abhinavp's picture
Training in progress, epoch 0, checkpoint
df82a13 verified
{
"best_metric": 4.488372802734375,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl/lstm/1/checkpoints/checkpoint-152638",
"epoch": 0.025000278439663435,
"eval_steps": 10,
"global_step": 152638,
"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": 10.8173,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5621,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0552,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9778,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9512,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8598,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7142,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6064,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5223,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4391,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.405,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.347,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2854,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.2171,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1624,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.1169,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0706,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 6.0137,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9735,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984066699730012e-05,
"loss": 5.9362,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8977,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8699,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8394,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.807,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7783,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7604,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7276,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.7055,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6716,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.667,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6342,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.6179,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.6075,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.589,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714926921053515e-05,
"loss": 5.5594,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706540973542995e-05,
"loss": 5.5456,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5373,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.9689785457325684e-05,
"loss": 5.5153,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.9681399509815164e-05,
"loss": 5.5032,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.9673013562304644e-05,
"loss": 5.4829,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4577,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4464,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.4322,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.4251,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.4132,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.4073,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.3832,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960595873982795e-05,
"loss": 5.3828,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959757279231743e-05,
"loss": 5.3878,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3593,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3489,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3364,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956404538107908e-05,
"loss": 5.3456,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955565943356856e-05,
