abhinavp's picture
Training in progress, epoch 0, checkpoint
c625b3a verified
{
"best_metric": 4.007462501525879,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/lstm/4/checkpoints/checkpoint-1984320",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 1984320,
"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": 10.8207,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5526,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0612,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9978,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9523,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.9164,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7353,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6349,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993292879871958e-05,
"loss": 6.5372,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992454285120906e-05,
"loss": 6.4491,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.991615690369854e-05,
"loss": 6.389,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990777095618801e-05,
"loss": 6.3339,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 6.2708,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 6.2072,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 6.159,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 6.1045,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 6.0613,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 6.0227,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.986,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9484,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.9142,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8747,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8528,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.8107,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.793,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 5.7615,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 5.7385,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 5.7165,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6853,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6601,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 5.6473,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 5.6355,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 5.6129,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5888,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 5.5844,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 5.5564,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5426,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.5091,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.5112,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 5.4898,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966467675120532e-05,
"loss": 5.4805,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.96562908036948e-05,
"loss": 5.4686,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964790485618428e-05,
"loss": 5.4613,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 5.4309,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 5.4245,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 5.4194,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 5.4028,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.4054,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 5.3842,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 5.3631,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 5.3727,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 5.3514,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 5.3465,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 5.3189,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 5.3297,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 5.3066,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 5.3341,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 5.2953,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 5.2958,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 5.2888,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 5.2691,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 5.2564,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 5.2567,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 5.2384,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 5.2349,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2508,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 5.232,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 5.2178,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 5.195,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 5.1929,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 5.2004,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1974,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 5.189,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 5.1869,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 5.1788,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 5.1709,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 5.1581,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 5.1483,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 5.1428,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 5.1312,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 5.1383,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 5.1284,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 5.1309,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930422841748654e-05,
"loss": 5.1123,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 5.0928,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 5.1066,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 5.1026,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 5.1002,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 5.0864,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 5.0878,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 5.0741,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 5.0695,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 5.0666,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 5.0613,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 5.0657,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.059,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 5.0564,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 5.0342,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 5.0306,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 5.029,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 5.0287,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 5.0209,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 5.0135,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 5.0041,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 5.0116,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.9868,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9936,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9901,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.9818,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.9765,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.9817,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.9692,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.971,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.9626,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.9535,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.9588,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.9556,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.9494,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.9361,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.9426,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.9439,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.9322,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.9193,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.9288,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.9278,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.9157,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.9097,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.8988,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.9044,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.8949,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.9094,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.8986,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.8797,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888509482999785e-05,
