abhinavp's picture
Training in progress, epoch 1, checkpoint
7bd42ab verified
{
"best_metric": 4.260177135467529,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-c-command/lstm/2/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": 10.8197,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5521,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.055,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9903,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9127,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.7893,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.6787,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.5934,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.4969,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4322,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3551,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.2878,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2252,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.1543,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1155,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0618,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0314,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.9886,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.9447,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.909,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983231380739706e-05,
"loss": 5.8728,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 5.8364,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 5.8061,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.7687,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7504,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7207,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.6917,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6699,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6434,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6267,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.608,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.589,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.567,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5462,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5416,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5324,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5062,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.9689785457325684e-05,
"loss": 5.4663,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.9681399509815164e-05,
"loss": 5.4706,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.9673013562304644e-05,
"loss": 5.4407,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.9664627614794124e-05,
"loss": 5.4422,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4263,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 5.4138,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.39,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.3948,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3814,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.9614377444945934e-05,
"loss": 5.3798,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.9605991497435414e-05,
"loss": 5.3627,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 5.3421,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 5.3365,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 5.3372,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 5.3141,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 5.3066,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 5.2921,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 5.2884,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 5.2723,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 5.2861,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 5.2478,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 5.254,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 5.2463,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 5.2257,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 5.2266,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 5.2152,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 5.1986,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 5.1905,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2068,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.1829,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1734,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1549,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1639,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.169,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940477789359412e-05,
"loss": 5.1524,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.93963919460836e-05,
"loss": 5.1471,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.1519,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.141,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371250482355776e-05,
"loss": 5.1282,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1085,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 5.1141,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346109018627945e-05,
"loss": 5.0984,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.0965,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329337123606905e-05,
"loss": 5.0886,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932095117609638e-05,
"loss": 5.0864,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.0949,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 5.0836,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295809712368554e-05,
"loss": 5.0569,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.058,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.0608,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.0565,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 5.0469,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925389635361968e-05,
"loss": 5.0413,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924551040610916e-05,
"loss": 5.0343,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923712445859864e-05,
"loss": 5.0202,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922873851108812e-05,
"loss": 5.0263,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92203525635776e-05,
"loss": 5.0195,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921198299487081e-05,
"loss": 5.01,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920359704736029e-05,
"loss": 5.0176,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 4.9972,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918682515233926e-05,
"loss": 4.995,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.9826,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.979,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.9872,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.9711,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.9666,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.963,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.9619,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.9448,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9344,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9413,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.9454,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.9375,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.9334,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9196,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9248,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.9116,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.9156,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.9107,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.90275576648543e-05,
"loss": 4.9085,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.9015,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901080214863699e-05,
"loss": 4.8954,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.9019,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899403025361595e-05,
"loss": 4.8983,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.898564430610543e-05,
