|
[ |
|
{ |
|
"current_steps": 1, |
|
"loss": 2.243, |
|
"learning_rate": 0.0, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 3, |
|
"loss": 2.4906, |
|
"learning_rate": 0.0, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 5, |
|
"loss": 2.4031, |
|
"learning_rate": 0.0, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 7, |
|
"loss": 2.0465, |
|
"learning_rate": 4.9999999999999996e-06, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 9, |
|
"loss": 2.1139, |
|
"learning_rate": 4.9999999999999996e-06, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 11, |
|
"loss": 2.3079, |
|
"learning_rate": 9.999999999999999e-06, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 13, |
|
"loss": 2.4454, |
|
"learning_rate": 9.999999999999999e-06, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 15, |
|
"loss": 2.1482, |
|
"learning_rate": 1.4999999999999999e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 17, |
|
"loss": 2.2773, |
|
"learning_rate": 1.9999999999999998e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 19, |
|
"loss": 2.1211, |
|
"learning_rate": 1.9999999999999998e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 21, |
|
"loss": 2.4949, |
|
"learning_rate": 2.4999999999999998e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 23, |
|
"loss": 1.9488, |
|
"learning_rate": 2.9999999999999997e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 25, |
|
"loss": 2.0129, |
|
"learning_rate": 3.5e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 27, |
|
"loss": 2.3205, |
|
"learning_rate": 3.9999999999999996e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 29, |
|
"loss": 1.7864, |
|
"learning_rate": 4.4999999999999996e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 31, |
|
"loss": 2.161, |
|
"learning_rate": 4.9999999999999996e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 33, |
|
"loss": 2.0796, |
|
"learning_rate": 5.499999999999999e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 35, |
|
"loss": 2.0092, |
|
"learning_rate": 5.9999999999999995e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 37, |
|
"loss": 1.9249, |
|
"learning_rate": 6.5e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 39, |
|
"loss": 2.0162, |
|
"learning_rate": 7e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 41, |
|
"loss": 1.9155, |
|
"learning_rate": 7.5e-05, |
|
"epoch": 0.0 |
|
}, |
|
{ |
|
"current_steps": 43, |
|
"loss": 1.9234, |
|
"learning_rate": 7.999999999999999e-05, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 45, |
|
"loss": 1.8821, |
|
"learning_rate": 8.499999999999999e-05, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 47, |
|
"loss": 1.8072, |
|
"learning_rate": 8.999999999999999e-05, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 49, |
|
"loss": 1.9472, |
|
"learning_rate": 9.499999999999999e-05, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 51, |
|
"loss": 1.8368, |
|
"learning_rate": 9.999999999999999e-05, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 53, |
|
"loss": 1.6759, |
|
"learning_rate": 0.00010499999999999999, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 55, |
|
"loss": 1.9959, |
|
"learning_rate": 0.00010999999999999998, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 57, |
|
"loss": 1.7571, |
|
"learning_rate": 0.000115, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 59, |
|
"loss": 1.6964, |
|
"learning_rate": 0.00011999999999999999, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 61, |
|
"loss": 1.7602, |
|
"learning_rate": 0.000125, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 63, |
|
"loss": 1.6103, |
|
"learning_rate": 0.00013, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 65, |
|
"loss": 1.73, |
|
"learning_rate": 0.000135, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 67, |
|
"loss": 1.6363, |
|
"learning_rate": 0.00014, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 69, |
|
"loss": 1.6342, |
|
"learning_rate": 0.000145, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 71, |
|
"loss": 1.6227, |
|
"learning_rate": 0.00015, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 73, |
|
"loss": 1.7408, |
|
"learning_rate": 0.000155, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 75, |
|
"loss": 1.6787, |
|
"learning_rate": 0.00015999999999999999, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 77, |
|
"loss": 1.998, |
|
"learning_rate": 0.000165, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 79, |
|
"loss": 1.5218, |
|
"learning_rate": 0.00016999999999999999, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 81, |
|
"loss": 1.648, |
|
"learning_rate": 0.000175, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 83, |
|
"loss": 1.8393, |
|
"learning_rate": 0.00017999999999999998, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 85, |
|
"loss": 1.5411, |
|
"learning_rate": 0.000185, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 87, |
|
"loss": 1.5455, |
|
"learning_rate": 0.00018999999999999998, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 89, |
|
"loss": 1.8884, |
|
"learning_rate": 0.000195, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 91, |
|
"loss": 1.7582, |
|
"learning_rate": 0.00019999999999999998, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 93, |
|
"loss": 1.6639, |
|
"learning_rate": 0.000205, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 95, |
|
"loss": 1.5912, |
|
"learning_rate": 0.00020999999999999998, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 97, |
|
"loss": 1.8708, |
|
"learning_rate": 0.000215, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 99, |
|
"loss": 1.776, |
|
"learning_rate": 0.00021999999999999995, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 101, |
|
"loss": 1.726, |
|
"learning_rate": 0.000225, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 103, |
|
"loss": 1.7652, |
|
"learning_rate": 0.00023, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 105, |
|
"loss": 1.655, |
|
"learning_rate": 0.00023499999999999997, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 107, |
|
"loss": 1.552, |
|
"learning_rate": 0.00023999999999999998, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 109, |
|
"loss": 1.8468, |
|
"learning_rate": 0.000245, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 111, |
|
"loss": 1.7365, |
|
"learning_rate": 0.00025, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 113, |
|
"loss": 1.8068, |
|
"learning_rate": 0.00025499999999999996, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 115, |
|
"loss": 1.6334, |
|
"learning_rate": 0.00026, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 117, |
|
"loss": 1.7037, |
|
"learning_rate": 0.000265, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 119, |
|
"loss": 1.7575, |
|
"learning_rate": 0.00027, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 121, |
|
"loss": 1.5549, |
|
"learning_rate": 0.00027499999999999996, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 123, |
|
"loss": 1.7386, |
|
"learning_rate": 0.00028, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 125, |
|
"loss": 1.4847, |
|
"learning_rate": 0.000285, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 127, |
|
"loss": 1.912, |
|
"learning_rate": 0.00029, |
|
"epoch": 0.01 |
|
}, |
|
{ |
|
"current_steps": 129, |
|
"loss": 1.4259, |
|
"learning_rate": 0.00029499999999999996, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 131, |
|
"loss": 1.7833, |
|
"learning_rate": 0.0003, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 133, |
|
"loss": 1.6208, |
|
"learning_rate": 0.00029970443349753694, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 135, |
|
"loss": 1.7041, |
|
"learning_rate": 0.00029940886699507385, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 137, |
|
"loss": 1.6153, |
|
"learning_rate": 0.0002991133004926108, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 139, |
|
"loss": 1.716, |
|
"learning_rate": 0.00029881773399014774, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 141, |
|
"loss": 1.5853, |
|
"learning_rate": 0.0002985221674876847, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 143, |
|
"loss": 1.728, |
|
"learning_rate": 0.00029822660098522167, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 145, |
|
"loss": 1.9886, |
|
"learning_rate": 0.0002979310344827586, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 147, |
|
"loss": 1.7207, |
|
"learning_rate": 0.00029763546798029555, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 149, |
|
"loss": 1.6006, |
|
"learning_rate": 0.00029733990147783247, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 151, |
|
"loss": 1.3388, |
|
"learning_rate": 0.00029704433497536943, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 153, |
|
"loss": 1.5003, |
|
"learning_rate": 0.00029674876847290635, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 155, |
|
"loss": 1.479, |
|
"learning_rate": 0.0002964532019704433, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 157, |
|
"loss": 1.58, |
|
"learning_rate": 0.0002961576354679803, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 159, |
|
"loss": 1.8409, |
|
"learning_rate": 0.0002958620689655172, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 161, |
|
"loss": 1.6689, |
|
"learning_rate": 0.00029556650246305416, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 163, |
|
"loss": 1.5511, |
|
"learning_rate": 0.0002952709359605911, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 165, |
|
"loss": 1.6765, |
|
"learning_rate": 0.00029497536945812805, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 167, |
|
"loss": 1.8226, |
|
"learning_rate": 0.000294679802955665, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 169, |
|
"loss": 1.7741, |
|
"learning_rate": 0.0002943842364532019, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 171, |
|
"loss": 1.59, |
|
"learning_rate": 0.0002940886699507389, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 173, |
|
"loss": 1.6031, |
|
"learning_rate": 0.0002937931034482758, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 175, |
|
"loss": 1.568, |
|
"learning_rate": 0.0002934975369458128, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 177, |
|
"loss": 1.2813, |
|
"learning_rate": 0.00029320197044334974, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 179, |
|
"loss": 1.6867, |
|
"learning_rate": 0.00029290640394088666, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 181, |
|
"loss": 1.7537, |
|
"learning_rate": 0.0002926108374384236, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 183, |
|
"loss": 1.6056, |
|
"learning_rate": 0.00029231527093596054, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 185, |
|
"loss": 1.6866, |
|
"learning_rate": 0.0002920197044334975, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 187, |
|
"loss": 1.7206, |
|
"learning_rate": 0.0002917241379310344, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 189, |
|
"loss": 1.6578, |
|
"learning_rate": 0.0002914285714285714, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 191, |
|
"loss": 1.5329, |
|
"learning_rate": 0.00029113300492610836, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 193, |
|
"loss": 1.6231, |
|
"learning_rate": 0.00029083743842364527, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 195, |
|
"loss": 1.4756, |
|
"learning_rate": 0.00029054187192118224, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 197, |
|
"loss": 1.4725, |
|
"learning_rate": 0.00029024630541871915, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 199, |
|
"loss": 1.7892, |
|
"learning_rate": 0.0002899507389162561, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 201, |
|
"loss": 1.7455, |
|
"learning_rate": 0.0002896551724137931, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 203, |
|
"loss": 1.6733, |
|
"learning_rate": 0.00028935960591133, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 205, |
|
"loss": 1.4954, |
|
"learning_rate": 0.00028906403940886697, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 207, |
|
"loss": 1.6448, |
|
"learning_rate": 0.0002887684729064039, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 209, |
|
"loss": 1.7882, |
|
"learning_rate": 0.00028847290640394085, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 211, |
|
"loss": 1.7796, |
|
"learning_rate": 0.0002881773399014778, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 213, |
|
"loss": 1.6399, |
|
"learning_rate": 0.00028788177339901473, |
|
"epoch": 0.02 |
|
}, |
|
{ |
|
"current_steps": 215, |
|
"loss": 1.6645, |
|
"learning_rate": 0.0002875862068965517, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 217, |
|
"loss": 1.7824, |
|
"learning_rate": 0.0002872906403940886, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 219, |
|
"loss": 1.5053, |
|
"learning_rate": 0.0002869950738916256, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 221, |
|
"loss": 1.5483, |
|
"learning_rate": 0.00028669950738916255, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 223, |
|
"loss": 1.5874, |
|
"learning_rate": 0.00028640394088669946, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 225, |
|
"loss": 1.6807, |
|
"learning_rate": 0.00028610837438423643, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 227, |
|
"loss": 1.502, |
|
"learning_rate": 0.00028581280788177334, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 229, |
|
"loss": 1.6234, |
|
"learning_rate": 0.0002855172413793103, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 231, |
|
"loss": 1.8706, |
|
"learning_rate": 0.0002852216748768473, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 233, |
|
"loss": 1.456, |
|
"learning_rate": 0.0002849261083743842, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 235, |
|
"loss": 1.4441, |
|
"learning_rate": 0.00028463054187192116, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 237, |
|
"loss": 1.7222, |
|
"learning_rate": 0.00028433497536945807, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 239, |
|
"loss": 1.6667, |
|
"learning_rate": 0.00028403940886699504, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 241, |
|
"loss": 1.6506, |
|
"learning_rate": 0.000283743842364532, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 243, |
|
"loss": 1.4267, |
|
"learning_rate": 0.0002834482758620689, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 245, |
|
"loss": 1.6695, |
|
"learning_rate": 0.0002831527093596059, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 247, |
|
"loss": 1.6691, |
|
"learning_rate": 0.0002828571428571428, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 249, |
|
"loss": 1.5338, |
|
"learning_rate": 0.00028256157635467977, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 251, |
|
"loss": 1.6988, |
|
"learning_rate": 0.00028226600985221674, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 253, |
|
"loss": 1.4844, |
|
"learning_rate": 0.00028197044334975365, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 255, |
|
"loss": 1.7708, |
|
"learning_rate": 0.0002816748768472906, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 257, |
|
"loss": 1.6342, |
|
"learning_rate": 0.00028137931034482753, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 259, |
|
"loss": 1.4992, |
|
"learning_rate": 0.0002810837438423645, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 261, |
|
"loss": 1.5933, |
|
"learning_rate": 0.00028078817733990147, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 263, |
|
"loss": 1.5269, |
|
"learning_rate": 0.0002804926108374384, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 265, |
|
"loss": 1.7497, |
|
"learning_rate": 0.00028019704433497535, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 267, |
|
"loss": 1.3407, |
|
"learning_rate": 0.00027990147783251226, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 269, |
|
"loss": 1.611, |
|
"learning_rate": 0.00027960591133004923, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 271, |
|
"loss": 1.5756, |
|
"learning_rate": 0.0002793103448275862, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 273, |
|
"loss": 1.566, |
|
"learning_rate": 0.0002790147783251231, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 275, |
|