"loss": 5.3071,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 5.3256,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 5.2948,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 5.2928,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 5.2861,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 5.2759,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 5.2628,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 5.2518,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 5.2376,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2442,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 5.2314,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 5.2213,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2138,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.2024,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1858,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.203,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1795,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1736,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940477789359412e-05,
"loss": 5.1824,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.93963919460836e-05,
"loss": 5.1575,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.1701,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1621,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371250482355776e-05,
"loss": 5.1505,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1492,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935447858733473e-05,
"loss": 5.1231,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934609263982421e-05,
"loss": 5.1214,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933770669231369e-05,
"loss": 5.1192,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329337123606905e-05,
"loss": 5.1184,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932095117609638e-05,
"loss": 5.1077,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931256522858586e-05,
"loss": 5.0946,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930417928107534e-05,
"loss": 5.0808,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295793333564825e-05,
"loss": 5.0878,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287407386054305e-05,
"loss": 5.0868,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.0809,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.0794,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262265922326474e-05,
"loss": 5.0745,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.9253879974815954e-05,
"loss": 5.0617,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.9245494027305433e-05,
"loss": 5.0432,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923712445859864e-05,
"loss": 5.0402,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922873851108812e-05,
"loss": 5.0459,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92203525635776e-05,
"loss": 5.0425,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921196661606708e-05,
"loss": 5.0189,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920359704736029e-05,
"loss": 5.0237,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 5.0224,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918682515233926e-05,
"loss": 5.0212,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917843920482874e-05,
"loss": 5.0117,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917005325731822e-05,
"loss": 5.0127,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916168368861143e-05,
"loss": 5.0045,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915329774110091e-05,
"loss": 4.9936,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914491179359039e-05,
"loss": 4.9952,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913652584607987e-05,
"loss": 4.9946,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912813989856935e-05,
"loss": 4.9785,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9824,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111384382352036e-05,
"loss": 4.9603,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9102998434841516e-05,
"loss": 4.9551,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.9094612487330996e-05,
"loss": 4.9542,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.9086226539820476e-05,
"loss": 4.9587,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907784059230996e-05,
"loss": 4.9513,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906945464479944e-05,
"loss": 4.9289,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906106869728892e-05,
"loss": 4.9339,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905269912858213e-05,
"loss": 4.9377,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904431318107161e-05,
