abhinavp's picture
Training in progress, epoch 0, checkpoint
aeb5ced verified
raw
history blame contribute delete
No virus
204 kB
{
"best_metric": 4.067676067352295,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/superlative-quantifier/lstm/2/checkpoints/checkpoint-839520",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 839520,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.8196,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.563,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0597,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9935,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9463,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8805,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.6971,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.5925,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5066,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4414,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3894,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3248,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2579,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 6.1934,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 6.1367,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 6.0883,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 6.0428,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 6.0064,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.9585,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9316,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8963,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8503,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8204,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.7864,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7648,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7323,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7024,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6752,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6675,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6271,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6145,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.6054,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5755,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5571,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5518,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 5.5304,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5192,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4793,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4732,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4448,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 5.4417,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 5.4283,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 5.4231,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.3913,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.3909,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3769,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.377,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960595873982795e-05,
"loss": 5.3692,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 5.3412,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.326,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3344,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3277,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.3023,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2935,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 5.289,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 5.2721,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 5.2796,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 5.2439,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 5.249,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2383,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2366,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.2118,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2189,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.1924,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.1975,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.1963,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.1898,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1693,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1526,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1448,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1597,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1499,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.134,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.1439,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1404,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 5.126,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 5.1139,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 5.1033,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346109018627945e-05,
"loss": 5.1011,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337723071117425e-05,
"loss": 5.0854,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 5.0873,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 5.0756,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.0885,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 5.0735,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295809712368554e-05,
"loss": 5.0516,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 5.0544,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 5.0528,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 5.0511,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 5.0449,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 5.0279,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.92455267849129e-05,
"loss": 5.027,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.0211,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.0099,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 4.9991,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.9975,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.0054,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 4.994,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.982,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.9726,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.9762,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.9786,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.9713,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.9635,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.9532,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.9619,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9396,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9427,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9353,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.9284,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908624291862421e-05,
"loss": 4.9236,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907785697111369e-05,
"loss": 4.9283,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9156,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9141,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.9097,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.9063,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.9088,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.9032,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.8992,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.8952,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.8888,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.889,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.8765,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.8721,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.8707,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.8696,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.8635,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.8619,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.8591,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8463,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8567,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.8547,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.8353,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.8244,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.8306,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.8383,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.8448,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.8271,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.8268,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.8248,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.8259,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.8114,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.805,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.8124,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.8018,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.7997,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.8037,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.7876,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.7984,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.7939,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.7739,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.759090900421143,
"eval_runtime": 298.7399,
"eval_samples_per_second": 1277.335,
"eval_steps_per_second": 39.918,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.7881,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.777,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.7879,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.775,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.776,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.7596,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.7601,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.7426,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.7688,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.7615,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.7556,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.7612,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.7429,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.7418,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.7365,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.7354,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.7368,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.7278,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.7375,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.7396,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.727,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856651071861674e-05,
"loss": 4.7186,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.7189,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.7227,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.7149,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.7017,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.701,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.7174,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.6892,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.6953,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.704,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.7002,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.7,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.6983,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.696,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.6968,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.6721,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.6823,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.6675,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.6733,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840725960993552e-05,
"loss": 4.6735,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398873662425e-05,
"loss": 4.6737,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839048771491447e-05,
"loss": 4.6683,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838210176740395e-05,
"loss": 4.6665,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.6668,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365346251186646e-05,
"loss": 4.6707,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8356960303676126e-05,
"loss": 4.6726,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.8348574356165606e-05,
"loss": 4.6558,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.646,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331818839948295e-05,
"loss": 4.6613,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323432892437775e-05,
"loss": 4.6662,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315046944927255e-05,
"loss": 4.652,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306660997416735e-05,
"loss": 4.6473,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.6463,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.6392,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.6493,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273133586178384e-05,
"loss": 4.6281,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826474763866787e-05,
"loss": 4.6407,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.6357,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824797574364683e-05,
"loss": 4.6374,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823960617494004e-05,
"loss": 4.619,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823122022742952e-05,
"loss": 4.6404,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222834279919e-05,
"loss": 4.6128,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.6295,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820607876370169e-05,
"loss": 4.63,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819769281619117e-05,
"loss": 4.628,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818930686868065e-05,
"loss": 4.613,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818092092117013e-05,
"loss": 4.6089,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817253497365961e-05,
"loss": 4.6071,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816414902614909e-05,
"loss": 4.617,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815576307863857e-05,
"loss": 4.6193,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147393509931785e-05,
"loss": 4.612,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.6198,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.6233,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122235667400224e-05,
"loss": 4.6189,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113866098693434e-05,
"loss": 4.6019,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.6076,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097094203672393e-05,
"loss": 4.6086,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.8088708256161873e-05,
"loss": 4.5864,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.6072,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.5897,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.6114,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.6003,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046794897413e-05,
"loss": 4.578,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803842532870622e-05,
"loss": 4.5957,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.80300393811957e-05,
"loss": 4.5847,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802165343368518e-05,
"loss": 4.5978,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.5907,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800488153866413e-05,
"loss": 4.5865,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799649559115361e-05,
"loss": 4.5837,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798810964364309e-05,
"loss": 4.5799,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797972369613257e-05,
"loss": 4.5733,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.568,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796296817991526e-05,
"loss": 4.5704,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795458223240474e-05,
"loss": 4.5805,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794619628489423e-05,
"loss": 4.5724,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937826716187436e-05,
"loss": 4.565,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929440768676916e-05,
"loss": 4.5604,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921054821166396e-05,
"loss": 4.569,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912668873655876e-05,
"loss": 4.5742,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904282926145356e-05,
"loss": 4.5665,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895896978634836e-05,
"loss": 4.5619,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887511031124316e-05,
"loss": 4.5601,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879125083613796e-05,
"loss": 4.5661,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870755514907005e-05,
"loss": 4.5468,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862369567396485e-05,
"loss": 4.5565,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853983619885965e-05,
"loss": 4.555,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845597672375445e-05,
"loss": 4.5481,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.5496,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.5515,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782043982984389e-05,
"loss": 4.5455,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781205388233337e-05,
"loss": 4.5435,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780370069243031e-05,
"loss": 4.545,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779531474491979e-05,
