abhinavp's picture
Training in progress, epoch 0, checkpoint
aa1c8dd verified
{
"best_metric": 4.0523362159729,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/lstm/4/checkpoints/checkpoint-839520",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 839520,
"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": 10.8183,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5593,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0676,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9976,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9501,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.9288,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7641,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6452,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.544,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4772,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.4257,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3719,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.3132,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.2564,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.2037,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.141,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0915,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 6.0448,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 6.0,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984066699730012e-05,
"loss": 5.957,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.9177,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8721,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 5.8478,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.8093,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7852,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7546,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7303,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 5.7009,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6741,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6551,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6283,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 5.6215,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731731573682013e-05,
"loss": 5.5889,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 5.5772,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 5.5686,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 5.5457,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5312,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4952,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4877,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4661,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4594,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4411,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.4307,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.3992,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 5.4098,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 5.3974,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 5.3883,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.3758,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 5.3472,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3395,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 5.3412,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 5.3269,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.314,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2883,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.2889,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 5.2761,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 5.3023,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 5.2539,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 5.2587,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2521,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 5.2307,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 5.2327,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2158,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.2008,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.1996,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2147,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.1894,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1793,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1628,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1624,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1719,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1666,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.1531,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.1613,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1532,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371250482355776e-05,
"loss": 5.1411,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 5.121,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 5.111,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346109018627945e-05,
"loss": 5.107,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.1017,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 5.097,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 5.0927,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.0948,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 5.0858,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 5.0599,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 5.0558,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 5.0649,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 5.0653,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 5.0422,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925389635361968e-05,
"loss": 5.0436,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924551040610916e-05,
"loss": 5.0452,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923712445859864e-05,
"loss": 5.0294,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.0238,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 5.0227,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 5.0108,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.015,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 5.0042,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 4.9905,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.9883,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.9882,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.9839,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.9836,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.974,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.9701,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.9609,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.9419,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9466,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9444,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.9421,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.9334,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.9289,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9212,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9205,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.9164,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.9151,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.9071,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.9057,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.9066,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901080214863699e-05,
"loss": 4.8981,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.9028,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899403025361595e-05,
"loss": 4.9016,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.898564430610543e-05,
"loss": 4.8873,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897725835859491e-05,
"loss": 4.8919,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.8756,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.8823,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.8563,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.8684,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.8534,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.8566,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.8376,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.869,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.8552,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.8438,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.8412,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.8377,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.8464,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.8393,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.8277,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884314871364151e-05,
"loss": 4.8326,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883476276613099e-05,
"loss": 4.8196,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.8288,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.8124,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.8147,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.8105,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.7983,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.8018,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.8018,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876769156485057e-05,
"loss": 4.7952,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.7999,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.7888,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.7520880699157715,
"eval_runtime": 299.0244,
"eval_samples_per_second": 1276.12,
"eval_steps_per_second": 39.88,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.7771,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.7737,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.7904,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.773,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.7885,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.7598,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.7708,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.7498,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675478899842306e-05,
"loss": 4.7643,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.7592,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7639,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.7589,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.7414,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.743,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.7373,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.7325,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.7429,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.7371,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.733,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.7482,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.7219,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.7318,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.7245,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.7342,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.711,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.7175,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.7083,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851621141235735e-05,
"loss": 4.7161,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850782546484683e-05,
"loss": 4.6973,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849943951733631e-05,
"loss": 4.6991,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849105356982579e-05,
"loss": 4.7105,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848266762231527e-05,
"loss": 4.7022,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847428167480475e-05,
"loss": 4.7006,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846589572729423e-05,
"loss": 4.7083,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845750977978371e-05,
"loss": 4.6989,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.8449140211076924e-05,
"loss": 4.6982,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.8440754263566404e-05,
"loss": 4.6815,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.6909,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.674,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.6849,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.6834,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.6794,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.663,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.6798,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.6794,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836531349357918e-05,
"loss": 4.6722,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835692754606866e-05,
"loss": 4.6786,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834854159855814e-05,
"loss": 4.6474,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834015565104763e-05,
"loss": 4.6479,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833176970353711e-05,
"loss": 4.668,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832340013483032e-05,
"loss": 4.657,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.83150141873198e-05,
"loss": 4.655,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830662823980928e-05,
"loss": 4.6358,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829824229229876e-05,
"loss": 4.6417,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.6377,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.6625,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.6314,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.6413,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.6451,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.6259,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.6327,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.6273,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222801522311535e-05,
"loss": 4.617,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821443195360475e-05,
"loss": 4.6202,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.6369,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819766005858371e-05,
"loss": 4.6239,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189274111073184e-05,
"loss": 4.6129,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180888163562664e-05,
"loss": 4.6126,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172502216052144e-05,
"loss": 4.6116,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164116268541624e-05,
"loss": 4.6298,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815574669983483e-05,
"loss": 4.6293,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814736075232432e-05,
"loss": 4.6179,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.81389748048138e-05,
"loss": 4.6311,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813058885730328e-05,
"loss": 4.629,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122235667400224e-05,
"loss": 4.623,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.6074,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105463772379184e-05,
"loss": 4.6073,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809707782486866e-05,
"loss": 4.6025,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808869187735814e-05,
"loss": 4.6031,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808030592984762e-05,
"loss": 4.5993,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.6049,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806353403482658e-05,
"loss": 4.612,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.5998,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804677851860927e-05,
"loss": 4.5865,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803839257109875e-05,
"loss": 4.5866,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.5907,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802163705488144e-05,
"loss": 4.6031,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.5848,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800488153866413e-05,
"loss": 4.5899,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799649559115361e-05,
"loss": 4.5932,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798810964364309e-05,
"loss": 4.5849,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797972369613257e-05,
"loss": 4.579,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797133774862205e-05,
"loss": 4.578,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796295180111153e-05,
"loss": 4.5791,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795456585360101e-05,
"loss": 4.5796,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794617990609049e-05,
"loss": 4.5832,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.5665,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929440768676916e-05,
"loss": 4.5722,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921054821166396e-05,
"loss": 4.5692,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912668873655876e-05,
"loss": 4.5769,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904282926145356e-05,
"loss": 4.57,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895896978634836e-05,
"loss": 4.571,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887511031124316e-05,
"loss": 4.569,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879125083613796e-05,
"loss": 4.5658,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870739136103276e-05,
"loss": 4.5487,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862369567396485e-05,
"loss": 4.551,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853983619885965e-05,
"loss": 4.5573,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845597672375445e-05,
"loss": 4.5545,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.5529,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.5477,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782043982984389e-05,
