_rate": 4.328419270833334e-06, "loss": 2.9888, "step": 143000 }, { "epoch": 2.0, "learning_rate": 4.324165798611112e-06, "loss": 2.9873, "step": 143500 }, { "epoch": 2.01, "learning_rate": 4.319920833333334e-06, "loss": 2.9425, "step": 144000 }, { "epoch": 2.01, "learning_rate": 4.315667361111112e-06, "loss": 2.9582, "step": 144500 }, { "epoch": 2.02, "learning_rate": 4.311413888888889e-06, "loss": 2.9654, "step": 145000 }, { "epoch": 2.03, "learning_rate": 4.307160416666667e-06, "loss": 2.9714, "step": 145500 }, { "epoch": 2.03, "learning_rate": 4.302906944444445e-06, "loss": 2.9586, "step": 146000 }, { "epoch": 2.04, "learning_rate": 4.298653472222222e-06, "loss": 2.9601, "step": 146500 }, { "epoch": 2.05, "learning_rate": 4.2944e-06, "loss": 2.9509, "step": 147000 }, { "epoch": 2.05, "learning_rate": 4.290155034722223e-06, "loss": 2.9519, "step": 147500 }, { "epoch": 2.06, "learning_rate": 4.2859015625000004e-06, "loss": 2.9587, "step": 148000 }, { "epoch": 2.07, "learning_rate": 4.281648090277778e-06, "loss": 2.9801, "step": 148500 }, { "epoch": 2.08, "learning_rate": 4.277394618055556e-06, "loss": 2.9748, "step": 149000 }, { "epoch": 2.08, "learning_rate": 4.273141145833333e-06, "loss": 2.9592, "step": 149500 }, { "epoch": 2.09, "learning_rate": 4.268887673611112e-06, "loss": 2.9538, "step": 150000 }, { "epoch": 2.1, "learning_rate": 4.2646342013888894e-06, "loss": 2.9744, "step": 150500 }, { "epoch": 2.1, "learning_rate": 4.260380729166667e-06, "loss": 2.9744, "step": 151000 }, { "epoch": 2.11, "learning_rate": 4.256135763888889e-06, "loss": 2.9415, "step": 151500 }, { "epoch": 2.12, "learning_rate": 4.251882291666668e-06, "loss": 2.9657, "step": 152000 }, { "epoch": 2.12, "learning_rate": 4.247628819444445e-06, "loss": 2.964, "step": 152500 }, { "epoch": 2.13, "learning_rate": 4.243375347222223e-06, "loss": 2.9661, "step": 153000 }, { "epoch": 2.14, "learning_rate": 4.239130381944445e-06, "loss": 2.9604, "step": 153500 }, { "epoch": 2.15, "learning_rate": 4.2348769097222225e-06, "loss": 2.9375, "step": 154000 }, { "epoch": 2.15, "learning_rate": 4.2306319444444446e-06, "loss": 2.958, "step": 154500 }, { "epoch": 2.16, "learning_rate": 4.226378472222222e-06, "loss": 2.9596, "step": 155000 }, { "epoch": 2.17, "learning_rate": 4.222125000000001e-06, "loss": 2.9572, "step": 155500 }, { "epoch": 2.17, "learning_rate": 4.217871527777778e-06, "loss": 2.9557, "step": 156000 }, { "epoch": 2.18, "learning_rate": 4.213618055555556e-06, "loss": 2.9778, "step": 156500 }, { "epoch": 2.19, "learning_rate": 4.2093645833333336e-06, "loss": 2.9465, "step": 157000 }, { "epoch": 2.19, "learning_rate": 4.205111111111111e-06, "loss": 2.9641, "step": 157500 }, { "epoch": 2.2, "learning_rate": 4.20085763888889e-06, "loss": 2.9576, "step": 158000 }, { "epoch": 2.21, "learning_rate": 4.196612673611112e-06, "loss": 2.9681, "step": 158500 }, { "epoch": 2.22, "learning_rate": 4.192359201388889e-06, "loss": 2.9622, "step": 159000 }, { "epoch": 2.22, "learning_rate": 4.188105729166667e-06, "loss": 2.9608, "step": 159500 }, { "epoch": 2.23, "learning_rate": 4.183860763888889e-06, "loss": 2.9529, "step": 160000 }, { "epoch": 2.24, "learning_rate": 4.179607291666667e-06, "loss": 2.9539, "step": 160500 }, { "epoch": 2.24, "learning_rate": 4.175353819444444e-06, "loss": 2.9651, "step": 161000 }, { "epoch": 2.25, "learning_rate": 4.171100347222222e-06, "loss": 2.943, "step": 161500 }, { "epoch": 2.26, "learning_rate": 4.166846875e-06, "loss": 2.9517, "step": 162000 }, { "epoch": 2.26, "learning_rate": 4.162593402777778e-06, "loss": 2.9447, "step": 162500 }, { "epoch": 2.27, "learning_rate": 4.1583484375e-06, "loss": 2.9637, "step": 163000 }, { "epoch": 2.28, "learning_rate": 4.1540949652777785e-06, "loss": 2.9437, "step": 163500 }, { "epoch": 2.28, "learning_rate": 4.149841493055556e-06, "loss": 2.9462, "step": 164000 }, { "epoch": 2.29, "learning_rate": 4.145588020833334e-06, "loss": 2.9605, "step": 164500 }, { "epoch": 2.3, "learning_rate": 4.141334548611111e-06, "loss": 2.953, "step": 165000 }, { "epoch": 2.31, "learning_rate": 4.137081076388889e-06, "loss": 2.9702, "step": 165500 }, { "epoch": 2.31, "learning_rate": 4.1328276041666675e-06, "loss": 2.9636, "step": 166000 }, { "epoch": 2.32, "learning_rate": 4.128574131944445e-06, "loss": 2.9564, "step": 166500 }, { "epoch": 2.33, "learning_rate": 4.124329166666667e-06, "loss": 2.9356, "step": 167000 }, { "epoch": 2.33, "learning_rate": 4.120075694444445e-06, "loss": 2.9542, "step": 167500 }, { "epoch": 2.34, "learning_rate": 4.1158222222222225e-06, "loss": 2.9377, "step": 168000 }, { "epoch": 2.35, "learning_rate": 4.11156875e-06, "loss": 2.9439, "step": 168500 }, { "epoch": 2.35, "learning_rate": 4.107323784722222e-06, "loss": 2.9107, "step": 169000 }, { "epoch": 2.36, "learning_rate": 4.1030703125e-06, "loss": 2.9849, "step": 169500 }, { "epoch": 2.37, "learning_rate": 4.098816840277778e-06, "loss": 2.9479, "step": 170000 }, { "epoch": 2.38, "learning_rate": 4.094563368055556e-06, "loss": 2.9459, "step": 170500 }, { "epoch": 2.38, "learning_rate": 4.090318402777778e-06, "loss": 2.9558, "step": 171000 }, { "epoch": 2.39, "learning_rate": 4.086064930555556e-06, "loss": 2.9599, "step": 171500 }, { "epoch": 2.4, "learning_rate": 4.081811458333334e-06, "loss": 2.9456, "step": 172000 }, { "epoch": 2.4, "learning_rate": 4.077566493055556e-06, "loss": 2.943, "step": 172500 }, { "epoch": 2.41, "learning_rate": 4.073313020833334e-06, "loss": 2.9403, "step": 173000 }, { "epoch": 2.42, "learning_rate": 4.069059548611111e-06, "loss": 2.9553, "step": 173500 }, { "epoch": 2.42, "learning_rate": 4.064806076388889e-06, "loss": 2.9188, "step": 174000 }, { "epoch": 2.43, "learning_rate": 4.060552604166667e-06, "loss": 2.943, "step": 174500 }, { "epoch": 2.44, "learning_rate": 4.056299131944444e-06, "loss": 2.9477, "step": 175000 }, { "epoch": 2.45, "learning_rate": 4.052045659722223e-06, "loss": 2.9366, "step": 175500 }, { "epoch": 2.45, "learning_rate": 4.0477921875e-06, "loss": 2.923, "step": 176000 }, { "epoch": 2.46, "learning_rate": 4.043547222222222e-06, "loss": 2.9505, "step": 176500 }, { "epoch": 2.47, "learning_rate": 4.03929375e-06, "loss": 2.9468, "step": 177000 }, { "epoch": 2.47, "learning_rate": 4.035040277777778e-06, "loss": 2.9394, "step": 177500 }, { "epoch": 2.48, "learning_rate": 4.030786805555556e-06, "loss": 2.9291, "step": 178000 }, { "epoch": 2.49, "learning_rate": 4.026541840277778e-06, "loss": 2.935, "step": 178500 }, { "epoch": 2.49, "learning_rate": 4.022288368055556e-06, "loss": 2.9323, "step": 179000 }, { "epoch": 2.5, "learning_rate": 4.018034895833334e-06, "loss": 2.9527, "step": 179500 }, { "epoch": 2.51, "learning_rate": 4.013781423611112e-06, "loss": 2.9679, "step": 180000 }, { "epoch": 2.51, "learning_rate": 4.0095279513888895e-06, "loss": 2.9491, "step": 180500 }, { "epoch": 2.52, "learning_rate": 4.0052829861111116e-06, "loss": 2.9549, "step": 181000 }, { "epoch": 2.53, "learning_rate": 4.001038020833334e-06, "loss": 2.9441, "step": 181500 }, { "epoch": 2.54, "learning_rate": 3.996784548611111e-06, "loss": 2.9467, "step": 182000 }, { "epoch": 2.54, "learning_rate": 3.992531076388889e-06, "loss": 2.9639, "step": 182500 }, { "epoch": 2.55, "learning_rate": 3.9882776041666665e-06, "loss": 2.9197, "step": 183000 }, { "epoch": 2.56, "learning_rate": 3.984024131944445e-06, "loss": 2.9623, "step": 183500 }, { "epoch": 2.56, "learning_rate": 3.979770659722223e-06, "loss": 2.9327, "step": 184000 }, { "epoch": 2.57, "learning_rate": 3.9755171875e-06, "loss": 2.9428, "step": 184500 }, { "epoch": 2.58, "learning_rate": 3.971263715277778e-06, "loss": 2.9664, "step": 185000 }, { "epoch": 2.58, "learning_rate": 3.9670102430555555e-06, "loss": 2.9504, "step": 185500 }, { "epoch": 2.59, "learning_rate": 3.962756770833334e-06, "loss": 2.9371, "step": 186000 }, { "epoch": 2.6, "learning_rate": 3.958511805555556e-06, "loss": 2.9371, "step": 186500 }, { "epoch": 2.61, "learning_rate": 3.954266840277778e-06, "loss": 2.9273, "step": 187000 }, { "epoch": 2.61, "learning_rate": 3.950013368055556e-06, "loss": 2.9214, "step": 187500 }, { "epoch": 2.62, "learning_rate": 3.945759895833333e-06, "loss": 2.9627, "step": 188000 }, { "epoch": 2.63, "learning_rate": 3.941506423611111e-06, "loss": 2.9431, "step": 188500 }, { "epoch": 2.63, "learning_rate": 3.937252951388889e-06, "loss": 2.9278, "step": 189000 }, { "epoch": 2.64, "learning_rate": 3.932999479166667e-06, "loss": 2.9434, "step": 189500 }, { "epoch": 2.65, "learning_rate": 3.928746006944445e-06, "loss": 2.9549, "step": 190000 }, { "epoch": 2.65, "learning_rate": 3.924492534722222e-06, "loss": 2.9484, "step": 190500 }, { "epoch": 2.66, "learning_rate": 3.9202390625e-06, "loss": 2.9455, "step": 191000 }, { "epoch": 2.67, "learning_rate": 3.915985590277778e-06, "loss": 2.9293, "step": 191500 }, { "epoch": 2.67, "learning_rate": 3.911732118055556e-06, "loss": 2.9319, "step": 192000 }, { "epoch": 2.68, "learning_rate": 3.907487152777778e-06, "loss": 2.9432, "step": 192500 }, { "epoch": 2.69, "learning_rate": 3.903233680555556e-06, "loss": 2.9401, "step": 193000 }, { "epoch": 2.7, "learning_rate": 3.898980208333333e-06, "loss": 2.9472, "step": 193500 }, { "epoch": 2.7, "learning_rate": 3.894726736111112e-06, "loss": 2.9551, "step": 194000 }, { "epoch": 2.71, "learning_rate": 3.8904732638888895e-06, "loss": 2.961, "step": 194500 }, { "epoch": 2.72, "learning_rate": 3.886219791666667e-06, "loss": 2.9481, "step": 195000 }, { "epoch": 2.72, "learning_rate": 3.881966319444445e-06, "loss": 2.9435, "step": 195500 }, { "epoch": 2.73, "learning_rate": 3.877712847222223e-06, "loss": 2.9746, "step": 196000 }, { "epoch": 2.74, "learning_rate": 3.873467881944445e-06, "loss": 2.9425, "step": 196500 }, { "epoch": 2.74, "learning_rate": 3.869214409722223e-06, "loss": 2.9271, "step": 197000 }, { "epoch": 2.75, "learning_rate": 3.8649609375000005e-06, "loss": 2.9317, "step": 197500 }, { "epoch": 2.76, "learning_rate": 3.860707465277778e-06, "loss": 2.9337, "step": 198000 }, { "epoch": 2.77, "learning_rate": 3.8564625e-06, "loss": 2.9324, "step": 198500 }, { "epoch": 2.77, "learning_rate": 3.852209027777778e-06, "loss": 2.9317, "step": 199000 }, { "epoch": 2.78, "learning_rate": 3.847955555555556e-06, "loss": 2.9405, "step": 199500 }, { "epoch": 2.79, "learning_rate": 3.843702083333334e-06, "loss": 2.9489, "step": 200000 }, { "epoch": 2.79, "eval_gen_len": 19.9976, "eval_loss": 2.804373025894165, "eval_rouge1": 0.2997, "eval_rouge2": 0.1765, "eval_rougeL": 0.2536, "eval_rougeLsum": 0.285, "eval_runtime": 887.4822, "eval_samples_per_second": 15.063, "eval_steps_per_second": 3.766, "step": 200000 }, { "epoch": 2.79, "learning_rate": 3.839457118055556e-06, "loss": 2.942, "step": 200500 }, { "epoch": 2.8, "learning_rate": 3.835203645833334e-06, "loss": 2.9428, "step": 201000 }, { "epoch": 2.81, "learning_rate": 3.830950173611111e-06, "loss": 2.9295, "step": 201500 }, { "epoch": 2.81, "learning_rate": 3.82669670138889e-06, "loss": 2.9288, "step": 202000 }, { "epoch": 2.82, "learning_rate": 3.822451736111112e-06, "loss": 2.9385, "step": 202500 }, { "epoch": 2.83, "learning_rate": 3.818198263888889e-06, "loss": 2.9316, "step": 203000 }, { "epoch": 2.84, "learning_rate": 3.813944791666667e-06, "loss": 2.9343, "step": 203500 }, { "epoch": 2.84, "learning_rate": 3.809691319444445e-06, "loss": 2.9224, "step": 204000 }, { "epoch": 2.85, "learning_rate": 3.8054463541666663e-06, "loss": 2.921, "step": 204500 }, { "epoch": 2.86, "learning_rate": 