"loss": 1.5732, |
|
"learning_rate": 0.0002787192118226601, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 277, |
|
"loss": 1.5015, |
|
"learning_rate": 0.00027842364532019705, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 279, |
|
"loss": 1.5882, |
|
"learning_rate": 0.00027812807881773396, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 281, |
|
"loss": 1.7877, |
|
"learning_rate": 0.00027783251231527093, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 283, |
|
"loss": 1.4578, |
|
"learning_rate": 0.00027753694581280784, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 285, |
|
"loss": 1.4568, |
|
"learning_rate": 0.0002772413793103448, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 287, |
|
"loss": 1.4897, |
|
"learning_rate": 0.0002769458128078818, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 289, |
|
"loss": 1.642, |
|
"learning_rate": 0.0002766502463054187, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 291, |
|
"loss": 1.5697, |
|
"learning_rate": 0.00027635467980295566, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 293, |
|
"loss": 1.4063, |
|
"learning_rate": 0.00027605911330049257, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 295, |
|
"loss": 1.5415, |
|
"learning_rate": 0.00027576354679802954, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 297, |
|
"loss": 1.497, |
|
"learning_rate": 0.0002754679802955665, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 299, |
|
"loss": 1.561, |
|
"learning_rate": 0.0002751724137931034, |
|
"epoch": 0.03 |
|
}, |
|
{ |
|
"current_steps": 301, |
|
"loss": 1.5017, |
|
"learning_rate": 0.0002748768472906404, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 303, |
|
"loss": 1.478, |
|
"learning_rate": 0.0002745812807881773, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 305, |
|
"loss": 1.4427, |
|
"learning_rate": 0.00027428571428571427, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 307, |
|
"loss": 1.6162, |
|
"learning_rate": 0.00027399014778325124, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 309, |
|
"loss": 1.5174, |
|
"learning_rate": 0.00027369458128078815, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 311, |
|
"loss": 1.6452, |
|
"learning_rate": 0.0002733990147783251, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 313, |
|
"loss": 1.6152, |
|
"learning_rate": 0.00027310344827586203, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 315, |
|
"loss": 1.5749, |
|
"learning_rate": 0.000272807881773399, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 317, |
|
"loss": 1.6, |
|
"learning_rate": 0.00027251231527093597, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 319, |
|
"loss": 1.4854, |
|
"learning_rate": 0.0002722167487684729, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 321, |
|
"loss": 1.5066, |
|
"learning_rate": 0.00027192118226600985, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 323, |
|
"loss": 1.6054, |
|
"learning_rate": 0.00027162561576354676, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 325, |
|
"loss": 1.5749, |
|
"learning_rate": 0.00027133004926108373, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 327, |
|
"loss": 1.6021, |
|
"learning_rate": 0.0002710344827586207, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 329, |
|
"loss": 1.4024, |
|
"learning_rate": 0.0002707389162561576, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 331, |
|
"loss": 1.6317, |
|
"learning_rate": 0.0002704433497536946, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 333, |
|
"loss": 1.4919, |
|
"learning_rate": 0.00027014778325123155, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 335, |
|
"loss": 1.4037, |
|
"learning_rate": 0.00026985221674876846, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 337, |
|
"loss": 1.5371, |
|
"learning_rate": 0.00026955665024630543, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 339, |
|
"loss": 1.5984, |
|
"learning_rate": 0.00026926108374384234, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 341, |
|
"loss": 1.5313, |
|
"learning_rate": 0.0002689655172413793, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 343, |
|
"loss": 1.586, |
|
"learning_rate": 0.0002686699507389162, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 345, |
|
"loss": 1.5473, |
|
"learning_rate": 0.0002683743842364532, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 347, |
|
"loss": 1.6482, |
|
"learning_rate": 0.00026807881773399016, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 349, |
|
"loss": 1.5501, |
|
"learning_rate": 0.00026778325123152707, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 351, |
|
"loss": 1.8194, |
|
"learning_rate": 0.00026748768472906404, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 353, |
|
"loss": 1.4082, |
|
"learning_rate": 0.00026719211822660095, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 355, |
|
"loss": 1.7386, |
|
"learning_rate": 0.0002668965517241379, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 357, |
|
"loss": 1.591, |
|
"learning_rate": 0.0002666009852216749, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 359, |
|
"loss": 1.6685, |
|
"learning_rate": 0.0002663054187192118, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 361, |
|
"loss": 1.7065, |
|
"learning_rate": 0.00026600985221674877, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 363, |
|
"loss": 1.6918, |
|
"learning_rate": 0.0002657142857142857, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 365, |
|
"loss": 1.5165, |
|
"learning_rate": 0.00026541871921182265, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 367, |
|
"loss": 1.535, |
|
"learning_rate": 0.0002651231527093596, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 369, |
|
"loss": 1.6364, |
|
"learning_rate": 0.00026482758620689653, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 371, |
|
"loss": 1.4763, |
|
"learning_rate": 0.0002645320197044335, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 373, |
|
"loss": 1.4425, |
|
"learning_rate": 0.0002642364532019704, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 375, |
|
"loss": 1.3717, |
|
"learning_rate": 0.0002639408866995074, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 377, |
|
"loss": 1.4793, |
|
"learning_rate": 0.0002636453201970443, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 379, |
|
"loss": 1.7218, |
|
"learning_rate": 0.00026334975369458126, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 381, |
|
"loss": 1.4009, |
|
"learning_rate": 0.00026305418719211823, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 383, |
|
"loss": 1.7674, |
|
"learning_rate": 0.00026275862068965514, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 385, |
|
"loss": 1.5999, |
|
"learning_rate": 0.0002624630541871921, |
|
"epoch": 0.04 |
|
}, |
|
{ |
|
"current_steps": 387, |
|
"loss": 1.5977, |
|
"learning_rate": 0.000262167487684729, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 389, |
|
"loss": 1.5001, |
|
"learning_rate": 0.000261871921182266, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 391, |
|
"loss": 1.6639, |
|
"learning_rate": 0.00026157635467980296, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 393, |
|
"loss": 1.578, |
|
"learning_rate": 0.0002612807881773399, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 395, |
|
"loss": 1.7178, |
|
"learning_rate": 0.00026098522167487684, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 397, |
|
"loss": 1.6051, |
|
"learning_rate": 0.00026068965517241376, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 399, |
|
"loss": 1.7263, |
|
"learning_rate": 0.0002603940886699507, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 401, |
|
"loss": 1.4514, |
|
"learning_rate": 0.0002600985221674877, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 403, |
|
"loss": 1.5681, |
|
"learning_rate": 0.0002598029556650246, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 405, |
|
"loss": 1.3968, |
|
"learning_rate": 0.00025950738916256157, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 407, |
|
"loss": 1.5056, |
|
"learning_rate": 0.0002592118226600985, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 409, |
|
"loss": 1.4911, |
|
"learning_rate": 0.00025891625615763545, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 411, |
|
"loss": 1.1793, |
|
"learning_rate": 0.00025862068965517237, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 413, |
|
"loss": 1.6403, |
|
"learning_rate": 0.00025832512315270933, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 415, |
|
"loss": 1.4649, |
|
"learning_rate": 0.0002580295566502463, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 417, |
|
"loss": 1.4229, |
|
"learning_rate": 0.0002577339901477832, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 419, |
|
"loss": 1.5858, |
|
"learning_rate": 0.0002574384236453202, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 421, |
|
"loss": 1.5472, |
|
"learning_rate": 0.0002571428571428571, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 423, |
|
"loss": 1.521, |
|
"learning_rate": 0.00025684729064039406, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 425, |
|
"loss": 1.3612, |
|
"learning_rate": 0.00025655172413793103, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 427, |
|
"loss": 1.6238, |
|
"learning_rate": 0.00025625615763546795, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 429, |
|
"loss": 1.8308, |
|
"learning_rate": 0.0002559605911330049, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 431, |
|
"loss": 1.3374, |
|
"learning_rate": 0.00025566502463054183, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 433, |
|
"loss": 1.4902, |
|
"learning_rate": 0.0002553694581280788, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 435, |
|
"loss": 1.5373, |
|
"learning_rate": 0.00025507389162561576, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 437, |
|
"loss": 1.5823, |
|
"learning_rate": 0.0002547783251231527, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 439, |
|
"loss": 1.4721, |
|
"learning_rate": 0.00025448275862068964, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 441, |
|
"loss": 1.5371, |
|
"learning_rate": 0.00025418719211822656, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 443, |
|
"loss": 1.6405, |
|
"learning_rate": 0.0002538916256157635, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 445, |
|
"loss": 1.4804, |
|
"learning_rate": 0.00025359605911330044, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 447, |
|
"loss": 1.3803, |
|
"learning_rate": 0.0002533004926108374, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 449, |
|
"loss": 1.5504, |
|
"learning_rate": 0.0002530049261083744, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 451, |
|
"loss": 1.5377, |
|
"learning_rate": 0.0002527093596059113, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 453, |
|
"loss": 1.5253, |
|
"learning_rate": 0.00025241379310344826, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 455, |
|
"loss": 1.4337, |
|
"learning_rate": 0.00025211822660098517, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 457, |
|
"loss": 1.4687, |
|
"learning_rate": 0.00025182266009852214, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 459, |
|
"loss": 1.6957, |
|
"learning_rate": 0.0002515270935960591, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 461, |
|
"loss": 1.4894, |
|
"learning_rate": 0.000251231527093596, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 463, |
|
"loss": 1.5078, |
|
"learning_rate": 0.000250935960591133, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 465, |
|
"loss": 1.5807, |
|
"learning_rate": 0.0002506403940886699, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 467, |
|
"loss": 1.5709, |
|
"learning_rate": 0.00025034482758620687, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 469, |
|
"loss": 1.6079, |
|
"learning_rate": 0.00025004926108374383, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 471, |
|
"loss": 1.6427, |
|
"learning_rate": 0.00024975369458128075, |
|
"epoch": 0.05 |
|
}, |
|
{ |
|
"current_steps": 473, |
|
"loss": 1.3753, |
|
"learning_rate": 0.0002494581280788177, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 475, |
|
"loss": 1.6384, |
|
"learning_rate": 0.00024916256157635463, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 477, |
|
"loss": 1.5394, |
|
"learning_rate": 0.0002488669950738916, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 479, |
|
"loss": 1.4127, |
|
"learning_rate": 0.00024857142857142857, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 481, |
|
"loss": 1.5786, |
|
"learning_rate": 0.0002482758620689655, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 483, |
|
"loss": 1.4848, |
|
"learning_rate": 0.00024798029556650245, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 485, |
|
"loss": 1.4502, |
|
"learning_rate": 0.00024768472906403936, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 487, |
|
"loss": 1.6508, |
|
"learning_rate": 0.00024738916256157633, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 489, |
|
"loss": 1.5376, |
|
"learning_rate": 0.00024709359605911324, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 491, |
|
"loss": 1.5825, |
|
"learning_rate": 0.0002467980295566502, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 493, |
|
"loss": 1.6356, |
|
"learning_rate": 0.0002465024630541872, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 495, |
|
"loss": 1.5132, |
|
"learning_rate": 0.0002462068965517241, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 497, |
|
"loss": 1.6001, |
|
"learning_rate": 0.00024591133004926106, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 499, |
|
"loss": 1.4645, |
|
"learning_rate": 0.00024561576354679797, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 501, |
|
"loss": 1.592, |
|
"learning_rate": 0.00024532019704433494, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 503, |
|
"loss": 1.4911, |
|
"learning_rate": 0.0002450246305418719, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 505, |
|
"loss": 1.6054, |
|
"learning_rate": 0.0002447290640394088, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 507, |
|
"loss": 1.6558, |
|
"learning_rate": 0.0002444334975369458, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 509, |
|
"loss": 1.4264, |
|
"learning_rate": 0.00024413793103448273, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 511, |
|
"loss": 1.7094, |
|
"learning_rate": 0.0002438423645320197, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 513, |
|
"loss": 1.4223, |
|
"learning_rate": 0.00024354679802955664, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 515, |
|
"loss": 1.3422, |
|
"learning_rate": 0.00024325123152709358, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 517, |
|
"loss": 1.6417, |
|
"learning_rate": 0.00024295566502463052, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 519, |
|
"loss": 1.4039, |
|
"learning_rate": 0.00024266009852216746, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 521, |
|
"loss": 1.4574, |
|
"learning_rate": 0.00024236453201970443, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 523, |
|
"loss": 1.4048, |
|
"learning_rate": 0.00024206896551724134, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 525, |
|
"loss": 1.5909, |
|
"learning_rate": 0.0002417733990147783, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 527, |
|
"loss": 1.3579, |
|
"learning_rate": 0.00024147783251231525, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 529, |
|
"loss": 1.4976, |
|
"learning_rate": 0.0002411822660098522, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 531, |
|
"loss": 1.5886, |
|
"learning_rate": 0.00024088669950738916, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 533, |
|
"loss": 1.6522, |
|
"learning_rate": 0.00024059113300492607, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 535, |
|
"loss": 1.4365, |
|
"learning_rate": 0.00024029556650246304, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 537, |
|
"loss": 1.5958, |
|
"learning_rate": 0.00023999999999999998, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 539, |
|
"loss": 1.5983, |
|
"learning_rate": 0.00023970443349753692, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 541, |
