{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 1016679, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.998032810749509e-05, "loss": 1.0525, "step": 1000 }, { "epoch": 0.01, "learning_rate": 1.996065621499018e-05, "loss": 1.0569, "step": 2000 }, { "epoch": 0.01, "learning_rate": 1.994098432248527e-05, "loss": 1.0785, "step": 3000 }, { "epoch": 0.01, "learning_rate": 1.992131242998036e-05, "loss": 1.0907, "step": 4000 }, { "epoch": 0.01, "learning_rate": 1.9901640537475448e-05, "loss": 1.0982, "step": 5000 }, { "epoch": 0.02, "learning_rate": 1.9881968644970537e-05, "loss": 1.1017, "step": 6000 }, { "epoch": 0.02, "learning_rate": 1.986229675246563e-05, "loss": 1.0944, "step": 7000 }, { "epoch": 0.02, "learning_rate": 1.9842624859960718e-05, "loss": 1.1131, "step": 8000 }, { "epoch": 0.03, "learning_rate": 1.9822952967455806e-05, "loss": 1.1098, "step": 9000 }, { "epoch": 0.03, "learning_rate": 1.9803281074950895e-05, "loss": 1.1042, "step": 10000 }, { "epoch": 0.03, "learning_rate": 1.9783609182445983e-05, "loss": 1.1255, "step": 11000 }, { "epoch": 0.04, "learning_rate": 1.9763937289941075e-05, "loss": 1.1242, "step": 12000 }, { "epoch": 0.04, "learning_rate": 1.9744265397436164e-05, "loss": 1.1315, "step": 13000 }, { "epoch": 0.04, "learning_rate": 1.9724593504931253e-05, "loss": 1.1209, "step": 14000 }, { "epoch": 0.04, "learning_rate": 1.970492161242634e-05, "loss": 1.1163, "step": 15000 }, { "epoch": 0.05, "learning_rate": 1.968524971992143e-05, "loss": 1.1239, "step": 16000 }, { "epoch": 0.05, "learning_rate": 1.9665577827416522e-05, "loss": 1.117, "step": 17000 }, { "epoch": 0.05, "learning_rate": 1.964590593491161e-05, "loss": 1.1416, "step": 18000 }, { "epoch": 0.06, "learning_rate": 1.96262340424067e-05, "loss": 1.1294, "step": 19000 }, { "epoch": 0.06, "learning_rate": 1.9606562149901788e-05, "loss": 1.124, "step": 20000 }, { "epoch": 0.06, "learning_rate": 1.958689025739688e-05, "loss": 1.1277, "step": 21000 }, { "epoch": 0.06, "learning_rate": 1.956721836489197e-05, "loss": 1.1482, "step": 22000 }, { "epoch": 0.07, "learning_rate": 1.9547546472387057e-05, "loss": 1.1237, "step": 23000 }, { "epoch": 0.07, "learning_rate": 1.9527874579882146e-05, "loss": 1.1418, "step": 24000 }, { "epoch": 0.07, "learning_rate": 1.9508202687377235e-05, "loss": 1.1353, "step": 25000 }, { "epoch": 0.08, "learning_rate": 1.9488530794872327e-05, "loss": 1.136, "step": 26000 }, { "epoch": 0.08, "learning_rate": 1.9468858902367415e-05, "loss": 1.1399, "step": 27000 }, { "epoch": 0.08, "learning_rate": 1.9449187009862504e-05, "loss": 1.1259, "step": 28000 }, { "epoch": 0.09, "learning_rate": 1.9429515117357592e-05, "loss": 1.1416, "step": 29000 }, { "epoch": 0.09, "learning_rate": 1.9409843224852685e-05, "loss": 1.1476, "step": 30000 }, { "epoch": 0.09, "learning_rate": 1.9390171332347773e-05, "loss": 1.1364, "step": 31000 }, { "epoch": 0.09, "learning_rate": 1.9370499439842862e-05, "loss": 1.1387, "step": 32000 }, { "epoch": 0.1, "learning_rate": 1.935082754733795e-05, "loss": 1.1423, "step": 33000 }, { "epoch": 0.1, "learning_rate": 1.933115565483304e-05, "loss": 1.145, "step": 34000 }, { "epoch": 0.1, "learning_rate": 1.931148376232813e-05, "loss": 1.1537, "step": 35000 }, { "epoch": 0.11, "learning_rate": 1.929181186982322e-05, "loss": 1.1477, "step": 36000 }, { "epoch": 0.11, "learning_rate": 1.927213997731831e-05, "loss": 1.134, "step": 37000 }, { "epoch": 0.11, "learning_rate": 1.9252468084813397e-05, "loss": 1.1396, "step": 38000 }, { "epoch": 0.12, "learning_rate": 1.923279619230849e-05, "loss": 1.1512, "step": 39000 }, { "epoch": 0.12, "learning_rate": 1.9213124299803578e-05, "loss": 1.1396, "step": 40000 }, { "epoch": 0.12, "learning_rate": 1.9193452407298666e-05, "loss": 1.153, "step": 41000 }, { "epoch": 0.12, "learning_rate": 1.9173780514793755e-05, "loss": 1.1276, "step": 42000 }, { "epoch": 0.13, "learning_rate": 1.9154108622288844e-05, "loss": 1.1427, "step": 43000 }, { "epoch": 0.13, "learning_rate": 1.9134436729783936e-05, "loss": 1.1569, "step": 44000 }, { "epoch": 0.13, "learning_rate": 1.9114764837279024e-05, "loss": 1.1465, "step": 45000 }, { "epoch": 0.14, "learning_rate": 1.9095092944774113e-05, "loss": 1.1518, "step": 46000 }, { "epoch": 0.14, "learning_rate": 1.90754210522692e-05, "loss": 1.1516, "step": 47000 }, { "epoch": 0.14, "learning_rate": 1.905574915976429e-05, "loss": 1.1642, "step": 48000 }, { "epoch": 0.14, "learning_rate": 1.9036077267259382e-05, "loss": 1.1592, "step": 49000 }, { "epoch": 0.15, "learning_rate": 1.901640537475447e-05, "loss": 1.158, "step": 50000 }, { "epoch": 0.15, "learning_rate": 1.899673348224956e-05, "loss": 1.1494, "step": 51000 }, { "epoch": 0.15, "learning_rate": 1.8977061589744648e-05, "loss": 1.1298, "step": 52000 }, { "epoch": 0.16, "learning_rate": 1.895738969723974e-05, "loss": 1.1469, "step": 53000 }, { "epoch": 0.16, "learning_rate": 1.893771780473483e-05, "loss": 1.1545, "step": 54000 }, { "epoch": 0.16, "learning_rate": 1.8918045912229917e-05, "loss": 1.154, "step": 55000 }, { "epoch": 0.17, "learning_rate": 1.8898374019725006e-05, "loss": 1.1597, "step": 56000 }, { "epoch": 0.17, "learning_rate": 1.8878702127220098e-05, "loss": 1.1451, "step": 57000 }, { "epoch": 0.17, "learning_rate": 1.8859030234715187e-05, "loss": 1.1472, "step": 58000 }, { "epoch": 0.17, "learning_rate": 1.8839358342210275e-05, "loss": 1.1526, "step": 59000 }, { "epoch": 0.18, "learning_rate": 1.8819686449705364e-05, "loss": 1.1549, "step": 60000 }, { "epoch": 0.18, "learning_rate": 1.8800014557200456e-05, "loss": 1.1598, "step": 61000 }, { "epoch": 0.18, "learning_rate": 1.8780342664695545e-05, "loss": 1.1589, "step": 62000 }, { "epoch": 0.19, "learning_rate": 1.8760670772190633e-05, "loss": 1.1575, "step": 63000 }, { "epoch": 0.19, "learning_rate": 1.8740998879685722e-05, "loss": 1.1357, "step": 64000 }, { "epoch": 0.19, "learning_rate": 1.8721326987180814e-05, "loss": 1.1524, "step": 65000 }, { "epoch": 0.19, "learning_rate": 1.8701655094675903e-05, "loss": 1.1542, "step": 66000 }, { "epoch": 0.2, "learning_rate": 1.868198320217099e-05, "loss": 1.1449, "step": 67000 }, { "epoch": 0.2, "learning_rate": 1.866231130966608e-05, "loss": 1.168, "step": 68000 }, { "epoch": 0.2, "learning_rate": 1.864263941716117e-05, "loss": 1.1588, "step": 69000 }, { "epoch": 0.21, "learning_rate": 1.862296752465626e-05, "loss": 1.1612, "step": 70000 }, { "epoch": 0.21, "learning_rate": 1.860329563215135e-05, "loss": 1.1609, "step": 71000 }, { "epoch": 0.21, "learning_rate": 1.8583623739646438e-05, "loss": 1.1596, "step": 72000 }, { "epoch": 0.22, "learning_rate": 1.8563951847141526e-05, "loss": 1.1521, "step": 73000 }, { "epoch": 0.22, "learning_rate": 1.854427995463662e-05, "loss": 1.1675, "step": 74000 }, { "epoch": 0.22, "learning_rate": 1.8524608062131707e-05, "loss": 1.1594, "step": 75000 }, { "epoch": 0.22, "learning_rate": 1.8504936169626796e-05, "loss": 1.1476, "step": 76000 }, { "epoch": 0.23, "learning_rate": 1.8485264277121884e-05, "loss": 1.1494, "step": 77000 }, { "epoch": 0.23, "learning_rate": 1.8465592384616976e-05, "loss": 1.1679, "step": 78000 }, { "epoch": 0.23, "learning_rate": 1.8445920492112065e-05, "loss": 1.1586, "step": 79000 }, { "epoch": 0.24, "learning_rate": 1.8426248599607154e-05, "loss": 1.1572, "step": 80000 }, { "epoch": 0.24, "learning_rate": 1.8406576707102242e-05, "loss": 1.1605, "step": 81000 }, { "epoch": 0.24, "learning_rate": 1.8386904814597334e-05, "loss": 1.1598, "step": 82000 }, { "epoch": 0.24, "learning_rate": 1.8367232922092423e-05, "loss": 1.1525, "step": 83000 }, { "epoch": 0.25, "learning_rate": 1.834756102958751e-05, "loss": 1.1679, "step": 84000 }, { "epoch": 0.25, "learning_rate": 1.83278891370826e-05, "loss": 1.1613, "step": 85000 }, { "epoch": 0.25, "learning_rate": 1.8308217244577692e-05, "loss": 1.1566, "step": 86000 }, { "epoch": 0.26, "learning_rate": 1.828854535207278e-05, "loss": 1.1595, "step": 87000 }, { "epoch": 0.26, "learning_rate": 1.826887345956787e-05, "loss": 1.1576, "step": 88000 }, { "epoch": 0.26, "learning_rate": 1.8249201567062958e-05, "loss": 1.1602, "step": 89000 }, { "epoch": 0.27, "learning_rate": 1.8229529674558047e-05, "loss": 1.1522, "step": 90000 }, { "epoch": 0.27, "learning_rate": 1.820985778205314e-05, "loss": 1.1615, "step": 91000 }, { "epoch": 0.27, "learning_rate": 1.8190185889548228e-05, "loss": 1.1711, "step": 92000 }, { "epoch": 0.27, "learning_rate": 1.8170513997043316e-05, "loss": 1.1469, "step": 93000 }, { "epoch": 0.28, "learning_rate": 1.8150842104538405e-05, "loss": 1.1572, "step": 94000 }, { "epoch": 0.28, "learning_rate": 1.8131170212033497e-05, "loss": 1.1571, "step": 95000 }, { "epoch": 0.28, "learning_rate": 1.8111498319528585e-05, "loss": 1.1714, "step": 96000 }, { "epoch": 0.29, "learning_rate": 1.8091826427023674e-05, "loss": 1.1561, "step": 97000 }, { "epoch": 0.29, "learning_rate": 1.8072154534518763e-05, "loss": 1.164, "step": 98000 }, { "epoch": 0.29, "learning_rate": 1.8052482642013855e-05, "loss": 1.1605, "step": 99000 }, { "epoch": 0.3, "learning_rate": 1.8032810749508943e-05, "loss": 1.1544, "step": 100000 }, { "epoch": 0.3, "learning_rate": 1.8013138857004032e-05, "loss": 1.1637, "step": 101000 }, { "epoch": 0.3, "learning_rate": 1.799346696449912e-05, "loss": 1.1531, "step": 102000 }, { "epoch": 0.3, "learning_rate": 1.7973795071994213e-05, "loss": 1.1808, "step": 103000 }, { "epoch": 0.31, "learning_rate": 1.79541231794893e-05, "loss": 1.1638, "step": 104000 }, { "epoch": 0.31, "learning_rate": 1.793445128698439e-05, "loss": 1.1472, "step": 105000 }, { "epoch": 0.31, "learning_rate": 1.791477939447948e-05, "loss": 1.1618, "step": 106000 }, { "epoch": 0.32, "learning_rate": 1.7895107501974567e-05, "loss": 1.157, "step": 107000 }, { "epoch": 0.32, "learning_rate": 1.787543560946966e-05, "loss": 1.1657, "step": 108000 }, { "epoch": 0.32, "learning_rate": 1.7855763716964748e-05, "loss": 1.163, "step": 109000 }, { "epoch": 0.32, "learning_rate": 1.7836091824459837e-05, "loss": 1.1692, "step": 110000 }, { "epoch": 0.33, "learning_rate": 1.7816419931954925e-05, "loss": 1.15, "step": 111000 }, { "epoch": 0.33, "learning_rate": 1.7796748039450014e-05, "loss": 1.1522, "step": 112000 }, { "epoch": 0.33, "learning_rate": 1.7777076146945106e-05, "loss": 1.1459, "step": 113000 }, { "epoch": 0.34, "learning_rate": 1.7757404254440195e-05, "loss": 1.162, "step": 114000 }, { "epoch": 0.34, "learning_rate": 1.7737732361935283e-05, "loss": 1.1647, "step": 115000 }, { "epoch": 0.34, "learning_rate": 1.7718060469430372e-05, "loss": 1.1573, "step": 116000 }, { "epoch": 0.35, "learning_rate": 1.7698388576925464e-05, "loss": 1.1624, "step": 117000 }, { "epoch": 0.35, "learning_rate": 1.7678716684420552e-05, "loss": 1.1689, "step": 118000 }, { "epoch": 0.35, "learning_rate": 1.765904479191564e-05, "loss": 1.1759, "step": 119000 }, { "epoch": 0.35, "learning_rate": 1.763937289941073e-05, "loss": 1.1597, "step": 120000 }, { "epoch": 0.36, "learning_rate": 1.761970100690582e-05, "loss": 1.1656, "step": 121000 }, { "epoch": 0.36, "learning_rate": 1.760002911440091e-05, "loss": 1.1501, "step": 122000 }, { "epoch": 0.36, "learning_rate": 1.7580357221896e-05, "loss": 1.1603, "step": 123000 }, { "epoch": 0.37, "learning_rate": 1.7560685329391088e-05, "loss": 1.1541, "step": 124000 }, { "epoch": 0.37, "learning_rate": 1.7541013436886176e-05, "loss": 1.1582, "step": 125000 }, { "epoch": 0.37, "learning_rate": 1.752134154438127e-05, "loss": 1.1527, "step": 126000 }, { "epoch": 0.37, "learning_rate": 1.7501669651876357e-05, "loss": 1.1757, "step": 127000 }, { "epoch": 0.38, "learning_rate": 1.7481997759371446e-05, "loss": 1.1759, "step": 128000 }, { "epoch": 