"loss": 4.543,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781205388233337e-05,
"loss": 4.5482,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803667934822844e-05,
"loss": 4.5465,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795281987312324e-05,
"loss": 4.5442,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786896039801804e-05,
"loss": 4.5474,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777852647109502e-05,
"loss": 4.5454,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777014052358449e-05,
"loss": 4.5482,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776175457607397e-05,
"loss": 4.5422,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775336862856345e-05,
"loss": 4.5489,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774498268105293e-05,
"loss": 4.5498,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773659673354241e-05,
"loss": 4.5378,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772822716483563e-05,
"loss": 4.5475,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771984121732511e-05,
"loss": 4.5359,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771145526981459e-05,
"loss": 4.5425,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770306932230407e-05,
"loss": 4.5181,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769469975359728e-05,
"loss": 4.5355,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768631380608676e-05,
"loss": 4.5174,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767792785857624e-05,
"loss": 4.5251,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766954191106572e-05,
"loss": 4.5117,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.76611559635552e-05,
"loss": 4.5436,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.5334,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764440044733789e-05,
"loss": 4.5275,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763601449982737e-05,
"loss": 4.518,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762764493112058e-05,
"loss": 4.5231,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761925898361006e-05,
"loss": 4.5303,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761087303609954e-05,
"loss": 4.5267,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760248708858902e-05,
"loss": 4.5201,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941011410785e-05,
"loss": 4.5225,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758571519356798e-05,
"loss": 4.5143,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757732924605746e-05,
"loss": 4.5287,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756895967735067e-05,
"loss": 4.5087,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756057372984015e-05,
"loss": 4.5152,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755222053993709e-05,
"loss": 4.5099,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754383459242657e-05,
"loss": 4.5062,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753544864491605e-05,
"loss": 4.5114,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527062697405536e-05,
"loss": 4.5079,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518676749895016e-05,
"loss": 4.5099,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510290802384496e-05,
"loss": 4.5078,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501904854873976e-05,
"loss": 4.5036,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.471486568450928,
"eval_runtime": 299.4148,
"eval_samples_per_second": 1274.456,
"eval_steps_per_second": 39.828,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493518907363456e-05,
"loss": 4.4946,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485132959852936e-05,
"loss": 4.4889,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476747012342416e-05,
"loss": 4.5097,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468361064831896e-05,
"loss": 4.493,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7459975117321376e-05,
"loss": 4.5144,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745158916981085e-05,
"loss": 4.4831,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744320322230033e-05,
"loss": 4.4962,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743481727478981e-05,
"loss": 4.4801,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742643132727929e-05,
"loss": 4.4954,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741804537976877e-05,
"loss": 4.4915,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740965943225825e-05,
"loss": 4.4962,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401273484747736e-05,
"loss": 4.493,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392903916040945e-05,
"loss": 4.4747,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384517968530425e-05,
"loss": 4.4844,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376132021019905e-05,
"loss": 4.4792,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367762452313114e-05,
"loss": 4.4771,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359376504802594e-05,
"loss": 4.4802,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350990557292074e-05,
"loss": 4.4829,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342604609781554e-05,
"loss": 4.4754,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.7334218662271034e-05,
"loss": 4.4965,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325832714760514e-05,
"loss": 4.4716,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317446767249994e-05,
"loss": 4.4794,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7309060819739474e-05,
"loss": 4.4768,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300674872228953e-05,
"loss": 4.4862,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292288924718433e-05,
"loss": 4.4666,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728390297720791e-05,
"loss": 4.4769,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727551702969739e-05,
"loss": 4.4652,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726713108218687e-05,
"loss": 4.4715,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725876151348009e-05,
"loss": 4.4589,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725037556596957e-05,
"loss": 4.4609,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724198961845904e-05,
"loss": 4.4711,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723360367094852e-05,
"loss": 4.4693,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225217723438e-05,
"loss": 4.4684,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721683177592748e-05,
"loss": 4.4715,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720844582841696e-05,
"loss": 4.4646,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720005988090644e-05,
"loss": 4.4695,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719170669100339e-05,
"loss": 4.4518,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718332074349287e-05,
"loss": 4.4663,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717495117478608e-05,
"loss": 4.4485,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716656522727556e-05,
"loss": 4.458,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715817927976504e-05,
"loss": 4.4557,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149793332254516e-05,
"loss": 4.4586,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141407384743996e-05,
"loss": 4.4495,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133021437233476e-05,
"loss": 4.4529,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124651868526685e-05,
"loss": 4.4589,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.71162822998199e-05,
"loss": 4.4538,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710789635230938e-05,
"loss": 4.4577,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709952678360259e-05,
"loss": 4.4389,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709114083609208e-05,
"loss": 4.4301,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708275488858156e-05,
"loss": 4.4497,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074368941071037e-05,
"loss": 4.4441,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7065982993560517e-05,
"loss": 4.4429,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705759704604999e-05,
"loss": 4.4251,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704921109853947e-05,
"loss": 4.4312,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704082515102895e-05,
"loss": 4.4331,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703243920351843e-05,
"loss": 4.4466,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702405325600791e-05,
"loss": 4.425,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701566730849739e-05,
"loss": 4.436,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700728136098687e-05,
"loss": 4.4382,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699889541347635e-05,
"loss": 4.4241,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699050946596583e-05,
"loss": 4.4311,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698212351845531e-05,
"loss": 4.4261,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697373757094479e-05,
"loss": 4.4143,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965351623434276e-05,
"loss": 4.4257,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956982054727485e-05,
"loss": 4.4294,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.6948596107216965e-05,
"loss": 4.4329,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.6940210159706445e-05,
"loss": 4.4114,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931824212195925e-05,
"loss": 4.4174,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.69234382646854e-05,
"loss": 4.4147,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691505231717488e-05,
"loss": 4.4417,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906682748468094e-05,
"loss": 4.4281,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898296800957574e-05,
"loss": 4.4257,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688991085344705e-05,
"loss": 4.4385,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688152490593653e-05,
"loss": 4.4386,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687315533722974e-05,
"loss": 4.4322,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686476938971923e-05,
"loss": 4.4192,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.68563834422087e-05,
"loss": 4.4211,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684799749469818e-05,
"loss": 4.4175,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683961154718766e-05,
"loss": 4.4138,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683122559967714e-05,
"loss": 4.4166,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682285603097035e-05,
"loss": 4.4173,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681447008345983e-05,
"loss": 4.4279,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680608413594931e-05,
"loss": 4.4166,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679769818843879e-05,
"loss": 4.408,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678931224092827e-05,
"loss": 4.4029,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678092629341775e-05,
"loss": 4.4119,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677255672471097e-05,
"loss": 4.4183,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676417077720045e-05,
"loss": 4.4087,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755801208493657e-05,
"loss": 4.4069,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747415260983136e-05,
"loss": 4.4181,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739029313472616e-05,
"loss": 4.3986,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730643365962096e-05,
"loss": 4.4071,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722257418451576e-05,
"loss": 4.4023,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713871470941056e-05,
"loss": 4.4088,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705485523430536e-05,
"loss": 4.407,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697099575920016e-05,
"loss": 4.4034,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688713628409496e-05,
"loss": 4.395,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680327680898976e-05,
"loss": 4.4041,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6671941733388456e-05,
"loss": 4.3934,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663572164681665e-05,
"loss": 4.4105,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655186217171145e-05,
"loss": 4.4022,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664681664846436e-05,
"loss": 4.4015,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663843070095384e-05,
"loss": 4.3946,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663004475344332e-05,
"loss": 4.4026,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.66216588059328e-05,
"loss": 4.3788,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661327285842228e-05,
"loss": 4.387,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660490328971549e-05,
"loss": 4.3907,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659651734220497e-05,
"loss": 4.3921,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658814777349818e-05,
"loss": 4.3854,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657976182598766e-05,
"loss": 4.3865,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657137587847714e-05,
"loss": 4.3782,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656298993096662e-05,
"loss": 4.3868,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.65546039834561e-05,
"loss": 4.3839,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546218035945586e-05,
"loss": 4.3791,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6537832088435065e-05,
"loss": 4.3907,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652944614092454e-05,
"loss": 4.3891,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652106019341402e-05,
"loss": 4.3916,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.65126742459035e-05,
"loss": 4.3807,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650428829839298e-05,
"loss": 4.3902,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649590235088246e-05,
"loss": 4.3897,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648751640337194e-05,
"loss": 4.3796,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647913045586142e-05,
"loss": 4.3971,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647076088715463e-05,
"loss": 4.3772,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646237493964411e-05,
"loss": 4.3874,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645398899213359e-05,
"loss": 4.3663,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644560304462307e-05,
"loss": 4.3829,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437217097112554e-05,
"loss": 4.3621,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642884752840576e-05,
"loss": 4.3744,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642046158089524e-05,
"loss": 4.3619,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641207563338472e-05,
"loss": 4.3887,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.64036896858742e-05,
"loss": 4.3798,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639530373836368e-05,
"loss": 4.3794,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638693416965689e-05,
"loss": 4.3675,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637854822214637e-05,
"loss": 4.3724,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637016227463585e-05,
"loss": 4.3877,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636179270592906e-05,
"loss": 4.376,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635340675841854e-05,
"loss": 4.3712,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634502081090802e-05,
"loss": 4.3796,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633663486339751e-05,
"loss": 4.3696,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632824891588699e-05,
"loss": 4.3768,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631986296837647e-05,
"loss": 4.3635,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631149339966968e-05,
"loss": 4.3706,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630310745215916e-05,
"loss": 4.3648,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629472150464864e-05,
"loss": 4.3662,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628633555713812e-05,
"loss": 4.3619,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277949609627597e-05,
"loss": 4.369,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626956366211707e-05,
"loss": 4.3608,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626117771460655e-05,
"loss": 4.3652,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625279176709603e-05,
"loss": 4.3636,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.337629318237305,
"eval_runtime": 291.3009,
"eval_samples_per_second": 1309.955,
"eval_steps_per_second": 40.937,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.6244422198389246e-05,
"loss": 4.3576,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.6236036250878726e-05,
"loss": 4.3496,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622766668217194e-05,
"loss": 4.3685,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621928073466142e-05,
"loss": 4.3522,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.6210894787150895e-05,
"loss": 4.3775,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202508839640374e-05,
"loss": 4.343,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194122892129854e-05,
"loss": 4.3579,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185736944619334e-05,
"loss": 4.3417,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177350997108814e-05,
"loss": 4.3586,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6168965049598294e-05,
