rel-cl-lstm-4 / checkpoint-381600 /trainer_state.json
abhinavp's picture
Training in progress, epoch 0, checkpoint
edb37fb verified
raw
history blame
No virus
93.1 kB
{
"best_metric": 4.211251258850098,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/lstm/4/checkpoints/checkpoint-381600",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 381600,
"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": 10.82,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.559,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0554,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9937,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9447,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8936,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7488,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6478,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5524,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.469,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.4073,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3328,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2605,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 6.197,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 6.1498,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 6.0945,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 6.0577,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 6.022,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.9791,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9353,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.9076,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.865,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8413,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.8045,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.979875363855125e-05,
"loss": 5.7866,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.979036769104073e-05,
"loss": 5.7486,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.726,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6965,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6795,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.975684027980238e-05,
"loss": 5.6523,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 5.6403,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740117521192533e-05,
"loss": 5.6224,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731731573682013e-05,
"loss": 5.5978,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 5.582,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 5.5683,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 5.5442,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5402,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.5074,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4925,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4648,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4631,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4474,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.4437,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.416,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.4055,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.4031,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.3959,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.3829,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 5.3633,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 5.3487,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 5.3653,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 5.3515,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.3318,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.3092,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 5.3194,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 5.2973,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 5.3025,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 5.2727,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 5.2844,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2682,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2502,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.2366,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2499,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 5.2068,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 5.2212,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2284,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.2113,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.2028,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1777,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1749,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1704,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1821,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.1617,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.1707,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 5.1605,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 5.1583,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 5.1356,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 5.1329,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 5.1245,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 5.121,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 5.119,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 5.1014,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.1045,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 5.1023,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295809712368554e-05,
"loss": 5.0775,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.0852,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.0834,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.085,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 5.066,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925389635361968e-05,
"loss": 5.0622,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924551040610916e-05,
"loss": 5.0487,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923712445859864e-05,
"loss": 5.044,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.045,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 5.0442,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 5.0354,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.0387,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 5.0267,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 5.0117,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 5.0086,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 5.0093,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916168368861143e-05,
"loss": 5.0068,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915329774110091e-05,
"loss": 5.0104,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914491179359039e-05,
"loss": 4.9925,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913652584607987e-05,
"loss": 4.9838,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912813989856935e-05,
"loss": 4.9888,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911975395105883e-05,
"loss": 4.9691,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9747,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9626,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.964,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.952,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.9532,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.943,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9474,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.9426,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.9321,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.9421,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.90275576648543e-05,
"loss": 4.9398,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901917171734378e-05,