0.38, "learning_rate": 1.7462325866866534e-05, "loss": 1.1591, "step": 129000 }, { "epoch": 0.38, "learning_rate": 1.7442653974361623e-05, "loss": 1.168, "step": 130000 }, { "epoch": 0.39, "learning_rate": 1.7422982081856715e-05, "loss": 1.1624, "step": 131000 }, { "epoch": 0.39, "learning_rate": 1.7403310189351804e-05, "loss": 1.148, "step": 132000 }, { "epoch": 0.39, "learning_rate": 1.7383638296846892e-05, "loss": 1.1701, "step": 133000 }, { "epoch": 0.4, "learning_rate": 1.736396640434198e-05, "loss": 1.1629, "step": 134000 }, { "epoch": 0.4, "learning_rate": 1.7344294511837073e-05, "loss": 1.1622, "step": 135000 }, { "epoch": 0.4, "learning_rate": 1.732462261933216e-05, "loss": 1.1726, "step": 136000 }, { "epoch": 0.4, "learning_rate": 1.730495072682725e-05, "loss": 1.1646, "step": 137000 }, { "epoch": 0.41, "learning_rate": 1.728527883432234e-05, "loss": 1.1578, "step": 138000 }, { "epoch": 0.41, "learning_rate": 1.7265606941817427e-05, "loss": 1.1632, "step": 139000 }, { "epoch": 0.41, "learning_rate": 1.724593504931252e-05, "loss": 1.164, "step": 140000 }, { "epoch": 0.42, "learning_rate": 1.7226263156807608e-05, "loss": 1.1674, "step": 141000 }, { "epoch": 0.42, "learning_rate": 1.7206591264302697e-05, "loss": 1.1649, "step": 142000 }, { "epoch": 0.42, "learning_rate": 1.7186919371797785e-05, "loss": 1.1748, "step": 143000 }, { "epoch": 0.42, "learning_rate": 1.7167247479292874e-05, "loss": 1.1608, "step": 144000 }, { "epoch": 0.43, "learning_rate": 1.7147575586787966e-05, "loss": 1.1889, "step": 145000 }, { "epoch": 0.43, "learning_rate": 1.7127903694283055e-05, "loss": 1.174, "step": 146000 }, { "epoch": 0.43, "learning_rate": 1.7108231801778143e-05, "loss": 1.1804, "step": 147000 }, { "epoch": 0.44, "learning_rate": 1.7088559909273232e-05, "loss": 1.1609, "step": 148000 }, { "epoch": 0.44, "learning_rate": 1.7068888016768324e-05, "loss": 1.1723, "step": 149000 }, { "epoch": 0.44, "learning_rate": 1.7049216124263413e-05, "loss": 1.1714, "step": 150000 }, { "epoch": 0.45, "learning_rate": 1.70295442317585e-05, "loss": 1.1827, "step": 151000 }, { "epoch": 0.45, "learning_rate": 1.700987233925359e-05, "loss": 1.1749, "step": 152000 }, { "epoch": 0.45, "learning_rate": 1.699020044674868e-05, "loss": 1.1448, "step": 153000 }, { "epoch": 0.45, "learning_rate": 1.697052855424377e-05, "loss": 1.1621, "step": 154000 }, { "epoch": 0.46, "learning_rate": 1.695085666173886e-05, "loss": 1.1725, "step": 155000 }, { "epoch": 0.46, "learning_rate": 1.6931184769233948e-05, "loss": 1.1575, "step": 156000 }, { "epoch": 0.46, "learning_rate": 1.6911512876729037e-05, "loss": 1.1543, "step": 157000 }, { "epoch": 0.47, "learning_rate": 1.689184098422413e-05, "loss": 1.1661, "step": 158000 }, { "epoch": 0.47, "learning_rate": 1.6872169091719217e-05, "loss": 1.1606, "step": 159000 }, { "epoch": 0.47, "learning_rate": 1.6852497199214306e-05, "loss": 1.148, "step": 160000 }, { "epoch": 0.48, "learning_rate": 1.6832825306709394e-05, "loss": 1.1597, "step": 161000 }, { "epoch": 0.48, "learning_rate": 1.6813153414204483e-05, "loss": 1.1607, "step": 162000 }, { "epoch": 0.48, "learning_rate": 1.6793481521699575e-05, "loss": 1.1731, "step": 163000 }, { "epoch": 0.48, "learning_rate": 1.6773809629194664e-05, "loss": 1.1688, "step": 164000 }, { "epoch": 0.49, "learning_rate": 1.6754137736689752e-05, "loss": 1.1648, "step": 165000 }, { "epoch": 0.49, "learning_rate": 1.673446584418484e-05, "loss": 1.1592, "step": 166000 }, { "epoch": 0.49, "learning_rate": 1.6714793951679933e-05, "loss": 1.1358, "step": 167000 }, { "epoch": 0.5, "learning_rate": 1.669512205917502e-05, "loss": 1.1654, "step": 168000 }, { "epoch": 0.5, "learning_rate": 1.667545016667011e-05, "loss": 1.1647, "step": 169000 }, { "epoch": 0.5, "learning_rate": 1.66557782741652e-05, "loss": 1.1607, "step": 170000 }, { "epoch": 0.5, "learning_rate": 1.6636106381660288e-05, "loss": 1.1803, "step": 171000 }, { "epoch": 0.51, "learning_rate": 1.661643448915538e-05, "loss": 1.1756, "step": 172000 }, { "epoch": 0.51, "learning_rate": 1.6596762596650468e-05, "loss": 1.1589, "step": 173000 }, { "epoch": 0.51, "learning_rate": 1.6577090704145557e-05, "loss": 1.1755, "step": 174000 }, { "epoch": 0.52, "learning_rate": 1.6557418811640646e-05, "loss": 1.1667, "step": 175000 }, { "epoch": 0.52, "learning_rate": 1.6537746919135734e-05, "loss": 1.154, "step": 176000 }, { "epoch": 0.52, "learning_rate": 1.6518075026630826e-05, "loss": 1.15, "step": 177000 }, { "epoch": 0.53, "learning_rate": 1.6498403134125915e-05, "loss": 1.1725, "step": 178000 }, { "epoch": 0.53, "learning_rate": 1.6478731241621003e-05, "loss": 1.1676, "step": 179000 }, { "epoch": 0.53, "learning_rate": 1.6459059349116092e-05, "loss": 1.1672, "step": 180000 }, { "epoch": 0.53, "learning_rate": 1.6439387456611184e-05, "loss": 1.1719, "step": 181000 }, { "epoch": 0.54, "learning_rate": 1.6419715564106273e-05, "loss": 1.1705, "step": 182000 }, { "epoch": 0.54, "learning_rate": 1.640004367160136e-05, "loss": 1.1525, "step": 183000 }, { "epoch": 0.54, "learning_rate": 1.638037177909645e-05, "loss": 1.1624, "step": 184000 }, { "epoch": 0.55, "learning_rate": 1.636069988659154e-05, "loss": 1.1669, "step": 185000 }, { "epoch": 0.55, "learning_rate": 1.634102799408663e-05, "loss": 1.1691, "step": 186000 }, { "epoch": 0.55, "learning_rate": 1.632135610158172e-05, "loss": 1.171, "step": 187000 }, { "epoch": 0.55, "learning_rate": 1.6301684209076808e-05, "loss": 1.1598, "step": 188000 }, { "epoch": 0.56, "learning_rate": 1.6282012316571897e-05, "loss": 1.1712, "step": 189000 }, { "epoch": 0.56, "learning_rate": 1.626234042406699e-05, "loss": 1.1628, "step": 190000 }, { "epoch": 0.56, "learning_rate": 1.6242668531562077e-05, "loss": 1.1586, "step": 191000 }, { "epoch": 0.57, "learning_rate": 1.6222996639057166e-05, "loss": 1.16, "step": 192000 }, { "epoch": 0.57, "learning_rate": 1.6203324746552255e-05, "loss": 1.1714, "step": 193000 }, { "epoch": 0.57, "learning_rate": 1.6183652854047343e-05, "loss": 1.1523, "step": 194000 }, { "epoch": 0.58, "learning_rate": 1.6163980961542435e-05, "loss": 1.1501, "step": 195000 }, { "epoch": 0.58, "learning_rate": 1.6144309069037524e-05, "loss": 1.1721, "step": 196000 }, { "epoch": 0.58, "learning_rate": 1.6124637176532613e-05, "loss": 1.1516, "step": 197000 }, { "epoch": 0.58, "learning_rate": 1.61049652840277e-05, "loss": 1.1624, "step": 198000 }, { "epoch": 0.59, "learning_rate": 1.6085293391522793e-05, "loss": 1.1528, "step": 199000 }, { "epoch": 0.59, "learning_rate": 1.6065621499017882e-05, "loss": 1.1641, "step": 200000 }, { "epoch": 0.59, "learning_rate": 1.604594960651297e-05, "loss": 1.1646, "step": 201000 }, { "epoch": 0.6, "learning_rate": 1.602627771400806e-05, "loss": 1.1623, "step": 202000 }, { "epoch": 0.6, "learning_rate": 1.6006605821503148e-05, "loss": 1.1574, "step": 203000 }, { "epoch": 0.6, "learning_rate": 1.598693392899824e-05, "loss": 1.1764, "step": 204000 }, { "epoch": 0.6, "learning_rate": 1.596726203649333e-05, "loss": 1.1608, "step": 205000 }, { "epoch": 0.61, "learning_rate": 1.5947590143988417e-05, "loss": 1.1637, "step": 206000 }, { "epoch": 0.61, "learning_rate": 1.5927918251483506e-05, "loss": 1.1669, "step": 207000 }, { "epoch": 0.61, "learning_rate": 1.5908246358978598e-05, "loss": 1.1493, "step": 208000 }, { "epoch": 0.62, "learning_rate": 1.5888574466473686e-05, "loss": 1.1627, "step": 209000 }, { "epoch": 0.62, "learning_rate": 1.5868902573968775e-05, "loss": 1.1686, "step": 210000 }, { "epoch": 0.62, "learning_rate": 1.5849230681463864e-05, "loss": 1.1609, "step": 211000 }, { "epoch": 0.63, "learning_rate": 1.5829558788958956e-05, "loss": 1.1551, "step": 212000 }, { "epoch": 0.63, "learning_rate": 1.5809886896454044e-05, "loss": 1.1625, "step": 213000 }, { "epoch": 0.63, "learning_rate": 1.5790215003949133e-05, "loss": 1.1664, "step": 214000 }, { "epoch": 0.63, "learning_rate": 1.577054311144422e-05, "loss": 1.1646, "step": 215000 }, { "epoch": 0.64, "learning_rate": 1.5750871218939314e-05, "loss": 1.1551, "step": 216000 }, { "epoch": 0.64, "learning_rate": 1.5731199326434402e-05, "loss": 1.1724, "step": 217000 }, { "epoch": 0.64, "learning_rate": 1.571152743392949e-05, "loss": 1.1565, "step": 218000 }, { "epoch": 0.65, "learning_rate": 1.569185554142458e-05, "loss": 1.1725, "step": 219000 }, { "epoch": 0.65, "learning_rate": 1.567218364891967e-05, "loss": 1.1632, "step": 220000 }, { "epoch": 0.65, "learning_rate": 1.565251175641476e-05, "loss": 1.1646, "step": 221000 }, { "epoch": 0.66, "learning_rate": 1.563283986390985e-05, "loss": 1.1612, "step": 222000 }, { "epoch": 0.66, "learning_rate": 1.5613167971404937e-05, "loss": 1.1618, "step": 223000 }, { "epoch": 0.66, "learning_rate": 1.5593496078900026e-05, "loss": 1.1572, "step": 224000 }, { "epoch": 0.66, "learning_rate": 1.5573824186395118e-05, "loss": 1.1695, "step": 225000 }, { "epoch": 0.67, "learning_rate": 1.5554152293890207e-05, "loss": 1.1634, "step": 226000 }, { "epoch": 0.67, "learning_rate": 1.5534480401385295e-05, "loss": 1.1518, "step": 227000 }, { "epoch": 0.67, "learning_rate": 1.5514808508880384e-05, "loss": 1.1537, "step": 228000 }, { "epoch": 0.68, "learning_rate": 1.5495136616375476e-05, "loss": 1.1563, "step": 229000 }, { "epoch": 0.68, "learning_rate": 1.5475464723870565e-05, "loss": 1.1516, "step": 230000 }, { "epoch": 0.68, "learning_rate": 1.5455792831365653e-05, "loss": 1.1709, "step": 231000 }, { "epoch": 0.68, "learning_rate": 1.5436120938860742e-05, "loss": 1.1494, "step": 232000 }, { "epoch": 0.69, "learning_rate": 1.5416449046355834e-05, "loss": 1.1583, "step": 233000 }, { "epoch": 0.69, "learning_rate": 1.5396777153850923e-05, "loss": 1.171, "step": 234000 }, { "epoch": 0.69, "learning_rate": 1.537710526134601e-05, "loss": 1.1628, "step": 235000 }, { "epoch": 0.7, "learning_rate": 1.53574333688411e-05, "loss": 1.1516, "step": 236000 }, { "epoch": 0.7, "learning_rate": 1.5337761476336192e-05, "loss": 1.1814, "step": 237000 }, { "epoch": 0.7, "learning_rate": 1.531808958383128e-05, "loss": 1.1561, "step": 238000 }, { "epoch": 0.71, "learning_rate": 1.529841769132637e-05, "loss": 1.1584, "step": 239000 }, { "epoch": 0.71, "learning_rate": 1.5278745798821458e-05, "loss": 1.1541, "step": 240000 }, { "epoch": 0.71, "learning_rate": 1.525907390631655e-05, "loss": 1.1467, "step": 241000 }, { "epoch": 0.71, "learning_rate": 1.5239402013811637e-05, "loss": 1.1548, "step": 242000 }, { "epoch": 0.72, "learning_rate": 1.5219730121306726e-05, "loss": 1.1608, "step": 243000 }, { "epoch": 0.72, "learning_rate": 1.5200058228801816e-05, "loss": 1.1491, "step": 244000 }, { "epoch": 0.72, "learning_rate": 1.5180386336296906e-05, "loss": 1.1718, "step": 245000 }, { "epoch": 0.73, "learning_rate": 1.5160714443791995e-05, "loss": 1.1643, "step": 246000 }, { "epoch": 0.73, "learning_rate": 1.5141042551287083e-05, "loss": 1.158, "step": 247000 }, { "epoch": 0.73, "learning_rate": 1.5121370658782172e-05, "loss": 1.17, "step": 248000 }, { "epoch": 0.73, "learning_rate": 1.5101698766277262e-05, "loss": 1.1572, "step": 249000 }, { "epoch": 0.74, "learning_rate": 1.5082026873772353e-05, "loss": 1.1537, "step": 250000 }, { "epoch": 0.74, "learning_rate": 1.5062354981267441e-05, "loss": 1.1535, "step": 251000 }, { "epoch": 0.74, "learning_rate": 1.504268308876253e-05, "loss": 1.1629, "step": 252000 }, { "epoch": 0.75, "learning_rate": 1.502301119625762e-05, "loss": 1.1581, "step": 253000 }, { "epoch": 0.75, "learning_rate": 1.500333930375271e-05, "loss": 1.1726, "step": 254000 }, { "epoch": 0.75, "learning_rate": 1.49836674112478e-05, "loss": 1.1511, "step": 255000 }, { "epoch": 0.76, "learning_rate": 1.4963995518742888e-05, "loss": 1.1613, "step": 