3.8011928819444447e-06, "loss": 2.9351, "step": 205000 }, { "epoch": 2.86, "learning_rate": 3.7969394097222224e-06, "loss": 2.9315, "step": 205500 }, { "epoch": 2.87, "learning_rate": 3.7926859375000004e-06, "loss": 2.9432, "step": 206000 }, { "epoch": 2.88, "learning_rate": 3.7884409722222225e-06, "loss": 2.9229, "step": 206500 }, { "epoch": 2.88, "learning_rate": 3.784196006944445e-06, "loss": 2.9701, "step": 207000 }, { "epoch": 2.89, "learning_rate": 3.7799425347222226e-06, "loss": 2.9438, "step": 207500 }, { "epoch": 2.9, "learning_rate": 3.7756975694444446e-06, "loss": 2.9439, "step": 208000 }, { "epoch": 2.9, "learning_rate": 3.7714440972222223e-06, "loss": 2.9369, "step": 208500 }, { "epoch": 2.91, "learning_rate": 3.7671906250000003e-06, "loss": 2.9344, "step": 209000 }, { "epoch": 2.92, "learning_rate": 3.7629371527777788e-06, "loss": 2.92, "step": 209500 }, { "epoch": 2.93, "learning_rate": 3.758683680555556e-06, "loss": 2.9194, "step": 210000 }, { "epoch": 2.93, "learning_rate": 3.754430208333333e-06, "loss": 2.9129, "step": 210500 }, { "epoch": 2.94, "learning_rate": 3.750176736111112e-06, "loss": 2.9227, "step": 211000 }, { "epoch": 2.95, "learning_rate": 3.7459232638888893e-06, "loss": 2.9282, "step": 211500 }, { "epoch": 2.95, "learning_rate": 3.741678298611111e-06, "loss": 2.9398, "step": 212000 }, { "epoch": 2.96, "learning_rate": 3.7374333333333334e-06, "loss": 2.9403, "step": 212500 }, { "epoch": 2.97, "learning_rate": 3.733179861111111e-06, "loss": 2.9289, "step": 213000 }, { "epoch": 2.97, "learning_rate": 3.7289263888888887e-06, "loss": 2.9418, "step": 213500 }, { "epoch": 2.98, "learning_rate": 3.7246729166666667e-06, "loss": 2.9074, "step": 214000 }, { "epoch": 2.99, "learning_rate": 3.720419444444445e-06, "loss": 2.9215, "step": 214500 }, { "epoch": 3.0, "learning_rate": 3.7161744791666672e-06, "loss": 2.94, "step": 215000 }, { "epoch": 3.0, "learning_rate": 3.711921006944445e-06, "loss": 2.9053, "step": 215500 }, { "epoch": 3.01, "learning_rate": 3.7076675347222225e-06, "loss": 2.9239, "step": 216000 }, { "epoch": 3.02, "learning_rate": 3.7034140625000005e-06, "loss": 2.9077, "step": 216500 }, { "epoch": 3.02, "learning_rate": 3.6991605902777777e-06, "loss": 2.8968, "step": 217000 }, { "epoch": 3.03, "learning_rate": 3.694907118055556e-06, "loss": 2.8916, "step": 217500 }, { "epoch": 3.04, "learning_rate": 3.6906536458333334e-06, "loss": 2.8977, "step": 218000 }, { "epoch": 3.04, "learning_rate": 3.6864001736111115e-06, "loss": 2.9036, "step": 218500 }, { "epoch": 3.05, "learning_rate": 3.6821467013888895e-06, "loss": 2.9089, "step": 219000 }, { "epoch": 3.06, "learning_rate": 3.6778932291666667e-06, "loss": 2.9032, "step": 219500 }, { "epoch": 3.06, "learning_rate": 3.6736397569444448e-06, "loss": 2.8927, "step": 220000 }, { "epoch": 3.07, "learning_rate": 3.6693862847222224e-06, "loss": 2.9037, "step": 220500 }, { "epoch": 3.08, "learning_rate": 3.6651328125e-06, "loss": 2.8934, "step": 221000 }, { "epoch": 3.09, "learning_rate": 3.6608793402777777e-06, "loss": 2.8753, "step": 221500 }, { "epoch": 3.09, "learning_rate": 3.656625868055556e-06, "loss": 2.8971, "step": 222000 }, { "epoch": 3.1, "learning_rate": 3.652372395833334e-06, "loss": 2.921, "step": 222500 }, { "epoch": 3.11, "learning_rate": 3.6481274305555562e-06, "loss": 2.8975, "step": 223000 }, { "epoch": 3.11, "learning_rate": 3.643873958333334e-06, "loss": 2.9101, "step": 223500 }, { "epoch": 3.12, "learning_rate": 3.639620486111112e-06, "loss": 2.9017, "step": 224000 }, { "epoch": 3.13, "learning_rate": 3.6353755208333336e-06, "loss": 2.8966, "step": 224500 }, { "epoch": 3.13, "learning_rate": 3.6311220486111108e-06, "loss": 2.905, "step": 225000 }, { "epoch": 3.14, "learning_rate": 3.626868576388889e-06, "loss": 2.8967, "step": 225500 }, { "epoch": 3.15, "learning_rate": 3.622615104166667e-06, "loss": 2.9023, "step": 226000 }, { "epoch": 3.16, "learning_rate": 3.618361631944444e-06, "loss": 2.8865, "step": 226500 }, { "epoch": 3.16, "learning_rate": 3.6141081597222225e-06, "loss": 2.8802, "step": 227000 }, { "epoch": 3.17, "learning_rate": 3.6098546875000006e-06, "loss": 2.9002, "step": 227500 }, { "epoch": 3.18, "learning_rate": 3.6056012152777782e-06, "loss": 2.8917, "step": 228000 }, { "epoch": 3.18, "learning_rate": 3.601347743055556e-06, "loss": 2.9035, "step": 228500 }, { "epoch": 3.19, "learning_rate": 3.5970942708333335e-06, "loss": 2.8919, "step": 229000 }, { "epoch": 3.2, "learning_rate": 3.5928407986111115e-06, "loss": 2.8943, "step": 229500 }, { "epoch": 3.2, "learning_rate": 3.5885873263888887e-06, "loss": 2.8891, "step": 230000 }, { "epoch": 3.21, "learning_rate": 3.584342361111111e-06, "loss": 2.9066, "step": 230500 }, { "epoch": 3.22, "learning_rate": 3.580097395833334e-06, "loss": 2.9018, "step": 231000 }, { "epoch": 3.23, "learning_rate": 3.575843923611112e-06, "loss": 2.9047, "step": 231500 }, { "epoch": 3.23, "learning_rate": 3.5715904513888894e-06, "loss": 2.8973, "step": 232000 }, { "epoch": 3.24, "learning_rate": 3.5673369791666666e-06, "loss": 2.8793, "step": 232500 }, { "epoch": 3.25, "learning_rate": 3.5630835069444446e-06, "loss": 2.9009, "step": 233000 }, { "epoch": 3.25, "learning_rate": 3.5588300347222222e-06, "loss": 2.8949, "step": 233500 }, { "epoch": 3.26, "learning_rate": 3.5545765625e-06, "loss": 2.8778, "step": 234000 }, { "epoch": 3.27, "learning_rate": 3.550323090277778e-06, "loss": 2.9041, "step": 234500 }, { "epoch": 3.27, "learning_rate": 3.546078125000001e-06, "loss": 2.8886, "step": 235000 }, { "epoch": 3.28, "learning_rate": 3.5418246527777784e-06, "loss": 2.8954, "step": 235500 }, { "epoch": 3.29, "learning_rate": 3.537571180555556e-06, "loss": 2.9093, "step": 236000 }, { "epoch": 3.29, "learning_rate": 3.5333177083333337e-06, "loss": 2.9183, "step": 236500 }, { "epoch": 3.3, "learning_rate": 3.529072743055556e-06, "loss": 2.9078, "step": 237000 }, { "epoch": 3.31, "learning_rate": 3.524827777777778e-06, "loss": 2.8864, "step": 237500 }, { "epoch": 3.32, "learning_rate": 3.520574305555556e-06, "loss": 2.8886, "step": 238000 }, { "epoch": 3.32, "learning_rate": 3.516320833333334e-06, "loss": 2.8817, "step": 238500 }, { "epoch": 3.33, "learning_rate": 3.5120673611111115e-06, "loss": 2.8985, "step": 239000 }, { "epoch": 3.34, "learning_rate": 3.507813888888889e-06, "loss": 2.9103, "step": 239500 }, { "epoch": 3.34, "learning_rate": 3.5035604166666672e-06, "loss": 2.9197, "step": 240000 }, { "epoch": 3.35, "learning_rate": 3.499306944444445e-06, "loss": 2.9131, "step": 240500 }, { "epoch": 3.36, "learning_rate": 3.4950534722222225e-06, "loss": 2.8789, "step": 241000 }, { "epoch": 3.36, "learning_rate": 3.4908085069444445e-06, "loss": 2.8953, "step": 241500 }, { "epoch": 3.37, "learning_rate": 3.486563541666667e-06, "loss": 2.9162, "step": 242000 }, { "epoch": 3.38, "learning_rate": 3.4823100694444446e-06, "loss": 2.9018, "step": 242500 }, { "epoch": 3.39, "learning_rate": 3.4780565972222223e-06, "loss": 2.8845, "step": 243000 }, { "epoch": 3.39, "learning_rate": 3.4738031250000003e-06, "loss": 2.9187, "step": 243500 }, { "epoch": 3.4, "learning_rate": 3.469549652777778e-06, "loss": 2.9121, "step": 244000 }, { "epoch": 3.41, "learning_rate": 3.4652961805555556e-06, "loss": 2.8927, "step": 244500 }, { "epoch": 3.41, "learning_rate": 3.461042708333333e-06, "loss": 2.894, "step": 245000 }, { "epoch": 3.42, "learning_rate": 3.4567892361111112e-06, "loss": 2.8821, "step": 245500 }, { "epoch": 3.43, "learning_rate": 3.452544270833334e-06, "loss": 2.8956, "step": 246000 }, { "epoch": 3.43, "learning_rate": 3.4482907986111114e-06, "loss": 2.9154, "step": 246500 }, { "epoch": 3.44, "learning_rate": 3.4440373263888894e-06, "loss": 2.8951, "step": 247000 }, { "epoch": 3.45, "learning_rate": 3.4397838541666675e-06, "loss": 2.914, "step": 247500 }, { "epoch": 3.46, "learning_rate": 3.435538888888889e-06, "loss": 2.8909, "step": 248000 }, { "epoch": 3.46, "learning_rate": 3.4312939236111107e-06, "loss": 2.8745, "step": 248500 }, { "epoch": 3.47, "learning_rate": 3.4270404513888888e-06, "loss": 2.8936, "step": 249000 }, { "epoch": 3.48, "learning_rate": 3.4227869791666672e-06, "loss": 2.8971, "step": 249500 }, { "epoch": 3.48, "learning_rate": 3.418533506944445e-06, "loss": 2.8979, "step": 250000 }, { "epoch": 3.49, "learning_rate": 3.4142800347222225e-06, "loss": 2.9046, "step": 250500 }, { "epoch": 3.5, "learning_rate": 3.4100265625000005e-06, "loss": 2.9042, "step": 251000 }, { "epoch": 3.5, "learning_rate": 3.405773090277778e-06, "loss": 2.9047, "step": 251500 }, { "epoch": 3.51, "learning_rate": 3.401519618055556e-06, "loss": 2.8983, "step": 252000 }, { "epoch": 3.52, "learning_rate": 3.397274652777778e-06, "loss": 2.8899, "step": 252500 }, { "epoch": 3.52, "learning_rate": 3.393021180555556e-06, "loss": 2.8774, "step": 253000 }, { "epoch": 3.53, "learning_rate": 3.388767708333333e-06, "loss": 2.8801, "step": 253500 }, { "epoch": 3.54, "learning_rate": 3.3845142361111116e-06, "loss": 2.8942, "step": 254000 }, { "epoch": 3.55, "learning_rate": 3.380269270833334e-06, "loss": 2.8949, "step": 254500 }, { "epoch": 3.55, "learning_rate": 3.376015798611112e-06, "loss": 2.8979, "step": 255000 }, { "epoch": 3.56, "learning_rate": 3.3717623263888893e-06, "loss": 2.8841, "step": 255500 }, { "epoch": 3.57, "learning_rate": 3.3675088541666665e-06, "loss": 2.9073, "step": 256000 }, { "epoch": 3.57, "learning_rate": 3.363263888888889e-06, "loss": 2.8964, "step": 256500 }, { "epoch": 3.58, "learning_rate": 3.3590104166666666e-06, "loss": 2.8877, "step": 257000 }, { "epoch": 3.59, "learning_rate": 3.3547569444444443e-06, "loss": 2.8845, "step": 257500 }, { "epoch": 3.59, "learning_rate": 3.3505034722222223e-06, "loss": 2.8919, "step": 258000 }, { "epoch": 3.6, "learning_rate": 3.3462585069444452e-06, "loss": 2.8966, "step": 258500 }, { "epoch": 3.61, "learning_rate": 3.342005034722223e-06, "loss": 2.8818, "step": 259000 }, { "epoch": 3.62, "learning_rate": 3.3377515625000005e-06, "loss": 2.907, "step": 259500 }, { "epoch": 3.62, "learning_rate": 3.333498090277778e-06, "loss": 2.8971, "step": 260000 }, { "epoch": 3.63, "learning_rate": 3.329244618055556e-06, "loss": 2.8767, "step": 260500 }, { "epoch": 3.64, "learning_rate": 3.3249996527777778e-06, "loss": 2.8965, "step": 261000 }, { "epoch": 3.64, "learning_rate": 3.320746180555556e-06, "loss": 2.887, "step": 261500 }, { "epoch": 3.65, "learning_rate": 3.316492708333334e-06, "loss": 2.9044, "step": 262000 }, { "epoch": 3.66, "learning_rate": 3.3122392361111124e-06, "loss": 2.8872, "step": 262500 }, { "epoch": 3.66, "learning_rate": 3.3079857638888896e-06, "loss": 2.8991, "step": 263000 }, { "epoch": 3.67, "learning_rate": 3.303732291666667e-06, "loss": 2.8981, "step": 263500 }, { "epoch": 3.68, "learning_rate": 3.299478819444445e-06, "loss": 2.8841, "step": 264000 }, { "epoch": 3.68, "learning_rate": 3.2952253472222224e-06, "loss": 2.8795, "step": 264500 }, { "epoch": 3.69, "learning_rate": 3.2909803819444445e-06, "loss": 2.8832, "step": 265000 }, { "epoch": 3.7, "learning_rate": 3.2867269097222225e-06, "loss": 2.8909, "step": 265500 }, { "epoch": 3.71, "learning_rate": 3.2824734375e-06, "loss": 2.8991, "step": 266000 }, { "epoch": 3.71, "learning_rate": 3.278219965277778e-06, "loss": 2.8764, "step": 266500 }, { "epoch": 3.72, "learning_rate": 3.2739750000000003e-06, "loss": 2.9024, "step": 267000 }, { "epoch": 3.73, "learning_rate": 3.2697215277777783e-06, "loss": 2.8911, "step": 267500 }, { "epoch": 3.73, "learning_rate": 