"loss": 4.9296,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901078576983326e-05,
"loss": 4.9159,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.9172,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.9134,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.9165,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.9096,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.9001,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.9031,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.8894,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.8945,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893534499984604e-05,
"loss": 4.8803,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8865,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8748,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.8843,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890181758860769e-05,
"loss": 4.8833,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.8807,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.8567,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.8631,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.8608,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885990422985882e-05,
"loss": 4.864,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515182823483e-05,
"loss": 4.852,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.8563,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883476276613099e-05,
"loss": 4.8458,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882637681862047e-05,
"loss": 4.8609,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881799087110995e-05,
"loss": 4.8292,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880960492359943e-05,
"loss": 4.8477,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880121897608891e-05,
"loss": 4.8323,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.8283,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.8276,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.813,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876769156485057e-05,
"loss": 4.8177,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875930561734005e-05,
"loss": 4.8258,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.8127,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.776597499847412,
"eval_runtime": 334.2731,
"eval_samples_per_second": 1141.555,
"eval_steps_per_second": 35.674,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.8096,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873416415361222e-05,
"loss": 4.805,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.87257782061017e-05,
"loss": 4.8152,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871739225859118e-05,
"loss": 4.8041,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709006311080657e-05,
"loss": 4.8118,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700620363570137e-05,
"loss": 4.7888,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692234416059616e-05,
"loss": 4.7958,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.7784,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675478899842306e-05,
"loss": 4.7827,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667092952331785e-05,
"loss": 4.7873,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865870700482127e-05,
"loss": 4.7836,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.7868,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.7658,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.7791,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.7625,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.7657,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.7681,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.7592,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.7605,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858326623483405e-05,
"loss": 4.7733,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857488028732352e-05,
"loss": 4.7492,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856649433981301e-05,
"loss": 4.7564,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855810839230249e-05,
"loss": 4.7493,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.85497388235957e-05,
"loss": 4.759,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.7482,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.7478,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.73,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851621141235735e-05,
"loss": 4.7388,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850782546484683e-05,
"loss": 4.7267,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849943951733631e-05,
"loss": 4.7375,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.7324,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.7306,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.7344,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.8465912106097964e-05,
"loss": 4.7242,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.7293,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.7223,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844077064237013e-05,
"loss": 4.7112,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.7042,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842399874734909e-05,
"loss": 4.6943,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841561279983857e-05,
"loss": 4.7023,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840722685232805e-05,
"loss": 4.7005,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839884090481753e-05,
"loss": 4.7087,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.6918,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.6934,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.698,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.6902,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.6962,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.6815,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.6733,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833178608234084e-05,
"loss": 4.6997,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832340013483032e-05,
"loss": 4.6935,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.6806,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.6753,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.6821,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.6666,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281486776081446e-05,
"loss": 4.6843,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273100828570926e-05,
"loss": 4.6552,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264714881060406e-05,
"loss": 4.6788,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.6733,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.6567,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.6517,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.6662,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222801522311535e-05,
"loss": 4.6301,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214415574801015e-05,
"loss": 4.6503,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206029627290495e-05,
"loss": 4.6631,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197643679779975e-05,
"loss": 4.6546,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189274111073184e-05,
"loss": 4.6445,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180888163562664e-05,
"loss": 4.6318,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172502216052144e-05,
"loss": 4.636,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.6383,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815576307863857e-05,
"loss": 4.6462,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.6352,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138991183617535e-05,
"loss": 4.6425,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813060523610701e-05,