256000 }, { "epoch": 0.76, "learning_rate": 1.4944323626237978e-05, "loss": 1.1528, "step": 257000 }, { "epoch": 0.76, "learning_rate": 1.4924651733733067e-05, "loss": 1.1548, "step": 258000 }, { "epoch": 0.76, "learning_rate": 1.4904979841228157e-05, "loss": 1.1731, "step": 259000 }, { "epoch": 0.77, "learning_rate": 1.4885307948723246e-05, "loss": 1.1618, "step": 260000 }, { "epoch": 0.77, "learning_rate": 1.4865636056218336e-05, "loss": 1.1588, "step": 261000 }, { "epoch": 0.77, "learning_rate": 1.4845964163713425e-05, "loss": 1.1562, "step": 262000 }, { "epoch": 0.78, "learning_rate": 1.4826292271208514e-05, "loss": 1.1597, "step": 263000 }, { "epoch": 0.78, "learning_rate": 1.4806620378703604e-05, "loss": 1.1681, "step": 264000 }, { "epoch": 0.78, "learning_rate": 1.4786948486198694e-05, "loss": 1.1714, "step": 265000 }, { "epoch": 0.78, "learning_rate": 1.4767276593693783e-05, "loss": 1.1475, "step": 266000 }, { "epoch": 0.79, "learning_rate": 1.4747604701188871e-05, "loss": 1.1547, "step": 267000 }, { "epoch": 0.79, "learning_rate": 1.4727932808683962e-05, "loss": 1.1564, "step": 268000 }, { "epoch": 0.79, "learning_rate": 1.470826091617905e-05, "loss": 1.1568, "step": 269000 }, { "epoch": 0.8, "learning_rate": 1.468858902367414e-05, "loss": 1.156, "step": 270000 }, { "epoch": 0.8, "learning_rate": 1.466891713116923e-05, "loss": 1.1579, "step": 271000 }, { "epoch": 0.8, "learning_rate": 1.4649245238664318e-05, "loss": 1.1446, "step": 272000 }, { "epoch": 0.81, "learning_rate": 1.4629573346159408e-05, "loss": 1.149, "step": 273000 }, { "epoch": 0.81, "learning_rate": 1.4609901453654499e-05, "loss": 1.1518, "step": 274000 }, { "epoch": 0.81, "learning_rate": 1.4590229561149587e-05, "loss": 1.1426, "step": 275000 }, { "epoch": 0.81, "learning_rate": 1.4570557668644676e-05, "loss": 1.1576, "step": 276000 }, { "epoch": 0.82, "learning_rate": 1.4550885776139766e-05, "loss": 1.1562, "step": 277000 }, { "epoch": 0.82, "learning_rate": 1.4531213883634857e-05, "loss": 1.1607, "step": 278000 }, { "epoch": 0.82, "learning_rate": 1.4511541991129945e-05, "loss": 1.1651, "step": 279000 }, { "epoch": 0.83, "learning_rate": 1.4491870098625034e-05, "loss": 1.1567, "step": 280000 }, { "epoch": 0.83, "learning_rate": 1.4472198206120123e-05, "loss": 1.1303, "step": 281000 }, { "epoch": 0.83, "learning_rate": 1.4452526313615215e-05, "loss": 1.1573, "step": 282000 }, { "epoch": 0.84, "learning_rate": 1.4432854421110303e-05, "loss": 1.1578, "step": 283000 }, { "epoch": 0.84, "learning_rate": 1.4413182528605392e-05, "loss": 1.1588, "step": 284000 }, { "epoch": 0.84, "learning_rate": 1.439351063610048e-05, "loss": 1.1509, "step": 285000 }, { "epoch": 0.84, "learning_rate": 1.4373838743595573e-05, "loss": 1.151, "step": 286000 }, { "epoch": 0.85, "learning_rate": 1.4354166851090661e-05, "loss": 1.1534, "step": 287000 }, { "epoch": 0.85, "learning_rate": 1.433449495858575e-05, "loss": 1.1555, "step": 288000 }, { "epoch": 0.85, "learning_rate": 1.4314823066080838e-05, "loss": 1.1621, "step": 289000 }, { "epoch": 0.86, "learning_rate": 1.4295151173575927e-05, "loss": 1.1466, "step": 290000 }, { "epoch": 0.86, "learning_rate": 1.4275479281071019e-05, "loss": 1.1628, "step": 291000 }, { "epoch": 0.86, "learning_rate": 1.4255807388566108e-05, "loss": 1.1483, "step": 292000 }, { "epoch": 0.86, "learning_rate": 1.4236135496061196e-05, "loss": 1.1517, "step": 293000 }, { "epoch": 0.87, "learning_rate": 1.4216463603556285e-05, "loss": 1.1445, "step": 294000 }, { "epoch": 0.87, "learning_rate": 1.4196791711051374e-05, "loss": 1.144, "step": 295000 }, { "epoch": 0.87, "learning_rate": 1.4177119818546466e-05, "loss": 1.1649, "step": 296000 }, { "epoch": 0.88, "learning_rate": 1.4157447926041554e-05, "loss": 1.1567, "step": 297000 }, { "epoch": 0.88, "learning_rate": 1.4137776033536643e-05, "loss": 1.1465, "step": 298000 }, { "epoch": 0.88, "learning_rate": 1.4118104141031732e-05, "loss": 1.1655, "step": 299000 }, { "epoch": 0.89, "learning_rate": 1.4098432248526824e-05, "loss": 1.1584, "step": 300000 }, { "epoch": 0.89, "learning_rate": 1.4078760356021912e-05, "loss": 1.1522, "step": 301000 }, { "epoch": 0.89, "learning_rate": 1.4059088463517001e-05, "loss": 1.1445, "step": 302000 }, { "epoch": 0.89, "learning_rate": 1.403941657101209e-05, "loss": 1.1668, "step": 303000 }, { "epoch": 0.9, "learning_rate": 1.4019744678507178e-05, "loss": 1.1619, "step": 304000 }, { "epoch": 0.9, "learning_rate": 1.400007278600227e-05, "loss": 1.157, "step": 305000 }, { "epoch": 0.9, "learning_rate": 1.3980400893497359e-05, "loss": 1.1522, "step": 306000 }, { "epoch": 0.91, "learning_rate": 1.3960729000992448e-05, "loss": 1.1561, "step": 307000 }, { "epoch": 0.91, "learning_rate": 1.3941057108487536e-05, "loss": 1.1615, "step": 308000 }, { "epoch": 0.91, "learning_rate": 1.3921385215982628e-05, "loss": 1.1638, "step": 309000 }, { "epoch": 0.91, "learning_rate": 1.3901713323477717e-05, "loss": 1.1495, "step": 310000 }, { "epoch": 0.92, "learning_rate": 1.3882041430972805e-05, "loss": 1.1653, "step": 311000 }, { "epoch": 0.92, "learning_rate": 1.3862369538467894e-05, "loss": 1.1475, "step": 312000 }, { "epoch": 0.92, "learning_rate": 1.3842697645962984e-05, "loss": 1.1432, "step": 313000 }, { "epoch": 0.93, "learning_rate": 1.3823025753458075e-05, "loss": 1.1585, "step": 314000 }, { "epoch": 0.93, "learning_rate": 1.3803353860953163e-05, "loss": 1.1388, "step": 315000 }, { "epoch": 0.93, "learning_rate": 1.3783681968448252e-05, "loss": 1.1432, "step": 316000 }, { "epoch": 0.94, "learning_rate": 1.376401007594334e-05, "loss": 1.162, "step": 317000 }, { "epoch": 0.94, "learning_rate": 1.3744338183438433e-05, "loss": 1.147, "step": 318000 }, { "epoch": 0.94, "learning_rate": 1.3724666290933521e-05, "loss": 1.1569, "step": 319000 }, { "epoch": 0.94, "learning_rate": 1.370499439842861e-05, "loss": 1.1496, "step": 320000 }, { "epoch": 0.95, "learning_rate": 1.3685322505923699e-05, "loss": 1.145, "step": 321000 }, { "epoch": 0.95, "learning_rate": 1.3665650613418789e-05, "loss": 1.1491, "step": 322000 }, { "epoch": 0.95, "learning_rate": 1.364597872091388e-05, "loss": 1.1449, "step": 323000 }, { "epoch": 0.96, "learning_rate": 1.3626306828408968e-05, "loss": 1.147, "step": 324000 }, { "epoch": 0.96, "learning_rate": 1.3606634935904057e-05, "loss": 1.1531, "step": 325000 }, { "epoch": 0.96, "learning_rate": 1.3586963043399147e-05, "loss": 1.151, "step": 326000 }, { "epoch": 0.96, "learning_rate": 1.3567291150894236e-05, "loss": 1.1603, "step": 327000 }, { "epoch": 0.97, "learning_rate": 1.3547619258389326e-05, "loss": 1.1659, "step": 328000 }, { "epoch": 0.97, "learning_rate": 1.3527947365884415e-05, "loss": 1.1501, "step": 329000 }, { "epoch": 0.97, "learning_rate": 1.3508275473379505e-05, "loss": 1.156, "step": 330000 }, { "epoch": 0.98, "learning_rate": 1.3488603580874593e-05, "loss": 1.1503, "step": 331000 }, { "epoch": 0.98, "learning_rate": 1.3468931688369684e-05, "loss": 1.1519, "step": 332000 }, { "epoch": 0.98, "learning_rate": 1.3449259795864772e-05, "loss": 1.1411, "step": 333000 }, { "epoch": 0.99, "learning_rate": 1.3429587903359863e-05, "loss": 1.1557, "step": 334000 }, { "epoch": 0.99, "learning_rate": 1.3409916010854951e-05, "loss": 1.1634, "step": 335000 }, { "epoch": 0.99, "learning_rate": 1.339024411835004e-05, "loss": 1.1485, "step": 336000 }, { "epoch": 0.99, "learning_rate": 1.337057222584513e-05, "loss": 1.1565, "step": 337000 }, { "epoch": 1.0, "learning_rate": 1.3350900333340219e-05, "loss": 1.153, "step": 338000 }, { "epoch": 1.0, "eval_bleu": 39.6181, "eval_gen_len": 17.4011, "eval_loss": 1.1415810585021973, "eval_runtime": 973.3635, "eval_samples_per_second": 56.27, "eval_steps_per_second": 3.518, "step": 338893 }, { "epoch": 1.0, "learning_rate": 1.333122844083531e-05, "loss": 1.1296, "step": 339000 }, { "epoch": 1.0, "learning_rate": 1.3311556548330398e-05, "loss": 1.0545, "step": 340000 }, { "epoch": 1.01, "learning_rate": 1.3291884655825488e-05, "loss": 1.0629, "step": 341000 }, { "epoch": 1.01, "learning_rate": 1.3272212763320577e-05, "loss": 1.0636, "step": 342000 }, { "epoch": 1.01, "learning_rate": 1.3252540870815667e-05, "loss": 1.0544, "step": 343000 }, { "epoch": 1.02, "learning_rate": 1.3232868978310756e-05, "loss": 1.0525, "step": 344000 }, { "epoch": 1.02, "learning_rate": 1.3213197085805845e-05, "loss": 1.0664, "step": 345000 }, { "epoch": 1.02, "learning_rate": 1.3193525193300935e-05, "loss": 1.05, "step": 346000 }, { "epoch": 1.02, "learning_rate": 1.3173853300796025e-05, "loss": 1.0642, "step": 347000 }, { "epoch": 1.03, "learning_rate": 1.3154181408291114e-05, "loss": 1.0714, "step": 348000 }, { "epoch": 1.03, "learning_rate": 1.3134509515786203e-05, "loss": 1.0698, "step": 349000 }, { "epoch": 1.03, "learning_rate": 1.3114837623281293e-05, "loss": 1.0665, "step": 350000 }, { "epoch": 1.04, "learning_rate": 1.3095165730776383e-05, "loss": 1.0671, "step": 351000 }, { "epoch": 1.04, "learning_rate": 1.3075493838271472e-05, "loss": 1.0466, "step": 352000 }, { "epoch": 1.04, "learning_rate": 1.305582194576656e-05, "loss": 1.0786, "step": 353000 }, { "epoch": 1.04, "learning_rate": 1.3036150053261649e-05, "loss": 1.06, "step": 354000 }, { "epoch": 1.05, "learning_rate": 1.3016478160756741e-05, "loss": 1.0635, "step": 355000 }, { "epoch": 1.05, "learning_rate": 1.299680626825183e-05, "loss": 1.0636, "step": 356000 }, { "epoch": 1.05, "learning_rate": 1.2977134375746918e-05, "loss": 1.0702, "step": 357000 }, { "epoch": 1.06, "learning_rate": 1.2957462483242007e-05, "loss": 1.0572, "step": 358000 }, { "epoch": 1.06, "learning_rate": 1.2937790590737096e-05, "loss": 1.0601, "step": 359000 }, { "epoch": 1.06, "learning_rate": 1.2918118698232188e-05, "loss": 1.0573, "step": 360000 }, { "epoch": 1.07, "learning_rate": 1.2898446805727276e-05, "loss": 1.0653, "step": 361000 }, { "epoch": 1.07, "learning_rate": 1.2878774913222365e-05, "loss": 1.077, "step": 362000 }, { "epoch": 1.07, "learning_rate": 1.2859103020717454e-05, "loss": 1.0636, "step": 363000 }, { "epoch": 1.07, "learning_rate": 1.2839431128212546e-05, "loss": 1.0714, "step": 364000 }, { "epoch": 1.08, "learning_rate": 1.2819759235707634e-05, "loss": 1.056, "step": 365000 }, { "epoch": 1.08, "learning_rate": 1.2800087343202723e-05, "loss": 1.0583, "step": 366000 }, { "epoch": 1.08, "learning_rate": 1.2780415450697812e-05, "loss": 1.0491, "step": 367000 }, { "epoch": 1.09, "learning_rate": 1.27607435581929e-05, "loss": 1.0455, "step": 368000 }, { "epoch": 1.09, "learning_rate": 1.2741071665687992e-05, "loss": 1.0629, "step": 369000 }, { "epoch": 1.09, "learning_rate": 1.2721399773183081e-05, "loss": 1.0544, "step": 370000 }, { "epoch": 1.09, "learning_rate": 1.270172788067817e-05, "loss": 1.073, "step": 371000 }, { "epoch": 1.1, "learning_rate": 1.2682055988173258e-05, "loss": 1.0671, "step": 372000 }, { "epoch": 1.1, "learning_rate": 1.266238409566835e-05, "loss": 1.0705, "step": 373000 }, { "epoch": 1.1, "learning_rate": 1.2642712203163439e-05, "loss": 1.0723, "step": 374000 }, { "epoch": 1.11, "learning_rate": 1.2623040310658527e-05, "loss": 1.071, "step": 375000 }, { "epoch": 1.11, "learning_rate": 1.2603368418153616e-05, "loss": 1.0658, "step": 376000 }, { "epoch": 1.11, "learning_rate": 1.2583696525648705e-05, "loss": 1.0697, "step": 377000 }, { "epoch": 1.12, "learning_rate": 1.2564024633143797e-05, "loss": 1.0658, "step": 378000 }, { "epoch": 1.12, "learning_rate": 1.2544352740638885e-05, "loss": 1.0611, "step": 379000 }, { "epoch": 1.12, "learning_rate": 1.2524680848133974e-05, "loss": 1.0567, "step": 380000 }, { "epoch": 1.12, "learning_rate": 1.2505008955629063e-05, "loss": 1.0618, "step": 381000 }, { "epoch": 