"loss": 4.3591,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.6160579102087774e-05,
"loss": 4.3547,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615220953338098e-05,
"loss": 4.3577,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614385634347793e-05,
"loss": 4.3396,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135470395967415e-05,
"loss": 4.3506,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.6127084448456895e-05,
"loss": 4.3463,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611869850094637e-05,
"loss": 4.344,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611031255343585e-05,
"loss": 4.3447,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610192660592533e-05,
"loss": 4.3493,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609354065841481e-05,
"loss": 4.3465,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608515471090429e-05,
"loss": 4.3602,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607676876339377e-05,
"loss": 4.3423,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606838281588325e-05,
"loss": 4.3475,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.605999686837273e-05,
"loss": 4.3458,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605161092086221e-05,
"loss": 4.3582,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604322497335169e-05,
"loss": 4.3365,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.60348554046449e-05,
"loss": 4.3492,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602646945713438e-05,
"loss": 4.3373,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018083509623864e-05,
"loss": 4.3395,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009697562113344e-05,
"loss": 4.3294,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001311614602824e-05,
"loss": 4.3389,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599294204589603e-05,
"loss": 4.3397,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598455609838551e-05,
"loss": 4.3448,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597617015087499e-05,
"loss": 4.3404,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596778420336447e-05,
"loss": 4.3467,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595939825585395e-05,
"loss": 4.3369,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595101230834343e-05,
"loss": 4.3441,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594264273963664e-05,
"loss": 4.3317,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593425679212612e-05,
"loss": 4.3387,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.59258708446156e-05,
"loss": 4.3251,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591748489710508e-05,
"loss": 4.3335,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.59091153283983e-05,
"loss": 4.3329,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590072938088778e-05,
"loss": 4.3369,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589234343337726e-05,
"loss": 4.3278,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588395748586673e-05,
"loss": 4.3305,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587557153835621e-05,
"loss": 4.3374,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867201969649426e-05,
"loss": 4.332,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858816022138906e-05,
"loss": 4.3348,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585043007462838e-05,
"loss": 4.3247,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584204412711786e-05,
"loss": 4.3055,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583365817960734e-05,
"loss": 4.3305,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582527223209682e-05,
"loss": 4.3234,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.5816902663390035e-05,
"loss": 4.3208,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808516715879515e-05,
"loss": 4.3157,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800130768368995e-05,
"loss": 4.3126,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791744820858475e-05,
"loss": 4.3113,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783358873347955e-05,
"loss": 4.3284,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5774989304641164e-05,
"loss": 4.3087,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766603357130644e-05,
"loss": 4.3164,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758217409620124e-05,
"loss": 4.3251,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5749831462109604e-05,
"loss": 4.3093,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574146189340281e-05,
"loss": 4.3126,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573307594589229e-05,
"loss": 4.3159,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572468999838177e-05,
"loss": 4.2938,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571630405087125e-05,
"loss": 4.3129,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570791810336074e-05,
"loss": 4.3168,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569953215585022e-05,
"loss": 4.3163,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.56911462083397e-05,
"loss": 4.2991,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568276026082918e-05,
"loss": 4.3068,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567440707092612e-05,
"loss": 4.3003,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.56660211234156e-05,
"loss": 4.3231,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565763517590508e-05,
"loss": 4.3174,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564924922839456e-05,
"loss": 4.3167,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564086328088404e-05,
"loss": 4.3246,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563247733337352e-05,
"loss": 4.3262,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624091385863e-05,
"loss": 4.3237,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561570543835248e-05,
"loss": 4.3023,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560733586964569e-05,
"loss": 4.3102,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559894992213517e-05,
"loss": 4.3121,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559056397462465e-05,
"loss": 4.3019,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558217802711413e-05,
"loss": 4.3121,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557379207960361e-05,
"loss": 4.3046,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556542251089682e-05,
"loss": 4.315,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.55570365633863e-05,
"loss": 4.3105,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554865061587578e-05,
"loss": 4.2925,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554026466836526e-05,
"loss": 4.2981,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553187872085474e-05,
"loss": 4.3061,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523492773344215e-05,
"loss": 4.3082,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515106825833695e-05,
"loss": 4.3009,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550673725712691e-05,
"loss": 4.2986,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549835130961639e-05,
"loss": 4.3084,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.548996536210587e-05,
"loss": 4.2952,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548157941459535e-05,
"loss": 4.2961,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547320984588857e-05,
"loss": 4.3004,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.5464840277181776e-05,
"loss": 4.3032,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.5456454329671256e-05,
"loss": 4.3044,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448068382160736e-05,
"loss": 4.2972,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.5439682434650216e-05,
"loss": 4.2851,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543129648713969e-05,
"loss": 4.3038,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542291053962917e-05,
"loss": 4.2879,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541452459211865e-05,
"loss": 4.3081,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540613864460813e-05,
"loss": 4.2994,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5397769075901345e-05,
"loss": 4.2966,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389383128390824e-05,
"loss": 4.2922,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5380997180880304e-05,
"loss": 4.3004,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372611233369784e-05,
"loss": 4.2772,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364225285859264e-05,
"loss": 4.2877,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5355839338348744e-05,
"loss": 4.2841,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347453390838224e-05,
"loss": 4.2909,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339067443327704e-05,
"loss": 4.2842,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533069787462091e-05,
"loss": 4.2887,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532231192711039e-05,
"loss": 4.2799,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531392597959987e-05,
"loss": 4.2777,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530554003208935e-05,
"loss": 4.2876,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529715408457883e-05,
"loss": 4.2774,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528878451587205e-05,
"loss": 4.2946,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528039856836153e-05,
"loss": 4.2902,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527201262085101e-05,
"loss": 4.2927,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526362667334049e-05,
"loss": 4.2839,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525524072582997e-05,
"loss": 4.2899,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524685477831945e-05,
"loss": 4.2941,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523846883080893e-05,
"loss": 4.281,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523011564090587e-05,
"loss": 4.2978,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522172969339535e-05,
"loss": 4.2806,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521334374588483e-05,
"loss": 4.2879,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520495779837431e-05,
"loss": 4.2731,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519657185086379e-05,
"loss": 4.2836,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518818590335327e-05,
"loss": 4.2656,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517979995584275e-05,
"loss": 4.2792,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517141400833223e-05,
"loss": 4.2681,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516302806082171e-05,
"loss": 4.2881,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.5154642113311187e-05,
"loss": 4.2812,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.51462725446044e-05,
"loss": 4.2872,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5137886597093876e-05,
"loss": 4.2731,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512951702838709e-05,
"loss": 4.281,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512113108087657e-05,
"loss": 4.2908,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.5112745133366045e-05,
"loss": 4.2817,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104359185855525e-05,
"loss": 4.2779,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5095973238345005e-05,
"loss": 4.2885,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087587290834485e-05,
"loss": 4.2739,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507920134332397e-05,
"loss": 4.2855,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507081539581345e-05,
"loss": 4.2677,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506244582710666e-05,
"loss": 4.2803,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505405987959614e-05,
"loss": 4.2723,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504567393208562e-05,
"loss": 4.272,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.50372879845751e-05,
"loss": 4.2749,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502890203706458e-05,
"loss": 4.2713,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502053246835779e-05,
"loss": 4.2703,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501214652084727e-05,
"loss": 4.2717,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500376057333675e-05,
"loss": 4.2765,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.254123687744141,
"eval_runtime": 289.5433,
"eval_samples_per_second": 1317.906,
"eval_steps_per_second": 41.186,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499537462582623e-05,
"loss": 4.2625,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498698867831571e-05,
"loss": 4.2574,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497860273080519e-05,
"loss": 4.277,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497021678329467e-05,
"loss": 4.2622,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496183083578415e-05,
"loss": 4.2835,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953444888273636e-05,
"loss": 4.2619,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945058940763116e-05,
"loss": 4.2623,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493667299325259e-05,
"loss": 4.2517,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492828704574207e-05,
"loss": 4.2703,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.491990109823155e-05,
"loss": 4.2737,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491151515072103e-05,
"loss": 4.2646,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490312920321051e-05,
"loss": 4.2655,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489475963450372e-05,
"loss": 4.2547,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.48863736869932e-05,
"loss": 4.2611,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487798773948268e-05,
"loss": 4.2602,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486960179197216e-05,
"loss": 4.2546,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486121584446164e-05,
"loss": 4.2574,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485282989695112e-05,
"loss": 4.2646,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.4844443949440604e-05,
"loss": 4.2587,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.4836058001930084e-05,
"loss": 4.2705,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482768843322329e-05,
"loss": 4.2606,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481930248571277e-05,
"loss": 4.2639,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481093291700598e-05,
"loss": 4.26,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480254696949546e-05,
"loss": 4.2701,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479416102198494e-05,
"loss": 4.2516,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478577507447442e-05,
"loss": 4.2613,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.47773891269639e-05,
"loss": 4.2555,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476900317945338e-05,
"loss": 4.2509,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476061723194286e-05,
"loss": 4.2461,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475223128443234e-05,
"loss": 4.2523,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474384533692182e-05,
"loss": 4.2591,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.47354593894113e-05,
"loss": 4.2587,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472707344190078e-05,
"loss": 4.2595,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471868749439026e-05,
"loss": 4.259,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471031792568348e-05,
"loss": 4.2539,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470193197817295e-05,
"loss": 4.2592,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469354603066243e-05,
"loss": 4.2509,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468517646195565e-05,
"loss": 4.2542,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4676806893248856e-05,
"loss": 4.2445,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668420945738336e-05,
"loss": 4.2511,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660034998227816e-05,
"loss": 4.2498,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651649050717296e-05,
"loss": 4.2558,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.4643263103206776e-05,
"loss": 4.2452,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4634877155696256e-05,
"loss": 4.2493,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626491208185736e-05,
"loss": 4.2578,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618105260675215e-05,
"loss": 4.2481,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4609719313164695e-05,
"loss": 4.2523,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601333365654175e-05,
"loss": 4.2441,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4592947418143655e-05,
"loss": 4.2254,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584561470633135e-05,
"loss": 4.2535,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576191901926344e-05,
"loss": 4.2426,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4567822333219554e-05,
"loss": 4.2416,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559436385709033e-05,
"loss": 4.2303,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551050438198513e-05,
"loss": 4.237,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454266449068799e-05,
"loss": 4.2283,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453429492198121e-05,
"loss": 4.2502,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452590897447069e-05,
"loss": 4.2316,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451752302696017e-05,
"loss": 4.234,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450913707944965e-05,
"loss": 4.2471,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450075113193913e-05,
"loss": 4.2314,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449238156323234e-05,