"loss": 4.5415,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778692879740927e-05,
"loss": 4.5529,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777854284989875e-05,
"loss": 4.5478,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777017328119196e-05,
"loss": 4.5448,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776178733368144e-05,
"loss": 4.5425,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775340138617092e-05,
"loss": 4.544,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450154386604e-05,
"loss": 4.5397,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773662949114988e-05,
"loss": 4.5332,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772824354363936e-05,
"loss": 4.5305,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719857596128845e-05,
"loss": 4.5348,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771147164861832e-05,
"loss": 4.5336,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703102079911534e-05,
"loss": 4.5314,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694716132401014e-05,
"loss": 4.5325,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686330184890494e-05,
"loss": 4.5252,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76779606161837e-05,
"loss": 4.5276,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766957466867318e-05,
"loss": 4.5277,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766118872116266e-05,
"loss": 4.537,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.7652802773652136e-05,
"loss": 4.5168,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.7644416826141616e-05,
"loss": 4.5072,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763604725743483e-05,
"loss": 4.5142,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762766130992431e-05,
"loss": 4.5263,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761927536241379e-05,
"loss": 4.5303,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761088941490327e-05,
"loss": 4.5198,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760251984619649e-05,
"loss": 4.519,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759413389868596e-05,
"loss": 4.5219,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758574795117544e-05,
"loss": 4.5201,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757736200366492e-05,
"loss": 4.5137,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.75689760561544e-05,
"loss": 4.5107,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756059010864388e-05,
"loss": 4.5147,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755220416113336e-05,
"loss": 4.5111,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754381821362284e-05,
"loss": 4.5023,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753544864491605e-05,
"loss": 4.5162,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527062697405536e-05,
"loss": 4.4989,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518676749895016e-05,
"loss": 4.5099,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510290802384496e-05,
"loss": 4.5068,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501921233677705e-05,
"loss": 4.4948,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.481330394744873,
"eval_runtime": 298.0471,
"eval_samples_per_second": 1280.304,
"eval_steps_per_second": 40.01,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493535286167185e-05,
"loss": 4.506,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485149338656665e-05,
"loss": 4.4964,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476763391146145e-05,
"loss": 4.5061,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468377443635625e-05,
"loss": 4.4983,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7459991496125105e-05,
"loss": 4.5036,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451605548614585e-05,
"loss": 4.489,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443219601104065e-05,
"loss": 4.4876,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434833653593545e-05,
"loss": 4.4743,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426447706083025e-05,
"loss": 4.5051,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418061758572505e-05,
"loss": 4.4956,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409675811061985e-05,
"loss": 4.4876,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401289863551465e-05,
"loss": 4.5027,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739292029484468e-05,
"loss": 4.4791,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384534347334154e-05,
"loss": 4.4868,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376148399823634e-05,
"loss": 4.4795,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367762452313114e-05,
"loss": 4.4765,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359376504802594e-05,
"loss": 4.4854,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350990557292074e-05,
"loss": 4.4737,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342604609781554e-05,
"loss": 4.4851,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.7334218662271034e-05,
"loss": 4.4885,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325832714760514e-05,
"loss": 4.4783,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317446767249994e-05,
"loss": 4.4745,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7309060819739474e-05,
"loss": 4.4744,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730069125103269e-05,
"loss": 4.4782,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729230530352217e-05,
"loss": 4.4669,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728391935601165e-05,
"loss": 4.4674,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727553340850113e-05,
"loss": 4.4579,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726714746099061e-05,
"loss": 4.4788,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725877789228382e-05,
"loss": 4.4497,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725040832357703e-05,
"loss": 4.4626,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724202237606651e-05,
"loss": 4.4675,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723363642855599e-05,
"loss": 4.469,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722525048104547e-05,
"loss": 4.4654,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721686453353495e-05,
"loss": 4.4668,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720847858602443e-05,
"loss": 4.4646,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720010901731764e-05,
"loss": 4.4693,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719172306980712e-05,
"loss": 4.4502,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71833371222966e-05,
"loss": 4.4557,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717495117478608e-05,
"loss": 4.4417,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716656522727556e-05,
"loss": 4.4503,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715819565856877e-05,
"loss": 4.4473,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714980971105825e-05,
"loss": 4.4565,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714142376354773e-05,
"loss": 4.4466,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713303781603721e-05,
"loss": 4.448,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124651868526685e-05,
"loss": 4.4509,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.71162822998199e-05,
"loss": 4.4519,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710789635230938e-05,
"loss": 4.4549,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709951040479886e-05,
"loss": 4.4401,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709112445728834e-05,
"loss": 4.4299,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708275488858156e-05,
"loss": 4.4523,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074368941071037e-05,
"loss": 4.4506,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7065982993560517e-05,
"loss": 4.4423,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705759704604999e-05,
"loss": 4.4409,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704921109853947e-05,
"loss": 4.4328,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704082515102895e-05,
"loss": 4.4359,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703245558232216e-05,
"loss": 4.4424,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702406963481164e-05,
"loss": 4.4238,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701568368730112e-05,
"loss": 4.4364,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.70072977397906e-05,
"loss": 4.4327,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699891179228008e-05,
"loss": 4.4314,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699052584476956e-05,
"loss": 4.4183,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982139897259045e-05,
"loss": 4.4412,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973753949748525e-05,
"loss": 4.4174,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965384381041734e-05,
"loss": 4.43,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956998433531214e-05,
"loss": 4.4268,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.6948612486020694e-05,
"loss": 4.4332,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.6940226538510174e-05,
"loss": 4.4163,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693185696980338e-05,
"loss": 4.4182,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692347102229286e-05,
"loss": 4.406,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691508507478234e-05,
"loss": 4.4256,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690669912727182e-05,
"loss": 4.4273,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689832955856503e-05,
"loss": 4.4231,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688994361105451e-05,
"loss": 4.4254,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688157404234773e-05,
"loss": 4.4321,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687318809483721e-05,
"loss": 4.4329,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686480214732669e-05,
"loss": 4.4107,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685641619981617e-05,
"loss": 4.4198,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684803025230565e-05,
"loss": 4.4264,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683964430479513e-05,
"loss": 4.4014,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683125835728461e-05,
"loss": 4.4196,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682288878857782e-05,
"loss": 4.4041,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.68145028410673e-05,
"loss": 4.4284,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680611689355678e-05,
"loss": 4.4183,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679773094604626e-05,
"loss": 4.3975,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678934499853574e-05,
"loss": 4.4103,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678095905102522e-05,
"loss": 4.4088,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772573103514697e-05,
"loss": 4.4177,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764187156004177e-05,
"loss": 4.4119,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675581758729739e-05,
"loss": 4.409,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674743163978687e-05,
"loss": 4.4055,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739045692276346e-05,
"loss": 4.4022,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730659744765826e-05,
"loss": 4.4002,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672229017605904e-05,
"loss": 4.3886,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671390422854852e-05,
"loss": 4.4001,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705518281037995e-05,
"loss": 4.4085,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697132333527474e-05,
"loss": 4.4021,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668876276482069e-05,
"loss": 4.3933,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668037681731017e-05,
"loss": 4.391,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667199086979965e-05,
"loss": 4.3959,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666360492228913e-05,
"loss": 4.4069,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665521897477861e-05,
"loss": 4.3948,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664683302726809e-05,
"loss": 4.3959,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663844707975757e-05,
"loss": 4.3897,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663006113224705e-05,
"loss": 4.4003,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662169156354026e-05,
"loss": 4.3792,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661330561602974e-05,
"loss": 4.3943,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660493604732295e-05,
"loss": 4.3856,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659655009981243e-05,
"loss": 4.3884,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658816415230191e-05,
"loss": 4.3849,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657977820479139e-05,
"loss": 4.3866,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657139225728087e-05,
"loss": 4.3859,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6563006309770355e-05,
"loss": 4.381,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554620362259835e-05,
"loss": 4.3866,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546250793553044e-05,
"loss": 4.382,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6537864846042524e-05,
"loss": 4.3903,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652949527733573e-05,
"loss": 4.391,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652110932982521e-05,
"loss": 4.3874,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651272338231469e-05,
"loss": 4.3871,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650433743480417e-05,
"loss": 4.3833,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649595148729365e-05,
"loss": 4.379,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648756553978313e-05,
"loss": 4.3792,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647917959227261e-05,
"loss": 4.3795,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647079364476209e-05,
"loss": 4.3751,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646242407605531e-05,
"loss": 4.3849,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645403812854479e-05,
"loss": 4.3759,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644565218103427e-05,
"loss": 4.3812,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643726623352375e-05,
"loss": 4.373,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428913043620687e-05,
"loss": 4.3744,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420527096110166e-05,
"loss": 4.3722,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412157527403376e-05,
"loss": 4.3879,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403771579892856e-05,
"loss": 4.366,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395385632382335e-05,
"loss": 4.3631,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6386999684871815e-05,
"loss": 4.3591,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378613737361295e-05,
"loss": 4.3752,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370227789850775e-05,
"loss": 4.3809,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636184184234026e-05,
"loss": 4.3771,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635345589482974e-05,
"loss": 4.3701,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634506994731922e-05,
"loss": 4.3778,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.63366839998087e-05,
"loss": 4.3695,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632829805229818e-05,
"loss": 4.3732,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631992848359139e-05,
"loss": 4.3628,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631154253608087e-05,
"loss": 4.3722,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630315658857035e-05,
"loss": 4.3668,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629477064105983e-05,
"loss": 4.3572,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286384693549304e-05,
"loss": 4.3724,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277998746038784e-05,
"loss": 4.3628,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.6269612798528264e-05,
"loss": 4.3635,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.6261226851017744e-05,
"loss": 4.3637,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625285728231096e-05,
"loss": 4.3521,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.347398281097412,
"eval_runtime": 291.2821,
"eval_samples_per_second": 1310.039,
"eval_steps_per_second": 40.94,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.6244487713604176e-05,
"loss": 4.3667,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.6236101766093656e-05,
"loss": 4.357,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622771581858313e-05,
"loss": 4.365,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621932987107261e-05,
"loss": 4.3576,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621094392356209e-05,
"loss": 4.3697,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620255797605157e-05,
"loss": 4.3511,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619417202854105e-05,
"loss": 4.3473,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618578608103053e-05,
"loss": 4.34,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617741651232374e-05,
"loss": 4.3652,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616903056481322e-05,
"loss": 4.3632,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.61606446173027e-05,
"loss": 4.3478,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.6152258669792184e-05,
"loss": 4.3661,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6143889101085393e-05,