1.13, "learning_rate": 1.2485337063124155e-05, "loss": 1.0618, "step": 382000 }, { "epoch": 1.13, "learning_rate": 1.2465665170619243e-05, "loss": 1.0679, "step": 383000 }, { "epoch": 1.13, "learning_rate": 1.2445993278114332e-05, "loss": 1.0812, "step": 384000 }, { "epoch": 1.14, "learning_rate": 1.242632138560942e-05, "loss": 1.0581, "step": 385000 }, { "epoch": 1.14, "learning_rate": 1.240664949310451e-05, "loss": 1.0675, "step": 386000 }, { "epoch": 1.14, "learning_rate": 1.2386977600599601e-05, "loss": 1.0617, "step": 387000 }, { "epoch": 1.14, "learning_rate": 1.236730570809469e-05, "loss": 1.0744, "step": 388000 }, { "epoch": 1.15, "learning_rate": 1.2347633815589779e-05, "loss": 1.0717, "step": 389000 }, { "epoch": 1.15, "learning_rate": 1.2327961923084867e-05, "loss": 1.0769, "step": 390000 }, { "epoch": 1.15, "learning_rate": 1.2308290030579958e-05, "loss": 1.0802, "step": 391000 }, { "epoch": 1.16, "learning_rate": 1.2288618138075048e-05, "loss": 1.0655, "step": 392000 }, { "epoch": 1.16, "learning_rate": 1.2268946245570137e-05, "loss": 1.0843, "step": 393000 }, { "epoch": 1.16, "learning_rate": 1.2249274353065225e-05, "loss": 1.0756, "step": 394000 }, { "epoch": 1.17, "learning_rate": 1.2229602460560315e-05, "loss": 1.0729, "step": 395000 }, { "epoch": 1.17, "learning_rate": 1.2209930568055406e-05, "loss": 1.0675, "step": 396000 }, { "epoch": 1.17, "learning_rate": 1.2190258675550494e-05, "loss": 1.0564, "step": 397000 }, { "epoch": 1.17, "learning_rate": 1.2170586783045583e-05, "loss": 1.073, "step": 398000 }, { "epoch": 1.18, "learning_rate": 1.2150914890540673e-05, "loss": 1.0634, "step": 399000 }, { "epoch": 1.18, "learning_rate": 1.2131242998035762e-05, "loss": 1.0648, "step": 400000 }, { "epoch": 1.18, "learning_rate": 1.2111571105530852e-05, "loss": 1.0659, "step": 401000 }, { "epoch": 1.19, "learning_rate": 1.2091899213025941e-05, "loss": 1.0754, "step": 402000 }, { "epoch": 1.19, "learning_rate": 1.2072227320521031e-05, "loss": 1.0661, "step": 403000 }, { "epoch": 1.19, "learning_rate": 1.205255542801612e-05, "loss": 1.0685, "step": 404000 }, { "epoch": 1.2, "learning_rate": 1.203288353551121e-05, "loss": 1.0763, "step": 405000 }, { "epoch": 1.2, "learning_rate": 1.2013211643006299e-05, "loss": 1.066, "step": 406000 }, { "epoch": 1.2, "learning_rate": 1.1993539750501388e-05, "loss": 1.0758, "step": 407000 }, { "epoch": 1.2, "learning_rate": 1.1973867857996478e-05, "loss": 1.0679, "step": 408000 }, { "epoch": 1.21, "learning_rate": 1.1954195965491567e-05, "loss": 1.0683, "step": 409000 }, { "epoch": 1.21, "learning_rate": 1.1934524072986657e-05, "loss": 1.072, "step": 410000 }, { "epoch": 1.21, "learning_rate": 1.1914852180481746e-05, "loss": 1.0774, "step": 411000 }, { "epoch": 1.22, "learning_rate": 1.1895180287976836e-05, "loss": 1.0627, "step": 412000 }, { "epoch": 1.22, "learning_rate": 1.1875508395471925e-05, "loss": 1.0736, "step": 413000 }, { "epoch": 1.22, "learning_rate": 1.1855836502967013e-05, "loss": 1.0701, "step": 414000 }, { "epoch": 1.22, "learning_rate": 1.1836164610462103e-05, "loss": 1.0763, "step": 415000 }, { "epoch": 1.23, "learning_rate": 1.1816492717957194e-05, "loss": 1.0578, "step": 416000 }, { "epoch": 1.23, "learning_rate": 1.1796820825452282e-05, "loss": 1.0737, "step": 417000 }, { "epoch": 1.23, "learning_rate": 1.1777148932947371e-05, "loss": 1.0791, "step": 418000 }, { "epoch": 1.24, "learning_rate": 1.1757477040442461e-05, "loss": 1.074, "step": 419000 }, { "epoch": 1.24, "learning_rate": 1.1737805147937552e-05, "loss": 1.0828, "step": 420000 }, { "epoch": 1.24, "learning_rate": 1.171813325543264e-05, "loss": 1.0716, "step": 421000 }, { "epoch": 1.25, "learning_rate": 1.1698461362927729e-05, "loss": 1.0765, "step": 422000 }, { "epoch": 1.25, "learning_rate": 1.1678789470422818e-05, "loss": 1.0684, "step": 423000 }, { "epoch": 1.25, "learning_rate": 1.165911757791791e-05, "loss": 1.0712, "step": 424000 }, { "epoch": 1.25, "learning_rate": 1.1639445685412998e-05, "loss": 1.0686, "step": 425000 }, { "epoch": 1.26, "learning_rate": 1.1619773792908087e-05, "loss": 1.0802, "step": 426000 }, { "epoch": 1.26, "learning_rate": 1.1600101900403176e-05, "loss": 1.072, "step": 427000 }, { "epoch": 1.26, "learning_rate": 1.1580430007898266e-05, "loss": 1.0568, "step": 428000 }, { "epoch": 1.27, "learning_rate": 1.1560758115393356e-05, "loss": 1.0693, "step": 429000 }, { "epoch": 1.27, "learning_rate": 1.1541086222888445e-05, "loss": 1.0621, "step": 430000 }, { "epoch": 1.27, "learning_rate": 1.1521414330383534e-05, "loss": 1.0619, "step": 431000 }, { "epoch": 1.27, "learning_rate": 1.1501742437878622e-05, "loss": 1.0609, "step": 432000 }, { "epoch": 1.28, "learning_rate": 1.1482070545373714e-05, "loss": 1.0811, "step": 433000 }, { "epoch": 1.28, "learning_rate": 1.1462398652868803e-05, "loss": 1.0687, "step": 434000 }, { "epoch": 1.28, "learning_rate": 1.1442726760363892e-05, "loss": 1.0674, "step": 435000 }, { "epoch": 1.29, "learning_rate": 1.142305486785898e-05, "loss": 1.0692, "step": 436000 }, { "epoch": 1.29, "learning_rate": 1.1403382975354072e-05, "loss": 1.0756, "step": 437000 }, { "epoch": 1.29, "learning_rate": 1.138371108284916e-05, "loss": 1.0721, "step": 438000 }, { "epoch": 1.3, "learning_rate": 1.136403919034425e-05, "loss": 1.0694, "step": 439000 }, { "epoch": 1.3, "learning_rate": 1.1344367297839338e-05, "loss": 1.0724, "step": 440000 }, { "epoch": 1.3, "learning_rate": 1.1324695405334427e-05, "loss": 1.0636, "step": 441000 }, { "epoch": 1.3, "learning_rate": 1.1305023512829519e-05, "loss": 1.0797, "step": 442000 }, { "epoch": 1.31, "learning_rate": 1.1285351620324607e-05, "loss": 1.0836, "step": 443000 }, { "epoch": 1.31, "learning_rate": 1.1265679727819696e-05, "loss": 1.0807, "step": 444000 }, { "epoch": 1.31, "learning_rate": 1.1246007835314785e-05, "loss": 1.0828, "step": 445000 }, { "epoch": 1.32, "learning_rate": 1.1226335942809873e-05, "loss": 1.0788, "step": 446000 }, { "epoch": 1.32, "learning_rate": 1.1206664050304965e-05, "loss": 1.0753, "step": 447000 }, { "epoch": 1.32, "learning_rate": 1.1186992157800054e-05, "loss": 1.0719, "step": 448000 }, { "epoch": 1.32, "learning_rate": 1.1167320265295143e-05, "loss": 1.0733, "step": 449000 }, { "epoch": 1.33, "learning_rate": 1.1147648372790231e-05, "loss": 1.0777, "step": 450000 }, { "epoch": 1.33, "learning_rate": 1.1127976480285323e-05, "loss": 1.0762, "step": 451000 }, { "epoch": 1.33, "learning_rate": 1.1108304587780412e-05, "loss": 1.0689, "step": 452000 }, { "epoch": 1.34, "learning_rate": 1.10886326952755e-05, "loss": 1.0728, "step": 453000 }, { "epoch": 1.34, "learning_rate": 1.106896080277059e-05, "loss": 1.0629, "step": 454000 }, { "epoch": 1.34, "learning_rate": 1.1049288910265678e-05, "loss": 1.0646, "step": 455000 }, { "epoch": 1.35, "learning_rate": 1.102961701776077e-05, "loss": 1.0794, "step": 456000 }, { "epoch": 1.35, "learning_rate": 1.1009945125255859e-05, "loss": 1.0632, "step": 457000 }, { "epoch": 1.35, "learning_rate": 1.0990273232750947e-05, "loss": 1.0751, "step": 458000 }, { "epoch": 1.35, "learning_rate": 1.0970601340246036e-05, "loss": 1.0681, "step": 459000 }, { "epoch": 1.36, "learning_rate": 1.0950929447741128e-05, "loss": 1.0673, "step": 460000 }, { "epoch": 1.36, "learning_rate": 1.0931257555236216e-05, "loss": 1.0738, "step": 461000 }, { "epoch": 1.36, "learning_rate": 1.0911585662731305e-05, "loss": 1.0745, "step": 462000 }, { "epoch": 1.37, "learning_rate": 1.0891913770226394e-05, "loss": 1.0681, "step": 463000 }, { "epoch": 1.37, "learning_rate": 1.0872241877721484e-05, "loss": 1.0709, "step": 464000 }, { "epoch": 1.37, "learning_rate": 1.0852569985216574e-05, "loss": 1.0679, "step": 465000 }, { "epoch": 1.38, "learning_rate": 1.0832898092711663e-05, "loss": 1.0785, "step": 466000 }, { "epoch": 1.38, "learning_rate": 1.0813226200206752e-05, "loss": 1.0649, "step": 467000 }, { "epoch": 1.38, "learning_rate": 1.0793554307701842e-05, "loss": 1.0695, "step": 468000 }, { "epoch": 1.38, "learning_rate": 1.0773882415196932e-05, "loss": 1.0727, "step": 469000 }, { "epoch": 1.39, "learning_rate": 1.0754210522692021e-05, "loss": 1.0733, "step": 470000 }, { "epoch": 1.39, "learning_rate": 1.073453863018711e-05, "loss": 1.0691, "step": 471000 }, { "epoch": 1.39, "learning_rate": 1.0714866737682198e-05, "loss": 1.0798, "step": 472000 }, { "epoch": 1.4, "learning_rate": 1.0695194845177289e-05, "loss": 1.0822, "step": 473000 }, { "epoch": 1.4, "learning_rate": 1.0675522952672379e-05, "loss": 1.06, "step": 474000 }, { "epoch": 1.4, "learning_rate": 1.0655851060167468e-05, "loss": 1.0774, "step": 475000 }, { "epoch": 1.4, "learning_rate": 1.0636179167662556e-05, "loss": 1.0663, "step": 476000 }, { "epoch": 1.41, "learning_rate": 1.0616507275157647e-05, "loss": 1.0725, "step": 477000 }, { "epoch": 1.41, "learning_rate": 1.0596835382652735e-05, "loss": 1.0644, "step": 478000 }, { "epoch": 1.41, "learning_rate": 1.0577163490147826e-05, "loss": 1.0609, "step": 479000 }, { "epoch": 1.42, "learning_rate": 1.0557491597642914e-05, "loss": 1.0703, "step": 480000 }, { "epoch": 1.42, "learning_rate": 1.0537819705138004e-05, "loss": 1.0702, "step": 481000 }, { "epoch": 1.42, "learning_rate": 1.0518147812633093e-05, "loss": 1.0648, "step": 482000 }, { "epoch": 1.43, "learning_rate": 1.0498475920128183e-05, "loss": 1.0654, "step": 483000 }, { "epoch": 1.43, "learning_rate": 1.0478804027623272e-05, "loss": 1.0796, "step": 484000 }, { "epoch": 1.43, "learning_rate": 1.0459132135118362e-05, "loss": 1.052, "step": 485000 }, { "epoch": 1.43, "learning_rate": 1.0439460242613451e-05, "loss": 1.0703, "step": 486000 }, { "epoch": 1.44, "learning_rate": 1.041978835010854e-05, "loss": 1.0701, "step": 487000 }, { "epoch": 1.44, "learning_rate": 1.040011645760363e-05, "loss": 1.0679, "step": 488000 }, { "epoch": 1.44, "learning_rate": 1.038044456509872e-05, "loss": 1.0675, "step": 489000 }, { "epoch": 1.45, "learning_rate": 1.0360772672593809e-05, "loss": 1.046, "step": 490000 }, { "epoch": 1.45, "learning_rate": 1.0341100780088898e-05, "loss": 1.0799, "step": 491000 }, { "epoch": 1.45, "learning_rate": 1.0321428887583988e-05, "loss": 1.0686, "step": 492000 }, { "epoch": 1.45, "learning_rate": 1.0301756995079077e-05, "loss": 1.0701, "step": 493000 }, { "epoch": 1.46, "learning_rate": 1.0282085102574167e-05, "loss": 1.0889, "step": 494000 }, { "epoch": 1.46, "learning_rate": 1.0262413210069256e-05, "loss": 1.0717, "step": 495000 }, { "epoch": 1.46, "learning_rate": 1.0242741317564344e-05, "loss": 1.0743, "step": 496000 }, { "epoch": 1.47, "learning_rate": 1.0223069425059435e-05, "loss": 1.0755, "step": 497000 }, { "epoch": 1.47, "learning_rate": 1.0203397532554525e-05, "loss": 1.0574, "step": 498000 }, { "epoch": 1.47, "learning_rate": 1.0183725640049614e-05, "loss": 1.0724, "step": 499000 }, { "epoch": 1.48, "learning_rate": 1.0164053747544702e-05, "loss": 1.0765, "step": 500000 }, { "epoch": 1.48, "learning_rate": 1.0144381855039792e-05, "loss": 1.0707, "step": 501000 }, { "epoch": 1.48, "learning_rate": 1.0124709962534883e-05, "loss": 1.0775, "step": 502000 }, { "epoch": 1.48, "learning_rate": 1.0105038070029971e-05, "loss": 1.0776, "step": 503000 }, { "epoch": 1.49, "learning_rate": 1.008536617752506e-05, "loss": 1.0511, "step": 504000 }, { "epoch": 1.49, "learning_rate": 1.0065694285020149e-05, "loss": 1.0672, "step": 505000 }, { "epoch": 1.49, "learning_rate": 1.004602239251524e-05, "loss": 1.0748, "step": 506000 }, { "epoch": 1.5, "learning_rate": 1.002635050001033e-05, "loss": 1.0604, "step": 507000 }, { "epoch": 1.5, "learning_rate": 1.0006678607505418e-05, "loss": 1.0592, "step": 508000 }, { "epoch": 1.5, "learning_rate": 9.987006715000508e-06, "loss": 