3.2654680555555555e-06, "loss": 2.8698, "step": 268000 }, { "epoch": 3.74, "learning_rate": 3.2612145833333336e-06, "loss": 2.8976, "step": 268500 }, { "epoch": 3.75, "learning_rate": 3.2569696180555556e-06, "loss": 2.9034, "step": 269000 }, { "epoch": 3.75, "learning_rate": 3.252716145833334e-06, "loss": 2.8884, "step": 269500 }, { "epoch": 3.76, "learning_rate": 3.2484626736111113e-06, "loss": 2.8702, "step": 270000 }, { "epoch": 3.77, "learning_rate": 3.2442092013888894e-06, "loss": 2.8704, "step": 270500 }, { "epoch": 3.78, "learning_rate": 3.239964236111112e-06, "loss": 2.8964, "step": 271000 }, { "epoch": 3.78, "learning_rate": 3.235710763888889e-06, "loss": 2.8667, "step": 271500 }, { "epoch": 3.79, "learning_rate": 3.2314572916666663e-06, "loss": 2.8679, "step": 272000 }, { "epoch": 3.8, "learning_rate": 3.2272038194444443e-06, "loss": 2.9098, "step": 272500 }, { "epoch": 3.8, "learning_rate": 3.2229588541666664e-06, "loss": 2.9084, "step": 273000 }, { "epoch": 3.81, "learning_rate": 3.218705381944445e-06, "loss": 2.8924, "step": 273500 }, { "epoch": 3.82, "learning_rate": 3.2144519097222225e-06, "loss": 2.8818, "step": 274000 }, { "epoch": 3.82, "learning_rate": 3.2101984375000005e-06, "loss": 2.8812, "step": 274500 }, { "epoch": 3.83, "learning_rate": 3.2059534722222226e-06, "loss": 2.8916, "step": 275000 }, { "epoch": 3.84, "learning_rate": 3.2017e-06, "loss": 2.8987, "step": 275500 }, { "epoch": 3.85, "learning_rate": 3.197446527777778e-06, "loss": 2.8862, "step": 276000 }, { "epoch": 3.85, "learning_rate": 3.193193055555556e-06, "loss": 2.9055, "step": 276500 }, { "epoch": 3.86, "learning_rate": 3.188939583333333e-06, "loss": 2.8696, "step": 277000 }, { "epoch": 3.87, "learning_rate": 3.184703125e-06, "loss": 2.8985, "step": 277500 }, { "epoch": 3.87, "learning_rate": 3.1804496527777785e-06, "loss": 2.8928, "step": 278000 }, { "epoch": 3.88, "learning_rate": 3.1761961805555565e-06, "loss": 2.9052, "step": 278500 }, { "epoch": 3.89, "learning_rate": 3.1719427083333337e-06, "loss": 2.889, "step": 279000 }, { "epoch": 3.89, "learning_rate": 3.167689236111111e-06, "loss": 2.9006, "step": 279500 }, { "epoch": 3.9, "learning_rate": 3.163435763888889e-06, "loss": 2.8991, "step": 280000 }, { "epoch": 3.91, "learning_rate": 3.1591822916666666e-06, "loss": 2.866, "step": 280500 }, { "epoch": 3.91, "learning_rate": 3.1549288194444442e-06, "loss": 2.9045, "step": 281000 }, { "epoch": 3.92, "learning_rate": 3.1506838541666667e-06, "loss": 2.8751, "step": 281500 }, { "epoch": 3.93, "learning_rate": 3.146430381944445e-06, "loss": 2.896, "step": 282000 }, { "epoch": 3.94, "learning_rate": 3.142176909722223e-06, "loss": 2.8861, "step": 282500 }, { "epoch": 3.94, "learning_rate": 3.137931944444445e-06, "loss": 2.8944, "step": 283000 }, { "epoch": 3.95, "learning_rate": 3.1336784722222225e-06, "loss": 2.8774, "step": 283500 }, { "epoch": 3.96, "learning_rate": 3.1294250000000005e-06, "loss": 2.8914, "step": 284000 }, { "epoch": 3.96, "learning_rate": 3.1251715277777777e-06, "loss": 2.8857, "step": 284500 }, { "epoch": 3.97, "learning_rate": 3.1209180555555554e-06, "loss": 2.8913, "step": 285000 }, { "epoch": 3.98, "learning_rate": 3.116664583333334e-06, "loss": 2.8684, "step": 285500 }, { "epoch": 3.98, "learning_rate": 3.112411111111111e-06, "loss": 2.9081, "step": 286000 }, { "epoch": 3.99, "learning_rate": 3.1081576388888895e-06, "loss": 2.8912, "step": 286500 }, { "epoch": 4.0, "learning_rate": 3.103921180555556e-06, "loss": 2.8903, "step": 287000 }, { "epoch": 4.01, "learning_rate": 3.0996677083333336e-06, "loss": 2.884, "step": 287500 }, { "epoch": 4.01, "learning_rate": 3.0954142361111113e-06, "loss": 2.8876, "step": 288000 }, { "epoch": 4.02, "learning_rate": 3.091160763888889e-06, "loss": 2.8451, "step": 288500 }, { "epoch": 4.03, "learning_rate": 3.086907291666667e-06, "loss": 2.8658, "step": 289000 }, { "epoch": 4.03, "learning_rate": 3.0826538194444446e-06, "loss": 2.8625, "step": 289500 }, { "epoch": 4.04, "learning_rate": 3.078400347222223e-06, "loss": 2.8439, "step": 290000 }, { "epoch": 4.05, "learning_rate": 3.0741468750000007e-06, "loss": 2.855, "step": 290500 }, { "epoch": 4.05, "learning_rate": 3.0699019097222223e-06, "loss": 2.8535, "step": 291000 }, { "epoch": 4.06, "learning_rate": 3.0656484375e-06, "loss": 2.8424, "step": 291500 }, { "epoch": 4.07, "learning_rate": 3.061394965277778e-06, "loss": 2.8511, "step": 292000 }, { "epoch": 4.08, "learning_rate": 3.05715e-06, "loss": 2.8617, "step": 292500 }, { "epoch": 4.08, "learning_rate": 3.0528965277777785e-06, "loss": 2.8729, "step": 293000 }, { "epoch": 4.09, "learning_rate": 3.0486430555555557e-06, "loss": 2.8677, "step": 293500 }, { "epoch": 4.1, "learning_rate": 3.0443895833333338e-06, "loss": 2.8543, "step": 294000 }, { "epoch": 4.1, "learning_rate": 3.040136111111112e-06, "loss": 2.8521, "step": 294500 }, { "epoch": 4.11, "learning_rate": 3.035882638888889e-06, "loss": 2.8704, "step": 295000 }, { "epoch": 4.12, "learning_rate": 3.031629166666667e-06, "loss": 2.8627, "step": 295500 }, { "epoch": 4.12, "learning_rate": 3.0273756944444447e-06, "loss": 2.8586, "step": 296000 }, { "epoch": 4.13, "learning_rate": 3.0231307291666667e-06, "loss": 2.8735, "step": 296500 }, { "epoch": 4.14, "learning_rate": 3.018877256944445e-06, "loss": 2.8473, "step": 297000 }, { "epoch": 4.14, "learning_rate": 3.0146237847222224e-06, "loss": 2.854, "step": 297500 }, { "epoch": 4.15, "learning_rate": 3.0103703125000005e-06, "loss": 2.8491, "step": 298000 }, { "epoch": 4.16, "learning_rate": 3.0061253472222225e-06, "loss": 2.8709, "step": 298500 }, { "epoch": 4.17, "learning_rate": 3.001871875e-06, "loss": 2.8364, "step": 299000 }, { "epoch": 4.17, "learning_rate": 2.9976269097222222e-06, "loss": 2.8504, "step": 299500 }, { "epoch": 4.18, "learning_rate": 2.9933734375000003e-06, "loss": 2.8511, "step": 300000 }, { "epoch": 4.18, "eval_gen_len": 19.9976, "eval_loss": 2.775161027908325, "eval_rouge1": 0.2957, "eval_rouge2": 0.173, "eval_rougeL": 0.2501, "eval_rougeLsum": 0.2812, "eval_runtime": 899.8085, "eval_samples_per_second": 14.856, "eval_steps_per_second": 3.714, "step": 300000 }, { "epoch": 4.19, "learning_rate": 2.9891199652777775e-06, "loss": 2.8515, "step": 300500 }, { "epoch": 4.19, "learning_rate": 2.984866493055556e-06, "loss": 2.8585, "step": 301000 }, { "epoch": 4.2, "learning_rate": 2.9806130208333336e-06, "loss": 2.8539, "step": 301500 }, { "epoch": 4.21, "learning_rate": 2.976359548611112e-06, "loss": 2.8733, "step": 302000 }, { "epoch": 4.21, "learning_rate": 2.9721060763888892e-06, "loss": 2.8662, "step": 302500 }, { "epoch": 4.22, "learning_rate": 2.9678526041666665e-06, "loss": 2.8563, "step": 303000 }, { "epoch": 4.23, "learning_rate": 2.963607638888889e-06, "loss": 2.8411, "step": 303500 }, { "epoch": 4.24, "learning_rate": 2.959362673611111e-06, "loss": 2.8743, "step": 304000 }, { "epoch": 4.24, "learning_rate": 2.9551092013888886e-06, "loss": 2.8903, "step": 304500 }, { "epoch": 4.25, "learning_rate": 2.950855729166667e-06, "loss": 2.8469, "step": 305000 }, { "epoch": 4.26, "learning_rate": 2.9466022569444447e-06, "loss": 2.8481, "step": 305500 }, { "epoch": 4.26, "learning_rate": 2.9423487847222228e-06, "loss": 2.8606, "step": 306000 }, { "epoch": 4.27, "learning_rate": 2.938103819444445e-06, "loss": 2.8752, "step": 306500 }, { "epoch": 4.28, "learning_rate": 2.9338503472222224e-06, "loss": 2.8531, "step": 307000 }, { "epoch": 4.28, "learning_rate": 2.9295968750000005e-06, "loss": 2.8507, "step": 307500 }, { "epoch": 4.29, "learning_rate": 2.9253434027777777e-06, "loss": 2.8744, "step": 308000 }, { "epoch": 4.3, "learning_rate": 2.9210899305555553e-06, "loss": 2.8672, "step": 308500 }, { "epoch": 4.3, "learning_rate": 2.916836458333334e-06, "loss": 2.8692, "step": 309000 }, { "epoch": 4.31, "learning_rate": 2.9125829861111114e-06, "loss": 2.8503, "step": 309500 }, { "epoch": 4.32, "learning_rate": 2.9083295138888895e-06, "loss": 2.8534, "step": 310000 }, { "epoch": 4.33, "learning_rate": 2.9040845486111115e-06, "loss": 2.8941, "step": 310500 }, { "epoch": 4.33, "learning_rate": 2.899831076388889e-06, "loss": 2.8798, "step": 311000 }, { "epoch": 4.34, "learning_rate": 2.895577604166667e-06, "loss": 2.8578, "step": 311500 }, { "epoch": 4.35, "learning_rate": 2.8913241319444444e-06, "loss": 2.8472, "step": 312000 }, { "epoch": 4.35, "learning_rate": 2.8870791666666665e-06, "loss": 2.859, "step": 312500 }, { "epoch": 4.36, "learning_rate": 2.8828256944444445e-06, "loss": 2.85, "step": 313000 }, { "epoch": 4.37, "learning_rate": 2.878572222222222e-06, "loss": 2.863, "step": 313500 }, { "epoch": 4.37, "learning_rate": 2.8743187500000006e-06, "loss": 2.8716, "step": 314000 }, { "epoch": 4.38, "learning_rate": 2.8700737847222227e-06, "loss": 2.8425, "step": 314500 }, { "epoch": 4.39, "learning_rate": 2.8658203125e-06, "loss": 2.867, "step": 315000 }, { "epoch": 4.4, "learning_rate": 2.861566840277778e-06, "loss": 2.8505, "step": 315500 }, { "epoch": 4.4, "learning_rate": 2.8573133680555556e-06, "loss": 2.848, "step": 316000 }, { "epoch": 4.41, "learning_rate": 2.8530684027777785e-06, "loss": 2.8435, "step": 316500 }, { "epoch": 4.42, "learning_rate": 2.8488149305555557e-06, "loss": 2.8632, "step": 317000 }, { "epoch": 4.42, "learning_rate": 2.844569965277778e-06, "loss": 2.8656, "step": 317500 }, { "epoch": 4.43, "learning_rate": 2.840316493055556e-06, "loss": 2.8368, "step": 318000 }, { "epoch": 4.44, "learning_rate": 2.8360630208333334e-06, "loss": 2.873, "step": 318500 }, { "epoch": 4.44, "learning_rate": 2.8318095486111115e-06, "loss": 2.851, "step": 319000 }, { "epoch": 4.45, "learning_rate": 2.8275560763888895e-06, "loss": 2.861, "step": 319500 }, { "epoch": 4.46, "learning_rate": 2.8233026041666667e-06, "loss": 2.8546, "step": 320000 }, { "epoch": 4.47, "learning_rate": 2.819049131944444e-06, "loss": 2.8439, "step": 320500 }, { "epoch": 4.47, "learning_rate": 2.8147956597222224e-06, "loss": 2.8733, "step": 321000 }, { "epoch": 4.48, "learning_rate": 2.810550694444445e-06, "loss": 2.861, "step": 321500 }, { "epoch": 4.49, "learning_rate": 2.8062972222222225e-06, "loss": 2.8453, "step": 322000 }, { "epoch": 4.49, "learning_rate": 2.8020522569444445e-06, "loss": 2.8492, "step": 322500 }, { "epoch": 4.5, "learning_rate": 2.797798784722222e-06, "loss": 2.8501, "step": 323000 }, { "epoch": 4.51, "learning_rate": 2.7935453125000002e-06, "loss": 2.8624, "step": 323500 }, { "epoch": 4.51, "learning_rate": 2.7892918402777774e-06, "loss": 2.8503, "step": 324000 }, { "epoch": 4.52, "learning_rate": 2.785038368055556e-06, "loss": 2.871, "step": 324500 }, { "epoch": 4.53, "learning_rate": 2.7807848958333335e-06, "loss": 2.8643, "step": 325000 }, { "epoch": 4.53, "learning_rate": 2.776531423611112e-06, "loss": 2.8591, "step": 325500 }, { "epoch": 4.54, "learning_rate": 2.772277951388889e-06, "loss": 2.8494, "step": 326000 }, { "epoch": 4.55, "learning_rate": 2.768032986111111e-06, "loss": 2.8592, "step": 326500 }, { "epoch": 4.56, "learning_rate": 2.763779513888889e-06, "loss": 2.866, "step": 327000 }, { "epoch": 4.56, "learning_rate": 2.7595260416666665e-06, "loss": 2.8772, "step": 327500 }, { "epoch": 4.57, "learning_rate": 2.755272569444444e-06, "loss": 2.8435, "step": 328000 }, { "epoch": 4.58, "learning_rate": 2.751027604166667e-06, "loss": 2.8715, "step": 328500 }, { "epoch": 4.58, "learning_rate": 2.7467826388888895e-06, "loss": 2.8687, "step": 329000 }, { "epoch": 4.59, "learning_rate": 2.742529166666667e-06, "loss": 