"loss": 4.8879,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.8857,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.8811,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.8845,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.8712,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.873,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.8796,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.8623,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.8601,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.8617,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.8468,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.8461,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.8518,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.8371,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.8392,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.8462,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.8393,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.799422264099121,
"eval_runtime": 295.7715,
"eval_samples_per_second": 1290.155,
"eval_steps_per_second": 40.318,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.8219,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.8218,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872584372131662e-05,
"loss": 4.8371,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.87174577738061e-05,
"loss": 4.8213,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870907182629558e-05,
"loss": 4.832,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870068587878506e-05,
"loss": 4.8041,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869229993127454e-05,
"loss": 4.8236,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683913983764027e-05,
"loss": 4.8059,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.8006,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.8069,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.8087,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.8094,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642000625015155e-05,
"loss": 4.7923,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.791,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.783,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.7842,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.7828,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860008726626628e-05,
"loss": 4.7821,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591701318755764e-05,
"loss": 4.7787,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583315371245244e-05,
"loss": 4.7981,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.7739,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.7823,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.7685,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.7764,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.7643,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.764,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.7594,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.7562,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.7383,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.7541,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.7518,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.7549,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.7442,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.7474,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.7392,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.7355,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.7197,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.7267,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842404788376029e-05,
"loss": 4.7266,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.7228,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.7273,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.7262,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.7139,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.72,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.7204,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365346251186646e-05,
"loss": 4.7064,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8356960303676126e-05,
"loss": 4.7187,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.8348574356165606e-05,
"loss": 4.7039,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.6918,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.7119,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323432892437775e-05,
"loss": 4.6953,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315046944927255e-05,
"loss": 4.6944,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306660997416735e-05,
"loss": 4.6834,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.6934,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.6804,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281519533688904e-05,
"loss": 4.7121,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273133586178384e-05,
"loss": 4.6815,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826474763866787e-05,
"loss": 4.6921,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.6893,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824799212245056e-05,
"loss": 4.6755,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823960617494004e-05,
"loss": 4.6665,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823122022742952e-05,
"loss": 4.6787,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222834279919e-05,
"loss": 4.6655,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.6638,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.6798,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819769281619117e-05,
"loss": 4.6746,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818930686868065e-05,
"loss": 4.6598,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818092092117013e-05,
"loss": 4.6541,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817253497365961e-05,
"loss": 4.6529,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816414902614909e-05,
"loss": 4.6649,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155779457442305e-05,
"loss": 4.6638,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147393509931785e-05,
"loss": 4.662,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.6623,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.662,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122252046203954e-05,
"loss": 4.6613,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113866098693434e-05,
"loss": 4.6441,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.6484,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097094203672393e-05,
"loss": 4.6472,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887246349656e-05,
"loss": 4.6311,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808033868745508e-05,
"loss": 4.6473,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807196911874829e-05,
"loss": 4.6442,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806358317123777e-05,
"loss": 4.6475,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805519722372726e-05,
"loss": 4.6287,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804681127621674e-05,
"loss": 4.6191,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803842532870622e-05,
"loss": 4.6375,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.80300393811957e-05,
"loss": 4.6317,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802165343368518e-05,
"loss": 4.6388,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.6295,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800489791746787e-05,
"loss": 4.632,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799651196995735e-05,
"loss": 4.626,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798812602244683e-05,
"loss": 4.6175,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.79797400749363e-05,
"loss": 4.6234,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.6214,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7962984558718996e-05,
"loss": 4.628,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954598611208476e-05,
"loss": 4.6271,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946212663697956e-05,
"loss": 4.6239,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937826716187436e-05,
"loss": 4.6118,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792947352628438e-05,
"loss": 4.6111,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792108757877386e-05,
