HBERTv1_48_L6_H256_A4 / trainer_state.json
gokuls's picture
End of training
18c217f
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.187394389996621,
"eval_steps": 1000000,
"global_step": 436077,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 5.000000000000001e-07,
"loss": 10.2964,
"step": 500
},
{
"epoch": 0.02,
"learning_rate": 1.0000000000000002e-06,
"loss": 9.9954,
"step": 1000
},
{
"epoch": 0.03,
"learning_rate": 1.5e-06,
"loss": 9.7899,
"step": 1500
},
{
"epoch": 0.04,
"learning_rate": 2.0000000000000003e-06,
"loss": 9.5645,
"step": 2000
},
{
"epoch": 0.05,
"learning_rate": 2.5e-06,
"loss": 9.2869,
"step": 2500
},
{
"epoch": 0.06,
"learning_rate": 3e-06,
"loss": 8.9682,
"step": 3000
},
{
"epoch": 0.07,
"learning_rate": 3.5e-06,
"loss": 8.6247,
"step": 3500
},
{
"epoch": 0.08,
"learning_rate": 4.000000000000001e-06,
"loss": 8.2729,
"step": 4000
},
{
"epoch": 0.08,
"learning_rate": 4.5e-06,
"loss": 7.9409,
"step": 4500
},
{
"epoch": 0.09,
"learning_rate": 5e-06,
"loss": 7.6415,
"step": 5000
},
{
"epoch": 0.1,
"learning_rate": 5.500000000000001e-06,
"loss": 7.4069,
"step": 5500
},
{
"epoch": 0.11,
"learning_rate": 6e-06,
"loss": 7.2384,
"step": 6000
},
{
"epoch": 0.12,
"learning_rate": 6.5000000000000004e-06,
"loss": 7.1242,
"step": 6500
},
{
"epoch": 0.13,
"learning_rate": 7e-06,
"loss": 7.0509,
"step": 7000
},
{
"epoch": 0.14,
"learning_rate": 7.500000000000001e-06,
"loss": 6.9832,
"step": 7500
},
{
"epoch": 0.15,
"learning_rate": 8.000000000000001e-06,
"loss": 6.9322,
"step": 8000
},
{
"epoch": 0.16,
"learning_rate": 8.5e-06,
"loss": 6.8855,
"step": 8500
},
{
"epoch": 0.17,
"learning_rate": 9e-06,
"loss": 6.8442,
"step": 9000
},
{
"epoch": 0.18,
"learning_rate": 9.5e-06,
"loss": 6.8089,
"step": 9500
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 6.782,
"step": 10000
},
{
"epoch": 0.2,
"learning_rate": 9.999059478574923e-06,
"loss": 6.7503,
"step": 10500
},
{
"epoch": 0.21,
"learning_rate": 9.998118957149845e-06,
"loss": 6.7255,
"step": 11000
},
{
"epoch": 0.22,
"learning_rate": 9.997178435724768e-06,
"loss": 6.7089,
"step": 11500
},
{
"epoch": 0.23,
"learning_rate": 9.99623791429969e-06,
"loss": 6.6792,
"step": 12000
},
{
"epoch": 0.23,
"learning_rate": 9.99529739287461e-06,
"loss": 6.6624,
"step": 12500
},
{
"epoch": 0.24,
"learning_rate": 9.994356871449533e-06,
"loss": 6.6473,
"step": 13000
},
{
"epoch": 0.25,
"learning_rate": 9.993416350024455e-06,
"loss": 6.6272,
"step": 13500
},
{
"epoch": 0.26,
"learning_rate": 9.992475828599375e-06,
"loss": 6.6144,
"step": 14000
},
{
"epoch": 0.27,
"learning_rate": 9.991535307174298e-06,
"loss": 6.5958,
"step": 14500
},
{
"epoch": 0.28,
"learning_rate": 9.99059478574922e-06,
"loss": 6.5822,
"step": 15000
},
{
"epoch": 0.29,
"learning_rate": 9.989654264324142e-06,
"loss": 6.5724,
"step": 15500
},
{
"epoch": 0.3,
"learning_rate": 9.988713742899064e-06,
"loss": 6.5556,
"step": 16000
},
{
"epoch": 0.31,
"learning_rate": 9.987773221473987e-06,
"loss": 6.548,
"step": 16500
},
{
"epoch": 0.32,
"learning_rate": 9.986832700048909e-06,
"loss": 6.5402,
"step": 17000
},
{
"epoch": 0.33,
"learning_rate": 9.98589217862383e-06,
"loss": 6.5252,
"step": 17500
},
{
"epoch": 0.34,
"learning_rate": 9.984951657198752e-06,
"loss": 6.5188,
"step": 18000
},
{
"epoch": 0.35,
"learning_rate": 9.984011135773674e-06,
"loss": 6.5053,
"step": 18500
},
{
"epoch": 0.36,
"learning_rate": 9.983070614348596e-06,
"loss": 6.4978,
"step": 19000
},
{
"epoch": 0.37,
"learning_rate": 9.982130092923518e-06,
"loss": 6.4894,
"step": 19500
},
{
"epoch": 0.38,
"learning_rate": 9.981189571498439e-06,
"loss": 6.4767,
"step": 20000
},
{
"epoch": 0.38,
"learning_rate": 9.980249050073361e-06,
"loss": 6.4654,
"step": 20500
},
{
"epoch": 0.39,
"learning_rate": 9.979308528648283e-06,
"loss": 6.4625,
"step": 21000
},
{
"epoch": 0.4,
"learning_rate": 9.978368007223206e-06,
"loss": 6.454,
"step": 21500
},
{
"epoch": 0.41,
"learning_rate": 9.977427485798126e-06,
"loss": 6.4461,
"step": 22000
},
{
"epoch": 0.42,
"learning_rate": 9.976486964373048e-06,
"loss": 6.4384,
"step": 22500
},
{
"epoch": 0.43,
"learning_rate": 9.97554644294797e-06,
"loss": 6.4276,
"step": 23000
},
{
"epoch": 0.44,
"learning_rate": 9.974605921522893e-06,
"loss": 6.4224,
"step": 23500
},
{
"epoch": 0.45,
"learning_rate": 9.973665400097815e-06,
"loss": 6.4152,
"step": 24000
},
{
"epoch": 0.46,
"learning_rate": 9.972724878672737e-06,
"loss": 6.4087,
"step": 24500
},
{
"epoch": 0.47,
"learning_rate": 9.97178435724766e-06,
"loss": 6.4084,
"step": 25000
},
{
"epoch": 0.48,
"learning_rate": 9.970843835822582e-06,
"loss": 6.3935,
"step": 25500
},
{
"epoch": 0.49,
"learning_rate": 9.969903314397504e-06,
"loss": 6.3907,
"step": 26000
},
{
"epoch": 0.5,
"learning_rate": 9.968962792972425e-06,
"loss": 6.388,
"step": 26500
},
{
"epoch": 0.51,
"learning_rate": 9.968022271547347e-06,
"loss": 6.3794,
"step": 27000
},
{
"epoch": 0.52,
"learning_rate": 9.967081750122269e-06,
"loss": 6.372,
"step": 27500
},
{
"epoch": 0.53,
"learning_rate": 9.96614122869719e-06,
"loss": 6.3684,
"step": 28000
},
{
"epoch": 0.54,
"learning_rate": 9.965200707272112e-06,
"loss": 6.3621,
"step": 28500
},
{
"epoch": 0.54,
"learning_rate": 9.964260185847034e-06,
"loss": 6.3588,
"step": 29000
},
{
"epoch": 0.55,
"learning_rate": 9.963319664421956e-06,
"loss": 6.3554,
"step": 29500
},
{
"epoch": 0.56,
"learning_rate": 9.962379142996879e-06,
"loss": 6.3447,
"step": 30000
},
{
"epoch": 0.57,
"learning_rate": 9.961438621571801e-06,
"loss": 6.3408,
"step": 30500
},
{
"epoch": 0.58,
"learning_rate": 9.960498100146723e-06,
"loss": 6.3407,
"step": 31000
},
{
"epoch": 0.59,
"learning_rate": 9.959557578721644e-06,
"loss": 6.3334,
"step": 31500
},
{
"epoch": 0.6,
"learning_rate": 9.958617057296566e-06,
"loss": 6.3301,
"step": 32000
},
{
"epoch": 0.61,
"learning_rate": 9.957676535871488e-06,
"loss": 6.3263,
"step": 32500
},
{
"epoch": 0.62,
"learning_rate": 9.95673601444641e-06,
"loss": 6.3176,
"step": 33000
},
{
"epoch": 0.63,
"learning_rate": 9.955795493021333e-06,
"loss": 6.3177,
"step": 33500
},
{
"epoch": 0.64,
"learning_rate": 9.954854971596253e-06,
"loss": 6.3101,
"step": 34000
},
{
"epoch": 0.65,
"learning_rate": 9.953914450171175e-06,
"loss": 6.3095,
"step": 34500
},
{
"epoch": 0.66,
"learning_rate": 9.952973928746098e-06,
"loss": 6.3072,
"step": 35000
},
{
"epoch": 0.67,
"learning_rate": 9.95203340732102e-06,
"loss": 6.3014,
"step": 35500
},
{
"epoch": 0.68,
"learning_rate": 9.95109288589594e-06,
"loss": 6.2963,
"step": 36000
},
{
"epoch": 0.69,
"learning_rate": 9.950152364470863e-06,
"loss": 6.2912,
"step": 36500
},
{
"epoch": 0.69,
"learning_rate": 9.949211843045785e-06,
"loss": 6.2908,
"step": 37000
},
{
"epoch": 0.7,
"learning_rate": 9.948271321620707e-06,
"loss": 6.2843,
"step": 37500
},
{
"epoch": 0.71,
"learning_rate": 9.94733080019563e-06,
"loss": 6.2769,
"step": 38000
},
{
"epoch": 0.72,
"learning_rate": 9.946390278770552e-06,
"loss": 6.2772,
"step": 38500
},
{
"epoch": 0.73,
"learning_rate": 9.945449757345474e-06,
"loss": 6.2736,
"step": 39000
},
{
"epoch": 0.74,
"learning_rate": 9.944509235920396e-06,
"loss": 6.2716,
"step": 39500
},
{
"epoch": 0.75,
"learning_rate": 9.943568714495317e-06,
"loss": 6.2665,
"step": 40000
},
{
"epoch": 0.76,
"learning_rate": 9.942628193070239e-06,
"loss": 6.2665,
"step": 40500
},
{
"epoch": 0.77,
"learning_rate": 9.941687671645161e-06,
"loss": 6.2649,
"step": 41000
},
{
"epoch": 0.78,
"learning_rate": 9.940747150220082e-06,
"loss": 6.2578,
"step": 41500
},
{
"epoch": 0.79,
"learning_rate": 9.939806628795004e-06,
"loss": 6.2538,
"step": 42000
},
{
"epoch": 0.8,
"learning_rate": 9.938866107369926e-06,
"loss": 6.2555,
"step": 42500
},
{
"epoch": 0.81,
"learning_rate": 9.937925585944848e-06,
"loss": 6.2504,
"step": 43000
},
{
"epoch": 0.82,
"learning_rate": 9.93698506451977e-06,
"loss": 6.2505,
"step": 43500
},
{
"epoch": 0.83,
"learning_rate": 9.936044543094693e-06,
"loss": 6.243,
"step": 44000
},
{
"epoch": 0.84,
"learning_rate": 9.935104021669615e-06,
"loss": 6.239,
"step": 44500
},
{
"epoch": 0.84,
"learning_rate": 9.934163500244537e-06,
"loss": 6.2412,
"step": 45000
},
{
"epoch": 0.85,
"learning_rate": 9.933222978819458e-06,
"loss": 6.2346,
"step": 45500
},
{
"epoch": 0.86,
"learning_rate": 9.93228245739438e-06,
"loss": 6.2309,
"step": 46000
},
{
"epoch": 0.87,
"learning_rate": 9.931341935969302e-06,
"loss": 6.2338,
"step": 46500
},
{
"epoch": 0.88,
"learning_rate": 9.930401414544225e-06,
"loss": 6.2331,
"step": 47000
},
{
"epoch": 0.89,
"learning_rate": 9.929460893119145e-06,
"loss": 6.2272,
"step": 47500
},
{
"epoch": 0.9,
"learning_rate": 9.928520371694067e-06,
"loss": 6.2253,
"step": 48000
},
{
"epoch": 0.91,
"learning_rate": 9.92757985026899e-06,
"loss": 6.2231,
"step": 48500
},
{
"epoch": 0.92,
"learning_rate": 9.926639328843912e-06,
"loss": 6.2282,
"step": 49000
},
{
"epoch": 0.93,
"learning_rate": 9.925698807418834e-06,
"loss": 6.2167,
"step": 49500
},
{
"epoch": 0.94,
"learning_rate": 9.924758285993755e-06,
"loss": 6.219,
"step": 50000
},
{
"epoch": 0.95,
"learning_rate": 9.923817764568677e-06,
"loss": 6.2201,
"step": 50500
},
{
"epoch": 0.96,
"learning_rate": 9.9228772431436e-06,
"loss": 6.2167,
"step": 51000
},
{
"epoch": 0.97,
"learning_rate": 9.921936721718521e-06,
"loss": 6.2066,
"step": 51500
},
{
"epoch": 0.98,
"learning_rate": 9.920996200293444e-06,
"loss": 6.2149,
"step": 52000
},
{
"epoch": 0.99,
"learning_rate": 9.920055678868366e-06,
"loss": 6.2071,
"step": 52500
},
{
"epoch": 1.0,
"learning_rate": 9.919115157443288e-06,
"loss": 6.2071,
"step": 53000
},
{
"epoch": 1.0,
"learning_rate": 9.91817463601821e-06,
"loss": 6.2037,
"step": 53500
},
{
"epoch": 1.01,
"learning_rate": 9.917234114593131e-06,
"loss": 6.2028,
"step": 54000
},
{
"epoch": 1.02,
"learning_rate": 9.916293593168053e-06,
"loss": 6.1999,
"step": 54500
},
{
"epoch": 1.03,
"learning_rate": 9.915353071742975e-06,
"loss": 6.1982,
"step": 55000
},
{
"epoch": 1.04,
