npi-only-lstm-1 / checkpoint-228960 /trainer_state.json
abhinavp's picture
Training in progress, epoch 0, checkpoint
d16acb6 verified
raw
history blame
No virus
56 kB
{
"best_metric": 4.330287933349609,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-only/lstm/1/checkpoints/checkpoint-228960",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 228960,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.8191,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5474,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0562,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9904,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9436,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8394,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.682,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.5858,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993292879871958e-05,
"loss": 6.4898,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992454285120906e-05,
"loss": 6.4265,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.991615690369854e-05,
"loss": 6.3737,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990777095618801e-05,
"loss": 6.3089,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 6.2352,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 6.1763,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 6.127,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 6.0632,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 6.0303,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.9826,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.9348,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9037,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8696,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8321,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8074,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.7667,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.979875363855125e-05,
"loss": 5.749,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.979036769104073e-05,
"loss": 5.7241,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.978198174353021e-05,
"loss": 5.699,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6708,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.638,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.975684027980238e-05,
"loss": 5.6277,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.974845433229186e-05,
"loss": 5.6054,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.5934,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5672,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.5493,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714926921053515e-05,
"loss": 5.5388,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706540973542995e-05,
"loss": 5.5212,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5041,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4724,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4676,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4366,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4384,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4126,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.4148,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.3857,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963110020355577e-05,
"loss": 5.3782,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3726,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.3643,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960595873982795e-05,
"loss": 5.3487,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959757279231743e-05,
"loss": 5.3248,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958918684480691e-05,
"loss": 5.3222,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3262,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3132,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956404538107908e-05,
"loss": 5.2916,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955565943356856e-05,
"loss": 5.2797,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.2774,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.265,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.2739,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2307,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2445,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2294,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2149,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.2218,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948021866358134e-05,
"loss": 5.2001,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947183271607082e-05,
"loss": 5.19,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.94634467685603e-05,
"loss": 5.1862,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.1966,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.173,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943830530483247e-05,
"loss": 5.1667,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942991935732195e-05,
"loss": 5.152,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1446,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1489,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940477789359412e-05,
"loss": 5.1518,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.93963919460836e-05,
"loss": 5.1258,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938800599857309e-05,
"loss": 5.1368,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1374,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371250482355776e-05,
"loss": 5.1157,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 5.0994,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 5.0998,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346109018627945e-05,
"loss": 5.0942,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.0812,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329337123606905e-05,
"loss": 5.0807,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932095117609638e-05,
"loss": 5.0829,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931256522858586e-05,
"loss": 5.0821,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930417928107534e-05,
"loss": 5.0646,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295809712368554e-05,
"loss": 5.0424,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.049,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.0537,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.042,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262265922326474e-05,
"loss": 5.0399,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925389635361968e-05,
"loss": 5.0213,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.92455267849129e-05,
"loss": 5.0208,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.0139,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.0135,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 5.0129,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.9952,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.012,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 4.9972,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 4.9764,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.9733,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 4.9738,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916168368861143e-05,
"loss": 4.971,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915329774110091e-05,
"loss": 4.9701,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914491179359039e-05,
"loss": 4.9629,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913652584607987e-05,
"loss": 4.9552,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.9505,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9288,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111384382352036e-05,