"loss": 4.6092,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791270163126334e-05,
"loss": 4.6179,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790433206255655e-05,
"loss": 4.6047,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789594611504603e-05,
"loss": 4.604,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788756016753551e-05,
"loss": 4.5983,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787917422002499e-05,
"loss": 4.6117,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.787078827251447e-05,
"loss": 4.5861,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786240232500395e-05,
"loss": 4.5974,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785401637749343e-05,
"loss": 4.6002,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784563042998291e-05,
"loss": 4.592,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783724448247239e-05,
"loss": 4.5896,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782885853496187e-05,
"loss": 4.6012,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782047258745135e-05,
"loss": 4.5868,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781208663994083e-05,
"loss": 4.5885,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780370069243031e-05,
"loss": 4.595,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779531474491979e-05,
"loss": 4.5808,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778692879740927e-05,
"loss": 4.5913,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777854284989875e-05,
"loss": 4.5959,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777017328119196e-05,
"loss": 4.5871,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776178733368144e-05,
"loss": 4.5757,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775340138617092e-05,
"loss": 4.5863,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7745031817464134e-05,
"loss": 4.5848,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736645869953614e-05,
"loss": 4.575,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728259922443094e-05,
"loss": 4.5728,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719873974932574e-05,
"loss": 4.5759,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771150440622578e-05,
"loss": 4.5863,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770311845871526e-05,
"loss": 4.5743,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769473251120474e-05,
"loss": 4.5702,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768634656369422e-05,
"loss": 4.5606,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767797699498743e-05,
"loss": 4.5676,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766960742628064e-05,
"loss": 4.5603,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766122147877012e-05,
"loss": 4.5779,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.76528355312596e-05,
"loss": 4.5716,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764444958374909e-05,
"loss": 4.5538,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763606363623857e-05,
"loss": 4.5601,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762767768872805e-05,
"loss": 4.5664,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761929174121753e-05,
"loss": 4.5628,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761090579370701e-05,
"loss": 4.5687,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760251984619649e-05,
"loss": 4.5555,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941502774897e-05,
"loss": 4.5572,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758576432997918e-05,
"loss": 4.5652,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757737838246866e-05,
"loss": 4.5521,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7568992434958137e-05,
"loss": 4.5536,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756060648744761e-05,
"loss": 4.5588,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755222053993709e-05,
"loss": 4.5431,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543850971230306e-05,
"loss": 4.5473,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535465023719786e-05,
"loss": 4.554,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527079076209266e-05,
"loss": 4.5381,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518693128698745e-05,
"loss": 4.5445,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510307181188225e-05,
"loss": 4.5499,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501921233677705e-05,
"loss": 4.545,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.51077938079834,
"eval_runtime": 296.1256,
"eval_samples_per_second": 1288.612,
"eval_steps_per_second": 40.27,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493535286167185e-05,
"loss": 4.5317,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485149338656665e-05,
"loss": 4.5335,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476763391146145e-05,
"loss": 4.5516,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468377443635625e-05,
"loss": 4.5319,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7459991496125105e-05,
"loss": 4.5478,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451605548614585e-05,
"loss": 4.5273,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443219601104065e-05,
"loss": 4.5422,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434833653593545e-05,
"loss": 4.5257,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426447706083025e-05,
"loss": 4.5349,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418061758572505e-05,
"loss": 4.5307,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409675811061985e-05,
"loss": 4.5336,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401289863551465e-05,
"loss": 4.5395,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739292029484468e-05,
"loss": 4.5194,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384534347334154e-05,
"loss": 4.5241,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376148399823634e-05,
"loss": 4.5182,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367762452313114e-05,
"loss": 4.5163,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359376504802594e-05,
"loss": 4.5198,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350990557292074e-05,
"loss": 4.5236,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342604609781554e-05,
"loss": 4.5175,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.7334218662271034e-05,
"loss": 4.5393,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325832714760514e-05,
"loss": 4.5188,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731746314605372e-05,
"loss": 4.5246,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73090771985432e-05,
"loss": 4.5168,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730069125103269e-05,
"loss": 4.5255,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729230530352217e-05,
"loss": 4.516,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728391935601165e-05,
"loss": 4.5102,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727553340850113e-05,
"loss": 4.5144,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726714746099061e-05,
"loss": 4.5079,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725876151348009e-05,
"loss": 4.492,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.72503919447733e-05,
"loss": 4.5085,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724200599726278e-05,
"loss": 4.5147,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723362004975226e-05,
"loss": 4.5094,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722523410224174e-05,
"loss": 4.5059,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721686453353495e-05,
"loss": 4.5083,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208494964828156e-05,
"loss": 4.502,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720010901731764e-05,
"loss": 4.4971,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719172306980712e-05,
"loss": 4.4914,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71833371222966e-05,
"loss": 4.491,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717495117478608e-05,
"loss": 4.4923,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716658160607929e-05,
"loss": 4.4927,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715819565856877e-05,
"loss": 4.5006,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714980971105825e-05,
"loss": 4.4996,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714142376354773e-05,
"loss": 4.4878,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713303781603721e-05,
"loss": 4.4938,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124651868526685e-05,