"loss": 4.8866,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897725835859491e-05,
"loss": 4.8888,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.8787,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.8807,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.8623,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.8581,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.8618,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8636,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8535,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.8648,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890181758860769e-05,
"loss": 4.8558,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889343164109717e-05,
"loss": 4.8395,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888504569358665e-05,
"loss": 4.8449,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.8492,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.8403,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885990422985882e-05,
"loss": 4.8382,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515182823483e-05,
"loss": 4.8276,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.831,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883474638732726e-05,
"loss": 4.8344,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882636043981674e-05,
"loss": 4.8169,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881797449230622e-05,
"loss": 4.8109,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880960492359943e-05,
"loss": 4.8156,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.8081,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.8056,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.8091,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.8,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876769156485057e-05,
"loss": 4.7984,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.7961,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.7904,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.757678985595703,
"eval_runtime": 298.6287,
"eval_samples_per_second": 1277.811,
"eval_steps_per_second": 39.933,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.7842,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873416415361222e-05,
"loss": 4.7871,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.87257782061017e-05,
"loss": 4.7943,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871739225859118e-05,
"loss": 4.7826,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709006311080657e-05,
"loss": 4.7804,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700620363570137e-05,
"loss": 4.7766,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.7783,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.756,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.7801,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.7654,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7728,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.7702,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.7496,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.7515,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.7467,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.7426,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.7496,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.7371,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.735,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.7534,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.7375,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856651071861674e-05,
"loss": 4.7314,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558124771106226e-05,
"loss": 4.7243,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.85497388235957e-05,
"loss": 4.7398,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854135287608518e-05,
"loss": 4.7181,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.7138,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.7151,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851621141235735e-05,
"loss": 4.717,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850782546484683e-05,
"loss": 4.7084,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.7087,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.7105,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.7103,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.6968,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.8465912106097964e-05,
"loss": 4.7088,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.8457526158587444e-05,
"loss": 4.7102,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.8449140211076924e-05,
"loss": 4.703,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.8440754263566404e-05,
"loss": 4.6744,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.6842,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.6823,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.6873,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.6796,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.6811,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.6701,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.6835,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.6773,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836531349357918e-05,
"loss": 4.6793,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835692754606866e-05,
"loss": 4.6784,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.6585,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.666,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833178608234084e-05,
"loss": 4.6713,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832340013483032e-05,
"loss": 4.665,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.662,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.6512,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.6566,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.6417,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.6714,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.6421,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.6518,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.6519,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.629,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.6453,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.6375,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222801522311535e-05,
"loss": 4.623,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214415574801015e-05,
"loss": 4.6229,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206029627290495e-05,
"loss": 4.6421,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819766005858371e-05,
"loss": 4.6293,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.6201,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.6159,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817251859485588e-05,
"loss": 4.6285,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.6356,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815574669983483e-05,
"loss": 4.6277,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814736075232432e-05,
"loss": 4.6203,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.81389748048138e-05,
"loss": 4.6345,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813058885730328e-05,
"loss": 4.6283,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.625,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811383334108597e-05,
"loss": 4.6052,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105463772379184e-05,
"loss": 4.6161,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809707782486866e-05,
"loss": 4.6097,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808869187735814e-05,
"loss": 4.6055,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808030592984762e-05,
"loss": 4.608,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.6064,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.6206,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.6147,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804677851860927e-05,
"loss": 4.5908,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803840894990248e-05,