|
"loss": 1.5317, |
|
"learning_rate": 0.0002394088669950739, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 543, |
|
"loss": 1.6437, |
|
"learning_rate": 0.0002391133004926108, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 545, |
|
"loss": 1.3556, |
|
"learning_rate": 0.00023881773399014777, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 547, |
|
"loss": 1.3637, |
|
"learning_rate": 0.00023852216748768474, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 549, |
|
"loss": 1.3729, |
|
"learning_rate": 0.00023822660098522165, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 551, |
|
"loss": 1.656, |
|
"learning_rate": 0.00023793103448275862, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 553, |
|
"loss": 1.5467, |
|
"learning_rate": 0.00023763546798029553, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 555, |
|
"loss": 1.4409, |
|
"learning_rate": 0.0002373399014778325, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 557, |
|
"loss": 1.4597, |
|
"learning_rate": 0.0002370443349753694, |
|
"epoch": 0.06 |
|
}, |
|
{ |
|
"current_steps": 559, |
|
"loss": 1.4803, |
|
"learning_rate": 0.00023674876847290638, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 561, |
|
"loss": 1.4419, |
|
"learning_rate": 0.00023645320197044335, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 563, |
|
"loss": 1.5701, |
|
"learning_rate": 0.00023615763546798026, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 565, |
|
"loss": 1.543, |
|
"learning_rate": 0.00023586206896551723, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 567, |
|
"loss": 1.625, |
|
"learning_rate": 0.00023556650246305414, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 569, |
|
"loss": 1.7143, |
|
"learning_rate": 0.0002352709359605911, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 571, |
|
"loss": 1.4128, |
|
"learning_rate": 0.00023497536945812808, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 573, |
|
"loss": 1.6889, |
|
"learning_rate": 0.000234679802955665, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 575, |
|
"loss": 1.5572, |
|
"learning_rate": 0.00023438423645320196, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 577, |
|
"loss": 1.3485, |
|
"learning_rate": 0.00023408866995073887, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 579, |
|
"loss": 1.6611, |
|
"learning_rate": 0.00023379310344827584, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 581, |
|
"loss": 1.503, |
|
"learning_rate": 0.0002334975369458128, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 583, |
|
"loss": 1.4661, |
|
"learning_rate": 0.00023320197044334972, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 585, |
|
"loss": 1.4585, |
|
"learning_rate": 0.0002329064039408867, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 587, |
|
"loss": 1.5381, |
|
"learning_rate": 0.0002326108374384236, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 589, |
|
"loss": 1.5061, |
|
"learning_rate": 0.00023231527093596057, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 591, |
|
"loss": 1.5201, |
|
"learning_rate": 0.00023201970443349754, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 593, |
|
"loss": 1.5733, |
|
"learning_rate": 0.00023172413793103445, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 595, |
|
"loss": 1.4034, |
|
"learning_rate": 0.00023142857142857142, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 597, |
|
"loss": 1.6211, |
|
"learning_rate": 0.00023113300492610833, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 599, |
|
"loss": 1.6118, |
|
"learning_rate": 0.0002308374384236453, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 601, |
|
"loss": 1.5431, |
|
"learning_rate": 0.00023054187192118224, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 603, |
|
"loss": 1.6332, |
|
"learning_rate": 0.00023024630541871918, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 605, |
|
"loss": 1.4212, |
|
"learning_rate": 0.00022995073891625615, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 607, |
|
"loss": 1.5234, |
|
"learning_rate": 0.00022965517241379306, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 609, |
|
"loss": 1.7482, |
|
"learning_rate": 0.00022935960591133003, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 611, |
|
"loss": 1.483, |
|
"learning_rate": 0.00022906403940886697, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 613, |
|
"loss": 1.3697, |
|
"learning_rate": 0.0002287684729064039, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 615, |
|
"loss": 1.484, |
|
"learning_rate": 0.00022847290640394088, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 617, |
|
"loss": 1.7224, |
|
"learning_rate": 0.0002281773399014778, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 619, |
|
"loss": 1.3295, |
|
"learning_rate": 0.00022788177339901476, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 621, |
|
"loss": 1.7212, |
|
"learning_rate": 0.0002275862068965517, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 623, |
|
"loss": 1.4627, |
|
"learning_rate": 0.00022729064039408864, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 625, |
|
"loss": 1.6296, |
|
"learning_rate": 0.0002269950738916256, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 627, |
|
"loss": 1.6696, |
|
"learning_rate": 0.00022669950738916255, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 629, |
|
"loss": 1.5944, |
|
"learning_rate": 0.0002264039408866995, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 631, |
|
"loss": 1.6079, |
|
"learning_rate": 0.00022610837438423643, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 633, |
|
"loss": 1.4051, |
|
"learning_rate": 0.00022581280788177337, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 635, |
|
"loss": 1.4022, |
|
"learning_rate": 0.00022551724137931031, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 637, |
|
"loss": 1.6161, |
|
"learning_rate": 0.00022522167487684728, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 639, |
|
"loss": 1.5758, |
|
"learning_rate": 0.00022492610837438422, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 641, |
|
"loss": 1.4163, |
|
"learning_rate": 0.00022463054187192116, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 643, |
|
"loss": 1.4388, |
|
"learning_rate": 0.0002243349753694581, |
|
"epoch": 0.07 |
|
}, |
|
{ |
|
"current_steps": 645, |
|
"loss": 1.5208, |
|
"learning_rate": 0.00022403940886699504, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 647, |
|
"loss": 1.6124, |
|
"learning_rate": 0.000223743842364532, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 649, |
|
"loss": 1.6304, |
|
"learning_rate": 0.00022344827586206895, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 651, |
|
"loss": 1.2748, |
|
"learning_rate": 0.0002231527093596059, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 653, |
|
"loss": 1.4693, |
|
"learning_rate": 0.00022285714285714283, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 655, |
|
"loss": 1.4548, |
|
"learning_rate": 0.00022256157635467977, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 657, |
|
"loss": 1.5686, |
|
"learning_rate": 0.00022226600985221674, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 659, |
|
"loss": 1.467, |
|
"learning_rate": 0.00022197044334975368, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 661, |
|
"loss": 1.4681, |
|
"learning_rate": 0.00022167487684729062, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 663, |
|
"loss": 1.6515, |
|
"learning_rate": 0.00022137931034482756, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 665, |
|
"loss": 1.4428, |
|
"learning_rate": 0.0002210837438423645, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 667, |
|
"loss": 1.4966, |
|
"learning_rate": 0.00022078817733990147, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 669, |
|
"loss": 1.526, |
|
"learning_rate": 0.00022049261083743839, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 671, |
|
"loss": 1.5171, |
|
"learning_rate": 0.00022019704433497535, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 673, |
|
"loss": 1.478, |
|
"learning_rate": 0.0002199014778325123, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 675, |
|
"loss": 1.3102, |
|
"learning_rate": 0.00021960591133004923, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 677, |
|
"loss": 1.4725, |
|
"learning_rate": 0.0002193103448275862, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 679, |
|
"loss": 1.6475, |
|
"learning_rate": 0.00021901477832512312, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 681, |
|
"loss": 1.4398, |
|
"learning_rate": 0.00021871921182266008, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 683, |
|
"loss": 1.4224, |
|
"learning_rate": 0.00021842364532019705, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 685, |
|
"loss": 1.4644, |
|
"learning_rate": 0.00021812807881773397, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 687, |
|
"loss": 1.4869, |
|
"learning_rate": 0.00021783251231527093, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 689, |
|
"loss": 1.5006, |
|
"learning_rate": 0.00021753694581280785, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 691, |
|
"loss": 1.385, |
|
"learning_rate": 0.00021724137931034481, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 693, |
|
"loss": 1.4807, |
|
"learning_rate": 0.00021694581280788178, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 695, |
|
"loss": 1.4785, |
|
"learning_rate": 0.0002166502463054187, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 697, |
|
"loss": 1.3646, |
|
"learning_rate": 0.00021635467980295566, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 699, |
|
"loss": 1.5786, |
|
"learning_rate": 0.00021605911330049258, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 701, |
|
"loss": 1.5026, |
|
"learning_rate": 0.00021576354679802954, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 703, |
|
"loss": 1.5796, |
|
"learning_rate": 0.0002154679802955665, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 705, |
|
"loss": 1.3805, |
|
"learning_rate": 0.00021517241379310343, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 707, |
|
"loss": 1.3003, |
|
"learning_rate": 0.0002148768472906404, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 709, |
|
"loss": 1.6073, |
|
"learning_rate": 0.0002145812807881773, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 711, |
|
"loss": 1.6322, |
|
"learning_rate": 0.00021428571428571427, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 713, |
|
"loss": 1.4224, |
|
"learning_rate": 0.0002139901477832512, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 715, |
|
"loss": 1.5127, |
|
"learning_rate": 0.00021369458128078816, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 717, |
|
"loss": 1.5959, |
|
"learning_rate": 0.00021339901477832512, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 719, |
|
"loss": 1.5482, |
|
"learning_rate": 0.00021310344827586204, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 721, |
|
"loss": 1.4671, |
|
"learning_rate": 0.000212807881773399, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 723, |
|
"loss": 1.3553, |
|
"learning_rate": 0.00021251231527093592, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 725, |
|
"loss": 1.3771, |
|
"learning_rate": 0.00021221674876847289, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 727, |
|
"loss": 1.3838, |
|
"learning_rate": 0.00021192118226600985, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 729, |
|
"loss": 1.5396, |
|
"learning_rate": 0.00021162561576354677, |
|
"epoch": 0.08 |
|
}, |
|
{ |
|
"current_steps": 731, |
|
"loss": 1.4486, |
|
"learning_rate": 0.00021133004926108374, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 733, |
|
"loss": 1.7393, |
|
"learning_rate": 0.00021103448275862065, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 735, |
|
"loss": 1.6453, |
|
"learning_rate": 0.00021073891625615762, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 737, |
|
"loss": 1.531, |
|
"learning_rate": 0.00021044334975369458, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 739, |
|
"loss": 1.4001, |
|
"learning_rate": 0.0002101477832512315, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 741, |
|
"loss": 1.715, |
|
"learning_rate": 0.00020985221674876847, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 743, |
|
"loss": 1.5752, |
|
"learning_rate": 0.00020955665024630538, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 745, |
|
"loss": 1.6571, |
|
"learning_rate": 0.00020926108374384235, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 747, |
|
"loss": 1.3944, |
|
"learning_rate": 0.0002089655172413793, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 749, |
|
"loss": 1.4435, |
|
"learning_rate": 0.00020866995073891623, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 751, |
|
"loss": 1.5315, |
|
"learning_rate": 0.0002083743842364532, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 753, |
|
"loss": 1.5234, |
|
"learning_rate": 0.0002080788177339901, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 755, |
|
"loss": 1.3887, |
|
"learning_rate": 0.00020778325123152708, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 757, |
|
"loss": 1.7222, |
|
"learning_rate": 0.00020748768472906402, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 759, |
|
"loss": 1.3696, |
|
"learning_rate": 0.00020719211822660096, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 761, |
|
"loss": 1.7286, |
|
"learning_rate": 0.00020689655172413793, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 763, |
|
"loss": 1.4161, |
|
"learning_rate": 0.00020660098522167484, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 765, |
|
"loss": 1.3924, |
|
"learning_rate": 0.0002063054187192118, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 767, |
|
"loss": 1.5465, |
|
"learning_rate": 0.00020600985221674875, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 769, |
|
"loss": 1.4817, |
|
"learning_rate": 0.0002057142857142857, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 771, |
|
"loss": 1.3681, |
|
"learning_rate": 0.00020541871921182266, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 773, |
|
"loss": 1.4576, |
|
"learning_rate": 0.0002051231527093596, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 775, |
|
"loss": 1.6408, |
|
"learning_rate": 0.00020482758620689654, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 777, |
|
"loss": 1.3061, |
|
"learning_rate": 0.00020453201970443348, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 779, |
|
"loss": 1.3361, |
|
"learning_rate": 0.00020423645320197042, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 781, |
|
"loss": 1.6419, |
|
"learning_rate": 0.00020394088669950736, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 783, |
|
"loss": 1.5729, |
|
"learning_rate": 0.00020364532019704433, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 785, |
|
"loss": 1.4599, |
|
"learning_rate": 0.00020334975369458127, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 787, |
|
"loss": 1.6963, |
|
"learning_rate": 0.0002030541871921182, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 789, |
|
"loss": 1.34, |
|
"learning_rate": 0.00020275862068965515, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 791, |
|
"loss": 1.5912, |
|
"learning_rate": 0.0002024630541871921, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 793, |
|
"loss": 1.2494, |
|
"learning_rate": 0.00020216748768472906, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 795, |
|
"loss": 1.6001, |
|
"learning_rate": 0.000201871921182266, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 797, |
|
"loss": 1.476, |
|
"learning_rate": 0.00020157635467980294, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 799, |
|
"loss": 1.4616, |
|
"learning_rate": 0.00020128078817733988, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 801, |
|
"loss": 1.4727, |
|
"learning_rate": 0.00020098522167487682, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 803, |
|
"loss": 1.6162, |
|
"learning_rate": 0.0002006896551724138, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 805, |
|
"loss": 1.4267, |