"loss": 4.4986,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116265921016165e-05,
"loss": 4.481,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107879973505645e-05,
"loss": 4.4947,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709951040479886e-05,
"loss": 4.4869,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709112445728834e-05,
"loss": 4.4691,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708273850977782e-05,
"loss": 4.4891,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074368941071037e-05,
"loss": 4.4825,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7065982993560517e-05,
"loss": 4.4762,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705759704604999e-05,
"loss": 4.4726,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704921109853947e-05,
"loss": 4.4774,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040841529832686e-05,
"loss": 4.4642,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703245558232216e-05,
"loss": 4.493,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702406963481164e-05,
"loss": 4.4736,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701568368730112e-05,
"loss": 4.4812,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.70072977397906e-05,
"loss": 4.4824,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699891179228008e-05,
"loss": 4.4666,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699052584476956e-05,
"loss": 4.459,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982139897259045e-05,
"loss": 4.4757,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973753949748525e-05,
"loss": 4.4626,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965384381041734e-05,
"loss": 4.4569,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956998433531214e-05,
"loss": 4.4763,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.6948612486020694e-05,
"loss": 4.4744,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.6940226538510174e-05,
"loss": 4.4593,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931840590999654e-05,
"loss": 4.4525,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.6923454643489134e-05,
"loss": 4.4538,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915068695978614e-05,
"loss": 4.464,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906682748468094e-05,
"loss": 4.4673,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.68983131797613e-05,
"loss": 4.4641,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688992723225078e-05,
"loss": 4.4672,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688154128474026e-05,
"loss": 4.4666,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687315533722974e-05,
"loss": 4.4672,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686480214732669e-05,
"loss": 4.4526,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685641619981617e-05,
"loss": 4.4574,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684803025230565e-05,
"loss": 4.46,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683964430479513e-05,
"loss": 4.4398,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683127473608834e-05,
"loss": 4.4563,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682288878857782e-05,
"loss": 4.4604,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.68145028410673e-05,
"loss": 4.4588,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680611689355678e-05,
"loss": 4.4444,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679773094604626e-05,
"loss": 4.4319,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789361377339466e-05,
"loss": 4.4518,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678097542982895e-05,
"loss": 4.4431,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677258948231843e-05,
"loss": 4.459,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676420353480791e-05,
"loss": 4.4469,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675583396610112e-05,
"loss": 4.4511,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.67474480185906e-05,
"loss": 4.4466,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673906207108008e-05,
"loss": 4.4341,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673067612356956e-05,
"loss": 4.4437,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672229017605904e-05,
"loss": 4.4402,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671390422854852e-05,
"loss": 4.4522,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705518281037995e-05,
"loss": 4.4542,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697132333527474e-05,
"loss": 4.4461,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668877914362442e-05,
"loss": 4.4318,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680393196113906e-05,
"loss": 4.4381,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6672007248603386e-05,
"loss": 4.4364,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663621301092866e-05,
"loss": 4.4444,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655235353582346e-05,
"loss": 4.4318,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664684940607182e-05,
"loss": 4.4352,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.66384634585613e-05,
"loss": 4.4249,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663007751105078e-05,
"loss": 4.4439,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621707942343995e-05,
"loss": 4.4166,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661332199483347e-05,
"loss": 4.4321,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6604952426126684e-05,
"loss": 4.4229,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596566478616164e-05,
"loss": 4.4278,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588180531105644e-05,
"loss": 4.4241,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579794583595124e-05,
"loss": 4.4338,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571408636084604e-05,
"loss": 4.4272,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6563022688574084e-05,
"loss": 4.4203,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554636741063564e-05,
"loss": 4.43,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654626717235677e-05,
"loss": 4.4137,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653788122484625e-05,
"loss": 4.4331,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652949527733573e-05,
"loss": 4.4359,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652110932982521e-05,
"loss": 4.4217,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651272338231469e-05,
"loss": 4.418,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650433743480417e-05,
"loss": 4.4215,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649595148729365e-05,
"loss": 4.4238,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648756553978313e-05,
"loss": 4.4157,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647919597107634e-05,
"loss": 4.4147,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647081002356582e-05,
"loss": 4.4135,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646242407605531e-05,
"loss": 4.4294,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645403812854479e-05,
"loss": 4.4187,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445668559838e-05,
"loss": 4.4136,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643728261232748e-05,
"loss": 4.4039,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428913043620687e-05,
"loss": 4.4146,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420527096110166e-05,
"loss": 4.4041,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412141148599646e-05,
"loss": 4.4242,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403755201089126e-05,
"loss": 4.4192,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395369253578606e-05,
"loss": 4.4064,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6386983306068086e-05,
"loss": 4.4034,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378597358557566e-05,
"loss": 4.4133,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370227789850775e-05,
"loss": 4.4097,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636184184234026e-05,
"loss": 4.4212,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635345589482974e-05,
"loss": 4.4026,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634506994731922e-05,
"loss": 4.4128,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.63366839998087e-05,
"loss": 4.4107,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632829805229818e-05,
"loss": 4.4083,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6319912104787655e-05,