"loss": 4.9436,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903592723356109e-05,
"loss": 4.9289,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.90275576648543e-05,
"loss": 4.9288,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.9254,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901080214863699e-05,
"loss": 4.9262,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.9102,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899403025361595e-05,
"loss": 4.9102,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.898564430610543e-05,
"loss": 4.9012,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897725835859491e-05,
"loss": 4.905,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968872411084396e-05,
"loss": 4.8878,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.896048646357387e-05,
"loss": 4.8999,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895210051606335e-05,
"loss": 4.8903,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.8972,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893534499984604e-05,
"loss": 4.8688,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8801,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8895,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.8614,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890181758860769e-05,
"loss": 4.882,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889343164109717e-05,
"loss": 4.8646,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888504569358665e-05,
"loss": 4.868,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.8876659746076134e-05,
"loss": 4.8582,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.8868273798565614e-05,
"loss": 4.8538,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.8859887851055094e-05,
"loss": 4.8555,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.8851501903544574e-05,
"loss": 4.8526,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.8526,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883474638732726e-05,
"loss": 4.8449,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882636043981674e-05,
"loss": 4.8474,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881797449230622e-05,
"loss": 4.8465,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88095885447957e-05,
"loss": 4.8267,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880120259728518e-05,
"loss": 4.8271,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879283302857839e-05,
"loss": 4.818,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878444708106787e-05,
"loss": 4.8204,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877606113355735e-05,
"loss": 4.8187,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876767518604683e-05,
"loss": 4.8119,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875930561734005e-05,
"loss": 4.8099,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875091966982953e-05,
"loss": 4.8102,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.7706427574157715,
"eval_runtime": 545.2364,
"eval_samples_per_second": 699.863,
"eval_steps_per_second": 21.871,
"step": 76319
},
{
"epoch": 0.0,
"learning_rate": 4.874253372231901e-05,
"loss": 4.819,
"step": 76800
},
{
"epoch": 0.0,
"learning_rate": 4.873414777480849e-05,
"loss": 4.8106,
"step": 77312
},
{
"epoch": 0.0,
"learning_rate": 4.872576182729797e-05,
"loss": 4.7982,
"step": 77824
},
{
"epoch": 0.0,
"learning_rate": 4.871737587978745e-05,
"loss": 4.8001,
"step": 78336
},
{
"epoch": 0.0,
"learning_rate": 4.870898993227693e-05,
"loss": 4.7934,
"step": 78848
},
{
"epoch": 0.0,
"learning_rate": 4.87006039847664e-05,
"loss": 4.7726,
"step": 79360
},
{
"epoch": 0.0,
"learning_rate": 4.869221803725588e-05,
"loss": 4.785,
"step": 79872
},
{
"epoch": 0.0,
"learning_rate": 4.868383208974536e-05,
"loss": 4.7882,
"step": 80384
},
{
"epoch": 0.0,
"learning_rate": 4.867544614223484e-05,
"loss": 4.7692,
"step": 80896
},
{
"epoch": 0.0,
"learning_rate": 4.866706019472432e-05,
"loss": 4.785,
"step": 81408
},
{
"epoch": 0.0,
"learning_rate": 4.86586742472138e-05,
"loss": 4.7886,
"step": 81920
},
{
"epoch": 0.0,
"learning_rate": 4.865028829970329e-05,
"loss": 4.7729,
"step": 82432
},
{
"epoch": 0.0,