"loss": 4.5979,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803002300239196e-05,
"loss": 4.5992,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802163705488144e-05,
"loss": 4.601,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801325110737092e-05,
"loss": 4.5996,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.80048651598604e-05,
"loss": 4.5971,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799647921234988e-05,
"loss": 4.5922,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798809326483936e-05,
"loss": 4.5822,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797972369613257e-05,
"loss": 4.5948,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.586,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796296817991526e-05,
"loss": 4.5866,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795458223240474e-05,
"loss": 4.593,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794619628489423e-05,
"loss": 4.5834,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.5772,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792942438987319e-05,
"loss": 4.5748,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921054821166396e-05,
"loss": 4.5793,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912668873655876e-05,
"loss": 4.5829,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904282926145356e-05,
"loss": 4.5699,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895896978634836e-05,
"loss": 4.5684,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887511031124316e-05,
"loss": 4.5695,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879125083613796e-05,
"loss": 4.5703,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870739136103276e-05,
"loss": 4.5602,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862353188592756e-05,
"loss": 4.5457,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853967241082236e-05,
"loss": 4.5638,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845581293571715e-05,
"loss": 4.564,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837195346061195e-05,
"loss": 4.5603,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.5599,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782043982984389e-05,
"loss": 4.5536,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781205388233337e-05,
"loss": 4.559,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803667934822844e-05,
"loss": 4.5477,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795281987312324e-05,
"loss": 4.5508,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786896039801804e-05,
"loss": 4.5556,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778510092291284e-05,
"loss": 4.5554,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777015690238823e-05,
"loss": 4.5478,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776177095487771e-05,
"loss": 4.5466,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775338500736719e-05,
"loss": 4.5535,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774499905985666e-05,
"loss": 4.5532,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773661311234615e-05,
"loss": 4.5392,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772822716483563e-05,
"loss": 4.5515,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771984121732511e-05,
"loss": 4.5374,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771145526981459e-05,
"loss": 4.5503,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770306932230407e-05,
"loss": 4.5291,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769468337479355e-05,
"loss": 4.5284,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768631380608676e-05,
"loss": 4.5325,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767792785857624e-05,
"loss": 4.5393,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766954191106572e-05,
"loss": 4.5282,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.76611559635552e-05,
"loss": 4.5464,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765277001604468e-05,
"loss": 4.5351,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764440044733789e-05,
"loss": 4.5268,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763601449982737e-05,
"loss": 4.5299,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762762855231685e-05,
"loss": 4.5393,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761924260480633e-05,
"loss": 4.5313,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610856657295813e-05,
"loss": 4.5303,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760248708858902e-05,
"loss": 4.5232,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941011410785e-05,
"loss": 4.5256,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758571519356798e-05,
"loss": 4.5312,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757732924605746e-05,
"loss": 4.5183,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756894329854694e-05,
"loss": 4.5164,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756055735103642e-05,
"loss": 4.5221,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755218778232963e-05,
"loss": 4.512,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754380183481911e-05,
"loss": 4.5129,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753541588730859e-05,
"loss": 4.5205,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.75270463186018e-05,
"loss": 4.5119,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751866037109128e-05,
"loss": 4.5122,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751027442358077e-05,
"loss": 4.511,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750188847607025e-05,
"loss": 4.5063,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.477365493774414,
"eval_runtime": 296.8326,
"eval_samples_per_second": 1285.543,
"eval_steps_per_second": 40.174,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749350252855973e-05,
"loss": 4.4996,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748511658104921e-05,
"loss": 4.5067,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747673063353868e-05,
"loss": 4.5177,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746834468602816e-05,
"loss": 4.5074,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745995873851764e-05,
"loss": 4.5066,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745157279100712e-05,
"loss": 4.5014,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.74431868434966e-05,
"loss": 4.5079,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743480089598608e-05,
"loss": 4.4869,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742641494847556e-05,
"loss": 4.5106,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741802900096504e-05,
"loss": 4.5058,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740964305345452e-05,
"loss": 4.503,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401257105944e-05,
"loss": 4.5119,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392887537237216e-05,
"loss": 4.4868,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384501589726696e-05,
"loss": 4.492,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376115642216176e-05,
"loss": 4.4978,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367729694705656e-05,
"loss": 4.48,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359343747195135e-05,
"loss": 4.4917,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350974178488345e-05,
"loss": 4.4807,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342588230977825e-05,
"loss": 4.4837,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.7334202283467305e-05,
"loss": 4.5048,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325816335956784e-05,
"loss": 4.4858,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317430388446264e-05,
"loss": 4.4865,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730904444093574e-05,
"loss": 4.4758,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730065849342522e-05,
"loss": 4.4946,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292272545914704e-05,
"loss": 4.471,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7283886598404184e-05,
"loss": 4.4721,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727551702969739e-05,
"loss": 4.4708,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726713108218687e-05,