"loss": 4.4065,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311526157277135e-05,
"loss": 4.4099,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630315658857035e-05,
"loss": 4.396,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629477064105983e-05,
"loss": 4.4043,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286384693549304e-05,
"loss": 4.4064,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277998746038784e-05,
"loss": 4.3988,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.6269629177332e-05,
"loss": 4.3956,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626124322982148e-05,
"loss": 4.4035,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625285728231096e-05,
"loss": 4.4018,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.373067855834961,
"eval_runtime": 292.1016,
"eval_samples_per_second": 1306.364,
"eval_steps_per_second": 40.825,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624447133480044e-05,
"loss": 4.3954,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623608538728992e-05,
"loss": 4.3865,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.62276994397794e-05,
"loss": 4.4115,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621932987107261e-05,
"loss": 4.3908,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621094392356209e-05,
"loss": 4.4104,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620255797605157e-05,
"loss": 4.3828,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619417202854105e-05,
"loss": 4.4047,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185818838637994e-05,
"loss": 4.3897,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177432891127474e-05,
"loss": 4.3931,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616906332242068e-05,
"loss": 4.3933,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616067737491017e-05,
"loss": 4.3947,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615229142739965e-05,
"loss": 4.4016,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614392185869286e-05,
"loss": 4.3859,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613553591118234e-05,
"loss": 4.3842,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612714996367182e-05,
"loss": 4.3895,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.61187640161613e-05,
"loss": 4.3743,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611037806865078e-05,
"loss": 4.3866,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610199212114025e-05,
"loss": 4.3878,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609360617362973e-05,
"loss": 4.3805,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608522022611921e-05,
"loss": 4.4037,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607683427860869e-05,
"loss": 4.39,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606844833109817e-05,
"loss": 4.3946,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606006238358765e-05,
"loss": 4.3838,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605167643607714e-05,
"loss": 4.39,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604329048856662e-05,
"loss": 4.3832,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603492091985983e-05,
"loss": 4.3807,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602653497234931e-05,
"loss": 4.3842,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601814902483879e-05,
"loss": 4.3734,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.600976307732827e-05,
"loss": 4.3701,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600137712981775e-05,
"loss": 4.3734,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599299118230723e-05,
"loss": 4.3849,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598460523479671e-05,
"loss": 4.3831,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597621928728619e-05,
"loss": 4.3803,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5967849718579396e-05,
"loss": 4.3835,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.5959480149872605e-05,
"loss": 4.3671,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595109420236209e-05,
"loss": 4.3727,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594270825485157e-05,
"loss": 4.3707,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593432230734105e-05,
"loss": 4.3607,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592593635983053e-05,
"loss": 4.3674,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591755041232001e-05,
"loss": 4.3639,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590916446480949e-05,
"loss": 4.3763,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.59007948961027e-05,
"loss": 4.3753,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589240894859218e-05,
"loss": 4.3667,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588402300108166e-05,
"loss": 4.3648,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587563705357114e-05,
"loss": 4.3778,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867251106060614e-05,
"loss": 4.3575,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858865158550094e-05,
"loss": 4.3723,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.5850479211039573e-05,
"loss": 4.3639,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.5842093263529053e-05,
"loss": 4.3481,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583370731601854e-05,
"loss": 4.371,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582532136850802e-05,
"loss": 4.3605,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581695179980123e-05,
"loss": 4.3595,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580856585229071e-05,
"loss": 4.3477,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580017990478019e-05,
"loss": 4.3573,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579179395726967e-05,
"loss": 4.3479,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578340800975915e-05,
"loss": 4.3675,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577503844105236e-05,
"loss": 4.3558,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576665249354184e-05,
"loss": 4.3603,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575826654603132e-05,
"loss": 4.3636,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.57498805985208e-05,
"loss": 4.3508,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574149465101028e-05,
"loss": 4.3396,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573310870349976e-05,
"loss": 4.3617,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572472275598924e-05,
"loss": 4.3456,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716336808478725e-05,
"loss": 4.3419,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570798361857566e-05,
"loss": 4.3597,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569959767106514e-05,
"loss": 4.3565,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569121172355462e-05,
"loss": 4.3449,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.56828257760441e-05,
"loss": 4.3424,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567443982853358e-05,
"loss": 4.3347,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566605388102306e-05,
"loss": 4.346,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565768431231627e-05,
"loss": 4.3558,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564929836480575e-05,
"loss": 4.3556,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564091241729523e-05,
"loss": 4.3523,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563252646978471e-05,
"loss": 4.349,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562414052227419e-05,
"loss": 4.3614,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561575457476368e-05,
"loss": 4.3392,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560736862725315e-05,
"loss": 4.3488,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559898267974263e-05,
"loss": 4.3458,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.5590629489839576e-05,
"loss": 4.3257,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582243542329056e-05,
"loss": 4.3517,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.5573857594818536e-05,
"loss": 4.3484,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.5565471647308016e-05,
"loss": 4.3457,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.5557085699797496e-05,
"loss": 4.3369,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.5548716131090705e-05,
"loss": 4.3264,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.5540330183580185e-05,
"loss": 4.3413,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.5531944236069665e-05,