"loss": 4.6462,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.6435,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811383334108597e-05,
"loss": 4.6267,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810544739357545e-05,
"loss": 4.6316,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809706144606493e-05,
"loss": 4.63,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808867549855441e-05,
"loss": 4.623,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808030592984762e-05,
"loss": 4.6265,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.6174,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806353403482658e-05,
"loss": 4.6268,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805514808731606e-05,
"loss": 4.6247,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804676213980554e-05,
"loss": 4.6032,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803837619229502e-05,
"loss": 4.6183,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.6152,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802162067607771e-05,
"loss": 4.6234,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801323472856719e-05,
"loss": 4.6128,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800484878105667e-05,
"loss": 4.608,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799646283354615e-05,
"loss": 4.6014,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798807688603563e-05,
"loss": 4.5973,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797970731732884e-05,
"loss": 4.6022,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797132136981832e-05,
"loss": 4.6073,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.79629354223078e-05,
"loss": 4.6041,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795454947479728e-05,
"loss": 4.608,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794617990609049e-05,
"loss": 4.5992,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793779395857997e-05,
"loss": 4.5927,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792940801106946e-05,
"loss": 4.59,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792102206355894e-05,
"loss": 4.5944,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791263611604842e-05,
"loss": 4.5985,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.79042501685379e-05,
"loss": 4.5987,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789586422102737e-05,
"loss": 4.5886,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788747827351685e-05,
"loss": 4.5791,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879108704810067e-05,
"loss": 4.5914,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870722757299546e-05,
"loss": 4.5754,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862353188592756e-05,
"loss": 4.581,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853967241082236e-05,
"loss": 4.5751,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845581293571715e-05,
"loss": 4.5765,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837195346061195e-05,
"loss": 4.5667,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828809398550675e-05,
"loss": 4.5766,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820423451040155e-05,
"loss": 4.5643,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812037503529635e-05,
"loss": 4.5688,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803651556019115e-05,
"loss": 4.5736,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795265608508595e-05,
"loss": 4.5606,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786896039801804e-05,
"loss": 4.5814,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778510092291284e-05,
"loss": 4.5775,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777014052358449e-05,
"loss": 4.5696,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776175457607397e-05,
"loss": 4.5604,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775336862856345e-05,
"loss": 4.5581,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774498268105293e-05,
"loss": 4.5644,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773659673354241e-05,
"loss": 4.5577,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772821078603189e-05,
"loss": 4.5691,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771982483852137e-05,
"loss": 4.5521,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771143889101086e-05,
"loss": 4.5572,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770306932230407e-05,
"loss": 4.5541,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769468337479355e-05,
"loss": 4.5601,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768629742728303e-05,
"loss": 4.5416,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767791147977251e-05,
"loss": 4.5538,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766954191106572e-05,
"loss": 4.5505,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.76611559635552e-05,
"loss": 4.5506,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765277001604468e-05,
"loss": 4.5552,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764438406853416e-05,
"loss": 4.5583,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763599812102364e-05,
"loss": 4.5369,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762761217351312e-05,
"loss": 4.543,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.76192262260026e-05,
"loss": 4.5481,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610856657295813e-05,
"loss": 4.5451,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602470709785293e-05,
"loss": 4.5414,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594084762274773e-05,
"loss": 4.5443,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758569881476425e-05,
"loss": 4.5371,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757732924605746e-05,
"loss": 4.5547,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756894329854694e-05,
"loss": 4.5258,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756055735103642e-05,
"loss": 4.545,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.75521714035259e-05,
"loss": 4.5325,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543785456015375e-05,
"loss": 4.5294,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753541588730859e-05,
"loss": 4.5291,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752702993979807e-05,
"loss": 4.523,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751866037109128e-05,
"loss": 4.5243,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751027442358077e-05,
"loss": 4.5291,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750188847607025e-05,
"loss": 4.522,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.489930629730225,
"eval_runtime": 296.2133,
"eval_samples_per_second": 1288.231,
"eval_steps_per_second": 40.258,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749350252855973e-05,
"loss": 4.5215,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748511658104921e-05,
"loss": 4.514,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747673063353868e-05,
"loss": 4.5337,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746834468602816e-05,
"loss": 4.5199,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745995873851764e-05,
"loss": 4.5307,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745157279100712e-05,
"loss": 4.5101,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.74431868434966e-05,
"loss": 4.5181,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743480089598608e-05,
"loss": 4.503,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742641494847556e-05,
"loss": 4.5138,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741802900096504e-05,
"loss": 4.5129,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740964305345452e-05,
"loss": 4.5098,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401257105944e-05,
"loss": 4.5219,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392887537237216e-05,