"loss": 4.2358,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448399561572182e-05,
"loss": 4.2404,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.44756096682113e-05,
"loss": 4.2166,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446722372070078e-05,
"loss": 4.2357,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445885415199399e-05,
"loss": 4.2357,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445046820448347e-05,
"loss": 4.2424,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444208225697295e-05,
"loss": 4.2231,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443371268826616e-05,
"loss": 4.2311,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442532674075564e-05,
"loss": 4.2201,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441694079324512e-05,
"loss": 4.2489,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.44085548457346e-05,
"loss": 4.2405,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440016889822408e-05,
"loss": 4.238,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439178295071356e-05,
"loss": 4.2504,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438339700320304e-05,
"loss": 4.2441,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437501105569252e-05,
"loss": 4.2558,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436664148698573e-05,
"loss": 4.2304,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435825553947521e-05,
"loss": 4.234,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.434986959196469e-05,
"loss": 4.2384,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434148364445417e-05,
"loss": 4.2246,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433311407574738e-05,
"loss": 4.2393,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432472812823687e-05,
"loss": 4.2293,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431634218072635e-05,
"loss": 4.2402,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430795623321583e-05,
"loss": 4.2357,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429957028570531e-05,
"loss": 4.2207,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429118433819479e-05,
"loss": 4.2332,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428279839068426e-05,
"loss": 4.2217,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427441244317374e-05,
"loss": 4.2374,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266042874466956e-05,
"loss": 4.2293,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257673305760165e-05,
"loss": 4.2251,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249287358249645e-05,
"loss": 4.2344,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4240917789542854e-05,
"loss": 4.2282,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232531842032334e-05,
"loss": 4.2197,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422414589452182e-05,
"loss": 4.2255,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.42157599470113e-05,
"loss": 4.2343,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420737399950078e-05,
"loss": 4.231,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419898805199026e-05,
"loss": 4.2277,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190602104479734e-05,
"loss": 4.2135,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182216156969214e-05,
"loss": 4.2293,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4173830209458694e-05,
"loss": 4.2181,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.4165444261948174e-05,
"loss": 4.2327,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157058314437654e-05,
"loss": 4.2313,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.4148672366927134e-05,
"loss": 4.2266,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414030279822034e-05,
"loss": 4.2205,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413191685070982e-05,
"loss": 4.2331,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.41235309031993e-05,
"loss": 4.2022,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411514495568879e-05,
"loss": 4.2196,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106791765785735e-05,
"loss": 4.2112,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409840581827521e-05,
"loss": 4.2253,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409001987076469e-05,
"loss": 4.2105,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408163392325417e-05,
"loss": 4.217,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407324797574365e-05,
"loss": 4.2121,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406486202823313e-05,
"loss": 4.209,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405647608072261e-05,
"loss": 4.2158,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404809013321209e-05,
"loss": 4.2133,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.403970418570157e-05,
"loss": 4.2242,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.4031334616994777e-05,
"loss": 4.2213,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.4022948669484257e-05,
"loss": 4.2207,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401456272197374e-05,
"loss": 4.2134,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400617677446322e-05,
"loss": 4.2233,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.39977908269527e-05,
"loss": 4.2204,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398940487944218e-05,
"loss": 4.2131,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398101893193166e-05,
"loss": 4.2313,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397264936322487e-05,
"loss": 4.2125,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396427979451808e-05,
"loss": 4.217,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395589384700756e-05,
"loss": 4.2051,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394750789949704e-05,
"loss": 4.2167,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393912195198652e-05,
"loss": 4.2012,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3930736004476e-05,
"loss": 4.2099,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392235005696548e-05,
"loss": 4.207,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391396410945496e-05,
"loss": 4.22,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390559454074818e-05,
"loss": 4.2137,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389720859323766e-05,
"loss": 4.2169,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388882264572714e-05,
"loss": 4.2044,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388043669821662e-05,
"loss": 4.2167,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387205075070609e-05,
"loss": 4.2238,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386366480319557e-05,
"loss": 4.2156,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385527885568505e-05,
"loss": 4.2108,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384689290817453e-05,
"loss": 4.2192,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383850696066401e-05,
"loss": 4.2099,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383013739195722e-05,
"loss": 4.219,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.38217514444467e-05,
"loss": 4.2037,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381336549693618e-05,
"loss": 4.2132,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380497954942566e-05,
"loss": 4.2051,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796593601915145e-05,
"loss": 4.2076,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788207654404625e-05,
"loss": 4.2075,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3779838085697835e-05,
"loss": 4.2057,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771452138187314e-05,
"loss": 4.2091,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763066190676794e-05,
"loss": 4.2016,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3754680243166274e-05,
"loss": 4.2146,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.196988105773926,
"eval_runtime": 337.8385,
"eval_samples_per_second": 1129.507,
"eval_steps_per_second": 35.298,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.3746310674459483e-05,
"loss": 4.2032,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.3737924726948963e-05,
"loss": 4.1913,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.3729538779438443e-05,
"loss": 4.2138,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.372115283192792e-05,
"loss": 4.2,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.37127668844174e-05,
"loss": 4.2166,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.370439731571061e-05,
"loss": 4.201,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.36960113682001e-05,
"loss": 4.1917,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368762542068958e-05,
"loss": 4.1958,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367923947317906e-05,
"loss": 4.2009,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367085352566854e-05,
"loss": 4.2102,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366246757815802e-05,
"loss": 4.2012,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.36540816306475e-05,
"loss": 4.2036,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.364571206194071e-05,
"loss": 4.1941,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.363732611443019e-05,
"loss": 4.1948,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.362894016691967e-05,
"loss": 4.2012,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.362055421940915e-05,
"loss": 4.189,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.361216827189863e-05,
"loss": 4.1922,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.36037823243881e-05,
"loss": 4.2003,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.359539637687758e-05,
"loss": 4.1999,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.35870268081708e-05,
"loss": 4.2051,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.3578640860660284e-05,
"loss": 4.1996,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.357025491314976e-05,
"loss": 4.2012,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.356186896563924e-05,
"loss": 4.1986,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.355348301812872e-05,
"loss": 4.2039,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.35450970706182e-05,
"loss": 4.1887,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.3536727501911406e-05,
"loss": 4.2039,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.3528341554400886e-05,
"loss": 4.1886,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.3519955606890366e-05,
"loss": 4.1895,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.3511569659379846e-05,
"loss": 4.1866,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.3503183711869326e-05,
"loss": 4.1905,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.3494814143162535e-05,
"loss": 4.197,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.348642819565202e-05,
"loss": 4.1956,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.34780422481415e-05,
"loss": 4.2016,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.346965630063098e-05,
"loss": 4.2035,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.346127035312046e-05,
"loss": 4.1899,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345290078441367e-05,
"loss": 4.1974,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344451483690315e-05,
"loss": 4.1928,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.343612888939263e-05,
"loss": 4.1906,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.342774294188211e-05,
"loss": 4.187,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.341937337317532e-05,
"loss": 4.1873,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.34109874256648e-05,
"loss": 4.1929,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.340260147815428e-05,
"loss": 4.1971,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.339421553064376e-05,
"loss": 4.1838,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338582958313324e-05,
"loss": 4.1897,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337744363562272e-05,
"loss": 4.1976,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.33690576881122e-05,
"loss": 4.19,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.3360671740601686e-05,
"loss": 4.1929,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.3352285793091166e-05,
"loss": 4.1861,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334389984558064e-05,
"loss": 4.1629,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.333551389807012e-05,
"loss": 4.1959,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.3327144329363335e-05,
"loss": 4.1837,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.3318774760656544e-05,
"loss": 4.1843,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.3310388813146024e-05,
"loss": 4.1768,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.3302002865635504e-05,
"loss": 4.1713,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.3293616918124984e-05,
"loss": 4.1731,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328524734941819e-05,
"loss": 4.1854,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.327686140190767e-05,
"loss": 4.1753,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326847545439715e-05,
"loss": 4.1786,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326008950688664e-05,
"loss": 4.1869,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.325171993817985e-05,
"loss": 4.1733,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.324333399066933e-05,
"loss": 4.1763,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.323494804315881e-05,
"loss": 4.185,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322656209564829e-05,
"loss": 4.1624,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.321817614813776e-05,
"loss": 4.1759,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.320979020062724e-05,
"loss": 4.1762,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.320142063192046e-05,
"loss": 4.1873,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.319303468440994e-05,
"loss": 4.163,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.318464873689941e-05,
"loss": 4.175,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.317626278938889e-05,
"loss": 4.1621,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.316790959948584e-05,
"loss": 4.188,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.315952365197532e-05,
"loss": 4.1837,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.31511377044648e-05,
"loss": 4.1801,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.314275175695428e-05,
"loss": 4.19,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313436580944376e-05,
"loss": 4.1897,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.3125979861933235e-05,
"loss": 4.1981,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.3117593914422715e-05,
"loss": 4.1752,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.3109207966912195e-05,
"loss": 4.178,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310083839820541e-05,
"loss": 4.1795,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.3092452450694884e-05,
"loss": 4.1663,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.3084066503184364e-05,
"loss": 4.1851,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.3075680555673844e-05,
"loss": 4.1719,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.306729460816333e-05,
"loss": 4.1856,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.305892503945654e-05,
"loss": 4.1804,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.305053909194602e-05,
"loss": 4.1655,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.30421531444355e-05,
"loss": 4.1775,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.303376719692498e-05,
"loss": 4.1652,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.302538124941446e-05,
"loss": 4.1814,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.301699530190394e-05,
"loss": 4.1772,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.300862573319715e-05,
"loss": 4.1655,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.300023978568663e-05,
"loss": 4.1836,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.299185383817611e-05,
"loss": 4.1715,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.298348426946932e-05,
"loss": 4.1649,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.29750983219588e-05,
"loss": 4.1704,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.2966712374448285e-05,
"loss": 4.181,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.2958326426937765e-05,
"loss": 4.1752,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.2949940479427244e-05,
"loss": 4.1794,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.2941570910720454e-05,
"loss": 4.159,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.2933184963209934e-05,
"loss": 4.1732,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.2924799015699413e-05,
"loss": 4.165,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.291642944699262e-05,
"loss": 4.1788,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.29080434994821e-05,
"loss": 4.1787,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.289965755197158e-05,
"loss": 4.1681,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289127160446106e-05,
"loss": 4.172,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288288565695054e-05,
"loss": 4.1782,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.287449970944002e-05,
"loss": 4.151,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.28661137619295e-05,
"loss": 4.1647,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.285772781441898e-05,
"loss": 4.1581,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.284934186690847e-05,
"loss": 4.1702,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284095591939795e-05,
"loss": 4.1626,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.283256997188742e-05,
"loss": 4.1662,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.28241840243769e-05,