|
"learning_rate": 0.00020039408866995073, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 807, |
|
"loss": 1.3787, |
|
"learning_rate": 0.00020009852216748767, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 809, |
|
"loss": 1.6201, |
|
"learning_rate": 0.0001998029556650246, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 811, |
|
"loss": 1.5628, |
|
"learning_rate": 0.00019950738916256155, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 813, |
|
"loss": 1.5113, |
|
"learning_rate": 0.00019921182266009852, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 815, |
|
"loss": 1.5544, |
|
"learning_rate": 0.00019891625615763543, |
|
"epoch": 0.09 |
|
}, |
|
{ |
|
"current_steps": 817, |
|
"loss": 1.4982, |
|
"learning_rate": 0.0001986206896551724, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 819, |
|
"loss": 1.4648, |
|
"learning_rate": 0.00019832512315270934, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 821, |
|
"loss": 1.3321, |
|
"learning_rate": 0.00019802955665024628, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 823, |
|
"loss": 1.3048, |
|
"learning_rate": 0.00019773399014778325, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 825, |
|
"loss": 1.4533, |
|
"learning_rate": 0.00019743842364532016, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 827, |
|
"loss": 1.6091, |
|
"learning_rate": 0.00019714285714285713, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 829, |
|
"loss": 1.5188, |
|
"learning_rate": 0.0001968472906403941, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 831, |
|
"loss": 1.612, |
|
"learning_rate": 0.000196551724137931, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 833, |
|
"loss": 1.3739, |
|
"learning_rate": 0.00019625615763546798, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 835, |
|
"loss": 1.5841, |
|
"learning_rate": 0.0001959605911330049, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 837, |
|
"loss": 1.382, |
|
"learning_rate": 0.00019566502463054186, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 839, |
|
"loss": 1.4158, |
|
"learning_rate": 0.00019536945812807883, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 841, |
|
"loss": 1.4126, |
|
"learning_rate": 0.00019507389162561574, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 843, |
|
"loss": 1.5635, |
|
"learning_rate": 0.0001947783251231527, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 845, |
|
"loss": 1.375, |
|
"learning_rate": 0.00019448275862068962, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 847, |
|
"loss": 1.6939, |
|
"learning_rate": 0.0001941871921182266, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 849, |
|
"loss": 1.6394, |
|
"learning_rate": 0.00019389162561576356, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 851, |
|
"loss": 1.6799, |
|
"learning_rate": 0.00019359605911330047, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 853, |
|
"loss": 1.393, |
|
"learning_rate": 0.00019330049261083744, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 855, |
|
"loss": 1.3931, |
|
"learning_rate": 0.00019300492610837435, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 857, |
|
"loss": 1.5691, |
|
"learning_rate": 0.00019270935960591132, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 859, |
|
"loss": 1.3421, |
|
"learning_rate": 0.00019241379310344823, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 861, |
|
"loss": 1.3255, |
|
"learning_rate": 0.0001921182266009852, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 863, |
|
"loss": 1.468, |
|
"learning_rate": 0.00019182266009852217, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 865, |
|
"loss": 1.6568, |
|
"learning_rate": 0.00019152709359605908, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 867, |
|
"loss": 1.6134, |
|
"learning_rate": 0.00019123152709359605, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 869, |
|
"loss": 1.5257, |
|
"learning_rate": 0.00019093596059113296, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 871, |
|
"loss": 1.3118, |
|
"learning_rate": 0.00019064039408866993, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 873, |
|
"loss": 1.449, |
|
"learning_rate": 0.0001903448275862069, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 875, |
|
"loss": 1.627, |
|
"learning_rate": 0.0001900492610837438, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 877, |
|
"loss": 1.4511, |
|
"learning_rate": 0.00018975369458128078, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 879, |
|
"loss": 1.6959, |
|
"learning_rate": 0.0001894581280788177, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 881, |
|
"loss": 1.5174, |
|
"learning_rate": 0.00018916256157635466, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 883, |
|
"loss": 1.5205, |
|
"learning_rate": 0.00018886699507389163, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 885, |
|
"loss": 1.4595, |
|
"learning_rate": 0.00018857142857142854, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 887, |
|
"loss": 1.5407, |
|
"learning_rate": 0.0001882758620689655, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 889, |
|
"loss": 1.8308, |
|
"learning_rate": 0.00018798029556650242, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 891, |
|
"loss": 1.3327, |
|
"learning_rate": 0.0001876847290640394, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 893, |
|
"loss": 1.5598, |
|
"learning_rate": 0.00018738916256157633, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 895, |
|
"loss": 1.5892, |
|
"learning_rate": 0.00018709359605911327, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 897, |
|
"loss": 1.5615, |
|
"learning_rate": 0.00018679802955665024, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 899, |
|
"loss": 1.3798, |
|
"learning_rate": 0.00018650246305418715, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 901, |
|
"loss": 1.7268, |
|
"learning_rate": 0.00018620689655172412, |
|
"epoch": 0.1 |
|
}, |
|
{ |
|
"current_steps": 903, |
|
"loss": 1.3698, |
|
"learning_rate": 0.00018591133004926106, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 905, |
|
"loss": 1.6856, |
|
"learning_rate": 0.000185615763546798, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 907, |
|
"loss": 1.4168, |
|
"learning_rate": 0.00018532019704433497, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 909, |
|
"loss": 1.3779, |
|
"learning_rate": 0.0001850246305418719, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 911, |
|
"loss": 1.4477, |
|
"learning_rate": 0.00018472906403940885, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 913, |
|
"loss": 1.5091, |
|
"learning_rate": 0.0001844334975369458, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 915, |
|
"loss": 1.4676, |
|
"learning_rate": 0.00018413793103448273, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 917, |
|
"loss": 1.417, |
|
"learning_rate": 0.0001838423645320197, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 919, |
|
"loss": 1.537, |
|
"learning_rate": 0.00018354679802955664, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 921, |
|
"loss": 1.4578, |
|
"learning_rate": 0.00018325123152709358, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 923, |
|
"loss": 1.5152, |
|
"learning_rate": 0.00018295566502463052, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 925, |
|
"loss": 1.5826, |
|
"learning_rate": 0.00018266009852216746, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 927, |
|
"loss": 1.4088, |
|
"learning_rate": 0.0001823645320197044, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 929, |
|
"loss": 1.4405, |
|
"learning_rate": 0.00018206896551724137, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 931, |
|
"loss": 1.4493, |
|
"learning_rate": 0.0001817733990147783, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 933, |
|
"loss": 1.4781, |
|
"learning_rate": 0.00018147783251231525, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 935, |
|
"loss": 1.5156, |
|
"learning_rate": 0.0001811822660098522, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 937, |
|
"loss": 1.3937, |
|
"learning_rate": 0.00018088669950738914, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 939, |
|
"loss": 1.4797, |
|
"learning_rate": 0.0001805911330049261, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 941, |
|
"loss": 1.504, |
|
"learning_rate": 0.00018029556650246304, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 943, |
|
"loss": 1.5977, |
|
"learning_rate": 0.00017999999999999998, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 945, |
|
"loss": 1.6771, |
|
"learning_rate": 0.00017970443349753692, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 947, |
|
"loss": 1.5078, |
|
"learning_rate": 0.00017940886699507387, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 949, |
|
"loss": 1.3564, |
|
"learning_rate": 0.00017911330049261083, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 951, |
|
"loss": 1.4263, |
|
"learning_rate": 0.00017881773399014777, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 953, |
|
"loss": 1.4985, |
|
"learning_rate": 0.00017852216748768471, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 955, |
|
"loss": 1.3852, |
|
"learning_rate": 0.00017822660098522166, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 957, |
|
"loss": 1.2973, |
|
"learning_rate": 0.0001779310344827586, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 959, |
|
"loss": 1.3745, |
|
"learning_rate": 0.00017763546798029556, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 961, |
|
"loss": 1.5937, |
|
"learning_rate": 0.0001773399014778325, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 963, |
|
"loss": 1.5452, |
|
"learning_rate": 0.00017704433497536944, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 965, |
|
"loss": 1.5924, |
|
"learning_rate": 0.0001767487684729064, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 967, |
|
"loss": 1.5265, |
|
"learning_rate": 0.00017645320197044333, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 969, |
|
"loss": 1.4742, |
|
"learning_rate": 0.0001761576354679803, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 971, |
|
"loss": 1.45, |
|
"learning_rate": 0.0001758620689655172, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 973, |
|
"loss": 1.5054, |
|
"learning_rate": 0.00017556650246305418, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 975, |
|
"loss": 1.2477, |
|
"learning_rate": 0.00017527093596059114, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 977, |
|
"loss": 1.4494, |
|
"learning_rate": 0.00017497536945812806, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 979, |
|
"loss": 1.4671, |
|
"learning_rate": 0.00017467980295566502, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 981, |
|
"loss": 1.4439, |
|
"learning_rate": 0.00017438423645320194, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 983, |
|
"loss": 1.457, |
|
"learning_rate": 0.0001740886699507389, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 985, |
|
"loss": 1.3146, |
|
"learning_rate": 0.00017379310344827587, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 987, |
|
"loss": 1.6909, |
|
"learning_rate": 0.0001734975369458128, |
|
"epoch": 0.11 |
|
}, |
|
{ |
|
"current_steps": 989, |
|
"loss": 1.4458, |
|
"learning_rate": 0.00017320197044334975, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 991, |
|
"loss": 1.4335, |
|
"learning_rate": 0.00017290640394088667, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 993, |
|
"loss": 1.4131, |
|
"learning_rate": 0.00017261083743842364, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 995, |
|
"loss": 1.6884, |
|
"learning_rate": 0.0001723152709359606, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 997, |
|
"loss": 1.4066, |
|
"learning_rate": 0.00017201970443349752, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 999, |
|
"loss": 1.4257, |
|
"learning_rate": 0.00017172413793103448, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1001, |
|
"loss": 1.452, |
|
"learning_rate": 0.0001714285714285714, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1003, |
|
"loss": 1.4184, |
|
"learning_rate": 0.00017113300492610837, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1005, |
|
"loss": 1.3286, |
|
"learning_rate": 0.00017083743842364528, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1007, |
|
"loss": 1.3791, |
|
"learning_rate": 0.00017054187192118225, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1009, |
|
"loss": 1.6685, |
|
"learning_rate": 0.00017024630541871921, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1011, |
|
"loss": 1.6164, |
|
"learning_rate": 0.00016995073891625613, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1013, |
|
"loss": 1.4075, |
|
"learning_rate": 0.0001696551724137931, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1015, |
|
"loss": 1.5294, |
|
"learning_rate": 0.00016935960591133, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1017, |
|
"loss": 1.3351, |
|
"learning_rate": 0.00016906403940886698, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1019, |
|
"loss": 1.6398, |
|
"learning_rate": 0.00016876847290640395, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1021, |
|
"loss": 1.2795, |
|
"learning_rate": 0.00016847290640394086, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1023, |
|
"loss": 1.3947, |
|
"learning_rate": 0.00016817733990147783, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1025, |
|
"loss": 1.4945, |
|
"learning_rate": 0.00016788177339901474, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1027, |
|
"loss": 1.4894, |
|
"learning_rate": 0.0001675862068965517, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1029, |
|
"loss": 1.3364, |
|
"learning_rate": 0.00016729064039408868, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1031, |
|
"loss": 1.4511, |
|
"learning_rate": 0.0001669950738916256, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1033, |
|
"loss": 1.4264, |
|
"learning_rate": 0.00016669950738916256, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1035, |
|
"loss": 1.455, |
|
"learning_rate": 0.00016640394088669947, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1037, |
|
"loss": 1.4287, |
|
"learning_rate": 0.00016610837438423644, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1039, |
|
"loss": 1.6167, |
|
"learning_rate": 0.00016581280788177338, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1041, |
|
"loss": 1.6667, |
|
"learning_rate": 0.00016551724137931032, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1043, |
|
"loss": 1.5287, |
|
"learning_rate": 0.0001652216748768473, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1045, |
|
"loss": 1.5189, |
|
"learning_rate": 0.0001649261083743842, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1047, |
|
"loss": 1.6377, |
|
"learning_rate": 0.00016463054187192117, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1049, |
|
"loss": 1.6074, |
|
"learning_rate": 0.0001643349753694581, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1051, |
|
"loss": 1.4497, |
|
"learning_rate": 0.00016403940886699505, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1053, |
|
"loss": 1.5705, |
|
"learning_rate": 0.00016374384236453202, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1055, |
|
"loss": 1.7055, |
|
"learning_rate": 0.00016344827586206896, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1057, |
|
"loss": 1.4076, |
|
"learning_rate": 0.0001631527093596059, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1059, |
|
"loss": 1.4607, |
|
"learning_rate": 0.00016285714285714284, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1061, |
|
"loss": 1.4689, |
|
"learning_rate": 0.00016256157635467978, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1063, |
|
"loss": 1.3713, |
|
"learning_rate": 0.00016226600985221675, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1065, |
|
"loss": 1.407, |
|
"learning_rate": 0.0001619704433497537, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1067, |
|
"loss": 1.5291, |
|
"learning_rate": 0.00016167487684729063, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1069, |
|
"loss": 1.382, |
|
"learning_rate": 0.00016137931034482757, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1071, |