"learning_rate": 9.914412550317896e-06,
"loss": 6.1912,
"step": 55500
},
{
"epoch": 1.05,
"learning_rate": 9.913472028892818e-06,
"loss": 6.1919,
"step": 56000
},
{
"epoch": 1.06,
"learning_rate": 9.91253150746774e-06,
"loss": 6.1895,
"step": 56500
},
{
"epoch": 1.07,
"learning_rate": 9.911590986042663e-06,
"loss": 6.1902,
"step": 57000
},
{
"epoch": 1.08,
"learning_rate": 9.910650464617585e-06,
"loss": 6.1867,
"step": 57500
},
{
"epoch": 1.09,
"learning_rate": 9.909709943192507e-06,
"loss": 6.1875,
"step": 58000
},
{
"epoch": 1.1,
"learning_rate": 9.90876942176743e-06,
"loss": 6.1861,
"step": 58500
},
{
"epoch": 1.11,
"learning_rate": 9.907828900342352e-06,
"loss": 6.1794,
"step": 59000
},
{
"epoch": 1.12,
"learning_rate": 9.906888378917272e-06,
"loss": 6.1791,
"step": 59500
},
{
"epoch": 1.13,
"learning_rate": 9.905947857492194e-06,
"loss": 6.1775,
"step": 60000
},
{
"epoch": 1.14,
"learning_rate": 9.905007336067117e-06,
"loss": 6.1779,
"step": 60500
},
{
"epoch": 1.15,
"learning_rate": 9.904066814642039e-06,
"loss": 6.177,
"step": 61000
},
{
"epoch": 1.15,
"learning_rate": 9.90312629321696e-06,
"loss": 6.1744,
"step": 61500
},
{
"epoch": 1.16,
"learning_rate": 9.902185771791882e-06,
"loss": 6.1684,
"step": 62000
},
{
"epoch": 1.17,
"learning_rate": 9.901245250366804e-06,
"loss": 6.1744,
"step": 62500
},
{
"epoch": 1.18,
"learning_rate": 9.900304728941726e-06,
"loss": 6.1639,
"step": 63000
},
{
"epoch": 1.19,
"learning_rate": 9.899364207516648e-06,
"loss": 6.164,
"step": 63500
},
{
"epoch": 1.2,
"learning_rate": 9.898423686091569e-06,
"loss": 6.1651,
"step": 64000
},
{
"epoch": 1.21,
"learning_rate": 9.897483164666491e-06,
"loss": 6.1586,
"step": 64500
},
{
"epoch": 1.22,
"learning_rate": 9.896542643241414e-06,
"loss": 6.1612,
"step": 65000
},
{
"epoch": 1.23,
"learning_rate": 9.895602121816336e-06,
"loss": 6.155,
"step": 65500
},
{
"epoch": 1.24,
"learning_rate": 9.894661600391258e-06,
"loss": 6.1565,
"step": 66000
},
{
"epoch": 1.25,
"learning_rate": 9.89372107896618e-06,
"loss": 6.1531,
"step": 66500
},
{
"epoch": 1.26,
"learning_rate": 9.892780557541102e-06,
"loss": 6.1569,
"step": 67000
},
{
"epoch": 1.27,
"learning_rate": 9.891840036116023e-06,
"loss": 6.1588,
"step": 67500
},
{
"epoch": 1.28,
"learning_rate": 9.890899514690945e-06,
"loss": 6.1535,
"step": 68000
},
{
"epoch": 1.29,
"learning_rate": 9.889958993265868e-06,
"loss": 6.1559,
"step": 68500
},
{
"epoch": 1.3,
"learning_rate": 9.889018471840788e-06,
"loss": 6.1534,
"step": 69000
},
{
"epoch": 1.3,
"learning_rate": 9.88807795041571e-06,
"loss": 6.1497,
"step": 69500
},
{
"epoch": 1.31,
"learning_rate": 9.887137428990633e-06,
"loss": 6.1505,
"step": 70000
},
{
"epoch": 1.32,
"learning_rate": 9.886196907565555e-06,
"loss": 6.1422,
"step": 70500
},
{
"epoch": 1.33,
"learning_rate": 9.885256386140477e-06,
"loss": 6.1485,
"step": 71000
},
{
"epoch": 1.34,
"learning_rate": 9.8843158647154e-06,
"loss": 6.142,
"step": 71500
},
{
"epoch": 1.35,
"learning_rate": 9.883375343290322e-06,
"loss": 6.1431,
"step": 72000
},
{
"epoch": 1.36,
"learning_rate": 9.882434821865244e-06,
"loss": 6.1408,
"step": 72500
},
{
"epoch": 1.37,
"learning_rate": 9.881494300440166e-06,
"loss": 6.1361,
"step": 73000
},
{
"epoch": 1.38,
"learning_rate": 9.880553779015087e-06,
"loss": 6.1371,
"step": 73500
},
{
"epoch": 1.39,
"learning_rate": 9.879613257590009e-06,
"loss": 6.1377,
"step": 74000
},
{
"epoch": 1.4,
"learning_rate": 9.878672736164931e-06,
"loss": 6.1405,
"step": 74500
},
{
"epoch": 1.41,
"learning_rate": 9.877732214739853e-06,
"loss": 6.1327,
"step": 75000
},
{
"epoch": 1.42,
"learning_rate": 9.876791693314774e-06,
"loss": 6.1328,
"step": 75500
},
{
"epoch": 1.43,
"learning_rate": 9.875851171889696e-06,
"loss": 6.1296,
"step": 76000
},
{
"epoch": 1.44,
"learning_rate": 9.874910650464618e-06,
"loss": 6.1355,
"step": 76500
},
{
"epoch": 1.45,
"learning_rate": 9.87397012903954e-06,
"loss": 6.1347,
"step": 77000
},
{
"epoch": 1.46,
"learning_rate": 9.873029607614463e-06,
"loss": 6.1301,
"step": 77500
},
{
"epoch": 1.46,
"learning_rate": 9.872089086189383e-06,
"loss": 6.1269,
"step": 78000
},
{
"epoch": 1.47,
"learning_rate": 9.871148564764306e-06,
"loss": 6.1258,
"step": 78500
},
{
"epoch": 1.48,
"learning_rate": 9.870208043339228e-06,
"loss": 6.1257,
"step": 79000
},
{
"epoch": 1.49,
"learning_rate": 9.86926752191415e-06,
"loss": 6.1208,
"step": 79500
},
{
"epoch": 1.5,
"learning_rate": 9.868327000489072e-06,
"loss": 6.1202,
"step": 80000
},
{
"epoch": 1.51,
"learning_rate": 9.867386479063995e-06,
"loss": 6.1194,
"step": 80500
},
{
"epoch": 1.52,
"learning_rate": 9.866445957638917e-06,
"loss": 6.117,
"step": 81000
},
{
"epoch": 1.53,
"learning_rate": 9.865505436213837e-06,
"loss": 6.1202,
"step": 81500
},
{
"epoch": 1.54,
"learning_rate": 9.86456491478876e-06,
"loss": 6.116,
"step": 82000
},
{
"epoch": 1.55,
"learning_rate": 9.863624393363682e-06,
"loss": 6.1205,
"step": 82500
},
{
"epoch": 1.56,
"learning_rate": 9.862683871938602e-06,
"loss": 6.1232,
"step": 83000
},
{
"epoch": 1.57,
"learning_rate": 9.861743350513525e-06,
"loss": 6.1144,
"step": 83500
},
{
"epoch": 1.58,
"learning_rate": 9.860802829088447e-06,
"loss": 6.116,
"step": 84000
},
{
"epoch": 1.59,
"learning_rate": 9.859862307663369e-06,
"loss": 6.1121,
"step": 84500
},
{
"epoch": 1.6,
"learning_rate": 9.858921786238291e-06,
"loss": 6.1157,
"step": 85000
},
{
"epoch": 1.61,
"learning_rate": 9.857981264813214e-06,
"loss": 6.115,
"step": 85500
},
{
"epoch": 1.61,
"learning_rate": 9.857040743388136e-06,
"loss": 6.1151,
"step": 86000
},
{
"epoch": 1.62,
"learning_rate": 9.856100221963058e-06,
"loss": 6.1069,
"step": 86500
},
{
"epoch": 1.63,
"learning_rate": 9.85515970053798e-06,
"loss": 6.1096,
"step": 87000
},
{
"epoch": 1.64,
"learning_rate": 9.854219179112901e-06,
"loss": 6.109,
"step": 87500
},
{
"epoch": 1.65,
"learning_rate": 9.853278657687823e-06,
"loss": 6.1072,
"step": 88000
},
{
"epoch": 1.66,
"learning_rate": 9.852338136262745e-06,
"loss": 6.1062,
"step": 88500
},
{
"epoch": 1.67,
"learning_rate": 9.851397614837666e-06,
"loss": 6.104,
"step": 89000
},
{
"epoch": 1.68,
"learning_rate": 9.850457093412588e-06,
"loss": 6.1095,
"step": 89500
},
{
"epoch": 1.69,
"learning_rate": 9.84951657198751e-06,
"loss": 6.1034,
"step": 90000
},
{
"epoch": 1.7,
"learning_rate": 9.848576050562433e-06,
"loss": 6.0996,
"step": 90500
},
{
"epoch": 1.71,
"learning_rate": 9.847635529137355e-06,
"loss": 6.1052,
"step": 91000
},
{
"epoch": 1.72,
"learning_rate": 9.846695007712277e-06,
"loss": 6.1022,
"step": 91500
},
{
"epoch": 1.73,
"learning_rate": 9.845754486287198e-06,
"loss": 6.1006,
"step": 92000
},
{
"epoch": 1.74,
"learning_rate": 9.84481396486212e-06,
"loss": 6.1033,
"step": 92500
},
{
"epoch": 1.75,
"learning_rate": 9.843873443437042e-06,
"loss": 6.1,
"step": 93000
},
{
"epoch": 1.76,
"learning_rate": 9.842932922011964e-06,
"loss": 6.0979,
"step": 93500
},
{
"epoch": 1.76,
"learning_rate": 9.841992400586887e-06,
"loss": 6.0964,
"step": 94000
},
{
"epoch": 1.77,
"learning_rate": 9.841051879161809e-06,
"loss": 6.0965,
"step": 94500
},
{
"epoch": 1.78,
"learning_rate": 9.84011135773673e-06,
"loss": 6.092,
"step": 95000
},
{
"epoch": 1.79,
"learning_rate": 9.839170836311652e-06,
"loss": 6.0946,
"step": 95500
},
{
"epoch": 1.8,
"learning_rate": 9.838230314886574e-06,
"loss": 6.0942,
"step": 96000
},
{
"epoch": 1.81,
"learning_rate": 9.837289793461496e-06,
"loss": 6.0951,
"step": 96500
},
{
"epoch": 1.82,
"learning_rate": 9.836349272036417e-06,
"loss": 6.0945,
"step": 97000
},
{
"epoch": 1.83,
"learning_rate": 9.835408750611339e-06,
"loss": 6.0921,
"step": 97500
},
{
"epoch": 1.84,
"learning_rate": 9.834468229186261e-06,
"loss": 6.0934,
"step": 98000
},
{
"epoch": 1.85,
"learning_rate": 9.833527707761183e-06,
"loss": 6.0904,
"step": 98500
},
{
"epoch": 1.86,
"learning_rate": 9.832587186336106e-06,
"loss": 6.0887,
"step": 99000
},
{
"epoch": 1.87,
"learning_rate": 9.831646664911028e-06,
"loss": 6.0897,
"step": 99500
},
{
"epoch": 1.88,
"learning_rate": 9.83070614348595e-06,
"loss": 6.091,
"step": 100000
},
{
"epoch": 1.89,
"learning_rate": 9.829765622060872e-06,
"loss": 6.0868,
"step": 100500
},
{
"epoch": 1.9,
"learning_rate": 9.828825100635795e-06,
"loss": 6.0867,
"step": 101000
},
{
"epoch": 1.91,
"learning_rate": 9.827884579210715e-06,
"loss": 6.0859,
"step": 101500
},
{
"epoch": 1.92,
"learning_rate": 9.826944057785637e-06,
"loss": 6.0837,
"step": 102000
},
{
"epoch": 1.92,
"learning_rate": 9.82600353636056e-06,
"loss": 6.0843,
"step": 102500
},
{
"epoch": 1.93,
"learning_rate": 9.82506301493548e-06,
"loss": 6.0876,
"step": 103000
},
{
"epoch": 1.94,
"learning_rate": 9.824122493510402e-06,
"loss": 6.0808,
"step": 103500
},
{
"epoch": 1.95,
"learning_rate": 9.823181972085325e-06,
"loss": 6.0833,
"step": 104000
},
{
"epoch": 1.96,
"learning_rate": 9.822241450660247e-06,
"loss": 6.08,
"step": 104500
},
{
"epoch": 1.97,
"learning_rate": 9.821300929235169e-06,
"loss": 6.0788,
"step": 105000
},
{
"epoch": 1.98,
"learning_rate": 9.820360407810091e-06,
"loss": 6.0789,
"step": 105500
},
{
"epoch": 1.99,
"learning_rate": 9.819419886385014e-06,
"loss": 6.0756,
"step": 106000
},
{
"epoch": 2.0,
"learning_rate": 9.818479364959934e-06,
"loss": 6.0802,
"step": 106500
},
{
"epoch": 2.01,
"learning_rate": 9.817538843534856e-06,
"loss": 6.0757,
"step": 107000
},
{
"epoch": 2.02,
"learning_rate": 9.816598322109779e-06,
"loss": 6.0776,
"step": 107500
},
{
"epoch": 2.03,
"learning_rate": 9.815657800684701e-06,
"loss": 6.0726,
"step": 108000
},
{
"epoch": 2.04,
"learning_rate": 9.814717279259623e-06,
"loss": 6.0776,
"step": 108500
},
{
"epoch": 2.05,
"learning_rate": 9.813776757834544e-06,
"loss": 6.0742,
"step": 109000
},
{
"epoch": 2.06,
"learning_rate": 9.812836236409466e-06,
"loss": 6.0712,
"step": 109500
},
{
"epoch": 2.07,
"learning_rate": 9.811895714984388e-06,
"loss": 6.0709,
"step": 110000
},
{
"epoch": 2.07,
"learning_rate": 9.81095519355931e-06,