"loss": 4.3467,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613550315357487e-05,
"loss": 4.351,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612711720606435e-05,
"loss": 4.3498,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611873125855383e-05,
"loss": 4.3424,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611034531104331e-05,
"loss": 4.3494,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610195936353279e-05,
"loss": 4.3436,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609357341602227e-05,
"loss": 4.3526,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608518746851175e-05,
"loss": 4.3549,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607681789980496e-05,
"loss": 4.353,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606843195229444e-05,
"loss": 4.3449,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606004600478392e-05,
"loss": 4.339,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.60516600572734e-05,
"loss": 4.3534,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604329048856662e-05,
"loss": 4.3351,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.60349045410561e-05,
"loss": 4.3404,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602651859354558e-05,
"loss": 4.3305,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601813264603506e-05,
"loss": 4.35,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.600976307732827e-05,
"loss": 4.3247,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600137712981775e-05,
"loss": 4.3353,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599299118230723e-05,
"loss": 4.3432,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598460523479671e-05,
"loss": 4.3388,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597621928728619e-05,
"loss": 4.3394,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5967849718579396e-05,
"loss": 4.3418,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.5959463771068876e-05,
"loss": 4.3407,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.5951077823558356e-05,
"loss": 4.3433,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594270825485157e-05,
"loss": 4.3311,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593432230734105e-05,
"loss": 4.324,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592593635983053e-05,
"loss": 4.3203,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591755041232001e-05,
"loss": 4.3274,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590916446480949e-05,
"loss": 4.3239,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900778517298965e-05,
"loss": 4.3364,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.5892392569788445e-05,
"loss": 4.3246,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5884006622277925e-05,
"loss": 4.3271,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587563705357114e-05,
"loss": 4.3322,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586726748486435e-05,
"loss": 4.3258,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585888153735383e-05,
"loss": 4.3372,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585049558984331e-05,
"loss": 4.3212,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584210964233279e-05,
"loss": 4.3057,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.5833740073626005e-05,
"loss": 4.3377,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.5825354126115485e-05,
"loss": 4.3303,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.5816968178604965e-05,
"loss": 4.3285,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580858223109444e-05,
"loss": 4.3199,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580019628358392e-05,
"loss": 4.3167,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.57918103360734e-05,
"loss": 4.3182,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578342438856288e-05,
"loss": 4.3222,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577503844105236e-05,
"loss": 4.3092,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576666887234557e-05,
"loss": 4.3147,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575828292483505e-05,
"loss": 4.323,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.574989697732453e-05,
"loss": 4.3128,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574151102981401e-05,
"loss": 4.3026,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733125082303494e-05,
"loss": 4.3286,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.57247555135967e-05,
"loss": 4.302,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571636956608618e-05,
"loss": 4.3098,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570798361857566e-05,
"loss": 4.3174,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569959767106514e-05,
"loss": 4.3208,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569122810235835e-05,
"loss": 4.3037,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568284215484783e-05,
"loss": 4.307,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567445620733731e-05,
"loss": 4.2906,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566607025982679e-05,
"loss": 4.3178,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565768431231627e-05,
"loss": 4.3129,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564929836480575e-05,
"loss": 4.3128,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564091241729523e-05,
"loss": 4.3103,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563252646978471e-05,
"loss": 4.3222,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562415690107793e-05,
"loss": 4.325,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615787332371137e-05,
"loss": 4.2986,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.5607401384860617e-05,
"loss": 4.3104,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.5599015437350096e-05,
"loss": 4.3181,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.5590629489839576e-05,
"loss": 4.2917,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582243542329056e-05,
"loss": 4.3128,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.5573857594818536e-05,
"loss": 4.2993,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.5565471647308016e-05,
"loss": 4.316,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.5557085699797496e-05,
"loss": 4.313,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.5548716131090705e-05,
"loss": 4.2912,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.5540330183580185e-05,
"loss": 4.3037,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.5531944236069665e-05,
"loss": 4.3008,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523558288559145e-05,
"loss": 4.3126,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551518871985236e-05,
"loss": 4.3012,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550681915114557e-05,
"loss": 4.3013,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549843320363505e-05,
"loss": 4.2992,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549004725612453e-05,
"loss": 4.2999,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548166130861401e-05,
"loss": 4.2952,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547327536110349e-05,
"loss": 4.284,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546488941359297e-05,
"loss": 4.2931,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545651984488618e-05,
"loss": 4.3021,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544813389737566e-05,
"loss": 4.3037,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543976432866887e-05,
"loss": 4.2848,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.5431378381158355e-05,
"loss": 4.2915,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.5422992433647835e-05,
"loss": 4.2922,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.5414606486137315e-05,
"loss": 4.3039,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406220538626795e-05,
"loss": 4.2919,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5397834591116275e-05,
"loss": 4.294,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538944864360575e-05,
"loss": 4.2862,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538106269609523e-05,
"loss": 4.3013,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537267674858471e-05,
"loss": 4.2751,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536429080107419e-05,
"loss": 4.2926,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.53559212323674e-05,
"loss": 4.2831,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534753528485688e-05,
"loss": 4.2884,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533914933734636e-05,
"loss": 4.283,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533076338983584e-05,
"loss": 4.293,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532237744232532e-05,
"loss": 4.282,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.53139914948148e-05,
"loss": 4.2823,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530560554730428e-05,
"loss": 4.2853,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529721959979376e-05,
"loss": 4.2851,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528885003108697e-05,
"loss": 4.2921,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528046408357645e-05,
"loss": 4.2936,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527209451486966e-05,
"loss": 4.2881,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526370856735914e-05,
"loss": 4.2914,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525532261984862e-05,
"loss": 4.2867,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.52469366723381e-05,
"loss": 4.279,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523855072482758e-05,
"loss": 4.2809,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523018115612079e-05,
"loss": 4.2817,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522179520861027e-05,
"loss": 4.2811,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521340926109976e-05,
"loss": 4.2871,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520502331358924e-05,
"loss": 4.2799,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.5196653744882446e-05,
"loss": 4.2877,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.5188284176175655e-05,
"loss": 4.276,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5179898228665135e-05,
"loss": 4.2794,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171512281154615e-05,
"loss": 4.2769,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163126333644095e-05,
"loss": 4.2923,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.5154740386133575e-05,
"loss": 4.2741,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146354438623055e-05,
"loss": 4.2679,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5137968491112535e-05,
"loss": 4.2638,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.5129582543602015e-05,
"loss": 4.2815,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.5121212974895224e-05,
"loss": 4.2878,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511282702738471e-05,
"loss": 4.2869,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510444107987419e-05,
"loss": 4.2777,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509605513236367e-05,
"loss": 4.2838,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508766918485315e-05,
"loss": 4.2774,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507928323734263e-05,
"loss": 4.2783,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070897289832104e-05,
"loss": 4.271,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062511342321584e-05,
"loss": 4.2804,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.50541417736148e-05,
"loss": 4.2774,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504575582610428e-05,
"loss": 4.2644,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503736987859375e-05,
"loss": 4.2814,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502898393108323e-05,
"loss": 4.2742,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502059798357271e-05,
"loss": 4.2673,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501221203606219e-05,
"loss": 4.2727,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500382608855168e-05,
"loss": 4.2673,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.265713214874268,
"eval_runtime": 288.8086,
"eval_samples_per_second": 1321.259,
"eval_steps_per_second": 41.29,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499545651984489e-05,
"loss": 4.273,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498707057233437e-05,
"loss": 4.2684,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497868462482385e-05,
"loss": 4.276,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497029867731333e-05,
"loss": 4.2647,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496191272980281e-05,
"loss": 4.2778,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495352678229229e-05,
"loss": 4.2664,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494514083478177e-05,
"loss": 4.2566,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493675488727125e-05,
"loss": 4.2573,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492836893976073e-05,
"loss": 4.2723,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.491998299225021e-05,
"loss": 4.2736,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491159704473969e-05,
"loss": 4.2633,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490321109722917e-05,
"loss": 4.2738,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489484152852238e-05,
"loss": 4.2603,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.4886455581011864e-05,
"loss": 4.2644,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4878069633501344e-05,
"loss": 4.2606,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.4869683685990824e-05,
"loss": 4.2557,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.48612977384803e-05,
"loss": 4.2601,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485291179096978e-05,
"loss": 4.2562,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484452584345926e-05,
"loss": 4.2679,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483613989594874e-05,
"loss": 4.2681,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.4827753948438217e-05,
"loss": 4.2684,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.4819368000927697e-05,
"loss": 4.2599,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.4810982053417177e-05,
"loss": 4.2542,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.4802596105906656e-05,
"loss": 4.2644,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.4794226537199866e-05,
"loss": 4.2544,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.4785840589689346e-05,
"loss": 4.2551,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.4777454642178825e-05,
"loss": 4.245,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476906869466831e-05,
"loss": 4.2609,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476069912596152e-05,
"loss": 4.2472,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.4752313178451e-05,
"loss": 4.2464,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474392723094048e-05,
"loss": 4.2608,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473554128342996e-05,
"loss": 4.2541,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472715533591944e-05,
"loss": 4.2599,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471878576721265e-05,
"loss": 4.2613,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471041619850586e-05,
"loss": 4.2525,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470203025099534e-05,
"loss": 4.2611,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469364430348482e-05,
"loss": 4.2515,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.46852583559743e-05,
"loss": 4.241,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467687240846378e-05,
"loss": 4.2377,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668486460953266e-05,
"loss": 4.2432,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660100513442746e-05,
"loss": 4.2432,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651714565932226e-05,
"loss": 4.255,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.4643344997225435e-05,
"loss": 4.2426,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4634959049714915e-05,
"loss": 4.2448,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626573102204395e-05,
"loss": 4.2535,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618187154693875e-05,
"loss": 4.2481,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460983396479081e-05,
"loss": 4.2543,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460144801728029e-05,
"loss": 4.2401,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459306206976977e-05,
"loss": 4.2234,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.458467612225925e-05,
"loss": 4.2563,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457629017474873e-05,
"loss": 4.2557,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456790422723822e-05,
"loss": 4.2485,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.45595182797277e-05,
"loss": 4.2412,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455113233221718e-05,
"loss": 4.2367,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454274638470665e-05,
"loss": 4.2382,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453436043719613e-05,
"loss": 4.2416,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452597448968561e-05,
"loss": 4.233,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451760492097883e-05,
"loss": 4.2372,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.45092189734683e-05,
"loss": 4.2469,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450083302595778e-05,
"loss": 4.2381,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449244707844726e-05,
"loss": 4.2254,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448406113093674e-05,
"loss": 4.2517,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447569156222996e-05,