"loss": 4.9351,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9102998434841516e-05,
"loss": 4.9326,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.9094612487330996e-05,
"loss": 4.9279,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.9086226539820476e-05,
"loss": 4.9228,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907784059230996e-05,
"loss": 4.9293,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906947102360317e-05,
"loss": 4.9039,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906108507609265e-05,
"loss": 4.9066,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905269912858213e-05,
"loss": 4.9007,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904431318107161e-05,
"loss": 4.9075,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903592723356109e-05,
"loss": 4.9122,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027541286050565e-05,
"loss": 4.8949,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901917171734378e-05,
"loss": 4.8927,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901078576983326e-05,
"loss": 4.8831,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900239982232274e-05,
"loss": 4.8897,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994013874812214e-05,
"loss": 4.8835,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.89856279273017e-05,
"loss": 4.8797,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897724197979118e-05,
"loss": 4.8706,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.896885603228066e-05,
"loss": 4.8661,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.896047008477014e-05,
"loss": 4.8592,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895208413725962e-05,
"loss": 4.8493,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.894371456855283e-05,
"loss": 4.8547,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893532862104231e-05,
"loss": 4.8485,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892694267353179e-05,
"loss": 4.8435,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891855672602127e-05,
"loss": 4.8358,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891017077851075e-05,
"loss": 4.8512,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890178483100023e-05,
"loss": 4.8501,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889341526229344e-05,
"loss": 4.8396,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888504569358665e-05,
"loss": 4.8285,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.8876659746076134e-05,
"loss": 4.8275,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.8868273798565614e-05,
"loss": 4.8306,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.8859887851055094e-05,
"loss": 4.8264,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.8851501903544574e-05,
"loss": 4.8222,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.8843115956034054e-05,
"loss": 4.8184,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.8834730008523534e-05,
"loss": 4.815,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.8826344061013014e-05,
"loss": 4.8085,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.8817958113502494e-05,
"loss": 4.8032,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809572165991974e-05,
"loss": 4.8079,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801186218481454e-05,
"loss": 4.7961,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879281664977466e-05,
"loss": 4.7909,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878443070226414e-05,
"loss": 4.7983,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877604475475362e-05,
"loss": 4.7846,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87676588072431e-05,
"loss": 4.793,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875927285973258e-05,
"loss": 4.782,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.87509032910258e-05,
"loss": 4.7741,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.741952896118164,
"eval_runtime": 347.3647,
"eval_samples_per_second": 1098.531,
"eval_steps_per_second": 34.33,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874251734351528e-05,
"loss": 4.7684,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873413139600475e-05,
"loss": 4.7679,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872576182729797e-05,
"loss": 4.7801,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871737587978745e-05,
"loss": 4.7668,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870898993227693e-05,
"loss": 4.7692,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.87006039847664e-05,
"loss": 4.756,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869221803725588e-05,
"loss": 4.7591,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868383208974536e-05,
"loss": 4.743,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867544614223484e-05,
"loss": 4.7566,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866706019472432e-05,
"loss": 4.7545,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.86586742472138e-05,
"loss": 4.7603,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.8650304678507016e-05,
"loss": 4.7405,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8641918730996496e-05,
"loss": 4.7387,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633532783485976e-05,
"loss": 4.7343,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625146835975456e-05,
"loss": 4.726,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616760888464936e-05,
"loss": 4.7295,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608374940954416e-05,
"loss": 4.7363,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.8600005372247625e-05,
"loss": 4.7194,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591619424737105e-05,
"loss": 4.7201,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583233477226585e-05,
"loss": 4.735,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574847529716065e-05,
"loss": 4.7232,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566477961009274e-05,
"loss": 4.7218,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558092013498754e-05,
"loss": 4.7101,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854970606598824e-05,
"loss": 4.7232,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854132011847772e-05,
"loss": 4.7093,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.85329341709672e-05,
"loss": 4.7072,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852456460226041e-05,
"loss": 4.703,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851617865474989e-05,
"loss": 4.6972,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850779270723937e-05,
"loss": 4.6902,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849940675972885e-05,
"loss": 4.692,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849102081221833e-05,
"loss": 4.7025,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848263486470781e-05,
"loss": 4.6971,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847426529600102e-05,
"loss": 4.6882,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.84658793484905e-05,
"loss": 4.6979,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845749340097998e-05,
"loss": 4.6894,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844910745346946e-05,
"loss": 4.6875,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.8440737884762674e-05,
"loss": 4.6746,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.8432351937252154e-05,
"loss": 4.6753,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.8423965989741634e-05,
"loss": 4.6641,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.8415580042231114e-05,
"loss": 4.6747,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840721047352432e-05,