2.8434, "step": 329500 }, { "epoch": 4.6, "learning_rate": 2.7382756944444448e-06, "loss": 2.8617, "step": 330000 }, { "epoch": 4.6, "learning_rate": 2.7340222222222224e-06, "loss": 2.8492, "step": 330500 }, { "epoch": 4.61, "learning_rate": 2.7297687500000005e-06, "loss": 2.8672, "step": 331000 }, { "epoch": 4.62, "learning_rate": 2.7255152777777777e-06, "loss": 2.8813, "step": 331500 }, { "epoch": 4.63, "learning_rate": 2.7212618055555553e-06, "loss": 2.8522, "step": 332000 }, { "epoch": 4.63, "learning_rate": 2.7170083333333338e-06, "loss": 2.8501, "step": 332500 }, { "epoch": 4.64, "learning_rate": 2.712763368055556e-06, "loss": 2.8442, "step": 333000 }, { "epoch": 4.65, "learning_rate": 2.708509895833334e-06, "loss": 2.857, "step": 333500 }, { "epoch": 4.65, "learning_rate": 2.7042564236111115e-06, "loss": 2.8543, "step": 334000 }, { "epoch": 4.66, "learning_rate": 2.700002951388889e-06, "loss": 2.8721, "step": 334500 }, { "epoch": 4.67, "learning_rate": 2.6957494791666668e-06, "loss": 2.8362, "step": 335000 }, { "epoch": 4.67, "learning_rate": 2.6915130208333332e-06, "loss": 2.848, "step": 335500 }, { "epoch": 4.68, "learning_rate": 2.6872595486111113e-06, "loss": 2.8602, "step": 336000 }, { "epoch": 4.69, "learning_rate": 2.6830145833333333e-06, "loss": 2.8643, "step": 336500 }, { "epoch": 4.69, "learning_rate": 2.678761111111111e-06, "loss": 2.857, "step": 337000 }, { "epoch": 4.7, "learning_rate": 2.6745076388888894e-06, "loss": 2.8649, "step": 337500 }, { "epoch": 4.71, "learning_rate": 2.670254166666667e-06, "loss": 2.8405, "step": 338000 }, { "epoch": 4.72, "learning_rate": 2.6660006944444443e-06, "loss": 2.859, "step": 338500 }, { "epoch": 4.72, "learning_rate": 2.6617472222222223e-06, "loss": 2.8678, "step": 339000 }, { "epoch": 4.73, "learning_rate": 2.65749375e-06, "loss": 2.8263, "step": 339500 }, { "epoch": 4.74, "learning_rate": 2.6532402777777776e-06, "loss": 2.8557, "step": 340000 }, { "epoch": 4.74, "learning_rate": 2.6489868055555556e-06, "loss": 2.8472, "step": 340500 }, { "epoch": 4.75, "learning_rate": 2.644741840277778e-06, "loss": 2.8889, "step": 341000 }, { "epoch": 4.76, "learning_rate": 2.640488368055556e-06, "loss": 2.8811, "step": 341500 }, { "epoch": 4.76, "learning_rate": 2.636234895833334e-06, "loss": 2.8624, "step": 342000 }, { "epoch": 4.77, "learning_rate": 2.6319814236111114e-06, "loss": 2.8698, "step": 342500 }, { "epoch": 4.78, "learning_rate": 2.627727951388889e-06, "loss": 2.8478, "step": 343000 }, { "epoch": 4.79, "learning_rate": 2.623482986111111e-06, "loss": 2.8581, "step": 343500 }, { "epoch": 4.79, "learning_rate": 2.619229513888889e-06, "loss": 2.8464, "step": 344000 }, { "epoch": 4.8, "learning_rate": 2.6149760416666668e-06, "loss": 2.8497, "step": 344500 }, { "epoch": 4.81, "learning_rate": 2.610722569444445e-06, "loss": 2.8453, "step": 345000 }, { "epoch": 4.81, "learning_rate": 2.6064690972222225e-06, "loss": 2.8648, "step": 345500 }, { "epoch": 4.82, "learning_rate": 2.602215625e-06, "loss": 2.8335, "step": 346000 }, { "epoch": 4.83, "learning_rate": 2.597962152777778e-06, "loss": 2.8401, "step": 346500 }, { "epoch": 4.83, "learning_rate": 2.5937086805555558e-06, "loss": 2.8645, "step": 347000 }, { "epoch": 4.84, "learning_rate": 2.589463715277778e-06, "loss": 2.867, "step": 347500 }, { "epoch": 4.85, "learning_rate": 2.5852102430555554e-06, "loss": 2.8612, "step": 348000 }, { "epoch": 4.86, "learning_rate": 2.5809567708333335e-06, "loss": 2.869, "step": 348500 }, { "epoch": 4.86, "learning_rate": 2.5767118055555564e-06, "loss": 2.8559, "step": 349000 }, { "epoch": 4.87, "learning_rate": 2.5724583333333336e-06, "loss": 2.8605, "step": 349500 }, { "epoch": 4.88, "learning_rate": 2.568204861111111e-06, "loss": 2.8604, "step": 350000 }, { "epoch": 4.88, "learning_rate": 2.563951388888889e-06, "loss": 2.8465, "step": 350500 }, { "epoch": 4.89, "learning_rate": 2.559697916666667e-06, "loss": 2.8692, "step": 351000 }, { "epoch": 4.9, "learning_rate": 2.555444444444444e-06, "loss": 2.8702, "step": 351500 }, { "epoch": 4.9, "learning_rate": 2.551190972222222e-06, "loss": 2.8705, "step": 352000 }, { "epoch": 4.91, "learning_rate": 2.5469375e-06, "loss": 2.8593, "step": 352500 }, { "epoch": 4.92, "learning_rate": 2.542692534722222e-06, "loss": 2.8565, "step": 353000 }, { "epoch": 4.92, "learning_rate": 2.5384390625e-06, "loss": 2.8441, "step": 353500 }, { "epoch": 4.93, "learning_rate": 2.534185590277778e-06, "loss": 2.841, "step": 354000 }, { "epoch": 4.94, "learning_rate": 2.529932118055556e-06, "loss": 2.8591, "step": 354500 }, { "epoch": 4.95, "learning_rate": 2.5256871527777776e-06, "loss": 2.8393, "step": 355000 }, { "epoch": 4.95, "learning_rate": 2.521433680555556e-06, "loss": 2.8701, "step": 355500 }, { "epoch": 4.96, "learning_rate": 2.5171802083333337e-06, "loss": 2.8733, "step": 356000 }, { "epoch": 4.97, "learning_rate": 2.5129267361111114e-06, "loss": 2.874, "step": 356500 }, { "epoch": 4.97, "learning_rate": 2.5086817708333334e-06, "loss": 2.8754, "step": 357000 }, { "epoch": 4.98, "learning_rate": 2.5044282986111115e-06, "loss": 2.8503, "step": 357500 }, { "epoch": 4.99, "learning_rate": 2.500174826388889e-06, "loss": 2.836, "step": 358000 }, { "epoch": 4.99, "learning_rate": 2.4959213541666667e-06, "loss": 2.8584, "step": 358500 }, { "epoch": 5.0, "learning_rate": 2.4916678819444443e-06, "loss": 2.835, "step": 359000 }, { "epoch": 5.01, "learning_rate": 2.4874229166666672e-06, "loss": 2.8445, "step": 359500 }, { "epoch": 5.02, "learning_rate": 2.483169444444445e-06, "loss": 2.8368, "step": 360000 }, { "epoch": 5.02, "learning_rate": 2.4789159722222225e-06, "loss": 2.8288, "step": 360500 }, { "epoch": 5.03, "learning_rate": 2.4746625e-06, "loss": 2.8424, "step": 361000 }, { "epoch": 5.04, "learning_rate": 2.4704175347222226e-06, "loss": 2.8338, "step": 361500 }, { "epoch": 5.04, "learning_rate": 2.4661640625000002e-06, "loss": 2.8387, "step": 362000 }, { "epoch": 5.05, "learning_rate": 2.461910590277778e-06, "loss": 2.8373, "step": 362500 }, { "epoch": 5.06, "learning_rate": 2.4576571180555555e-06, "loss": 2.8195, "step": 363000 }, { "epoch": 5.06, "learning_rate": 2.453412152777778e-06, "loss": 2.8317, "step": 363500 }, { "epoch": 5.07, "learning_rate": 2.4491586805555556e-06, "loss": 2.8574, "step": 364000 }, { "epoch": 5.08, "learning_rate": 2.4449052083333332e-06, "loss": 2.8183, "step": 364500 }, { "epoch": 5.09, "learning_rate": 2.4406517361111113e-06, "loss": 2.8213, "step": 365000 }, { "epoch": 5.09, "learning_rate": 2.436415277777778e-06, "loss": 2.8332, "step": 365500 }, { "epoch": 5.1, "learning_rate": 2.432161805555556e-06, "loss": 2.848, "step": 366000 }, { "epoch": 5.11, "learning_rate": 2.4279083333333334e-06, "loss": 2.831, "step": 366500 }, { "epoch": 5.11, "learning_rate": 2.4236548611111115e-06, "loss": 2.8363, "step": 367000 }, { "epoch": 5.12, "learning_rate": 2.4194098958333335e-06, "loss": 2.8482, "step": 367500 }, { "epoch": 5.13, "learning_rate": 2.415156423611111e-06, "loss": 2.8307, "step": 368000 }, { "epoch": 5.13, "learning_rate": 2.410902951388889e-06, "loss": 2.8349, "step": 368500 }, { "epoch": 5.14, "learning_rate": 2.406649479166667e-06, "loss": 2.8065, "step": 369000 }, { "epoch": 5.15, "learning_rate": 2.402396006944445e-06, "loss": 2.8475, "step": 369500 }, { "epoch": 5.15, "learning_rate": 2.3981425347222225e-06, "loss": 2.8422, "step": 370000 }, { "epoch": 5.16, "learning_rate": 2.3938890625e-06, "loss": 2.8521, "step": 370500 }, { "epoch": 5.17, "learning_rate": 2.3896355902777778e-06, "loss": 2.8115, "step": 371000 }, { "epoch": 5.18, "learning_rate": 2.385382118055556e-06, "loss": 2.8041, "step": 371500 }, { "epoch": 5.18, "learning_rate": 2.3811286458333335e-06, "loss": 2.8452, "step": 372000 }, { "epoch": 5.19, "learning_rate": 2.376875173611111e-06, "loss": 2.8396, "step": 372500 }, { "epoch": 5.2, "learning_rate": 2.372630208333333e-06, "loss": 2.844, "step": 373000 }, { "epoch": 5.2, "learning_rate": 2.3683767361111116e-06, "loss": 2.8406, "step": 373500 }, { "epoch": 5.21, "learning_rate": 2.3641232638888892e-06, "loss": 2.8107, "step": 374000 }, { "epoch": 5.22, "learning_rate": 2.359869791666667e-06, "loss": 2.8292, "step": 374500 }, { "epoch": 5.22, "learning_rate": 2.3556163194444445e-06, "loss": 2.8411, "step": 375000 }, { "epoch": 5.23, "learning_rate": 2.3513628472222225e-06, "loss": 2.8439, "step": 375500 }, { "epoch": 5.24, "learning_rate": 2.347109375e-06, "loss": 2.8482, "step": 376000 }, { "epoch": 5.25, "learning_rate": 2.342855902777778e-06, "loss": 2.8161, "step": 376500 }, { "epoch": 5.25, "learning_rate": 2.3386109375e-06, "loss": 2.8375, "step": 377000 }, { "epoch": 5.26, "learning_rate": 2.334357465277778e-06, "loss": 2.8337, "step": 377500 }, { "epoch": 5.27, "learning_rate": 2.330103993055556e-06, "loss": 2.8339, "step": 378000 }, { "epoch": 5.27, "learning_rate": 2.3258505208333336e-06, "loss": 2.82, "step": 378500 }, { "epoch": 5.28, "learning_rate": 2.3216055555555556e-06, "loss": 2.8272, "step": 379000 }, { "epoch": 5.29, "learning_rate": 2.3173520833333337e-06, "loss": 2.8164, "step": 379500 }, { "epoch": 5.29, "learning_rate": 2.3130986111111113e-06, "loss": 2.8323, "step": 380000 }, { "epoch": 5.3, "learning_rate": 2.308845138888889e-06, "loss": 2.8662, "step": 380500 }, { "epoch": 5.31, "learning_rate": 2.3045916666666666e-06, "loss": 2.8664, "step": 381000 }, { "epoch": 5.31, "learning_rate": 2.300346701388889e-06, "loss": 2.8331, "step": 381500 }, { "epoch": 5.32, "learning_rate": 2.2960932291666667e-06, "loss": 2.8471, "step": 382000 }, { "epoch": 5.33, "learning_rate": 2.2918397569444443e-06, "loss": 2.8169, "step": 382500 }, { "epoch": 5.34, "learning_rate": 2.2875862847222224e-06, "loss": 2.8311, "step": 383000 }, { "epoch": 5.34, "learning_rate": 2.2833328125000004e-06, "loss": 2.8265, "step": 383500 }, { "epoch": 5.35, "learning_rate": 2.279079340277778e-06, "loss": 2.8364, "step": 384000 }, { "epoch": 5.36, "learning_rate": 2.2748258680555557e-06, "loss": 2.8051, "step": 384500 }, { "epoch": 5.36, "learning_rate": 2.2705723958333333e-06, "loss": 2.844, "step": 385000 }, { "epoch": 5.37, "learning_rate": 2.2663274305555558e-06, "loss": 2.831, "step": 385500 }, { "epoch": 5.38, "learning_rate": 2.2620739583333334e-06, "loss": 2.8235, "step": 386000 }, { "epoch": 5.38, "learning_rate": 2.257820486111111e-06, "loss": 2.8099, "step": 386500 }, { "epoch": 5.39, "learning_rate": 2.2535670138888886e-06, "loss": 2.8455, "step": 387000 }, { "epoch": 5.4, "learning_rate": 2.2493220486111116e-06, "loss": 2.8496, "step": 387500 }, { "epoch": 5.41, "learning_rate": 2.245068576388889e-06, "loss": 2.8497, "step": 388000 }, { "epoch": 5.41, "learning_rate": 2.240815104166667e-06, "loss": 2.8506, "step": 388500 }, { "epoch": 5.42, "learning_rate": 2.2365616319444444e-06, "loss": 2.8424, "step": 389000 }, { "epoch": 5.43, "learning_rate": 2.2323081597222225e-06, "loss": 2.844, "step": 389500 }, { "epoch": 5.43, "learning_rate": 2.2280546875e-06, "loss": 2.8288, "step": 390000 }, { "epoch": 5.44, "learning_rate": 2.2238012152777777e-06, "loss": 2.8439, "step": 390500 }, { "epoch": 5.45, "learning_rate": 2.2195477430555554e-06, "loss": 2.8261, "step": 391000 }, { "epoch": 5.45, "learning_rate": 2.2153027777777783e-06, "loss": 2.8425, "step": 391500 }, { "epoch": 5.46, "learning_rate": 2.211049305555556e-06, "loss": 2.8202, "step": 392000 }, { "epoch": 5.47, "learning_rate": 2.2067958333333335e-06, "loss": 2.8259, "step": 392500 }, { "epoch": 5.48, "learning_rate": 