"loss": 4.1581,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281581445567012e-05,
"loss": 4.158,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.28074285081596e-05,
"loss": 4.1649,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.279904256064907e-05,
"loss": 4.1583,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.279065661313855e-05,
"loss": 4.1713,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.278227066562803e-05,
"loss": 4.1683,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.277388471811751e-05,
"loss": 4.1701,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276549877060699e-05,
"loss": 4.1603,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.275711282309647e-05,
"loss": 4.1678,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.274874325438969e-05,
"loss": 4.1714,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.274035730687917e-05,
"loss": 4.1592,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273197135936865e-05,
"loss": 4.1825,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.2723585411858127e-05,
"loss": 4.1563,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.2715199464347607e-05,
"loss": 4.1673,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.2706813516837087e-05,
"loss": 4.1511,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.2698460326934025e-05,
"loss": 4.1686,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.2690074379423505e-05,
"loss": 4.1493,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.2681688431912985e-05,
"loss": 4.1604,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.2673302484402465e-05,
"loss": 4.15,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.2664916536891945e-05,
"loss": 4.1748,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.2656530589381425e-05,
"loss": 4.1589,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.2648144641870904e-05,
"loss": 4.1676,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.2639758694360384e-05,
"loss": 4.1538,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.263137274684987e-05,
"loss": 4.1668,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.262300317814308e-05,
"loss": 4.1717,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.261461723063256e-05,
"loss": 4.1651,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.260623128312204e-05,
"loss": 4.1655,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.259784533561152e-05,
"loss": 4.1651,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.2589459388101e-05,
"loss": 4.1597,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.258107344059048e-05,
"loss": 4.1707,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.257270387188369e-05,
"loss": 4.1537,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256431792437317e-05,
"loss": 4.162,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255593197686265e-05,
"loss": 4.1587,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254754602935213e-05,
"loss": 4.1574,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253916008184161e-05,
"loss": 4.1591,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253077413433109e-05,
"loss": 4.1511,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252238818682057e-05,
"loss": 4.1675,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.2514018618113785e-05,
"loss": 4.1476,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250563267060326e-05,
"loss": 4.1686,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 4.155876636505127,
"eval_runtime": 338.792,
"eval_samples_per_second": 1126.328,
"eval_steps_per_second": 35.199,
"step": 457920
},
{
"epoch": 0.0,
"learning_rate": 4.249724672309274e-05,
"loss": 4.1548,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.248886077558222e-05,
"loss": 4.1418,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.24804748280717e-05,
"loss": 4.1598,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.247208888056118e-05,
"loss": 4.155,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.246370293305066e-05,
"loss": 4.1642,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.245531698554014e-05,
"loss": 4.1531,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.244693103802962e-05,
"loss": 4.144,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.24385450905191e-05,
"loss": 4.1443,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.243015914300858e-05,
"loss": 4.1556,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.242177319549806e-05,
"loss": 4.1612,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.241338724798754e-05,
"loss": 4.1541,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.2405001300477024e-05,
"loss": 4.1536,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239663173177023e-05,
"loss": 4.1511,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238824578425971e-05,
"loss": 4.1457,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.237985983674919e-05,
"loss": 4.151,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237147388923867e-05,
"loss": 4.1381,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.2363087941728146e-05,
"loss": 4.1491,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.2354701994217626e-05,
"loss": 4.1523,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.2346316046707106e-05,
"loss": 4.1526,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.2337930099196586e-05,
"loss": 4.1575,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.2329544151686066e-05,
"loss": 4.1578,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.2321158204175546e-05,
"loss": 4.1501,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.231278863546876e-05,
"loss": 4.1492,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.230440268795824e-05,
"loss": 4.1596,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.229601674044772e-05,
"loss": 4.1372,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.22876307929372e-05,
"loss": 4.1613,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.227924484542668e-05,
"loss": 4.1431,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.227087527671989e-05,
"loss": 4.1401,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.226248932920937e-05,
"loss": 4.1399,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.225410338169885e-05,
"loss": 4.1479,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.224571743418833e-05,
"loss": 4.1464,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.223733148667781e-05,
"loss": 4.1515,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.222894553916729e-05,
"loss": 4.1525,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.222055959165677e-05,
"loss": 4.1575,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.221217364414625e-05,
"loss": 4.142,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.2203820454243196e-05,
"loss": 4.1546,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.2195434506732676e-05,
"loss": 4.1498,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.2187048559222156e-05,
"loss": 4.1415,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.2178662611711635e-05,
"loss": 4.1417,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.2170276664201115e-05,
"loss": 4.1424,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.2161890716690595e-05,
"loss": 4.1444,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.2153504769180075e-05,
"loss": 4.1538,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.2145118821669555e-05,
"loss": 4.1389,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.2136749252962764e-05,
"loss": 4.1436,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.2128363305452244e-05,
"loss": 4.1546,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.2119993736745453e-05,
"loss": 4.1425,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.211160778923493e-05,
"loss": 4.1523,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.210322184172441e-05,
"loss": 4.1418,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.209483589421389e-05,
"loss": 4.1108,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.208644994670338e-05,
"loss": 4.1556,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.207808037799659e-05,
"loss": 4.1398,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.206969443048607e-05,
"loss": 4.1407,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.206130848297555e-05,
"loss": 4.1339,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.205292253546503e-05,
"loss": 4.1218,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.204455296675824e-05,
"loss": 4.1314,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.203618339805145e-05,
"loss": 4.1384,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.202779745054093e-05,
"loss": 4.1321,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.201941150303041e-05,
"loss": 4.1333,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.201102555551989e-05,
"loss": 4.1457,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.200263960800937e-05,
"loss": 4.1279,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.199425366049885e-05,
"loss": 4.1295,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.1985867712988334e-05,
"loss": 4.1434,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.197748176547781e-05,
"loss": 4.1137,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.196909581796729e-05,
"loss": 4.1303,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196070987045677e-05,
"loss": 4.1323,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195232392294625e-05,
"loss": 4.1458,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.194393797543573e-05,
"loss": 4.117,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.1935568406728936e-05,
"loss": 4.1346,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.1927182459218416e-05,
"loss": 4.1166,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.1918796511707896e-05,
"loss": 4.1473,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.1910426943001105e-05,
"loss": 4.1437,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.1902040995490585e-05,
"loss": 4.1388,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.189365504798007e-05,
"loss": 4.142,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.188526910046955e-05,
"loss": 4.1457,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.187688315295903e-05,
"loss": 4.158,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.186851358425224e-05,
"loss": 4.1322,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.186012763674172e-05,
"loss": 4.1366,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.18517416892312e-05,
"loss": 4.1374,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.184335574172068e-05,
"loss": 4.1218,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.183496979421016e-05,
"loss": 4.1379,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.182660022550337e-05,
"loss": 4.1316,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.181821427799285e-05,
"loss": 4.1424,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.180982833048233e-05,
"loss": 4.1463,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.180144238297181e-05,
"loss": 4.1245,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.179305643546129e-05,
"loss": 4.1275,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.178467048795077e-05,
"loss": 4.1262,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.1776300919243985e-05,
"loss": 4.1416,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.1767914971733465e-05,
"loss": 4.1319,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.1759529024222945e-05,
"loss": 4.1296,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.1751143076712425e-05,
"loss": 4.1282,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.1742757129201905e-05,
"loss": 4.1369,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.1734387560495114e-05,
"loss": 4.1252,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.1726001612984594e-05,
"loss": 4.1276,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.1717615665474074e-05,
"loss": 4.1441,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.1709229717963554e-05,
"loss": 4.1296,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.1700843770453034e-05,
"loss": 4.1349,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.1692457822942514e-05,
"loss": 4.1171,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.168407187543199e-05,
"loss": 4.131,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.1675685927921474e-05,
"loss": 4.1246,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.166733273801842e-05,
"loss": 4.1365,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.16589467905079e-05,
"loss": 4.1358,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.165056084299738e-05,
"loss": 4.1321,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.164217489548686e-05,
"loss": 4.1315,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.163378894797634e-05,
"loss": 4.1327,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.162540300046581e-05,
"loss": 4.1115,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.161703343175903e-05,
"loss": 4.1248,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.160864748424851e-05,
"loss": 4.112,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.160026153673799e-05,
"loss": 4.1309,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.159187558922746e-05,
"loss": 4.1203,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.158348964171694e-05,
"loss": 4.1228,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.157510369420643e-05,
"loss": 4.1151,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.156671774669591e-05,
"loss": 4.1199,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.1558348177989116e-05,
"loss": 4.1259,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.1549962230478596e-05,
"loss": 4.1172,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.1541576282968076e-05,
"loss": 4.1267,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.1533190335457556e-05,
"loss": 4.1325,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.1524804387947036e-05,
"loss": 4.1247,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.1516434819240245e-05,
"loss": 4.1279,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.1508048871729725e-05,
"loss": 4.1235,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.1499662924219205e-05,
"loss": 4.1303,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.1491276976708685e-05,
"loss": 4.1233,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.1482891029198165e-05,
"loss": 4.1351,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.1474505081687645e-05,
"loss": 4.1163,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.1466119134177125e-05,
"loss": 4.1272,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.145773318666661e-05,
"loss": 4.1141,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.144936361795982e-05,
"loss": 4.1217,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.14409776704493e-05,
"loss": 4.1137,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.143259172293878e-05,
"loss": 4.1188,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.142420577542826e-05,
"loss": 4.1117,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.141581982791774e-05,
"loss": 4.1294,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.140745025921095e-05,
"loss": 4.1223,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.139906431170043e-05,
"loss": 4.1259,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.139067836418991e-05,
"loss": 4.112,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.138229241667939e-05,
"loss": 4.13,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.13739228479726e-05,
"loss": 4.1289,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.136553690046208e-05,
"loss": 4.1265,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.1357150952951565e-05,
"loss": 4.1264,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.1348765005441045e-05,
"loss": 4.1212,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.1340395436734254e-05,
"loss": 4.123,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.1332009489223734e-05,
"loss": 4.1335,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.1323639920516944e-05,
"loss": 4.1113,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.1315253973006424e-05,
"loss": 4.1204,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.1306868025495903e-05,
"loss": 4.1235,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.1298482077985383e-05,
"loss": 4.1213,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.129009613047486e-05,
"loss": 4.1118,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.128172656176807e-05,
"loss": 4.1125,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.127334061425755e-05,
"loss": 4.1272,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.126495466674703e-05,
"loss": 4.114,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.125656871923652e-05,
"loss": 4.128,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 4.125317573547363,
"eval_runtime": 299.9764,
"eval_samples_per_second": 1272.07,
"eval_steps_per_second": 39.753,
"step": 534240
},
{
"epoch": 1.0,
"learning_rate": 4.1248182771726e-05,
"loss": 4.1142,
"step": 534528
},
{
"epoch": 1.0,
"learning_rate": 4.123979682421548e-05,
"loss": 4.1033,
"step": 535040
},
{
"epoch": 1.0,
"learning_rate": 4.123141087670495e-05,
"loss": 4.1224,
"step": 535552
},
{
"epoch": 1.0,
"learning_rate": 4.122304130799817e-05,
"loss": 4.1117,
"step": 536064
},
{
"epoch": 1.0,
"learning_rate": 4.121465536048765e-05,
"loss": 4.123,
"step": 536576
},
{
"epoch": 1.0,
"learning_rate": 4.120626941297712e-05,
"loss": 4.1187,
"step": 537088
},
{
"epoch": 1.0,
"learning_rate": 4.11978834654666e-05,
"loss": 4.1069,
"step": 537600
},
{
"epoch": 1.0,
"learning_rate": 4.118949751795608e-05,
"loss": 4.1063,
"step": 538112
},
{
"epoch": 1.0,