"loss": 4.2262,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446730561471944e-05,
"loss": 4.2281,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445891966720892e-05,
"loss": 4.2431,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.44505337196984e-05,
"loss": 4.2471,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444214777218788e-05,
"loss": 4.2236,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443376182467736e-05,
"loss": 4.2331,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442537587716684e-05,
"loss": 4.2158,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441698992965632e-05,
"loss": 4.2412,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.4408620360949526e-05,
"loss": 4.2407,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.4400234413439006e-05,
"loss": 4.2321,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.4391848465928486e-05,
"loss": 4.2374,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.4383462518417966e-05,
"loss": 4.2428,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.4375092949711175e-05,
"loss": 4.2533,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436672338100439e-05,
"loss": 4.2235,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435833743349387e-05,
"loss": 4.2364,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.434995148598335e-05,
"loss": 4.2417,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434156553847283e-05,
"loss": 4.2167,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433317959096231e-05,
"loss": 4.2401,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432481002225552e-05,
"loss": 4.2269,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316424074745e-05,
"loss": 4.2413,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430803812723448e-05,
"loss": 4.2392,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429965217972396e-05,
"loss": 4.2207,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429128261101717e-05,
"loss": 4.2264,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428289666350665e-05,
"loss": 4.2264,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427451071599613e-05,
"loss": 4.2426,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426612476848561e-05,
"loss": 4.2293,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257738820975095e-05,
"loss": 4.2259,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249352873464575e-05,
"loss": 4.2234,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4240983304757784e-05,
"loss": 4.2303,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232597357247264e-05,
"loss": 4.2227,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224211409736744e-05,
"loss": 4.2091,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4215825462226224e-05,
"loss": 4.2241,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207439514715704e-05,
"loss": 4.2291,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.4199053567205184e-05,
"loss": 4.2312,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190667619694664e-05,
"loss": 4.2127,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418228167218414e-05,
"loss": 4.2186,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417391210347735e-05,
"loss": 4.2212,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416552615596683e-05,
"loss": 4.2298,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415714020845631e-05,
"loss": 4.2243,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414875426094579e-05,
"loss": 4.2228,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414036831343527e-05,
"loss": 4.2151,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413199874472849e-05,
"loss": 4.2292,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412361279721796e-05,
"loss": 4.2039,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411522684970744e-05,
"loss": 4.2223,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410685728100066e-05,
"loss": 4.211,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409847133349014e-05,
"loss": 4.2207,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409008538597961e-05,
"loss": 4.2084,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408169943846909e-05,
"loss": 4.2232,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407331349095857e-05,
"loss": 4.2141,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406492754344805e-05,
"loss": 4.2115,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405654159593753e-05,
"loss": 4.2156,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404817202723075e-05,
"loss": 4.216,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.403978607972023e-05,
"loss": 4.2214,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403140013220971e-05,
"loss": 4.228,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402301418469919e-05,
"loss": 4.2222,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401462823718867e-05,
"loss": 4.2213,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.4006242289678147e-05,
"loss": 4.2171,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.3997856342167627e-05,
"loss": 4.2119,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.3989470394657106e-05,
"loss": 4.2086,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.3981100825950316e-05,
"loss": 4.2194,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.3972714878439796e-05,
"loss": 4.2102,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.3964328930929276e-05,
"loss": 4.2174,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3955942983418755e-05,
"loss": 4.2113,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.3947573414711965e-05,
"loss": 4.2201,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393918746720145e-05,
"loss": 4.2095,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393081789849466e-05,
"loss": 4.2125,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392243195098414e-05,
"loss": 4.2084,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391404600347362e-05,
"loss": 4.2206,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.39056600559631e-05,
"loss": 4.2099,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389727410845258e-05,
"loss": 4.2021,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388888816094206e-05,
"loss": 4.1948,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388051859223527e-05,
"loss": 4.2158,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387213264472475e-05,
"loss": 4.2203,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386374669721423e-05,
"loss": 4.2185,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385536074970371e-05,
"loss": 4.2141,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384697480219319e-05,
"loss": 4.2157,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383858885468267e-05,
"loss": 4.2096,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383020290717215e-05,
"loss": 4.2173,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382181695966163e-05,
"loss": 4.2014,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813463769758574e-05,
"loss": 4.2116,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3805077822248054e-05,
"loss": 4.209,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796691874737534e-05,
"loss": 4.2031,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788305927227014e-05,
"loss": 4.214,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.377993635852022e-05,
"loss": 4.2079,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.37715504110097e-05,
"loss": 4.2051,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376316446349918e-05,
"loss": 4.2062,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375477851598866e-05,
"loss": 4.2044,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.2105817794799805,
"eval_runtime": 292.2977,
"eval_samples_per_second": 1305.488,
"eval_steps_per_second": 40.797,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.374639256847814e-05,
"loss": 4.2057,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.373802299977136e-05,
"loss": 4.2043,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.372963705226084e-05,
"loss": 4.2104,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.372125110475032e-05,
"loss": 4.2014,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.37128651572398e-05,
"loss": 4.2134,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.370447920972927e-05,
"loss": 4.2027,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.369609326221875e-05,
"loss": 4.1932,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368770731470823e-05,
"loss": 4.1907,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367933774600145e-05,
"loss": 4.2087,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367095179849092e-05,
"loss": 4.2099,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.36625658509804e-05,
"loss": 4.2028,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.365417990346988e-05,
"loss": 4.2075,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.3645810334763096e-05,
"loss": 4.2012,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.3637424387252576e-05,
"loss": 4.2041,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.3629038439742056e-05,
"loss": 4.1985,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.3620652492231536e-05,
"loss": 4.1892,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.3612266544721016e-05,
"loss": 4.1992,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.3603880597210496e-05,
"loss": 4.1932,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.3595494649699976e-05,
"loss": 4.205,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.3587108702189456e-05,
"loss": 4.206,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.3578722754678936e-05,
"loss": 4.2104,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.3570336807168416e-05,
"loss": 4.1987,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.3561950859657896e-05,
"loss": 4.195,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.3553564912147376e-05,
"loss": 4.1994,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.3545195343440585e-05,
"loss": 4.1918,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.353684215353753e-05,
"loss": 4.1958,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.352845620602701e-05,
"loss": 4.18,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.352007025851649e-05,
"loss": 4.2016,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.351168431100597e-05,
"loss": 4.1893,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.350329836349545e-05,
"loss": 4.1851,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.349491241598493e-05,
"loss": 4.1944,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.348652646847441e-05,
"loss": 4.199,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.347814052096389e-05,
"loss": 4.2006,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.346975457345337e-05,
"loss": 4.1972,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.346138500474658e-05,
"loss": 4.1918,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345299905723606e-05,
"loss": 4.1989,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344461310972554e-05,
"loss": 4.1966,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.343622716221502e-05,
"loss": 4.1788,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.34278412147045e-05,
"loss": 4.1802,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.341945526719398e-05,
"loss": 4.181,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.341106931968346e-05,
"loss": 4.1874,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.3402699750976674e-05,
"loss": 4.1953,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.3394313803466154e-05,
"loss": 4.1851,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.3385927855955634e-05,
"loss": 4.1819,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337754190844511e-05,
"loss": 4.1949,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.336915596093459e-05,
"loss": 4.1865,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.33607863922278e-05,
"loss": 4.1995,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.3352400444717276e-05,
"loss": 4.1816,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.3344014497206756e-05,
"loss": 4.1613,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.3335628549696236e-05,
"loss": 4.1992,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.3327242602185716e-05,
"loss": 4.1919,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.331887303347893e-05,
"loss": 4.1924,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331048708596841e-05,
"loss": 4.185,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.330210113845789e-05,
"loss": 4.1803,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.329371519094737e-05,
"loss": 4.1783,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328532924343685e-05,
"loss": 4.1814,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.327694329592633e-05,
"loss": 4.1759,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326855734841581e-05,
"loss": 4.1791,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326017140090529e-05,
"loss": 4.1871,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.32518018321985e-05,
"loss": 4.1803,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.324341588468798e-05,
"loss": 4.1694,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.323502993717746e-05,
"loss": 4.1911,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322664398966694e-05,
"loss": 4.171,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.321827442096015e-05,
"loss": 4.1716,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.3209904852253366e-05,
"loss": 4.185,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.3201518904742846e-05,
"loss": 4.1878,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.3193132957232326e-05,
"loss": 4.166,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.3184747009721806e-05,
"loss": 4.1793,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.3176361062211286e-05,
"loss": 4.1593,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.3167991493504495e-05,
"loss": 4.1814,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.3159605545993975e-05,
"loss": 4.1821,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.3151219598483455e-05,
"loss": 4.1798,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.3142833650972935e-05,
"loss": 4.1795,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.3134447703462415e-05,
"loss": 4.1865,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.3126061755951895e-05,
"loss": 4.1929,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.3117692187245104e-05,
"loss": 4.1685,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310930623973459e-05,
"loss": 4.1833,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310092029222407e-05,
"loss": 4.1857,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.309253434471355e-05,
"loss": 4.1608,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308414839720303e-05,
"loss": 4.1854,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.307576244969251e-05,
"loss": 4.1713,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.306739288098572e-05,
"loss": 4.1845,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.30590069334752e-05,
"loss": 4.1831,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.305062098596468e-05,
"loss": 4.168,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.304223503845416e-05,
"loss": 4.1663,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.303384909094364e-05,
"loss": 4.1717,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.302546314343311e-05,
"loss": 4.1883,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.301707719592259e-05,
"loss": 4.1722,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.300869124841207e-05,
"loss": 4.1724,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.300032167970529e-05,
"loss": 4.1699,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.299193573219477e-05,
"loss": 4.1761,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.298354978468425e-05,
"loss": 4.1683,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.297516383717373e-05,
"loss": 4.1546,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.296677788966321e-05,
"loss": 4.1683,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.295839194215269e-05,
"loss": 4.1772,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.295000599464217e-05,
"loss": 4.178,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294162004713165e-05,
"loss": 4.1608,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293325047842486e-05,
"loss": 4.1631,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.2924880909718066e-05,
"loss": 4.1681,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.2916494962207546e-05,
"loss": 4.1733,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.2908109014697026e-05,
"loss": 4.1764,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.2899723067186506e-05,
"loss": 4.1624,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289133711967599e-05,
"loss": 4.1668,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288295117216547e-05,
"loss": 4.1746,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.287456522465495e-05,
"loss": 4.1524,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286617927714443e-05,
"loss": 4.1661,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.285782608724137e-05,
"loss": 4.1574,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.284944013973085e-05,
"loss": 4.1702,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284105419222033e-05,
"loss": 4.1563,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.283266824470981e-05,
"loss": 4.1709,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.282428229719929e-05,
"loss": 4.1608,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281589634968877e-05,