2.202542361111111e-06, "loss": 2.8405, "step": 393000 }, { "epoch": 5.48, "learning_rate": 2.1982973958333336e-06, "loss": 2.85, "step": 393500 }, { "epoch": 5.49, "learning_rate": 2.1940439236111113e-06, "loss": 2.8459, "step": 394000 }, { "epoch": 5.5, "learning_rate": 2.189790451388889e-06, "loss": 2.8092, "step": 394500 }, { "epoch": 5.5, "learning_rate": 2.1855369791666665e-06, "loss": 2.82, "step": 395000 }, { "epoch": 5.51, "learning_rate": 2.181292013888889e-06, "loss": 2.8212, "step": 395500 }, { "epoch": 5.52, "learning_rate": 2.177047048611111e-06, "loss": 2.8484, "step": 396000 }, { "epoch": 5.52, "learning_rate": 2.1727935763888887e-06, "loss": 2.8344, "step": 396500 }, { "epoch": 5.53, "learning_rate": 2.1685401041666667e-06, "loss": 2.8265, "step": 397000 }, { "epoch": 5.54, "learning_rate": 2.1642866319444448e-06, "loss": 2.8357, "step": 397500 }, { "epoch": 5.54, "learning_rate": 2.160041666666667e-06, "loss": 2.8295, "step": 398000 }, { "epoch": 5.55, "learning_rate": 2.155796701388889e-06, "loss": 2.827, "step": 398500 }, { "epoch": 5.56, "learning_rate": 2.151543229166667e-06, "loss": 2.8175, "step": 399000 }, { "epoch": 5.57, "learning_rate": 2.1472897569444446e-06, "loss": 2.8275, "step": 399500 }, { "epoch": 5.57, "learning_rate": 2.143036284722222e-06, "loss": 2.8357, "step": 400000 }, { "epoch": 5.57, "eval_gen_len": 19.9973, "eval_loss": 2.7551486492156982, "eval_rouge1": 0.2972, "eval_rouge2": 0.1745, "eval_rougeL": 0.2513, "eval_rougeLsum": 0.2824, "eval_runtime": 881.1984, "eval_samples_per_second": 15.17, "eval_steps_per_second": 3.793, "step": 400000 }, { "epoch": 5.58, "learning_rate": 2.1387828125e-06, "loss": 2.8298, "step": 400500 }, { "epoch": 5.59, "learning_rate": 2.1345293402777783e-06, "loss": 2.8371, "step": 401000 }, { "epoch": 5.59, "learning_rate": 2.130275868055556e-06, "loss": 2.8121, "step": 401500 }, { "epoch": 5.6, "learning_rate": 2.1260223958333335e-06, "loss": 2.8355, "step": 402000 }, { "epoch": 5.61, "learning_rate": 2.121768923611111e-06, "loss": 2.8341, "step": 402500 }, { "epoch": 5.61, "learning_rate": 2.117515451388889e-06, "loss": 2.8311, "step": 403000 }, { "epoch": 5.62, "learning_rate": 2.113261979166667e-06, "loss": 2.831, "step": 403500 }, { "epoch": 5.63, "learning_rate": 2.1090085069444445e-06, "loss": 2.8232, "step": 404000 }, { "epoch": 5.64, "learning_rate": 2.104755034722222e-06, "loss": 2.8277, "step": 404500 }, { "epoch": 5.64, "learning_rate": 2.1005015624999997e-06, "loss": 2.8317, "step": 405000 }, { "epoch": 5.65, "learning_rate": 2.096248090277778e-06, "loss": 2.8267, "step": 405500 }, { "epoch": 5.66, "learning_rate": 2.091994618055556e-06, "loss": 2.8385, "step": 406000 }, { "epoch": 5.66, "learning_rate": 2.087749652777778e-06, "loss": 2.8262, "step": 406500 }, { "epoch": 5.67, "learning_rate": 2.0834961805555555e-06, "loss": 2.8507, "step": 407000 }, { "epoch": 5.68, "learning_rate": 2.0792427083333336e-06, "loss": 2.8364, "step": 407500 }, { "epoch": 5.68, "learning_rate": 2.074989236111111e-06, "loss": 2.834, "step": 408000 }, { "epoch": 5.69, "learning_rate": 2.070735763888889e-06, "loss": 2.828, "step": 408500 }, { "epoch": 5.7, "learning_rate": 2.0664822916666665e-06, "loss": 2.8183, "step": 409000 }, { "epoch": 5.71, "learning_rate": 2.0622288194444445e-06, "loss": 2.8342, "step": 409500 }, { "epoch": 5.71, "learning_rate": 2.0579753472222226e-06, "loss": 2.8115, "step": 410000 }, { "epoch": 5.72, "learning_rate": 2.0537303819444446e-06, "loss": 2.8207, "step": 410500 }, { "epoch": 5.73, "learning_rate": 2.0494769097222222e-06, "loss": 2.8469, "step": 411000 }, { "epoch": 5.73, "learning_rate": 2.0452234375e-06, "loss": 2.8344, "step": 411500 }, { "epoch": 5.74, "learning_rate": 2.040969965277778e-06, "loss": 2.8193, "step": 412000 }, { "epoch": 5.75, "learning_rate": 2.036725e-06, "loss": 2.8214, "step": 412500 }, { "epoch": 5.75, "learning_rate": 2.032480034722222e-06, "loss": 2.8352, "step": 413000 }, { "epoch": 5.76, "learning_rate": 2.0282265625e-06, "loss": 2.84, "step": 413500 }, { "epoch": 5.77, "learning_rate": 2.023973090277778e-06, "loss": 2.8185, "step": 414000 }, { "epoch": 5.77, "learning_rate": 2.0197196180555558e-06, "loss": 2.8221, "step": 414500 }, { "epoch": 5.78, "learning_rate": 2.0154661458333334e-06, "loss": 2.8284, "step": 415000 }, { "epoch": 5.79, "learning_rate": 2.0112126736111114e-06, "loss": 2.8441, "step": 415500 }, { "epoch": 5.8, "learning_rate": 2.006959201388889e-06, "loss": 2.8231, "step": 416000 }, { "epoch": 5.8, "learning_rate": 2.0027057291666667e-06, "loss": 2.8212, "step": 416500 }, { "epoch": 5.81, "learning_rate": 1.9984607638888887e-06, "loss": 2.8001, "step": 417000 }, { "epoch": 5.82, "learning_rate": 1.9942072916666672e-06, "loss": 2.8389, "step": 417500 }, { "epoch": 5.82, "learning_rate": 1.989953819444445e-06, "loss": 2.8112, "step": 418000 }, { "epoch": 5.83, "learning_rate": 1.9857003472222225e-06, "loss": 2.8256, "step": 418500 }, { "epoch": 5.84, "learning_rate": 1.9814553819444445e-06, "loss": 2.8145, "step": 419000 }, { "epoch": 5.84, "learning_rate": 1.9772019097222226e-06, "loss": 2.8222, "step": 419500 }, { "epoch": 5.85, "learning_rate": 1.9729484375e-06, "loss": 2.8176, "step": 420000 }, { "epoch": 5.86, "learning_rate": 1.9687034722222223e-06, "loss": 2.8256, "step": 420500 }, { "epoch": 5.87, "learning_rate": 1.96445e-06, "loss": 2.8239, "step": 421000 }, { "epoch": 5.87, "learning_rate": 1.960196527777778e-06, "loss": 2.8322, "step": 421500 }, { "epoch": 5.88, "learning_rate": 1.955943055555556e-06, "loss": 2.8346, "step": 422000 }, { "epoch": 5.89, "learning_rate": 1.9516895833333336e-06, "loss": 2.8255, "step": 422500 }, { "epoch": 5.89, "learning_rate": 1.9474361111111112e-06, "loss": 2.8222, "step": 423000 }, { "epoch": 5.9, "learning_rate": 1.9431826388888893e-06, "loss": 2.8244, "step": 423500 }, { "epoch": 5.91, "learning_rate": 1.938929166666667e-06, "loss": 2.8334, "step": 424000 }, { "epoch": 5.91, "learning_rate": 1.934684201388889e-06, "loss": 2.8224, "step": 424500 }, { "epoch": 5.92, "learning_rate": 1.9304392361111115e-06, "loss": 2.8211, "step": 425000 }, { "epoch": 5.93, "learning_rate": 1.926185763888889e-06, "loss": 2.8458, "step": 425500 }, { "epoch": 5.93, "learning_rate": 1.9219322916666667e-06, "loss": 2.8058, "step": 426000 }, { "epoch": 5.94, "learning_rate": 1.9176788194444443e-06, "loss": 2.8512, "step": 426500 }, { "epoch": 5.95, "learning_rate": 1.9134253472222224e-06, "loss": 2.809, "step": 427000 }, { "epoch": 5.96, "learning_rate": 1.9091718750000004e-06, "loss": 2.8273, "step": 427500 }, { "epoch": 5.96, "learning_rate": 1.904918402777778e-06, "loss": 2.8381, "step": 428000 }, { "epoch": 5.97, "learning_rate": 1.9006734375000001e-06, "loss": 2.8201, "step": 428500 }, { "epoch": 5.98, "learning_rate": 1.896419965277778e-06, "loss": 2.8257, "step": 429000 }, { "epoch": 5.98, "learning_rate": 1.8921664930555558e-06, "loss": 2.8287, "step": 429500 }, { "epoch": 5.99, "learning_rate": 1.8879130208333334e-06, "loss": 2.8369, "step": 430000 }, { "epoch": 6.0, "learning_rate": 1.8836595486111113e-06, "loss": 2.8348, "step": 430500 }, { "epoch": 6.0, "learning_rate": 1.8794060763888885e-06, "loss": 2.8321, "step": 431000 }, { "epoch": 6.01, "learning_rate": 1.8751526041666672e-06, "loss": 2.8143, "step": 431500 }, { "epoch": 6.02, "learning_rate": 1.8708991319444448e-06, "loss": 2.8112, "step": 432000 }, { "epoch": 6.03, "learning_rate": 1.8666541666666668e-06, "loss": 2.8206, "step": 432500 }, { "epoch": 6.03, "learning_rate": 1.862409201388889e-06, "loss": 2.817, "step": 433000 }, { "epoch": 6.04, "learning_rate": 1.858155729166667e-06, "loss": 2.8042, "step": 433500 }, { "epoch": 6.05, "learning_rate": 1.8539022569444446e-06, "loss": 2.8123, "step": 434000 }, { "epoch": 6.05, "learning_rate": 1.8496487847222222e-06, "loss": 2.7912, "step": 434500 }, { "epoch": 6.06, "learning_rate": 1.8453953124999998e-06, "loss": 2.8157, "step": 435000 }, { "epoch": 6.07, "learning_rate": 1.8411418402777783e-06, "loss": 2.8023, "step": 435500 }, { "epoch": 6.07, "learning_rate": 1.8368968750000006e-06, "loss": 2.8037, "step": 436000 }, { "epoch": 6.08, "learning_rate": 1.8326434027777778e-06, "loss": 2.7876, "step": 436500 }, { "epoch": 6.09, "learning_rate": 1.8283899305555556e-06, "loss": 2.7751, "step": 437000 }, { "epoch": 6.1, "learning_rate": 1.8241364583333337e-06, "loss": 2.7996, "step": 437500 }, { "epoch": 6.1, "learning_rate": 1.8198829861111115e-06, "loss": 2.8035, "step": 438000 }, { "epoch": 6.11, "learning_rate": 1.8156295138888887e-06, "loss": 2.8158, "step": 438500 }, { "epoch": 6.12, "learning_rate": 1.8113760416666665e-06, "loss": 2.8115, "step": 439000 }, { "epoch": 6.12, "learning_rate": 1.807122569444445e-06, "loss": 2.8153, "step": 439500 }, { "epoch": 6.13, "learning_rate": 1.802877604166667e-06, "loss": 2.8082, "step": 440000 }, { "epoch": 6.14, "learning_rate": 1.7986241319444447e-06, "loss": 2.8053, "step": 440500 }, { "epoch": 6.14, "learning_rate": 1.7943706597222223e-06, "loss": 2.8283, "step": 441000 }, { "epoch": 6.15, "learning_rate": 1.7901171875000004e-06, "loss": 2.8127, "step": 441500 }, { "epoch": 6.16, "learning_rate": 1.7858722222222224e-06, "loss": 2.8448, "step": 442000 }, { "epoch": 6.16, "learning_rate": 1.78161875e-06, "loss": 2.8294, "step": 442500 }, { "epoch": 6.17, "learning_rate": 1.7773652777777777e-06, "loss": 2.8089, "step": 443000 }, { "epoch": 6.18, "learning_rate": 1.7731118055555557e-06, "loss": 2.8223, "step": 443500 }, { "epoch": 6.19, "learning_rate": 1.7688668402777778e-06, "loss": 2.8255, "step": 444000 }, { "epoch": 6.19, "learning_rate": 1.7646133680555554e-06, "loss": 2.8177, "step": 444500 }, { "epoch": 6.2, "learning_rate": 1.7603598958333335e-06, "loss": 2.8101, "step": 445000 }, { "epoch": 6.21, "learning_rate": 1.7561064236111113e-06, "loss": 2.789, "step": 445500 }, { "epoch": 6.21, "learning_rate": 1.7518529513888891e-06, "loss": 2.7933, "step": 446000 }, { "epoch": 6.22, "learning_rate": 1.7475994791666668e-06, "loss": 2.7962, "step": 446500 }, { "epoch": 6.23, "learning_rate": 1.7433460069444444e-06, "loss": 2.8138, "step": 447000 }, { "epoch": 6.23, "learning_rate": 1.7390925347222222e-06, "loss": 2.8133, "step": 447500 }, { "epoch": 6.24, "learning_rate": 1.734856076388889e-06, "loss": 2.7906, "step": 448000 }, { "epoch": 6.25, "learning_rate": 1.7306026041666666e-06, "loss": 2.8106, "step": 448500 }, { "epoch": 6.26, "learning_rate": 1.726349131944445e-06, "loss": 2.8054, "step": 449000 }, { "epoch": 6.26, "learning_rate": 1.7220956597222227e-06, "loss": 2.8087, "step": 449500 }, { "epoch": 6.27, "learning_rate": 1.7178421875000003e-06, "loss": 2.8293, "step": 450000 }, { "epoch": 6.28, "learning_rate": 1.7135887152777781e-06, "loss": 2.8109, "step": 450500 }, { "epoch": 6.28, "learning_rate": 1.7093352430555553e-06, "loss": 2.7943, "step": 451000 }, { "epoch": 6.29, "learning_rate": 1.7050817708333336e-06, "loss": 2.793, "step": 451500 }, { "epoch": 6.3, "learning_rate": 1.7008368055555557e-06, "loss": 2.7984, "step": 452000 }, { "epoch": 6.3, "learning_rate": 1.6965833333333335e-06, "loss": 2.8314, "step": 452500 }, { "epoch": 6.31, "learning_rate": 1.692329861111111e-06, "loss": 2.8224, "step": 453000 }, { "epoch": 6.32, "learning_rate": 1.6880763888888894e-06, "loss": 2.8134, "step": 453500 }, { "epoch": 6.32, "learning_rate": 1.683822916666667e-06, "loss": 2.7947, "step": 454000 }, { "epoch": 6.33, "learning_rate": 