abhinavp's picture
Training in progress, epoch 1, checkpoint
0206b6f verified
{
"best_metric": 4.479715824127197,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/lstm/2/checkpoints/checkpoint-152640",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 152640,
"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": 10.8193,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5543,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0616,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.992,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9441,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.899,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7351,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6336,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5381,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4683,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.4032,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3381,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2653,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.2021,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1498,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0901,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0446,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 6.0028,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9639,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984066699730012e-05,
"loss": 5.9241,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8872,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8426,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8187,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.7808,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.979875363855125e-05,
"loss": 5.7581,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.979036769104073e-05,
"loss": 5.7278,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.978198174353021e-05,
"loss": 5.7038,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.977359579601969e-05,
"loss": 5.6725,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6474,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6292,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6027,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.5956,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5646,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5562,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5465,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5251,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5112,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.9689785457325684e-05,
"loss": 5.4767,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4702,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4476,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4426,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4255,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.415,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.3848,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963110020355577e-05,
"loss": 5.3956,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3822,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.3739,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960595873982795e-05,
"loss": 5.3612,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959757279231743e-05,
"loss": 5.3349,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3263,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3295,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3142,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956404538107908e-05,
"loss": 5.3019,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955565943356856e-05,
"loss": 5.2764,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.2786,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2646,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.2896,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2425,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2471,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2424,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2219,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 5.2232,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2088,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.1916,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.1906,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.2071,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.1811,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943830530483247e-05,
"loss": 5.1708,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942991935732195e-05,
"loss": 5.1554,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1558,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1654,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940477789359412e-05,
"loss": 5.1608,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.93963919460836e-05,
"loss": 5.1476,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938800599857309e-05,
"loss": 5.1548,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.937962005106256e-05,
"loss": 5.148,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.937123410355204e-05,
"loss": 5.1352,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1163,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935447858733473e-05,
"loss": 5.1067,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934609263982421e-05,
"loss": 5.1025,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933770669231369e-05,
"loss": 5.0968,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329337123606905e-05,
"loss": 5.0923,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932095117609638e-05,
"loss": 5.089,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931256522858586e-05,
"loss": 5.091,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930417928107534e-05,
"loss": 5.0825,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295809712368554e-05,
"loss": 5.0565,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.0518,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.0616,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.0631,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262265922326474e-05,
"loss": 5.0383,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 5.0412,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.92455267849129e-05,
"loss": 5.0429,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.0267,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.0215,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 5.0202,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 5.0097,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.015,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 5.0025,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 4.9886,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.9864,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 4.9864,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.9828,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.9831,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.972,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.9688,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.9604,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9426,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111384382352036e-05,
"loss": 4.9462,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9102998434841516e-05,
"loss": 4.9449,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.9409,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.9324,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.928,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9199,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9217,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.9156,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.9154,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.9069,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.90275576648543e-05,
"loss": 4.9064,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901917171734378e-05,
"loss": 4.9076,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901078576983326e-05,
"loss": 4.8975,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.9042,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.9037,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.8883,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.8915,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.8776,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.8823,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.8567,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.8707,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.856,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8571,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8391,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.8717,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.8579,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.8446,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.8432,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.8387,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.8491,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.8418,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.8309,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884314871364151e-05,
"loss": 4.8359,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.8208,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.8312,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.8138,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.8154,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.8145,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.8029,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.8047,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.8053,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.7996,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.8048,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.7933,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.754898548126221,
"eval_runtime": 309.1681,
"eval_samples_per_second": 1234.251,
"eval_steps_per_second": 38.571,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.7814,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.7767,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.7931,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.7761,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.7932,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.7633,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.7753,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.7527,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.7658,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.7626,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7686,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.7627,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864195148860396e-05,