"loss": 4.1611,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.280751040217825e-05,
"loss": 4.1619,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.279912445466773e-05,
"loss": 4.1663,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.2790754885960946e-05,
"loss": 4.1631,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.2782368938450426e-05,
"loss": 4.1801,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.2773999369743635e-05,
"loss": 4.169,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.2765613422233115e-05,
"loss": 4.1715,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.2757243853526324e-05,
"loss": 4.1611,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.2748857906015804e-05,
"loss": 4.1653,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.2740471958505284e-05,
"loss": 4.1574,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.2732086010994764e-05,
"loss": 4.1643,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.2723700063484244e-05,
"loss": 4.1609,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.2715314115973724e-05,
"loss": 4.164,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.2706928168463204e-05,
"loss": 4.1631,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.2698542220952684e-05,
"loss": 4.164,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.26901726522459e-05,
"loss": 4.1585,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.268180308353911e-05,
"loss": 4.1654,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.267341713602859e-05,
"loss": 4.1576,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.266503118851807e-05,
"loss": 4.1666,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.265664524100755e-05,
"loss": 4.1616,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.264825929349703e-05,
"loss": 4.1551,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.263987334598651e-05,
"loss": 4.1408,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.263148739847599e-05,
"loss": 4.1676,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.262310145096547e-05,
"loss": 4.1692,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.261473188225868e-05,
"loss": 4.1685,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.260634593474816e-05,
"loss": 4.163,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.259795998723764e-05,
"loss": 4.1647,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.258957403972712e-05,
"loss": 4.1594,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.25811880922166e-05,
"loss": 4.1717,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.2572818523509813e-05,
"loss": 4.1521,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.2564432575999293e-05,
"loss": 4.1602,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255604662848877e-05,
"loss": 4.1582,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.2547660680978247e-05,
"loss": 4.1561,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253929111227146e-05,
"loss": 4.167,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253090516476094e-05,
"loss": 4.154,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252251921725042e-05,
"loss": 4.1616,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.2514133269739896e-05,
"loss": 4.1532,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.2505747322229375e-05,
"loss": 4.1584,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 4.16970682144165,
"eval_runtime": 289.0674,
"eval_samples_per_second": 1320.076,
"eval_steps_per_second": 41.253,
"step": 457920
},
{
"epoch": 0.0,
"learning_rate": 4.249737775352259e-05,
"loss": 4.1653,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.248899180601207e-05,
"loss": 4.1556,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.248060585850155e-05,
"loss": 4.1614,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.247221991099103e-05,
"loss": 4.1526,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.246383396348051e-05,
"loss": 4.1665,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.245544801596999e-05,
"loss": 4.1532,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.244706206845947e-05,
"loss": 4.1472,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.243867612094895e-05,
"loss": 4.1414,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.243029017343843e-05,
"loss": 4.161,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.242190422592791e-05,
"loss": 4.1602,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.241351827841739e-05,
"loss": 4.1542,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.240513233090687e-05,
"loss": 4.1603,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239676276220008e-05,
"loss": 4.1532,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238837681468956e-05,
"loss": 4.1546,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.237999086717904e-05,
"loss": 4.1476,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237160491966852e-05,
"loss": 4.1439,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.2363218972158e-05,
"loss": 4.1506,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.2354833024647487e-05,
"loss": 4.1497,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.2346447077136966e-05,
"loss": 4.1547,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.233806112962644e-05,
"loss": 4.1584,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.232967518211592e-05,
"loss": 4.165,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.23212892346054e-05,
"loss": 4.1522,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.231290328709488e-05,
"loss": 4.1476,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.230453371838809e-05,
"loss": 4.1514,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.229614777087757e-05,
"loss": 4.1487,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.228776182336705e-05,
"loss": 4.1489,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.227937587585653e-05,
"loss": 4.1301,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.227098992834601e-05,
"loss": 4.1592,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.226260398083549e-05,
"loss": 4.1456,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.225421803332497e-05,
"loss": 4.1389,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.2245832085814455e-05,
"loss": 4.1471,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.2237462517107664e-05,
"loss": 4.1531,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.2229076569597144e-05,
"loss": 4.1492,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.2220690622086624e-05,
"loss": 4.1535,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.2212304674576104e-05,
"loss": 4.1448,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.220393510586931e-05,
"loss": 4.1554,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.219554915835879e-05,
"loss": 4.1492,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.218716321084827e-05,
"loss": 4.1327,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.217877726333775e-05,
"loss": 4.1343,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.217039131582723e-05,
"loss": 4.1357,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.216200536831671e-05,
"loss": 4.1417,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.215361942080619e-05,
"loss": 4.1507,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.214524985209941e-05,
"loss": 4.138,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.213688028339262e-05,
"loss": 4.1384,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.21284943358821e-05,
"loss": 4.1458,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.212010838837158e-05,
"loss": 4.1388,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.211172244086106e-05,
"loss": 4.155,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.210333649335054e-05,
"loss": 4.1389,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.209495054584002e-05,
"loss": 4.1124,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.20865645983295e-05,
"loss": 4.1546,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.207817865081897e-05,
"loss": 4.1495,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.206980908211219e-05,
"loss": 4.1459,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.2061423134601667e-05,
"loss": 4.1395,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.2053037187091147e-05,
"loss": 4.1356,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.2044651239580626e-05,
"loss": 4.1326,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.2036265292070106e-05,
"loss": 4.1394,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.202789572336332e-05,
"loss": 4.1321,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.2019509775852796e-05,
"loss": 4.1331,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.2011123828342275e-05,
"loss": 4.1424,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.2002737880831755e-05,
"loss": 4.1383,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.1994351933321235e-05,
"loss": 4.125,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.1985965985810715e-05,
"loss": 4.1469,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.1977580038300195e-05,
"loss": 4.1251,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.1969194090789675e-05,
"loss": 4.13,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.1960824522082884e-05,
"loss": 4.1415,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.1952438574572364e-05,
"loss": 4.1424,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.1944052627061844e-05,
"loss": 4.1228,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.1935666679551324e-05,
"loss": 4.1328,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.192729711084454e-05,
"loss": 4.1164,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.191891116333402e-05,
"loss": 4.1375,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.19105252158235e-05,
"loss": 4.1397,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.190213926831298e-05,
"loss": 4.1393,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.189375332080246e-05,
"loss": 4.1332,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.188538375209567e-05,
"loss": 4.1429,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.187699780458515e-05,
"loss": 4.1514,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.186862823587836e-05,
"loss": 4.1279,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.186024228836784e-05,
"loss": 4.139,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.185185634085732e-05,
"loss": 4.1412,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.18434703933468e-05,
"loss": 4.1202,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.183508444583628e-05,
"loss": 4.1392,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.1826698498325765e-05,
"loss": 4.1342,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.1818312550815245e-05,
"loss": 4.1381,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.1809926603304725e-05,
"loss": 4.1414,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.1801557034597934e-05,
"loss": 4.1275,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.1793171087087414e-05,
"loss": 4.1257,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.1784785139576894e-05,
"loss": 4.1307,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.1776399192066373e-05,
"loss": 4.1392,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.1768013244555853e-05,
"loss": 4.133,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.175964367584906e-05,
"loss": 4.1296,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.175127410714227e-05,
"loss": 4.1303,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.174288815963175e-05,
"loss": 4.1351,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.173450221212123e-05,
"loss": 4.1265,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.172611626461072e-05,
"loss": 4.1119,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.17177303171002e-05,
"loss": 4.129,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.170934436958968e-05,
"loss": 4.1314,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.170095842207916e-05,
"loss": 4.1344,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.169257247456863e-05,
"loss": 4.1212,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.168420290586185e-05,
"loss": 4.1209,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.167581695835133e-05,
"loss": 4.1284,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.166743101084081e-05,
"loss": 4.1284,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.1659061442134016e-05,
"loss": 4.1389,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.1650675494623496e-05,
"loss": 4.1217,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.1642289547112976e-05,
"loss": 4.1255,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.1633903599602456e-05,
"loss": 4.1322,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.1625517652091936e-05,
"loss": 4.1107,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.1617131704581416e-05,
"loss": 4.128,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.160876213587463e-05,
"loss": 4.1117,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.1600376188364105e-05,
"loss": 4.1323,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.159200661965732e-05,
"loss": 4.1137,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.15836206721468e-05,
"loss": 4.1294,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.157523472463628e-05,
"loss": 4.1197,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.1566848777125754e-05,
"loss": 4.118,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.1558462829615234e-05,
"loss": 4.1222,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.1550076882104714e-05,
"loss": 4.1269,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.1541690934594194e-05,
"loss": 4.1242,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.1533304987083674e-05,
"loss": 4.1385,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.1524919039573154e-05,
"loss": 4.1257,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.151653309206264e-05,
"loss": 4.1383,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.150814714455212e-05,
"loss": 4.1216,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.149977757584533e-05,
"loss": 4.1213,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.149139162833481e-05,
"loss": 4.1224,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.148300568082429e-05,
"loss": 4.1202,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.147461973331377e-05,
"loss": 4.1201,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.146623378580325e-05,
"loss": 4.125,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.145784783829273e-05,
"loss": 4.122,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.144946189078221e-05,
"loss": 4.1261,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.144107594327169e-05,
"loss": 4.1204,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.14327063745649e-05,
"loss": 4.1253,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.142432042705438e-05,
"loss": 4.1209,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.141593447954386e-05,
"loss": 4.1218,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.140754853203334e-05,
"loss": 4.1191,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.139916258452282e-05,
"loss": 4.1183,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.13907766370123e-05,
"loss": 4.1015,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.138239068950178e-05,
"loss": 4.128,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.137400474199126e-05,
"loss": 4.129,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.136563517328447e-05,
"loss": 4.1312,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.135724922577395e-05,
"loss": 4.1201,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.134886327826343e-05,
"loss": 4.1293,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.134047733075291e-05,
"loss": 4.1217,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.1332107762046116e-05,
"loss": 4.1304,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.1323721814535596e-05,
"loss": 4.1111,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.1315335867025076e-05,
"loss": 4.1189,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.130696629831829e-05,
"loss": 4.1224,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.129858035080777e-05,
"loss": 4.1193,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.129019440329725e-05,
"loss": 4.123,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.128180845578673e-05,
"loss": 4.1165,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.127342250827621e-05,
"loss": 4.1209,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.126505293956942e-05,
"loss": 4.1141,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.12566669920589e-05,
"loss": 4.1237,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 4.139695644378662,
"eval_runtime": 298.1743,
"eval_samples_per_second": 1279.758,
"eval_steps_per_second": 39.993,
"step": 534240
},
{
"epoch": 1.0,
"learning_rate": 4.124828104454838e-05,
"loss": 4.1158,
"step": 534528
},
{
"epoch": 1.0,
"learning_rate": 4.123989509703786e-05,
"loss": 4.1191,
"step": 535040
},
{
"epoch": 1.0,
"learning_rate": 4.123150914952734e-05,
"loss": 4.1183,
"step": 535552
},
{
"epoch": 1.0,
"learning_rate": 4.122312320201682e-05,
"loss": 4.1129,
"step": 536064
},
{
"epoch": 1.0,
"learning_rate": 4.12147372545063e-05,
"loss": 4.1251,
"step": 536576
},
{
"epoch": 1.0,
"learning_rate": 4.120635130699578e-05,
"loss": 4.1189,
"step": 537088
},
{
"epoch": 1.0,
"learning_rate": 4.1197981738288996e-05,
"loss": 4.1105,
"step": 537600
},
{
"epoch": 1.0,
"learning_rate": 4.1189595790778476e-05,
"loss": 4.1059,
"step": 538112
},
{
"epoch": 1.0,
"learning_rate": 4.1181226222071685e-05,
"loss": 4.1172,
"step": 538624
},
{
"epoch": 1.0,