"loss": 4.4984,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384501589726696e-05,
"loss": 4.5136,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376115642216176e-05,
"loss": 4.4982,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367729694705656e-05,
"loss": 4.4992,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359343747195135e-05,
"loss": 4.4996,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350957799684615e-05,
"loss": 4.5065,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342571852174095e-05,
"loss": 4.4979,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733418590466357e-05,
"loss": 4.5167,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732579995715305e-05,
"loss": 4.4986,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731741400964253e-05,
"loss": 4.5005,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730902806213201e-05,
"loss": 4.499,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730064211462149e-05,
"loss": 4.5098,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292288924718433e-05,
"loss": 4.4952,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728390297720791e-05,
"loss": 4.499,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727551702969739e-05,
"loss": 4.4853,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726713108218687e-05,
"loss": 4.491,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725874513467635e-05,
"loss": 4.4797,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725035918716583e-05,
"loss": 4.4946,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724197323965531e-05,
"loss": 4.4916,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723358729214479e-05,
"loss": 4.4887,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722523410224174e-05,
"loss": 4.4968,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721684815473121e-05,
"loss": 4.4855,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720847858602443e-05,
"loss": 4.4859,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720009263851391e-05,
"loss": 4.4882,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719170669100339e-05,
"loss": 4.4807,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718332074349287e-05,
"loss": 4.4705,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717493479598235e-05,
"loss": 4.463,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716654884847183e-05,
"loss": 4.4725,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715816290096131e-05,
"loss": 4.4739,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714977695345079e-05,
"loss": 4.4795,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714139100594027e-05,
"loss": 4.47,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713300505842975e-05,
"loss": 4.4642,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712461911091923e-05,
"loss": 4.478,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711623316340871e-05,
"loss": 4.4691,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107863594701916e-05,
"loss": 4.47,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099477647191396e-05,
"loss": 4.4637,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091091699680876e-05,
"loss": 4.4517,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082705752170356e-05,
"loss": 4.4822,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707433618346357e-05,
"loss": 4.474,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706595023595305e-05,
"loss": 4.4638,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705756428844253e-05,
"loss": 4.4611,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704917834093201e-05,
"loss": 4.47,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704080877222522e-05,
"loss": 4.4506,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.70324228247147e-05,
"loss": 4.4718,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702403687720418e-05,
"loss": 4.4457,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701565092969366e-05,
"loss": 4.4634,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700726498218314e-05,
"loss": 4.4678,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699887903467262e-05,
"loss": 4.4494,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.69904930871621e-05,
"loss": 4.4421,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698212351845531e-05,
"loss": 4.4598,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697373757094479e-05,
"loss": 4.4308,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965351623434276e-05,
"loss": 4.4475,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956965675923756e-05,
"loss": 4.4555,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694857972841323e-05,
"loss": 4.4547,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694019378090271e-05,
"loss": 4.4462,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693180783339219e-05,
"loss": 4.4318,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692342188588167e-05,
"loss": 4.4346,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691505231717488e-05,
"loss": 4.4378,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690666636966436e-05,
"loss": 4.4504,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689828042215384e-05,
"loss": 4.4381,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688989447464332e-05,
"loss": 4.4476,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.68815085271328e-05,
"loss": 4.4533,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873138958426014e-05,
"loss": 4.4485,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864753010915494e-05,
"loss": 4.4331,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.68563834422087e-05,
"loss": 4.4384,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684799749469818e-05,
"loss": 4.4454,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683961154718766e-05,
"loss": 4.4325,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683122559967714e-05,
"loss": 4.4364,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682283965216662e-05,
"loss": 4.4319,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.68144537046561e-05,
"loss": 4.4336,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680606775714558e-05,
"loss": 4.4405,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679768180963506e-05,
"loss": 4.4168,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678931224092827e-05,
"loss": 4.4361,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678092629341775e-05,
"loss": 4.4272,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677254034590723e-05,
"loss": 4.44,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676415439839671e-05,
"loss": 4.4292,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675578482968993e-05,
"loss": 4.4273,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674739888217941e-05,
"loss": 4.4213,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673901293466889e-05,
"loss": 4.4176,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673062698715837e-05,
"loss": 4.4176,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672224103964785e-05,
"loss": 4.4251,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713871470941056e-05,
"loss": 4.433,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705485523430536e-05,
"loss": 4.4272,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697115954723745e-05,
"loss": 4.4187,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688746386016954e-05,
"loss": 4.4147,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680360438506434e-05,
"loss": 4.4157,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667197449099592e-05,
"loss": 4.4176,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.66635885434854e-05,
"loss": 4.4262,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665520259597488e-05,