"loss": 4.4808,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725874513467635e-05,
"loss": 4.4682,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725035918716583e-05,
"loss": 4.4693,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724197323965531e-05,
"loss": 4.4776,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723358729214479e-05,
"loss": 4.4793,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722520134463427e-05,
"loss": 4.4609,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721683177592748e-05,
"loss": 4.4756,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720844582841696e-05,
"loss": 4.4771,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720005988090644e-05,
"loss": 4.4712,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719167393339592e-05,
"loss": 4.448,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71832879858854e-05,
"loss": 4.4629,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717490203837488e-05,
"loss": 4.4505,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716651609086437e-05,
"loss": 4.4663,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715813014335385e-05,
"loss": 4.457,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714976057464706e-05,
"loss": 4.4613,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714137462713654e-05,
"loss": 4.4508,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713298867962602e-05,
"loss": 4.4598,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712461911091923e-05,
"loss": 4.4602,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711623316340871e-05,
"loss": 4.4607,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710784721589819e-05,
"loss": 4.4627,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099461268387667e-05,
"loss": 4.4401,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091075320877147e-05,
"loss": 4.4485,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082689373366627e-05,
"loss": 4.4643,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074319804659836e-05,
"loss": 4.4473,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706593385714932e-05,
"loss": 4.4493,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.70575479096388e-05,
"loss": 4.4439,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704916196212828e-05,
"loss": 4.4471,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040776014617755e-05,
"loss": 4.4357,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032390067107235e-05,
"loss": 4.4544,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024004119596715e-05,
"loss": 4.4403,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015618172086195e-05,
"loss": 4.4428,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007232224575675e-05,
"loss": 4.4522,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998862655868884e-05,
"loss": 4.4245,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990476708358364e-05,
"loss": 4.4423,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982107139651573e-05,
"loss": 4.4347,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697372119214106e-05,
"loss": 4.4272,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696533524463054e-05,
"loss": 4.4236,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695694929712002e-05,
"loss": 4.4386,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.69485633496095e-05,
"loss": 4.4338,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694017740209898e-05,
"loss": 4.4218,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693179145458846e-05,
"loss": 4.4187,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692340550707794e-05,
"loss": 4.4365,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691503593837115e-05,
"loss": 4.4454,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690664999086063e-05,
"loss": 4.4308,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689828042215384e-05,
"loss": 4.4303,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688989447464332e-05,
"loss": 4.4407,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.68815085271328e-05,
"loss": 4.4371,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687312257962228e-05,
"loss": 4.4386,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864753010915494e-05,
"loss": 4.4137,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856367063404974e-05,
"loss": 4.4292,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6847981115894454e-05,
"loss": 4.4302,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839595168383934e-05,
"loss": 4.4157,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831209220873414e-05,
"loss": 4.4256,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822823273362894e-05,
"loss": 4.4218,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814437325852373e-05,
"loss": 4.4366,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806051378341853e-05,
"loss": 4.4279,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679768180963506e-05,
"loss": 4.4095,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678931224092827e-05,
"loss": 4.4176,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678092629341775e-05,
"loss": 4.4173,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677254034590723e-05,
"loss": 4.422,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676415439839671e-05,
"loss": 4.4205,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675578482968993e-05,
"loss": 4.4167,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674739888217941e-05,
"loss": 4.4139,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673901293466889e-05,
"loss": 4.4058,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673062698715837e-05,
"loss": 4.419,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672224103964785e-05,
"loss": 4.4074,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671385509213733e-05,
"loss": 4.4143,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670546914462681e-05,
"loss": 4.4186,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669708319711629e-05,
"loss": 4.4114,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668869724960576e-05,
"loss": 4.4055,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668031130209524e-05,
"loss": 4.4047,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667192535458472e-05,
"loss": 4.4062,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.66635394070742e-05,
"loss": 4.4117,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655169838367416e-05,
"loss": 4.4014,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.6646783890856896e-05,
"loss": 4.3995,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.6638397943346376e-05,
"loss": 4.3975,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.6630011995835856e-05,
"loss": 4.4038,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621626048325336e-05,
"loss": 4.3944,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613256479618545e-05,
"loss": 4.3822,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660488691091176e-05,
"loss": 4.3935,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596500963401234e-05,
"loss": 4.4003,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588115015890714e-05,
"loss": 4.3931,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579729068380194e-05,
"loss": 4.4,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571343120869674e-05,
"loss": 4.3866,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6562957173359154e-05,
"loss": 4.3963,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554571225848634e-05,
"loss": 4.3873,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654620165714185e-05,
"loss": 4.3862,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653781570963133e-05,
"loss": 4.3986,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652942976212081e-05,
"loss": 4.3957,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521076572217755e-05,
"loss": 4.3887,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512690624707234e-05,
"loss": 4.389,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650430467719671e-05,
"loss": 4.3896,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649591872968619e-05,