"learning_rate": 4.1172840274561165e-05,
"loss": 4.1245,
"step": 539136
},
{
"epoch": 1.0,
"learning_rate": 4.1164454327050645e-05,
"loss": 4.1133,
"step": 539648
},
{
"epoch": 1.0,
"learning_rate": 4.1156068379540125e-05,
"loss": 4.1208,
"step": 540160
},
{
"epoch": 1.0,
"learning_rate": 4.1147698810833334e-05,
"loss": 4.1228,
"step": 540672
},
{
"epoch": 1.0,
"learning_rate": 4.1139312863322814e-05,
"loss": 4.1115,
"step": 541184
},
{
"epoch": 1.0,
"learning_rate": 4.1130926915812294e-05,
"loss": 4.1109,
"step": 541696
},
{
"epoch": 1.0,
"learning_rate": 4.1122540968301774e-05,
"loss": 4.1066,
"step": 542208
},
{
"epoch": 1.0,
"learning_rate": 4.1114155020791254e-05,
"loss": 4.1138,
"step": 542720
},
{
"epoch": 1.0,
"learning_rate": 4.1105769073280734e-05,
"loss": 4.1096,
"step": 543232
},
{
"epoch": 1.0,
"learning_rate": 4.109739950457395e-05,
"loss": 4.1125,
"step": 543744
},
{
"epoch": 1.0,
"learning_rate": 4.108901355706343e-05,
"loss": 4.1238,
"step": 544256
},
{
"epoch": 1.0,
"learning_rate": 4.108062760955291e-05,
"loss": 4.1259,
"step": 544768
},
{
"epoch": 1.0,
"learning_rate": 4.107224166204239e-05,
"loss": 4.1153,
"step": 545280
},
{
"epoch": 1.0,
"learning_rate": 4.106385571453187e-05,
"loss": 4.1099,
"step": 545792
},
{
"epoch": 1.0,
"learning_rate": 4.105546976702135e-05,
"loss": 4.1117,
"step": 546304
},
{
"epoch": 1.0,
"learning_rate": 4.104710019831456e-05,
"loss": 4.1115,
"step": 546816
},
{
"epoch": 1.0,
"learning_rate": 4.103871425080404e-05,
"loss": 4.1103,
"step": 547328
},
{
"epoch": 1.0,
"learning_rate": 4.103032830329352e-05,
"loss": 4.0963,
"step": 547840
},
{
"epoch": 1.0,
"learning_rate": 4.1021942355783e-05,
"loss": 4.1202,
"step": 548352
},
{
"epoch": 1.0,
"learning_rate": 4.101355640827247e-05,
"loss": 4.1098,
"step": 548864
},
{
"epoch": 1.0,
"learning_rate": 4.100517046076195e-05,
"loss": 4.1028,
"step": 549376
},
{
"epoch": 1.01,
"learning_rate": 4.099678451325143e-05,
"loss": 4.103,
"step": 549888
},
{
"epoch": 1.01,
"learning_rate": 4.098841494454465e-05,
"loss": 4.1177,
"step": 550400
},
{
"epoch": 1.01,
"learning_rate": 4.098002899703413e-05,
"loss": 4.1158,
"step": 550912
},
{
"epoch": 1.01,
"learning_rate": 4.097164304952361e-05,
"loss": 4.114,
"step": 551424
},
{
"epoch": 1.01,
"learning_rate": 4.096325710201309e-05,
"loss": 4.1072,
"step": 551936
},
{
"epoch": 1.01,
"learning_rate": 4.095487115450257e-05,
"loss": 4.1138,
"step": 552448
},
{
"epoch": 1.01,
"learning_rate": 4.094648520699205e-05,
"loss": 4.1148,
"step": 552960
},
{
"epoch": 1.01,
"learning_rate": 4.093809925948153e-05,
"loss": 4.097,
"step": 553472
},
{
"epoch": 1.01,
"learning_rate": 4.092971331197101e-05,
"loss": 4.097,
"step": 553984
},
{
"epoch": 1.01,
"learning_rate": 4.0921360122067946e-05,
"loss": 4.0983,
"step": 554496
},
{
"epoch": 1.01,
"learning_rate": 4.0912974174557426e-05,
"loss": 4.1044,
"step": 555008
},
{
"epoch": 1.01,
"learning_rate": 4.0904588227046906e-05,
"loss": 4.1106,
"step": 555520
},
{
"epoch": 1.01,
"learning_rate": 4.0896202279536386e-05,
"loss": 4.107,
"step": 556032
},
{
"epoch": 1.01,
"learning_rate": 4.08878327108296e-05,
"loss": 4.1011,
"step": 556544
},
{
"epoch": 1.01,
"learning_rate": 4.087944676331908e-05,
"loss": 4.1071,
"step": 557056
},
{
"epoch": 1.01,
"learning_rate": 4.087106081580856e-05,
"loss": 4.1021,
"step": 557568
},
{
"epoch": 1.01,
"learning_rate": 4.086267486829804e-05,
"loss": 4.1154,
"step": 558080
},
{
"epoch": 1.01,
"learning_rate": 4.085428892078752e-05,
"loss": 4.1071,
"step": 558592
},
{
"epoch": 1.01,
"learning_rate": 4.0845902973277e-05,
"loss": 4.078,
"step": 559104
},
{
"epoch": 1.01,
"learning_rate": 4.0837549783373946e-05,
"loss": 4.1153,
"step": 559616
},
{
"epoch": 1.01,
"learning_rate": 4.082916383586342e-05,
"loss": 4.1112,
"step": 560128
},
{
"epoch": 1.01,
"learning_rate": 4.08207778883529e-05,
"loss": 4.1151,
"step": 560640
},
{
"epoch": 1.01,
"learning_rate": 4.081239194084238e-05,
"loss": 4.1011,
"step": 561152
},
{
"epoch": 1.01,
"learning_rate": 4.080400599333186e-05,
"loss": 4.0985,
"step": 561664
},
{
"epoch": 1.01,
"learning_rate": 4.079562004582134e-05,
"loss": 4.1005,
"step": 562176
},
{
"epoch": 1.01,
"learning_rate": 4.0787234098310826e-05,
"loss": 4.1028,
"step": 562688
},
{
"epoch": 1.01,
"learning_rate": 4.0778848150800306e-05,
"loss": 4.1013,
"step": 563200
},
{
"epoch": 1.01,
"learning_rate": 4.0770462203289786e-05,
"loss": 4.0922,
"step": 563712
},
{
"epoch": 1.01,
"learning_rate": 4.0762076255779266e-05,
"loss": 4.1077,
"step": 564224
},
{
"epoch": 1.01,
"learning_rate": 4.0753690308268746e-05,
"loss": 4.1041,
"step": 564736
},
{
"epoch": 1.01,
"learning_rate": 4.0745304360758226e-05,
"loss": 4.0883,
"step": 565248
},
{
"epoch": 1.01,
"learning_rate": 4.0736918413247706e-05,
"loss": 4.1122,
"step": 565760
},
{
"epoch": 1.01,
"learning_rate": 4.0728548844540915e-05,
"loss": 4.0911,
"step": 566272
},
{
"epoch": 1.01,
"learning_rate": 4.0720162897030395e-05,
"loss": 4.0911,
"step": 566784
},
{
"epoch": 1.01,
"learning_rate": 4.0711776949519875e-05,
"loss": 4.1058,
"step": 567296
},
{
"epoch": 1.01,
"learning_rate": 4.0703391002009355e-05,
"loss": 4.1065,
"step": 567808
},
{
"epoch": 1.01,
"learning_rate": 4.0695021433302564e-05,
"loss": 4.0889,
"step": 568320
},
{
"epoch": 1.01,
"learning_rate": 4.0686635485792044e-05,
"loss": 4.0976,
"step": 568832
},
{
"epoch": 1.01,
"learning_rate": 4.067826591708526e-05,
"loss": 4.0809,
"step": 569344
},
{
"epoch": 1.01,
"learning_rate": 4.066987996957474e-05,
"loss": 4.1018,
"step": 569856
},
{
"epoch": 1.01,
"learning_rate": 4.066149402206422e-05,
"loss": 4.1035,
"step": 570368
},
{
"epoch": 1.01,
"learning_rate": 4.06531080745537e-05,
"loss": 4.1043,
"step": 570880
},
{
"epoch": 1.01,
"learning_rate": 4.064472212704318e-05,
"loss": 4.0975,
"step": 571392
},
{
"epoch": 1.01,
"learning_rate": 4.063633617953266e-05,
"loss": 4.104,
"step": 571904
},
{
"epoch": 1.01,
"learning_rate": 4.062795023202214e-05,
"loss": 4.1191,
"step": 572416
},
{
"epoch": 1.01,
"learning_rate": 4.061958066331535e-05,
"loss": 4.088,
"step": 572928
},
{
"epoch": 1.01,
"learning_rate": 4.061119471580483e-05,
"loss": 4.1053,
"step": 573440
},
{
"epoch": 1.01,
"learning_rate": 4.060280876829431e-05,
"loss": 4.1061,
"step": 573952
},
{
"epoch": 1.01,
"learning_rate": 4.059442282078378e-05,
"loss": 4.0869,
"step": 574464
},
{
"epoch": 1.01,
"learning_rate": 4.058603687327326e-05,
"loss": 4.1027,
"step": 574976
},
{
"epoch": 1.01,
"learning_rate": 4.057765092576274e-05,
"loss": 4.102,
"step": 575488
},
{
"epoch": 1.01,
"learning_rate": 4.056926497825223e-05,
"loss": 4.1034,
"step": 576000
},
{
"epoch": 1.01,
"learning_rate": 4.056089540954544e-05,
"loss": 4.1116,
"step": 576512
},
{
"epoch": 1.01,
"learning_rate": 4.055250946203492e-05,
"loss": 4.0876,
"step": 577024
},
{
"epoch": 1.01,
"learning_rate": 4.05441235145244e-05,
"loss": 4.0935,
"step": 577536
},
{
"epoch": 1.01,
"learning_rate": 4.053573756701388e-05,
"loss": 4.0948,
"step": 578048
},
{
"epoch": 1.01,
"learning_rate": 4.0527367998307086e-05,
"loss": 4.1046,
"step": 578560
},
{
"epoch": 1.01,
"learning_rate": 4.0518982050796566e-05,
"loss": 4.096,
"step": 579072
},
{
"epoch": 1.01,
"learning_rate": 4.0510596103286046e-05,
"loss": 4.1006,
"step": 579584
},
{
"epoch": 1.02,
"learning_rate": 4.0502210155775526e-05,
"loss": 4.0983,
"step": 580096
},
{
"epoch": 1.02,
"learning_rate": 4.0493824208265006e-05,
"loss": 4.0946,
"step": 580608
},
{
"epoch": 1.02,
"learning_rate": 4.0485438260754486e-05,
"loss": 4.0935,
"step": 581120
},
{
"epoch": 1.02,
"learning_rate": 4.0477052313243966e-05,
"loss": 4.0779,
"step": 581632
},
{
"epoch": 1.02,
"learning_rate": 4.0468666365733446e-05,
"loss": 4.0926,
"step": 582144
},
{
"epoch": 1.02,
"learning_rate": 4.046029679702666e-05,
"loss": 4.0965,
"step": 582656
},
{
"epoch": 1.02,
"learning_rate": 4.045191084951614e-05,
"loss": 4.1025,
"step": 583168
},
{
"epoch": 1.02,
"learning_rate": 4.044352490200562e-05,
"loss": 4.0875,
"step": 583680
},
{
"epoch": 1.02,
"learning_rate": 4.04351389544951e-05,
"loss": 4.0838,
"step": 584192
},
{
"epoch": 1.02,
"learning_rate": 4.042676938578831e-05,
"loss": 4.093,
"step": 584704
},
{
"epoch": 1.02,
"learning_rate": 4.041839981708152e-05,
"loss": 4.0957,
"step": 585216
},
{
"epoch": 1.02,
"learning_rate": 4.0410013869571e-05,
"loss": 4.1003,
"step": 585728
},
{
"epoch": 1.02,
"learning_rate": 4.040162792206048e-05,
"loss": 4.0928,
"step": 586240
},
{
"epoch": 1.02,
"learning_rate": 4.039324197454996e-05,
"loss": 4.0941,
"step": 586752
},
{
"epoch": 1.02,
"learning_rate": 4.038487240584317e-05,
"loss": 4.0931,
"step": 587264
},
{
"epoch": 1.02,
"learning_rate": 4.037648645833265e-05,
"loss": 4.0834,
"step": 587776
},
{
"epoch": 1.02,
"learning_rate": 4.0368100510822135e-05,
"loss": 4.0882,
"step": 588288
},
{
"epoch": 1.02,
"learning_rate": 4.0359730942115345e-05,
"loss": 4.0798,
"step": 588800
},
{
"epoch": 1.02,
"learning_rate": 4.0351344994604824e-05,
"loss": 4.0997,
"step": 589312
},
{
"epoch": 1.02,
"learning_rate": 4.0342959047094304e-05,
"loss": 4.0806,
"step": 589824
},
{
"epoch": 1.02,
"learning_rate": 4.0334573099583784e-05,
"loss": 4.0949,
"step": 590336
},
{
"epoch": 1.02,
"learning_rate": 4.0326187152073264e-05,
"loss": 4.0859,
"step": 590848
},
{
"epoch": 1.02,
"learning_rate": 4.0317801204562744e-05,
"loss": 4.0922,
"step": 591360
},
{
"epoch": 1.02,
"learning_rate": 4.0309415257052224e-05,
"loss": 4.0866,
"step": 591872
},
{
"epoch": 1.02,
"learning_rate": 4.0301029309541704e-05,
"loss": 4.0915,
"step": 592384
},
{
"epoch": 1.02,
"learning_rate": 4.0292643362031184e-05,
"loss": 4.0907,
"step": 592896
},
{
"epoch": 1.02,
"learning_rate": 4.0284257414520664e-05,
"loss": 4.1061,
"step": 593408
},
{
"epoch": 1.02,
"learning_rate": 4.027588784581387e-05,
"loss": 4.0888,
"step": 593920
},
{
"epoch": 1.02,
"learning_rate": 4.026750189830335e-05,
"loss": 4.1022,
"step": 594432
},
{
"epoch": 1.02,
"learning_rate": 4.025911595079283e-05,
"loss": 4.0856,
"step": 594944
},
{
"epoch": 1.02,
"learning_rate": 4.025073000328231e-05,
"loss": 4.0884,
"step": 595456
},
{
"epoch": 1.02,
"learning_rate": 4.02423440557718e-05,
"loss": 4.0885,
"step": 595968
},
{
"epoch": 1.02,
"learning_rate": 4.023397448706501e-05,
"loss": 4.0912,
"step": 596480
},
{
"epoch": 1.02,
"learning_rate": 4.022558853955449e-05,
"loss": 4.0837,
"step": 596992
},
{
"epoch": 1.02,
"learning_rate": 4.021720259204397e-05,
"loss": 4.0925,
"step": 597504
},
{
"epoch": 1.02,
"learning_rate": 4.020881664453344e-05,
"loss": 4.0846,
"step": 598016
},
{
"epoch": 1.02,
"learning_rate": 4.020043069702292e-05,
"loss": 4.0925,
"step": 598528
},
{
"epoch": 1.02,
"learning_rate": 4.01920447495124e-05,
"loss": 4.0905,
"step": 599040
},
{
"epoch": 1.02,
"learning_rate": 4.018367518080562e-05,
"loss": 4.0867,
"step": 599552
},
{
"epoch": 1.02,
"learning_rate": 4.017528923329509e-05,
"loss": 4.0895,
"step": 600064
},
{
"epoch": 1.02,
"learning_rate": 4.016690328578457e-05,
"loss": 4.0944,
"step": 600576
},
{
"epoch": 1.02,
"learning_rate": 4.015851733827406e-05,
"loss": 4.0837,
"step": 601088
},
{
"epoch": 1.02,
"learning_rate": 4.015013139076354e-05,
"loss": 4.0858,
"step": 601600
},
{
"epoch": 1.02,
"learning_rate": 4.014174544325302e-05,
"loss": 4.0664,
"step": 602112
},
{
"epoch": 1.02,
"learning_rate": 4.01333594957425e-05,
"loss": 4.0948,
"step": 602624
},
{
"epoch": 1.02,
"learning_rate": 4.012497354823198e-05,
"loss": 4.097,
"step": 603136
},
{
"epoch": 1.02,
"learning_rate": 4.011658760072146e-05,
"loss": 4.0977,
"step": 603648
},
{
"epoch": 1.02,
"learning_rate": 4.0108218032014667e-05,
"loss": 4.0878,
"step": 604160
},
{
"epoch": 1.02,
"learning_rate": 4.0099832084504146e-05,
"loss": 4.0938,
"step": 604672
},
{
"epoch": 1.02,
"learning_rate": 4.0091446136993626e-05,
"loss": 4.0903,
"step": 605184
},
{
"epoch": 1.02,
"learning_rate": 4.0083060189483106e-05,
"loss": 4.096,
"step": 605696
},
{
"epoch": 1.02,
"learning_rate": 4.0074690620776315e-05,
"loss": 4.08,
"step": 606208
},
{
"epoch": 1.02,
"learning_rate": 4.0066304673265795e-05,
"loss": 4.0871,
"step": 606720
},
{
"epoch": 1.02,
"learning_rate": 4.0057918725755275e-05,
"loss": 4.0871,
"step": 607232
},
{
"epoch": 1.02,
"learning_rate": 4.0049532778244755e-05,
"loss": 4.088,
"step": 607744
},
{
"epoch": 1.02,
"learning_rate": 4.0041146830734235e-05,
"loss": 4.0894,
"step": 608256
},
{
"epoch": 1.02,
"learning_rate": 4.003277726202745e-05,
"loss": 4.0813,
"step": 608768
},
{
"epoch": 1.02,
"learning_rate": 4.002439131451693e-05,
"loss": 4.0923,
"step": 609280
},
{
"epoch": 1.02,
"learning_rate": 4.001600536700641e-05,
"loss": 4.0794,
"step": 609792
},
{
"epoch": 1.02,
"learning_rate": 4.000761941949589e-05,
"loss": 4.0937,
"step": 610304
},
{
"epoch": 1.03,
"eval_loss": 4.115260601043701,
"eval_runtime": 297.6648,
"eval_samples_per_second": 1281.949,
"eval_steps_per_second": 40.062,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.999923347198537e-05,
"loss": 4.0875,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.999084752447485e-05,
"loss": 4.086,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.998246157696433e-05,
"loss": 4.087,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.9974075629453804e-05,
"loss": 4.0846,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.9965689681943284e-05,
"loss": 4.0953,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.9957303734432764e-05,
"loss": 4.0861,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.9948917786922244e-05,
"loss": 4.0764,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.9940531839411724e-05,
"loss": 4.074,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.9932145891901204e-05,
"loss": 4.0847,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.992375994439069e-05,
"loss": 4.0927,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.991537399688017e-05,
"loss": 4.0846,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.990698804936965e-05,
"loss": 4.0869,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.989861848066286e-05,
"loss": 4.0885,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.989023253315234e-05,
"loss": 4.0793,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.988184658564182e-05,
"loss": 4.079,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.98734606381313e-05,
"loss": 4.0742,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.986507469062078e-05,
"loss": 4.0831,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.985668874311026e-05,
"loss": 4.0784,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.984830279559974e-05,
"loss": 4.0823,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.983991684808922e-05,
"loss": 4.0903,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.983153090057869e-05,
"loss": 4.0942,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.982314495306817e-05,
"loss": 4.0828,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.981475900555766e-05,
"loss": 4.081,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.980637305804714e-05,
"loss": 4.0803,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.9798019868144084e-05,
"loss": 4.0794,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.9789633920633564e-05,
"loss": 4.0789,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.9781247973123044e-05,
"loss": 4.0663,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.977286202561252e-05,
"loss": 4.09,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.9764476078102e-05,
"loss": 4.0796,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.975609013059148e-05,
"loss": 4.0683,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.974770418308096e-05,
"loss": 4.0727,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.973931823557044e-05,
"loss": 4.0876,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.973093228805992e-05,
"loss": 4.0862,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.97225463405494e-05,
"loss": 4.0845,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971416039303888e-05,
"loss": 4.0779,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.970580720313582e-05,
"loss": 4.0773,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.96974212556253e-05,
"loss": 4.0889,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.968903530811478e-05,
"loss": 4.0665,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.968064936060426e-05,
"loss": 4.067,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.967226341309374e-05,
"loss": 4.0707,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.966387746558322e-05,
"loss": 4.0691,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.96554915180727e-05,
"loss": 4.0801,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.964710557056218e-05,
"loss": 4.0699,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.963871962305166e-05,
"loss": 4.0789,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.963033367554114e-05,
"loss": 4.0736,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.962196410683435e-05,
"loss": 4.0706,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.961357815932383e-05,
"loss": 4.0881,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.960519221181331e-05,
"loss": 4.0741,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.959680626430279e-05,
"loss": 4.0528,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.9588436695596006e-05,
"loss": 4.0823,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.9580067126889215e-05,
"loss": 4.0773,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.9571681179378695e-05,
"loss": 4.0847,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.9563295231868175e-05,
"loss": 4.072,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.9554909284357655e-05,
"loss": 4.067,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.9546523336847135e-05,
"loss": 4.0698,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.9538137389336615e-05,