"loss": 4.4243,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664681664846436e-05,
"loss": 4.4153,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663843070095384e-05,
"loss": 4.407,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663004475344332e-05,
"loss": 4.4235,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662167518473653e-05,
"loss": 4.4028,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661328923722601e-05,
"loss": 4.4133,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660490328971549e-05,
"loss": 4.4047,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659651734220497e-05,
"loss": 4.4109,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658813139469445e-05,
"loss": 4.4009,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657974544718393e-05,
"loss": 4.4125,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657135949967341e-05,
"loss": 4.4016,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656297355216288e-05,
"loss": 4.3972,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655458760465237e-05,
"loss": 4.4141,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654620165714185e-05,
"loss": 4.3937,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653781570963133e-05,
"loss": 4.419,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652942976212081e-05,
"loss": 4.4143,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521076572217755e-05,
"loss": 4.4084,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512690624707234e-05,
"loss": 4.3995,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650430467719671e-05,
"loss": 4.4006,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649591872968619e-05,
"loss": 4.4,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648753278217567e-05,
"loss": 4.3996,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647914683466515e-05,
"loss": 4.4089,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647076088715463e-05,
"loss": 4.3915,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462391318447837e-05,
"loss": 4.4,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645400537093732e-05,
"loss": 4.4,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.64456194234268e-05,
"loss": 4.3993,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643723347591628e-05,
"loss": 4.3895,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642884752840576e-05,
"loss": 4.3958,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642046158089524e-05,
"loss": 4.3956,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641207563338472e-05,
"loss": 4.3985,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.64036896858742e-05,
"loss": 4.3988,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639532011716741e-05,
"loss": 4.4063,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638693416965689e-05,
"loss": 4.3841,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637854822214637e-05,
"loss": 4.3943,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637016227463585e-05,
"loss": 4.3981,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636179270592906e-05,
"loss": 4.3923,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635340675841854e-05,
"loss": 4.3885,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634502081090802e-05,
"loss": 4.3993,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633663486339751e-05,
"loss": 4.3885,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632826529469072e-05,
"loss": 4.4045,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.63198793471802e-05,
"loss": 4.3784,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631149339966968e-05,
"loss": 4.392,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630310745215916e-05,
"loss": 4.3873,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294737883452366e-05,
"loss": 4.3845,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286351935941846e-05,
"loss": 4.3813,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277965988431326e-05,
"loss": 4.3787,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.6269580040920806e-05,
"loss": 4.3754,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.6261210472214015e-05,
"loss": 4.3829,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.6252824524703495e-05,
"loss": 4.3812,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.353302478790283,
"eval_runtime": 306.5317,
"eval_samples_per_second": 1244.866,
"eval_steps_per_second": 38.903,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.6244438577192975e-05,
"loss": 4.3829,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623605262968246e-05,
"loss": 4.369,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622766668217194e-05,
"loss": 4.3908,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621929711346515e-05,
"loss": 4.3763,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621091116595463e-05,
"loss": 4.3939,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620252521844411e-05,
"loss": 4.3709,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619413927093359e-05,
"loss": 4.3779,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.61857697022268e-05,
"loss": 4.3614,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617738375471628e-05,
"loss": 4.3768,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616901418600949e-05,
"loss": 4.3758,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616062823849897e-05,
"loss": 4.3716,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615224229098845e-05,
"loss": 4.3786,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6143872722281664e-05,
"loss": 4.3637,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135486774771144e-05,
"loss": 4.377,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.6127100827260624e-05,
"loss": 4.3641,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.6118714879750104e-05,
"loss": 4.3602,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.6110328932239584e-05,
"loss": 4.365,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.6101942984729064e-05,
"loss": 4.3684,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609357341602227e-05,
"loss": 4.3641,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608518746851175e-05,
"loss": 4.3815,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607680152100123e-05,
"loss": 4.3676,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606841557349071e-05,
"loss": 4.3717,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606002962598019e-05,
"loss": 4.3646,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051643678469666e-05,
"loss": 4.3749,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604325773095915e-05,
"loss": 4.3639,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603487178344863e-05,
"loss": 4.3668,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602648583593811e-05,
"loss": 4.3576,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601811626723132e-05,
"loss": 4.3538,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.60097303197208e-05,
"loss": 4.3524,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600134437221028e-05,
"loss": 4.3628,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599295842469976e-05,
"loss": 4.3652,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598458885599297e-05,
"loss": 4.3602,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597620290848245e-05,
"loss": 4.3701,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596781696097193e-05,
"loss": 4.3586,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595944739226514e-05,
"loss": 4.3565,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595106144475462e-05,
"loss": 4.3587,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.59426754972441e-05,
"loss": 4.3618,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.5934289549733587e-05,
"loss": 4.3411,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.5925903602223066e-05,