"loss": 6.0764,
"step": 110500
},
{
"epoch": 2.08,
"learning_rate": 9.810014672134231e-06,
"loss": 6.0717,
"step": 111000
},
{
"epoch": 2.09,
"learning_rate": 9.809074150709153e-06,
"loss": 6.0683,
"step": 111500
},
{
"epoch": 2.1,
"learning_rate": 9.808133629284075e-06,
"loss": 6.073,
"step": 112000
},
{
"epoch": 2.11,
"learning_rate": 9.807193107858998e-06,
"loss": 6.072,
"step": 112500
},
{
"epoch": 2.12,
"learning_rate": 9.80625258643392e-06,
"loss": 6.0699,
"step": 113000
},
{
"epoch": 2.13,
"learning_rate": 9.805312065008842e-06,
"loss": 6.0697,
"step": 113500
},
{
"epoch": 2.14,
"learning_rate": 9.804371543583764e-06,
"loss": 6.0657,
"step": 114000
},
{
"epoch": 2.15,
"learning_rate": 9.803431022158687e-06,
"loss": 6.0678,
"step": 114500
},
{
"epoch": 2.16,
"learning_rate": 9.802490500733607e-06,
"loss": 6.0656,
"step": 115000
},
{
"epoch": 2.17,
"learning_rate": 9.80154997930853e-06,
"loss": 6.0705,
"step": 115500
},
{
"epoch": 2.18,
"learning_rate": 9.800609457883452e-06,
"loss": 6.0656,
"step": 116000
},
{
"epoch": 2.19,
"learning_rate": 9.799668936458372e-06,
"loss": 6.0693,
"step": 116500
},
{
"epoch": 2.2,
"learning_rate": 9.798728415033294e-06,
"loss": 6.0674,
"step": 117000
},
{
"epoch": 2.21,
"learning_rate": 9.797787893608217e-06,
"loss": 6.0626,
"step": 117500
},
{
"epoch": 2.22,
"learning_rate": 9.796847372183139e-06,
"loss": 6.0638,
"step": 118000
},
{
"epoch": 2.22,
"learning_rate": 9.795906850758061e-06,
"loss": 6.0691,
"step": 118500
},
{
"epoch": 2.23,
"learning_rate": 9.794966329332983e-06,
"loss": 6.0599,
"step": 119000
},
{
"epoch": 2.24,
"learning_rate": 9.794025807907906e-06,
"loss": 6.0595,
"step": 119500
},
{
"epoch": 2.25,
"learning_rate": 9.793085286482828e-06,
"loss": 6.0627,
"step": 120000
},
{
"epoch": 2.26,
"learning_rate": 9.792144765057748e-06,
"loss": 6.0604,
"step": 120500
},
{
"epoch": 2.27,
"learning_rate": 9.79120424363267e-06,
"loss": 6.0594,
"step": 121000
},
{
"epoch": 2.28,
"learning_rate": 9.790263722207593e-06,
"loss": 6.0652,
"step": 121500
},
{
"epoch": 2.29,
"learning_rate": 9.789323200782515e-06,
"loss": 6.0599,
"step": 122000
},
{
"epoch": 2.3,
"learning_rate": 9.788382679357436e-06,
"loss": 6.0613,
"step": 122500
},
{
"epoch": 2.31,
"learning_rate": 9.787442157932358e-06,
"loss": 6.0596,
"step": 123000
},
{
"epoch": 2.32,
"learning_rate": 9.78650163650728e-06,
"loss": 6.0586,
"step": 123500
},
{
"epoch": 2.33,
"learning_rate": 9.785561115082202e-06,
"loss": 6.0568,
"step": 124000
},
{
"epoch": 2.34,
"learning_rate": 9.784620593657125e-06,
"loss": 6.0595,
"step": 124500
},
{
"epoch": 2.35,
"learning_rate": 9.783680072232045e-06,
"loss": 6.058,
"step": 125000
},
{
"epoch": 2.36,
"learning_rate": 9.782739550806967e-06,
"loss": 6.059,
"step": 125500
},
{
"epoch": 2.37,
"learning_rate": 9.78179902938189e-06,
"loss": 6.0535,
"step": 126000
},
{
"epoch": 2.38,
"learning_rate": 9.780858507956812e-06,
"loss": 6.0562,
"step": 126500
},
{
"epoch": 2.38,
"learning_rate": 9.779917986531734e-06,
"loss": 6.0533,
"step": 127000
},
{
"epoch": 2.39,
"learning_rate": 9.778977465106656e-06,
"loss": 6.0524,
"step": 127500
},
{
"epoch": 2.4,
"learning_rate": 9.778036943681579e-06,
"loss": 6.0568,
"step": 128000
},
{
"epoch": 2.41,
"learning_rate": 9.777096422256501e-06,
"loss": 6.0528,
"step": 128500
},
{
"epoch": 2.42,
"learning_rate": 9.776155900831421e-06,
"loss": 6.0535,
"step": 129000
},
{
"epoch": 2.43,
"learning_rate": 9.775215379406344e-06,
"loss": 6.051,
"step": 129500
},
{
"epoch": 2.44,
"learning_rate": 9.774274857981266e-06,
"loss": 6.0503,
"step": 130000
},
{
"epoch": 2.45,
"learning_rate": 9.773334336556187e-06,
"loss": 6.0471,
"step": 130500
},
{
"epoch": 2.46,
"learning_rate": 9.772393815131109e-06,
"loss": 6.0495,
"step": 131000
},
{
"epoch": 2.47,
"learning_rate": 9.771453293706031e-06,
"loss": 6.0486,
"step": 131500
},
{
"epoch": 2.48,
"learning_rate": 9.770512772280953e-06,
"loss": 6.0511,
"step": 132000
},
{
"epoch": 2.49,
"learning_rate": 9.769572250855875e-06,
"loss": 6.0477,
"step": 132500
},
{
"epoch": 2.5,
"learning_rate": 9.768631729430798e-06,
"loss": 6.0516,
"step": 133000
},
{
"epoch": 2.51,
"learning_rate": 9.76769120800572e-06,
"loss": 6.0459,
"step": 133500
},
{
"epoch": 2.52,
"learning_rate": 9.766750686580642e-06,
"loss": 6.0446,
"step": 134000
},
{
"epoch": 2.53,
"learning_rate": 9.765810165155563e-06,
"loss": 6.0452,
"step": 134500
},
{
"epoch": 2.53,
"learning_rate": 9.764869643730485e-06,
"loss": 6.0472,
"step": 135000
},
{
"epoch": 2.54,
"learning_rate": 9.763929122305407e-06,
"loss": 6.0451,
"step": 135500
},
{
"epoch": 2.55,
"learning_rate": 9.76298860088033e-06,
"loss": 6.0451,
"step": 136000
},
{
"epoch": 2.56,
"learning_rate": 9.76204807945525e-06,
"loss": 6.0415,
"step": 136500
},
{
"epoch": 2.57,
"learning_rate": 9.761107558030172e-06,
"loss": 6.047,
"step": 137000
},
{
"epoch": 2.58,
"learning_rate": 9.760167036605095e-06,
"loss": 6.0397,
"step": 137500
},
{
"epoch": 2.59,
"learning_rate": 9.759226515180017e-06,
"loss": 6.0414,
"step": 138000
},
{
"epoch": 2.6,
"learning_rate": 9.758285993754939e-06,
"loss": 6.0401,
"step": 138500
},
{
"epoch": 2.61,
"learning_rate": 9.75734547232986e-06,
"loss": 6.0422,
"step": 139000
},
{
"epoch": 2.62,
"learning_rate": 9.756404950904782e-06,
"loss": 6.0438,
"step": 139500
},
{
"epoch": 2.63,
"learning_rate": 9.755464429479704e-06,
"loss": 6.0437,
"step": 140000
},
{
"epoch": 2.64,
"learning_rate": 9.754523908054626e-06,
"loss": 6.0382,
"step": 140500
},
{
"epoch": 2.65,
"learning_rate": 9.753583386629549e-06,
"loss": 6.0407,
"step": 141000
},
{
"epoch": 2.66,
"learning_rate": 9.75264286520447e-06,
"loss": 6.0355,
"step": 141500
},
{
"epoch": 2.67,
"learning_rate": 9.751702343779393e-06,
"loss": 6.0388,
"step": 142000
},
{
"epoch": 2.68,
"learning_rate": 9.750761822354314e-06,
"loss": 6.0384,
"step": 142500
},
{
"epoch": 2.68,
"learning_rate": 9.749821300929236e-06,
"loss": 6.0418,
"step": 143000
},
{
"epoch": 2.69,
"learning_rate": 9.748880779504158e-06,
"loss": 6.0371,
"step": 143500
},
{
"epoch": 2.7,
"learning_rate": 9.747940258079079e-06,
"loss": 6.0386,
"step": 144000
},
{
"epoch": 2.71,
"learning_rate": 9.746999736654e-06,
"loss": 6.0355,
"step": 144500
},
{
"epoch": 2.72,
"learning_rate": 9.746059215228923e-06,
"loss": 6.0379,
"step": 145000
},
{
"epoch": 2.73,
"learning_rate": 9.745118693803845e-06,
"loss": 6.0347,
"step": 145500
},
{
"epoch": 2.74,
"learning_rate": 9.744178172378768e-06,
"loss": 6.0336,
"step": 146000
},
{
"epoch": 2.75,
"learning_rate": 9.74323765095369e-06,
"loss": 6.0376,
"step": 146500
},
{
"epoch": 2.76,
"learning_rate": 9.742297129528612e-06,
"loss": 6.0349,
"step": 147000
},
{
"epoch": 2.77,
"learning_rate": 9.741356608103534e-06,
"loss": 6.0293,
"step": 147500
},
{
"epoch": 2.78,
"learning_rate": 9.740416086678457e-06,
"loss": 6.0392,
"step": 148000
},
{
"epoch": 2.79,
"learning_rate": 9.739475565253377e-06,
"loss": 6.033,
"step": 148500
},
{
"epoch": 2.8,
"learning_rate": 9.7385350438283e-06,
"loss": 6.0328,
"step": 149000
},
{
"epoch": 2.81,
"learning_rate": 9.737594522403222e-06,
"loss": 6.0302,
"step": 149500
},
{
"epoch": 2.82,
"learning_rate": 9.736654000978144e-06,
"loss": 6.032,
"step": 150000
},
{
"epoch": 2.83,
"learning_rate": 9.735713479553064e-06,
"loss": 6.0353,
"step": 150500
},
{
"epoch": 2.84,
"learning_rate": 9.734772958127987e-06,
"loss": 6.0347,
"step": 151000
},
{
"epoch": 2.84,
"learning_rate": 9.733832436702909e-06,
"loss": 6.0323,
"step": 151500
},
{
"epoch": 2.85,
"learning_rate": 9.732891915277831e-06,
"loss": 6.0281,
"step": 152000
},
{
"epoch": 2.86,
"learning_rate": 9.731951393852753e-06,
"loss": 6.0294,
"step": 152500
},
{
"epoch": 2.87,
"learning_rate": 9.731010872427674e-06,
"loss": 6.0259,
"step": 153000
},
{
"epoch": 2.88,
"learning_rate": 9.730070351002596e-06,
"loss": 6.0255,
"step": 153500
},
{
"epoch": 2.89,
"learning_rate": 9.729129829577518e-06,
"loss": 6.0274,
"step": 154000
},
{
"epoch": 2.9,
"learning_rate": 9.72818930815244e-06,
"loss": 6.0272,
"step": 154500
},
{
"epoch": 2.91,
"learning_rate": 9.727248786727363e-06,
"loss": 6.025,
"step": 155000
},
{
"epoch": 2.92,
"learning_rate": 9.726308265302285e-06,
"loss": 6.0242,
"step": 155500
},
{
"epoch": 2.93,
"learning_rate": 9.725367743877207e-06,
"loss": 6.0291,
"step": 156000
},
{
"epoch": 2.94,
"learning_rate": 9.724427222452128e-06,
"loss": 6.0261,
"step": 156500
},
{
"epoch": 2.95,
"learning_rate": 9.72348670102705e-06,
"loss": 6.0268,
"step": 157000
},
{
"epoch": 2.96,
"learning_rate": 9.722546179601972e-06,
"loss": 6.0249,
"step": 157500
},
{
"epoch": 2.97,
"learning_rate": 9.721605658176893e-06,
"loss": 6.0282,
"step": 158000
},
{
"epoch": 2.98,
"learning_rate": 9.720665136751815e-06,
"loss": 6.0259,
"step": 158500
},
{
"epoch": 2.99,
"learning_rate": 9.719724615326737e-06,
"loss": 6.0247,
"step": 159000
},
{
"epoch": 2.99,
"learning_rate": 9.71878409390166e-06,
"loss": 6.023,
"step": 159500
},
{
"epoch": 3.0,
"learning_rate": 9.717843572476582e-06,
"loss": 6.0228,
"step": 160000
},
{
"epoch": 3.01,
"learning_rate": 9.716903051051504e-06,
"loss": 6.0235,
"step": 160500
},
{
"epoch": 3.02,
"learning_rate": 9.715962529626426e-06,
"loss": 6.0242,
"step": 161000
},
{
"epoch": 3.03,
"learning_rate": 9.715022008201349e-06,
"loss": 6.0255,
"step": 161500
},
{
"epoch": 3.04,
"learning_rate": 9.71408148677627e-06,
"loss": 6.0262,
"step": 162000
},
{
"epoch": 3.05,
"learning_rate": 9.713140965351191e-06,
"loss": 6.0201,
"step": 162500
},
{
"epoch": 3.06,
"learning_rate": 9.712200443926114e-06,
"loss": 6.0228,
"step": 163000
},
{
"epoch": 3.07,
"learning_rate": 9.711259922501036e-06,
"loss": 6.0255,
"step": 163500
},
{
"epoch": 3.08,
"learning_rate": 9.710319401075956e-06,
"loss": 6.0206,
"step": 164000
},
{
"epoch": 3.09,
"learning_rate": 9.709378879650879e-06,
"loss": 6.0158,
"step": 164500
},
{
"epoch": 3.1,
"learning_rate": 9.708438358225801e-06,
"loss": 6.0223,