1.0773, "step": 509000 }, { "epoch": 1.5, "learning_rate": 9.967334822495597e-06, "loss": 1.0654, "step": 510000 }, { "epoch": 1.51, "learning_rate": 9.947662929990686e-06, "loss": 1.0759, "step": 511000 }, { "epoch": 1.51, "learning_rate": 9.927991037485776e-06, "loss": 1.0541, "step": 512000 }, { "epoch": 1.51, "learning_rate": 9.908319144980865e-06, "loss": 1.0558, "step": 513000 }, { "epoch": 1.52, "learning_rate": 9.888647252475955e-06, "loss": 1.0778, "step": 514000 }, { "epoch": 1.52, "learning_rate": 9.868975359971044e-06, "loss": 1.0688, "step": 515000 }, { "epoch": 1.52, "learning_rate": 9.849303467466134e-06, "loss": 1.0723, "step": 516000 }, { "epoch": 1.53, "learning_rate": 9.829631574961223e-06, "loss": 1.0763, "step": 517000 }, { "epoch": 1.53, "learning_rate": 9.809959682456311e-06, "loss": 1.0784, "step": 518000 }, { "epoch": 1.53, "learning_rate": 9.790287789951402e-06, "loss": 1.0785, "step": 519000 }, { "epoch": 1.53, "learning_rate": 9.77061589744649e-06, "loss": 1.078, "step": 520000 }, { "epoch": 1.54, "learning_rate": 9.75094400494158e-06, "loss": 1.0655, "step": 521000 }, { "epoch": 1.54, "learning_rate": 9.73127211243667e-06, "loss": 1.0667, "step": 522000 }, { "epoch": 1.54, "learning_rate": 9.71160021993176e-06, "loss": 1.0753, "step": 523000 }, { "epoch": 1.55, "learning_rate": 9.691928327426848e-06, "loss": 1.0823, "step": 524000 }, { "epoch": 1.55, "learning_rate": 9.672256434921938e-06, "loss": 1.0667, "step": 525000 }, { "epoch": 1.55, "learning_rate": 9.652584542417027e-06, "loss": 1.0717, "step": 526000 }, { "epoch": 1.56, "learning_rate": 9.632912649912116e-06, "loss": 1.0704, "step": 527000 }, { "epoch": 1.56, "learning_rate": 9.613240757407206e-06, "loss": 1.0637, "step": 528000 }, { "epoch": 1.56, "learning_rate": 9.593568864902295e-06, "loss": 1.0642, "step": 529000 }, { "epoch": 1.56, "learning_rate": 9.573896972397385e-06, "loss": 1.0854, "step": 530000 }, { "epoch": 1.57, "learning_rate": 9.554225079892474e-06, "loss": 1.0594, "step": 531000 }, { "epoch": 1.57, "learning_rate": 9.534553187387564e-06, "loss": 1.0543, "step": 532000 }, { "epoch": 1.57, "learning_rate": 9.514881294882653e-06, "loss": 1.063, "step": 533000 }, { "epoch": 1.58, "learning_rate": 9.495209402377741e-06, "loss": 1.0562, "step": 534000 }, { "epoch": 1.58, "learning_rate": 9.475537509872832e-06, "loss": 1.0808, "step": 535000 }, { "epoch": 1.58, "learning_rate": 9.45586561736792e-06, "loss": 1.0594, "step": 536000 }, { "epoch": 1.58, "learning_rate": 9.43619372486301e-06, "loss": 1.0637, "step": 537000 }, { "epoch": 1.59, "learning_rate": 9.4165218323581e-06, "loss": 1.0656, "step": 538000 }, { "epoch": 1.59, "learning_rate": 9.39684993985319e-06, "loss": 1.0613, "step": 539000 }, { "epoch": 1.59, "learning_rate": 9.377178047348278e-06, "loss": 1.0782, "step": 540000 }, { "epoch": 1.6, "learning_rate": 9.357506154843369e-06, "loss": 1.0612, "step": 541000 }, { "epoch": 1.6, "learning_rate": 9.337834262338457e-06, "loss": 1.0653, "step": 542000 }, { "epoch": 1.6, "learning_rate": 9.318162369833546e-06, "loss": 1.0781, "step": 543000 }, { "epoch": 1.61, "learning_rate": 9.298490477328636e-06, "loss": 1.0632, "step": 544000 }, { "epoch": 1.61, "learning_rate": 9.278818584823725e-06, "loss": 1.0625, "step": 545000 }, { "epoch": 1.61, "learning_rate": 9.259146692318815e-06, "loss": 1.0642, "step": 546000 }, { "epoch": 1.61, "learning_rate": 9.239474799813904e-06, "loss": 1.0742, "step": 547000 }, { "epoch": 1.62, "learning_rate": 9.219802907308994e-06, "loss": 1.0657, "step": 548000 }, { "epoch": 1.62, "learning_rate": 9.200131014804083e-06, "loss": 1.0721, "step": 549000 }, { "epoch": 1.62, "learning_rate": 9.180459122299173e-06, "loss": 1.0643, "step": 550000 }, { "epoch": 1.63, "learning_rate": 9.160787229794262e-06, "loss": 1.0734, "step": 551000 }, { "epoch": 1.63, "learning_rate": 9.141115337289352e-06, "loss": 1.0551, "step": 552000 }, { "epoch": 1.63, "learning_rate": 9.12144344478444e-06, "loss": 1.0663, "step": 553000 }, { "epoch": 1.63, "learning_rate": 9.101771552279531e-06, "loss": 1.0651, "step": 554000 }, { "epoch": 1.64, "learning_rate": 9.08209965977462e-06, "loss": 1.0557, "step": 555000 }, { "epoch": 1.64, "learning_rate": 9.06242776726971e-06, "loss": 1.05, "step": 556000 }, { "epoch": 1.64, "learning_rate": 9.042755874764799e-06, "loss": 1.0664, "step": 557000 }, { "epoch": 1.65, "learning_rate": 9.023083982259889e-06, "loss": 1.0649, "step": 558000 }, { "epoch": 1.65, "learning_rate": 9.003412089754978e-06, "loss": 1.0578, "step": 559000 }, { "epoch": 1.65, "learning_rate": 8.983740197250066e-06, "loss": 1.0791, "step": 560000 }, { "epoch": 1.66, "learning_rate": 8.964068304745157e-06, "loss": 1.0677, "step": 561000 }, { "epoch": 1.66, "learning_rate": 8.944396412240245e-06, "loss": 1.0605, "step": 562000 }, { "epoch": 1.66, "learning_rate": 8.924724519735336e-06, "loss": 1.0472, "step": 563000 }, { "epoch": 1.66, "learning_rate": 8.905052627230424e-06, "loss": 1.0641, "step": 564000 }, { "epoch": 1.67, "learning_rate": 8.885380734725515e-06, "loss": 1.0609, "step": 565000 }, { "epoch": 1.67, "learning_rate": 8.865708842220603e-06, "loss": 1.0469, "step": 566000 }, { "epoch": 1.67, "learning_rate": 8.846036949715693e-06, "loss": 1.0583, "step": 567000 }, { "epoch": 1.68, "learning_rate": 8.826365057210782e-06, "loss": 1.0518, "step": 568000 }, { "epoch": 1.68, "learning_rate": 8.806693164705872e-06, "loss": 1.0702, "step": 569000 }, { "epoch": 1.68, "learning_rate": 8.787021272200961e-06, "loss": 1.0763, "step": 570000 }, { "epoch": 1.68, "learning_rate": 8.767349379696051e-06, "loss": 1.0515, "step": 571000 }, { "epoch": 1.69, "learning_rate": 8.74767748719114e-06, "loss": 1.0731, "step": 572000 }, { "epoch": 1.69, "learning_rate": 8.72800559468623e-06, "loss": 1.0629, "step": 573000 }, { "epoch": 1.69, "learning_rate": 8.708333702181319e-06, "loss": 1.0569, "step": 574000 }, { "epoch": 1.7, "learning_rate": 8.688661809676408e-06, "loss": 1.0613, "step": 575000 }, { "epoch": 1.7, "learning_rate": 8.668989917171498e-06, "loss": 1.0669, "step": 576000 }, { "epoch": 1.7, "learning_rate": 8.649318024666587e-06, "loss": 1.0517, "step": 577000 }, { "epoch": 1.71, "learning_rate": 8.629646132161677e-06, "loss": 1.0734, "step": 578000 }, { "epoch": 1.71, "learning_rate": 8.609974239656766e-06, "loss": 1.0725, "step": 579000 }, { "epoch": 1.71, "learning_rate": 8.590302347151856e-06, "loss": 1.0595, "step": 580000 }, { "epoch": 1.71, "learning_rate": 8.570630454646945e-06, "loss": 1.0518, "step": 581000 }, { "epoch": 1.72, "learning_rate": 8.550958562142033e-06, "loss": 1.0693, "step": 582000 }, { "epoch": 1.72, "learning_rate": 8.531286669637124e-06, "loss": 1.0732, "step": 583000 }, { "epoch": 1.72, "learning_rate": 8.511614777132212e-06, "loss": 1.0694, "step": 584000 }, { "epoch": 1.73, "learning_rate": 8.491942884627303e-06, "loss": 1.071, "step": 585000 }, { "epoch": 1.73, "learning_rate": 8.472270992122391e-06, "loss": 1.0635, "step": 586000 }, { "epoch": 1.73, "learning_rate": 8.452599099617481e-06, "loss": 1.0705, "step": 587000 }, { "epoch": 1.74, "learning_rate": 8.43292720711257e-06, "loss": 1.0778, "step": 588000 }, { "epoch": 1.74, "learning_rate": 8.41325531460766e-06, "loss": 1.0507, "step": 589000 }, { "epoch": 1.74, "learning_rate": 8.393583422102749e-06, "loss": 1.066, "step": 590000 }, { "epoch": 1.74, "learning_rate": 8.373911529597838e-06, "loss": 1.0637, "step": 591000 }, { "epoch": 1.75, "learning_rate": 8.354239637092928e-06, "loss": 1.0691, "step": 592000 }, { "epoch": 1.75, "learning_rate": 8.334567744588017e-06, "loss": 1.0615, "step": 593000 }, { "epoch": 1.75, "learning_rate": 8.314895852083107e-06, "loss": 1.0609, "step": 594000 }, { "epoch": 1.76, "learning_rate": 8.295223959578196e-06, "loss": 1.0677, "step": 595000 }, { "epoch": 1.76, "learning_rate": 8.275552067073286e-06, "loss": 1.0667, "step": 596000 }, { "epoch": 1.76, "learning_rate": 8.255880174568375e-06, "loss": 1.0588, "step": 597000 }, { "epoch": 1.76, "learning_rate": 8.236208282063463e-06, "loss": 1.0568, "step": 598000 }, { "epoch": 1.77, "learning_rate": 8.216536389558554e-06, "loss": 1.0599, "step": 599000 }, { "epoch": 1.77, "learning_rate": 8.196864497053642e-06, "loss": 1.0509, "step": 600000 }, { "epoch": 1.77, "learning_rate": 8.177192604548733e-06, "loss": 1.0577, "step": 601000 }, { "epoch": 1.78, "learning_rate": 8.157520712043821e-06, "loss": 1.0681, "step": 602000 }, { "epoch": 1.78, "learning_rate": 8.137848819538912e-06, "loss": 1.0763, "step": 603000 }, { "epoch": 1.78, "learning_rate": 8.118176927034e-06, "loss": 1.0633, "step": 604000 }, { "epoch": 1.79, "learning_rate": 8.09850503452909e-06, "loss": 1.0584, "step": 605000 }, { "epoch": 1.79, "learning_rate": 8.07883314202418e-06, "loss": 1.0621, "step": 606000 }, { "epoch": 1.79, "learning_rate": 8.059161249519268e-06, "loss": 1.0641, "step": 607000 }, { "epoch": 1.79, "learning_rate": 8.039489357014358e-06, "loss": 1.0799, "step": 608000 }, { "epoch": 1.8, "learning_rate": 8.019817464509447e-06, "loss": 1.0595, "step": 609000 }, { "epoch": 1.8, "learning_rate": 8.000145572004537e-06, "loss": 1.0591, "step": 610000 }, { "epoch": 1.8, "learning_rate": 7.980473679499626e-06, "loss": 1.0659, "step": 611000 }, { "epoch": 1.81, "learning_rate": 7.960801786994716e-06, "loss": 1.0531, "step": 612000 }, { "epoch": 1.81, "learning_rate": 7.941129894489805e-06, "loss": 1.0511, "step": 613000 }, { "epoch": 1.81, "learning_rate": 7.921458001984893e-06, "loss": 1.0695, "step": 614000 }, { "epoch": 1.81, "learning_rate": 7.901786109479984e-06, "loss": 1.0684, "step": 615000 }, { "epoch": 1.82, "learning_rate": 7.882114216975072e-06, "loss": 1.0543, "step": 616000 }, { "epoch": 1.82, "learning_rate": 7.862442324470163e-06, "loss": 1.0591, "step": 617000 }, { "epoch": 1.82, "learning_rate": 7.842770431965251e-06, "loss": 1.0576, "step": 618000 }, { "epoch": 1.83, "learning_rate": 7.823098539460342e-06, "loss": 1.0714, "step": 619000 }, { "epoch": 1.83, "learning_rate": 7.80342664695543e-06, "loss": 1.0526, "step": 620000 }, { "epoch": 1.83, "learning_rate": 7.78375475445052e-06, "loss": 1.069, "step": 621000 }, { "epoch": 1.84, "learning_rate": 7.76408286194561e-06, "loss": 1.0648, "step": 622000 }, { "epoch": 1.84, "learning_rate": 7.7444109694407e-06, "loss": 1.0705, "step": 623000 }, { "epoch": 1.84, "learning_rate": 7.724739076935788e-06, "loss": 1.0578, "step": 624000 }, { "epoch": 1.84, "learning_rate": 7.705067184430879e-06, "loss": 1.0598, "step": 625000 }, { "epoch": 1.85, "learning_rate": 7.685395291925967e-06, "loss": 1.0428, "step": 626000 }, { "epoch": 1.85, "learning_rate": 7.665723399421058e-06, "loss": 1.0551, "step": 627000 }, { "epoch": 1.85, "learning_rate": 7.646051506916146e-06, "loss": 1.0596, "step": 628000 }, { "epoch": 1.86, "learning_rate": 7.626379614411236e-06, "loss": 1.0548, "step": 629000 }, { "epoch": 1.86, "learning_rate": 7.606707721906324e-06, "loss": 1.0559, "step": 630000 }, { "epoch": 1.86, "learning_rate": 7.587035829401415e-06, "loss": 1.0653, "step": 631000 }, { "epoch": 1.86, "learning_rate": 7.567363936896503e-06, "loss": 1.0502, "step": 632000 }, { "epoch": 1.87, "learning_rate": 7.547692044391594e-06, "loss": 1.0769, "step": 633000 }, { "epoch": 1.87, "learning_rate": 7.528020151886682e-06, "loss": 1.0618, "step": 634000 }, { "epoch": 1.87, "learning_rate": 7.508348259381773e-06, "loss": 1.0691, "step": 635000 }, { "epoch": 1.88, "learning_rate": 7.488676366876861e-06, "loss": 1.057, "step": 636000 }, { "epoch": 1.88, "learning_rate": 7.469004474371951e-06, "loss": 1.063, "step": 637000 }, { "epoch": 1.88, "learning_rate": 