"loss": 4.3394,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523558288559145e-05,
"loss": 4.3455,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551518871985236e-05,
"loss": 4.3356,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550680277234184e-05,
"loss": 4.3471,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549841682483132e-05,
"loss": 4.3318,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.54900308773208e-05,
"loss": 4.3323,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.5481644929810274e-05,
"loss": 4.3328,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.5473258982299754e-05,
"loss": 4.3296,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546488941359297e-05,
"loss": 4.3484,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545650346608244e-05,
"loss": 4.3443,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544811751857192e-05,
"loss": 4.3456,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.54397315710614e-05,
"loss": 4.3248,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543134562355088e-05,
"loss": 4.3328,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542295967604037e-05,
"loss": 4.3329,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541459010733358e-05,
"loss": 4.3374,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540620415982306e-05,
"loss": 4.329,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539781821231254e-05,
"loss": 4.3271,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538943226480202e-05,
"loss": 4.3202,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.53810463172915e-05,
"loss": 4.341,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537266036978098e-05,
"loss": 4.312,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536427442227046e-05,
"loss": 4.3272,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535590485356367e-05,
"loss": 4.3229,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534751890605315e-05,
"loss": 4.3255,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533913295854263e-05,
"loss": 4.3215,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533074701103211e-05,
"loss": 4.3354,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532236106352159e-05,
"loss": 4.3241,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531397511601107e-05,
"loss": 4.3164,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530558916850055e-05,
"loss": 4.3315,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297203220990034e-05,
"loss": 4.3158,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528883365228324e-05,
"loss": 4.3296,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528044770477272e-05,
"loss": 4.3363,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.52720617572622e-05,
"loss": 4.3247,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526369218855541e-05,
"loss": 4.3186,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525530624104489e-05,
"loss": 4.3181,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524692029353437e-05,
"loss": 4.3229,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523853434602385e-05,
"loss": 4.3191,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523016477731706e-05,
"loss": 4.3223,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522177882980654e-05,
"loss": 4.3097,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521339288229602e-05,
"loss": 4.3295,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.52050069347855e-05,
"loss": 4.3243,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519662098727499e-05,
"loss": 4.3187,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518823503976446e-05,
"loss": 4.3035,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517986547105768e-05,
"loss": 4.3192,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517147952354716e-05,
"loss": 4.3091,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516309357603663e-05,
"loss": 4.323,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515470762852611e-05,
"loss": 4.3271,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514632168101559e-05,
"loss": 4.316,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513793573350507e-05,
"loss": 4.2994,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512954978599455e-05,
"loss": 4.3174,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512118021728776e-05,
"loss": 4.3128,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511279426977724e-05,
"loss": 4.3282,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104408322266726e-05,
"loss": 4.305,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5096022374756206e-05,
"loss": 4.3181,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087636427245685e-05,
"loss": 4.3173,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079266858538895e-05,
"loss": 4.3189,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070880911028375e-05,
"loss": 4.3126,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062494963517855e-05,
"loss": 4.3143,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.5054109016007334e-05,
"loss": 4.3022,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.5045723068496814e-05,
"loss": 4.3137,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.5037337120986294e-05,
"loss": 4.3108,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5028951173475774e-05,
"loss": 4.3092,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020565225965254e-05,
"loss": 4.3017,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501221203606219e-05,
"loss": 4.3137,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500382608855168e-05,
"loss": 4.307,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.287594318389893,
"eval_runtime": 291.8841,
"eval_samples_per_second": 1307.337,
"eval_steps_per_second": 40.855,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499544014104116e-05,
"loss": 4.2988,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498705419353064e-05,
"loss": 4.2985,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497866824602012e-05,
"loss": 4.3173,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.49702822985096e-05,
"loss": 4.3023,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496189635099908e-05,
"loss": 4.3147,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.495351040348856e-05,
"loss": 4.3015,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494512445597804e-05,
"loss": 4.3081,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493673850846752e-05,
"loss": 4.3027,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492835256095699e-05,
"loss": 4.3009,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.491996661344647e-05,
"loss": 4.3047,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491158066593595e-05,
"loss": 4.3064,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490319471842543e-05,
"loss": 4.3111,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489482514971865e-05,
"loss": 4.2976,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488643920220813e-05,
"loss": 4.2959,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487805325469761e-05,
"loss": 4.2984,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486966730718709e-05,
"loss": 4.2887,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486128135967657e-05,
"loss": 4.2969,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485289541216605e-05,
"loss": 4.3003,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484450946465553e-05,
"loss": 4.2943,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483612351714501e-05,
"loss": 4.3157,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482773756963449e-05,
"loss": 4.3019,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481935162212397e-05,
"loss": 4.3085,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481096567461345e-05,
"loss": 4.2984,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480257972710293e-05,
"loss": 4.3035,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.4794210158396136e-05,
"loss": 4.2944,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.4785824210885616e-05,
"loss": 4.298,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.4777438263375096e-05,
"loss": 4.296,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476906869466831e-05,
"loss": 4.2899,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476068274715779e-05,
"loss": 4.2861,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475229679964727e-05,
"loss": 4.2879,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474391085213675e-05,