"loss": 4.6601,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.83988245260138e-05,
"loss": 4.6734,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839043857850328e-05,
"loss": 4.6556,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838205263099276e-05,
"loss": 4.6638,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373666683482236e-05,
"loss": 4.6621,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365280735971716e-05,
"loss": 4.6611,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8356894788461196e-05,
"loss": 4.6551,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834852521975441e-05,
"loss": 4.6433,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834013927224389e-05,
"loss": 4.6412,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833175332473337e-05,
"loss": 4.659,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832336737722285e-05,
"loss": 4.6489,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831498142971233e-05,
"loss": 4.6443,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830659548220181e-05,
"loss": 4.6313,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829820953469129e-05,
"loss": 4.6415,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.82898399659845e-05,
"loss": 4.6282,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828145401847398e-05,
"loss": 4.6545,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827306807096346e-05,
"loss": 4.6175,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826468212345294e-05,
"loss": 4.6399,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825629617594242e-05,
"loss": 4.6293,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.82479102284319e-05,
"loss": 4.6187,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823952428092138e-05,
"loss": 4.6296,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823113833341086e-05,
"loss": 4.6248,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222768764704077e-05,
"loss": 4.6091,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214382817193557e-05,
"loss": 4.6171,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8205996869683037e-05,
"loss": 4.6293,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197610922172516e-05,
"loss": 4.6132,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189241353465726e-05,
"loss": 4.6107,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180855405955206e-05,
"loss": 4.6082,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172502216052144e-05,
"loss": 4.6029,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164116268541624e-05,
"loss": 4.6119,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155730321031104e-05,
"loss": 4.6251,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147344373520584e-05,
"loss": 4.5999,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138958426010064e-05,
"loss": 4.6179,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813057247849955e-05,
"loss": 4.6179,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812218653098903e-05,
"loss": 4.6057,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811380058347851e-05,
"loss": 4.5928,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810541463596799e-05,
"loss": 4.6043,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809702868845747e-05,
"loss": 4.5988,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808864274094695e-05,
"loss": 4.5911,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808025679343642e-05,
"loss": 4.5924,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807188722472964e-05,
"loss": 4.5963,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806350127721912e-05,
"loss": 4.6038,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.80551153297086e-05,
"loss": 4.5919,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804672938219807e-05,
"loss": 4.5764,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803835981349129e-05,
"loss": 4.5863,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.802997386598077e-05,
"loss": 4.5889,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802158791847025e-05,
"loss": 4.5849,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801320197095973e-05,
"loss": 4.5908,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004832402252944e-05,
"loss": 4.5767,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996446454742424e-05,
"loss": 4.5708,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.79880605072319e-05,
"loss": 4.5729,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797967455972138e-05,
"loss": 4.5769,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797130499101459e-05,
"loss": 4.5755,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796291904350407e-05,
"loss": 4.5669,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954533095993546e-05,
"loss": 4.5889,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946147148483026e-05,
"loss": 4.5758,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937761200972506e-05,
"loss": 4.5584,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929375253461986e-05,
"loss": 4.5614,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792098930595147e-05,
"loss": 4.5651,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791261973724468e-05,
"loss": 4.5648,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790423378973416e-05,
"loss": 4.5645,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789584784222364e-05,
"loss": 4.5614,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788746189471312e-05,
"loss": 4.556,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.78790759472026e-05,
"loss": 4.56,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.787068999969208e-05,
"loss": 4.5356,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786230405218156e-05,
"loss": 4.5516,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785391810467104e-05,
"loss": 4.5463,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784554853596425e-05,
"loss": 4.5496,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783717896725746e-05,
"loss": 4.5434,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782879301974694e-05,
"loss": 4.5531,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782040707223642e-05,
"loss": 4.5343,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812021124725906e-05,
"loss": 4.5372,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803635177215386e-05,
"loss": 4.5391,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795249229704866e-05,
"loss": 4.5392,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786863282194346e-05,
"loss": 4.553,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778477334683826e-05,
"loss": 4.542,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770091387173306e-05,
"loss": 4.5389,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761705439662786e-05,
"loss": 4.5328,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.7753352249759724e-05,
"loss": 4.5381,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7744966302249204e-05,
"loss": 4.5379,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736580354738684e-05,
"loss": 4.5299,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728194407228164e-05,
"loss": 4.5315,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719808459717644e-05,
"loss": 4.526,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711422512207124e-05,
"loss": 4.5235,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703036564696604e-05,
"loss": 4.5155,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694650617186084e-05,
"loss": 4.5208,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.76862810484793e-05,
"loss": 4.5158,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767791147977251e-05,
"loss": 4.5227,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766952553226199e-05,