7.44933258186704e-06, "loss": 1.0477, "step": 638000 }, { "epoch": 1.89, "learning_rate": 7.42966068936213e-06, "loss": 1.0568, "step": 639000 }, { "epoch": 1.89, "learning_rate": 7.409988796857219e-06, "loss": 1.0518, "step": 640000 }, { "epoch": 1.89, "learning_rate": 7.390316904352308e-06, "loss": 1.0537, "step": 641000 }, { "epoch": 1.89, "learning_rate": 7.370645011847398e-06, "loss": 1.0452, "step": 642000 }, { "epoch": 1.9, "learning_rate": 7.350973119342487e-06, "loss": 1.0611, "step": 643000 }, { "epoch": 1.9, "learning_rate": 7.331301226837577e-06, "loss": 1.0561, "step": 644000 }, { "epoch": 1.9, "learning_rate": 7.311629334332666e-06, "loss": 1.0364, "step": 645000 }, { "epoch": 1.91, "learning_rate": 7.291957441827755e-06, "loss": 1.0581, "step": 646000 }, { "epoch": 1.91, "learning_rate": 7.272285549322845e-06, "loss": 1.0637, "step": 647000 }, { "epoch": 1.91, "learning_rate": 7.252613656817934e-06, "loss": 1.0598, "step": 648000 }, { "epoch": 1.92, "learning_rate": 7.232941764313024e-06, "loss": 1.057, "step": 649000 }, { "epoch": 1.92, "learning_rate": 7.213269871808113e-06, "loss": 1.0482, "step": 650000 }, { "epoch": 1.92, "learning_rate": 7.193597979303203e-06, "loss": 1.048, "step": 651000 }, { "epoch": 1.92, "learning_rate": 7.173926086798292e-06, "loss": 1.0488, "step": 652000 }, { "epoch": 1.93, "learning_rate": 7.154254194293381e-06, "loss": 1.0554, "step": 653000 }, { "epoch": 1.93, "learning_rate": 7.134582301788471e-06, "loss": 1.0576, "step": 654000 }, { "epoch": 1.93, "learning_rate": 7.11491040928356e-06, "loss": 1.0561, "step": 655000 }, { "epoch": 1.94, "learning_rate": 7.09523851677865e-06, "loss": 1.0501, "step": 656000 }, { "epoch": 1.94, "learning_rate": 7.075566624273739e-06, "loss": 1.047, "step": 657000 }, { "epoch": 1.94, "learning_rate": 7.055894731768829e-06, "loss": 1.0578, "step": 658000 }, { "epoch": 1.94, "learning_rate": 7.036222839263918e-06, "loss": 1.0533, "step": 659000 }, { "epoch": 1.95, "learning_rate": 7.016550946759008e-06, "loss": 1.0391, "step": 660000 }, { "epoch": 1.95, "learning_rate": 6.996879054254097e-06, "loss": 1.0546, "step": 661000 }, { "epoch": 1.95, "learning_rate": 6.977207161749185e-06, "loss": 1.052, "step": 662000 }, { "epoch": 1.96, "learning_rate": 6.957535269244276e-06, "loss": 1.0568, "step": 663000 }, { "epoch": 1.96, "learning_rate": 6.937863376739364e-06, "loss": 1.0574, "step": 664000 }, { "epoch": 1.96, "learning_rate": 6.918191484234455e-06, "loss": 1.0464, "step": 665000 }, { "epoch": 1.97, "learning_rate": 6.898519591729543e-06, "loss": 1.0449, "step": 666000 }, { "epoch": 1.97, "learning_rate": 6.878847699224634e-06, "loss": 1.0661, "step": 667000 }, { "epoch": 1.97, "learning_rate": 6.859175806719722e-06, "loss": 1.0505, "step": 668000 }, { "epoch": 1.97, "learning_rate": 6.839503914214811e-06, "loss": 1.0491, "step": 669000 }, { "epoch": 1.98, "learning_rate": 6.819832021709901e-06, "loss": 1.0549, "step": 670000 }, { "epoch": 1.98, "learning_rate": 6.80016012920499e-06, "loss": 1.0545, "step": 671000 }, { "epoch": 1.98, "learning_rate": 6.78048823670008e-06, "loss": 1.0526, "step": 672000 }, { "epoch": 1.99, "learning_rate": 6.760816344195169e-06, "loss": 1.0548, "step": 673000 }, { "epoch": 1.99, "learning_rate": 6.741144451690259e-06, "loss": 1.0466, "step": 674000 }, { "epoch": 1.99, "learning_rate": 6.721472559185348e-06, "loss": 1.0601, "step": 675000 }, { "epoch": 1.99, "learning_rate": 6.701800666680438e-06, "loss": 1.0452, "step": 676000 }, { "epoch": 2.0, "learning_rate": 6.682128774175527e-06, "loss": 1.0542, "step": 677000 }, { "epoch": 2.0, "eval_bleu": 40.9459, "eval_gen_len": 17.4725, "eval_loss": 1.094636082649231, "eval_runtime": 975.1915, "eval_samples_per_second": 56.164, "eval_steps_per_second": 3.511, "step": 677786 }, { "epoch": 2.0, "learning_rate": 6.662456881670616e-06, "loss": 1.0344, "step": 678000 }, { "epoch": 2.0, "learning_rate": 6.642784989165706e-06, "loss": 0.9632, "step": 679000 }, { "epoch": 2.01, "learning_rate": 6.623113096660795e-06, "loss": 0.9809, "step": 680000 }, { "epoch": 2.01, "learning_rate": 6.603441204155885e-06, "loss": 0.9859, "step": 681000 }, { "epoch": 2.01, "learning_rate": 6.583769311650974e-06, "loss": 0.9681, "step": 682000 }, { "epoch": 2.02, "learning_rate": 6.564097419146064e-06, "loss": 0.9736, "step": 683000 }, { "epoch": 2.02, "learning_rate": 6.544425526641152e-06, "loss": 0.9695, "step": 684000 }, { "epoch": 2.02, "learning_rate": 6.524753634136242e-06, "loss": 0.9848, "step": 685000 }, { "epoch": 2.02, "learning_rate": 6.505081741631331e-06, "loss": 0.9775, "step": 686000 }, { "epoch": 2.03, "learning_rate": 6.485409849126421e-06, "loss": 0.9738, "step": 687000 }, { "epoch": 2.03, "learning_rate": 6.46573795662151e-06, "loss": 0.9662, "step": 688000 }, { "epoch": 2.03, "learning_rate": 6.4460660641166e-06, "loss": 0.9705, "step": 689000 }, { "epoch": 2.04, "learning_rate": 6.426394171611689e-06, "loss": 0.9674, "step": 690000 }, { "epoch": 2.04, "learning_rate": 6.406722279106779e-06, "loss": 0.975, "step": 691000 }, { "epoch": 2.04, "learning_rate": 6.387050386601868e-06, "loss": 0.9763, "step": 692000 }, { "epoch": 2.04, "learning_rate": 6.367378494096958e-06, "loss": 0.9712, "step": 693000 }, { "epoch": 2.05, "learning_rate": 6.347706601592046e-06, "loss": 0.9718, "step": 694000 }, { "epoch": 2.05, "learning_rate": 6.328034709087137e-06, "loss": 0.9996, "step": 695000 }, { "epoch": 2.05, "learning_rate": 6.308362816582225e-06, "loss": 0.9744, "step": 696000 }, { "epoch": 2.06, "learning_rate": 6.288690924077316e-06, "loss": 0.9728, "step": 697000 }, { "epoch": 2.06, "learning_rate": 6.269019031572404e-06, "loss": 0.974, "step": 698000 }, { "epoch": 2.06, "learning_rate": 6.249347139067495e-06, "loss": 0.9766, "step": 699000 }, { "epoch": 2.07, "learning_rate": 6.229675246562583e-06, "loss": 0.972, "step": 700000 }, { "epoch": 2.07, "learning_rate": 6.210003354057672e-06, "loss": 0.973, "step": 701000 }, { "epoch": 2.07, "learning_rate": 6.190331461552762e-06, "loss": 0.9685, "step": 702000 }, { "epoch": 2.07, "learning_rate": 6.170659569047851e-06, "loss": 0.9883, "step": 703000 }, { "epoch": 2.08, "learning_rate": 6.150987676542941e-06, "loss": 0.9834, "step": 704000 }, { "epoch": 2.08, "learning_rate": 6.13131578403803e-06, "loss": 0.973, "step": 705000 }, { "epoch": 2.08, "learning_rate": 6.11164389153312e-06, "loss": 0.98, "step": 706000 }, { "epoch": 2.09, "learning_rate": 6.091971999028209e-06, "loss": 0.9797, "step": 707000 }, { "epoch": 2.09, "learning_rate": 6.072300106523299e-06, "loss": 0.9663, "step": 708000 }, { "epoch": 2.09, "learning_rate": 6.052628214018388e-06, "loss": 0.9792, "step": 709000 }, { "epoch": 2.1, "learning_rate": 6.032956321513476e-06, "loss": 0.9783, "step": 710000 }, { "epoch": 2.1, "learning_rate": 6.013284429008567e-06, "loss": 0.9797, "step": 711000 }, { "epoch": 2.1, "learning_rate": 5.993612536503655e-06, "loss": 0.9706, "step": 712000 }, { "epoch": 2.1, "learning_rate": 5.973940643998746e-06, "loss": 0.9754, "step": 713000 }, { "epoch": 2.11, "learning_rate": 5.954268751493834e-06, "loss": 0.9811, "step": 714000 }, { "epoch": 2.11, "learning_rate": 5.934596858988925e-06, "loss": 0.9731, "step": 715000 }, { "epoch": 2.11, "learning_rate": 5.914924966484013e-06, "loss": 0.976, "step": 716000 }, { "epoch": 2.12, "learning_rate": 5.895253073979103e-06, "loss": 0.9815, "step": 717000 }, { "epoch": 2.12, "learning_rate": 5.875581181474192e-06, "loss": 0.9706, "step": 718000 }, { "epoch": 2.12, "learning_rate": 5.855909288969282e-06, "loss": 0.985, "step": 719000 }, { "epoch": 2.12, "learning_rate": 5.836237396464371e-06, "loss": 0.9787, "step": 720000 }, { "epoch": 2.13, "learning_rate": 5.816565503959461e-06, "loss": 0.9817, "step": 721000 }, { "epoch": 2.13, "learning_rate": 5.79689361145455e-06, "loss": 0.9861, "step": 722000 }, { "epoch": 2.13, "learning_rate": 5.77722171894964e-06, "loss": 0.9763, "step": 723000 }, { "epoch": 2.14, "learning_rate": 5.757549826444729e-06, "loss": 0.9746, "step": 724000 }, { "epoch": 2.14, "learning_rate": 5.737877933939819e-06, "loss": 0.9779, "step": 725000 }, { "epoch": 2.14, "learning_rate": 5.718206041434907e-06, "loss": 0.9743, "step": 726000 }, { "epoch": 2.15, "learning_rate": 5.698534148929998e-06, "loss": 0.9834, "step": 727000 }, { "epoch": 2.15, "learning_rate": 5.678862256425086e-06, "loss": 0.9754, "step": 728000 }, { "epoch": 2.15, "learning_rate": 5.659190363920176e-06, "loss": 0.9836, "step": 729000 }, { "epoch": 2.15, "learning_rate": 5.639518471415265e-06, "loss": 0.9788, "step": 730000 }, { "epoch": 2.16, "learning_rate": 5.619846578910355e-06, "loss": 0.973, "step": 731000 }, { "epoch": 2.16, "learning_rate": 5.600174686405444e-06, "loss": 0.9761, "step": 732000 }, { "epoch": 2.16, "learning_rate": 5.580502793900533e-06, "loss": 0.9739, "step": 733000 }, { "epoch": 2.17, "learning_rate": 5.560830901395623e-06, "loss": 0.9828, "step": 734000 }, { "epoch": 2.17, "learning_rate": 5.541159008890712e-06, "loss": 0.9842, "step": 735000 }, { "epoch": 2.17, "learning_rate": 5.521487116385802e-06, "loss": 0.9867, "step": 736000 }, { "epoch": 2.17, "learning_rate": 5.501815223880891e-06, "loss": 0.9707, "step": 737000 }, { "epoch": 2.18, "learning_rate": 5.482143331375981e-06, "loss": 0.9757, "step": 738000 }, { "epoch": 2.18, "learning_rate": 5.46247143887107e-06, "loss": 0.9754, "step": 739000 }, { "epoch": 2.18, "learning_rate": 5.44279954636616e-06, "loss": 0.9943, "step": 740000 }, { "epoch": 2.19, "learning_rate": 5.423127653861249e-06, "loss": 0.9788, "step": 741000 }, { "epoch": 2.19, "learning_rate": 5.403455761356337e-06, "loss": 0.98, "step": 742000 }, { "epoch": 2.19, "learning_rate": 5.383783868851428e-06, "loss": 0.9706, "step": 743000 }, { "epoch": 2.2, "learning_rate": 5.364111976346516e-06, "loss": 0.9777, "step": 744000 }, { "epoch": 2.2, "learning_rate": 5.344440083841607e-06, "loss": 0.9813, "step": 745000 }, { "epoch": 2.2, "learning_rate": 5.324768191336695e-06, "loss": 0.9771, "step": 746000 }, { "epoch": 2.2, "learning_rate": 5.305096298831786e-06, "loss": 0.9881, "step": 747000 }, { "epoch": 2.21, "learning_rate": 5.285424406326874e-06, "loss": 0.9805, "step": 748000 }, { "epoch": 2.21, "learning_rate": 5.265752513821964e-06, "loss": 0.9775, "step": 749000 }, { "epoch": 2.21, "learning_rate": 5.246080621317053e-06, "loss": 0.9865, "step": 750000 }, { "epoch": 2.22, "learning_rate": 5.226408728812142e-06, "loss": 0.9831, "step": 751000 }, { "epoch": 2.22, "learning_rate": 5.206736836307232e-06, "loss": 0.972, "step": 752000 }, { "epoch": 2.22, "learning_rate": 5.187064943802321e-06, "loss": 0.9796, "step": 753000 }, { "epoch": 2.22, "learning_rate": 5.167393051297411e-06, "loss": 0.9872, "step": 754000 }, { "epoch": 2.23, "learning_rate": 5.1477211587925e-06, "loss": 0.9849, "step": 755000 }, { "epoch": 2.23, "learning_rate": 5.12804926628759e-06, "loss": 0.9951, "step": 756000 }, { "epoch": 2.23, "learning_rate": 5.108377373782679e-06, "loss": 0.9861, "step": 757000 }, { "epoch": 2.24, "learning_rate": 5.088705481277768e-06, "loss": 0.9804, "step": 758000 }, { "epoch": 2.24, "learning_rate": 5.069033588772858e-06, "loss": 0.9744, "step": 759000 }, { "epoch": 2.24, "learning_rate": 5.049361696267947e-06, "loss": 0.9745, "step": 760000 }, { "epoch": 2.25, "learning_rate": 5.029689803763037e-06, "loss": 0.9727, "step": 761000 }, { "epoch": 2.25, "learning_rate": 5.010017911258126e-06, "loss": 0.9739, "step": 762000 }, { "epoch": 2.25, "learning_rate": 4.990346018753216e-06, "loss": 0.9823, "step": 763000 }, { "epoch": 2.25, "learning_rate": 4.970674126248305e-06, "loss": 0.9793, "step": 764000 }, { "epoch": 