"loss": 4.2958,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473554128342996e-05,
"loss": 4.2999,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472715533591944e-05,
"loss": 4.2939,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471876938840892e-05,
"loss": 4.2968,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.47103834408984e-05,
"loss": 4.2845,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470199749338788e-05,
"loss": 4.2892,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469362792468109e-05,
"loss": 4.2882,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468524197717057e-05,
"loss": 4.2752,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467685602966005e-05,
"loss": 4.2882,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466847008214953e-05,
"loss": 4.2789,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466008413463901e-05,
"loss": 4.2933,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465169818712849e-05,
"loss": 4.2925,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464331223961797e-05,
"loss": 4.2857,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463494267091118e-05,
"loss": 4.2797,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462655672340066e-05,
"loss": 4.2974,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461817077589014e-05,
"loss": 4.2761,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460978482837962e-05,
"loss": 4.2911,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.46013988808691e-05,
"loss": 4.2803,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459301293335858e-05,
"loss": 4.2662,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.458464336465179e-05,
"loss": 4.2916,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457625741714127e-05,
"loss": 4.2793,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456787146963075e-05,
"loss": 4.2769,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559485522120234e-05,
"loss": 4.2718,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551099574609714e-05,
"loss": 4.272,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542713627099194e-05,
"loss": 4.273,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534327679588674e-05,
"loss": 4.2815,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4525941732078154e-05,
"loss": 4.2788,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451757216337136e-05,
"loss": 4.2799,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450918621586084e-05,
"loss": 4.2853,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450080026835032e-05,
"loss": 4.2726,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.44924143208398e-05,
"loss": 4.2608,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448404475213301e-05,
"loss": 4.2826,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447565880462249e-05,
"loss": 4.2667,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446727285711197e-05,
"loss": 4.2599,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445888690960145e-05,
"loss": 4.2835,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445050096209093e-05,
"loss": 4.2772,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444211501458041e-05,
"loss": 4.2683,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.44337290670699e-05,
"loss": 4.2661,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442535949836311e-05,
"loss": 4.2544,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441697355085259e-05,
"loss": 4.269,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440858760334207e-05,
"loss": 4.279,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440020165583154e-05,
"loss": 4.2739,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439181570832102e-05,
"loss": 4.2745,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.43834297608105e-05,
"loss": 4.2717,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437504381329998e-05,
"loss": 4.2873,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436665786578946e-05,
"loss": 4.2618,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435828829708267e-05,
"loss": 4.2741,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.434990234957216e-05,
"loss": 4.2715,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434151640206164e-05,
"loss": 4.2452,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333130454551117e-05,
"loss": 4.2806,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4324744507040597e-05,
"loss": 4.2706,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316358559530076e-05,
"loss": 4.2722,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4307972612019556e-05,
"loss": 4.2645,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299586664509036e-05,
"loss": 4.2486,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291217095802245e-05,
"loss": 4.2669,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4282831148291725e-05,
"loss": 4.2634,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274461579584935e-05,
"loss": 4.2726,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266075632074415e-05,
"loss": 4.2594,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257689684563894e-05,
"loss": 4.27,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249303737053374e-05,
"loss": 4.2575,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424093416834659e-05,
"loss": 4.2612,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423254822083607e-05,
"loss": 4.2586,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422417865212928e-05,
"loss": 4.2568,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421579270461876e-05,
"loss": 4.2747,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420740675710824e-05,
"loss": 4.2687,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419902080959772e-05,
"loss": 4.2762,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.41906348620872e-05,
"loss": 4.2491,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418224891457668e-05,
"loss": 4.2597,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417386296706616e-05,
"loss": 4.2591,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416547701955564e-05,
"loss": 4.263,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415710745084885e-05,
"loss": 4.259,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414872150333833e-05,
"loss": 4.2521,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414033555582781e-05,
"loss": 4.2525,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413194960831729e-05,
"loss": 4.2691,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123563660806775e-05,
"loss": 4.2415,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115177713296255e-05,
"loss": 4.254,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106791765785735e-05,
"loss": 4.2493,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098422197078944e-05,
"loss": 4.2585,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.4090036249568424e-05,
"loss": 4.2506,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081650302057904e-05,
"loss": 4.2609,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407326435454738e-05,
"loss": 4.2553,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406487840703686e-05,
"loss": 4.2453,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405649245952634e-05,
"loss": 4.26,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404810651201582e-05,
"loss": 4.2476,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.40397205645053e-05,
"loss": 4.2616,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403136737460224e-05,
"loss": 4.265,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402298142709173e-05,
"loss": 4.2519,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.40145954795812e-05,
"loss": 4.2483,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400620953207068e-05,
"loss": 4.2513,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399782358456016e-05,
"loss": 4.2518,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398943763704964e-05,
"loss": 4.251,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398105168953912e-05,
"loss": 4.252,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397268212083233e-05,
"loss": 4.2419,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396429617332181e-05,
"loss": 4.2608,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395591022581129e-05,
"loss": 4.254,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394752427830077e-05,
"loss": 4.252,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393913833079025e-05,
"loss": 4.2365,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3930768762083466e-05,