1.6795694444444446e-06, "loss": 2.8263, "step": 454500 }, { "epoch": 6.34, "learning_rate": 1.6753159722222223e-06, "loss": 2.8167, "step": 455000 }, { "epoch": 6.35, "learning_rate": 1.6710625000000003e-06, "loss": 2.8025, "step": 455500 }, { "epoch": 6.35, "learning_rate": 1.6668175347222224e-06, "loss": 2.8089, "step": 456000 }, { "epoch": 6.36, "learning_rate": 1.6625640625e-06, "loss": 2.804, "step": 456500 }, { "epoch": 6.37, "learning_rate": 1.6583105902777776e-06, "loss": 2.8116, "step": 457000 }, { "epoch": 6.37, "learning_rate": 1.654057118055556e-06, "loss": 2.8084, "step": 457500 }, { "epoch": 6.38, "learning_rate": 1.6498121527777784e-06, "loss": 2.8117, "step": 458000 }, { "epoch": 6.39, "learning_rate": 1.6455586805555556e-06, "loss": 2.8105, "step": 458500 }, { "epoch": 6.39, "learning_rate": 1.6413052083333334e-06, "loss": 2.8115, "step": 459000 }, { "epoch": 6.4, "learning_rate": 1.6370517361111115e-06, "loss": 2.7928, "step": 459500 }, { "epoch": 6.41, "learning_rate": 1.6328067708333333e-06, "loss": 2.8119, "step": 460000 }, { "epoch": 6.42, "learning_rate": 1.6285532986111111e-06, "loss": 2.8158, "step": 460500 }, { "epoch": 6.42, "learning_rate": 1.6242998263888888e-06, "loss": 2.8183, "step": 461000 }, { "epoch": 6.43, "learning_rate": 1.620046354166667e-06, "loss": 2.8114, "step": 461500 }, { "epoch": 6.44, "learning_rate": 1.6157928819444442e-06, "loss": 2.8105, "step": 462000 }, { "epoch": 6.44, "learning_rate": 1.6115479166666665e-06, "loss": 2.8069, "step": 462500 }, { "epoch": 6.45, "learning_rate": 1.6072944444444441e-06, "loss": 2.8118, "step": 463000 }, { "epoch": 6.46, "learning_rate": 1.6030409722222226e-06, "loss": 2.8225, "step": 463500 }, { "epoch": 6.46, "learning_rate": 1.5987875000000002e-06, "loss": 2.8067, "step": 464000 }, { "epoch": 6.47, "learning_rate": 1.5945425347222223e-06, "loss": 2.8069, "step": 464500 }, { "epoch": 6.48, "learning_rate": 1.5902890625000003e-06, "loss": 2.7902, "step": 465000 }, { "epoch": 6.49, "learning_rate": 1.586035590277778e-06, "loss": 2.7965, "step": 465500 }, { "epoch": 6.49, "learning_rate": 1.5817821180555556e-06, "loss": 2.8137, "step": 466000 }, { "epoch": 6.5, "learning_rate": 1.5775371527777776e-06, "loss": 2.7941, "step": 466500 }, { "epoch": 6.51, "learning_rate": 1.5732836805555563e-06, "loss": 2.8074, "step": 467000 }, { "epoch": 6.51, "learning_rate": 1.5690302083333335e-06, "loss": 2.8056, "step": 467500 }, { "epoch": 6.52, "learning_rate": 1.5647767361111114e-06, "loss": 2.804, "step": 468000 }, { "epoch": 6.53, "learning_rate": 1.5605317708333334e-06, "loss": 2.8002, "step": 468500 }, { "epoch": 6.53, "learning_rate": 1.5562782986111113e-06, "loss": 2.835, "step": 469000 }, { "epoch": 6.54, "learning_rate": 1.5520248263888891e-06, "loss": 2.8121, "step": 469500 }, { "epoch": 6.55, "learning_rate": 1.5477713541666667e-06, "loss": 2.7782, "step": 470000 }, { "epoch": 6.55, "learning_rate": 1.5435263888888888e-06, "loss": 2.8107, "step": 470500 }, { "epoch": 6.56, "learning_rate": 1.5392729166666666e-06, "loss": 2.81, "step": 471000 }, { "epoch": 6.57, "learning_rate": 1.5350194444444445e-06, "loss": 2.8008, "step": 471500 }, { "epoch": 6.58, "learning_rate": 1.5307659722222225e-06, "loss": 2.8294, "step": 472000 }, { "epoch": 6.58, "learning_rate": 1.5265210069444442e-06, "loss": 2.8149, "step": 472500 }, { "epoch": 6.59, "learning_rate": 1.522276041666667e-06, "loss": 2.8073, "step": 473000 }, { "epoch": 6.6, "learning_rate": 1.5180225694444447e-06, "loss": 2.801, "step": 473500 }, { "epoch": 6.6, "learning_rate": 1.5137690972222225e-06, "loss": 2.8211, "step": 474000 }, { "epoch": 6.61, "learning_rate": 1.5095156249999997e-06, "loss": 2.8333, "step": 474500 }, { "epoch": 6.62, "learning_rate": 1.505262152777778e-06, "loss": 2.8257, "step": 475000 }, { "epoch": 6.62, "learning_rate": 1.5010086805555556e-06, "loss": 2.8251, "step": 475500 }, { "epoch": 6.63, "learning_rate": 1.4967637152777779e-06, "loss": 2.8062, "step": 476000 }, { "epoch": 6.64, "learning_rate": 1.492510243055556e-06, "loss": 2.8145, "step": 476500 }, { "epoch": 6.65, "learning_rate": 1.4882567708333338e-06, "loss": 2.8073, "step": 477000 }, { "epoch": 6.65, "learning_rate": 1.4840032986111114e-06, "loss": 2.7967, "step": 477500 }, { "epoch": 6.66, "learning_rate": 1.479749826388889e-06, "loss": 2.7949, "step": 478000 }, { "epoch": 6.67, "learning_rate": 1.4754963541666667e-06, "loss": 2.8006, "step": 478500 }, { "epoch": 6.67, "learning_rate": 1.4712428819444447e-06, "loss": 2.8169, "step": 479000 }, { "epoch": 6.68, "learning_rate": 1.4669894097222223e-06, "loss": 2.8238, "step": 479500 }, { "epoch": 6.69, "learning_rate": 1.4627359375e-06, "loss": 2.8261, "step": 480000 }, { "epoch": 6.69, "learning_rate": 1.458490972222222e-06, "loss": 2.8045, "step": 480500 }, { "epoch": 6.7, "learning_rate": 1.4542375000000005e-06, "loss": 2.8009, "step": 481000 }, { "epoch": 6.71, "learning_rate": 1.4499840277777783e-06, "loss": 2.8209, "step": 481500 }, { "epoch": 6.72, "learning_rate": 1.4457305555555555e-06, "loss": 2.8186, "step": 482000 }, { "epoch": 6.72, "learning_rate": 1.4414855902777778e-06, "loss": 2.8115, "step": 482500 }, { "epoch": 6.73, "learning_rate": 1.4372406250000005e-06, "loss": 2.7988, "step": 483000 }, { "epoch": 6.74, "learning_rate": 1.4329871527777777e-06, "loss": 2.791, "step": 483500 }, { "epoch": 6.74, "learning_rate": 1.4287336805555555e-06, "loss": 2.8064, "step": 484000 }, { "epoch": 6.75, "learning_rate": 1.424488715277778e-06, "loss": 2.8008, "step": 484500 }, { "epoch": 6.76, "learning_rate": 1.4202352430555559e-06, "loss": 2.7846, "step": 485000 }, { "epoch": 6.76, "learning_rate": 1.415981770833333e-06, "loss": 2.8192, "step": 485500 }, { "epoch": 6.77, "learning_rate": 1.4117368055555553e-06, "loss": 2.7963, "step": 486000 }, { "epoch": 6.78, "learning_rate": 1.4074833333333338e-06, "loss": 2.8059, "step": 486500 }, { "epoch": 6.78, "learning_rate": 1.4032298611111114e-06, "loss": 2.8261, "step": 487000 }, { "epoch": 6.79, "learning_rate": 1.398976388888889e-06, "loss": 2.8126, "step": 487500 }, { "epoch": 6.8, "learning_rate": 1.3947229166666667e-06, "loss": 2.8273, "step": 488000 }, { "epoch": 6.81, "learning_rate": 1.3904694444444447e-06, "loss": 2.8116, "step": 488500 }, { "epoch": 6.81, "learning_rate": 1.3862159722222224e-06, "loss": 2.8293, "step": 489000 }, { "epoch": 6.82, "learning_rate": 1.3819625e-06, "loss": 2.8008, "step": 489500 }, { "epoch": 6.83, "learning_rate": 1.3777090277777776e-06, "loss": 2.8145, "step": 490000 }, { "epoch": 6.83, "learning_rate": 1.3734555555555555e-06, "loss": 2.7985, "step": 490500 }, { "epoch": 6.84, "learning_rate": 1.3692020833333335e-06, "loss": 2.8154, "step": 491000 }, { "epoch": 6.85, "learning_rate": 1.3649486111111113e-06, "loss": 2.8174, "step": 491500 }, { "epoch": 6.85, "learning_rate": 1.360695138888889e-06, "loss": 2.8222, "step": 492000 }, { "epoch": 6.86, "learning_rate": 1.3564416666666666e-06, "loss": 2.7957, "step": 492500 }, { "epoch": 6.87, "learning_rate": 1.3521881944444446e-06, "loss": 2.8146, "step": 493000 }, { "epoch": 6.88, "learning_rate": 1.3479347222222223e-06, "loss": 2.8174, "step": 493500 }, { "epoch": 6.88, "learning_rate": 1.3436897569444443e-06, "loss": 2.8001, "step": 494000 }, { "epoch": 6.89, "learning_rate": 1.339436284722222e-06, "loss": 2.824, "step": 494500 }, { "epoch": 6.9, "learning_rate": 1.3351828125000004e-06, "loss": 2.8116, "step": 495000 }, { "epoch": 6.9, "learning_rate": 1.330929340277778e-06, "loss": 2.8288, "step": 495500 }, { "epoch": 6.91, "learning_rate": 1.3266843750000003e-06, "loss": 2.8051, "step": 496000 }, { "epoch": 6.92, "learning_rate": 1.3224309027777777e-06, "loss": 2.8137, "step": 496500 }, { "epoch": 6.92, "learning_rate": 1.3181774305555558e-06, "loss": 2.8232, "step": 497000 }, { "epoch": 6.93, "learning_rate": 1.3139239583333336e-06, "loss": 2.8078, "step": 497500 }, { "epoch": 6.94, "learning_rate": 1.3096789930555553e-06, "loss": 2.8099, "step": 498000 }, { "epoch": 6.94, "learning_rate": 1.305425520833333e-06, "loss": 2.8348, "step": 498500 }, { "epoch": 6.95, "learning_rate": 1.3011805555555556e-06, "loss": 2.8256, "step": 499000 }, { "epoch": 6.96, "learning_rate": 1.2969270833333336e-06, "loss": 2.8088, "step": 499500 }, { "epoch": 6.97, "learning_rate": 1.2926736111111113e-06, "loss": 2.8246, "step": 500000 }, { "epoch": 6.97, "eval_gen_len": 19.9977, "eval_loss": 2.7420477867126465, "eval_rouge1": 0.2999, "eval_rouge2": 0.1775, "eval_rougeL": 0.2543, "eval_rougeLsum": 0.2853, "eval_runtime": 894.3032, "eval_samples_per_second": 14.948, "eval_steps_per_second": 3.737, "step": 500000 }, { "epoch": 6.97, "learning_rate": 1.2884201388888893e-06, "loss": 2.8164, "step": 500500 }, { "epoch": 6.98, "learning_rate": 1.284166666666667e-06, "loss": 2.8191, "step": 501000 }, { "epoch": 6.99, "learning_rate": 1.279921701388889e-06, "loss": 2.8262, "step": 501500 }, { "epoch": 6.99, "learning_rate": 1.2756682291666666e-06, "loss": 2.8011, "step": 502000 }, { "epoch": 7.0, "learning_rate": 1.2714147569444447e-06, "loss": 2.7934, "step": 502500 }, { "epoch": 7.01, "learning_rate": 1.2671612847222223e-06, "loss": 2.8052, "step": 503000 }, { "epoch": 7.01, "learning_rate": 1.2629078125e-06, "loss": 2.7867, "step": 503500 }, { "epoch": 7.02, "learning_rate": 1.258654340277778e-06, "loss": 2.7945, "step": 504000 }, { "epoch": 7.03, "learning_rate": 1.2544093750000005e-06, "loss": 2.788, "step": 504500 }, { "epoch": 7.04, "learning_rate": 1.2501559027777783e-06, "loss": 2.8143, "step": 505000 }, { "epoch": 7.04, "learning_rate": 1.2459024305555557e-06, "loss": 2.787, "step": 505500 }, { "epoch": 7.05, "learning_rate": 1.2416489583333333e-06, "loss": 2.7988, "step": 506000 }, { "epoch": 7.06, "learning_rate": 1.237395486111111e-06, "loss": 2.7957, "step": 506500 }, { "epoch": 7.06, "learning_rate": 1.233142013888889e-06, "loss": 2.8049, "step": 507000 }, { "epoch": 7.07, "learning_rate": 1.2288885416666666e-06, "loss": 2.7759, "step": 507500 }, { "epoch": 7.08, "learning_rate": 1.2246350694444447e-06, "loss": 2.7944, "step": 508000 }, { "epoch": 7.08, "learning_rate": 1.2203901041666672e-06, "loss": 2.7896, "step": 508500 }, { "epoch": 7.09, "learning_rate": 1.2161366319444448e-06, "loss": 2.8019, "step": 509000 }, { "epoch": 7.1, "learning_rate": 1.2118831597222224e-06, "loss": 2.7732, "step": 509500 }, { "epoch": 7.11, "learning_rate": 1.2076296875e-06, "loss": 2.824, "step": 510000 }, { "epoch": 7.11, "learning_rate": 1.2033762152777777e-06, "loss": 2.7803, "step": 510500 }, { "epoch": 7.12, "learning_rate": 1.1991227430555557e-06, "loss": 2.7941, "step": 511000 }, { "epoch": 7.13, "learning_rate": 1.1948692708333334e-06, "loss": 2.7869, "step": 511500 }, { "epoch": 7.13, "learning_rate": 1.190615798611111e-06, "loss": 2.7976, "step": 512000 }, { "epoch": 7.14, "learning_rate": 1.186362326388889e-06, "loss": 2.8163, "step": 512500 }, { "epoch": 7.15, "learning_rate": 1.1821173611111115e-06, "loss": 2.7951, "step": 513000 }, { "epoch": 7.15, "learning_rate": 1.1778638888888891e-06, "loss": 2.7913, "step": 513500 }, { "epoch": 7.16, "learning_rate": 1.1736104166666668e-06, "loss": 2.7938, "step": 514000 }, { "epoch": 7.17, "learning_rate": 1.1693569444444444e-06, "loss": 2.8009, "step": 514500 }, { "epoch": 7.17, "learning_rate": 1.1651119791666669e-06, "loss": 2.7747, "step": 515000 }, { "epoch": 7.18, "learning_rate": 1.1608585069444445e-06, "loss": 2.7833, "step": 515500 }, { "epoch": 7.19, "learning_rate": 