"loss": 4.0707,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.9529751441826095e-05,
"loss": 4.0752,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.9521365494315575e-05,
"loss": 4.0591,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.9512995925608784e-05,
"loss": 4.0806,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.9504609978098264e-05,
"loss": 4.0725,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.9496224030587744e-05,
"loss": 4.0605,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.948783808307723e-05,
"loss": 4.082,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.947946851437044e-05,
"loss": 4.0604,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.947108256685992e-05,
"loss": 4.0633,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.94626966193494e-05,
"loss": 4.0741,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.945431067183888e-05,
"loss": 4.0797,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.944594110313209e-05,
"loss": 4.0544,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.943755515562157e-05,
"loss": 4.0746,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.942916920811105e-05,
"loss": 4.0525,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.942078326060053e-05,
"loss": 4.0714,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.941239731309e-05,
"loss": 4.0758,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.940401136557948e-05,
"loss": 4.0698,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.939562541806897e-05,
"loss": 4.0747,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.938723947055845e-05,
"loss": 4.0729,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.937885352304793e-05,
"loss": 4.0909,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.9370500333144874e-05,
"loss": 4.0581,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.9362114385634354e-05,
"loss": 4.0765,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.935372843812383e-05,
"loss": 4.0732,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.934534249061331e-05,
"loss": 4.0649,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.933695654310279e-05,
"loss": 4.0722,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.932857059559227e-05,
"loss": 4.0697,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.9320184648081747e-05,
"loss": 4.0739,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.9311798700571227e-05,
"loss": 4.0819,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.9303429131864436e-05,
"loss": 4.0576,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.929504318435392e-05,
"loss": 4.0654,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.92866572368434e-05,
"loss": 4.0663,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.927827128933288e-05,
"loss": 4.0787,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.926990172062609e-05,
"loss": 4.0627,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.926151577311557e-05,
"loss": 4.0703,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.925312982560505e-05,
"loss": 4.0707,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.924474387809453e-05,
"loss": 4.0662,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.923635793058401e-05,
"loss": 4.0633,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.922797198307349e-05,
"loss": 4.0493,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.92196024143667e-05,
"loss": 4.0624,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.921121646685618e-05,
"loss": 4.0662,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.920283051934566e-05,
"loss": 4.0732,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.919444457183514e-05,
"loss": 4.0592,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.918605862432462e-05,
"loss": 4.0561,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.91776726768141e-05,
"loss": 4.0614,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.916928672930359e-05,
"loss": 4.0706,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.916090078179307e-05,
"loss": 4.07,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.915251483428254e-05,
"loss": 4.0643,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.9144145265575756e-05,
"loss": 4.0685,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.9135759318065236e-05,
"loss": 4.0603,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.9127373370554716e-05,
"loss": 4.0591,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.911898742304419e-05,
"loss": 4.0567,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.9110634233141134e-05,
"loss": 4.0563,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.9102248285630614e-05,
"loss": 4.0717,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.9093862338120094e-05,
"loss": 4.0533,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.9085476390609574e-05,
"loss": 4.0644,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.907710682190279e-05,
"loss": 4.0546,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.906872087439227e-05,
"loss": 4.0661,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.906033492688175e-05,
"loss": 4.0596,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.905194897937123e-05,
"loss": 4.0609,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.904356303186071e-05,
"loss": 4.0639,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.903517708435019e-05,
"loss": 4.0744,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.902679113683966e-05,
"loss": 4.0632,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.901842156813288e-05,
"loss": 4.0724,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.901003562062236e-05,
"loss": 4.062,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.900164967311184e-05,
"loss": 4.0615,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.899326372560131e-05,
"loss": 4.0634,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.898487777809079e-05,
"loss": 4.0627,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.897649183058028e-05,
"loss": 4.0546,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.896810588306976e-05,
"loss": 4.0638,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.895973631436297e-05,
"loss": 4.0561,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.895135036685245e-05,
"loss": 4.0659,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.894296441934193e-05,
"loss": 4.0587,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.893457847183141e-05,
"loss": 4.0653,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.8926208903124616e-05,
"loss": 4.0597,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.8917822955614096e-05,
"loss": 4.0692,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.8909437008103576e-05,
"loss": 4.0542,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.8901051060593056e-05,
"loss": 4.0597,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.8892665113082536e-05,
"loss": 4.0375,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.8884279165572016e-05,
"loss": 4.0691,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.8875893218061496e-05,
"loss": 4.0673,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.8867507270550976e-05,
"loss": 4.074,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.885913770184419e-05,
"loss": 4.0578,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.885075175433367e-05,
"loss": 4.0678,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884236580682315e-05,
"loss": 4.0614,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.883397985931263e-05,
"loss": 4.0731,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.882561029060584e-05,
"loss": 4.0509,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.881722434309532e-05,
"loss": 4.0578,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.88088383955848e-05,
"loss": 4.0592,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.880046882687801e-05,
"loss": 4.0673,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.879208287936749e-05,
"loss": 4.0553,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.878369693185697e-05,
"loss": 4.055,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.877531098434645e-05,
"loss": 4.0627,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.876692503683593e-05,
"loss": 4.059,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.8758539089325416e-05,
"loss": 4.0646,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 4.096133232116699,
"eval_runtime": 308.4387,
"eval_samples_per_second": 1237.17,
"eval_steps_per_second": 38.662,
"step": 686880
},
{
"epoch": 1.0,
"learning_rate": 3.8750153141814896e-05,
"loss": 4.0516,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.8741767194304376e-05,
"loss": 4.063,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.8733397625597585e-05,
"loss": 4.056,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.8725028056890794e-05,
"loss": 4.0589,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.8716642109380274e-05,
"loss": 4.0699,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.8708256161869754e-05,
"loss": 4.0582,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.8699886593162963e-05,
"loss": 4.0501,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.869150064565244e-05,
"loss": 4.0483,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.868311469814192e-05,
"loss": 4.0579,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.86747287506314e-05,
"loss": 4.0676,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.866634280312088e-05,
"loss": 4.0573,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.86579732344141e-05,
"loss": 4.0595,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.864958728690358e-05,
"loss": 4.0639,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.864120133939306e-05,
"loss": 4.0539,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.863281539188254e-05,
"loss": 4.0515,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.862442944437202e-05,
"loss": 4.0468,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.86160434968615e-05,
"loss": 4.0588,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.860765754935097e-05,
"loss": 4.0543,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.859927160184045e-05,
"loss": 4.0504,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.859088565432993e-05,
"loss": 4.0627,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.858249970681941e-05,
"loss": 4.0682,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.857411375930889e-05,
"loss": 4.0567,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.856574419060211e-05,
"loss": 4.0551,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.855735824309159e-05,
"loss": 4.0568,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.854897229558107e-05,
"loss": 4.0559,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.854058634807055e-05,
"loss": 4.0535,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.853220040056003e-05,
"loss": 4.0398,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.852381445304951e-05,
"loss": 4.0616,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.851544488434272e-05,
"loss": 4.0587,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.8507058936832197e-05,
"loss": 4.0406,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.8498672989321677e-05,
"loss": 4.0485,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.8490287041811157e-05,
"loss": 4.0556,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.8481901094300636e-05,
"loss": 4.0584,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.8473531525593846e-05,
"loss": 4.0596,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.8465145578083326e-05,
"loss": 4.0561,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.8456759630572805e-05,
"loss": 4.0466,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.8448373683062285e-05,
"loss": 4.0663,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.843998773555177e-05,
"loss": 4.0384,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.843160178804125e-05,
"loss": 4.04,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.842321584053073e-05,
"loss": 4.0434,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.841484627182394e-05,
"loss": 4.0471,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.840646032431342e-05,
"loss": 4.0526,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.83980743768029e-05,
"loss": 4.0457,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.838968842929238e-05,
"loss": 4.0519,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.838130248178186e-05,
"loss": 4.0491,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.8372916534271334e-05,
"loss": 4.0443,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.8364530586760814e-05,
"loss": 4.0567,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.8356144639250294e-05,
"loss": 4.0557,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.834777507054351e-05,
"loss": 4.0277,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.833938912303299e-05,
"loss": 4.054,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.8331019554326206e-05,
"loss": 4.0563,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.8322633606815686e-05,
"loss": 4.061,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.8314264038108895e-05,
"loss": 4.045,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.8305878090598375e-05,
"loss": 4.0431,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.8297492143087855e-05,
"loss": 4.0402,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.8289106195577335e-05,
"loss": 4.0448,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.828072024806681e-05,
"loss": 4.0505,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.827233430055629e-05,
"loss": 4.0343,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.826394835304577e-05,
"loss": 4.0523,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.825556240553525e-05,
"loss": 4.0485,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.824717645802473e-05,
"loss": 4.0383,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.823879051051421e-05,
"loss": 4.051,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.8230404563003694e-05,
"loss": 4.037,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.8222018615493174e-05,
"loss": 4.0396,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.8213632667982654e-05,
"loss": 4.0444,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.8205263099275863e-05,
"loss": 4.0551,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.819689353056907e-05,
"loss": 4.0356,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.818850758305855e-05,
"loss": 4.0484,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.818012163554803e-05,
"loss": 4.0244,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.817173568803751e-05,
"loss": 4.0468,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.816334974052699e-05,
"loss": 4.0484,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.815496379301647e-05,
"loss": 4.0502,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.814657784550595e-05,
"loss": 4.0436,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.813819189799543e-05,
"loss": 4.0489,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.812980595048491e-05,
"loss": 4.0634,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.812145276058186e-05,
"loss": 4.0367,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.811306681307134e-05,
"loss": 4.0515,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.810468086556082e-05,
"loss": 4.042,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.80962949180503e-05,
"loss": 4.0448,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.808790897053978e-05,
"loss": 4.0456,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.807952302302926e-05,
"loss": 4.0423,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.807113707551874e-05,
"loss": 4.0509,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.806275112800822e-05,
"loss": 4.06,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.805436518049769e-05,
"loss": 4.0321,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.8045995611790906e-05,
"loss": 4.0422,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.8037609664280386e-05,
"loss": 4.0397,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.80292400955736e-05,
"loss": 4.0545,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.802085414806308e-05,
"loss": 4.0373,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.801246820055256e-05,
"loss": 4.0503,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.800408225304204e-05,
"loss": 4.0447,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.799569630553152e-05,
"loss": 4.0414,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.7987310358020995e-05,
"loss": 4.0407,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.7978924410510475e-05,
"loss": 4.0281,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.7970538462999955e-05,
"loss": 4.037,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.7962168894293164e-05,
"loss": 4.0439,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.7953782946782644e-05,
"loss": 4.0508,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.7945396999272124e-05,
"loss": 4.0333,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.793702743056534e-05,
"loss": 4.0344,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.792864148305482e-05,
"loss": 4.0379,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.79202555355443e-05,
"loss": 4.0441,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.791186958803378e-05,
"loss": 4.0457,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.790348364052326e-05,
"loss": 4.0384,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.789509769301274e-05,
"loss": 4.0434,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.788671174550222e-05,
"loss": 4.0389,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.78783257979917e-05,