"loss": 4.3942,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648753278217567e-05,
"loss": 4.3831,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647914683466515e-05,
"loss": 4.3949,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647076088715463e-05,
"loss": 4.3838,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646237493964411e-05,
"loss": 4.3949,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645398899213359e-05,
"loss": 4.3699,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644560304462307e-05,
"loss": 4.3811,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643723347591628e-05,
"loss": 4.376,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642886390720949e-05,
"loss": 4.3848,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642047795969897e-05,
"loss": 4.3764,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641209201218845e-05,
"loss": 4.3957,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640370606467793e-05,
"loss": 4.3834,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639532011716741e-05,
"loss": 4.3777,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638693416965689e-05,
"loss": 4.3732,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637854822214637e-05,
"loss": 4.3878,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637016227463585e-05,
"loss": 4.3827,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636177632712533e-05,
"loss": 4.3843,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635339037961481e-05,
"loss": 4.375,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634500443210429e-05,
"loss": 4.3774,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633661848459377e-05,
"loss": 4.3846,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632826529469072e-05,
"loss": 4.3724,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.63198793471802e-05,
"loss": 4.3692,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631149339966968e-05,
"loss": 4.3794,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630310745215916e-05,
"loss": 4.3692,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629472150464864e-05,
"loss": 4.3659,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628633555713812e-05,
"loss": 4.3723,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277949609627597e-05,
"loss": 4.3761,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626956366211707e-05,
"loss": 4.3674,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.6261194093410286e-05,
"loss": 4.3658,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.6252808145899766e-05,
"loss": 4.3601,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.34266996383667,
"eval_runtime": 350.4175,
"eval_samples_per_second": 1088.961,
"eval_steps_per_second": 34.031,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.6244422198389246e-05,
"loss": 4.3672,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.6236036250878726e-05,
"loss": 4.3628,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.6227650303368205e-05,
"loss": 4.3776,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219264355857685e-05,
"loss": 4.3644,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.6210878408347165e-05,
"loss": 4.3686,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202508839640374e-05,
"loss": 4.3615,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194122892129854e-05,
"loss": 4.368,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185736944619334e-05,
"loss": 4.3516,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177350997108814e-05,
"loss": 4.3734,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6168965049598294e-05,
"loss": 4.3672,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.6160579102087774e-05,
"loss": 4.3684,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615220953338098e-05,
"loss": 4.376,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.61438399646742e-05,
"loss": 4.3485,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613545401716368e-05,
"loss": 4.3567,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612706806965316e-05,
"loss": 4.3638,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611868212214264e-05,
"loss": 4.3513,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611029617463212e-05,
"loss": 4.3541,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.61019102271216e-05,
"loss": 4.3472,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609354065841481e-05,
"loss": 4.3524,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608515471090429e-05,
"loss": 4.3743,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607676876339377e-05,
"loss": 4.3526,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606838281588325e-05,
"loss": 4.354,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.605999686837273e-05,
"loss": 4.3467,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605161092086221e-05,
"loss": 4.3599,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604322497335169e-05,
"loss": 4.3442,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603483902584117e-05,
"loss": 4.3416,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602645307833065e-05,
"loss": 4.3448,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601806713082013e-05,
"loss": 4.3531,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009697562113344e-05,
"loss": 4.3366,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001311614602824e-05,
"loss": 4.3444,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.5992925667092303e-05,
"loss": 4.3457,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.5984539719581783e-05,
"loss": 4.3524,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.5976153772071257e-05,
"loss": 4.3413,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5967767824560737e-05,
"loss": 4.3471,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595939825585395e-05,
"loss": 4.351,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595101230834343e-05,
"loss": 4.3468,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.5942626360832906e-05,
"loss": 4.3245,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.5934240413322386e-05,
"loss": 4.3411,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.5925854465811865e-05,
"loss": 4.3249,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.5917468518301345e-05,
"loss": 4.3439,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590908257079083e-05,
"loss": 4.3308,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590071300208404e-05,
"loss": 4.3404,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589232705457352e-05,
"loss": 4.3329,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5883941107063e-05,
"loss": 4.334,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587557153835621e-05,
"loss": 4.3403,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586718559084569e-05,
"loss": 4.3365,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585879964333517e-05,
"loss": 4.3407,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585041369582465e-05,
"loss": 4.326,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584202774831413e-05,
"loss": 4.3268,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583365817960734e-05,
"loss": 4.3436,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582527223209682e-05,
"loss": 4.3312,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.58168862845863e-05,
"loss": 4.3262,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808500337075786e-05,
"loss": 4.3269,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800114389565266e-05,
"loss": 4.33,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791728442054746e-05,
"loss": 4.3173,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783342494544226e-05,
"loss": 4.3369,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5774956547033706e-05,
"loss": 4.3233,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766570599523186e-05,
"loss": 4.3282,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758184652012666e-05,
"loss": 4.3342,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5749798704502146e-05,
"loss": 4.3136,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574141275699162e-05,