2.26, "learning_rate": 4.951002233743395e-06, "loss": 0.9846, "step": 765000 }, { "epoch": 2.26, "learning_rate": 4.931330341238484e-06, "loss": 0.9906, "step": 766000 }, { "epoch": 2.26, "learning_rate": 4.911658448733574e-06, "loss": 0.9892, "step": 767000 }, { "epoch": 2.27, "learning_rate": 4.891986556228663e-06, "loss": 0.9862, "step": 768000 }, { "epoch": 2.27, "learning_rate": 4.872314663723752e-06, "loss": 0.9855, "step": 769000 }, { "epoch": 2.27, "learning_rate": 4.852642771218841e-06, "loss": 0.9688, "step": 770000 }, { "epoch": 2.28, "learning_rate": 4.832970878713931e-06, "loss": 0.9715, "step": 771000 }, { "epoch": 2.28, "learning_rate": 4.81329898620902e-06, "loss": 0.9735, "step": 772000 }, { "epoch": 2.28, "learning_rate": 4.79362709370411e-06, "loss": 0.9778, "step": 773000 }, { "epoch": 2.28, "learning_rate": 4.773955201199199e-06, "loss": 0.9694, "step": 774000 }, { "epoch": 2.29, "learning_rate": 4.754283308694289e-06, "loss": 0.9721, "step": 775000 }, { "epoch": 2.29, "learning_rate": 4.734611416189378e-06, "loss": 0.979, "step": 776000 }, { "epoch": 2.29, "learning_rate": 4.714939523684467e-06, "loss": 0.9674, "step": 777000 }, { "epoch": 2.3, "learning_rate": 4.695267631179556e-06, "loss": 0.9804, "step": 778000 }, { "epoch": 2.3, "learning_rate": 4.675595738674646e-06, "loss": 0.9927, "step": 779000 }, { "epoch": 2.3, "learning_rate": 4.655923846169735e-06, "loss": 0.9715, "step": 780000 }, { "epoch": 2.3, "learning_rate": 4.636251953664825e-06, "loss": 0.9657, "step": 781000 }, { "epoch": 2.31, "learning_rate": 4.616580061159914e-06, "loss": 0.9803, "step": 782000 }, { "epoch": 2.31, "learning_rate": 4.596908168655004e-06, "loss": 0.9806, "step": 783000 }, { "epoch": 2.31, "learning_rate": 4.577236276150093e-06, "loss": 0.9818, "step": 784000 }, { "epoch": 2.32, "learning_rate": 4.557564383645182e-06, "loss": 0.9706, "step": 785000 }, { "epoch": 2.32, "learning_rate": 4.537892491140271e-06, "loss": 0.9822, "step": 786000 }, { "epoch": 2.32, "learning_rate": 4.518220598635361e-06, "loss": 0.9799, "step": 787000 }, { "epoch": 2.33, "learning_rate": 4.49854870613045e-06, "loss": 0.9548, "step": 788000 }, { "epoch": 2.33, "learning_rate": 4.47887681362554e-06, "loss": 0.9791, "step": 789000 }, { "epoch": 2.33, "learning_rate": 4.459204921120629e-06, "loss": 0.9851, "step": 790000 }, { "epoch": 2.33, "learning_rate": 4.439533028615719e-06, "loss": 0.9744, "step": 791000 }, { "epoch": 2.34, "learning_rate": 4.419861136110808e-06, "loss": 0.9644, "step": 792000 }, { "epoch": 2.34, "learning_rate": 4.400189243605898e-06, "loss": 0.9762, "step": 793000 }, { "epoch": 2.34, "learning_rate": 4.380517351100987e-06, "loss": 0.9787, "step": 794000 }, { "epoch": 2.35, "learning_rate": 4.360845458596077e-06, "loss": 0.9838, "step": 795000 }, { "epoch": 2.35, "learning_rate": 4.341173566091165e-06, "loss": 0.9657, "step": 796000 }, { "epoch": 2.35, "learning_rate": 4.321501673586255e-06, "loss": 0.9813, "step": 797000 }, { "epoch": 2.35, "learning_rate": 4.301829781081344e-06, "loss": 0.9628, "step": 798000 }, { "epoch": 2.36, "learning_rate": 4.282157888576434e-06, "loss": 0.9899, "step": 799000 }, { "epoch": 2.36, "learning_rate": 4.262485996071523e-06, "loss": 0.9803, "step": 800000 }, { "epoch": 2.36, "learning_rate": 4.242814103566613e-06, "loss": 0.9739, "step": 801000 }, { "epoch": 2.37, "learning_rate": 4.223142211061702e-06, "loss": 0.9746, "step": 802000 }, { "epoch": 2.37, "learning_rate": 4.203470318556792e-06, "loss": 0.9647, "step": 803000 }, { "epoch": 2.37, "learning_rate": 4.183798426051881e-06, "loss": 0.9928, "step": 804000 }, { "epoch": 2.38, "learning_rate": 4.164126533546971e-06, "loss": 0.9721, "step": 805000 }, { "epoch": 2.38, "learning_rate": 4.14445464104206e-06, "loss": 0.9803, "step": 806000 }, { "epoch": 2.38, "learning_rate": 4.12478274853715e-06, "loss": 0.9823, "step": 807000 }, { "epoch": 2.38, "learning_rate": 4.105110856032238e-06, "loss": 0.9717, "step": 808000 }, { "epoch": 2.39, "learning_rate": 4.085438963527328e-06, "loss": 0.9867, "step": 809000 }, { "epoch": 2.39, "learning_rate": 4.065767071022417e-06, "loss": 0.9768, "step": 810000 }, { "epoch": 2.39, "learning_rate": 4.046095178517507e-06, "loss": 0.973, "step": 811000 }, { "epoch": 2.4, "learning_rate": 4.026423286012596e-06, "loss": 0.9789, "step": 812000 }, { "epoch": 2.4, "learning_rate": 4.006751393507686e-06, "loss": 0.9762, "step": 813000 }, { "epoch": 2.4, "learning_rate": 3.987079501002775e-06, "loss": 0.9849, "step": 814000 }, { "epoch": 2.4, "learning_rate": 3.967407608497865e-06, "loss": 0.98, "step": 815000 }, { "epoch": 2.41, "learning_rate": 3.947735715992953e-06, "loss": 0.9691, "step": 816000 }, { "epoch": 2.41, "learning_rate": 3.928063823488043e-06, "loss": 0.9826, "step": 817000 }, { "epoch": 2.41, "learning_rate": 3.908391930983132e-06, "loss": 0.9707, "step": 818000 }, { "epoch": 2.42, "learning_rate": 3.888720038478222e-06, "loss": 0.9704, "step": 819000 }, { "epoch": 2.42, "learning_rate": 3.869048145973311e-06, "loss": 0.9797, "step": 820000 }, { "epoch": 2.42, "learning_rate": 3.849376253468401e-06, "loss": 0.9699, "step": 821000 }, { "epoch": 2.43, "learning_rate": 3.82970436096349e-06, "loss": 0.9815, "step": 822000 }, { "epoch": 2.43, "learning_rate": 3.81003246845858e-06, "loss": 0.964, "step": 823000 }, { "epoch": 2.43, "learning_rate": 3.790360575953669e-06, "loss": 0.9744, "step": 824000 }, { "epoch": 2.43, "learning_rate": 3.7706886834487584e-06, "loss": 0.9823, "step": 825000 }, { "epoch": 2.44, "learning_rate": 3.751016790943848e-06, "loss": 0.9782, "step": 826000 }, { "epoch": 2.44, "learning_rate": 3.7313448984389373e-06, "loss": 0.97, "step": 827000 }, { "epoch": 2.44, "learning_rate": 3.711673005934027e-06, "loss": 0.9819, "step": 828000 }, { "epoch": 2.45, "learning_rate": 3.6920011134291163e-06, "loss": 0.9961, "step": 829000 }, { "epoch": 2.45, "learning_rate": 3.6723292209242058e-06, "loss": 0.9722, "step": 830000 }, { "epoch": 2.45, "learning_rate": 3.6526573284192953e-06, "loss": 0.9742, "step": 831000 }, { "epoch": 2.46, "learning_rate": 3.632985435914384e-06, "loss": 0.9701, "step": 832000 }, { "epoch": 2.46, "learning_rate": 3.6133135434094734e-06, "loss": 0.9812, "step": 833000 }, { "epoch": 2.46, "learning_rate": 3.593641650904563e-06, "loss": 0.9717, "step": 834000 }, { "epoch": 2.46, "learning_rate": 3.5739697583996524e-06, "loss": 0.9744, "step": 835000 }, { "epoch": 2.47, "learning_rate": 3.554297865894742e-06, "loss": 0.9733, "step": 836000 }, { "epoch": 2.47, "learning_rate": 3.5346259733898313e-06, "loss": 0.9798, "step": 837000 }, { "epoch": 2.47, "learning_rate": 3.514954080884921e-06, "loss": 0.9777, "step": 838000 }, { "epoch": 2.48, "learning_rate": 3.4952821883800103e-06, "loss": 0.9802, "step": 839000 }, { "epoch": 2.48, "learning_rate": 3.4756102958750994e-06, "loss": 0.9689, "step": 840000 }, { "epoch": 2.48, "learning_rate": 3.455938403370189e-06, "loss": 0.9647, "step": 841000 }, { "epoch": 2.48, "learning_rate": 3.4362665108652783e-06, "loss": 0.9736, "step": 842000 }, { "epoch": 2.49, "learning_rate": 3.416594618360368e-06, "loss": 0.9896, "step": 843000 }, { "epoch": 2.49, "learning_rate": 3.3969227258554573e-06, "loss": 0.9882, "step": 844000 }, { "epoch": 2.49, "learning_rate": 3.377250833350547e-06, "loss": 0.9604, "step": 845000 }, { "epoch": 2.5, "learning_rate": 3.357578940845636e-06, "loss": 0.9821, "step": 846000 }, { "epoch": 2.5, "learning_rate": 3.3379070483407254e-06, "loss": 0.9684, "step": 847000 }, { "epoch": 2.5, "learning_rate": 3.3182351558358144e-06, "loss": 0.976, "step": 848000 }, { "epoch": 2.51, "learning_rate": 3.298563263330904e-06, "loss": 0.9714, "step": 849000 }, { "epoch": 2.51, "learning_rate": 3.2788913708259934e-06, "loss": 0.982, "step": 850000 }, { "epoch": 2.51, "learning_rate": 3.259219478321083e-06, "loss": 0.9673, "step": 851000 }, { "epoch": 2.51, "learning_rate": 3.2395475858161724e-06, "loss": 0.9851, "step": 852000 }, { "epoch": 2.52, "learning_rate": 3.219875693311262e-06, "loss": 0.9802, "step": 853000 }, { "epoch": 2.52, "learning_rate": 3.2002038008063513e-06, "loss": 0.9663, "step": 854000 }, { "epoch": 2.52, "learning_rate": 3.180531908301441e-06, "loss": 0.9751, "step": 855000 }, { "epoch": 2.53, "learning_rate": 3.16086001579653e-06, "loss": 0.9608, "step": 856000 }, { "epoch": 2.53, "learning_rate": 3.1411881232916194e-06, "loss": 0.9687, "step": 857000 }, { "epoch": 2.53, "learning_rate": 3.1215162307867084e-06, "loss": 0.9762, "step": 858000 }, { "epoch": 2.53, "learning_rate": 3.101844338281798e-06, "loss": 0.9624, "step": 859000 }, { "epoch": 2.54, "learning_rate": 3.0821724457768874e-06, "loss": 0.9934, "step": 860000 }, { "epoch": 2.54, "learning_rate": 3.062500553271977e-06, "loss": 0.9746, "step": 861000 }, { "epoch": 2.54, "learning_rate": 3.0428286607670664e-06, "loss": 0.9695, "step": 862000 }, { "epoch": 2.55, "learning_rate": 3.023156768262156e-06, "loss": 0.9795, "step": 863000 }, { "epoch": 2.55, "learning_rate": 3.003484875757245e-06, "loss": 0.9716, "step": 864000 }, { "epoch": 2.55, "learning_rate": 2.9838129832523344e-06, "loss": 0.9812, "step": 865000 }, { "epoch": 2.56, "learning_rate": 2.964141090747424e-06, "loss": 0.9875, "step": 866000 }, { "epoch": 2.56, "learning_rate": 2.9444691982425134e-06, "loss": 0.9805, "step": 867000 }, { "epoch": 2.56, "learning_rate": 2.924797305737603e-06, "loss": 0.9674, "step": 868000 }, { "epoch": 2.56, "learning_rate": 2.9051254132326923e-06, "loss": 0.9894, "step": 869000 }, { "epoch": 2.57, "learning_rate": 2.885453520727782e-06, "loss": 0.9677, "step": 870000 }, { "epoch": 2.57, "learning_rate": 2.8657816282228713e-06, "loss": 0.9716, "step": 871000 }, { "epoch": 2.57, "learning_rate": 2.84610973571796e-06, "loss": 0.9673, "step": 872000 }, { "epoch": 2.58, "learning_rate": 2.8264378432130494e-06, "loss": 0.9691, "step": 873000 }, { "epoch": 2.58, "learning_rate": 2.806765950708139e-06, "loss": 0.9897, "step": 874000 }, { "epoch": 2.58, "learning_rate": 2.7870940582032284e-06, "loss": 0.9717, "step": 875000 }, { "epoch": 2.58, "learning_rate": 2.767422165698318e-06, "loss": 0.9845, "step": 876000 }, { "epoch": 2.59, "learning_rate": 2.7477502731934074e-06, "loss": 0.979, "step": 877000 }, { "epoch": 2.59, "learning_rate": 2.728078380688497e-06, "loss": 0.9764, "step": 878000 }, { "epoch": 2.59, "learning_rate": 2.7084064881835864e-06, "loss": 0.9655, "step": 879000 }, { "epoch": 2.6, "learning_rate": 2.6887345956786754e-06, "loss": 0.9797, "step": 880000 }, { "epoch": 2.6, "learning_rate": 2.669062703173765e-06, "loss": 0.9551, "step": 881000 }, { "epoch": 2.6, "learning_rate": 2.6493908106688544e-06, "loss": 0.9653, "step": 882000 }, { "epoch": 2.61, "learning_rate": 2.629718918163944e-06, "loss": 0.9762, "step": 883000 }, { "epoch": 2.61, "learning_rate": 2.6100470256590334e-06, "loss": 0.9565, "step": 884000 }, { "epoch": 2.61, "learning_rate": 2.590375133154123e-06, "loss": 0.9764, "step": 885000 }, { "epoch": 2.61, "learning_rate": 2.5707032406492123e-06, "loss": 0.9669, "step": 886000 }, { "epoch": 2.62, "learning_rate": 2.551031348144302e-06, "loss": 0.9636, "step": 887000 }, { "epoch": 2.62, "learning_rate": 2.5313594556393905e-06, "loss": 0.9765, "step": 888000 }, { "epoch": 2.62, "learning_rate": 2.51168756313448e-06, "loss": 0.9652, "step": 889000 }, { "epoch": 2.63, "learning_rate": 2.4920156706295694e-06, "loss": 0.9668, "step": 890000 }, { "epoch": 2.63, "learning_rate": 2.472343778124659e-06, "loss": 0.9789, "step": 891000 }, { "epoch": 2.63, "learning_rate": 2.4526718856197484e-06, "loss": 0.9778, "step": 892000 }, { "epoch": 2.64, "learning_rate": 