"loss": 4.3366,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.5917517654712546e-05,
"loss": 4.3452,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.5909131707202026e-05,
"loss": 4.3547,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900745759691506e-05,
"loss": 4.3538,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.5892359812180986e-05,
"loss": 4.3473,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5883990243474195e-05,
"loss": 4.3375,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.5875604295963675e-05,
"loss": 4.3538,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867218348453155e-05,
"loss": 4.3474,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858832400942635e-05,
"loss": 4.3485,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.5850446453432115e-05,
"loss": 4.3397,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.5842060505921595e-05,
"loss": 4.3252,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.5833674558411075e-05,
"loss": 4.3669,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.5825288610900555e-05,
"loss": 4.3511,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581691904219377e-05,
"loss": 4.3449,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580853309468325e-05,
"loss": 4.3433,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580016352597646e-05,
"loss": 4.3442,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579177757846594e-05,
"loss": 4.3343,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578339163095542e-05,
"loss": 4.3481,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.57750056834449e-05,
"loss": 4.3295,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576663611473811e-05,
"loss": 4.3424,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575825016722759e-05,
"loss": 4.3547,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.574986421971707e-05,
"loss": 4.3318,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574147827220655e-05,
"loss": 4.3211,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573309232469602e-05,
"loss": 4.3481,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572470637718551e-05,
"loss": 4.3149,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571632042967499e-05,
"loss": 4.327,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5707950860968205e-05,
"loss": 4.3422,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569956491345768e-05,
"loss": 4.3391,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569117896594716e-05,
"loss": 4.3299,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568279301843664e-05,
"loss": 4.3234,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567440707092612e-05,
"loss": 4.3141,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566603750221933e-05,
"loss": 4.3244,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565765155470881e-05,
"loss": 4.3368,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564928198600202e-05,
"loss": 4.3235,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.5640896038491496e-05,
"loss": 4.3375,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.5632510090980976e-05,
"loss": 4.3359,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562412414347046e-05,
"loss": 4.3408,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561573819595994e-05,
"loss": 4.3221,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560735224844942e-05,
"loss": 4.3238,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.55989663009389e-05,
"loss": 4.3348,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559058035342838e-05,
"loss": 4.3187,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558221078472159e-05,
"loss": 4.3317,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557382483721107e-05,
"loss": 4.3199,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556543888970055e-05,
"loss": 4.323,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555705294219003e-05,
"loss": 4.3298,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554868337348324e-05,
"loss": 4.3113,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554029742597272e-05,
"loss": 4.3232,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.55319114784622e-05,
"loss": 4.3234,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552352553095168e-05,
"loss": 4.3298,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551513958344116e-05,
"loss": 4.318,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550675363593064e-05,
"loss": 4.3204,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.5498384067223856e-05,
"loss": 4.3126,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.5490014498517065e-05,
"loss": 4.3092,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.5481628551006545e-05,
"loss": 4.3118,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.5473242603496025e-05,
"loss": 4.3168,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.5464856655985505e-05,
"loss": 4.3261,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.5456470708474985e-05,
"loss": 4.3246,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448084760964465e-05,
"loss": 4.3138,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.5439698813453945e-05,
"loss": 4.3077,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.5431312865943425e-05,
"loss": 4.3097,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.5422926918432905e-05,
"loss": 4.3149,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.5414540970922385e-05,
"loss": 4.3181,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406155023411865e-05,
"loss": 4.319,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5397769075901345e-05,
"loss": 4.3113,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538939950719456e-05,
"loss": 4.3035,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538101355968404e-05,
"loss": 4.3242,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372627612173514e-05,
"loss": 4.295,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364241664662994e-05,
"loss": 4.3145,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535587209595621e-05,
"loss": 4.3008,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534748614844569e-05,
"loss": 4.3081,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533910020093516e-05,
"loss": 4.2998,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533071425342464e-05,
"loss": 4.3084,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532234468471786e-05,
"loss": 4.3018,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531395873720733e-05,
"loss": 4.296,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530557278969682e-05,
"loss": 4.3098,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.52971868421863e-05,
"loss": 4.296,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.5288817273479514e-05,
"loss": 4.3153,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528044770477272e-05,
"loss": 4.3166,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.52720617572622e-05,
"loss": 4.3113,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526367580975168e-05,
"loss": 4.2993,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525528986224116e-05,
"loss": 4.3012,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.5246903914730636e-05,
"loss": 4.2998,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523853434602385e-05,
"loss": 4.3001,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523014839851333e-05,
"loss": 4.3122,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.5221762451002805e-05,
"loss": 4.289,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.5213376503492285e-05,
"loss": 4.3026,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520499055598177e-05,
"loss": 4.2983,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519660460847125e-05,
"loss": 4.3059,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518823503976446e-05,