"step": 165000
},
{
"epoch": 3.11,
"learning_rate": 9.707497836800723e-06,
"loss": 6.0168,
"step": 165500
},
{
"epoch": 3.12,
"learning_rate": 9.706557315375645e-06,
"loss": 6.0238,
"step": 166000
},
{
"epoch": 3.13,
"learning_rate": 9.705616793950568e-06,
"loss": 6.0204,
"step": 166500
},
{
"epoch": 3.14,
"learning_rate": 9.704676272525488e-06,
"loss": 6.017,
"step": 167000
},
{
"epoch": 3.14,
"learning_rate": 9.70373575110041e-06,
"loss": 6.0167,
"step": 167500
},
{
"epoch": 3.15,
"learning_rate": 9.702795229675333e-06,
"loss": 6.0168,
"step": 168000
},
{
"epoch": 3.16,
"learning_rate": 9.701854708250255e-06,
"loss": 6.021,
"step": 168500
},
{
"epoch": 3.17,
"learning_rate": 9.700914186825177e-06,
"loss": 6.0146,
"step": 169000
},
{
"epoch": 3.18,
"learning_rate": 9.6999736654001e-06,
"loss": 6.0218,
"step": 169500
},
{
"epoch": 3.19,
"learning_rate": 9.69903314397502e-06,
"loss": 6.0187,
"step": 170000
},
{
"epoch": 3.2,
"learning_rate": 9.698092622549942e-06,
"loss": 6.0206,
"step": 170500
},
{
"epoch": 3.21,
"learning_rate": 9.697152101124864e-06,
"loss": 6.0184,
"step": 171000
},
{
"epoch": 3.22,
"learning_rate": 9.696211579699787e-06,
"loss": 6.0149,
"step": 171500
},
{
"epoch": 3.23,
"learning_rate": 9.695271058274707e-06,
"loss": 6.01,
"step": 172000
},
{
"epoch": 3.24,
"learning_rate": 9.69433053684963e-06,
"loss": 6.0172,
"step": 172500
},
{
"epoch": 3.25,
"learning_rate": 9.693390015424552e-06,
"loss": 6.0182,
"step": 173000
},
{
"epoch": 3.26,
"learning_rate": 9.692449493999474e-06,
"loss": 6.0157,
"step": 173500
},
{
"epoch": 3.27,
"learning_rate": 9.691508972574396e-06,
"loss": 6.0155,
"step": 174000
},
{
"epoch": 3.28,
"learning_rate": 9.690568451149318e-06,
"loss": 6.0103,
"step": 174500
},
{
"epoch": 3.29,
"learning_rate": 9.68962792972424e-06,
"loss": 6.0106,
"step": 175000
},
{
"epoch": 3.3,
"learning_rate": 9.688687408299163e-06,
"loss": 6.0163,
"step": 175500
},
{
"epoch": 3.3,
"learning_rate": 9.687746886874085e-06,
"loss": 6.0122,
"step": 176000
},
{
"epoch": 3.31,
"learning_rate": 9.686806365449006e-06,
"loss": 6.0111,
"step": 176500
},
{
"epoch": 3.32,
"learning_rate": 9.685865844023928e-06,
"loss": 6.0124,
"step": 177000
},
{
"epoch": 3.33,
"learning_rate": 9.68492532259885e-06,
"loss": 6.0116,
"step": 177500
},
{
"epoch": 3.34,
"learning_rate": 9.68398480117377e-06,
"loss": 6.0105,
"step": 178000
},
{
"epoch": 3.35,
"learning_rate": 9.683044279748693e-06,
"loss": 6.0092,
"step": 178500
},
{
"epoch": 3.36,
"learning_rate": 9.682103758323615e-06,
"loss": 6.011,
"step": 179000
},
{
"epoch": 3.37,
"learning_rate": 9.681163236898537e-06,
"loss": 6.0087,
"step": 179500
},
{
"epoch": 3.38,
"learning_rate": 9.68022271547346e-06,
"loss": 6.0085,
"step": 180000
},
{
"epoch": 3.39,
"learning_rate": 9.679282194048382e-06,
"loss": 6.0089,
"step": 180500
},
{
"epoch": 3.4,
"learning_rate": 9.678341672623302e-06,
"loss": 6.0083,
"step": 181000
},
{
"epoch": 3.41,
"learning_rate": 9.677401151198225e-06,
"loss": 6.0119,
"step": 181500
},
{
"epoch": 3.42,
"learning_rate": 9.676460629773147e-06,
"loss": 6.008,
"step": 182000
},
{
"epoch": 3.43,
"learning_rate": 9.67552010834807e-06,
"loss": 6.0068,
"step": 182500
},
{
"epoch": 3.44,
"learning_rate": 9.674579586922991e-06,
"loss": 6.0099,
"step": 183000
},
{
"epoch": 3.45,
"learning_rate": 9.673639065497914e-06,
"loss": 6.0072,
"step": 183500
},
{
"epoch": 3.45,
"learning_rate": 9.672698544072834e-06,
"loss": 6.0102,
"step": 184000
},
{
"epoch": 3.46,
"learning_rate": 9.671758022647756e-06,
"loss": 6.0048,
"step": 184500
},
{
"epoch": 3.47,
"learning_rate": 9.670817501222679e-06,
"loss": 6.0067,
"step": 185000
},
{
"epoch": 3.48,
"learning_rate": 9.669876979797601e-06,
"loss": 6.0065,
"step": 185500
},
{
"epoch": 3.49,
"learning_rate": 9.668936458372521e-06,
"loss": 6.0074,
"step": 186000
},
{
"epoch": 3.5,
"learning_rate": 9.667995936947444e-06,
"loss": 6.0049,
"step": 186500
},
{
"epoch": 3.51,
"learning_rate": 9.667055415522366e-06,
"loss": 6.0057,
"step": 187000
},
{
"epoch": 3.52,
"learning_rate": 9.666114894097288e-06,
"loss": 6.0076,
"step": 187500
},
{
"epoch": 3.53,
"learning_rate": 9.66517437267221e-06,
"loss": 6.0037,
"step": 188000
},
{
"epoch": 3.54,
"learning_rate": 9.664233851247133e-06,
"loss": 6.0037,
"step": 188500
},
{
"epoch": 3.55,
"learning_rate": 9.663293329822055e-06,
"loss": 6.0049,
"step": 189000
},
{
"epoch": 3.56,
"learning_rate": 9.662352808396977e-06,
"loss": 6.003,
"step": 189500
},
{
"epoch": 3.57,
"learning_rate": 9.661412286971898e-06,
"loss": 6.0069,
"step": 190000
},
{
"epoch": 3.58,
"learning_rate": 9.66047176554682e-06,
"loss": 6.0041,
"step": 190500
},
{
"epoch": 3.59,
"learning_rate": 9.659531244121742e-06,
"loss": 6.0057,
"step": 191000
},
{
"epoch": 3.6,
"learning_rate": 9.658590722696663e-06,
"loss": 6.0004,
"step": 191500
},
{
"epoch": 3.6,
"learning_rate": 9.657650201271585e-06,
"loss": 6.0063,
"step": 192000
},
{
"epoch": 3.61,
"learning_rate": 9.656709679846507e-06,
"loss": 5.9992,
"step": 192500
},
{
"epoch": 3.62,
"learning_rate": 9.65576915842143e-06,
"loss": 6.0026,
"step": 193000
},
{
"epoch": 3.63,
"learning_rate": 9.654828636996352e-06,
"loss": 6.0043,
"step": 193500
},
{
"epoch": 3.64,
"learning_rate": 9.653888115571274e-06,
"loss": 6.0027,
"step": 194000
},
{
"epoch": 3.65,
"learning_rate": 9.652947594146196e-06,
"loss": 6.0026,
"step": 194500
},
{
"epoch": 3.66,
"learning_rate": 9.652007072721118e-06,
"loss": 6.002,
"step": 195000
},
{
"epoch": 3.67,
"learning_rate": 9.651066551296039e-06,
"loss": 6.0013,
"step": 195500
},
{
"epoch": 3.68,
"learning_rate": 9.650126029870961e-06,
"loss": 5.9994,
"step": 196000
},
{
"epoch": 3.69,
"learning_rate": 9.649185508445883e-06,
"loss": 5.9981,
"step": 196500
},
{
"epoch": 3.7,
"learning_rate": 9.648244987020806e-06,
"loss": 5.9964,
"step": 197000
},
{
"epoch": 3.71,
"learning_rate": 9.647304465595726e-06,
"loss": 5.997,
"step": 197500
},
{
"epoch": 3.72,
"learning_rate": 9.646363944170649e-06,
"loss": 5.9987,
"step": 198000
},
{
"epoch": 3.73,
"learning_rate": 9.64542342274557e-06,
"loss": 6.002,
"step": 198500
},
{
"epoch": 3.74,
"learning_rate": 9.644482901320493e-06,
"loss": 5.9975,
"step": 199000
},
{
"epoch": 3.75,
"learning_rate": 9.643542379895415e-06,
"loss": 6.0003,
"step": 199500
},
{
"epoch": 3.76,
"learning_rate": 9.642601858470336e-06,
"loss": 5.9968,
"step": 200000
},
{
"epoch": 3.76,
"learning_rate": 9.641661337045258e-06,
"loss": 5.9974,
"step": 200500
},
{
"epoch": 3.77,
"learning_rate": 9.64072081562018e-06,
"loss": 5.998,
"step": 201000
},
{
"epoch": 3.78,
"learning_rate": 9.639780294195102e-06,
"loss": 6.0,
"step": 201500
},
{
"epoch": 3.79,
"learning_rate": 9.638839772770025e-06,
"loss": 5.9975,
"step": 202000
},
{
"epoch": 3.8,
"learning_rate": 9.637899251344947e-06,
"loss": 5.9925,
"step": 202500
},
{
"epoch": 3.81,
"learning_rate": 9.63695872991987e-06,
"loss": 5.9953,
"step": 203000
},
{
"epoch": 3.82,
"learning_rate": 9.636018208494791e-06,
"loss": 5.9993,
"step": 203500
},
{
"epoch": 3.83,
"learning_rate": 9.635077687069712e-06,
"loss": 5.9904,
"step": 204000
},
{
"epoch": 3.84,
"learning_rate": 9.634137165644634e-06,
"loss": 5.9957,
"step": 204500
},
{
"epoch": 3.85,
"learning_rate": 9.633196644219556e-06,
"loss": 6.0005,
"step": 205000
},
{
"epoch": 3.86,
"learning_rate": 9.632256122794477e-06,
"loss": 5.9974,
"step": 205500
},
{
"epoch": 3.87,
"learning_rate": 9.6313156013694e-06,
"loss": 5.999,
"step": 206000
},
{
"epoch": 3.88,
"learning_rate": 9.630375079944322e-06,
"loss": 5.9947,
"step": 206500
},
{
"epoch": 3.89,
"learning_rate": 9.629434558519244e-06,
"loss": 5.9953,
"step": 207000
},
{
"epoch": 3.9,
"learning_rate": 9.628494037094166e-06,
"loss": 5.9935,
"step": 207500
},
{
"epoch": 3.91,
"learning_rate": 9.627553515669088e-06,
"loss": 5.9897,
"step": 208000
},
{
"epoch": 3.91,
"learning_rate": 9.62661299424401e-06,
"loss": 5.9947,
"step": 208500
},
{
"epoch": 3.92,
"learning_rate": 9.625672472818933e-06,
"loss": 5.9901,
"step": 209000
},
{
"epoch": 3.93,
"learning_rate": 9.624731951393853e-06,
"loss": 5.9967,
"step": 209500
},
{
"epoch": 3.94,
"learning_rate": 9.623791429968776e-06,
"loss": 5.994,
"step": 210000
},
{
"epoch": 3.95,
"learning_rate": 9.622850908543698e-06,
"loss": 5.9942,
"step": 210500
},
{
"epoch": 3.96,
"learning_rate": 9.62191038711862e-06,
"loss": 5.9917,
"step": 211000
},
{
"epoch": 3.97,
"learning_rate": 9.62096986569354e-06,
"loss": 5.9961,
"step": 211500
},
{
"epoch": 3.98,
"learning_rate": 9.620029344268463e-06,
"loss": 5.9941,
"step": 212000
},
{
"epoch": 3.99,
"learning_rate": 9.619088822843385e-06,
"loss": 5.9916,
"step": 212500
},
{
"epoch": 4.0,
"learning_rate": 9.618148301418307e-06,
"loss": 5.9906,
"step": 213000
},
{
"epoch": 4.01,
"learning_rate": 9.61720777999323e-06,
"loss": 5.99,
"step": 213500
},
{
"epoch": 4.02,
"learning_rate": 9.61626725856815e-06,
"loss": 5.9919,
"step": 214000
},
{
"epoch": 4.03,
"learning_rate": 9.615326737143072e-06,
"loss": 5.9893,
"step": 214500
},
{
"epoch": 4.04,
"learning_rate": 9.614386215717995e-06,
"loss": 5.9947,
"step": 215000
},
{
"epoch": 4.05,
"learning_rate": 9.613445694292917e-06,
"loss": 5.9867,
"step": 215500
},
{
"epoch": 4.06,
"learning_rate": 9.612505172867839e-06,
"loss": 5.9899,
"step": 216000
},
{
"epoch": 4.06,
"learning_rate": 9.611564651442761e-06,
"loss": 5.9883,
"step": 216500
},
{
"epoch": 4.07,
"learning_rate": 9.610624130017684e-06,
"loss": 5.9891,
"step": 217000
},
{
"epoch": 4.08,
"learning_rate": 9.609683608592604e-06,
"loss": 5.9908,
"step": 217500
},
{
"epoch": 4.09,
"learning_rate": 9.608743087167526e-06,
"loss": 5.9862,
"step": 218000
},
{
"epoch": 4.1,
"learning_rate": 9.607802565742449e-06,
"loss": 5.9902,
"step": 218500
},
{
"epoch": 4.11,
"learning_rate": 9.606862044317369e-06,
"loss": 5.9913,
"step": 219000
},
{
"epoch": 4.12,
"learning_rate": 9.605921522892291e-06,
"loss": 5.9876,
"step": 219500
},
{
"epoch": 4.13,