|
"loss": 1.553, |
|
"learning_rate": 0.0001610837438423645, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1073, |
|
"loss": 1.6119, |
|
"learning_rate": 0.00016078817733990145, |
|
"epoch": 0.12 |
|
}, |
|
{ |
|
"current_steps": 1075, |
|
"loss": 1.5013, |
|
"learning_rate": 0.00016049261083743842, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1077, |
|
"loss": 1.6357, |
|
"learning_rate": 0.00016019704433497536, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1079, |
|
"loss": 1.4906, |
|
"learning_rate": 0.0001599014778325123, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1081, |
|
"loss": 1.3798, |
|
"learning_rate": 0.00015960591133004924, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1083, |
|
"loss": 1.4316, |
|
"learning_rate": 0.00015931034482758618, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1085, |
|
"loss": 1.4263, |
|
"learning_rate": 0.00015901477832512315, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1087, |
|
"loss": 1.2947, |
|
"learning_rate": 0.0001587192118226601, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1089, |
|
"loss": 1.5948, |
|
"learning_rate": 0.00015842364532019703, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1091, |
|
"loss": 1.4573, |
|
"learning_rate": 0.00015812807881773397, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1093, |
|
"loss": 1.267, |
|
"learning_rate": 0.0001578325123152709, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1095, |
|
"loss": 1.4615, |
|
"learning_rate": 0.00015753694581280788, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1097, |
|
"loss": 1.4817, |
|
"learning_rate": 0.00015724137931034482, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1099, |
|
"loss": 1.5427, |
|
"learning_rate": 0.00015694581280788176, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1101, |
|
"loss": 1.5629, |
|
"learning_rate": 0.0001566502463054187, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1103, |
|
"loss": 1.5958, |
|
"learning_rate": 0.00015635467980295564, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1105, |
|
"loss": 1.5782, |
|
"learning_rate": 0.0001560591133004926, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1107, |
|
"loss": 1.533, |
|
"learning_rate": 0.00015576354679802955, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1109, |
|
"loss": 1.486, |
|
"learning_rate": 0.0001554679802955665, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1111, |
|
"loss": 1.6014, |
|
"learning_rate": 0.00015517241379310346, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1113, |
|
"loss": 1.5115, |
|
"learning_rate": 0.00015487684729064037, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1115, |
|
"loss": 1.4503, |
|
"learning_rate": 0.00015458128078817734, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1117, |
|
"loss": 1.4544, |
|
"learning_rate": 0.00015428571428571425, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1119, |
|
"loss": 1.4324, |
|
"learning_rate": 0.00015399014778325122, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1121, |
|
"loss": 1.6173, |
|
"learning_rate": 0.0001536945812807882, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1123, |
|
"loss": 1.2486, |
|
"learning_rate": 0.0001533990147783251, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1125, |
|
"loss": 1.3345, |
|
"learning_rate": 0.00015310344827586207, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1127, |
|
"loss": 1.3289, |
|
"learning_rate": 0.00015280788177339898, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1129, |
|
"loss": 1.4645, |
|
"learning_rate": 0.00015251231527093595, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1131, |
|
"loss": 1.2622, |
|
"learning_rate": 0.00015221674876847292, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1133, |
|
"loss": 1.6447, |
|
"learning_rate": 0.00015192118226600983, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1135, |
|
"loss": 1.4101, |
|
"learning_rate": 0.0001516256157635468, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1137, |
|
"loss": 1.2335, |
|
"learning_rate": 0.0001513300492610837, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1139, |
|
"loss": 1.5197, |
|
"learning_rate": 0.00015103448275862068, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1141, |
|
"loss": 1.4544, |
|
"learning_rate": 0.00015073891625615765, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1143, |
|
"loss": 1.653, |
|
"learning_rate": 0.00015044334975369456, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1145, |
|
"loss": 1.4697, |
|
"learning_rate": 0.00015014778325123153, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1147, |
|
"loss": 1.5149, |
|
"learning_rate": 0.00014985221674876847, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1149, |
|
"loss": 1.5345, |
|
"learning_rate": 0.0001495566502463054, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1151, |
|
"loss": 1.4074, |
|
"learning_rate": 0.00014926108374384235, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1153, |
|
"loss": 1.6013, |
|
"learning_rate": 0.0001489655172413793, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1155, |
|
"loss": 1.4285, |
|
"learning_rate": 0.00014866995073891623, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1157, |
|
"loss": 1.4755, |
|
"learning_rate": 0.00014837438423645317, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1159, |
|
"loss": 1.3552, |
|
"learning_rate": 0.00014807881773399014, |
|
"epoch": 0.13 |
|
}, |
|
{ |
|
"current_steps": 1161, |
|
"loss": 1.3876, |
|
"learning_rate": 0.00014778325123152708, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1163, |
|
"loss": 1.3403, |
|
"learning_rate": 0.00014748768472906402, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1165, |
|
"loss": 1.305, |
|
"learning_rate": 0.00014719211822660096, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1167, |
|
"loss": 1.523, |
|
"learning_rate": 0.0001468965517241379, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1169, |
|
"loss": 1.575, |
|
"learning_rate": 0.00014660098522167487, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1171, |
|
"loss": 1.6639, |
|
"learning_rate": 0.0001463054187192118, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1173, |
|
"loss": 1.4092, |
|
"learning_rate": 0.00014600985221674875, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1175, |
|
"loss": 1.6079, |
|
"learning_rate": 0.0001457142857142857, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1177, |
|
"loss": 1.6555, |
|
"learning_rate": 0.00014541871921182263, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1179, |
|
"loss": 1.5001, |
|
"learning_rate": 0.00014512315270935958, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1181, |
|
"loss": 1.4116, |
|
"learning_rate": 0.00014482758620689654, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1183, |
|
"loss": 1.4401, |
|
"learning_rate": 0.00014453201970443348, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1185, |
|
"loss": 1.6073, |
|
"learning_rate": 0.00014423645320197042, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1187, |
|
"loss": 1.5916, |
|
"learning_rate": 0.00014394088669950736, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1189, |
|
"loss": 1.4508, |
|
"learning_rate": 0.0001436453201970443, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1191, |
|
"loss": 1.2755, |
|
"learning_rate": 0.00014334975369458127, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1193, |
|
"loss": 1.4433, |
|
"learning_rate": 0.00014305418719211821, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1195, |
|
"loss": 1.6638, |
|
"learning_rate": 0.00014275862068965515, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1197, |
|
"loss": 1.5391, |
|
"learning_rate": 0.0001424630541871921, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1199, |
|
"loss": 1.2966, |
|
"learning_rate": 0.00014216748768472904, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1201, |
|
"loss": 1.6218, |
|
"learning_rate": 0.000141871921182266, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1203, |
|
"loss": 1.3367, |
|
"learning_rate": 0.00014157635467980294, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1205, |
|
"loss": 1.5205, |
|
"learning_rate": 0.00014128078817733988, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1207, |
|
"loss": 1.2991, |
|
"learning_rate": 0.00014098522167487683, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1209, |
|
"loss": 1.5471, |
|
"learning_rate": 0.00014068965517241377, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1211, |
|
"loss": 1.3356, |
|
"learning_rate": 0.00014039408866995073, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1213, |
|
"loss": 1.4511, |
|
"learning_rate": 0.00014009852216748767, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1215, |
|
"loss": 1.3815, |
|
"learning_rate": 0.00013980295566502461, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1217, |
|
"loss": 1.5201, |
|
"learning_rate": 0.00013950738916256156, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1219, |
|
"loss": 1.5778, |
|
"learning_rate": 0.00013921182266009852, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1221, |
|
"loss": 1.3516, |
|
"learning_rate": 0.00013891625615763546, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1223, |
|
"loss": 1.4532, |
|
"learning_rate": 0.0001386206896551724, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1225, |
|
"loss": 1.468, |
|
"learning_rate": 0.00013832512315270935, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1227, |
|
"loss": 1.4443, |
|
"learning_rate": 0.00013802955665024629, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1229, |
|
"loss": 1.2362, |
|
"learning_rate": 0.00013773399014778325, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1231, |
|
"loss": 1.6585, |
|
"learning_rate": 0.0001374384236453202, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1233, |
|
"loss": 1.7561, |
|
"learning_rate": 0.00013714285714285713, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1235, |
|
"loss": 1.6997, |
|
"learning_rate": 0.00013684729064039408, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1237, |
|
"loss": 1.4349, |
|
"learning_rate": 0.00013655172413793102, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1239, |
|
"loss": 1.3657, |
|
"learning_rate": 0.00013625615763546798, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1241, |
|
"loss": 1.6985, |
|
"learning_rate": 0.00013596059113300492, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1243, |
|
"loss": 1.5181, |
|
"learning_rate": 0.00013566502463054186, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1245, |
|
"loss": 1.4471, |
|
"learning_rate": 0.0001353694581280788, |
|
"epoch": 0.14 |
|
}, |
|
{ |
|
"current_steps": 1247, |
|
"loss": 1.65, |
|
"learning_rate": 0.00013507389162561577, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1249, |
|
"loss": 1.1517, |
|
"learning_rate": 0.00013477832512315271, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1251, |
|
"loss": 1.4166, |
|
"learning_rate": 0.00013448275862068965, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1253, |
|
"loss": 1.4719, |
|
"learning_rate": 0.0001341871921182266, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1255, |
|
"loss": 1.4172, |
|
"learning_rate": 0.00013389162561576354, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1257, |
|
"loss": 1.3626, |
|
"learning_rate": 0.00013359605911330048, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1259, |
|
"loss": 1.4102, |
|
"learning_rate": 0.00013330049261083744, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1261, |
|
"loss": 1.3181, |
|
"learning_rate": 0.00013300492610837438, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1263, |
|
"loss": 1.4147, |
|
"learning_rate": 0.00013270935960591133, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1265, |
|
"loss": 1.5692, |
|
"learning_rate": 0.00013241379310344827, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1267, |
|
"loss": 1.3556, |
|
"learning_rate": 0.0001321182266009852, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1269, |
|
"loss": 1.5808, |
|
"learning_rate": 0.00013182266009852215, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1271, |
|
"loss": 1.2675, |
|
"learning_rate": 0.00013152709359605912, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1273, |
|
"loss": 1.4857, |
|
"learning_rate": 0.00013123152709359606, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1275, |
|
"loss": 1.445, |
|
"learning_rate": 0.000130935960591133, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1277, |
|
"loss": 1.6075, |
|
"learning_rate": 0.00013064039408866994, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1279, |
|
"loss": 1.3829, |
|
"learning_rate": 0.00013034482758620688, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1281, |
|
"loss": 1.3487, |
|
"learning_rate": 0.00013004926108374385, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1283, |
|
"loss": 1.3105, |
|
"learning_rate": 0.00012975369458128079, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1285, |
|
"loss": 1.5299, |
|
"learning_rate": 0.00012945812807881773, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1287, |
|
"loss": 1.5279, |
|
"learning_rate": 0.00012916256157635467, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1289, |
|
"loss": 1.5722, |
|
"learning_rate": 0.0001288669950738916, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1291, |
|
"loss": 1.4816, |
|
"learning_rate": 0.00012857142857142855, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1293, |
|
"loss": 1.3207, |
|
"learning_rate": 0.00012827586206896552, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1295, |
|
"loss": 1.566, |
|
"learning_rate": 0.00012798029556650246, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1297, |
|
"loss": 1.5285, |
|
"learning_rate": 0.0001276847290640394, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1299, |
|
"loss": 1.6871, |
|
"learning_rate": 0.00012738916256157634, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1301, |
|
"loss": 1.3097, |
|
"learning_rate": 0.00012709359605911328, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1303, |
|
"loss": 1.408, |
|
"learning_rate": 0.00012679802955665022, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1305, |
|
"loss": 1.3767, |
|
"learning_rate": 0.0001265024630541872, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1307, |
|
"loss": 1.3903, |
|
"learning_rate": 0.00012620689655172413, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1309, |
|
"loss": 1.433, |
|
"learning_rate": 0.00012591133004926107, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1311, |
|
"loss": 1.3245, |
|
"learning_rate": 0.000125615763546798, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1313, |
|
"loss": 1.3325, |
|
"learning_rate": 0.00012532019704433495, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1315, |
|
"loss": 1.4503, |
|
"learning_rate": 0.00012502463054187192, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1317, |
|
"loss": 1.49, |
|
"learning_rate": 0.00012472906403940886, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1319, |
|
"loss": 1.485, |
|
"learning_rate": 0.0001244334975369458, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1321, |
|
"loss": 1.4404, |
|
"learning_rate": 0.00012413793103448274, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1323, |
|
"loss": 1.3019, |
|
"learning_rate": 0.00012384236453201968, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1325, |
|
"loss": 1.5872, |
|
"learning_rate": 0.00012354679802955662, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1327, |
|
"loss": 1.5612, |
|
"learning_rate": 0.0001232512315270936, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1329, |
|
"loss": 1.4557, |
|
"learning_rate": 0.00012295566502463053, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1331, |
|
"loss": 1.5886, |
|
"learning_rate": 0.00012266009852216747, |
|
"epoch": 0.15 |
|
}, |
|
{ |
|
"current_steps": 1333, |
|
"loss": 1.3797, |
|
"learning_rate": 0.0001223645320197044, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1335, |