"learning_rate": 4.118111157044556e-05,
"loss": 4.117,
"step": 538624
},
{
"epoch": 1.0,
"learning_rate": 4.117274200173877e-05,
"loss": 4.1208,
"step": 539136
},
{
"epoch": 1.0,
"learning_rate": 4.116435605422826e-05,
"loss": 4.1137,
"step": 539648
},
{
"epoch": 1.0,
"learning_rate": 4.115597010671774e-05,
"loss": 4.1138,
"step": 540160
},
{
"epoch": 1.0,
"learning_rate": 4.114760053801095e-05,
"loss": 4.112,
"step": 540672
},
{
"epoch": 1.0,
"learning_rate": 4.1139214590500426e-05,
"loss": 4.1086,
"step": 541184
},
{
"epoch": 1.0,
"learning_rate": 4.1130828642989906e-05,
"loss": 4.1139,
"step": 541696
},
{
"epoch": 1.0,
"learning_rate": 4.1122442695479386e-05,
"loss": 4.1029,
"step": 542208
},
{
"epoch": 1.0,
"learning_rate": 4.1114056747968866e-05,
"loss": 4.1088,
"step": 542720
},
{
"epoch": 1.0,
"learning_rate": 4.1105670800458346e-05,
"loss": 4.1137,
"step": 543232
},
{
"epoch": 1.0,
"learning_rate": 4.1097284852947826e-05,
"loss": 4.1138,
"step": 543744
},
{
"epoch": 1.0,
"learning_rate": 4.1088898905437306e-05,
"loss": 4.1142,
"step": 544256
},
{
"epoch": 1.0,
"learning_rate": 4.1080529336730515e-05,
"loss": 4.1234,
"step": 544768
},
{
"epoch": 1.0,
"learning_rate": 4.1072143389219995e-05,
"loss": 4.1145,
"step": 545280
},
{
"epoch": 1.0,
"learning_rate": 4.1063757441709475e-05,
"loss": 4.1103,
"step": 545792
},
{
"epoch": 1.0,
"learning_rate": 4.1055371494198955e-05,
"loss": 4.1164,
"step": 546304
},
{
"epoch": 1.0,
"learning_rate": 4.1046985546688435e-05,
"loss": 4.1067,
"step": 546816
},
{
"epoch": 1.0,
"learning_rate": 4.103861597798165e-05,
"loss": 4.1193,
"step": 547328
},
{
"epoch": 1.0,
"learning_rate": 4.103023003047113e-05,
"loss": 4.1044,
"step": 547840
},
{
"epoch": 1.0,
"learning_rate": 4.102184408296061e-05,
"loss": 4.1082,
"step": 548352
},
{
"epoch": 1.0,
"learning_rate": 4.101345813545009e-05,
"loss": 4.1052,
"step": 548864
},
{
"epoch": 1.0,
"learning_rate": 4.100507218793957e-05,
"loss": 4.1071,
"step": 549376
},
{
"epoch": 1.01,
"learning_rate": 4.099668624042905e-05,
"loss": 4.1075,
"step": 549888
},
{
"epoch": 1.01,
"learning_rate": 4.098830029291853e-05,
"loss": 4.1145,
"step": 550400
},
{
"epoch": 1.01,
"learning_rate": 4.097993072421174e-05,
"loss": 4.1125,
"step": 550912
},
{
"epoch": 1.01,
"learning_rate": 4.097154477670122e-05,
"loss": 4.1181,
"step": 551424
},
{
"epoch": 1.01,
"learning_rate": 4.09631588291907e-05,
"loss": 4.1047,
"step": 551936
},
{
"epoch": 1.01,
"learning_rate": 4.095477288168018e-05,
"loss": 4.1193,
"step": 552448
},
{
"epoch": 1.01,
"learning_rate": 4.094640331297339e-05,
"loss": 4.1132,
"step": 552960
},
{
"epoch": 1.01,
"learning_rate": 4.0938017365462875e-05,
"loss": 4.1009,
"step": 553472
},
{
"epoch": 1.01,
"learning_rate": 4.0929631417952355e-05,
"loss": 4.1072,
"step": 553984
},
{
"epoch": 1.01,
"learning_rate": 4.0921245470441835e-05,
"loss": 4.1061,
"step": 554496
},
{
"epoch": 1.01,
"learning_rate": 4.091285952293131e-05,
"loss": 4.1061,
"step": 555008
},
{
"epoch": 1.01,
"learning_rate": 4.090447357542079e-05,
"loss": 4.1144,
"step": 555520
},
{
"epoch": 1.01,
"learning_rate": 4.089608762791027e-05,
"loss": 4.1012,
"step": 556032
},
{
"epoch": 1.01,
"learning_rate": 4.088770168039975e-05,
"loss": 4.1053,
"step": 556544
},
{
"epoch": 1.01,
"learning_rate": 4.087933211169296e-05,
"loss": 4.1148,
"step": 557056
},
{
"epoch": 1.01,
"learning_rate": 4.087094616418244e-05,
"loss": 4.1062,
"step": 557568
},
{
"epoch": 1.01,
"learning_rate": 4.086256021667192e-05,
"loss": 4.1109,
"step": 558080
},
{
"epoch": 1.01,
"learning_rate": 4.08541742691614e-05,
"loss": 4.1073,
"step": 558592
},
{
"epoch": 1.01,
"learning_rate": 4.084578832165088e-05,
"loss": 4.0715,
"step": 559104
},
{
"epoch": 1.01,
"learning_rate": 4.083741875294409e-05,
"loss": 4.1209,
"step": 559616
},
{
"epoch": 1.01,
"learning_rate": 4.082903280543357e-05,
"loss": 4.0995,
"step": 560128
},
{
"epoch": 1.01,
"learning_rate": 4.082064685792305e-05,
"loss": 4.1086,
"step": 560640
},
{
"epoch": 1.01,
"learning_rate": 4.081226091041253e-05,
"loss": 4.0926,
"step": 561152
},
{
"epoch": 1.01,
"learning_rate": 4.080387496290201e-05,
"loss": 4.0873,
"step": 561664
},
{
"epoch": 1.01,
"learning_rate": 4.079548901539149e-05,
"loss": 4.0938,
"step": 562176
},
{
"epoch": 1.01,
"learning_rate": 4.078710306788097e-05,
"loss": 4.0992,
"step": 562688
},
{
"epoch": 1.01,
"learning_rate": 4.077871712037045e-05,
"loss": 4.0989,
"step": 563200
},
{
"epoch": 1.01,
"learning_rate": 4.077034755166366e-05,
"loss": 4.0914,
"step": 563712
},
{
"epoch": 1.01,
"learning_rate": 4.076196160415314e-05,
"loss": 4.1134,
"step": 564224
},
{
"epoch": 1.01,
"learning_rate": 4.075357565664262e-05,
"loss": 4.0928,
"step": 564736
},
{
"epoch": 1.01,
"learning_rate": 4.07451897091321e-05,
"loss": 4.0938,
"step": 565248
},
{
"epoch": 1.01,
"learning_rate": 4.073680376162158e-05,
"loss": 4.1074,
"step": 565760
},
{
"epoch": 1.01,
"learning_rate": 4.072841781411106e-05,
"loss": 4.0787,
"step": 566272
},
{
"epoch": 1.01,
"learning_rate": 4.072003186660054e-05,
"loss": 4.0893,
"step": 566784
},
{
"epoch": 1.01,
"learning_rate": 4.071164591909002e-05,
"loss": 4.0978,
"step": 567296
},
{
"epoch": 1.01,
"learning_rate": 4.07032599715795e-05,
"loss": 4.1089,
"step": 567808
},
{
"epoch": 1.01,
"learning_rate": 4.069489040287272e-05,
"loss": 4.0837,
"step": 568320
},
{
"epoch": 1.01,
"learning_rate": 4.06865044553622e-05,
"loss": 4.099,
"step": 568832
},
{
"epoch": 1.01,
"learning_rate": 4.067811850785167e-05,
"loss": 4.0813,
"step": 569344
},
{
"epoch": 1.01,
"learning_rate": 4.066973256034115e-05,
"loss": 4.1094,
"step": 569856
},
{
"epoch": 1.01,
"learning_rate": 4.0661362991634366e-05,
"loss": 4.1032,
"step": 570368
},
{
"epoch": 1.01,
"learning_rate": 4.0652977044123846e-05,
"loss": 4.1022,
"step": 570880
},
{
"epoch": 1.01,
"learning_rate": 4.064459109661332e-05,
"loss": 4.1026,
"step": 571392
},
{
"epoch": 1.01,
"learning_rate": 4.06362051491028e-05,
"loss": 4.1116,
"step": 571904
},
{
"epoch": 1.01,
"learning_rate": 4.062781920159228e-05,
"loss": 4.1221,
"step": 572416
},
{
"epoch": 1.01,
"learning_rate": 4.0619449632885495e-05,
"loss": 4.0979,
"step": 572928
},
{
"epoch": 1.01,
"learning_rate": 4.061108006417871e-05,
"loss": 4.1005,
"step": 573440
},
{
"epoch": 1.01,
"learning_rate": 4.060269411666819e-05,
"loss": 4.1042,
"step": 573952
},
{
"epoch": 1.01,
"learning_rate": 4.059430816915767e-05,
"loss": 4.0865,
"step": 574464
},
{
"epoch": 1.01,
"learning_rate": 4.0585922221647144e-05,
"loss": 4.0976,
"step": 574976
},
{
"epoch": 1.01,
"learning_rate": 4.0577536274136624e-05,
"loss": 4.0988,
"step": 575488
},
{
"epoch": 1.01,
"learning_rate": 4.056916670542984e-05,
"loss": 4.1057,
"step": 576000
},
{
"epoch": 1.01,
"learning_rate": 4.056078075791932e-05,
"loss": 4.1077,
"step": 576512
},
{
"epoch": 1.01,
"learning_rate": 4.055239481040879e-05,
"loss": 4.0913,
"step": 577024
},
{
"epoch": 1.01,
"learning_rate": 4.054400886289827e-05,
"loss": 4.0889,
"step": 577536
},
{
"epoch": 1.01,
"learning_rate": 4.053562291538775e-05,
"loss": 4.0937,
"step": 578048
},
{
"epoch": 1.01,
"learning_rate": 4.052723696787723e-05,
"loss": 4.1048,
"step": 578560
},
{
"epoch": 1.01,
"learning_rate": 4.051886739917045e-05,
"loss": 4.0971,
"step": 579072
},
{
"epoch": 1.01,
"learning_rate": 4.0510497830463664e-05,
"loss": 4.0927,
"step": 579584
},
{
"epoch": 1.02,
"learning_rate": 4.0502111882953144e-05,
"loss": 4.0912,
"step": 580096
},
{
"epoch": 1.02,
"learning_rate": 4.049372593544262e-05,
"loss": 4.103,
"step": 580608
},
{
"epoch": 1.02,
"learning_rate": 4.04853399879321e-05,
"loss": 4.0918,
"step": 581120
},
{
"epoch": 1.02,
"learning_rate": 4.047695404042158e-05,
"loss": 4.0905,
"step": 581632
},
{
"epoch": 1.02,
"learning_rate": 4.046856809291106e-05,
"loss": 4.1077,
"step": 582144
},
{
"epoch": 1.02,
"learning_rate": 4.046018214540054e-05,
"loss": 4.0977,
"step": 582656
},
{
"epoch": 1.02,
"learning_rate": 4.045179619789002e-05,
"loss": 4.0977,
"step": 583168
},
{
"epoch": 1.02,
"learning_rate": 4.04434102503795e-05,
"loss": 4.0875,
"step": 583680
},
{
"epoch": 1.02,
"learning_rate": 4.043502430286898e-05,
"loss": 4.0936,
"step": 584192
},
{
"epoch": 1.02,
"learning_rate": 4.042663835535846e-05,
"loss": 4.0874,
"step": 584704
},
{
"epoch": 1.02,
"learning_rate": 4.0418268786651666e-05,
"loss": 4.1043,
"step": 585216
},
{
"epoch": 1.02,
"learning_rate": 4.040988283914115e-05,
"loss": 4.098,
"step": 585728
},
{
"epoch": 1.02,
"learning_rate": 4.040149689163063e-05,
"loss": 4.0994,
"step": 586240
},
{
"epoch": 1.02,
"learning_rate": 4.039311094412011e-05,
"loss": 4.0976,
"step": 586752
},
{
"epoch": 1.02,
"learning_rate": 4.038474137541332e-05,
"loss": 4.097,
"step": 587264
},
{
"epoch": 1.02,
"learning_rate": 4.03763554279028e-05,
"loss": 4.0822,
"step": 587776
},
{
"epoch": 1.02,
"learning_rate": 4.036796948039228e-05,
"loss": 4.0863,
"step": 588288
},
{
"epoch": 1.02,
"learning_rate": 4.035958353288176e-05,
"loss": 4.0802,
"step": 588800
},
{
"epoch": 1.02,
"learning_rate": 4.035119758537124e-05,
"loss": 4.0975,
"step": 589312
},
{
"epoch": 1.02,
"learning_rate": 4.034281163786072e-05,
"loss": 4.0852,
"step": 589824
},
{
"epoch": 1.02,
"learning_rate": 4.03344256903502e-05,
"loss": 4.0866,
"step": 590336
},
{
"epoch": 1.02,
"learning_rate": 4.032603974283968e-05,
"loss": 4.0793,
"step": 590848
},
{
"epoch": 1.02,
"learning_rate": 4.031767017413289e-05,
"loss": 4.0883,
"step": 591360
},
{
"epoch": 1.02,
"learning_rate": 4.030928422662237e-05,
"loss": 4.0892,
"step": 591872
},
{
"epoch": 1.02,
"learning_rate": 4.030089827911185e-05,
"loss": 4.0819,
"step": 592384
},
{
"epoch": 1.02,
"learning_rate": 4.029251233160133e-05,
"loss": 4.0988,
"step": 592896
},
{
"epoch": 1.02,
"learning_rate": 4.0284142762894547e-05,
"loss": 4.0945,
"step": 593408
},
{
"epoch": 1.02,
"learning_rate": 4.0275756815384027e-05,
"loss": 4.0889,
"step": 593920
},
{
"epoch": 1.02,
"learning_rate": 4.0267387246677236e-05,
"loss": 4.0959,
"step": 594432
},
{
"epoch": 1.02,
"learning_rate": 4.0259001299166716e-05,
"loss": 4.09,
"step": 594944
},
{
"epoch": 1.02,
"learning_rate": 4.0250615351656196e-05,
"loss": 4.0922,
"step": 595456
},
{
"epoch": 1.02,
"learning_rate": 4.0242229404145675e-05,
"loss": 4.0955,
"step": 595968
},
{
"epoch": 1.02,
"learning_rate": 4.0233843456635155e-05,
"loss": 4.0985,
"step": 596480
},
{
"epoch": 1.02,
"learning_rate": 4.0225473887928365e-05,
"loss": 4.0859,
"step": 596992
},
{
"epoch": 1.02,
"learning_rate": 4.0217087940417845e-05,
"loss": 4.0943,
"step": 597504
},
{
"epoch": 1.02,
"learning_rate": 4.0208701992907324e-05,
"loss": 4.0861,
"step": 598016
},
{
"epoch": 1.02,
"learning_rate": 4.0200316045396804e-05,
"loss": 4.0891,
"step": 598528
},
{
"epoch": 1.02,
"learning_rate": 4.0191930097886284e-05,
"loss": 4.0802,
"step": 599040
},
{
"epoch": 1.02,
"learning_rate": 4.0183544150375764e-05,
"loss": 4.0838,
"step": 599552
},
{
"epoch": 1.02,
"learning_rate": 4.017517458166898e-05,
"loss": 4.0801,
"step": 600064
},
{
"epoch": 1.02,
"learning_rate": 4.016678863415845e-05,
"loss": 4.0954,
"step": 600576
},
{
"epoch": 1.02,
"learning_rate": 4.015840268664793e-05,
"loss": 4.0875,
"step": 601088
},
{
"epoch": 1.02,
"learning_rate": 4.015001673913741e-05,
"loss": 4.095,
"step": 601600
},
{
"epoch": 1.02,
"learning_rate": 4.014163079162689e-05,
"loss": 4.0763,
"step": 602112
},
{
"epoch": 1.02,
"learning_rate": 4.013324484411637e-05,
"loss": 4.1018,
"step": 602624
},
{
"epoch": 1.02,
"learning_rate": 4.012485889660585e-05,
"loss": 4.0905,
"step": 603136
},
{
"epoch": 1.02,
"learning_rate": 4.011647294909533e-05,
"loss": 4.0949,
"step": 603648
},
{
"epoch": 1.02,
"learning_rate": 4.010810338038854e-05,
"loss": 4.0924,
"step": 604160
},
{
"epoch": 1.02,
"learning_rate": 4.009971743287803e-05,
"loss": 4.0899,
"step": 604672
},
{
"epoch": 1.02,
"learning_rate": 4.009133148536751e-05,
"loss": 4.0882,
"step": 605184
},
{
"epoch": 1.02,
"learning_rate": 4.008294553785699e-05,
"loss": 4.0984,
"step": 605696
},
{
"epoch": 1.02,
"learning_rate": 4.00745759691502e-05,
"loss": 4.0813,
"step": 606208
},
{
"epoch": 1.02,
"learning_rate": 4.006619002163968e-05,
"loss": 4.0905,
"step": 606720
},
{
"epoch": 1.02,
"learning_rate": 4.005780407412916e-05,
"loss": 4.0905,
"step": 607232
},
{
"epoch": 1.02,
"learning_rate": 4.004941812661864e-05,
"loss": 4.0867,
"step": 607744
},
{
"epoch": 1.02,
"learning_rate": 4.004103217910812e-05,
"loss": 4.0802,
"step": 608256
},
{
"epoch": 1.02,
"learning_rate": 4.003266261040133e-05,
"loss": 4.0806,
"step": 608768
},
{
"epoch": 1.02,
"learning_rate": 4.002427666289081e-05,
"loss": 4.0945,
"step": 609280
},
{
"epoch": 1.02,
"learning_rate": 4.001589071538029e-05,
"loss": 4.0835,
"step": 609792
},
{
"epoch": 1.02,
"learning_rate": 4.000750476786977e-05,
"loss": 4.0952,
"step": 610304
},
{
"epoch": 1.03,
"eval_loss": 4.10066556930542,
"eval_runtime": 301.8195,
"eval_samples_per_second": 1264.302,
"eval_steps_per_second": 39.51,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.999911882035925e-05,
"loss": 4.0795,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.999073287284873e-05,
"loss": 4.0772,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.9982346925338207e-05,
"loss": 4.0838,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.997396097782769e-05,
"loss": 4.083,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.9965575030317167e-05,
"loss": 4.0921,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.9957189082806646e-05,
"loss": 4.0851,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.9948803135296126e-05,
"loss": 4.0759,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.994043356658934e-05,
"loss": 4.0758,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.9932047619078815e-05,
"loss": 4.0804,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.9923661671568295e-05,
"loss": 4.0929,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.9915275724057775e-05,
"loss": 4.081,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.9906889776547255e-05,
"loss": 4.0792,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.9898503829036735e-05,
"loss": 4.0906,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.9890117881526215e-05,
"loss": 4.0706,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.9881731934015695e-05,
"loss": 4.0777,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.9873345986505175e-05,
"loss": 4.0742,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.986496003899466e-05,
"loss": 4.0766,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.985657409148414e-05,
"loss": 4.0839,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.984818814397362e-05,
"loss": 4.0831,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.98398021964631e-05,
"loss": 4.0807,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.983141624895258e-05,
"loss": 4.0951,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.9823030301442055e-05,
"loss": 4.0821,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.9814644353931535e-05,
"loss": 4.0831,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.9806258406421015e-05,
"loss": 4.0804,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.9797872458910495e-05,
"loss": 4.0795,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.9789502890203704e-05,
"loss": 4.0865,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.9781116942693184e-05,
"loss": 4.0753,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.97727473739864e-05,
"loss": 4.0792,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.976436142647588e-05,
"loss": 4.069,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.975597547896536e-05,
"loss": 4.0764,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.974758953145484e-05,
"loss": 4.0748,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.973920358394432e-05,
"loss": 4.0813,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.97308176364338e-05,
"loss": 4.0862,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.972243168892328e-05,
"loss": 4.0875,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971404574141276e-05,
"loss": 4.0768,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.970565979390224e-05,
"loss": 4.0818,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.969729022519545e-05,
"loss": 4.0857,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.968890427768493e-05,
"loss": 4.0724,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.968051833017441e-05,
"loss": 4.0735,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.967213238266389e-05,
"loss": 4.0746,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.966374643515337e-05,
"loss": 4.0779,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.9655376866446584e-05,
"loss": 4.0753,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.9646990918936064e-05,
"loss": 4.0774,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.9638604971425544e-05,
"loss": 4.0765,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.9630219023915024e-05,
"loss": 4.0822,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.9621833076404504e-05,
"loss": 4.0781,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.961346350769771e-05,
"loss": 4.0781,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.960507756018719e-05,
"loss": 4.0763,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.959669161267667e-05,
"loss": 4.0415,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.958830566516615e-05,
"loss": 4.0888,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.957991971765563e-05,
"loss": 4.0683,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.957155014894884e-05,
"loss": 4.0802,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.956316420143832e-05,
"loss": 4.0659,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.95547782539278e-05,
"loss": 4.0587,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.954639230641728e-05,
"loss": 4.0598,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.953800635890676e-05,