"learning_rate": 9.604981001467214e-06,
"loss": 5.9854,
"step": 220000
},
{
"epoch": 4.14,
"learning_rate": 9.604040480042136e-06,
"loss": 5.9876,
"step": 220500
},
{
"epoch": 4.15,
"learning_rate": 9.603099958617058e-06,
"loss": 5.9875,
"step": 221000
},
{
"epoch": 4.16,
"learning_rate": 9.60215943719198e-06,
"loss": 5.986,
"step": 221500
},
{
"epoch": 4.17,
"learning_rate": 9.601218915766903e-06,
"loss": 5.9838,
"step": 222000
},
{
"epoch": 4.18,
"learning_rate": 9.600278394341825e-06,
"loss": 5.9859,
"step": 222500
},
{
"epoch": 4.19,
"learning_rate": 9.599337872916747e-06,
"loss": 5.9857,
"step": 223000
},
{
"epoch": 4.2,
"learning_rate": 9.598397351491668e-06,
"loss": 5.984,
"step": 223500
},
{
"epoch": 4.21,
"learning_rate": 9.59745683006659e-06,
"loss": 5.9866,
"step": 224000
},
{
"epoch": 4.22,
"learning_rate": 9.596516308641512e-06,
"loss": 5.9837,
"step": 224500
},
{
"epoch": 4.22,
"learning_rate": 9.595575787216433e-06,
"loss": 5.9831,
"step": 225000
},
{
"epoch": 4.23,
"learning_rate": 9.594635265791355e-06,
"loss": 5.9881,
"step": 225500
},
{
"epoch": 4.24,
"learning_rate": 9.593694744366277e-06,
"loss": 5.9861,
"step": 226000
},
{
"epoch": 4.25,
"learning_rate": 9.5927542229412e-06,
"loss": 5.9845,
"step": 226500
},
{
"epoch": 4.26,
"learning_rate": 9.591813701516122e-06,
"loss": 5.9861,
"step": 227000
},
{
"epoch": 4.27,
"learning_rate": 9.590873180091044e-06,
"loss": 5.9811,
"step": 227500
},
{
"epoch": 4.28,
"learning_rate": 9.589932658665964e-06,
"loss": 5.9819,
"step": 228000
},
{
"epoch": 4.29,
"learning_rate": 9.588992137240887e-06,
"loss": 5.984,
"step": 228500
},
{
"epoch": 4.3,
"learning_rate": 9.588051615815809e-06,
"loss": 5.9864,
"step": 229000
},
{
"epoch": 4.31,
"learning_rate": 9.587111094390731e-06,
"loss": 5.9815,
"step": 229500
},
{
"epoch": 4.32,
"learning_rate": 9.586170572965653e-06,
"loss": 5.9838,
"step": 230000
},
{
"epoch": 4.33,
"learning_rate": 9.585230051540576e-06,
"loss": 5.988,
"step": 230500
},
{
"epoch": 4.34,
"learning_rate": 9.584289530115498e-06,
"loss": 5.9785,
"step": 231000
},
{
"epoch": 4.35,
"learning_rate": 9.583349008690418e-06,
"loss": 5.9864,
"step": 231500
},
{
"epoch": 4.36,
"learning_rate": 9.58240848726534e-06,
"loss": 5.9843,
"step": 232000
},
{
"epoch": 4.37,
"learning_rate": 9.581467965840263e-06,
"loss": 5.9829,
"step": 232500
},
{
"epoch": 4.37,
"learning_rate": 9.580527444415183e-06,
"loss": 5.9818,
"step": 233000
},
{
"epoch": 4.38,
"learning_rate": 9.579586922990106e-06,
"loss": 5.9791,
"step": 233500
},
{
"epoch": 4.39,
"learning_rate": 9.578646401565028e-06,
"loss": 5.9782,
"step": 234000
},
{
"epoch": 4.4,
"learning_rate": 9.57770588013995e-06,
"loss": 5.984,
"step": 234500
},
{
"epoch": 4.41,
"learning_rate": 9.576765358714872e-06,
"loss": 5.9844,
"step": 235000
},
{
"epoch": 4.42,
"learning_rate": 9.575824837289795e-06,
"loss": 5.9833,
"step": 235500
},
{
"epoch": 4.43,
"learning_rate": 9.574884315864717e-06,
"loss": 5.9771,
"step": 236000
},
{
"epoch": 4.44,
"learning_rate": 9.573943794439639e-06,
"loss": 5.9799,
"step": 236500
},
{
"epoch": 4.45,
"learning_rate": 9.573003273014561e-06,
"loss": 5.9827,
"step": 237000
},
{
"epoch": 4.46,
"learning_rate": 9.572062751589482e-06,
"loss": 5.9785,
"step": 237500
},
{
"epoch": 4.47,
"learning_rate": 9.571122230164404e-06,
"loss": 5.9811,
"step": 238000
},
{
"epoch": 4.48,
"learning_rate": 9.570181708739326e-06,
"loss": 5.9823,
"step": 238500
},
{
"epoch": 4.49,
"learning_rate": 9.569241187314247e-06,
"loss": 5.9818,
"step": 239000
},
{
"epoch": 4.5,
"learning_rate": 9.568300665889169e-06,
"loss": 5.9796,
"step": 239500
},
{
"epoch": 4.51,
"learning_rate": 9.567360144464091e-06,
"loss": 5.9825,
"step": 240000
},
{
"epoch": 4.52,
"learning_rate": 9.566419623039014e-06,
"loss": 5.9748,
"step": 240500
},
{
"epoch": 4.52,
"learning_rate": 9.565479101613936e-06,
"loss": 5.9747,
"step": 241000
},
{
"epoch": 4.53,
"learning_rate": 9.564538580188858e-06,
"loss": 5.9785,
"step": 241500
},
{
"epoch": 4.54,
"learning_rate": 9.563598058763779e-06,
"loss": 5.9788,
"step": 242000
},
{
"epoch": 4.55,
"learning_rate": 9.562657537338701e-06,
"loss": 5.978,
"step": 242500
},
{
"epoch": 4.56,
"learning_rate": 9.561717015913623e-06,
"loss": 5.9723,
"step": 243000
},
{
"epoch": 4.57,
"learning_rate": 9.560776494488545e-06,
"loss": 5.9796,
"step": 243500
},
{
"epoch": 4.58,
"learning_rate": 9.559835973063468e-06,
"loss": 5.9733,
"step": 244000
},
{
"epoch": 4.59,
"learning_rate": 9.55889545163839e-06,
"loss": 5.9772,
"step": 244500
},
{
"epoch": 4.6,
"learning_rate": 9.55795493021331e-06,
"loss": 5.9777,
"step": 245000
},
{
"epoch": 4.61,
"learning_rate": 9.557014408788233e-06,
"loss": 5.9779,
"step": 245500
},
{
"epoch": 4.62,
"learning_rate": 9.556073887363155e-06,
"loss": 5.9741,
"step": 246000
},
{
"epoch": 4.63,
"learning_rate": 9.555133365938077e-06,
"loss": 5.974,
"step": 246500
},
{
"epoch": 4.64,
"learning_rate": 9.554192844512998e-06,
"loss": 5.9783,
"step": 247000
},
{
"epoch": 4.65,
"learning_rate": 9.55325232308792e-06,
"loss": 5.9792,
"step": 247500
},
{
"epoch": 4.66,
"learning_rate": 9.552311801662842e-06,
"loss": 5.9747,
"step": 248000
},
{
"epoch": 4.67,
"learning_rate": 9.551371280237764e-06,
"loss": 5.9747,
"step": 248500
},
{
"epoch": 4.68,
"learning_rate": 9.550430758812687e-06,
"loss": 5.9765,
"step": 249000
},
{
"epoch": 4.68,
"learning_rate": 9.549490237387609e-06,
"loss": 5.9727,
"step": 249500
},
{
"epoch": 4.69,
"learning_rate": 9.548549715962531e-06,
"loss": 5.9698,
"step": 250000
},
{
"epoch": 4.7,
"learning_rate": 9.547609194537453e-06,
"loss": 5.9733,
"step": 250500
},
{
"epoch": 4.71,
"learning_rate": 9.546668673112374e-06,
"loss": 5.9741,
"step": 251000
},
{
"epoch": 4.72,
"learning_rate": 9.545728151687296e-06,
"loss": 5.9743,
"step": 251500
},
{
"epoch": 4.73,
"learning_rate": 9.544787630262218e-06,
"loss": 5.9718,
"step": 252000
},
{
"epoch": 4.74,
"learning_rate": 9.54384710883714e-06,
"loss": 5.9753,
"step": 252500
},
{
"epoch": 4.75,
"learning_rate": 9.542906587412061e-06,
"loss": 5.9757,
"step": 253000
},
{
"epoch": 4.76,
"learning_rate": 9.541966065986983e-06,
"loss": 5.9719,
"step": 253500
},
{
"epoch": 4.77,
"learning_rate": 9.541025544561906e-06,
"loss": 5.9748,
"step": 254000
},
{
"epoch": 4.78,
"learning_rate": 9.540085023136828e-06,
"loss": 5.9749,
"step": 254500
},
{
"epoch": 4.79,
"learning_rate": 9.53914450171175e-06,
"loss": 5.9717,
"step": 255000
},
{
"epoch": 4.8,
"learning_rate": 9.538203980286672e-06,
"loss": 5.9747,
"step": 255500
},
{
"epoch": 4.81,
"learning_rate": 9.537263458861593e-06,
"loss": 5.9692,
"step": 256000
},
{
"epoch": 4.82,
"learning_rate": 9.536322937436515e-06,
"loss": 5.9739,
"step": 256500
},
{
"epoch": 4.83,
"learning_rate": 9.535382416011437e-06,
"loss": 5.9703,
"step": 257000
},
{
"epoch": 4.83,
"learning_rate": 9.53444189458636e-06,
"loss": 5.9728,
"step": 257500
},
{
"epoch": 4.84,
"learning_rate": 9.533501373161282e-06,
"loss": 5.9702,
"step": 258000
},
{
"epoch": 4.85,
"learning_rate": 9.532560851736204e-06,
"loss": 5.9746,
"step": 258500
},
{
"epoch": 4.86,
"learning_rate": 9.531620330311125e-06,
"loss": 5.9676,
"step": 259000
},
{
"epoch": 4.87,
"learning_rate": 9.530679808886047e-06,
"loss": 5.9686,
"step": 259500
},
{
"epoch": 4.88,
"learning_rate": 9.52973928746097e-06,
"loss": 5.9682,
"step": 260000
},
{
"epoch": 4.89,
"learning_rate": 9.528798766035891e-06,
"loss": 5.9629,
"step": 260500
},
{
"epoch": 4.9,
"learning_rate": 9.527858244610812e-06,
"loss": 5.9739,
"step": 261000
},
{
"epoch": 4.91,
"learning_rate": 9.526917723185734e-06,
"loss": 5.9666,
"step": 261500
},
{
"epoch": 4.92,
"learning_rate": 9.525977201760656e-06,
"loss": 5.9683,
"step": 262000
},
{
"epoch": 4.93,
"learning_rate": 9.525036680335579e-06,
"loss": 5.9666,
"step": 262500
},
{
"epoch": 4.94,
"learning_rate": 9.524096158910501e-06,
"loss": 5.9701,
"step": 263000
},
{
"epoch": 4.95,
"learning_rate": 9.523155637485423e-06,
"loss": 5.9677,
"step": 263500
},
{
"epoch": 4.96,
"learning_rate": 9.522215116060345e-06,
"loss": 5.9693,
"step": 264000
},
{
"epoch": 4.97,
"learning_rate": 9.521274594635268e-06,
"loss": 5.9679,
"step": 264500
},
{
"epoch": 4.98,
"learning_rate": 9.520334073210188e-06,
"loss": 5.9671,
"step": 265000
},
{
"epoch": 4.98,
"learning_rate": 9.51939355178511e-06,
"loss": 5.9717,
"step": 265500
},
{
"epoch": 4.99,
"learning_rate": 9.518453030360033e-06,
"loss": 5.9687,
"step": 266000
},
{
"epoch": 5.0,
"learning_rate": 9.517512508934953e-06,
"loss": 5.9598,
"step": 266500
},
{
"epoch": 5.01,
"learning_rate": 9.516571987509876e-06,
"loss": 5.9659,
"step": 267000
},
{
"epoch": 5.02,
"learning_rate": 9.515631466084798e-06,
"loss": 5.9645,
"step": 267500
},
{
"epoch": 5.03,
"learning_rate": 9.51469094465972e-06,
"loss": 5.9627,
"step": 268000
},
{
"epoch": 5.04,
"learning_rate": 9.513750423234642e-06,
"loss": 5.962,
"step": 268500
},
{
"epoch": 5.05,
"learning_rate": 9.512809901809564e-06,
"loss": 5.9653,
"step": 269000
},
{
"epoch": 5.06,
"learning_rate": 9.511869380384487e-06,
"loss": 5.9638,
"step": 269500
},
{
"epoch": 5.07,
"learning_rate": 9.510928858959409e-06,
"loss": 5.9608,
"step": 270000
},
{
"epoch": 5.08,
"learning_rate": 9.50998833753433e-06,
"loss": 5.9616,
"step": 270500
},
{
"epoch": 5.09,
"learning_rate": 9.509047816109252e-06,
"loss": 5.9596,
"step": 271000
},
{
"epoch": 5.1,
"learning_rate": 9.508107294684174e-06,
"loss": 5.9601,
"step": 271500
},
{
"epoch": 5.11,
"learning_rate": 9.507166773259096e-06,
"loss": 5.9551,
"step": 272000
},
{
"epoch": 5.12,
"learning_rate": 9.506226251834017e-06,
"loss": 5.9589,
"step": 272500
},
{
"epoch": 5.13,
"learning_rate": 9.505285730408939e-06,
"loss": 5.9497,
"step": 273000
},
{
"epoch": 5.13,
"learning_rate": 9.504345208983861e-06,
"loss": 5.9459,
"step": 273500
},
{
"epoch": 5.14,
"learning_rate": 9.503404687558783e-06,
"loss": 5.9428,
"step": 274000
},
{
"epoch": 5.15,