"loss": 4.745,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.7478,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.7408,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.7367,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.7466,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.741,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.7365,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.7523,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.7268,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.7363,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.7288,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.7394,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.7137,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.7218,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.7132,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.7214,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.7004,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.705,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.7142,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.7064,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.7057,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.8465912106097964e-05,
"loss": 4.7123,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.7031,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.705,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.6856,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.6966,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.6815,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.6906,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.6868,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.6849,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.6689,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.6862,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.6845,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.6779,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.6828,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.6531,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.654,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.6742,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.6618,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.6604,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.6416,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.6459,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.6421,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281486776081446e-05,
"loss": 4.6687,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273133586178384e-05,
"loss": 4.6373,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826474763866787e-05,
"loss": 4.6456,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.6503,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824797574364683e-05,
"loss": 4.6326,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823958979613631e-05,
"loss": 4.6383,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823120384862579e-05,
"loss": 4.6319,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822281790111527e-05,
"loss": 4.6226,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.6279,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.6418,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.6304,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.6187,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.6175,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817251859485588e-05,
"loss": 4.6183,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.6349,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815574669983483e-05,
"loss": 4.635,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814736075232432e-05,
"loss": 4.6248,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.81389748048138e-05,
"loss": 4.6375,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813058885730328e-05,
"loss": 4.6347,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.6309,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811383334108597e-05,
"loss": 4.6155,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810544739357545e-05,
"loss": 4.6147,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809706144606493e-05,
"loss": 4.6113,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808869187735814e-05,
"loss": 4.6106,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808030592984762e-05,
"loss": 4.6059,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.6109,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.6181,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.6069,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804677851860927e-05,
"loss": 4.5921,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803839257109875e-05,
"loss": 4.5936,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.5985,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802162067607771e-05,
"loss": 4.6111,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801323472856719e-05,
"loss": 4.5916,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800484878105667e-05,
"loss": 4.5977,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799646283354615e-05,
"loss": 4.6004,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798809326483936e-05,
"loss": 4.5921,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797970731732884e-05,
"loss": 4.5869,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797132136981832e-05,
"loss": 4.5862,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.79629354223078e-05,
"loss": 4.5857,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795454947479728e-05,
"loss": 4.5865,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794617990609049e-05,
"loss": 4.5884,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793779395857997e-05,
"loss": 4.5729,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792940801106946e-05,
"loss": 4.5787,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792102206355894e-05,
"loss": 4.5763,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791263611604842e-05,
"loss": 4.5841,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.79042501685379e-05,
"loss": 4.5795,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789586422102737e-05,
"loss": 4.5778,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788747827351685e-05,
"loss": 4.5762,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879108704810067e-05,
"loss": 4.5728,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870722757299546e-05,
"loss": 4.5575,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862353188592756e-05,
"loss": 4.5596,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853967241082236e-05,
"loss": 4.5654,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845581293571715e-05,
"loss": 4.5606,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.5584,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.5553,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782043982984389e-05,
"loss": 4.5508,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.78120702611371e-05,
"loss": 4.5553,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780368431362658e-05,
"loss": 4.5531,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779529836611606e-05,
"loss": 4.5523,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778691241860554e-05,
"loss": 4.5538,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777852647109502e-05,
"loss": 4.5545,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777014052358449e-05,
"loss": 4.5536,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776175457607397e-05,
"loss": 4.548,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775336862856345e-05,
"loss": 4.5589,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774498268105293e-05,
"loss": 4.5564,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773659673354241e-05,
"loss": 4.5438,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772821078603189e-05,
"loss": 4.5554,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771984121732511e-05,
"loss": 4.5422,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771145526981459e-05,
"loss": 4.549,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770306932230407e-05,
"loss": 4.523,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769468337479355e-05,
"loss": 4.5447,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768629742728303e-05,
"loss": 4.5268,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767791147977251e-05,
"loss": 4.5331,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766954191106572e-05,
"loss": 4.5192,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.76611559635552e-05,
"loss": 4.55,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765277001604468e-05,
"loss": 4.5413,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764438406853416e-05,
"loss": 4.5329,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763599812102364e-05,
"loss": 4.5277,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762761217351312e-05,
"loss": 4.5306,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.76192262260026e-05,
"loss": 4.539,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610856657295813e-05,
"loss": 4.5335,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602470709785293e-05,
"loss": 4.5278,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594084762274773e-05,
"loss": 4.5311,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758569881476425e-05,
"loss": 4.5222,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757732924605746e-05,
"loss": 4.5368,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756894329854694e-05,
"loss": 4.5161,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756055735103642e-05,
"loss": 4.522,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.75521714035259e-05,
"loss": 4.5178,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543785456015375e-05,
"loss": 4.5144,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535399508504855e-05,
"loss": 4.5191,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527013560994335e-05,
"loss": 4.5173,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518627613483815e-05,
"loss": 4.5179,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510241665973295e-05,
"loss": 4.5173,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750187209726651e-05,
"loss": 4.5118,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.479715824127197,
"eval_runtime": 325.7634,
"eval_samples_per_second": 1171.375,
"eval_steps_per_second": 36.606,
"step": 152640
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 6.301543303671373e+16,
"trial_name": null,
"trial_params": null
}