"learning_rate": 4.864190235219277e-05,
"loss": 4.7658,
"step": 82944
},
{
"epoch": 0.0,
"learning_rate": 4.863351640468225e-05,
"loss": 4.7677,
"step": 83456
},
{
"epoch": 0.0,
"learning_rate": 4.862513045717173e-05,
"loss": 4.767,
"step": 83968
},
{
"epoch": 0.0,
"learning_rate": 4.861674450966121e-05,
"loss": 4.7616,
"step": 84480
},
{
"epoch": 0.0,
"learning_rate": 4.860835856215069e-05,
"loss": 4.7565,
"step": 84992
},
{
"epoch": 0.0,
"learning_rate": 4.859997261464017e-05,
"loss": 4.756,
"step": 85504
},
{
"epoch": 0.0,
"learning_rate": 4.859158666712964e-05,
"loss": 4.7509,
"step": 86016
},
{
"epoch": 0.0,
"learning_rate": 4.8583233477226585e-05,
"loss": 4.7549,
"step": 86528
},
{
"epoch": 0.0,
"learning_rate": 4.8574847529716065e-05,
"loss": 4.7551,
"step": 87040
},
{
"epoch": 0.0,
"learning_rate": 4.8566461582205545e-05,
"loss": 4.7543,
"step": 87552
},
{
"epoch": 0.0,
"learning_rate": 4.8558075634695025e-05,
"loss": 4.7496,
"step": 88064
},
{
"epoch": 0.0,
"learning_rate": 4.8549689687184505e-05,
"loss": 4.7474,
"step": 88576
},
{
"epoch": 0.0,
"learning_rate": 4.854132011847772e-05,
"loss": 4.7419,
"step": 89088
},
{
"epoch": 0.0,
"learning_rate": 4.85329341709672e-05,
"loss": 4.7387,
"step": 89600
},
{
"epoch": 0.0,
"learning_rate": 4.852454822345668e-05,
"loss": 4.7425,
"step": 90112
},
{
"epoch": 0.0,
"learning_rate": 4.851616227594616e-05,
"loss": 4.723,
"step": 90624
},
{
"epoch": 0.0,
"learning_rate": 4.850777632843564e-05,
"loss": 4.7354,
"step": 91136
},
{
"epoch": 0.01,
"learning_rate": 4.8499390380925114e-05,
"loss": 4.7177,
"step": 91648
},
{
"epoch": 0.01,
"learning_rate": 4.8491004433414594e-05,
"loss": 4.722,
"step": 92160
},
{
"epoch": 0.01,
"learning_rate": 4.8482618485904074e-05,
"loss": 4.7319,
"step": 92672
},
{
"epoch": 0.01,
"learning_rate": 4.847424891719729e-05,
"loss": 4.7296,
"step": 93184
},
{
"epoch": 0.01,
"learning_rate": 4.846586296968676e-05,
"loss": 4.715,
"step": 93696
},
{
"epoch": 0.01,
"learning_rate": 4.845747702217624e-05,
"loss": 4.707,
"step": 94208
},
{
"epoch": 0.01,
"learning_rate": 4.844910745346946e-05,
"loss": 4.7239,
"step": 94720
},
{
"epoch": 0.01,
"learning_rate": 4.844072150595894e-05,
"loss": 4.7108,
"step": 95232
},
{
"epoch": 0.01,
"learning_rate": 4.843233555844842e-05,
"loss": 4.7093,
"step": 95744
},
{
"epoch": 0.01,
"learning_rate": 4.84239496109379e-05,
"loss": 4.7055,
"step": 96256
},
{
"epoch": 0.01,
"learning_rate": 4.841556366342738e-05,
"loss": 4.6932,
"step": 96768
},
{
"epoch": 0.01,
"learning_rate": 4.840717771591686e-05,
"loss": 4.6894,
"step": 97280
},
{
"epoch": 0.01,
"learning_rate": 4.839879176840634e-05,
"loss": 4.6913,
"step": 97792
},
{
"epoch": 0.01,
"learning_rate": 4.839040582089582e-05,
"loss": 4.6954,
"step": 98304
},
{
"epoch": 0.01,
"learning_rate": 4.83820198733853e-05,
"loss": 4.6896,
"step": 98816
},
{
"epoch": 0.01,
"learning_rate": 4.837363392587478e-05,
"loss": 4.6924,
"step": 99328
},
{
"epoch": 0.01,
"learning_rate": 4.836524797836426e-05,
"loss": 4.6844,
"step": 99840
},
{
"epoch": 0.01,
"learning_rate": 4.835686203085374e-05,
"loss": 4.6879,
"step": 100352
},
{
"epoch": 0.01,
"learning_rate": 4.834849246214695e-05,
"loss": 4.6993,
"step": 100864
},
{
"epoch": 0.01,
"learning_rate": 4.834010651463643e-05,
"loss": 4.6794,
"step": 101376
},
{
"epoch": 0.01,
"learning_rate": 4.833172056712591e-05,
"loss": 4.6801,
"step": 101888
},
{
"epoch": 0.01,
"learning_rate": 4.832333461961539e-05,
"loss": 4.6698,
"step": 102400
},
{
"epoch": 0.01,
"learning_rate": 4.8314948672104874e-05,
"loss": 4.6902,
"step": 102912
},
{
"epoch": 0.01,
"learning_rate": 4.830657910339808e-05,
"loss": 4.6616,
"step": 103424
},
{
"epoch": 0.01,
"learning_rate": 4.829819315588756e-05,
"loss": 4.6838,
"step": 103936
},
{
"epoch": 0.01,
"learning_rate": 4.828982358718077e-05,
"loss": 4.6604,
"step": 104448
},
{
"epoch": 0.01,
"learning_rate": 4.828143763967025e-05,
"loss": 4.6699,
"step": 104960
},
{
"epoch": 0.01,
"learning_rate": 4.827305169215973e-05,
"loss": 4.6682,
"step": 105472
},
{
"epoch": 0.01,
"learning_rate": 4.826466574464921e-05,
"loss": 4.6641,
"step": 105984
},
{
"epoch": 0.01,
"learning_rate": 4.825627979713869e-05,
"loss": 4.6559,
"step": 106496
},
{
"epoch": 0.01,