"learning_rate": 9.502464166133706e-06,
"loss": 5.9414,
"step": 274500
},
{
"epoch": 5.16,
"learning_rate": 9.501523644708626e-06,
"loss": 5.9373,
"step": 275000
},
{
"epoch": 5.17,
"learning_rate": 9.500583123283549e-06,
"loss": 5.9284,
"step": 275500
},
{
"epoch": 5.18,
"learning_rate": 9.49964260185847e-06,
"loss": 5.9263,
"step": 276000
},
{
"epoch": 5.19,
"learning_rate": 9.498702080433393e-06,
"loss": 5.9239,
"step": 276500
},
{
"epoch": 5.2,
"learning_rate": 9.497761559008315e-06,
"loss": 5.9183,
"step": 277000
},
{
"epoch": 5.21,
"learning_rate": 9.496821037583237e-06,
"loss": 5.9156,
"step": 277500
},
{
"epoch": 5.22,
"learning_rate": 9.49588051615816e-06,
"loss": 5.9107,
"step": 278000
},
{
"epoch": 5.23,
"learning_rate": 9.494939994733082e-06,
"loss": 5.908,
"step": 278500
},
{
"epoch": 5.24,
"learning_rate": 9.493999473308003e-06,
"loss": 5.9034,
"step": 279000
},
{
"epoch": 5.25,
"learning_rate": 9.493058951882925e-06,
"loss": 5.9,
"step": 279500
},
{
"epoch": 5.26,
"learning_rate": 9.492118430457847e-06,
"loss": 5.8955,
"step": 280000
},
{
"epoch": 5.27,
"learning_rate": 9.491177909032768e-06,
"loss": 5.8943,
"step": 280500
},
{
"epoch": 5.28,
"learning_rate": 9.49023738760769e-06,
"loss": 5.8884,
"step": 281000
},
{
"epoch": 5.29,
"learning_rate": 9.489296866182612e-06,
"loss": 5.8922,
"step": 281500
},
{
"epoch": 5.29,
"learning_rate": 9.488356344757534e-06,
"loss": 5.8877,
"step": 282000
},
{
"epoch": 5.3,
"learning_rate": 9.487415823332457e-06,
"loss": 5.8822,
"step": 282500
},
{
"epoch": 5.31,
"learning_rate": 9.486475301907379e-06,
"loss": 5.8777,
"step": 283000
},
{
"epoch": 5.32,
"learning_rate": 9.485534780482301e-06,
"loss": 5.8797,
"step": 283500
},
{
"epoch": 5.33,
"learning_rate": 9.484594259057223e-06,
"loss": 5.8745,
"step": 284000
},
{
"epoch": 5.34,
"learning_rate": 9.483653737632144e-06,
"loss": 5.8737,
"step": 284500
},
{
"epoch": 5.35,
"learning_rate": 9.482713216207066e-06,
"loss": 5.8684,
"step": 285000
},
{
"epoch": 5.36,
"learning_rate": 9.481772694781988e-06,
"loss": 5.8649,
"step": 285500
},
{
"epoch": 5.37,
"learning_rate": 9.48083217335691e-06,
"loss": 5.861,
"step": 286000
},
{
"epoch": 5.38,
"learning_rate": 9.479891651931831e-06,
"loss": 5.8596,
"step": 286500
},
{
"epoch": 5.39,
"learning_rate": 9.478951130506753e-06,
"loss": 5.856,
"step": 287000
},
{
"epoch": 5.4,
"learning_rate": 9.478010609081676e-06,
"loss": 5.8534,
"step": 287500
},
{
"epoch": 5.41,
"learning_rate": 9.477070087656598e-06,
"loss": 5.8516,
"step": 288000
},
{
"epoch": 5.42,
"learning_rate": 9.47612956623152e-06,
"loss": 5.8441,
"step": 288500
},
{
"epoch": 5.43,
"learning_rate": 9.47518904480644e-06,
"loss": 5.8483,
"step": 289000
},
{
"epoch": 5.44,
"learning_rate": 9.474248523381363e-06,
"loss": 5.8393,
"step": 289500
},
{
"epoch": 5.44,
"learning_rate": 9.473308001956285e-06,
"loss": 5.8395,
"step": 290000
},
{
"epoch": 5.45,
"learning_rate": 9.472367480531207e-06,
"loss": 5.8367,
"step": 290500
},
{
"epoch": 5.46,
"learning_rate": 9.47142695910613e-06,
"loss": 5.8355,
"step": 291000
},
{
"epoch": 5.47,
"learning_rate": 9.470486437681052e-06,
"loss": 5.8335,
"step": 291500
},
{
"epoch": 5.48,
"learning_rate": 9.469545916255974e-06,
"loss": 5.8336,
"step": 292000
},
{
"epoch": 5.49,
"learning_rate": 9.468605394830895e-06,
"loss": 5.8283,
"step": 292500
},
{
"epoch": 5.5,
"learning_rate": 9.467664873405817e-06,
"loss": 5.8262,
"step": 293000
},
{
"epoch": 5.51,
"learning_rate": 9.466724351980739e-06,
"loss": 5.8278,
"step": 293500
},
{
"epoch": 5.52,
"learning_rate": 9.46578383055566e-06,
"loss": 5.8238,
"step": 294000
},
{
"epoch": 5.53,
"learning_rate": 9.464843309130582e-06,
"loss": 5.8234,
"step": 294500
},
{
"epoch": 5.54,
"learning_rate": 9.463902787705504e-06,
"loss": 5.8174,
"step": 295000
},
{
"epoch": 5.55,
"learning_rate": 9.462962266280426e-06,
"loss": 5.8192,
"step": 295500
},
{
"epoch": 5.56,
"learning_rate": 9.462021744855349e-06,
"loss": 5.8156,
"step": 296000
},
{
"epoch": 5.57,
"learning_rate": 9.46108122343027e-06,
"loss": 5.8138,
"step": 296500
},
{
"epoch": 5.58,
"learning_rate": 9.460140702005193e-06,
"loss": 5.8147,
"step": 297000
},
{
"epoch": 5.59,
"learning_rate": 9.459200180580115e-06,
"loss": 5.811,
"step": 297500
},
{
"epoch": 5.59,
"learning_rate": 9.458259659155038e-06,
"loss": 5.8126,
"step": 298000
},
{
"epoch": 5.6,
"learning_rate": 9.457319137729958e-06,
"loss": 5.8089,
"step": 298500
},
{
"epoch": 5.61,
"learning_rate": 9.45637861630488e-06,
"loss": 5.8069,
"step": 299000
},
{
"epoch": 5.62,
"learning_rate": 9.455438094879803e-06,
"loss": 5.8086,
"step": 299500
},
{
"epoch": 5.63,
"learning_rate": 9.454497573454723e-06,
"loss": 5.7981,
"step": 300000
},
{
"epoch": 5.64,
"learning_rate": 9.453557052029645e-06,
"loss": 5.7995,
"step": 300500
},
{
"epoch": 5.65,
"learning_rate": 9.452616530604568e-06,
"loss": 5.7959,
"step": 301000
},
{
"epoch": 5.66,
"learning_rate": 9.45167600917949e-06,
"loss": 5.7978,
"step": 301500
},
{
"epoch": 5.67,
"learning_rate": 9.450735487754412e-06,
"loss": 5.7945,
"step": 302000
},
{
"epoch": 5.68,
"learning_rate": 9.449794966329334e-06,
"loss": 5.7942,
"step": 302500
},
{
"epoch": 5.69,
"learning_rate": 9.448854444904255e-06,
"loss": 5.7927,
"step": 303000
},
{
"epoch": 5.7,
"learning_rate": 9.447913923479177e-06,
"loss": 5.7892,
"step": 303500
},
{
"epoch": 5.71,
"learning_rate": 9.4469734020541e-06,
"loss": 5.7921,
"step": 304000
},
{
"epoch": 5.72,
"learning_rate": 9.446032880629022e-06,
"loss": 5.7912,
"step": 304500
},
{
"epoch": 5.73,
"learning_rate": 9.445092359203944e-06,
"loss": 5.7849,
"step": 305000
},
{
"epoch": 5.74,
"learning_rate": 9.444151837778866e-06,
"loss": 5.7797,
"step": 305500
},
{
"epoch": 5.75,
"learning_rate": 9.443211316353788e-06,
"loss": 5.7817,
"step": 306000
},
{
"epoch": 5.75,
"learning_rate": 9.442270794928709e-06,
"loss": 5.7823,
"step": 306500
},
{
"epoch": 5.76,
"learning_rate": 9.441330273503631e-06,
"loss": 5.784,
"step": 307000
},
{
"epoch": 5.77,
"learning_rate": 9.440389752078553e-06,
"loss": 5.7808,
"step": 307500
},
{
"epoch": 5.78,
"learning_rate": 9.439449230653474e-06,
"loss": 5.7768,
"step": 308000
},
{
"epoch": 5.79,
"learning_rate": 9.438508709228396e-06,
"loss": 5.7747,
"step": 308500
},
{
"epoch": 5.8,
"learning_rate": 9.437568187803318e-06,
"loss": 5.7752,
"step": 309000
},
{
"epoch": 5.81,
"learning_rate": 9.43662766637824e-06,
"loss": 5.7696,
"step": 309500
},
{
"epoch": 5.82,
"learning_rate": 9.435687144953163e-06,
"loss": 5.7699,
"step": 310000
},
{
"epoch": 5.83,
"learning_rate": 9.434746623528085e-06,
"loss": 5.7707,
"step": 310500
},
{
"epoch": 5.84,
"learning_rate": 9.433806102103007e-06,
"loss": 5.7692,
"step": 311000
},
{
"epoch": 5.85,
"learning_rate": 9.43286558067793e-06,
"loss": 5.7661,
"step": 311500
},
{
"epoch": 5.86,
"learning_rate": 9.431925059252852e-06,
"loss": 5.7615,
"step": 312000
},
{
"epoch": 5.87,
"learning_rate": 9.430984537827772e-06,
"loss": 5.767,
"step": 312500
},
{
"epoch": 5.88,
"learning_rate": 9.430044016402695e-06,
"loss": 5.7634,
"step": 313000
},
{
"epoch": 5.89,
"learning_rate": 9.429103494977617e-06,
"loss": 5.7597,
"step": 313500
},
{
"epoch": 5.9,
"learning_rate": 9.428162973552537e-06,
"loss": 5.7601,
"step": 314000
},
{
"epoch": 5.9,
"learning_rate": 9.42722245212746e-06,
"loss": 5.7595,
"step": 314500
},
{
"epoch": 5.91,
"learning_rate": 9.426281930702382e-06,
"loss": 5.7548,
"step": 315000
},
{
"epoch": 5.92,
"learning_rate": 9.425341409277304e-06,
"loss": 5.7577,
"step": 315500
},
{
"epoch": 5.93,
"learning_rate": 9.424400887852226e-06,
"loss": 5.7535,
"step": 316000
},
{
"epoch": 5.94,
"learning_rate": 9.423460366427149e-06,
"loss": 5.7502,
"step": 316500
},
{
"epoch": 5.95,
"learning_rate": 9.42251984500207e-06,
"loss": 5.7495,
"step": 317000
},
{
"epoch": 5.96,
"learning_rate": 9.421579323576991e-06,
"loss": 5.7461,
"step": 317500
},
{
"epoch": 5.97,
"learning_rate": 9.420638802151914e-06,
"loss": 5.7463,
"step": 318000
},
{
"epoch": 5.98,
"learning_rate": 9.419698280726836e-06,
"loss": 5.7455,
"step": 318500
},
{
"epoch": 5.99,
"learning_rate": 9.418757759301758e-06,
"loss": 5.744,
"step": 319000
},
{
"epoch": 6.0,
"learning_rate": 9.41781723787668e-06,
"loss": 5.7451,
"step": 319500
},
{
"epoch": 6.01,
"learning_rate": 9.416876716451601e-06,
"loss": 5.7394,
"step": 320000
},
{
"epoch": 6.02,
"learning_rate": 9.415936195026523e-06,
"loss": 5.7389,
"step": 320500
},
{
"epoch": 6.03,
"learning_rate": 9.414995673601445e-06,
"loss": 5.7369,
"step": 321000
},
{
"epoch": 6.04,
"learning_rate": 9.414055152176368e-06,
"loss": 5.7344,
"step": 321500
},
{
"epoch": 6.05,
"learning_rate": 9.413114630751288e-06,
"loss": 5.7336,
"step": 322000
},
{
"epoch": 6.05,
"learning_rate": 9.41217410932621e-06,
"loss": 5.732,
"step": 322500
},
{
"epoch": 6.06,
"learning_rate": 9.411233587901133e-06,
"loss": 5.7344,
"step": 323000
},
{
"epoch": 6.07,
"learning_rate": 9.410293066476055e-06,
"loss": 5.7307,
"step": 323500
},
{
"epoch": 6.08,
"learning_rate": 9.409352545050977e-06,
"loss": 5.7266,
"step": 324000
},
{
"epoch": 6.09,
"learning_rate": 9.4084120236259e-06,
"loss": 5.724,
"step": 324500
},
{
"epoch": 6.1,
"learning_rate": 9.407471502200822e-06,
"loss": 5.7232,
"step": 325000
},
{
"epoch": 6.11,
"learning_rate": 9.406530980775744e-06,
"loss": 5.7244,
"step": 325500
},
{
"epoch": 6.12,
"learning_rate": 9.405590459350664e-06,
"loss": 5.721,
"step": 326000
},
{
"epoch": 6.13,
"learning_rate": 9.404649937925587e-06,
"loss": 5.7226,
"step": 326500
},
{
"epoch": 6.14,
"learning_rate": 9.403709416500509e-06,
"loss": 5.7182,
"step": 327000
},
{
"epoch": 6.15,
"learning_rate": 9.402768895075431e-06,
"loss": 5.7117,
"step": 327500
},
{
"epoch": 6.16,
"learning_rate": 9.401828373650352e-06,
"loss": 5.7186,
"step": 328000
},
{
"epoch": 6.17,
"learning_rate": 9.400887852225274e-06,
"loss": 5.7132,
"step": 328500
},
{
"epoch": 6.18,
"learning_rate": 9.399947330800196e-06,