"loss": 4.2921,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517984909225394e-05,
"loss": 4.3008,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517147952354716e-05,
"loss": 4.2942,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516309357603663e-05,
"loss": 4.3086,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515470762852611e-05,
"loss": 4.2996,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514632168101559e-05,
"loss": 4.3087,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513793573350507e-05,
"loss": 4.2857,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512954978599455e-05,
"loss": 4.3016,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512116383848403e-05,
"loss": 4.3028,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511277789097351e-05,
"loss": 4.2921,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104408322266726e-05,
"loss": 4.2966,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5096022374756206e-05,
"loss": 4.3048,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087636427245685e-05,
"loss": 4.2954,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079250479735165e-05,
"loss": 4.3122,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070880911028375e-05,
"loss": 4.2832,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062494963517855e-05,
"loss": 4.3005,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.5054109016007334e-05,
"loss": 4.2901,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.5045723068496814e-05,
"loss": 4.2928,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.5037337120986294e-05,
"loss": 4.2899,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5028951173475774e-05,
"loss": 4.2843,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020565225965254e-05,
"loss": 4.2831,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012179278454734e-05,
"loss": 4.2877,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500380970974794e-05,
"loss": 4.2903,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.268551349639893,
"eval_runtime": 307.1362,
"eval_samples_per_second": 1242.416,
"eval_steps_per_second": 38.826,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499542376223742e-05,
"loss": 4.2901,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498703781472691e-05,
"loss": 4.2792,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497865186721639e-05,
"loss": 4.2981,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497026591970587e-05,
"loss": 4.2854,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496187997219535e-05,
"loss": 4.2968,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495349402468482e-05,
"loss": 4.2845,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.49451080771743e-05,
"loss": 4.2853,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493672212966378e-05,
"loss": 4.2736,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492833618215326e-05,
"loss": 4.2833,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.491996661344647e-05,
"loss": 4.2866,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491158066593595e-05,
"loss": 4.2855,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490319471842543e-05,
"loss": 4.2868,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489480877091491e-05,
"loss": 4.2749,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488642282340439e-05,
"loss": 4.2887,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487803687589387e-05,
"loss": 4.2748,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486965092838336e-05,
"loss": 4.2712,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486126498087284e-05,
"loss": 4.2758,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485287903336232e-05,
"loss": 4.284,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.48444930858518e-05,
"loss": 4.2755,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483610713834128e-05,
"loss": 4.2904,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482772119083076e-05,
"loss": 4.2807,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481933524332024e-05,
"loss": 4.2871,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481094929580971e-05,
"loss": 4.2745,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480256334829919e-05,
"loss": 4.2875,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479419377959241e-05,
"loss": 4.2773,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478580783208188e-05,
"loss": 4.281,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.4777438263375096e-05,
"loss": 4.2712,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.4769052315864576e-05,
"loss": 4.2714,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.4760666368354056e-05,
"loss": 4.2661,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.4752280420843536e-05,
"loss": 4.275,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.4743894473333016e-05,
"loss": 4.2793,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473552490462623e-05,
"loss": 4.276,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472713895711571e-05,
"loss": 4.2825,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471876938840892e-05,
"loss": 4.2704,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.47103834408984e-05,
"loss": 4.2711,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470199749338788e-05,
"loss": 4.2802,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693611545877354e-05,
"loss": 4.2775,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.4685225598366834e-05,
"loss": 4.2548,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4676839650856314e-05,
"loss": 4.2601,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668453703345794e-05,
"loss": 4.2599,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466006775583528e-05,
"loss": 4.2663,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465168180832476e-05,
"loss": 4.2756,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464329586081424e-05,
"loss": 4.2628,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463490991330372e-05,
"loss": 4.2594,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.46265239657932e-05,
"loss": 4.2697,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461815439708641e-05,
"loss": 4.2643,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460976844957589e-05,
"loss": 4.268,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460138250206537e-05,
"loss": 4.2607,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459301293335858e-05,
"loss": 4.2378,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.458462698584806e-05,
"loss": 4.2865,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457624103833754e-05,
"loss": 4.2687,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456785509082702e-05,
"loss": 4.2688,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.45594691433165e-05,
"loss": 4.261,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455108319580598e-05,
"loss": 4.2625,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542697248295465e-05,
"loss": 4.2552,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534344058392403e-05,
"loss": 4.2647,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4525958110881883e-05,
"loss": 4.2538,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451757216337136e-05,
"loss": 4.2607,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450918621586084e-05,
"loss": 4.274,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450080026835032e-05,
"loss": 4.2526,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.44924143208398e-05,
"loss": 4.2454,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448402837332928e-05,
"loss": 4.2691,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447564242581876e-05,
"loss": 4.2369,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446727285711197e-05,