"loss": 4.0674,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.952963679019998e-05,
"loss": 4.0709,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.952125084268946e-05,
"loss": 4.0646,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.951286489517894e-05,
"loss": 4.0796,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.950447894766842e-05,
"loss": 4.0664,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.949609300015789e-05,
"loss": 4.063,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.948770705264737e-05,
"loss": 4.076,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.947932110513685e-05,
"loss": 4.0528,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.947093515762633e-05,
"loss": 4.0581,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.946254921011581e-05,
"loss": 4.0685,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.945417964140902e-05,
"loss": 4.0762,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.94457936938985e-05,
"loss": 4.0564,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.9437407746387986e-05,
"loss": 4.0666,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.9429038177681195e-05,
"loss": 4.0505,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.9420652230170675e-05,
"loss": 4.0779,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.9412266282660155e-05,
"loss": 4.0762,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.9403880335149635e-05,
"loss": 4.0716,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.9395494387639115e-05,
"loss": 4.0756,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.9387108440128595e-05,
"loss": 4.0815,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.9378722492618075e-05,
"loss": 4.0935,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.9370352923911284e-05,
"loss": 4.0708,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.9361966976400764e-05,
"loss": 4.0705,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.9353581028890244e-05,
"loss": 4.07,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.9345195081379724e-05,
"loss": 4.0644,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.9336809133869204e-05,
"loss": 4.0683,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.932843956516242e-05,
"loss": 4.0706,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.93200536176519e-05,
"loss": 4.0757,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.931166767014138e-05,
"loss": 4.0807,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.930328172263086e-05,
"loss": 4.0614,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.929489577512034e-05,
"loss": 4.0592,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.928650982760982e-05,
"loss": 4.062,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.92781238800993e-05,
"loss": 4.0785,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.926975431139251e-05,
"loss": 4.0711,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.926138474268572e-05,
"loss": 4.0606,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.92529987951752e-05,
"loss": 4.0625,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.924461284766468e-05,
"loss": 4.0726,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.923622690015416e-05,
"loss": 4.0651,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.922784095264364e-05,
"loss": 4.0596,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.9219455005133124e-05,
"loss": 4.0776,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.9211069057622604e-05,
"loss": 4.0711,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.920268311011208e-05,
"loss": 4.0698,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.9194313541405293e-05,
"loss": 4.0609,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.91859439726985e-05,
"loss": 4.0628,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.917755802518798e-05,
"loss": 4.0619,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.916917207767746e-05,
"loss": 4.0735,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.916078613016694e-05,
"loss": 4.071,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.915240018265642e-05,
"loss": 4.0678,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.9144014235145896e-05,
"loss": 4.0737,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.9135628287635375e-05,
"loss": 4.0624,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.912724234012486e-05,
"loss": 4.0607,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.911887277141808e-05,
"loss": 4.055,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.911050320271129e-05,
"loss": 4.0501,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.910211725520077e-05,
"loss": 4.0706,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.909373130769025e-05,
"loss": 4.061,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.908534536017973e-05,
"loss": 4.0539,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.90769594126692e-05,
"loss": 4.0527,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.9068606222766145e-05,
"loss": 4.0562,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.9060220275255625e-05,
"loss": 4.066,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.9051834327745105e-05,
"loss": 4.0571,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.9043448380234585e-05,
"loss": 4.0684,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.9035062432724065e-05,
"loss": 4.069,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.9026676485213545e-05,
"loss": 4.0637,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.9018290537703025e-05,
"loss": 4.067,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.9009904590192505e-05,
"loss": 4.0604,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.9001518642681985e-05,
"loss": 4.0643,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.899316545277893e-05,
"loss": 4.0689,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.898477950526841e-05,
"loss": 4.0673,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.897639355775789e-05,
"loss": 4.06,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.896800761024737e-05,
"loss": 4.0651,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.895962166273684e-05,
"loss": 4.0596,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.895123571522632e-05,
"loss": 4.0598,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.89428497677158e-05,
"loss": 4.0506,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.893446382020528e-05,
"loss": 4.059,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.8926110630302235e-05,
"loss": 4.0511,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.8917724682791715e-05,
"loss": 4.0657,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.8909338735281195e-05,
"loss": 4.0566,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.8900952787770674e-05,
"loss": 4.0717,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.889256684026015e-05,
"loss": 4.0486,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.888418089274963e-05,
"loss": 4.0709,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.887579494523911e-05,
"loss": 4.0649,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.886740899772859e-05,
"loss": 4.0666,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.885902305021807e-05,
"loss": 4.0661,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.885063710270755e-05,
"loss": 4.0619,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884225115519703e-05,
"loss": 4.063,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.883386520768651e-05,
"loss": 4.0731,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.8825495638979716e-05,
"loss": 4.0514,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.881712607027293e-05,
"loss": 4.0632,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.880874012276241e-05,
"loss": 4.0609,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.880035417525189e-05,
"loss": 4.0589,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.879196822774137e-05,
"loss": 4.0566,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.878358228023085e-05,
"loss": 4.0523,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.877519633272033e-05,
"loss": 4.0666,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.876681038520981e-05,
"loss": 4.0589,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.875842443769929e-05,
"loss": 4.0646,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 4.081218719482422,
"eval_runtime": 294.2111,
"eval_samples_per_second": 1296.997,
"eval_steps_per_second": 40.532,
"step": 686880
},
{
"epoch": 1.0,
"learning_rate": 3.87500548689925e-05,
"loss": 4.049,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.874166892148198e-05,
"loss": 4.0519,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.873328297397146e-05,
"loss": 4.054,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.872491340526467e-05,
"loss": 4.058,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.871652745775416e-05,
"loss": 4.068,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.870814151024364e-05,
"loss": 4.0565,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.869975556273312e-05,
"loss": 4.0515,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.86913696152226e-05,
"loss": 4.0502,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.868298366771208e-05,
"loss": 4.0512,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.8674597720201557e-05,
"loss": 4.0662,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.866621177269103e-05,
"loss": 4.054,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.8657842203984246e-05,
"loss": 4.0537,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.8649489014081184e-05,
"loss": 4.0622,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.8641103066570664e-05,
"loss": 4.0446,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.8632717119060144e-05,
"loss": 4.0493,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.8624331171549624e-05,
"loss": 4.049,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.861594522403911e-05,
"loss": 4.0527,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.860755927652859e-05,
"loss": 4.0514,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.85991897078218e-05,
"loss": 4.0577,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.859080376031128e-05,
"loss": 4.0543,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.858241781280076e-05,
"loss": 4.0672,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.857403186529024e-05,
"loss": 4.0541,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.856564591777972e-05,
"loss": 4.0584,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.85572599702692e-05,
"loss": 4.0521,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.854889040156241e-05,
"loss": 4.0574,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.854050445405189e-05,
"loss": 4.0605,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.853211850654137e-05,
"loss": 4.0452,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.852373255903085e-05,
"loss": 4.0558,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.851534661152033e-05,
"loss": 4.0435,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.850696066400981e-05,
"loss": 4.0516,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.849857471649929e-05,
"loss": 4.0497,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.849018876898877e-05,
"loss": 4.0531,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.848181920028198e-05,
"loss": 4.0634,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.847344963157519e-05,
"loss": 4.0623,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.846506368406467e-05,
"loss": 4.0511,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.845667773655415e-05,
"loss": 4.0506,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.8448291789043626e-05,
"loss": 4.0636,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.8439905841533106e-05,
"loss": 4.0466,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.8431519894022586e-05,
"loss": 4.0481,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.8423133946512066e-05,
"loss": 4.05,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.8414747999001546e-05,
"loss": 4.0545,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.840636205149103e-05,
"loss": 4.0505,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.839797610398051e-05,
"loss": 4.0488,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.838959015646999e-05,
"loss": 4.0533,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.838120420895947e-05,
"loss": 4.0536,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.837283464025268e-05,
"loss": 4.0535,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.836444869274216e-05,
"loss": 4.0538,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.835606274523164e-05,
"loss": 4.0515,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.834769317652485e-05,
"loss": 4.0173,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.833930722901433e-05,
"loss": 4.0598,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.833092128150381e-05,
"loss": 4.0428,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.832253533399329e-05,
"loss": 4.057,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.831414938648277e-05,
"loss": 4.0393,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.8305779817775986e-05,
"loss": 4.0342,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.8297393870265466e-05,
"loss": 4.0344,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.8289024301558675e-05,
"loss": 4.0422,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.8280638354048155e-05,
"loss": 4.0517,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.8272252406537635e-05,
"loss": 4.0351,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.8263866459027115e-05,
"loss": 4.056,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.8255480511516595e-05,
"loss": 4.0453,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.8247110942809804e-05,
"loss": 4.0328,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.8238724995299284e-05,
"loss": 4.0515,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.8230339047788764e-05,
"loss": 4.0314,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.8221953100278244e-05,
"loss": 4.0304,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.8213567152767724e-05,
"loss": 4.0442,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.8205181205257204e-05,
"loss": 4.0509,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.8196795257746684e-05,
"loss": 4.0355,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.8188409310236164e-05,
"loss": 4.041,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.818003974152938e-05,
"loss": 4.0295,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.817165379401886e-05,
"loss": 4.0486,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.816326784650834e-05,
"loss": 4.0539,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.815488189899781e-05,
"loss": 4.0477,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.814649595148729e-05,
"loss": 4.0505,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.813811000397677e-05,
"loss": 4.0562,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.812972405646625e-05,
"loss": 4.066,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.812135448775946e-05,
"loss": 4.0473,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.811296854024894e-05,
"loss": 4.0488,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.810458259273842e-05,
"loss": 4.0424,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.80961966452279e-05,
"loss": 4.0439,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.808781069771739e-05,
"loss": 4.0407,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.80794411290106e-05,
"loss": 4.0485,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.807105518150008e-05,
"loss": 4.0477,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.806266923398956e-05,
"loss": 4.0581,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.805428328647904e-05,
"loss": 4.0342,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.804589733896852e-05,
"loss": 4.0364,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.8037511391458e-05,
"loss": 4.0421,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.8029141822751207e-05,
"loss": 4.0478,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.8020755875240687e-05,
"loss": 4.0475,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.8012369927730166e-05,
"loss": 4.0415,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.8003983980219646e-05,
"loss": 4.0385,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.7995598032709126e-05,
"loss": 4.0466,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.7987212085198606e-05,
"loss": 4.0409,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.797884251649182e-05,
"loss": 4.0348,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.79704565689813e-05,
"loss": 4.0537,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.796207062147078e-05,
"loss": 4.0454,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.795370105276399e-05,
"loss": 4.0475,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.794531510525347e-05,
"loss": 4.0368,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.793692915774295e-05,
"loss": 4.0404,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.792854321023243e-05,
"loss": 4.0366,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.792015726272191e-05,
"loss": 4.0477,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.791177131521139e-05,
"loss": 4.0533,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.790338536770087e-05,
"loss": 4.0398,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.789499942019035e-05,
"loss": 4.0512,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.7886613472679824e-05,