"loss": 4.5068,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766113958475147e-05,
"loss": 4.5297,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765275363724095e-05,
"loss": 4.5347,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764438406853416e-05,
"loss": 4.5192,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763599812102364e-05,
"loss": 4.5134,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762761217351312e-05,
"loss": 4.5143,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.76192262260026e-05,
"loss": 4.5187,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761084027849208e-05,
"loss": 4.5203,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760245433098156e-05,
"loss": 4.5122,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759406838347104e-05,
"loss": 4.5129,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758568243596052e-05,
"loss": 4.5091,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757729648845e-05,
"loss": 4.5123,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756891054093948e-05,
"loss": 4.5042,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756052459342896e-05,
"loss": 4.5134,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755213864591844e-05,
"loss": 4.5023,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543785456015375e-05,
"loss": 4.4979,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535399508504855e-05,
"loss": 4.5086,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527013560994335e-05,
"loss": 4.4967,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518627613483815e-05,
"loss": 4.5055,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510241665973295e-05,
"loss": 4.4936,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750185571846278e-05,
"loss": 4.4915,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.463145732879639,
"eval_runtime": 354.3654,
"eval_samples_per_second": 1076.829,
"eval_steps_per_second": 33.652,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749346977095226e-05,
"loss": 4.49,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748508382344174e-05,
"loss": 4.4806,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747669787593122e-05,
"loss": 4.5043,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.74683119284207e-05,
"loss": 4.4889,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745992598091018e-05,
"loss": 4.4979,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745154003339966e-05,
"loss": 4.4814,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744315408588914e-05,
"loss": 4.4901,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743476813837862e-05,
"loss": 4.4715,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426382190868095e-05,
"loss": 4.4877,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7417996243357575e-05,
"loss": 4.4914,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409610295847055e-05,
"loss": 4.4922,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401224348336535e-05,
"loss": 4.4831,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392838400826015e-05,
"loss": 4.4717,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384452453315495e-05,
"loss": 4.4745,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376066505804975e-05,
"loss": 4.4694,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736768055829446e-05,
"loss": 4.4726,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735929461078394e-05,
"loss": 4.4791,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735092504207715e-05,
"loss": 4.4653,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734253909456663e-05,
"loss": 4.4677,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733415314705611e-05,
"loss": 4.4889,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732578357834932e-05,
"loss": 4.4729,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.73173976308388e-05,
"loss": 4.4754,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730901168332828e-05,
"loss": 4.4647,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730062573581776e-05,
"loss": 4.4819,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729223978830724e-05,
"loss": 4.4592,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728385384079672e-05,
"loss": 4.4666,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.72754678932862e-05,
"loss": 4.4612,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726708194577568e-05,
"loss": 4.462,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725869599826516e-05,
"loss": 4.4481,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725031005075464e-05,
"loss": 4.4558,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724192410324412e-05,
"loss": 4.4639,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233554534537335e-05,
"loss": 4.4641,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722516858702681e-05,
"loss": 4.4589,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721678263951629e-05,
"loss": 4.4603,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720839669200577e-05,
"loss": 4.4573,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200027123298984e-05,
"loss": 4.4596,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719167393339592e-05,
"loss": 4.4456,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71832879858854e-05,
"loss": 4.4484,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717490203837488e-05,
"loss": 4.4392,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716651609086437e-05,
"loss": 4.4543,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715813014335385e-05,
"loss": 4.4382,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714974419584333e-05,
"loss": 4.4487,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714135824833281e-05,
"loss": 4.4401,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713297230082228e-05,
"loss": 4.4409,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712458635331176e-05,
"loss": 4.449,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711621678460498e-05,
"loss": 4.44,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710783083709446e-05,
"loss": 4.4411,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709944488958393e-05,
"loss": 4.4249,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709105894207341e-05,
"loss": 4.4301,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082689373366627e-05,
"loss": 4.4441,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074303425856106e-05,
"loss": 4.4357,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7065917478345586e-05,
"loss": 4.436,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057531530835066e-05,
"loss": 4.4212,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.7049145583324546e-05,
"loss": 4.4338,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040776014617755e-05,
"loss": 4.4206,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032390067107235e-05,
"loss": 4.4457,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024004119596715e-05,
"loss": 4.4139,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015618172086195e-05,
"loss": 4.4341,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007232224575675e-05,
"loss": 4.4279,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998846277065155e-05,
"loss": 4.4125,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990460329554635e-05,
"loss": 4.4232,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982074382044115e-05,
"loss": 4.4271,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973704813337324e-05,
"loss": 4.4103,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965318865826804e-05,
"loss": 4.4185,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695693291831629e-05,