"loss": 4.3197,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.57330268094811e-05,
"loss": 4.3223,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724657240774315e-05,
"loss": 4.3122,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716271293263794e-05,
"loss": 4.3112,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570788534575327e-05,
"loss": 4.3211,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.5699499398242754e-05,
"loss": 4.3222,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.5691113450732234e-05,
"loss": 4.3082,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5682743882025443e-05,
"loss": 4.3062,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567437431331866e-05,
"loss": 4.3206,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566598836580814e-05,
"loss": 4.3296,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565760241829762e-05,
"loss": 4.317,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564921647078709e-05,
"loss": 4.3232,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564083052327657e-05,
"loss": 4.3261,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563244457576605e-05,
"loss": 4.3286,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562407500705927e-05,
"loss": 4.3293,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561568905954874e-05,
"loss": 4.3023,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560730311203822e-05,
"loss": 4.3178,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559891716452771e-05,
"loss": 4.3236,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559054759582092e-05,
"loss": 4.3036,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.55821616483104e-05,
"loss": 4.3203,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557377570079988e-05,
"loss": 4.312,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556538975328936e-05,
"loss": 4.3264,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555700380577884e-05,
"loss": 4.3211,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554861785826832e-05,
"loss": 4.2996,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.55402319107578e-05,
"loss": 4.3118,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553184596324728e-05,
"loss": 4.3068,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523476394540486e-05,
"loss": 4.3126,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515090447029966e-05,
"loss": 4.3157,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.5506720878323175e-05,
"loss": 4.3083,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.5498334930812655e-05,
"loss": 4.3081,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.548994898330214e-05,
"loss": 4.3018,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548156303579162e-05,
"loss": 4.3093,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.54731770882811e-05,
"loss": 4.301,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546479114077058e-05,
"loss": 4.3112,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545640519326006e-05,
"loss": 4.3154,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544801924574954e-05,
"loss": 4.3064,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543963329823902e-05,
"loss": 4.2982,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.54312473507285e-05,
"loss": 4.3042,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542286140321798e-05,
"loss": 4.3013,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.5414475455707455e-05,
"loss": 4.3081,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406089508196934e-05,
"loss": 4.3029,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539771993949015e-05,
"loss": 4.298,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538935037078336e-05,
"loss": 4.2912,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538096442327284e-05,
"loss": 4.306,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372578475762326e-05,
"loss": 4.2866,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364192528251806e-05,
"loss": 4.2854,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535580658074128e-05,
"loss": 4.2913,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534742063323076e-05,
"loss": 4.2969,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533903468572024e-05,
"loss": 4.2935,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330665117013455e-05,
"loss": 4.3062,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532227916950293e-05,
"loss": 4.2879,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531389322199241e-05,
"loss": 4.2887,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530550727448189e-05,
"loss": 4.2922,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529712132697137e-05,
"loss": 4.2808,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528875175826458e-05,
"loss": 4.3047,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.5280365810754064e-05,
"loss": 4.2974,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.5271979863243544e-05,
"loss": 4.2925,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.5263593915733024e-05,
"loss": 4.2943,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.5255207968222504e-05,
"loss": 4.2854,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524683839951571e-05,
"loss": 4.2975,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523845245200519e-05,
"loss": 4.2868,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523006650449467e-05,
"loss": 4.3015,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522169693578788e-05,
"loss": 4.2846,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521331098827736e-05,
"loss": 4.2941,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520492504076684e-05,
"loss": 4.2801,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519653909325632e-05,
"loss": 4.2849,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.51881531457458e-05,
"loss": 4.2778,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517978357703902e-05,
"loss": 4.2916,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.51713976295285e-05,
"loss": 4.2798,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516301168201798e-05,
"loss": 4.2986,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515462573450746e-05,
"loss": 4.2914,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146256165800667e-05,
"loss": 4.2862,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5137870218290147e-05,
"loss": 4.2751,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.5129484270779626e-05,
"loss": 4.2913,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.5121098323269106e-05,
"loss": 4.2872,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.5112712375758586e-05,
"loss": 4.294,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104326428248066e-05,
"loss": 4.2812,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5095956859541275e-05,
"loss": 4.2815,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087570912030755e-05,
"loss": 4.2884,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079184964520235e-05,
"loss": 4.2845,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507081539581345e-05,
"loss": 4.274,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506242944830293e-05,
"loss": 4.2863,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505404350079241e-05,
"loss": 4.2774,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504565755328189e-05,
"loss": 4.2749,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503727160577137e-05,
"loss": 4.2802,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502888565826085e-05,
"loss": 4.286,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502049971075033e-05,
"loss": 4.2729,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501211376323981e-05,
"loss": 4.2711,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500372781572929e-05,
"loss": 4.2774,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.260177135467529,
"eval_runtime": 348.7269,
"eval_samples_per_second": 1094.24,
"eval_steps_per_second": 34.196,
"step": 305280
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.2665391454962547e+17,
"trial_name": null,
"trial_params": null
}