"learning_rate": 4.824789384962817e-05,
"loss": 4.6559,
"step": 107008
},
{
"epoch": 0.01,
"learning_rate": 4.823950790211765e-05,
"loss": 4.6452,
"step": 107520
},
{
"epoch": 0.01,
"learning_rate": 4.8231121954607125e-05,
"loss": 4.6602,
"step": 108032
},
{
"epoch": 0.01,
"learning_rate": 4.822273600709661e-05,
"loss": 4.6511,
"step": 108544
},
{
"epoch": 0.01,
"learning_rate": 4.821435005958609e-05,
"loss": 4.6454,
"step": 109056
},
{
"epoch": 0.01,
"learning_rate": 4.82059804908793e-05,
"loss": 4.6438,
"step": 109568
},
{
"epoch": 0.01,
"learning_rate": 4.819759454336878e-05,
"loss": 4.6443,
"step": 110080
},
{
"epoch": 0.01,
"learning_rate": 4.818920859585826e-05,
"loss": 4.6261,
"step": 110592
},
{
"epoch": 0.01,
"learning_rate": 4.818082264834774e-05,
"loss": 4.65,
"step": 111104
},
{
"epoch": 0.01,
"learning_rate": 4.817245307964095e-05,
"loss": 4.6354,
"step": 111616
},
{
"epoch": 0.01,
"learning_rate": 4.816406713213043e-05,
"loss": 4.6349,
"step": 112128
},
{
"epoch": 0.01,
"learning_rate": 4.815568118461991e-05,
"loss": 4.6435,
"step": 112640
},
{
"epoch": 0.01,
"learning_rate": 4.814729523710939e-05,
"loss": 4.6292,
"step": 113152
},
{
"epoch": 0.01,
"learning_rate": 4.813890928959887e-05,
"loss": 4.6431,
"step": 113664
},
{
"epoch": 0.01,
"learning_rate": 4.813053972089208e-05,
"loss": 4.6458,
"step": 114176
},
{
"epoch": 0.01,
"learning_rate": 4.8122153773381565e-05,
"loss": 4.6363,
"step": 114688
},
{
"epoch": 0.01,
"learning_rate": 4.8113767825871045e-05,
"loss": 4.6383,
"step": 115200
},
{
"epoch": 0.01,
"learning_rate": 4.8105381878360525e-05,
"loss": 4.6205,
"step": 115712
},
{
"epoch": 0.01,
"learning_rate": 4.8096995930850005e-05,
"loss": 4.6156,
"step": 116224
},
{
"epoch": 0.01,
"learning_rate": 4.8088609983339485e-05,
"loss": 4.6269,
"step": 116736
},
{
"epoch": 0.01,
"learning_rate": 4.8080240414632694e-05,
"loss": 4.6279,
"step": 117248
},
{
"epoch": 0.01,
"learning_rate": 4.8071854467122174e-05,
"loss": 4.6204,
"step": 117760
},
{
"epoch": 0.01,
"learning_rate": 4.8063468519611654e-05,
"loss": 4.6159,
"step": 118272
},
{
"epoch": 0.01,
"learning_rate": 4.8055082572101134e-05,
"loss": 4.5988,
"step": 118784
},
{
"epoch": 0.01,
"learning_rate": 4.8046696624590614e-05,
"loss": 4.61,
"step": 119296
},
{
"epoch": 0.01,
"learning_rate": 4.8038310677080094e-05,
"loss": 4.6138,
"step": 119808
},
{
"epoch": 0.01,
"learning_rate": 4.8029924729569574e-05,
"loss": 4.6127,
"step": 120320
},
{
"epoch": 0.01,
"learning_rate": 4.8021538782059054e-05,
"loss": 4.6194,
"step": 120832
},
{
"epoch": 0.01,
"learning_rate": 4.8013152834548534e-05,
"loss": 4.6174,
"step": 121344
},
{
"epoch": 0.01,
"learning_rate": 4.800478326584174e-05,
"loss": 4.607,
"step": 121856
},
{
"epoch": 0.02,
"learning_rate": 4.799639731833123e-05,
"loss": 4.5994,
"step": 122368
},
{
"epoch": 0.02,
"learning_rate": 4.798802774962444e-05,
"loss": 4.5926,
"step": 122880
},
{
"epoch": 0.02,
"learning_rate": 4.797964180211392e-05,
"loss": 4.599,
"step": 123392
},
{
"epoch": 0.02,
"learning_rate": 4.79712558546034e-05,
"loss": 4.6017,
"step": 123904
},
{
"epoch": 0.02,
"learning_rate": 4.796286990709288e-05,
"loss": 4.5893,
"step": 124416
},
{
"epoch": 0.02,
"learning_rate": 4.795448395958236e-05,
"loss": 4.5903,
"step": 124928
},
{
"epoch": 0.02,
"learning_rate": 4.794611439087557e-05,
"loss": 4.5981,
"step": 125440
},
{
"epoch": 0.02,
"learning_rate": 4.793772844336505e-05,
"loss": 4.6013,
"step": 125952
},
{
"epoch": 0.02,
"learning_rate": 4.792934249585453e-05,
"loss": 4.5899,
"step": 126464
},
{
"epoch": 0.02,
"learning_rate": 4.792095654834401e-05,
"loss": 4.596,
"step": 126976
},
{
"epoch": 0.02,
"learning_rate": 4.791257060083349e-05,
"loss": 4.5978,
"step": 127488
},
{
"epoch": 0.02,
"learning_rate": 4.790418465332297e-05,
"loss": 4.5883,
"step": 128000
},
{
"epoch": 0.02,
"learning_rate": 4.789579870581245e-05,
"loss": 4.585,
"step": 128512
},
{
"epoch": 0.02,
"learning_rate": 4.788741275830193e-05,
"loss": 4.5951,
"step": 129024
},
{
"epoch": 0.02,
"learning_rate": 4.7879043189595136e-05,
"loss": 4.5802,
"step": 129536
},
{
"epoch": 0.02,
"learning_rate": 4.7870657242084616e-05,
"loss": 4.5931,
"step": 130048
},
{
"epoch": 0.02,
"learning_rate": 4.786228767337783e-05,