"loss": 4.4273,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.69485633496095e-05,
"loss": 4.4188,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694017740209898e-05,
"loss": 4.4127,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693179145458846e-05,
"loss": 4.4145,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692340550707794e-05,
"loss": 4.4069,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691503593837115e-05,
"loss": 4.4192,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690664999086063e-05,
"loss": 4.4339,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689826404335011e-05,
"loss": 4.4092,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688987809583959e-05,
"loss": 4.4267,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688149214832907e-05,
"loss": 4.4256,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687310620081855e-05,
"loss": 4.4177,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686472025330803e-05,
"loss": 4.4024,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856350684601245e-05,
"loss": 4.421,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6847981115894454e-05,
"loss": 4.411,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839595168383934e-05,
"loss": 4.4095,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831209220873414e-05,
"loss": 4.4062,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822823273362894e-05,
"loss": 4.4113,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814437325852373e-05,
"loss": 4.4249,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806051378341853e-05,
"loss": 4.4079,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797665430831333e-05,
"loss": 4.3941,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678929586212454e-05,
"loss": 4.4025,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678090991461402e-05,
"loss": 4.4084,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.67725239671035e-05,
"loss": 4.4079,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676413801959298e-05,
"loss": 4.4135,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675575207208246e-05,
"loss": 4.3973,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674736612457194e-05,
"loss": 4.396,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673898017706142e-05,
"loss": 4.3902,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.67305942295509e-05,
"loss": 4.3978,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672220828204038e-05,
"loss": 4.4004,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671382233452986e-05,
"loss": 4.399,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670545276582307e-05,
"loss": 4.4168,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669706681831255e-05,
"loss": 4.3953,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668868087080203e-05,
"loss": 4.3918,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668029492329151e-05,
"loss": 4.3888,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667190897578099e-05,
"loss": 4.3919,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.66635394070742e-05,
"loss": 4.3973,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665515345956368e-05,
"loss": 4.3959,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664676751205316e-05,
"loss": 4.3908,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663838156454265e-05,
"loss": 4.3875,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.662999561703213e-05,
"loss": 4.3946,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662160966952161e-05,
"loss": 4.3699,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661322372201109e-05,
"loss": 4.3875,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6604837774500567e-05,
"loss": 4.3795,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596484584597505e-05,
"loss": 4.3851,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588098637086985e-05,
"loss": 4.3804,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579712689576465e-05,
"loss": 4.3902,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571326742065945e-05,
"loss": 4.3719,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6562940794555425e-05,
"loss": 4.3729,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554571225848634e-05,
"loss": 4.3828,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546185278338114e-05,
"loss": 4.3745,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.65377993308276e-05,
"loss": 4.3944,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652941338331708e-05,
"loss": 4.3859,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652104381461029e-05,
"loss": 4.3842,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651265786709977e-05,
"loss": 4.3719,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650427191958925e-05,
"loss": 4.3777,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649588597207873e-05,
"loss": 4.3802,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648750002456821e-05,
"loss": 4.3765,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647911407705769e-05,
"loss": 4.3774,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647072812954717e-05,
"loss": 4.3667,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646234218203665e-05,
"loss": 4.3733,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645395623452612e-05,
"loss": 4.363,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.64455702870156e-05,
"loss": 4.3685,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643720071830882e-05,
"loss": 4.365,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428831149602034e-05,
"loss": 4.3689,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420445202091514e-05,
"loss": 4.355,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412059254580994e-05,
"loss": 4.3806,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403673307070474e-05,
"loss": 4.3818,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639528735955995e-05,
"loss": 4.3732,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638691779085316e-05,
"loss": 4.3591,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637853184334264e-05,
"loss": 4.3679,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637014589583212e-05,
"loss": 4.3683,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6361759948321596e-05,
"loss": 4.3747,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353374000811076e-05,
"loss": 4.3658,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6344988053300556e-05,
"loss": 4.3644,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336602105790036e-05,
"loss": 4.3636,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632821615827952e-05,
"loss": 4.3695,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6319830210769e-05,
"loss": 4.3613,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631144426325848e-05,
"loss": 4.3671,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630305831574796e-05,
"loss": 4.3593,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629467236823744e-05,
"loss": 4.3565,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628630279953065e-05,
"loss": 4.3658,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627793323082386e-05,
"loss": 4.3593,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626954728331334e-05,
"loss": 4.3577,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626116133580282e-05,
"loss": 4.3518,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625279176709603e-05,
"loss": 4.3483,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.330287933349609,
"eval_runtime": 302.6809,
"eval_samples_per_second": 1260.704,
"eval_steps_per_second": 39.398,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 9.477738216745003e+16,
"trial_name": null,
"trial_params": null
}