"loss": 4.2512,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445888690960145e-05,
"loss": 4.2588,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445050096209093e-05,
"loss": 4.2628,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444211501458041e-05,
"loss": 4.2537,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.44337290670699e-05,
"loss": 4.2491,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442534311955937e-05,
"loss": 4.2325,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441697355085259e-05,
"loss": 4.2476,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440858760334207e-05,
"loss": 4.2569,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440020165583154e-05,
"loss": 4.249,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439181570832102e-05,
"loss": 4.2558,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.43834297608105e-05,
"loss": 4.2611,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437504381329998e-05,
"loss": 4.2663,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436665786578946e-05,
"loss": 4.2465,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435827191827894e-05,
"loss": 4.2432,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.434990234957216e-05,
"loss": 4.2589,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434151640206164e-05,
"loss": 4.2399,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333130454551117e-05,
"loss": 4.2594,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4324744507040597e-05,
"loss": 4.2439,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316358559530076e-05,
"loss": 4.2464,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4307972612019556e-05,
"loss": 4.2563,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299586664509036e-05,
"loss": 4.2361,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291217095802245e-05,
"loss": 4.2457,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4282831148291725e-05,
"loss": 4.2457,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274461579584935e-05,
"loss": 4.2544,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266075632074415e-05,
"loss": 4.2384,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257706063367624e-05,
"loss": 4.2477,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249320115857104e-05,
"loss": 4.2386,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424093416834659e-05,
"loss": 4.2381,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423254822083607e-05,
"loss": 4.2328,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422416227332555e-05,
"loss": 4.2456,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421577632581503e-05,
"loss": 4.2532,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420739037830451e-05,
"loss": 4.2474,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419900443079399e-05,
"loss": 4.2469,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419061848328347e-05,
"loss": 4.2346,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418223253577295e-05,
"loss": 4.2361,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417384658826243e-05,
"loss": 4.2414,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.41654606407519e-05,
"loss": 4.2475,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415707469324138e-05,
"loss": 4.244,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.41487051245346e-05,
"loss": 4.2387,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414031917702408e-05,
"loss": 4.235,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413193322951356e-05,
"loss": 4.2516,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412354728200304e-05,
"loss": 4.2248,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115177713296255e-05,
"loss": 4.2415,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106791765785735e-05,
"loss": 4.23,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409840581827521e-05,
"loss": 4.2383,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.4090036249568424e-05,
"loss": 4.2284,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081650302057904e-05,
"loss": 4.2387,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407326435454738e-05,
"loss": 4.2295,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406487840703686e-05,
"loss": 4.2286,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405649245952634e-05,
"loss": 4.2369,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404810651201582e-05,
"loss": 4.2282,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.4039736943309026e-05,
"loss": 4.2444,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403135099579851e-05,
"loss": 4.2478,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402296504828799e-05,
"loss": 4.2376,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401457910077747e-05,
"loss": 4.2358,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400619315326695e-05,
"loss": 4.2268,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399780720575643e-05,
"loss": 4.2312,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398942125824591e-05,
"loss": 4.2304,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398103531073539e-05,
"loss": 4.2459,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397264936322487e-05,
"loss": 4.2168,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396427979451808e-05,
"loss": 4.2347,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395589384700756e-05,
"loss": 4.23,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394752427830077e-05,
"loss": 4.2365,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393913833079025e-05,
"loss": 4.2268,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393075238327973e-05,
"loss": 4.2309,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392236643576921e-05,
"loss": 4.2254,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.39139804882587e-05,
"loss": 4.2393,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390559454074818e-05,
"loss": 4.2353,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389720859323766e-05,
"loss": 4.2377,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388882264572714e-05,
"loss": 4.2217,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.3880453077020346e-05,
"loss": 4.2346,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872083508313555e-05,
"loss": 4.2358,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3863697560803035e-05,
"loss": 4.2261,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855311613292515e-05,
"loss": 4.2303,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3846925665781995e-05,
"loss": 4.2374,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.3838539718271475e-05,
"loss": 4.2265,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830153770760955e-05,
"loss": 4.2476,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3821767823250435e-05,
"loss": 4.2191,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813398254543644e-05,
"loss": 4.232,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380501230703313e-05,
"loss": 4.2216,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379662635952261e-05,
"loss": 4.2255,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378824041201209e-05,
"loss": 4.2255,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3779854464501564e-05,
"loss": 4.218,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771468516991044e-05,
"loss": 4.2216,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763082569480524e-05,
"loss": 4.2159,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3754696621970004e-05,
"loss": 4.2294,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.211251258850098,
"eval_runtime": 295.0333,
"eval_samples_per_second": 1293.383,
"eval_steps_per_second": 40.419,
"step": 381600
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.546882247170784e+17,
"trial_name": null,
"trial_params": null
}