"loss": 5.7079,
"step": 329000
},
{
"epoch": 6.19,
"learning_rate": 9.399006809375118e-06,
"loss": 5.7112,
"step": 329500
},
{
"epoch": 6.2,
"learning_rate": 9.39806628795004e-06,
"loss": 5.7119,
"step": 330000
},
{
"epoch": 6.21,
"learning_rate": 9.397125766524963e-06,
"loss": 5.7051,
"step": 330500
},
{
"epoch": 6.21,
"learning_rate": 9.396185245099883e-06,
"loss": 5.7066,
"step": 331000
},
{
"epoch": 6.22,
"learning_rate": 9.395244723674806e-06,
"loss": 5.705,
"step": 331500
},
{
"epoch": 6.23,
"learning_rate": 9.394304202249728e-06,
"loss": 5.7024,
"step": 332000
},
{
"epoch": 6.24,
"learning_rate": 9.39336368082465e-06,
"loss": 5.6993,
"step": 332500
},
{
"epoch": 6.25,
"learning_rate": 9.392423159399572e-06,
"loss": 5.6991,
"step": 333000
},
{
"epoch": 6.26,
"learning_rate": 9.391482637974495e-06,
"loss": 5.6938,
"step": 333500
},
{
"epoch": 6.27,
"learning_rate": 9.390542116549415e-06,
"loss": 5.6967,
"step": 334000
},
{
"epoch": 6.28,
"learning_rate": 9.389601595124337e-06,
"loss": 5.6927,
"step": 334500
},
{
"epoch": 6.29,
"learning_rate": 9.38866107369926e-06,
"loss": 5.6963,
"step": 335000
},
{
"epoch": 6.3,
"learning_rate": 9.387720552274182e-06,
"loss": 5.6931,
"step": 335500
},
{
"epoch": 6.31,
"learning_rate": 9.386780030849103e-06,
"loss": 5.688,
"step": 336000
},
{
"epoch": 6.32,
"learning_rate": 9.385839509424025e-06,
"loss": 5.6873,
"step": 336500
},
{
"epoch": 6.33,
"learning_rate": 9.384898987998947e-06,
"loss": 5.6834,
"step": 337000
},
{
"epoch": 6.34,
"learning_rate": 9.38395846657387e-06,
"loss": 5.6803,
"step": 337500
},
{
"epoch": 6.35,
"learning_rate": 9.383017945148791e-06,
"loss": 5.6835,
"step": 338000
},
{
"epoch": 6.36,
"learning_rate": 9.382077423723714e-06,
"loss": 5.6783,
"step": 338500
},
{
"epoch": 6.36,
"learning_rate": 9.381136902298636e-06,
"loss": 5.6802,
"step": 339000
},
{
"epoch": 6.37,
"learning_rate": 9.380196380873558e-06,
"loss": 5.6793,
"step": 339500
},
{
"epoch": 6.38,
"learning_rate": 9.379255859448479e-06,
"loss": 5.6735,
"step": 340000
},
{
"epoch": 6.39,
"learning_rate": 9.378315338023401e-06,
"loss": 5.6676,
"step": 340500
},
{
"epoch": 6.4,
"learning_rate": 9.377374816598323e-06,
"loss": 5.6718,
"step": 341000
},
{
"epoch": 6.41,
"learning_rate": 9.376434295173244e-06,
"loss": 5.6673,
"step": 341500
},
{
"epoch": 6.42,
"learning_rate": 9.375493773748166e-06,
"loss": 5.6681,
"step": 342000
},
{
"epoch": 6.43,
"learning_rate": 9.374553252323088e-06,
"loss": 5.667,
"step": 342500
},
{
"epoch": 6.44,
"learning_rate": 9.37361273089801e-06,
"loss": 5.6677,
"step": 343000
},
{
"epoch": 6.45,
"learning_rate": 9.372672209472933e-06,
"loss": 5.666,
"step": 343500
},
{
"epoch": 6.46,
"learning_rate": 9.371731688047855e-06,
"loss": 5.6595,
"step": 344000
},
{
"epoch": 6.47,
"learning_rate": 9.370791166622777e-06,
"loss": 5.6604,
"step": 344500
},
{
"epoch": 6.48,
"learning_rate": 9.369850645197698e-06,
"loss": 5.6568,
"step": 345000
},
{
"epoch": 6.49,
"learning_rate": 9.36891012377262e-06,
"loss": 5.6578,
"step": 345500
},
{
"epoch": 6.5,
"learning_rate": 9.367969602347542e-06,
"loss": 5.6587,
"step": 346000
},
{
"epoch": 6.51,
"learning_rate": 9.367029080922464e-06,
"loss": 5.658,
"step": 346500
},
{
"epoch": 6.51,
"learning_rate": 9.366088559497387e-06,
"loss": 5.655,
"step": 347000
},
{
"epoch": 6.52,
"learning_rate": 9.365148038072307e-06,
"loss": 5.6501,
"step": 347500
},
{
"epoch": 6.53,
"learning_rate": 9.36420751664723e-06,
"loss": 5.6488,
"step": 348000
},
{
"epoch": 6.54,
"learning_rate": 9.363266995222152e-06,
"loss": 5.6457,
"step": 348500
},
{
"epoch": 6.55,
"learning_rate": 9.362326473797074e-06,
"loss": 5.6446,
"step": 349000
},
{
"epoch": 6.56,
"learning_rate": 9.361385952371996e-06,
"loss": 5.6466,
"step": 349500
},
{
"epoch": 6.57,
"learning_rate": 9.360445430946917e-06,
"loss": 5.6448,
"step": 350000
},
{
"epoch": 6.58,
"learning_rate": 9.359504909521839e-06,
"loss": 5.6437,
"step": 350500
},
{
"epoch": 6.59,
"learning_rate": 9.358564388096761e-06,
"loss": 5.6431,
"step": 351000
},
{
"epoch": 6.6,
"learning_rate": 9.357623866671684e-06,
"loss": 5.6376,
"step": 351500
},
{
"epoch": 6.61,
"learning_rate": 9.356683345246606e-06,
"loss": 5.6404,
"step": 352000
},
{
"epoch": 6.62,
"learning_rate": 9.355742823821528e-06,
"loss": 5.6378,
"step": 352500
},
{
"epoch": 6.63,
"learning_rate": 9.35480230239645e-06,
"loss": 5.6332,
"step": 353000
},
{
"epoch": 6.64,
"learning_rate": 9.353861780971372e-06,
"loss": 5.6392,
"step": 353500
},
{
"epoch": 6.65,
"learning_rate": 9.352921259546293e-06,
"loss": 5.6315,
"step": 354000
},
{
"epoch": 6.66,
"learning_rate": 9.351980738121215e-06,
"loss": 5.6292,
"step": 354500
},
{
"epoch": 6.67,
"learning_rate": 9.351040216696138e-06,
"loss": 5.6339,
"step": 355000
},
{
"epoch": 6.67,
"learning_rate": 9.350099695271058e-06,
"loss": 5.6272,
"step": 355500
},
{
"epoch": 6.68,
"learning_rate": 9.34915917384598e-06,
"loss": 5.6253,
"step": 356000
},
{
"epoch": 6.69,
"learning_rate": 9.348218652420903e-06,
"loss": 5.627,
"step": 356500
},
{
"epoch": 6.7,
"learning_rate": 9.347278130995825e-06,
"loss": 5.6228,
"step": 357000
},
{
"epoch": 6.71,
"learning_rate": 9.346337609570747e-06,
"loss": 5.6208,
"step": 357500
},
{
"epoch": 6.72,
"learning_rate": 9.34539708814567e-06,
"loss": 5.6196,
"step": 358000
},
{
"epoch": 6.73,
"learning_rate": 9.344456566720592e-06,
"loss": 5.62,
"step": 358500
},
{
"epoch": 6.74,
"learning_rate": 9.343516045295514e-06,
"loss": 5.6195,
"step": 359000
},
{
"epoch": 6.75,
"learning_rate": 9.342575523870434e-06,
"loss": 5.6157,
"step": 359500
},
{
"epoch": 6.76,
"learning_rate": 9.341635002445357e-06,
"loss": 5.6095,
"step": 360000
},
{
"epoch": 6.77,
"learning_rate": 9.340694481020279e-06,
"loss": 5.614,
"step": 360500
},
{
"epoch": 6.78,
"learning_rate": 9.339753959595201e-06,
"loss": 5.6164,
"step": 361000
},
{
"epoch": 6.79,
"learning_rate": 9.338813438170122e-06,
"loss": 5.6082,
"step": 361500
},
{
"epoch": 6.8,
"learning_rate": 9.337872916745044e-06,
"loss": 5.607,
"step": 362000
},
{
"epoch": 6.81,
"learning_rate": 9.336932395319966e-06,
"loss": 5.6047,
"step": 362500
},
{
"epoch": 6.82,
"learning_rate": 9.335991873894888e-06,
"loss": 5.6063,
"step": 363000
},
{
"epoch": 6.82,
"learning_rate": 9.33505135246981e-06,
"loss": 5.6062,
"step": 363500
},
{
"epoch": 6.83,
"learning_rate": 9.334110831044731e-06,
"loss": 5.6031,
"step": 364000
},
{
"epoch": 6.84,
"learning_rate": 9.333170309619653e-06,
"loss": 5.5982,
"step": 364500
},
{
"epoch": 6.85,
"learning_rate": 9.332229788194576e-06,
"loss": 5.597,
"step": 365000
},
{
"epoch": 6.86,
"learning_rate": 9.331289266769498e-06,
"loss": 5.5993,
"step": 365500
},
{
"epoch": 6.87,
"learning_rate": 9.33034874534442e-06,
"loss": 5.5955,
"step": 366000
},
{
"epoch": 6.88,
"learning_rate": 9.329408223919342e-06,
"loss": 5.5945,
"step": 366500
},
{
"epoch": 6.89,
"learning_rate": 9.328467702494265e-06,
"loss": 5.5895,
"step": 367000
},
{
"epoch": 6.9,
"learning_rate": 9.327527181069185e-06,
"loss": 5.5864,
"step": 367500
},
{
"epoch": 6.91,
"learning_rate": 9.326586659644107e-06,
"loss": 5.5865,
"step": 368000
},
{
"epoch": 6.92,
"learning_rate": 9.32564613821903e-06,
"loss": 5.5862,
"step": 368500
},
{
"epoch": 6.93,
"learning_rate": 9.32470561679395e-06,
"loss": 5.5843,
"step": 369000
},
{
"epoch": 6.94,
"learning_rate": 9.323765095368872e-06,
"loss": 5.5808,
"step": 369500
},
{
"epoch": 6.95,
"learning_rate": 9.322824573943795e-06,
"loss": 5.5855,
"step": 370000
},
{
"epoch": 6.96,
"learning_rate": 9.321884052518717e-06,
"loss": 5.5778,
"step": 370500
},
{
"epoch": 6.97,
"learning_rate": 9.320943531093639e-06,
"loss": 5.5809,
"step": 371000
},
{
"epoch": 6.97,
"learning_rate": 9.320003009668561e-06,
"loss": 5.5787,
"step": 371500
},
{
"epoch": 6.98,
"learning_rate": 9.319062488243484e-06,
"loss": 5.5734,
"step": 372000
},
{
"epoch": 6.99,
"learning_rate": 9.318121966818406e-06,
"loss": 5.5715,
"step": 372500
},
{
"epoch": 7.0,
"learning_rate": 9.317181445393328e-06,
"loss": 5.5709,
"step": 373000
},
{
"epoch": 7.01,
"learning_rate": 9.316240923968249e-06,
"loss": 5.57,
"step": 373500
},
{
"epoch": 7.02,
"learning_rate": 9.315300402543171e-06,
"loss": 5.5664,
"step": 374000
},
{
"epoch": 7.03,
"learning_rate": 9.314359881118093e-06,
"loss": 5.5659,
"step": 374500
},
{
"epoch": 7.04,
"learning_rate": 9.313419359693014e-06,
"loss": 5.5612,
"step": 375000
},
{
"epoch": 7.05,
"learning_rate": 9.312478838267936e-06,
"loss": 5.5632,
"step": 375500
},
{
"epoch": 7.06,
"learning_rate": 9.311538316842858e-06,
"loss": 5.5592,
"step": 376000
},
{
"epoch": 7.07,
"learning_rate": 9.31059779541778e-06,
"loss": 5.5593,
"step": 376500
},
{
"epoch": 7.08,
"learning_rate": 9.309657273992703e-06,
"loss": 5.5562,
"step": 377000
},
{
"epoch": 7.09,
"learning_rate": 9.308716752567625e-06,
"loss": 5.5521,
"step": 377500
},
{
"epoch": 7.1,
"learning_rate": 9.307776231142545e-06,
"loss": 5.5571,
"step": 378000
},
{
"epoch": 7.11,
"learning_rate": 9.306835709717468e-06,
"loss": 5.5508,
"step": 378500
},
{
"epoch": 7.12,
"learning_rate": 9.30589518829239e-06,
"loss": 5.5524,
"step": 379000
},
{
"epoch": 7.13,
"learning_rate": 9.304954666867312e-06,
"loss": 5.5464,
"step": 379500
},
{
"epoch": 7.13,
"learning_rate": 9.304014145442234e-06,
"loss": 5.5459,
"step": 380000
},
{
"epoch": 7.14,
"learning_rate": 9.303073624017157e-06,
"loss": 5.5432,
"step": 380500
},
{
"epoch": 7.15,
"learning_rate": 9.302133102592079e-06,
"loss": 5.5465,
"step": 381000
},
{
"epoch": 7.16,
"learning_rate": 9.301192581167e-06,
"loss": 5.54,
"step": 381500
},
{
"epoch": 7.17,
"learning_rate": 9.300252059741922e-06,
"loss": 5.5366,
"step": 382000
},
{
"epoch": 7.18,
"learning_rate": 9.299311538316844e-06,
"loss": 5.5365,
"step": 382500
},
{
"epoch": 7.19,
"learning_rate": 9.298371016891764e-06,
"loss": 5.5414,
"step": 383000
},
{
"epoch": 7.2,
"learning_rate": 9.297430495466687e-06,
"loss": 5.5331,
"step": 383500