"loss": 4.0389,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.786993985048118e-05,
"loss": 4.0295,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.786158666057812e-05,
"loss": 4.0329,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.78532007130676e-05,
"loss": 4.0438,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.784481476555708e-05,
"loss": 4.0332,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.783642881804656e-05,
"loss": 4.0387,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.782804287053604e-05,
"loss": 4.0292,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.781965692302552e-05,
"loss": 4.0404,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.7811270975515004e-05,
"loss": 4.034,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.7802885028004484e-05,
"loss": 4.0376,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.779451545929769e-05,
"loss": 4.0427,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.778612951178717e-05,
"loss": 4.0536,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.777775994308038e-05,
"loss": 4.0402,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.776937399556986e-05,
"loss": 4.0448,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.776098804805934e-05,
"loss": 4.0417,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.775260210054882e-05,
"loss": 4.0337,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.77442161530383e-05,
"loss": 4.0432,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.773584658433151e-05,
"loss": 4.0323,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.772746063682099e-05,
"loss": 4.0327,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.771907468931047e-05,
"loss": 4.0419,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.771068874179996e-05,
"loss": 4.0369,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.770230279428944e-05,
"loss": 4.0418,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.769393322558265e-05,
"loss": 4.0339,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.7685547278072127e-05,
"loss": 4.0432,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.7677161330561607e-05,
"loss": 4.0317,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.7668775383051087e-05,
"loss": 4.0467,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.7660389435540566e-05,
"loss": 4.0332,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.7652019866833776e-05,
"loss": 4.0344,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.7643633919323256e-05,
"loss": 4.0119,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.7635247971812735e-05,
"loss": 4.0468,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.7626862024302215e-05,
"loss": 4.042,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.7618476076791695e-05,
"loss": 4.0516,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.7610090129281175e-05,
"loss": 4.0355,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.7601704181770655e-05,
"loss": 4.0446,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.7593318234260135e-05,
"loss": 4.0368,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.758494866555335e-05,
"loss": 4.052,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.757656271804283e-05,
"loss": 4.03,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.7568176770532304e-05,
"loss": 4.0335,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.7559790823021784e-05,
"loss": 4.0364,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.7551421254315e-05,
"loss": 4.0436,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.754305168560821e-05,
"loss": 4.0343,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.753466573809769e-05,
"loss": 4.0314,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.752627979058717e-05,
"loss": 4.0365,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.751789384307665e-05,
"loss": 4.0388,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.750950789556613e-05,
"loss": 4.0397,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 4.080237865447998,
"eval_runtime": 301.6388,
"eval_samples_per_second": 1265.059,
"eval_steps_per_second": 39.534,
"step": 763200
},
{
"epoch": 0.0,
"learning_rate": 3.750112194805561e-05,
"loss": 4.0274,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.749273600054509e-05,
"loss": 4.0413,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.748435005303457e-05,
"loss": 4.0358,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.747596410552405e-05,
"loss": 4.036,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.746757815801353e-05,
"loss": 4.0463,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.745919221050301e-05,
"loss": 4.0348,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.745080626299249e-05,
"loss": 4.0324,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.744242031548197e-05,
"loss": 4.0241,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.743403436797145e-05,
"loss": 4.0327,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.742564842046093e-05,
"loss": 4.0401,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.741726247295041e-05,
"loss": 4.0411,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.740887652543989e-05,
"loss": 4.0364,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.74005069567331e-05,
"loss": 4.0413,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.739212100922258e-05,
"loss": 4.0292,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.738373506171206e-05,
"loss": 4.0303,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.7375349114201544e-05,
"loss": 4.0219,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.736696316669102e-05,
"loss": 4.039,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.73585772191805e-05,
"loss": 4.0316,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.735019127166998e-05,
"loss": 4.0295,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.734180532415946e-05,
"loss": 4.0392,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.733341937664894e-05,
"loss": 4.0473,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.732503342913842e-05,
"loss": 4.0341,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.7316663860431626e-05,
"loss": 4.0306,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.7308277912921106e-05,
"loss": 4.0331,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.7299891965410586e-05,
"loss": 4.0332,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.7291506017900066e-05,
"loss": 4.0317,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.7283120070389546e-05,
"loss": 4.0157,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.7274734122879026e-05,
"loss": 4.0359,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.726636455417224e-05,
"loss": 4.0357,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.725797860666172e-05,
"loss": 4.0201,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.72495926591512e-05,
"loss": 4.0262,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.724120671164068e-05,
"loss": 4.0348,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.723283714293389e-05,
"loss": 4.032,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.722445119542337e-05,
"loss": 4.042,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.721606524791285e-05,
"loss": 4.0329,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.720767930040233e-05,
"loss": 4.0257,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.719932611049927e-05,
"loss": 4.0471,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.719094016298875e-05,
"loss": 4.0116,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.7182554215478236e-05,
"loss": 4.0191,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.7174168267967716e-05,
"loss": 4.0245,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.7165782320457196e-05,
"loss": 4.0214,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.7157396372946676e-05,
"loss": 4.0277,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.7149010425436155e-05,
"loss": 4.0265,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.7140624477925635e-05,
"loss": 4.0299,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.7132238530415115e-05,
"loss": 4.0263,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.7123852582904595e-05,
"loss": 4.0216,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.7115466635394075e-05,
"loss": 4.0322,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.710708068788355e-05,
"loss": 4.0322,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.7098711119176764e-05,
"loss": 4.0073,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.7090325171666244e-05,
"loss": 4.0325,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.7081939224155724e-05,
"loss": 4.0318,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.7073553276645204e-05,
"loss": 4.0412,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.7065167329134684e-05,
"loss": 4.0226,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.7056781381624164e-05,
"loss": 4.023,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.7048395434113644e-05,
"loss": 4.0181,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.7040009486603124e-05,
"loss": 4.0187,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.703163991789633e-05,
"loss": 4.0324,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.702327034918955e-05,
"loss": 4.0139,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.701488440167902e-05,
"loss": 4.0288,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.70064984541685e-05,
"loss": 4.0259,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.699812888546172e-05,
"loss": 4.0193,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.69897429379512e-05,
"loss": 4.0268,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.698135699044067e-05,
"loss": 4.0151,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.697297104293016e-05,
"loss": 4.0179,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.696458509541964e-05,
"loss": 4.0223,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.695619914790912e-05,
"loss": 4.0329,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.69478132003986e-05,
"loss": 4.0129,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.693942725288808e-05,
"loss": 4.0275,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.693104130537756e-05,
"loss": 4.005,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.692265535786704e-05,
"loss": 4.0239,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.691426941035652e-05,
"loss": 4.025,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.690589984164973e-05,
"loss": 4.0317,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.689751389413921e-05,
"loss": 4.0232,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.6889127946628687e-05,
"loss": 4.0238,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.6880741999118167e-05,
"loss": 4.0432,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.6872356051607646e-05,
"loss": 4.0158,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.6863986482900856e-05,
"loss": 4.0345,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.685561691419407e-05,
"loss": 4.0176,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.684724734548728e-05,
"loss": 4.0213,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.683886139797676e-05,
"loss": 4.0258,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.683047545046624e-05,
"loss": 4.0182,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.682208950295572e-05,
"loss": 4.0313,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.68137035554452e-05,
"loss": 4.0358,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.680531760793468e-05,
"loss": 4.0183,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.679693166042416e-05,
"loss": 4.0164,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.678854571291364e-05,
"loss": 4.02,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.678015976540312e-05,
"loss": 4.0293,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.67717738178926e-05,
"loss": 4.0177,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.676338787038208e-05,
"loss": 4.0292,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.675500192287156e-05,
"loss": 4.0219,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.6746632354164776e-05,
"loss": 4.0225,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.6738246406654256e-05,
"loss": 4.0181,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.6729860459143736e-05,
"loss": 4.0071,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.6721490890436945e-05,
"loss": 4.0122,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.6713104942926425e-05,
"loss": 4.0253,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.6704718995415905e-05,
"loss": 4.0279,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.6696333047905385e-05,
"loss": 4.0126,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.6687963479198594e-05,
"loss": 4.0109,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.6679577531688074e-05,
"loss": 4.0174,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.6671191584177554e-05,
"loss": 4.0259,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.6662805636667034e-05,
"loss": 4.0274,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.6654419689156514e-05,
"loss": 4.0129,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.6646033741645994e-05,
"loss": 4.0231,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.6637647794135474e-05,
"loss": 4.0163,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.6629261846624954e-05,
"loss": 4.0153,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.6620875899114434e-05,
"loss": 4.0106,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.661250633040764e-05,
"loss": 4.0164,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.660412038289712e-05,
"loss": 4.0188,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.65957344353866e-05,
"loss": 4.0118,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.658734848787608e-05,
"loss": 4.0176,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.657896254036556e-05,
"loss": 4.0116,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.657057659285504e-05,
"loss": 4.0153,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.656219064534452e-05,
"loss": 4.0164,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.6553804697834e-05,
"loss": 4.0147,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.654543512912721e-05,
"loss": 4.0225,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.65370491816167e-05,
"loss": 4.0334,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.652866323410618e-05,
"loss": 4.0227,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.652029366539939e-05,
"loss": 4.0255,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.651190771788887e-05,
"loss": 4.0211,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.650352177037835e-05,
"loss": 4.0129,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.649513582286783e-05,
"loss": 4.0264,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.6486766254161036e-05,
"loss": 4.0092,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.6478380306650516e-05,
"loss": 4.0124,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.6469994359139996e-05,
"loss": 4.0203,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.6461608411629476e-05,
"loss": 4.0165,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.6453222464118956e-05,
"loss": 4.0197,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.6444852895412165e-05,
"loss": 4.018,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.643648332670538e-05,
"loss": 4.0206,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.642809737919486e-05,
"loss": 4.016,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.641971143168434e-05,
"loss": 4.0229,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.641132548417382e-05,
"loss": 4.0175,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.64029395366633e-05,
"loss": 4.0094,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.639455358915278e-05,
"loss": 3.9939,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.638616764164226e-05,
"loss": 4.0272,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.637779807293547e-05,
"loss": 4.0202,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.636941212542495e-05,
"loss": 4.0316,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.636102617791443e-05,
"loss": 4.0174,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.635264023040391e-05,
"loss": 4.0219,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.634425428289339e-05,
"loss": 4.0189,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.633586833538287e-05,
"loss": 4.0331,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.632748238787235e-05,
"loss": 4.0067,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.631909644036183e-05,
"loss": 4.0165,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.6310726871655045e-05,
"loss": 4.0186,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.630234092414452e-05,
"loss": 4.0229,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.6293954976634e-05,
"loss": 4.0127,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.628556902912348e-05,
"loss": 4.0131,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.627718308161296e-05,
"loss": 4.0146,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.626879713410244e-05,
"loss": 4.0243,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.626041118659192e-05,
"loss": 4.0188,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 4.067676067352295,
"eval_runtime": 300.628,
"eval_samples_per_second": 1269.313,
"eval_steps_per_second": 39.667,
"step": 839520
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.328843507789551e+17,
"trial_name": null,
"trial_params": null
}