2.432999993114838e-06, "loss": 0.9762, "step": 893000 }, { "epoch": 2.64, "learning_rate": 2.413328100609927e-06, "loss": 0.9652, "step": 894000 }, { "epoch": 2.64, "learning_rate": 2.3936562081050164e-06, "loss": 0.9637, "step": 895000 }, { "epoch": 2.64, "learning_rate": 2.373984315600106e-06, "loss": 0.9855, "step": 896000 }, { "epoch": 2.65, "learning_rate": 2.3543124230951954e-06, "loss": 0.9618, "step": 897000 }, { "epoch": 2.65, "learning_rate": 2.334640530590285e-06, "loss": 0.97, "step": 898000 }, { "epoch": 2.65, "learning_rate": 2.3149686380853744e-06, "loss": 0.9798, "step": 899000 }, { "epoch": 2.66, "learning_rate": 2.295296745580464e-06, "loss": 0.9667, "step": 900000 }, { "epoch": 2.66, "learning_rate": 2.2756248530755533e-06, "loss": 0.9697, "step": 901000 }, { "epoch": 2.66, "learning_rate": 2.2559529605706424e-06, "loss": 0.9634, "step": 902000 }, { "epoch": 2.66, "learning_rate": 2.236281068065732e-06, "loss": 0.9736, "step": 903000 }, { "epoch": 2.67, "learning_rate": 2.2166091755608214e-06, "loss": 0.9658, "step": 904000 }, { "epoch": 2.67, "learning_rate": 2.196937283055911e-06, "loss": 0.9655, "step": 905000 }, { "epoch": 2.67, "learning_rate": 2.177265390551e-06, "loss": 0.962, "step": 906000 }, { "epoch": 2.68, "learning_rate": 2.1575934980460894e-06, "loss": 0.975, "step": 907000 }, { "epoch": 2.68, "learning_rate": 2.137921605541179e-06, "loss": 0.983, "step": 908000 }, { "epoch": 2.68, "learning_rate": 2.1182497130362684e-06, "loss": 0.9622, "step": 909000 }, { "epoch": 2.69, "learning_rate": 2.0985778205313574e-06, "loss": 0.977, "step": 910000 }, { "epoch": 2.69, "learning_rate": 2.078905928026447e-06, "loss": 0.9745, "step": 911000 }, { "epoch": 2.69, "learning_rate": 2.0592340355215364e-06, "loss": 0.983, "step": 912000 }, { "epoch": 2.69, "learning_rate": 2.039562143016626e-06, "loss": 0.9624, "step": 913000 }, { "epoch": 2.7, "learning_rate": 2.019890250511715e-06, "loss": 0.9647, "step": 914000 }, { "epoch": 2.7, "learning_rate": 2.0002183580068045e-06, "loss": 0.9723, "step": 915000 }, { "epoch": 2.7, "learning_rate": 1.980546465501894e-06, "loss": 0.9648, "step": 916000 }, { "epoch": 2.71, "learning_rate": 1.9608745729969834e-06, "loss": 0.9748, "step": 917000 }, { "epoch": 2.71, "learning_rate": 1.941202680492073e-06, "loss": 0.9809, "step": 918000 }, { "epoch": 2.71, "learning_rate": 1.9215307879871624e-06, "loss": 0.958, "step": 919000 }, { "epoch": 2.71, "learning_rate": 1.9018588954822517e-06, "loss": 0.9728, "step": 920000 }, { "epoch": 2.72, "learning_rate": 1.8821870029773412e-06, "loss": 0.973, "step": 921000 }, { "epoch": 2.72, "learning_rate": 1.8625151104724304e-06, "loss": 0.956, "step": 922000 }, { "epoch": 2.72, "learning_rate": 1.84284321796752e-06, "loss": 0.9732, "step": 923000 }, { "epoch": 2.73, "learning_rate": 1.8231713254626094e-06, "loss": 0.9658, "step": 924000 }, { "epoch": 2.73, "learning_rate": 1.8034994329576989e-06, "loss": 0.9606, "step": 925000 }, { "epoch": 2.73, "learning_rate": 1.783827540452788e-06, "loss": 0.98, "step": 926000 }, { "epoch": 2.74, "learning_rate": 1.7641556479478774e-06, "loss": 0.9606, "step": 927000 }, { "epoch": 2.74, "learning_rate": 1.744483755442967e-06, "loss": 0.9662, "step": 928000 }, { "epoch": 2.74, "learning_rate": 1.7248118629380564e-06, "loss": 0.9596, "step": 929000 }, { "epoch": 2.74, "learning_rate": 1.7051399704331457e-06, "loss": 0.9665, "step": 930000 }, { "epoch": 2.75, "learning_rate": 1.6854680779282352e-06, "loss": 0.9616, "step": 931000 }, { "epoch": 2.75, "learning_rate": 1.6657961854233247e-06, "loss": 0.9682, "step": 932000 }, { "epoch": 2.75, "learning_rate": 1.646124292918414e-06, "loss": 0.9685, "step": 933000 }, { "epoch": 2.76, "learning_rate": 1.6264524004135032e-06, "loss": 0.9773, "step": 934000 }, { "epoch": 2.76, "learning_rate": 1.6067805079085927e-06, "loss": 0.9644, "step": 935000 }, { "epoch": 2.76, "learning_rate": 1.5871086154036822e-06, "loss": 0.9563, "step": 936000 }, { "epoch": 2.76, "learning_rate": 1.5674367228987717e-06, "loss": 0.9652, "step": 937000 }, { "epoch": 2.77, "learning_rate": 1.547764830393861e-06, "loss": 0.963, "step": 938000 }, { "epoch": 2.77, "learning_rate": 1.5280929378889502e-06, "loss": 0.9573, "step": 939000 }, { "epoch": 2.77, "learning_rate": 1.5084210453840397e-06, "loss": 0.9671, "step": 940000 }, { "epoch": 2.78, "learning_rate": 1.4887491528791292e-06, "loss": 0.9628, "step": 941000 }, { "epoch": 2.78, "learning_rate": 1.4690772603742185e-06, "loss": 0.97, "step": 942000 }, { "epoch": 2.78, "learning_rate": 1.449405367869308e-06, "loss": 0.9716, "step": 943000 }, { "epoch": 2.79, "learning_rate": 1.4297334753643974e-06, "loss": 0.9618, "step": 944000 }, { "epoch": 2.79, "learning_rate": 1.410061582859487e-06, "loss": 0.9827, "step": 945000 }, { "epoch": 2.79, "learning_rate": 1.390389690354576e-06, "loss": 0.966, "step": 946000 }, { "epoch": 2.79, "learning_rate": 1.3707177978496655e-06, "loss": 0.964, "step": 947000 }, { "epoch": 2.8, "learning_rate": 1.351045905344755e-06, "loss": 0.9646, "step": 948000 }, { "epoch": 2.8, "learning_rate": 1.3313740128398444e-06, "loss": 0.9603, "step": 949000 }, { "epoch": 2.8, "learning_rate": 1.3117021203349337e-06, "loss": 0.9776, "step": 950000 }, { "epoch": 2.81, "learning_rate": 1.2920302278300232e-06, "loss": 0.9642, "step": 951000 }, { "epoch": 2.81, "learning_rate": 1.2723583353251127e-06, "loss": 0.9515, "step": 952000 }, { "epoch": 2.81, "learning_rate": 1.2526864428202022e-06, "loss": 0.9685, "step": 953000 }, { "epoch": 2.82, "learning_rate": 1.2330145503152914e-06, "loss": 0.959, "step": 954000 }, { "epoch": 2.82, "learning_rate": 1.2133426578103807e-06, "loss": 0.9629, "step": 955000 }, { "epoch": 2.82, "learning_rate": 1.1936707653054702e-06, "loss": 0.9697, "step": 956000 }, { "epoch": 2.82, "learning_rate": 1.1739988728005595e-06, "loss": 0.977, "step": 957000 }, { "epoch": 2.83, "learning_rate": 1.154326980295649e-06, "loss": 0.9648, "step": 958000 }, { "epoch": 2.83, "learning_rate": 1.1346550877907384e-06, "loss": 0.9645, "step": 959000 }, { "epoch": 2.83, "learning_rate": 1.114983195285828e-06, "loss": 0.9651, "step": 960000 }, { "epoch": 2.84, "learning_rate": 1.0953113027809172e-06, "loss": 0.9674, "step": 961000 }, { "epoch": 2.84, "learning_rate": 1.0756394102760067e-06, "loss": 0.967, "step": 962000 }, { "epoch": 2.84, "learning_rate": 1.055967517771096e-06, "loss": 0.9553, "step": 963000 }, { "epoch": 2.84, "learning_rate": 1.0362956252661854e-06, "loss": 0.955, "step": 964000 }, { "epoch": 2.85, "learning_rate": 1.0166237327612747e-06, "loss": 0.9718, "step": 965000 }, { "epoch": 2.85, "learning_rate": 9.969518402563642e-07, "loss": 0.9692, "step": 966000 }, { "epoch": 2.85, "learning_rate": 9.772799477514535e-07, "loss": 0.9777, "step": 967000 }, { "epoch": 2.86, "learning_rate": 9.57608055246543e-07, "loss": 0.9596, "step": 968000 }, { "epoch": 2.86, "learning_rate": 9.379361627416323e-07, "loss": 0.9624, "step": 969000 }, { "epoch": 2.86, "learning_rate": 9.182642702367218e-07, "loss": 0.9514, "step": 970000 }, { "epoch": 2.87, "learning_rate": 8.985923777318112e-07, "loss": 0.9496, "step": 971000 }, { "epoch": 2.87, "learning_rate": 8.789204852269007e-07, "loss": 0.9758, "step": 972000 }, { "epoch": 2.87, "learning_rate": 8.5924859272199e-07, "loss": 0.9571, "step": 973000 }, { "epoch": 2.87, "learning_rate": 8.395767002170795e-07, "loss": 0.9558, "step": 974000 }, { "epoch": 2.88, "learning_rate": 8.199048077121688e-07, "loss": 0.9564, "step": 975000 }, { "epoch": 2.88, "learning_rate": 8.002329152072582e-07, "loss": 0.9574, "step": 976000 }, { "epoch": 2.88, "learning_rate": 7.805610227023476e-07, "loss": 0.9571, "step": 977000 }, { "epoch": 2.89, "learning_rate": 7.608891301974371e-07, "loss": 0.9659, "step": 978000 }, { "epoch": 2.89, "learning_rate": 7.412172376925264e-07, "loss": 0.9649, "step": 979000 }, { "epoch": 2.89, "learning_rate": 7.215453451876158e-07, "loss": 0.9662, "step": 980000 }, { "epoch": 2.89, "learning_rate": 7.018734526827052e-07, "loss": 0.9666, "step": 981000 }, { "epoch": 2.9, "learning_rate": 6.822015601777947e-07, "loss": 0.9694, "step": 982000 }, { "epoch": 2.9, "learning_rate": 6.62529667672884e-07, "loss": 0.9589, "step": 983000 }, { "epoch": 2.9, "learning_rate": 6.428577751679735e-07, "loss": 0.9613, "step": 984000 }, { "epoch": 2.91, "learning_rate": 6.231858826630628e-07, "loss": 0.9563, "step": 985000 }, { "epoch": 2.91, "learning_rate": 6.035139901581522e-07, "loss": 0.9708, "step": 986000 }, { "epoch": 2.91, "learning_rate": 5.838420976532416e-07, "loss": 0.9597, "step": 987000 }, { "epoch": 2.92, "learning_rate": 5.64170205148331e-07, "loss": 0.9544, "step": 988000 }, { "epoch": 2.92, "learning_rate": 5.444983126434205e-07, "loss": 0.9688, "step": 989000 }, { "epoch": 2.92, "learning_rate": 5.248264201385099e-07, "loss": 0.9742, "step": 990000 }, { "epoch": 2.92, "learning_rate": 5.051545276335992e-07, "loss": 0.9757, "step": 991000 }, { "epoch": 2.93, "learning_rate": 4.854826351286886e-07, "loss": 0.954, "step": 992000 }, { "epoch": 2.93, "learning_rate": 4.6581074262377804e-07, "loss": 0.9553, "step": 993000 }, { "epoch": 2.93, "learning_rate": 4.461388501188674e-07, "loss": 0.9491, "step": 994000 }, { "epoch": 2.94, "learning_rate": 4.2646695761395686e-07, "loss": 0.9695, "step": 995000 }, { "epoch": 2.94, "learning_rate": 4.0679506510904624e-07, "loss": 0.9665, "step": 996000 }, { "epoch": 2.94, "learning_rate": 3.8712317260413567e-07, "loss": 0.9613, "step": 997000 }, { "epoch": 2.94, "learning_rate": 3.6745128009922505e-07, "loss": 0.9606, "step": 998000 }, { "epoch": 2.95, "learning_rate": 3.477793875943145e-07, "loss": 0.9576, "step": 999000 }, { "epoch": 2.95, "learning_rate": 3.2810749508940386e-07, "loss": 0.9601, "step": 1000000 }, { "epoch": 2.95, "learning_rate": 3.0843560258449324e-07, "loss": 0.9631, "step": 1001000 }, { "epoch": 2.96, "learning_rate": 2.887637100795827e-07, "loss": 0.9613, "step": 1002000 }, { "epoch": 2.96, "learning_rate": 2.6909181757467205e-07, "loss": 0.9718, "step": 1003000 }, { "epoch": 2.96, "learning_rate": 2.494199250697615e-07, "loss": 0.9598, "step": 1004000 }, { "epoch": 2.97, "learning_rate": 2.2974803256485087e-07, "loss": 0.9636, "step": 1005000 }, { "epoch": 2.97, "learning_rate": 2.1007614005994027e-07, "loss": 0.9758, "step": 1006000 }, { "epoch": 2.97, "learning_rate": 1.9040424755502968e-07, "loss": 0.9643, "step": 1007000 }, { "epoch": 2.97, "learning_rate": 1.7073235505011909e-07, "loss": 0.9696, "step": 1008000 }, { "epoch": 2.98, "learning_rate": 1.510604625452085e-07, "loss": 0.9657, "step": 1009000 }, { "epoch": 2.98, "learning_rate": 1.3138857004029787e-07, "loss": 0.9624, "step": 1010000 }, { "epoch": 2.98, "learning_rate": 1.1171667753538729e-07, "loss": 0.9713, "step": 1011000 }, { "epoch": 2.99, "learning_rate": 9.204478503047668e-08, "loss": 0.9612, "step": 1012000 }, { "epoch": 2.99, "learning_rate": 7.237289252556609e-08, "loss": 0.9572, "step": 1013000 }, { "epoch": 2.99, "learning_rate": 5.270100002065549e-08, "loss": 0.9683, "step": 1014000 }, { "epoch": 3.0, "learning_rate": 3.302910751574489e-08, "loss": 0.9478, "step": 1015000 }, { "epoch": 3.0, "learning_rate": 1.3357215010834297e-08, "loss": 0.9568, "step": 1016000 }, { "epoch": 3.0, "eval_bleu": 41.8841, "eval_gen_len": 17.4785, "eval_loss": 1.0647151470184326, "eval_runtime": 964.3683, "eval_samples_per_second": 56.795, "eval_steps_per_second": 3.551, "step": 1016679 } ], "logging_steps": 1000, "max_steps": 1016679, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "total_flos": 7.29662426786562e+17, "train_batch_size": 16, "trial_name": null, "trial_params": null }