abhinavp's picture
Training in progress, epoch 1, checkpoint
dbc89b4 verified
raw
history blame
74.6 kB
{
"best_metric": 4.254123687744141,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-domain/lstm/4/checkpoints/checkpoint-305280",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 305280,
"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
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.2603086607342746e+17,
"trial_name": null,
"trial_params": null
}