"loss": 4.0409,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.787822752516931e-05,
"loss": 4.0395,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.786984157765879e-05,
"loss": 4.0287,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.786145563014827e-05,
"loss": 4.0288,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.785306968263775e-05,
"loss": 4.0411,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.784470011393096e-05,
"loss": 4.0423,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.783631416642044e-05,
"loss": 4.028,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.782792821890992e-05,
"loss": 4.0298,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.78195422713994e-05,
"loss": 4.0333,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.781117270269261e-05,
"loss": 4.0394,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.780278675518209e-05,
"loss": 4.0327,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.779440080767157e-05,
"loss": 4.0448,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.778601486016105e-05,
"loss": 4.0443,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.7777645291454264e-05,
"loss": 4.0426,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.7769259343943744e-05,
"loss": 4.0378,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.7760873396433224e-05,
"loss": 4.0419,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.7752487448922704e-05,
"loss": 4.0402,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.7744117880215913e-05,
"loss": 4.0473,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.773574831150912e-05,
"loss": 4.0443,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.77273623639986e-05,
"loss": 4.0365,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.771897641648808e-05,
"loss": 4.0419,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.771059046897756e-05,
"loss": 4.0398,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.770222090027077e-05,
"loss": 4.0331,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.769383495276025e-05,
"loss": 4.032,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.768544900524973e-05,
"loss": 4.0339,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.767706305773921e-05,
"loss": 4.0256,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.76686771102287e-05,
"loss": 4.0462,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.766029116271818e-05,
"loss": 4.0342,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.765190521520766e-05,
"loss": 4.0482,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.764351926769714e-05,
"loss": 4.027,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.763513332018662e-05,
"loss": 4.0446,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.762676375147983e-05,
"loss": 4.0435,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.761837780396931e-05,
"loss": 4.0461,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.7610008235262516e-05,
"loss": 4.0409,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.7601622287751996e-05,
"loss": 4.0371,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.7593236340241476e-05,
"loss": 4.0433,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.7584850392730956e-05,
"loss": 4.0464,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.7576464445220436e-05,
"loss": 4.0319,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.7568078497709916e-05,
"loss": 4.0386,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.7559692550199396e-05,
"loss": 4.0394,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.755130660268888e-05,
"loss": 4.0364,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.754292065517836e-05,
"loss": 4.0321,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.7534534707667836e-05,
"loss": 4.0283,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.752616513896105e-05,
"loss": 4.043,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.751779557025426e-05,
"loss": 4.039,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.750940962274374e-05,
"loss": 4.0432,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 4.065581321716309,
"eval_runtime": 294.1015,
"eval_samples_per_second": 1297.481,
"eval_steps_per_second": 40.547,
"step": 763200
},
{
"epoch": 0.0,
"learning_rate": 3.750102367523322e-05,
"loss": 4.0213,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.74926377277227e-05,
"loss": 4.0303,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.748425178021218e-05,
"loss": 4.031,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.7475865832701654e-05,
"loss": 4.0347,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.7467479885191134e-05,
"loss": 4.0446,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.745909393768062e-05,
"loss": 4.0394,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.74507079901701e-05,
"loss": 4.0265,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.744232204265958e-05,
"loss": 4.0281,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.743393609514906e-05,
"loss": 4.0277,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.742555014763854e-05,
"loss": 4.0391,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.741716420012802e-05,
"loss": 4.0346,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.74087782526175e-05,
"loss": 4.0357,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.740040868391071e-05,
"loss": 4.0404,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.739202273640019e-05,
"loss": 4.02,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.738363678888967e-05,
"loss": 4.028,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.737525084137915e-05,
"loss": 4.0222,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.736686489386863e-05,
"loss": 4.0339,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.735847894635811e-05,
"loss": 4.0296,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.735009299884759e-05,
"loss": 4.0353,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.734170705133707e-05,
"loss": 4.031,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.7333337482630285e-05,
"loss": 4.0428,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.7324951535119765e-05,
"loss": 4.0297,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.7316565587609245e-05,
"loss": 4.0389,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.7308179640098725e-05,
"loss": 4.0315,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.72997936925882e-05,
"loss": 4.0338,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.729140774507768e-05,
"loss": 4.0367,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.7283038176370894e-05,
"loss": 4.0227,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.7274652228860374e-05,
"loss": 4.0311,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.726626628134985e-05,
"loss": 4.0237,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.725789671264306e-05,
"loss": 4.0262,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.724951076513254e-05,
"loss": 4.0311,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.724112481762202e-05,
"loss": 4.0307,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.72327388701115e-05,
"loss": 4.0348,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.722435292260098e-05,
"loss": 4.0448,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.721596697509046e-05,
"loss": 4.0277,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.720758102757994e-05,
"loss": 4.0288,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.719919508006942e-05,
"loss": 4.0436,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.71908091325589e-05,
"loss": 4.0243,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.718243956385211e-05,
"loss": 4.0273,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.717405361634159e-05,
"loss": 4.0288,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.716566766883107e-05,
"loss": 4.027,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.715728172132055e-05,
"loss": 4.0315,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.714889577381003e-05,
"loss": 4.0249,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.714050982629951e-05,
"loss": 4.0359,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.713214025759272e-05,
"loss": 4.0285,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.712375431008221e-05,
"loss": 4.0337,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.711536836257169e-05,
"loss": 4.0289,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.710698241506117e-05,
"loss": 4.0352,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.7098612846354376e-05,
"loss": 3.9987,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.7090226898843856e-05,
"loss": 4.0385,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.7081840951333336e-05,
"loss": 4.0189,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.7073455003822816e-05,
"loss": 4.0346,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.7065069056312296e-05,
"loss": 4.0183,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.7056699487605505e-05,
"loss": 4.0137,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.7048313540094985e-05,
"loss": 4.0135,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.7039927592584465e-05,
"loss": 4.0217,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.7031541645073945e-05,
"loss": 4.0293,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.7023155697563425e-05,
"loss": 4.0131,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.7014769750052905e-05,
"loss": 4.0339,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.7006383802542385e-05,
"loss": 4.0262,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.6997997855031865e-05,
"loss": 4.0093,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.698962828632508e-05,
"loss": 4.0295,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.698124233881456e-05,
"loss": 4.0105,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.6972856391304034e-05,
"loss": 4.0101,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.696448682259725e-05,
"loss": 4.0239,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.695610087508673e-05,
"loss": 4.0283,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.69477149275762e-05,
"loss": 4.0119,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.693934535886942e-05,
"loss": 4.025,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.69309594113589e-05,
"loss": 4.0099,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.692257346384838e-05,
"loss": 4.0231,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.691418751633786e-05,
"loss": 4.0318,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.690580156882734e-05,
"loss": 4.0271,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.689741562131682e-05,
"loss": 4.0324,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.68890296738063e-05,
"loss": 4.0304,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.688064372629578e-05,
"loss": 4.0469,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.687227415758899e-05,
"loss": 4.0278,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.686388821007847e-05,
"loss": 4.0302,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.685550226256795e-05,
"loss": 4.0177,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.684711631505743e-05,
"loss": 4.0225,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.6838746746350636e-05,
"loss": 4.02,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.6830360798840116e-05,
"loss": 4.025,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.682199123013333e-05,
"loss": 4.0307,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.681360528262281e-05,
"loss": 4.0355,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.680521933511229e-05,
"loss": 4.0153,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.679683338760177e-05,
"loss": 4.0166,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.678844744009125e-05,
"loss": 4.0169,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.678006149258073e-05,
"loss": 4.027,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.677167554507021e-05,
"loss": 4.0254,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.676328959755969e-05,
"loss": 4.0195,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.675490365004917e-05,
"loss": 4.0199,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.674651770253865e-05,
"loss": 4.0239,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.673813175502813e-05,
"loss": 4.0199,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.672976218632134e-05,
"loss": 4.0136,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.672137623881082e-05,
"loss": 4.0313,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.67129902913003e-05,
"loss": 4.028,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.670460434378978e-05,
"loss": 4.0272,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.669621839627926e-05,
"loss": 4.0143,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.668783244876875e-05,
"loss": 4.0173,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.667944650125822e-05,
"loss": 4.0192,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.66710605537477e-05,
"loss": 4.0248,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.6662690985040916e-05,
"loss": 4.033,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.6654305037530396e-05,
"loss": 4.0148,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.664591909001987e-05,
"loss": 4.0316,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.663753314250935e-05,
"loss": 4.0207,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.6629163573802565e-05,
"loss": 4.0187,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.662077762629204e-05,
"loss": 4.0092,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.661239167878152e-05,
"loss": 4.0089,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.6604005731271e-05,
"loss": 4.0172,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.6595636162564214e-05,
"loss": 4.0196,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.658726659385743e-05,
"loss": 4.0098,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.657888064634691e-05,
"loss": 4.0092,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.657049469883639e-05,
"loss": 4.0058,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.656210875132587e-05,
"loss": 4.0228,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.655372280381534e-05,
"loss": 4.0155,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.654533685630482e-05,
"loss": 4.0216,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.65369509087943e-05,
"loss": 4.0232,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.652858134008751e-05,
"loss": 4.0214,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.652019539257699e-05,
"loss": 4.0189,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.651180944506647e-05,
"loss": 4.024,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.650342349755595e-05,
"loss": 4.0183,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.649503755004544e-05,
"loss": 4.0289,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.648665160253492e-05,
"loss": 4.0206,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.64782656550244e-05,
"loss": 4.0195,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.646987970751388e-05,
"loss": 4.0179,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.646149376000336e-05,
"loss": 4.0183,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.645312419129657e-05,
"loss": 4.0144,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.644473824378605e-05,
"loss": 4.0109,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.643636867507926e-05,
"loss": 4.0099,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.642798272756874e-05,
"loss": 4.0066,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.6419596780058217e-05,
"loss": 4.0242,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.6411210832547697e-05,
"loss": 4.0156,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.6402824885037176e-05,
"loss": 4.0244,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.6394438937526656e-05,
"loss": 4.0089,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.6386052990016136e-05,
"loss": 4.0241,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.637766704250562e-05,
"loss": 4.0219,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.636929747379883e-05,
"loss": 4.0208,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.636091152628831e-05,
"loss": 4.0211,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.635252557877779e-05,
"loss": 4.0154,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.634413963126727e-05,
"loss": 4.026,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.633577006256048e-05,
"loss": 4.0272,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.632738411504996e-05,
"loss": 4.0098,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.631899816753944e-05,
"loss": 4.0169,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.631061222002892e-05,
"loss": 4.0219,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.63022262725184e-05,
"loss": 4.0163,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.629385670381161e-05,
"loss": 4.0127,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.628547075630109e-05,
"loss": 4.011,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.627708480879058e-05,
"loss": 4.019,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.626869886128006e-05,
"loss": 4.0197,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.6260329292573266e-05,
"loss": 4.0226,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 4.0523362159729,
"eval_runtime": 294.5546,
"eval_samples_per_second": 1295.485,
"eval_steps_per_second": 40.485,
"step": 839520
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.465848817019255e+17,
"trial_name": null,
"trial_params": null
}