"loss": 4.573,
"step": 130560
},
{
"epoch": 0.02,
"learning_rate": 4.785390172586731e-05,
"loss": 4.5631,
"step": 131072
},
{
"epoch": 0.02,
"learning_rate": 4.7845515778356785e-05,
"loss": 4.5704,
"step": 131584
},
{
"epoch": 0.02,
"learning_rate": 4.7837129830846265e-05,
"loss": 4.5787,
"step": 132096
},
{
"epoch": 0.02,
"learning_rate": 4.782876026213948e-05,
"loss": 4.572,
"step": 132608
},
{
"epoch": 0.02,
"learning_rate": 4.782037431462896e-05,
"loss": 4.5589,
"step": 133120
},
{
"epoch": 0.02,
"learning_rate": 4.7811988367118434e-05,
"loss": 4.559,
"step": 133632
},
{
"epoch": 0.02,
"learning_rate": 4.780360241960792e-05,
"loss": 4.5672,
"step": 134144
},
{
"epoch": 0.02,
"learning_rate": 4.77952164720974e-05,
"loss": 4.5783,
"step": 134656
},
{
"epoch": 0.02,
"learning_rate": 4.778683052458688e-05,
"loss": 4.565,
"step": 135168
},
{
"epoch": 0.02,
"learning_rate": 4.777844457707636e-05,
"loss": 4.5736,
"step": 135680
},
{
"epoch": 0.02,
"learning_rate": 4.777005862956584e-05,
"loss": 4.5694,
"step": 136192
},
{
"epoch": 0.02,
"learning_rate": 4.776168906085905e-05,
"loss": 4.5658,
"step": 136704
},
{
"epoch": 0.02,
"learning_rate": 4.775331949215226e-05,
"loss": 4.5613,
"step": 137216
},
{
"epoch": 0.02,
"learning_rate": 4.774493354464174e-05,
"loss": 4.5578,
"step": 137728
},
{
"epoch": 0.02,
"learning_rate": 4.773654759713122e-05,
"loss": 4.5541,
"step": 138240
},
{
"epoch": 0.02,
"learning_rate": 4.77281616496207e-05,
"loss": 4.5645,
"step": 138752
},
{
"epoch": 0.02,
"learning_rate": 4.771977570211018e-05,
"loss": 4.5491,
"step": 139264
},
{
"epoch": 0.02,
"learning_rate": 4.771138975459966e-05,
"loss": 4.5512,
"step": 139776
},
{
"epoch": 0.02,
"learning_rate": 4.770300380708914e-05,
"loss": 4.5553,
"step": 140288
},
{
"epoch": 0.02,
"learning_rate": 4.769461785957862e-05,
"loss": 4.5625,
"step": 140800
},
{
"epoch": 0.02,
"learning_rate": 4.7686248290871835e-05,
"loss": 4.5395,
"step": 141312
},
{
"epoch": 0.02,
"learning_rate": 4.7677862343361315e-05,
"loss": 4.543,
"step": 141824
},
{
"epoch": 0.02,
"learning_rate": 4.7669476395850795e-05,
"loss": 4.5655,
"step": 142336
},
{
"epoch": 0.02,
"learning_rate": 4.7661090448340274e-05,
"loss": 4.5387,
"step": 142848
},
{
"epoch": 0.02,
"learning_rate": 4.7652720879633484e-05,
"loss": 4.5605,
"step": 143360
},
{
"epoch": 0.02,
"learning_rate": 4.764435131092669e-05,
"loss": 4.5427,
"step": 143872
},
{
"epoch": 0.02,
"learning_rate": 4.763596536341617e-05,
"loss": 4.5539,
"step": 144384
},
{
"epoch": 0.02,
"learning_rate": 4.762757941590565e-05,
"loss": 4.5414,
"step": 144896
},
{
"epoch": 0.02,
"learning_rate": 4.761919346839513e-05,
"loss": 4.537,
"step": 145408
},
{
"epoch": 0.02,
"learning_rate": 4.761080752088461e-05,
"loss": 4.5451,
"step": 145920
},
{
"epoch": 0.02,
"learning_rate": 4.760242157337409e-05,
"loss": 4.5409,
"step": 146432
},
{
"epoch": 0.02,
"learning_rate": 4.759405200466731e-05,
"loss": 4.5498,
"step": 146944
},
{
"epoch": 0.02,
"learning_rate": 4.758566605715679e-05,
"loss": 4.5441,
"step": 147456
},
{
"epoch": 0.02,
"learning_rate": 4.757728010964627e-05,
"loss": 4.5433,
"step": 147968
},
{
"epoch": 0.02,
"learning_rate": 4.756889416213575e-05,
"loss": 4.5408,
"step": 148480
},
{
"epoch": 0.02,
"learning_rate": 4.756052459342896e-05,
"loss": 4.5256,
"step": 148992
},
{
"epoch": 0.02,
"learning_rate": 4.755213864591844e-05,
"loss": 4.536,
"step": 149504
},
{
"epoch": 0.02,
"learning_rate": 4.754375269840792e-05,
"loss": 4.5226,
"step": 150016
},
{
"epoch": 0.02,
"learning_rate": 4.75353667508974e-05,
"loss": 4.5275,
"step": 150528
},
{
"epoch": 0.02,
"learning_rate": 4.7526997182190606e-05,
"loss": 4.5307,
"step": 151040
},
{
"epoch": 0.02,
"learning_rate": 4.7518611234680086e-05,
"loss": 4.518,
"step": 151552
},
{
"epoch": 0.02,
"learning_rate": 4.7510225287169566e-05,
"loss": 4.5247,
"step": 152064
},
{
"epoch": 0.02,
"learning_rate": 4.7501839339659046e-05,
"loss": 4.5218,
"step": 152576
},
{
"epoch": 0.03,
"eval_loss": 4.488372802734375,
"eval_runtime": 546.2477,
"eval_samples_per_second": 698.568,
"eval_steps_per_second": 21.831,
"step": 152638
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 6.18106757409527e+16,
"trial_name": null,
"trial_params": null
}