},
{
"epoch": 7.21,
"learning_rate": 9.296489974041609e-06,
"loss": 5.5263,
"step": 384000
},
{
"epoch": 7.22,
"learning_rate": 9.295549452616531e-06,
"loss": 5.5314,
"step": 384500
},
{
"epoch": 7.23,
"learning_rate": 9.294608931191453e-06,
"loss": 5.5257,
"step": 385000
},
{
"epoch": 7.24,
"learning_rate": 9.293668409766376e-06,
"loss": 5.5242,
"step": 385500
},
{
"epoch": 7.25,
"learning_rate": 9.292727888341298e-06,
"loss": 5.5214,
"step": 386000
},
{
"epoch": 7.26,
"learning_rate": 9.29178736691622e-06,
"loss": 5.5242,
"step": 386500
},
{
"epoch": 7.27,
"learning_rate": 9.290846845491142e-06,
"loss": 5.5206,
"step": 387000
},
{
"epoch": 7.28,
"learning_rate": 9.289906324066063e-06,
"loss": 5.5174,
"step": 387500
},
{
"epoch": 7.28,
"learning_rate": 9.288965802640985e-06,
"loss": 5.5111,
"step": 388000
},
{
"epoch": 7.29,
"learning_rate": 9.288025281215907e-06,
"loss": 5.5127,
"step": 388500
},
{
"epoch": 7.3,
"learning_rate": 9.287084759790828e-06,
"loss": 5.5128,
"step": 389000
},
{
"epoch": 7.31,
"learning_rate": 9.28614423836575e-06,
"loss": 5.5124,
"step": 389500
},
{
"epoch": 7.32,
"learning_rate": 9.285203716940672e-06,
"loss": 5.5052,
"step": 390000
},
{
"epoch": 7.33,
"learning_rate": 9.284263195515595e-06,
"loss": 5.5049,
"step": 390500
},
{
"epoch": 7.34,
"learning_rate": 9.283322674090517e-06,
"loss": 5.5037,
"step": 391000
},
{
"epoch": 7.35,
"learning_rate": 9.282382152665439e-06,
"loss": 5.4997,
"step": 391500
},
{
"epoch": 7.36,
"learning_rate": 9.28144163124036e-06,
"loss": 5.5022,
"step": 392000
},
{
"epoch": 7.37,
"learning_rate": 9.280501109815282e-06,
"loss": 5.4987,
"step": 392500
},
{
"epoch": 7.38,
"learning_rate": 9.279560588390204e-06,
"loss": 5.4957,
"step": 393000
},
{
"epoch": 7.39,
"learning_rate": 9.278620066965126e-06,
"loss": 5.4947,
"step": 393500
},
{
"epoch": 7.4,
"learning_rate": 9.277679545540049e-06,
"loss": 5.4929,
"step": 394000
},
{
"epoch": 7.41,
"learning_rate": 9.276739024114971e-06,
"loss": 5.4914,
"step": 394500
},
{
"epoch": 7.42,
"learning_rate": 9.275798502689891e-06,
"loss": 5.4901,
"step": 395000
},
{
"epoch": 7.43,
"learning_rate": 9.274857981264814e-06,
"loss": 5.4874,
"step": 395500
},
{
"epoch": 7.43,
"learning_rate": 9.273917459839736e-06,
"loss": 5.4849,
"step": 396000
},
{
"epoch": 7.44,
"learning_rate": 9.272976938414656e-06,
"loss": 5.4869,
"step": 396500
},
{
"epoch": 7.45,
"learning_rate": 9.272036416989579e-06,
"loss": 5.4822,
"step": 397000
},
{
"epoch": 7.46,
"learning_rate": 9.271095895564501e-06,
"loss": 5.4793,
"step": 397500
},
{
"epoch": 7.47,
"learning_rate": 9.270155374139423e-06,
"loss": 5.4792,
"step": 398000
},
{
"epoch": 7.48,
"learning_rate": 9.269214852714345e-06,
"loss": 5.4773,
"step": 398500
},
{
"epoch": 7.49,
"learning_rate": 9.268274331289268e-06,
"loss": 5.4786,
"step": 399000
},
{
"epoch": 7.5,
"learning_rate": 9.26733380986419e-06,
"loss": 5.4753,
"step": 399500
},
{
"epoch": 7.51,
"learning_rate": 9.266393288439112e-06,
"loss": 5.4723,
"step": 400000
},
{
"epoch": 7.52,
"learning_rate": 9.265452767014034e-06,
"loss": 5.469,
"step": 400500
},
{
"epoch": 7.53,
"learning_rate": 9.264512245588955e-06,
"loss": 5.4657,
"step": 401000
},
{
"epoch": 7.54,
"learning_rate": 9.263571724163877e-06,
"loss": 5.4651,
"step": 401500
},
{
"epoch": 7.55,
"learning_rate": 9.2626312027388e-06,
"loss": 5.4609,
"step": 402000
},
{
"epoch": 7.56,
"learning_rate": 9.261690681313722e-06,
"loss": 5.4648,
"step": 402500
},
{
"epoch": 7.57,
"learning_rate": 9.260750159888642e-06,
"loss": 5.4607,
"step": 403000
},
{
"epoch": 7.58,
"learning_rate": 9.259809638463564e-06,
"loss": 5.452,
"step": 403500
},
{
"epoch": 7.59,
"learning_rate": 9.258869117038487e-06,
"loss": 5.4547,
"step": 404000
},
{
"epoch": 7.59,
"learning_rate": 9.257928595613409e-06,
"loss": 5.4544,
"step": 404500
},
{
"epoch": 7.6,
"learning_rate": 9.256988074188331e-06,
"loss": 5.4469,
"step": 405000
},
{
"epoch": 7.61,
"learning_rate": 9.256047552763253e-06,
"loss": 5.4472,
"step": 405500
},
{
"epoch": 7.62,
"learning_rate": 9.255107031338174e-06,
"loss": 5.4468,
"step": 406000
},
{
"epoch": 7.63,
"learning_rate": 9.254166509913096e-06,
"loss": 5.4402,
"step": 406500
},
{
"epoch": 7.64,
"learning_rate": 9.253225988488018e-06,
"loss": 5.4415,
"step": 407000
},
{
"epoch": 7.65,
"learning_rate": 9.25228546706294e-06,
"loss": 5.4385,
"step": 407500
},
{
"epoch": 7.66,
"learning_rate": 9.251344945637863e-06,
"loss": 5.4357,
"step": 408000
},
{
"epoch": 7.67,
"learning_rate": 9.250404424212785e-06,
"loss": 5.4338,
"step": 408500
},
{
"epoch": 7.68,
"learning_rate": 9.249463902787706e-06,
"loss": 5.4324,
"step": 409000
},
{
"epoch": 7.69,
"learning_rate": 9.248523381362628e-06,
"loss": 5.4305,
"step": 409500
},
{
"epoch": 7.7,
"learning_rate": 9.24758285993755e-06,
"loss": 5.4266,
"step": 410000
},
{
"epoch": 7.71,
"learning_rate": 9.246642338512472e-06,
"loss": 5.4292,
"step": 410500
},
{
"epoch": 7.72,
"learning_rate": 9.245701817087393e-06,
"loss": 5.4254,
"step": 411000
},
{
"epoch": 7.73,
"learning_rate": 9.244761295662315e-06,
"loss": 5.4209,
"step": 411500
},
{
"epoch": 7.74,
"learning_rate": 9.243820774237238e-06,
"loss": 5.4171,
"step": 412000
},
{
"epoch": 7.74,
"learning_rate": 9.24288025281216e-06,
"loss": 5.4161,
"step": 412500
},
{
"epoch": 7.75,
"learning_rate": 9.241939731387082e-06,
"loss": 5.4145,
"step": 413000
},
{
"epoch": 7.76,
"learning_rate": 9.240999209962004e-06,
"loss": 5.4133,
"step": 413500
},
{
"epoch": 7.77,
"learning_rate": 9.240058688536926e-06,
"loss": 5.4116,
"step": 414000
},
{
"epoch": 7.78,
"learning_rate": 9.239118167111849e-06,
"loss": 5.4073,
"step": 414500
},
{
"epoch": 7.79,
"learning_rate": 9.23817764568677e-06,
"loss": 5.4086,
"step": 415000
},
{
"epoch": 7.8,
"learning_rate": 9.237237124261692e-06,
"loss": 5.4055,
"step": 415500
},
{
"epoch": 7.81,
"learning_rate": 9.236296602836614e-06,
"loss": 5.4003,
"step": 416000
},
{
"epoch": 7.82,
"learning_rate": 9.235356081411534e-06,
"loss": 5.3987,
"step": 416500
},
{
"epoch": 7.83,
"learning_rate": 9.234415559986457e-06,
"loss": 5.3959,
"step": 417000
},
{
"epoch": 7.84,
"learning_rate": 9.233475038561379e-06,
"loss": 5.3958,
"step": 417500
},
{
"epoch": 7.85,
"learning_rate": 9.232534517136301e-06,
"loss": 5.391,
"step": 418000
},
{
"epoch": 7.86,
"learning_rate": 9.231593995711223e-06,
"loss": 5.3911,
"step": 418500
},
{
"epoch": 7.87,
"learning_rate": 9.230653474286146e-06,
"loss": 5.3832,
"step": 419000
},
{
"epoch": 7.88,
"learning_rate": 9.229712952861068e-06,
"loss": 5.3849,
"step": 419500
},
{
"epoch": 7.89,
"learning_rate": 9.228772431435988e-06,
"loss": 5.3808,
"step": 420000
},
{
"epoch": 7.89,
"learning_rate": 9.22783191001091e-06,
"loss": 5.3755,
"step": 420500
},
{
"epoch": 7.9,
"learning_rate": 9.226891388585833e-06,
"loss": 5.3824,
"step": 421000
},
{
"epoch": 7.91,
"learning_rate": 9.225950867160755e-06,
"loss": 5.372,
"step": 421500
},
{
"epoch": 7.92,
"learning_rate": 9.225010345735677e-06,
"loss": 5.3717,
"step": 422000
},
{
"epoch": 7.93,
"learning_rate": 9.224069824310598e-06,
"loss": 5.3737,
"step": 422500
},
{
"epoch": 7.94,
"learning_rate": 9.22312930288552e-06,
"loss": 5.3676,
"step": 423000
},
{
"epoch": 7.95,
"learning_rate": 9.222188781460442e-06,
"loss": 5.3653,
"step": 423500
},
{
"epoch": 7.96,
"learning_rate": 9.221248260035365e-06,
"loss": 5.3653,
"step": 424000
},
{
"epoch": 7.97,
"learning_rate": 9.220307738610287e-06,
"loss": 5.3582,
"step": 424500
},
{
"epoch": 7.98,
"learning_rate": 9.219367217185207e-06,
"loss": 5.3556,
"step": 425000
},
{
"epoch": 7.99,
"learning_rate": 9.21842669576013e-06,
"loss": 5.3559,
"step": 425500
},
{
"epoch": 8.0,
"learning_rate": 9.217486174335052e-06,
"loss": 5.3559,
"step": 426000
},
{
"epoch": 8.01,
"learning_rate": 9.216545652909974e-06,
"loss": 5.3502,
"step": 426500
},
{
"epoch": 8.02,
"learning_rate": 9.215605131484896e-06,
"loss": 5.3474,
"step": 427000
},
{
"epoch": 8.03,
"learning_rate": 9.214664610059819e-06,
"loss": 5.3449,
"step": 427500
},
{
"epoch": 8.04,
"learning_rate": 9.21372408863474e-06,
"loss": 5.3373,
"step": 428000
},
{
"epoch": 8.05,
"learning_rate": 9.212783567209661e-06,
"loss": 5.34,
"step": 428500
},
{
"epoch": 8.05,
"learning_rate": 9.211843045784584e-06,
"loss": 5.3392,
"step": 429000
},
{
"epoch": 8.06,
"learning_rate": 9.210902524359506e-06,
"loss": 5.3367,
"step": 429500
},
{
"epoch": 8.07,
"learning_rate": 9.209962002934428e-06,
"loss": 5.3296,
"step": 430000
},
{
"epoch": 8.08,
"learning_rate": 9.209021481509349e-06,
"loss": 5.3302,
"step": 430500
},
{
"epoch": 8.09,
"learning_rate": 9.20808096008427e-06,
"loss": 5.3271,
"step": 431000
},
{
"epoch": 8.1,
"learning_rate": 9.207140438659193e-06,
"loss": 5.3236,
"step": 431500
},
{
"epoch": 8.11,
"learning_rate": 9.206199917234115e-06,
"loss": 5.3197,
"step": 432000
},
{
"epoch": 8.12,
"learning_rate": 9.205259395809038e-06,
"loss": 5.3175,
"step": 432500
},
{
"epoch": 8.13,
"learning_rate": 9.20431887438396e-06,
"loss": 5.313,
"step": 433000
},
{
"epoch": 8.14,
"learning_rate": 9.203378352958882e-06,
"loss": 5.3116,
"step": 433500
},
{
"epoch": 8.15,
"learning_rate": 9.202437831533803e-06,
"loss": 5.3108,
"step": 434000
},
{
"epoch": 8.16,
"learning_rate": 9.201497310108725e-06,
"loss": 5.3075,
"step": 434500
},
{
"epoch": 8.17,
"learning_rate": 9.200556788683647e-06,
"loss": 5.3057,
"step": 435000
},
{
"epoch": 8.18,
"learning_rate": 9.19961626725857e-06,
"loss": 5.3032,
"step": 435500
},
{
"epoch": 8.19,
"learning_rate": 9.198675745833492e-06,
"loss": 5.3037,
"step": 436000
},
{
"epoch": 8.19,
"step": 436077,
"total_flos": 8.014489056685588e+17,
"train_loss": 5.961271763625358,
"train_runtime": 197998.9382,
"train_samples_per_second": 2958.985,
"train_steps_per_second": 26.9
}
],
"logging_steps": 500,
"max_steps": 5326200,
"num_train_epochs": 100,
"save_steps": 1000000,
"total_flos": 8.014489056685588e+17,
"trial_name": null,
"trial_params": null
}