1.1566050347222221e-06, "loss": 2.8013, "step": 516000 }, { "epoch": 7.2, "learning_rate": 1.1523515624999998e-06, "loss": 2.8089, "step": 516500 }, { "epoch": 7.2, "learning_rate": 1.1481065972222227e-06, "loss": 2.8074, "step": 517000 }, { "epoch": 7.21, "learning_rate": 1.1438531250000003e-06, "loss": 2.7884, "step": 517500 }, { "epoch": 7.22, "learning_rate": 1.139599652777778e-06, "loss": 2.7911, "step": 518000 }, { "epoch": 7.22, "learning_rate": 1.1353461805555555e-06, "loss": 2.8035, "step": 518500 }, { "epoch": 7.23, "learning_rate": 1.131101215277778e-06, "loss": 2.8027, "step": 519000 }, { "epoch": 7.24, "learning_rate": 1.12685625e-06, "loss": 2.7828, "step": 519500 }, { "epoch": 7.24, "learning_rate": 1.1226027777777777e-06, "loss": 2.8245, "step": 520000 }, { "epoch": 7.25, "learning_rate": 1.1183493055555558e-06, "loss": 2.7839, "step": 520500 }, { "epoch": 7.26, "learning_rate": 1.1140958333333334e-06, "loss": 2.7935, "step": 521000 }, { "epoch": 7.27, "learning_rate": 1.109842361111111e-06, "loss": 2.8045, "step": 521500 }, { "epoch": 7.27, "learning_rate": 1.105588888888889e-06, "loss": 2.8039, "step": 522000 }, { "epoch": 7.28, "learning_rate": 1.1013354166666667e-06, "loss": 2.7892, "step": 522500 }, { "epoch": 7.29, "learning_rate": 1.0970819444444447e-06, "loss": 2.8009, "step": 523000 }, { "epoch": 7.29, "learning_rate": 1.0928284722222224e-06, "loss": 2.7927, "step": 523500 }, { "epoch": 7.3, "learning_rate": 1.0885835069444444e-06, "loss": 2.7763, "step": 524000 }, { "epoch": 7.31, "learning_rate": 1.0843300347222225e-06, "loss": 2.8008, "step": 524500 }, { "epoch": 7.31, "learning_rate": 1.0800765625e-06, "loss": 2.7839, "step": 525000 }, { "epoch": 7.32, "learning_rate": 1.0758230902777777e-06, "loss": 2.7787, "step": 525500 }, { "epoch": 7.33, "learning_rate": 1.0715781249999998e-06, "loss": 2.7914, "step": 526000 }, { "epoch": 7.34, "learning_rate": 1.0673246527777783e-06, "loss": 2.7903, "step": 526500 }, { "epoch": 7.34, "learning_rate": 1.0630711805555559e-06, "loss": 2.7869, "step": 527000 }, { "epoch": 7.35, "learning_rate": 1.0588177083333335e-06, "loss": 2.7885, "step": 527500 }, { "epoch": 7.36, "learning_rate": 1.0545727430555556e-06, "loss": 2.782, "step": 528000 }, { "epoch": 7.36, "learning_rate": 1.0503192708333336e-06, "loss": 2.7775, "step": 528500 }, { "epoch": 7.37, "learning_rate": 1.0460657986111112e-06, "loss": 2.7863, "step": 529000 }, { "epoch": 7.38, "learning_rate": 1.0418123263888889e-06, "loss": 2.7904, "step": 529500 }, { "epoch": 7.38, "learning_rate": 1.037567361111111e-06, "loss": 2.8, "step": 530000 }, { "epoch": 7.39, "learning_rate": 1.0333138888888892e-06, "loss": 2.8023, "step": 530500 }, { "epoch": 7.4, "learning_rate": 1.0290604166666668e-06, "loss": 2.7947, "step": 531000 }, { "epoch": 7.4, "learning_rate": 1.0248069444444447e-06, "loss": 2.7946, "step": 531500 }, { "epoch": 7.41, "learning_rate": 1.0205619791666665e-06, "loss": 2.7859, "step": 532000 }, { "epoch": 7.42, "learning_rate": 1.0163085069444448e-06, "loss": 2.7949, "step": 532500 }, { "epoch": 7.43, "learning_rate": 1.0120550347222224e-06, "loss": 2.7738, "step": 533000 }, { "epoch": 7.43, "learning_rate": 1.0078100694444444e-06, "loss": 2.7934, "step": 533500 }, { "epoch": 7.44, "learning_rate": 1.003556597222222e-06, "loss": 2.8105, "step": 534000 }, { "epoch": 7.45, "learning_rate": 9.993031250000001e-07, "loss": 2.8025, "step": 534500 }, { "epoch": 7.45, "learning_rate": 9.95049652777778e-07, "loss": 2.8159, "step": 535000 }, { "epoch": 7.46, "learning_rate": 9.907961805555556e-07, "loss": 2.8167, "step": 535500 }, { "epoch": 7.47, "learning_rate": 9.865427083333332e-07, "loss": 2.7768, "step": 536000 }, { "epoch": 7.47, "learning_rate": 9.822892361111115e-07, "loss": 2.7976, "step": 536500 }, { "epoch": 7.48, "learning_rate": 9.78035763888889e-07, "loss": 2.8063, "step": 537000 }, { "epoch": 7.49, "learning_rate": 9.737993055555556e-07, "loss": 2.7996, "step": 537500 }, { "epoch": 7.5, "learning_rate": 9.695458333333336e-07, "loss": 2.8008, "step": 538000 }, { "epoch": 7.5, "learning_rate": 9.652923611111113e-07, "loss": 2.7913, "step": 538500 }, { "epoch": 7.51, "learning_rate": 9.610388888888889e-07, "loss": 2.8131, "step": 539000 }, { "epoch": 7.52, "learning_rate": 9.567854166666665e-07, "loss": 2.802, "step": 539500 }, { "epoch": 7.52, "learning_rate": 9.525319444444441e-07, "loss": 2.8064, "step": 540000 }, { "epoch": 7.53, "learning_rate": 9.482784722222225e-07, "loss": 2.805, "step": 540500 }, { "epoch": 7.54, "learning_rate": 9.44025e-07, "loss": 2.7848, "step": 541000 }, { "epoch": 7.54, "learning_rate": 9.397800347222222e-07, "loss": 2.7907, "step": 541500 }, { "epoch": 7.55, "learning_rate": 9.355265624999998e-07, "loss": 2.7835, "step": 542000 }, { "epoch": 7.56, "learning_rate": 9.31273090277778e-07, "loss": 2.7738, "step": 542500 }, { "epoch": 7.56, "learning_rate": 9.270196180555557e-07, "loss": 2.7925, "step": 543000 }, { "epoch": 7.57, "learning_rate": 9.227661458333334e-07, "loss": 2.7831, "step": 543500 }, { "epoch": 7.58, "learning_rate": 9.185211805555559e-07, "loss": 2.799, "step": 544000 }, { "epoch": 7.59, "learning_rate": 9.142677083333336e-07, "loss": 2.7945, "step": 544500 }, { "epoch": 7.59, "learning_rate": 9.100227430555555e-07, "loss": 2.7981, "step": 545000 }, { "epoch": 7.6, "learning_rate": 9.057692708333332e-07, "loss": 2.8008, "step": 545500 }, { "epoch": 7.61, "learning_rate": 9.015157986111114e-07, "loss": 2.7949, "step": 546000 }, { "epoch": 7.61, "learning_rate": 8.972623263888891e-07, "loss": 2.7828, "step": 546500 }, { "epoch": 7.62, "learning_rate": 8.930088541666668e-07, "loss": 2.8011, "step": 547000 }, { "epoch": 7.63, "learning_rate": 8.887553819444445e-07, "loss": 2.8135, "step": 547500 }, { "epoch": 7.63, "learning_rate": 8.845019097222221e-07, "loss": 2.7942, "step": 548000 }, { "epoch": 7.64, "learning_rate": 8.802484375000004e-07, "loss": 2.8105, "step": 548500 }, { "epoch": 7.65, "learning_rate": 8.760119791666665e-07, "loss": 2.8071, "step": 549000 }, { "epoch": 7.66, "learning_rate": 8.717585069444443e-07, "loss": 2.7993, "step": 549500 }, { "epoch": 7.66, "learning_rate": 8.675050347222224e-07, "loss": 2.7991, "step": 550000 }, { "epoch": 7.67, "learning_rate": 8.632515625000002e-07, "loss": 2.8152, "step": 550500 }, { "epoch": 7.68, "learning_rate": 8.589980902777778e-07, "loss": 2.7994, "step": 551000 }, { "epoch": 7.68, "learning_rate": 8.547446180555555e-07, "loss": 2.8152, "step": 551500 }, { "epoch": 7.69, "learning_rate": 8.504911458333332e-07, "loss": 2.8158, "step": 552000 }, { "epoch": 7.7, "learning_rate": 8.462376736111114e-07, "loss": 2.8117, "step": 552500 }, { "epoch": 7.7, "learning_rate": 8.419927083333334e-07, "loss": 2.8052, "step": 553000 }, { "epoch": 7.71, "learning_rate": 8.377477430555554e-07, "loss": 2.8123, "step": 553500 }, { "epoch": 7.72, "learning_rate": 8.334942708333337e-07, "loss": 2.7848, "step": 554000 }, { "epoch": 7.73, "learning_rate": 8.292407986111112e-07, "loss": 2.8049, "step": 554500 }, { "epoch": 7.73, "learning_rate": 8.249873263888889e-07, "loss": 2.7832, "step": 555000 }, { "epoch": 7.74, "learning_rate": 8.207338541666665e-07, "loss": 2.801, "step": 555500 }, { "epoch": 7.75, "learning_rate": 8.164803819444447e-07, "loss": 2.7943, "step": 556000 }, { "epoch": 7.75, "learning_rate": 8.122269097222223e-07, "loss": 2.8053, "step": 556500 }, { "epoch": 7.76, "learning_rate": 8.079819444444444e-07, "loss": 2.7998, "step": 557000 }, { "epoch": 7.77, "learning_rate": 8.03728472222222e-07, "loss": 2.8004, "step": 557500 }, { "epoch": 7.77, "learning_rate": 7.994750000000003e-07, "loss": 2.8, "step": 558000 }, { "epoch": 7.78, "learning_rate": 7.952215277777779e-07, "loss": 2.7873, "step": 558500 }, { "epoch": 7.79, "learning_rate": 7.909680555555555e-07, "loss": 2.8024, "step": 559000 }, { "epoch": 7.79, "learning_rate": 7.867145833333333e-07, "loss": 2.7802, "step": 559500 }, { "epoch": 7.8, "learning_rate": 7.824696180555559e-07, "loss": 2.7845, "step": 560000 }, { "epoch": 7.81, "learning_rate": 7.782161458333334e-07, "loss": 2.8044, "step": 560500 }, { "epoch": 7.82, "learning_rate": 7.739626736111111e-07, "loss": 2.7849, "step": 561000 }, { "epoch": 7.82, "learning_rate": 7.697092013888887e-07, "loss": 2.7986, "step": 561500 }, { "epoch": 7.83, "learning_rate": 7.65455729166667e-07, "loss": 2.802, "step": 562000 }, { "epoch": 7.84, "learning_rate": 7.612022569444446e-07, "loss": 2.7929, "step": 562500 }, { "epoch": 7.84, "learning_rate": 7.569572916666668e-07, "loss": 2.8, "step": 563000 }, { "epoch": 7.85, "learning_rate": 7.527038194444443e-07, "loss": 2.8034, "step": 563500 }, { "epoch": 7.86, "learning_rate": 7.484503472222225e-07, "loss": 2.7871, "step": 564000 }, { "epoch": 7.86, "learning_rate": 7.441968750000002e-07, "loss": 2.8139, "step": 564500 }, { "epoch": 7.87, "learning_rate": 7.399434027777778e-07, "loss": 2.7982, "step": 565000 }, { "epoch": 7.88, "learning_rate": 7.356899305555555e-07, "loss": 2.7998, "step": 565500 }, { "epoch": 7.89, "learning_rate": 7.314364583333331e-07, "loss": 2.7829, "step": 566000 }, { "epoch": 7.89, "learning_rate": 7.271829861111114e-07, "loss": 2.7698, "step": 566500 }, { "epoch": 7.9, "learning_rate": 7.229380208333334e-07, "loss": 2.786, "step": 567000 }, { "epoch": 7.91, "learning_rate": 7.18684548611111e-07, "loss": 2.7959, "step": 567500 }, { "epoch": 7.91, "learning_rate": 7.144310763888887e-07, "loss": 2.8125, "step": 568000 }, { "epoch": 7.92, "learning_rate": 7.101776041666669e-07, "loss": 2.8022, "step": 568500 }, { "epoch": 7.93, "learning_rate": 7.059326388888889e-07, "loss": 2.8261, "step": 569000 }, { "epoch": 7.93, "learning_rate": 7.016791666666665e-07, "loss": 2.8114, "step": 569500 }, { "epoch": 7.94, "learning_rate": 6.974256944444448e-07, "loss": 2.7959, "step": 570000 }, { "epoch": 7.95, "learning_rate": 6.931722222222224e-07, "loss": 2.8008, "step": 570500 }, { "epoch": 7.95, "learning_rate": 6.889272569444445e-07, "loss": 2.7952, "step": 571000 }, { "epoch": 7.96, "learning_rate": 6.846737847222221e-07, "loss": 2.7794, "step": 571500 }, { "epoch": 7.97, "learning_rate": 6.804203125000003e-07, "loss": 2.7851, "step": 572000 }, { "epoch": 7.98, "learning_rate": 6.761753472222223e-07, "loss": 2.7843, "step": 572500 }, { "epoch": 7.98, "learning_rate": 6.719218749999999e-07, "loss": 2.8172, "step": 573000 }, { "epoch": 7.99, "learning_rate": 6.676684027777775e-07, "loss": 2.7935, "step": 573500 }, { "epoch": 8.0, "learning_rate": 6.634149305555558e-07, "loss": 2.8004, "step": 574000 }, { "epoch": 8.0, "learning_rate": 6.591699652777779e-07, "loss": 2.79, "step": 574500 }, { "epoch": 8.01, "learning_rate": 6.549164930555554e-07, "loss": 2.7959, "step": 575000 }, { "epoch": 8.02, "learning_rate": 6.506630208333331e-07, "loss": 2.7923, "step": 575500 }, { "epoch": 8.02, "learning_rate": 6.464095486111113e-07, "loss": 2.7841, "step": 576000 }, { "epoch": 8.03, "learning_rate": 6.42156076388889e-07, "loss": 2.788, "step": 576500 }, { "epoch": 8.04, "learning_rate": 6.379026041666666e-07, "loss": 2.7968, "step": 577000 }, { "epoch": 8.05, "learning_rate": 6.336491319444444e-07, "loss": 2.7838, "step": 577500 }, { "epoch": 8.05, "learning_rate": 6.293956597222225e-07, "loss": 2.7803, "step": 578000 }, { "epoch": 8.06, "learning_rate": 6.251506944444445e-07, "loss": 2.773, "step": 578500 }, { "epoch": 8.07, "learning_rate": 6.208972222222222e-07, "loss": 2.7854, "step": 579000 }, { "epoch": 8.07, "learning_rate": 6.166437499999998e-07, "loss": 2.7804, "step": 579500 }, { "epoch": 8.08, "learning_rate": 6.123902777777781e-07, "loss": 2.8082, "step": 580000 }, { "epoch": 8.09, "learning_rate": 6.081368055555557e-07, "loss": 2.8016, "step": 580500 }, { "epoch": 8.09, "learning_rate": 6.038833333333334e-07, "loss": 2.8075, "step": 581000 }, { "epoch": 8.1, "learning_rate": 5.996298611111111e-07, "loss": 2.7771, "step": 581500 }, { "epoch": 8.11, "learning_rate": 5.953763888888887e-07, "loss": 2.7736, "step": 582000 }, { "epoch": 8.12, "learning_rate": 5.911314236111113e-07, "loss": 2.7955, "step": 582500 }, { "epoch": 8.12, "learning_rate": 5.868779513888889e-07, "loss": 2.8003, "step": 583000 }, { "epoch": 8.13, "learning_rate": 5.826244791666666e-07, "loss": 2.7899, "step": 583500 }, { "epoch": 8.14, "learning_rate": 5.783710069444442e-07, "loss": 2.8008, "step": 584000 }, { "epoch": 8.14, "learning_rate": 5.741260416666668e-07, "loss": 2.7903, "step": 584500 }, { "epoch": 8.15, "learning_rate": 5.698725694444445e-07, "loss": 2.7711, "step": 585000 }, { "epoch": 8.16, "learning_rate": 5.656190972222221e-07, "loss": 2.7718, "step": 585500 }, { "epoch": 8.16, "learning_rate": 5.613656250000003e-07, "loss": 2.7588, "step": 586000 }, { "epoch": 8.17, "learning_rate": 5.571206597222223e-07, "loss": 2.7749, "step": 586500 }, { "epoch": 8.18, "learning_rate": 5.528671875e-07, "loss": 2.7829, "step": 587000 }, { "epoch": 8.18, "learning_rate": 5.486137152777777e-07, "loss": 2.7816, "step": 587500 }, { "epoch": 8.19, "learning_rate": 5.443602430555559e-07, "loss": 2.7968, "step": 588000 }, { "epoch": 8.2, "learning_rate": 5.401067708333335e-07, "loss": 2.7727, "step": 588500 }, { "epoch": 8.21, "learning_rate": 5.358618055555555e-07, "loss": 2.7742, "step": 589000 }, { "epoch": 8.21, "learning_rate": 5.316083333333332e-07, "loss": 2.7692, "step": 589500 }, { "epoch": 8.22, "learning_rate": 5.273548611111113e-07, "loss": 2.7719, "step": 590000 }, { "epoch": 8.23, "learning_rate": 5.23101388888889e-07, "loss": 2.7895, "step": 590500 }, { "epoch": 8.23, "learning_rate": 5.18856423611111e-07, "loss": 2.7767, "step": 591000 }, { "epoch": 8.24, "learning_rate": 5.146029513888886e-07, "loss": 2.7981, "step": 591500 }, { "epoch": 8.25, "learning_rate": 5.103494791666669e-07, "loss": 2.7965, "step": 592000 }, { "epoch": 8.25, "learning_rate": 5.061045138888889e-07, "loss": 2.7841, "step": 592500 }, { "epoch": 8.26, "learning_rate": 5.018510416666666e-07, "loss": 2.7986, "step": 593000 }, { "epoch": 8.27, "learning_rate": 4.975975694444442e-07, "loss": 2.78, "step": 593500 }, { "epoch": 8.28, "learning_rate": 4.933440972222225e-07, "loss": 2.7823, "step": 594000 }, { "epoch": 8.28, "learning_rate": 4.890906250000001e-07, "loss": 2.7821, "step": 594500 }, { "epoch": 8.29, "learning_rate": 4.848371527777777e-07, "loss": 2.7913, "step": 595000 }, { "epoch": 8.3, "learning_rate": 4.805921874999998e-07, "loss": 2.7755, "step": 595500 }, { "epoch": 8.3, "learning_rate": 4.76338715277778e-07, "loss": 2.7903, "step": 596000 }, { "epoch": 8.31, "learning_rate": 4.720852430555556e-07, "loss": 2.7955, "step": 596500 }, { "epoch": 8.32, "learning_rate": 4.6783177083333334e-07, "loss": 2.7777, "step": 597000 }, { "epoch": 8.32, "learning_rate": 4.635782986111109e-07, "loss": 2.7806, "step": 597500 }, { "epoch": 8.33, "learning_rate": 4.5932482638888913e-07, "loss": 2.7839, "step": 598000 }, { "epoch": 8.34, "learning_rate": 4.550713541666668e-07, "loss": 2.7949, "step": 598500 }, { "epoch": 8.35, "learning_rate": 4.5081788194444444e-07, "loss": 2.7796, "step": 599000 }, { "epoch": 8.35, "learning_rate": 4.465729166666665e-07, "loss": 2.7986, "step": 599500 }, { "epoch": 8.36, "learning_rate": 4.4231944444444475e-07, "loss": 2.7757, "step": 600000 }, { "epoch": 8.36, "eval_gen_len": 19.9975, "eval_loss": 2.741455316543579, "eval_rouge1": 0.2976, "eval_rouge2": 0.1752, "eval_rougeL": 0.2519, "eval_rougeLsum": 0.2829, "eval_runtime": 882.0888, "eval_samples_per_second": 15.155, "eval_steps_per_second": 3.789, "step": 600000 }, { "epoch": 8.37, "learning_rate": 4.3806597222222233e-07, "loss": 2.7922, "step": 600500 }, { "epoch": 8.37, "learning_rate": 4.338125e-07, "loss": 2.7716, "step": 601000 }, { "epoch": 8.38, "learning_rate": 4.29567534722222e-07, "loss": 2.8045, "step": 601500 }, { "epoch": 8.39, "learning_rate": 4.2531406250000027e-07, "loss": 2.7861, "step": 602000 }, { "epoch": 8.39, "learning_rate": 4.2106059027777785e-07, "loss": 2.7802, "step": 602500 }, { "epoch": 8.4, "learning_rate": 4.1680711805555553e-07, "loss": 2.7811, "step": 603000 }, { "epoch": 8.41, "learning_rate": 4.125536458333332e-07, "loss": 2.783, "step": 603500 }, { "epoch": 8.41, "learning_rate": 4.083171875000001e-07, "loss": 2.8022, "step": 604000 }, { "epoch": 8.42, "learning_rate": 4.0406371527777774e-07, "loss": 2.7942, "step": 604500 }, { "epoch": 8.43, "learning_rate": 3.9981024305555537e-07, "loss": 2.7873, "step": 605000 }, { "epoch": 8.44, "learning_rate": 3.9555677083333363e-07, "loss": 2.7764, "step": 605500 }, { "epoch": 8.44, "learning_rate": 3.9130329861111126e-07, "loss": 2.7902, "step": 606000 }, { "epoch": 8.45, "learning_rate": 3.8704982638888894e-07, "loss": 2.8043, "step": 606500 }, { "epoch": 8.46, "learning_rate": 3.8279635416666657e-07, "loss": 2.7922, "step": 607000 }, { "epoch": 8.46, "learning_rate": 3.785428819444442e-07, "loss": 2.7908, "step": 607500 }, { "epoch": 8.47, "learning_rate": 3.742979166666668e-07, "loss": 2.7532, "step": 608000 }, { "epoch": 8.48, "learning_rate": 3.7004444444444446e-07, "loss": 2.8076, "step": 608500 }, { "epoch": 8.48, "learning_rate": 3.6579097222222214e-07, "loss": 2.7842, "step": 609000 }, { "epoch": 8.49, "learning_rate": 3.615374999999997e-07, "loss": 2.7756, "step": 609500 }, { "epoch": 8.5, "learning_rate": 3.572925347222223e-07, "loss": 2.7801, "step": 610000 }, { "epoch": 8.51, "learning_rate": 3.530390625e-07, "loss": 2.7784, "step": 610500 }, { "epoch": 8.51, "learning_rate": 3.4878559027777766e-07, "loss": 2.7938, "step": 611000 }, { "epoch": 8.52, "learning_rate": 3.4453211805555534e-07, "loss": 2.7746, "step": 611500 }, { "epoch": 8.53, "learning_rate": 3.402871527777778e-07, "loss": 2.7951, "step": 612000 }, { "epoch": 8.53, "learning_rate": 3.360336805555555e-07, "loss": 2.7847, "step": 612500 }, { "epoch": 8.54, "learning_rate": 3.3178020833333323e-07, "loss": 2.7867, "step": 613000 }, { "epoch": 8.55, "learning_rate": 3.275267361111114e-07, "loss": 2.7873, "step": 613500 }, { "epoch": 8.55, "learning_rate": 3.23273263888889e-07, "loss": 2.7873, "step": 614000 }, { "epoch": 8.56, "learning_rate": 3.1902829861111107e-07, "loss": 2.8178, "step": 614500 }, { "epoch": 8.57, "learning_rate": 3.147748263888887e-07, "loss": 2.7938, "step": 615000 }, { "epoch": 8.57, "learning_rate": 3.1052135416666696e-07, "loss": 2.7965, "step": 615500 }, { "epoch": 8.58, "learning_rate": 3.062678819444446e-07, "loss": 2.7871, "step": 616000 }, { "epoch": 8.59, "learning_rate": 3.0202291666666664e-07, "loss": 2.8107, "step": 616500 }, { "epoch": 8.6, "learning_rate": 2.9776944444444427e-07, "loss": 2.7973, "step": 617000 }, { "epoch": 8.6, "learning_rate": 2.935159722222224e-07, "loss": 2.7989, "step": 617500 }, { "epoch": 8.61, "learning_rate": 2.892625000000001e-07, "loss": 2.7996, "step": 618000 }, { "epoch": 8.62, "learning_rate": 2.850175347222221e-07, "loss": 2.7958, "step": 618500 }, { "epoch": 8.62, "learning_rate": 2.807640624999998e-07, "loss": 2.7917, "step": 619000 }, { "epoch": 8.63, "learning_rate": 2.76510590277778e-07, "loss": 2.7705, "step": 619500 }, { "epoch": 8.64, "learning_rate": 2.72265625e-07, "loss": 2.8046, "step": 620000 }, { "epoch": 8.64, "learning_rate": 2.68020659722222e-07, "loss": 2.8015, "step": 620500 }, { "epoch": 8.65, "learning_rate": 2.6376718750000027e-07, "loss": 2.7911, "step": 621000 }, { "epoch": 8.66, "learning_rate": 2.595137152777779e-07, "loss": 2.7989, "step": 621500 }, { "epoch": 8.67, "learning_rate": 2.552602430555555e-07, "loss": 2.7843, "step": 622000 }, { "epoch": 8.67, "learning_rate": 2.510067708333332e-07, "loss": 2.7882, "step": 622500 }, { "epoch": 8.68, "learning_rate": 2.467532986111109e-07, "loss": 2.7863, "step": 623000 }, { "epoch": 8.69, "learning_rate": 2.4249982638888904e-07, "loss": 2.7838, "step": 623500 }, { "epoch": 8.69, "learning_rate": 2.3824635416666672e-07, "loss": 2.7985, "step": 624000 }, { "epoch": 8.7, "learning_rate": 2.3399288194444434e-07, "loss": 2.7769, "step": 624500 }, { "epoch": 8.71, "learning_rate": 2.2974791666666693e-07, "loss": 2.7946, "step": 625000 }, { "epoch": 8.71, "learning_rate": 2.2550295138888896e-07, "loss": 2.7666, "step": 625500 }, { "epoch": 8.72, "learning_rate": 2.212494791666666e-07, "loss": 2.7783, "step": 626000 }, { "epoch": 8.73, "learning_rate": 2.1699600694444427e-07, "loss": 2.7792, "step": 626500 }, { "epoch": 8.74, "learning_rate": 2.127425347222225e-07, "loss": 2.7928, "step": 627000 }, { "epoch": 8.74, "learning_rate": 2.0848906250000013e-07, "loss": 2.7946, "step": 627500 }, { "epoch": 8.75, "learning_rate": 2.0423559027777778e-07, "loss": 2.769, "step": 628000 }, { "epoch": 8.76, "learning_rate": 1.9998211805555544e-07, "loss": 2.7804, "step": 628500 }, { "epoch": 8.76, "learning_rate": 1.9572864583333312e-07, "loss": 2.7762, "step": 629000 }, { "epoch": 8.77, "learning_rate": 1.9147517361111133e-07, "loss": 2.776, "step": 629500 }, { "epoch": 8.78, "learning_rate": 1.8722170138888895e-07, "loss": 2.7643, "step": 630000 }, { "epoch": 8.78, "learning_rate": 1.8297673611111093e-07, "loss": 2.7831, "step": 630500 }, { "epoch": 8.79, "learning_rate": 1.7872326388888864e-07, "loss": 2.7748, "step": 631000 }, { "epoch": 8.8, "learning_rate": 1.7446979166666682e-07, "loss": 2.7785, "step": 631500 }, { "epoch": 8.8, "learning_rate": 1.7021631944444447e-07, "loss": 2.8047, "step": 632000 }, { "epoch": 8.81, "learning_rate": 1.6596284722222218e-07, "loss": 2.7804, "step": 632500 }, { "epoch": 8.82, "learning_rate": 1.617093749999998e-07, "loss": 2.7733, "step": 633000 }, { "epoch": 8.83, "learning_rate": 1.57455902777778e-07, "loss": 2.7808, "step": 633500 }, { "epoch": 8.83, "learning_rate": 1.5320243055555567e-07, "loss": 2.7608, "step": 634000 }, { "epoch": 8.84, "learning_rate": 1.4895746527777767e-07, "loss": 2.7795, "step": 634500 }, { "epoch": 8.85, "learning_rate": 1.4470399305555533e-07, "loss": 2.7757, "step": 635000 }, { "epoch": 8.85, "learning_rate": 1.4045902777777789e-07, "loss": 2.7762, "step": 635500 }, { "epoch": 8.86, "learning_rate": 1.3620555555555557e-07, "loss": 2.8027, "step": 636000 }, { "epoch": 8.87, "learning_rate": 1.3195208333333322e-07, "loss": 2.801, "step": 636500 }, { "epoch": 8.87, "learning_rate": 1.2770711805555578e-07, "loss": 2.805, "step": 637000 }, { "epoch": 8.88, "learning_rate": 1.2345364583333343e-07, "loss": 2.7915, "step": 637500 }, { "epoch": 8.89, "learning_rate": 1.1920017361111108e-07, "loss": 2.7784, "step": 638000 }, { "epoch": 8.9, "learning_rate": 1.1494670138888875e-07, "loss": 2.7728, "step": 638500 }, { "epoch": 8.9, "learning_rate": 1.106932291666664e-07, "loss": 2.784, "step": 639000 }, { "epoch": 8.91, "learning_rate": 1.0643975694444459e-07, "loss": 2.782, "step": 639500 }, { "epoch": 8.92, "learning_rate": 1.0218628472222226e-07, "loss": 2.7799, "step": 640000 } ], "max_steps": 640000, "num_train_epochs": 9, "total_flos": 1.5081584369164186e+18, "trial_name": null, "trial_params": null }