|
"loss": 1.3713, |
|
"learning_rate": 0.00012206896551724136, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1337, |
|
"loss": 1.4158, |
|
"learning_rate": 0.00012177339901477832, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1339, |
|
"loss": 1.4021, |
|
"learning_rate": 0.00012147783251231526, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1341, |
|
"loss": 1.4421, |
|
"learning_rate": 0.00012118226600985221, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1343, |
|
"loss": 1.2342, |
|
"learning_rate": 0.00012088669950738915, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1345, |
|
"loss": 1.3491, |
|
"learning_rate": 0.0001205911330049261, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1347, |
|
"loss": 1.3119, |
|
"learning_rate": 0.00012029556650246304, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1349, |
|
"loss": 1.328, |
|
"learning_rate": 0.00011999999999999999, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1351, |
|
"loss": 1.5423, |
|
"learning_rate": 0.00011970443349753694, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1353, |
|
"loss": 1.4857, |
|
"learning_rate": 0.00011940886699507388, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1355, |
|
"loss": 1.6532, |
|
"learning_rate": 0.00011911330049261082, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1357, |
|
"loss": 1.3726, |
|
"learning_rate": 0.00011881773399014777, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1359, |
|
"loss": 1.1621, |
|
"learning_rate": 0.0001185221674876847, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1361, |
|
"loss": 1.4227, |
|
"learning_rate": 0.00011822660098522167, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1363, |
|
"loss": 1.3642, |
|
"learning_rate": 0.00011793103448275861, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1365, |
|
"loss": 1.5377, |
|
"learning_rate": 0.00011763546798029556, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1367, |
|
"loss": 1.4044, |
|
"learning_rate": 0.0001173399014778325, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1369, |
|
"loss": 1.4965, |
|
"learning_rate": 0.00011704433497536944, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1371, |
|
"loss": 1.2706, |
|
"learning_rate": 0.0001167487684729064, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1373, |
|
"loss": 1.5986, |
|
"learning_rate": 0.00011645320197044334, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1375, |
|
"loss": 1.3399, |
|
"learning_rate": 0.00011615763546798029, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1377, |
|
"loss": 1.5509, |
|
"learning_rate": 0.00011586206896551723, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1379, |
|
"loss": 1.473, |
|
"learning_rate": 0.00011556650246305417, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1381, |
|
"loss": 1.487, |
|
"learning_rate": 0.00011527093596059112, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1383, |
|
"loss": 1.5032, |
|
"learning_rate": 0.00011497536945812808, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1385, |
|
"loss": 1.4614, |
|
"learning_rate": 0.00011467980295566502, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1387, |
|
"loss": 1.756, |
|
"learning_rate": 0.00011438423645320196, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1389, |
|
"loss": 1.4472, |
|
"learning_rate": 0.0001140886699507389, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1391, |
|
"loss": 1.3235, |
|
"learning_rate": 0.00011379310344827585, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1393, |
|
"loss": 1.4611, |
|
"learning_rate": 0.0001134975369458128, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1395, |
|
"loss": 1.5012, |
|
"learning_rate": 0.00011320197044334975, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1397, |
|
"loss": 1.4022, |
|
"learning_rate": 0.00011290640394088669, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1399, |
|
"loss": 1.6699, |
|
"learning_rate": 0.00011261083743842364, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1401, |
|
"loss": 1.3621, |
|
"learning_rate": 0.00011231527093596058, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1403, |
|
"loss": 1.414, |
|
"learning_rate": 0.00011201970443349752, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1405, |
|
"loss": 1.2507, |
|
"learning_rate": 0.00011172413793103448, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1407, |
|
"loss": 1.3533, |
|
"learning_rate": 0.00011142857142857142, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1409, |
|
"loss": 1.3269, |
|
"learning_rate": 0.00011113300492610837, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1411, |
|
"loss": 1.3367, |
|
"learning_rate": 0.00011083743842364531, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1413, |
|
"loss": 1.354, |
|
"learning_rate": 0.00011054187192118225, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1415, |
|
"loss": 1.4322, |
|
"learning_rate": 0.00011024630541871919, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1417, |
|
"loss": 1.3051, |
|
"learning_rate": 0.00010995073891625615, |
|
"epoch": 0.16 |
|
}, |
|
{ |
|
"current_steps": 1419, |
|
"loss": 1.4336, |
|
"learning_rate": 0.0001096551724137931, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1421, |
|
"loss": 1.4927, |
|
"learning_rate": 0.00010935960591133004, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1423, |
|
"loss": 1.2925, |
|
"learning_rate": 0.00010906403940886698, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1425, |
|
"loss": 1.5501, |
|
"learning_rate": 0.00010876847290640392, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1427, |
|
"loss": 1.4563, |
|
"learning_rate": 0.00010847290640394089, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1429, |
|
"loss": 1.5805, |
|
"learning_rate": 0.00010817733990147783, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1431, |
|
"loss": 1.603, |
|
"learning_rate": 0.00010788177339901477, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1433, |
|
"loss": 1.5101, |
|
"learning_rate": 0.00010758620689655171, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1435, |
|
"loss": 1.3574, |
|
"learning_rate": 0.00010729064039408865, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1437, |
|
"loss": 1.527, |
|
"learning_rate": 0.0001069950738916256, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1439, |
|
"loss": 1.6483, |
|
"learning_rate": 0.00010669950738916256, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1441, |
|
"loss": 1.5076, |
|
"learning_rate": 0.0001064039408866995, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1443, |
|
"loss": 1.1374, |
|
"learning_rate": 0.00010610837438423644, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1445, |
|
"loss": 1.4851, |
|
"learning_rate": 0.00010581280788177338, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1447, |
|
"loss": 1.4381, |
|
"learning_rate": 0.00010551724137931032, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1449, |
|
"loss": 1.4604, |
|
"learning_rate": 0.00010522167487684729, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1451, |
|
"loss": 1.3896, |
|
"learning_rate": 0.00010492610837438423, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1453, |
|
"loss": 1.6003, |
|
"learning_rate": 0.00010463054187192117, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1455, |
|
"loss": 1.4545, |
|
"learning_rate": 0.00010433497536945811, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1457, |
|
"loss": 1.5914, |
|
"learning_rate": 0.00010403940886699505, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1459, |
|
"loss": 1.4277, |
|
"learning_rate": 0.00010374384236453201, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1461, |
|
"loss": 1.4904, |
|
"learning_rate": 0.00010344827586206896, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1463, |
|
"loss": 1.2917, |
|
"learning_rate": 0.0001031527093596059, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1465, |
|
"loss": 1.5209, |
|
"learning_rate": 0.00010285714285714284, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1467, |
|
"loss": 1.6083, |
|
"learning_rate": 0.0001025615763546798, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1469, |
|
"loss": 1.322, |
|
"learning_rate": 0.00010226600985221674, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1471, |
|
"loss": 1.3146, |
|
"learning_rate": 0.00010197044334975368, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1473, |
|
"loss": 1.4603, |
|
"learning_rate": 0.00010167487684729063, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1475, |
|
"loss": 1.2714, |
|
"learning_rate": 0.00010137931034482757, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1477, |
|
"loss": 1.3224, |
|
"learning_rate": 0.00010108374384236453, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1479, |
|
"loss": 1.3709, |
|
"learning_rate": 0.00010078817733990147, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1481, |
|
"loss": 1.6218, |
|
"learning_rate": 0.00010049261083743841, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1483, |
|
"loss": 1.5694, |
|
"learning_rate": 0.00010019704433497536, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1485, |
|
"loss": 1.4105, |
|
"learning_rate": 9.99014778325123e-05, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1487, |
|
"loss": 1.5503, |
|
"learning_rate": 9.960591133004926e-05, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1489, |
|
"loss": 1.4169, |
|
"learning_rate": 9.93103448275862e-05, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1491, |
|
"loss": 1.5529, |
|
"learning_rate": 9.901477832512314e-05, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1493, |
|
"loss": 1.339, |
|
"learning_rate": 9.871921182266008e-05, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1495, |
|
"loss": 1.4177, |
|
"learning_rate": 9.842364532019705e-05, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1497, |
|
"loss": 1.3418, |
|
"learning_rate": 9.812807881773399e-05, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1499, |
|
"loss": 1.405, |
|
"learning_rate": 9.783251231527093e-05, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1501, |
|
"loss": 1.3082, |
|
"learning_rate": 9.753694581280787e-05, |
|
"epoch": 0.17 |
|
}, |
|
{ |
|
"current_steps": 1503, |
|
"loss": 1.5519, |
|
"learning_rate": 9.724137931034481e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1505, |
|
"loss": 1.4063, |
|
"learning_rate": 9.694581280788178e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1507, |
|
"loss": 1.4751, |
|
"learning_rate": 9.694581280788178e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1509, |
|
"loss": 1.6339, |
|
"learning_rate": 9.665024630541872e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1511, |
|
"loss": 1.4362, |
|
"learning_rate": 9.635467980295566e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1513, |
|
"loss": 1.5477, |
|
"learning_rate": 9.60591133004926e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1515, |
|
"loss": 1.3371, |
|
"learning_rate": 9.576354679802954e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1517, |
|
"loss": 1.2858, |
|
"learning_rate": 9.546798029556648e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1519, |
|
"loss": 1.2767, |
|
"learning_rate": 9.517241379310345e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1521, |
|
"loss": 1.374, |
|
"learning_rate": 9.487684729064039e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1523, |
|
"loss": 1.264, |
|
"learning_rate": 9.458128078817733e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1525, |
|
"loss": 1.3859, |
|
"learning_rate": 9.428571428571427e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1527, |
|
"loss": 1.538, |
|
"learning_rate": 9.399014778325121e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1529, |
|
"loss": 1.3722, |
|
"learning_rate": 9.369458128078817e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1531, |
|
"loss": 1.5568, |
|
"learning_rate": 9.339901477832512e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1533, |
|
"loss": 1.5843, |
|
"learning_rate": 9.310344827586206e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1535, |
|
"loss": 1.3413, |
|
"learning_rate": 9.2807881773399e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1537, |
|
"loss": 1.4297, |
|
"learning_rate": 9.251231527093596e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1539, |
|
"loss": 1.359, |
|
"learning_rate": 9.22167487684729e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1541, |
|
"loss": 1.3543, |
|
"learning_rate": 9.192118226600985e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1543, |
|
"loss": 1.5025, |
|
"learning_rate": 9.162561576354679e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1545, |
|
"loss": 1.4669, |
|
"learning_rate": 9.133004926108373e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1547, |
|
"loss": 1.3861, |
|
"learning_rate": 9.103448275862069e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1549, |
|
"loss": 1.2934, |
|
"learning_rate": 9.073891625615763e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1551, |
|
"loss": 1.3889, |
|
"learning_rate": 9.044334975369457e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1553, |
|
"loss": 1.4878, |
|
"learning_rate": 9.014778325123152e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1555, |
|
"loss": 1.6128, |
|
"learning_rate": 8.985221674876846e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1557, |
|
"loss": 1.3818, |
|
"learning_rate": 8.955665024630542e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1559, |
|
"loss": 1.5759, |
|
"learning_rate": 8.926108374384236e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1561, |
|
"loss": 1.3481, |
|
"learning_rate": 8.89655172413793e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1563, |
|
"loss": 1.402, |
|
"learning_rate": 8.866995073891625e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1565, |
|
"loss": 1.4652, |
|
"learning_rate": 8.83743842364532e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1567, |
|
"loss": 1.4362, |
|
"learning_rate": 8.807881773399015e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1569, |
|
"loss": 1.1903, |
|
"learning_rate": 8.778325123152709e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1571, |
|
"loss": 1.6198, |
|
"learning_rate": 8.748768472906403e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1573, |
|
"loss": 1.3341, |
|
"learning_rate": 8.719211822660097e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1575, |
|
"loss": 1.4117, |
|
"learning_rate": 8.689655172413794e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1577, |
|
"loss": 1.4784, |
|
"learning_rate": 8.660098522167488e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1579, |
|
"loss": 1.3749, |
|
"learning_rate": 8.630541871921182e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1581, |
|
"loss": 1.5399, |
|
"learning_rate": 8.600985221674876e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1583, |
|
"loss": 1.48, |
|
"learning_rate": 8.57142857142857e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1585, |
|
"loss": 1.5269, |
|
"learning_rate": 8.541871921182264e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1587, |
|
"loss": 1.6458, |
|
"learning_rate": 8.512315270935961e-05, |
|
"epoch": 0.18 |
|
}, |
|
{ |
|
"current_steps": 1589, |
|
"loss": 1.4381, |
|
"learning_rate": 8.482758620689655e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1591, |
|
"loss": 1.5807, |
|
"learning_rate": 8.453201970443349e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1593, |
|
"loss": 1.1841, |
|
"learning_rate": 8.423645320197043e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1595, |
|
"loss": 1.4327, |
|
"learning_rate": 8.394088669950737e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1597, |
|
"loss": 1.3586, |
|
"learning_rate": 8.364532019704434e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1599, |
|
"loss": 1.4018, |
|
"learning_rate": 8.334975369458128e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1601, |
|
"loss": 1.3762, |
|
"learning_rate": 8.305418719211822e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1603, |
|
"loss": 1.4126, |
|
"learning_rate": 8.275862068965516e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1605, |
|
"loss": 1.2462, |
|
"learning_rate": 8.24630541871921e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1607, |
|
"loss": 1.4754, |
|
"learning_rate": 8.216748768472905e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1609, |
|
"loss": 1.5572, |
|
"learning_rate": 8.187192118226601e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1611, |
|
"loss": 1.5467, |
|
"learning_rate": 8.157635467980295e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1613, |
|
"loss": 1.5242, |
|
"learning_rate": 8.128078817733989e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1615, |
|
"loss": 1.5588, |
|
"learning_rate": 8.098522167487684e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1617, |
|
"loss": 1.6107, |
|
"learning_rate": 8.068965517241378e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1619, |
|
"loss": 1.3845, |
|
"learning_rate": 8.039408866995073e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1621, |
|
"loss": 1.391, |
|
"learning_rate": 8.009852216748768e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1623, |
|
"loss": 1.3375, |
|
"learning_rate": 7.980295566502462e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1625, |
|
"loss": 1.5187, |
|
"learning_rate": 7.950738916256157e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1627, |
|
"loss": 1.4744, |
|
"learning_rate": 7.921182266009851e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1629, |
|
"loss": 1.4449, |
|
"learning_rate": 7.891625615763546e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1631, |
|
"loss": 1.4237, |
|
"learning_rate": 7.862068965517241e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1633, |
|
"loss": 1.3786, |
|
"learning_rate": 7.832512315270935e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1635, |
|
"loss": 1.6633, |
|
"learning_rate": 7.80295566502463e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1637, |
|
"loss": 1.3197, |
|
"learning_rate": 7.773399014778325e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1639, |
|
"loss": 1.2572, |
|
"learning_rate": 7.743842364532019e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1641, |
|
"loss": 1.6133, |
|
"learning_rate": 7.714285714285713e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1643, |
|
"loss": 1.3526, |
|
"learning_rate": 7.68472906403941e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1645, |
|
"loss": 1.2797, |
|
"learning_rate": 7.655172413793103e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1647, |
|
"loss": 1.3872, |
|
"learning_rate": 7.625615763546798e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1649, |
|
"loss": 1.2822, |
|
"learning_rate": 7.596059113300492e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1651, |
|
"loss": 1.3557, |
|
"learning_rate": 7.566502463054186e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1653, |
|
"loss": 1.1847, |
|
"learning_rate": 7.536945812807882e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1655, |
|
"loss": 1.4428, |
|
"learning_rate": 7.507389162561577e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1657, |
|
"loss": 1.443, |
|
"learning_rate": 7.47783251231527e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1659, |
|
"loss": 1.4633, |
|
"learning_rate": 7.448275862068965e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1661, |
|
"loss": 1.5413, |
|
"learning_rate": 7.418719211822659e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1663, |
|
"loss": 1.3113, |
|
"learning_rate": 7.389162561576354e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1665, |
|
"loss": 1.4703, |
|
"learning_rate": 7.359605911330048e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1667, |
|
"loss": 1.3975, |
|
"learning_rate": 7.330049261083744e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1669, |
|
"loss": 1.3937, |
|
"learning_rate": 7.300492610837438e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1671, |
|
"loss": 1.4717, |
|
"learning_rate": 7.270935960591132e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1673, |
|
"loss": 1.3512, |
|
"learning_rate": 7.241379310344827e-05, |
|
"epoch": 0.19 |
|
}, |
|
{ |
|
"current_steps": 1675, |
|
"loss": 1.4515, |
|
"learning_rate": 7.211822660098521e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1677, |
|
"loss": 1.6275, |
|
"learning_rate": 7.182266009852215e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1679, |
|
"loss": 1.3561, |
|
"learning_rate": 7.152709359605911e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1681, |
|
"loss": 1.2888, |
|
"learning_rate": 7.123152709359605e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1683, |
|
"loss": 1.351, |
|
"learning_rate": 7.0935960591133e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1685, |
|
"loss": 1.4117, |
|
"learning_rate": 7.064039408866994e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1687, |
|
"loss": 1.2991, |
|
"learning_rate": 7.034482758620688e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1689, |
|
"loss": 1.413, |
|
"learning_rate": 7.004926108374384e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1691, |
|
"loss": 1.3917, |
|
"learning_rate": 6.975369458128078e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1693, |
|
"loss": 1.3873, |
|
"learning_rate": 6.945812807881773e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1695, |
|
"loss": 1.4783, |
|
"learning_rate": 6.916256157635467e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1697, |
|
"loss": 1.5639, |
|
"learning_rate": 6.886699507389163e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1699, |
|
"loss": 1.5239, |
|
"learning_rate": 6.857142857142857e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1701, |
|
"loss": 1.5281, |
|
"learning_rate": 6.827586206896551e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1703, |
|
"loss": 1.2794, |
|
"learning_rate": 6.798029556650246e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1705, |
|
"loss": 1.2762, |
|
"learning_rate": 6.76847290640394e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1707, |
|
"loss": 1.2824, |
|
"learning_rate": 6.738916256157636e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1709, |
|
"loss": 1.2033, |
|
"learning_rate": 6.70935960591133e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1711, |
|
"loss": 1.4473, |
|
"learning_rate": 6.679802955665024e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1713, |
|
"loss": 1.6409, |
|
"learning_rate": 6.650246305418719e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1715, |
|
"loss": 1.6363, |
|
"learning_rate": 6.620689655172413e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1717, |
|
"loss": 1.3944, |
|
"learning_rate": 6.591133004926107e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1719, |
|
"loss": 1.5966, |
|
"learning_rate": 6.561576354679803e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1721, |
|
"loss": 1.4439, |
|
"learning_rate": 6.532019704433497e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1723, |
|
"loss": 1.4548, |
|
"learning_rate": 6.502463054187192e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1725, |
|
"loss": 1.2948, |
|
"learning_rate": 6.472906403940886e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1727, |
|
"loss": 1.5007, |
|
"learning_rate": 6.44334975369458e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1729, |
|
"loss": 1.3214, |
|
"learning_rate": 6.413793103448276e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1731, |
|
"loss": 1.4571, |
|
"learning_rate": 6.38423645320197e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1733, |
|
"loss": 1.5113, |
|
"learning_rate": 6.354679802955664e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1735, |
|
"loss": 1.4404, |
|
"learning_rate": 6.32512315270936e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1737, |
|
"loss": 1.3533, |
|
"learning_rate": 6.295566502463053e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1739, |
|
"loss": 1.4039, |
|
"learning_rate": 6.266009852216747e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1741, |
|
"loss": 1.4558, |
|
"learning_rate": 6.236453201970443e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1743, |
|
"loss": 1.4169, |
|
"learning_rate": 6.206896551724137e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1745, |
|
"loss": 1.5056, |
|
"learning_rate": 6.177339901477831e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1747, |
|
"loss": 1.4671, |
|
"learning_rate": 6.147783251231526e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1749, |
|
"loss": 1.3122, |
|
"learning_rate": 6.11822660098522e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1751, |
|
"loss": 1.3384, |
|
"learning_rate": 6.088669950738916e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1753, |
|
"loss": 1.3222, |
|
"learning_rate": 6.059113300492611e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1755, |
|
"loss": 1.4684, |
|
"learning_rate": 6.029556650246305e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1757, |
|
"loss": 1.2302, |
|
"learning_rate": 5.9999999999999995e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1759, |
|
"loss": 1.3662, |
|
"learning_rate": 5.970443349753694e-05, |
|
"epoch": 0.2 |
|
}, |
|
{ |
|
"current_steps": 1761, |
|
"loss": 1.4275, |
|
"learning_rate": 5.940886699507388e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1763, |
|
"loss": 1.2949, |
|
"learning_rate": 5.911330049261084e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1765, |
|
"loss": 1.4499, |
|
"learning_rate": 5.881773399014778e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1767, |
|
"loss": 1.3698, |
|
"learning_rate": 5.852216748768472e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1769, |
|
"loss": 1.217, |
|
"learning_rate": 5.822660098522167e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1771, |
|
"loss": 1.5283, |
|
"learning_rate": 5.793103448275861e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1773, |
|
"loss": 1.4191, |
|
"learning_rate": 5.763546798029556e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1775, |
|
"loss": 1.4649, |
|
"learning_rate": 5.733990147783251e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1777, |
|
"loss": 1.3919, |
|
"learning_rate": 5.704433497536945e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1779, |
|
"loss": 1.5556, |
|
"learning_rate": 5.67487684729064e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1781, |
|
"loss": 1.5268, |
|
"learning_rate": 5.645320197044334e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1783, |
|
"loss": 1.3228, |
|
"learning_rate": 5.615763546798029e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1785, |
|
"loss": 1.5109, |
|
"learning_rate": 5.586206896551724e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1787, |
|
"loss": 1.4711, |
|
"learning_rate": 5.5566502463054186e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1789, |
|
"loss": 1.5531, |
|
"learning_rate": 5.5270935960591126e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1791, |
|
"loss": 1.4627, |
|
"learning_rate": 5.4975369458128074e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1793, |
|
"loss": 1.375, |
|
"learning_rate": 5.467980295566502e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1795, |
|
"loss": 1.3208, |
|
"learning_rate": 5.438423645320196e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1797, |
|
"loss": 1.5061, |
|
"learning_rate": 5.4088669950738916e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1799, |
|
"loss": 1.4171, |
|
"learning_rate": 5.3793103448275856e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1801, |
|
"loss": 1.2523, |
|
"learning_rate": 5.34975369458128e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1803, |
|
"loss": 1.1953, |
|
"learning_rate": 5.320197044334975e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1805, |
|
"loss": 1.5136, |
|
"learning_rate": 5.290640394088669e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1807, |
|
"loss": 1.2321, |
|
"learning_rate": 5.2610837438423646e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1809, |
|
"loss": 1.2477, |
|
"learning_rate": 5.231527093596059e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1811, |
|
"loss": 1.4657, |
|
"learning_rate": 5.201970443349753e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1813, |
|
"loss": 1.6217, |
|
"learning_rate": 5.172413793103448e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1815, |
|
"loss": 1.4777, |
|
"learning_rate": 5.142857142857142e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1817, |
|
"loss": 1.2844, |
|
"learning_rate": 5.113300492610837e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1819, |
|
"loss": 1.5179, |
|
"learning_rate": 5.083743842364532e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1821, |
|
"loss": 1.5915, |
|
"learning_rate": 5.0541871921182264e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1823, |
|
"loss": 1.2204, |
|
"learning_rate": 5.0246305418719205e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1825, |
|
"loss": 1.3171, |
|
"learning_rate": 4.995073891625615e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1827, |
|
"loss": 1.4406, |
|
"learning_rate": 4.96551724137931e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1829, |
|
"loss": 1.4661, |
|
"learning_rate": 4.935960591133004e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1831, |
|
"loss": 1.4711, |
|
"learning_rate": 4.9064039408866995e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1833, |
|
"loss": 1.3958, |
|
"learning_rate": 4.8768472906403935e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1835, |
|
"loss": 1.3915, |
|
"learning_rate": 4.847290640394089e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1837, |
|
"loss": 1.412, |
|
"learning_rate": 4.817733990147783e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1839, |
|
"loss": 1.3662, |
|
"learning_rate": 4.788177339901477e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1841, |
|
"loss": 1.3259, |
|
"learning_rate": 4.788177339901477e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1843, |
|
"loss": 1.499, |
|
"learning_rate": 4.7586206896551725e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1845, |
|
"loss": 1.4059, |
|
"learning_rate": 4.7290640394088666e-05, |
|
"epoch": 0.21 |
|
}, |
|
{ |
|
"current_steps": 1847, |
|
"loss": 1.4343, |
|
"learning_rate": 4.6995073891625606e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1849, |
|
"loss": 1.3018, |
|
"learning_rate": 4.669950738916256e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1851, |
|
"loss": 1.3917, |
|
"learning_rate": 4.64039408866995e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1853, |
|
"loss": 1.2198, |
|
"learning_rate": 4.610837438423645e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1855, |
|
"loss": 1.3396, |
|
"learning_rate": 4.5812807881773396e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1857, |
|
"loss": 1.515, |
|
"learning_rate": 4.551724137931034e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1859, |
|
"loss": 1.2641, |
|
"learning_rate": 4.5221674876847284e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1861, |
|
"loss": 1.3899, |
|
"learning_rate": 4.492610837438423e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1863, |
|
"loss": 1.5666, |
|
"learning_rate": 4.463054187192118e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1865, |
|
"loss": 1.2917, |
|
"learning_rate": 4.4334975369458126e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1867, |
|
"loss": 1.4541, |
|
"learning_rate": 4.4039408866995073e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1869, |
|
"loss": 1.2695, |
|
"learning_rate": 4.3743842364532014e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1871, |
|
"loss": 1.4244, |
|
"learning_rate": 4.344827586206897e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1873, |
|
"loss": 1.325, |
|
"learning_rate": 4.315270935960591e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1875, |
|
"loss": 1.3828, |
|
"learning_rate": 4.285714285714285e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1877, |
|
"loss": 1.4658, |
|
"learning_rate": 4.2561576354679804e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1879, |
|
"loss": 1.4219, |
|
"learning_rate": 4.2266009852216744e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1881, |
|
"loss": 1.3448, |
|
"learning_rate": 4.1970443349753685e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1883, |
|
"loss": 1.3195, |
|
"learning_rate": 4.167487684729064e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1885, |
|
"loss": 1.3979, |
|
"learning_rate": 4.137931034482758e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1887, |
|
"loss": 1.4834, |
|
"learning_rate": 4.108374384236453e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1889, |
|
"loss": 1.4958, |
|
"learning_rate": 4.0788177339901475e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1891, |
|
"loss": 1.5403, |
|
"learning_rate": 4.049261083743842e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1893, |
|
"loss": 1.2163, |
|
"learning_rate": 4.019704433497536e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1895, |
|
"loss": 1.2908, |
|
"learning_rate": 3.990147783251231e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1897, |
|
"loss": 1.4287, |
|
"learning_rate": 3.960591133004926e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1899, |
|
"loss": 1.409, |
|
"learning_rate": 3.9310344827586205e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1901, |
|
"loss": 1.3897, |
|
"learning_rate": 3.901477832512315e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1903, |
|
"loss": 1.3014, |
|
"learning_rate": 3.871921182266009e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1905, |
|
"loss": 1.3687, |
|
"learning_rate": 3.842364532019705e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1907, |
|
"loss": 1.4001, |
|
"learning_rate": 3.812807881773399e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1909, |
|
"loss": 1.3124, |
|
"learning_rate": 3.783251231527093e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1911, |
|
"loss": 1.3053, |
|
"learning_rate": 3.753694581280788e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1913, |
|
"loss": 1.435, |
|
"learning_rate": 3.724137931034482e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1915, |
|
"loss": 1.2448, |
|
"learning_rate": 3.694581280788177e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1917, |
|
"loss": 1.3858, |
|
"learning_rate": 3.665024630541872e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1919, |
|
"loss": 1.3794, |
|
"learning_rate": 3.635467980295566e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1921, |
|
"loss": 1.3404, |
|
"learning_rate": 3.6059113300492606e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1923, |
|
"loss": 1.5008, |
|
"learning_rate": 3.5763546798029553e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1925, |
|
"loss": 1.5155, |
|
"learning_rate": 3.54679802955665e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1927, |
|
"loss": 1.2666, |
|
"learning_rate": 3.517241379310344e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1929, |
|
"loss": 1.457, |
|
"learning_rate": 3.487684729064039e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1931, |
|
"loss": 1.5565, |
|
"learning_rate": 3.4581280788177336e-05, |
|
"epoch": 0.22 |
|
}, |
|
{ |
|
"current_steps": 1933, |
|
"loss": 1.3359, |
|
"learning_rate": 3.4285714285714284e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1935, |
|
"loss": 1.4157, |
|
"learning_rate": 3.399014778325123e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1937, |
|
"loss": 1.322, |
|
"learning_rate": 3.369458128078818e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1939, |
|
"loss": 1.6225, |
|
"learning_rate": 3.339901477832512e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1941, |
|
"loss": 1.4268, |
|
"learning_rate": 3.3103448275862067e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1943, |
|
"loss": 1.3425, |
|
"learning_rate": 3.2807881773399014e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1945, |
|
"loss": 1.3537, |
|
"learning_rate": 3.251231527093596e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1947, |
|
"loss": 1.3513, |
|
"learning_rate": 3.22167487684729e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1949, |
|
"loss": 1.4673, |
|
"learning_rate": 3.192118226600985e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1951, |
|
"loss": 1.4394, |
|
"learning_rate": 3.16256157635468e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1953, |
|
"loss": 1.4502, |
|
"learning_rate": 3.133004926108374e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1955, |
|
"loss": 1.415, |
|
"learning_rate": 3.1034482758620685e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1957, |
|
"loss": 1.2713, |
|
"learning_rate": 3.073891625615763e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1959, |
|
"loss": 1.2928, |
|
"learning_rate": 3.044334975369458e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1961, |
|
"loss": 1.3281, |
|
"learning_rate": 3.0147783251231524e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1963, |
|
"loss": 1.3303, |
|
"learning_rate": 2.985221674876847e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1965, |
|
"loss": 1.3034, |
|
"learning_rate": 2.955665024630542e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1967, |
|
"loss": 1.5266, |
|
"learning_rate": 2.926108374384236e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1969, |
|
"loss": 1.6226, |
|
"learning_rate": 2.8965517241379307e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1971, |
|
"loss": 1.4254, |
|
"learning_rate": 2.8669950738916254e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1973, |
|
"loss": 1.4346, |
|
"learning_rate": 2.83743842364532e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1975, |
|
"loss": 1.4151, |
|
"learning_rate": 2.8078817733990145e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1977, |
|
"loss": 1.5342, |
|
"learning_rate": 2.7783251231527093e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1979, |
|
"loss": 1.4544, |
|
"learning_rate": 2.7487684729064037e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1981, |
|
"loss": 1.2191, |
|
"learning_rate": 2.719211822660098e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1983, |
|
"loss": 1.4886, |
|
"learning_rate": 2.6896551724137928e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1985, |
|
"loss": 1.4416, |
|
"learning_rate": 2.6600985221674876e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1987, |
|
"loss": 1.3084, |
|
"learning_rate": 2.6305418719211823e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1989, |
|
"loss": 1.4037, |
|
"learning_rate": 2.6009852216748764e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1991, |
|
"loss": 1.4999, |
|
"learning_rate": 2.571428571428571e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1993, |
|
"loss": 1.3526, |
|
"learning_rate": 2.541871921182266e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1995, |
|
"loss": 1.2452, |
|
"learning_rate": 2.5123152709359602e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1997, |
|
"loss": 1.4491, |
|
"learning_rate": 2.482758620689655e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 1999, |
|
"loss": 1.5146, |
|
"learning_rate": 2.4532019704433497e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 2001, |
|
"loss": 1.3113, |
|
"learning_rate": 2.4236453201970445e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 2003, |
|
"loss": 1.4204, |
|
"learning_rate": 2.3940886699507385e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 2005, |
|
"loss": 1.4282, |
|
"learning_rate": 2.3645320197044333e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 2007, |
|
"loss": 1.2543, |
|
"learning_rate": 2.334975369458128e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 2009, |
|
"loss": 1.4168, |
|
"learning_rate": 2.3054187192118224e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 2011, |
|
"loss": 1.3244, |
|
"learning_rate": 2.275862068965517e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 2013, |
|
"loss": 1.4299, |
|
"learning_rate": 2.2463054187192116e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 2015, |
|
"loss": 1.6615, |
|
"learning_rate": 2.2167487684729063e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 2017, |
|
"loss": 1.494, |
|
"learning_rate": 2.1871921182266007e-05, |
|
"epoch": 0.23 |
|
}, |
|
{ |
|
"current_steps": 2019, |
|
"loss": 1.4014, |
|
"learning_rate": 2.1576354679802954e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2021, |
|
"loss": 1.6533, |
|
"learning_rate": 2.1280788177339902e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2023, |
|
"loss": 1.3424, |
|
"learning_rate": 2.0985221674876842e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2025, |
|
"loss": 1.2958, |
|
"learning_rate": 2.068965517241379e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2027, |
|
"loss": 1.4598, |
|
"learning_rate": 2.0394088669950737e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2029, |
|
"loss": 1.2353, |
|
"learning_rate": 2.009852216748768e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2031, |
|
"loss": 1.3546, |
|
"learning_rate": 1.980295566502463e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2033, |
|
"loss": 1.3564, |
|
"learning_rate": 1.9507389162561576e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2035, |
|
"loss": 1.374, |
|
"learning_rate": 1.9211822660098524e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2037, |
|
"loss": 1.3581, |
|
"learning_rate": 1.8916256157635464e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2039, |
|
"loss": 1.5073, |
|
"learning_rate": 1.862068965517241e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2041, |
|
"loss": 1.4059, |
|
"learning_rate": 1.832512315270936e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2043, |
|
"loss": 1.3828, |
|
"learning_rate": 1.8029556650246303e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2045, |
|
"loss": 1.4461, |
|
"learning_rate": 1.773399014778325e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2047, |
|
"loss": 1.3237, |
|
"learning_rate": 1.7438423645320194e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2049, |
|
"loss": 1.3452, |
|
"learning_rate": 1.7142857142857142e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2051, |
|
"loss": 1.3552, |
|
"learning_rate": 1.684729064039409e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2053, |
|
"loss": 1.3517, |
|
"learning_rate": 1.6551724137931033e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2055, |
|
"loss": 1.4637, |
|
"learning_rate": 1.625615763546798e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2057, |
|
"loss": 1.4506, |
|
"learning_rate": 1.5960591133004925e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2059, |
|
"loss": 1.2913, |
|
"learning_rate": 1.566502463054187e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2061, |
|
"loss": 1.4415, |
|
"learning_rate": 1.5369458128078816e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2063, |
|
"loss": 1.3982, |
|
"learning_rate": 1.5073891625615762e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2065, |
|
"loss": 1.476, |
|
"learning_rate": 1.477832512315271e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2067, |
|
"loss": 1.4763, |
|
"learning_rate": 1.4482758620689653e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2069, |
|
"loss": 1.3806, |
|
"learning_rate": 1.41871921182266e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2071, |
|
"loss": 1.6809, |
|
"learning_rate": 1.3891625615763546e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2073, |
|
"loss": 1.3225, |
|
"learning_rate": 1.359605911330049e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2075, |
|
"loss": 1.5042, |
|
"learning_rate": 1.3300492610837438e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2077, |
|
"loss": 1.3123, |
|
"learning_rate": 1.3004926108374382e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2079, |
|
"loss": 1.2716, |
|
"learning_rate": 1.270935960591133e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2081, |
|
"loss": 1.4565, |
|
"learning_rate": 1.2413793103448275e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2083, |
|
"loss": 1.268, |
|
"learning_rate": 1.2118226600985222e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2085, |
|
"loss": 1.3143, |
|
"learning_rate": 1.1822660098522166e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2087, |
|
"loss": 1.4247, |
|
"learning_rate": 1.1527093596059112e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2089, |
|
"loss": 1.3091, |
|
"learning_rate": 1.1231527093596058e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2091, |
|
"loss": 1.4655, |
|
"learning_rate": 1.0935960591133004e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2093, |
|
"loss": 1.4689, |
|
"learning_rate": 1.0640394088669951e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2095, |
|
"loss": 1.3892, |
|
"learning_rate": 1.0344827586206895e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2097, |
|
"loss": 1.2808, |
|
"learning_rate": 1.004926108374384e-05, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2099, |
|
"loss": 1.5469, |
|
"learning_rate": 9.753694581280788e-06, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2101, |
|
"loss": 1.3735, |
|
"learning_rate": 9.458128078817732e-06, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2103, |
|
"loss": 1.4516, |
|
"learning_rate": 9.16256157635468e-06, |
|
"epoch": 0.24 |
|
}, |
|
{ |
|
"current_steps": 2105, |
|
"loss": 1.2961, |
|
"learning_rate": 8.866995073891625e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2107, |
|
"loss": 1.4416, |
|
"learning_rate": 8.571428571428571e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2109, |
|
"loss": 1.309, |
|
"learning_rate": 8.275862068965517e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2111, |
|
"loss": 1.4846, |
|
"learning_rate": 7.980295566502462e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2113, |
|
"loss": 1.4353, |
|
"learning_rate": 7.684729064039408e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2115, |
|
"loss": 1.3507, |
|
"learning_rate": 7.389162561576355e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2117, |
|
"loss": 1.1822, |
|
"learning_rate": 7.0935960591133e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2119, |
|
"loss": 1.3353, |
|
"learning_rate": 6.798029556650245e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2121, |
|
"loss": 1.3504, |
|
"learning_rate": 6.502463054187191e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2123, |
|
"loss": 1.3049, |
|
"learning_rate": 6.2068965517241375e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2125, |
|
"loss": 1.4379, |
|
"learning_rate": 5.911330049261083e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2127, |
|
"loss": 1.4737, |
|
"learning_rate": 5.615763546798029e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2129, |
|
"loss": 1.4593, |
|
"learning_rate": 5.3201970443349755e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2131, |
|
"loss": 1.5299, |
|
"learning_rate": 5.02463054187192e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2133, |
|
"loss": 1.2848, |
|
"learning_rate": 4.729064039408866e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2135, |
|
"loss": 1.1764, |
|
"learning_rate": 4.433497536945813e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2137, |
|
"loss": 1.3565, |
|
"learning_rate": 4.137931034482758e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2139, |
|
"loss": 1.47, |
|
"learning_rate": 3.842364532019704e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2141, |
|
"loss": 1.4827, |
|
"learning_rate": 3.54679802955665e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2143, |
|
"loss": 1.4833, |
|
"learning_rate": 3.2512315270935955e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2145, |
|
"loss": 1.3252, |
|
"learning_rate": 2.9556650246305416e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2147, |
|
"loss": 1.4242, |
|
"learning_rate": 2.6600985221674877e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2149, |
|
"loss": 1.4473, |
|
"learning_rate": 2.364532019704433e-06, |
|
"epoch": 0.25 |
|
}, |
|
{ |
|
"current_steps": 2149, |
|
"loss": 1.4473, |
|
"learning_rate": 2.364532019704433e-06, |
|
"epoch": 0.25 |
|
} |
|
] |