"loss": 4.25,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.3922382814572946e-05,
"loss": 4.2408,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3913996867062426e-05,
"loss": 4.2537,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905610919551906e-05,
"loss": 4.2563,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897224972041386e-05,
"loss": 4.2513,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.3888839024530866e-05,
"loss": 4.2307,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.3880469455824075e-05,
"loss": 4.2537,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872083508313555e-05,
"loss": 4.246,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3863697560803035e-05,
"loss": 4.2581,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855311613292515e-05,
"loss": 4.2368,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3846942044585724e-05,
"loss": 4.2542,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.3838556097075204e-05,
"loss": 4.2484,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830170149564684e-05,
"loss": 4.2525,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3821784202054164e-05,
"loss": 4.243,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813398254543644e-05,
"loss": 4.2492,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380501230703313e-05,
"loss": 4.2347,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379662635952261e-05,
"loss": 4.2496,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378824041201209e-05,
"loss": 4.245,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.37798708433053e-05,
"loss": 4.2428,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377148489579478e-05,
"loss": 4.2367,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376311532708799e-05,
"loss": 4.2445,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375472937957747e-05,
"loss": 4.2466,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.229648113250732,
"eval_runtime": 297.36,
"eval_samples_per_second": 1283.263,
"eval_steps_per_second": 40.103,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.374634343206695e-05,
"loss": 4.2409,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.373795748455643e-05,
"loss": 4.232,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.372957153704591e-05,
"loss": 4.251,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.372120196833912e-05,
"loss": 4.2372,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.37128160208286e-05,
"loss": 4.2469,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.3704430073318084e-05,
"loss": 4.2401,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.3696044125807564e-05,
"loss": 4.2412,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368767455710077e-05,
"loss": 4.2407,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367928860959025e-05,
"loss": 4.2369,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367090266207973e-05,
"loss": 4.2391,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366251671456921e-05,
"loss": 4.2449,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.3654130767058686e-05,
"loss": 4.244,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.36457611983519e-05,
"loss": 4.2364,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.363737525084138e-05,
"loss": 4.2318,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.362898930333086e-05,
"loss": 4.2383,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.3620603355820335e-05,
"loss": 4.2203,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.361221740830982e-05,
"loss": 4.235,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.360384783960304e-05,
"loss": 4.2344,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.359546189209251e-05,
"loss": 4.233,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.358707594458199e-05,
"loss": 4.2523,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.357868999707147e-05,
"loss": 4.2413,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.357030404956095e-05,
"loss": 4.2465,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.356191810205043e-05,
"loss": 4.2355,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.355353215453991e-05,
"loss": 4.2404,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.354516258583312e-05,
"loss": 4.2332,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.35367766383226e-05,
"loss": 4.2357,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.352839069081208e-05,
"loss": 4.2312,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.352000474330156e-05,
"loss": 4.2307,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.351161879579104e-05,
"loss": 4.2264,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.350323284828052e-05,
"loss": 4.229,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.3494846900770006e-05,
"loss": 4.233,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.3486460953259486e-05,
"loss": 4.2372,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.3478091384552696e-05,
"loss": 4.2341,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.3469705437042175e-05,
"loss": 4.2388,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.3461335868335385e-05,
"loss": 4.2239,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.3452949920824865e-05,
"loss": 4.2307,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.3444563973314344e-05,
"loss": 4.2255,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.3436178025803824e-05,
"loss": 4.216,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.3427792078293304e-05,
"loss": 4.2302,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.3419406130782784e-05,
"loss": 4.2131,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.3411036562075993e-05,
"loss": 4.2316,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.3402650614565473e-05,
"loss": 4.2321,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.339426466705496e-05,
"loss": 4.2292,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338587871954444e-05,
"loss": 4.2228,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337749277203392e-05,
"loss": 4.2364,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.33691068245234e-05,
"loss": 4.2147,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.336073725581661e-05,
"loss": 4.2352,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.335235130830609e-05,
"loss": 4.2211,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334396536079557e-05,
"loss": 4.2019,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.333557941328505e-05,
"loss": 4.2366,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.332719346577452e-05,
"loss": 4.2191,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.3318807518264e-05,
"loss": 4.2233,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331042157075348e-05,
"loss": 4.2118,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.33020520020467e-05,
"loss": 4.2117,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.329366605453618e-05,
"loss": 4.2183,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.3285296485829394e-05,
"loss": 4.2189,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.3276910538318874e-05,
"loss": 4.2236,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326852459080835e-05,
"loss": 4.2193,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326013864329783e-05,
"loss": 4.2326,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.325175269578731e-05,
"loss": 4.2148,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.324336674827679e-05,
"loss": 4.2045,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.323498080076627e-05,
"loss": 4.2244,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322659485325575e-05,
"loss": 4.2048,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.321820890574523e-05,
"loss": 4.2062,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.3209822958234707e-05,
"loss": 4.2236,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.3201437010724187e-05,
"loss": 4.2227,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.3193051063213666e-05,
"loss": 4.2088,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.3184681494506876e-05,
"loss": 4.211,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.317631192580009e-05,
"loss": 4.1991,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.316792597828957e-05,
"loss": 4.2108,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.315954003077905e-05,
"loss": 4.2214,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.315115408326853e-05,
"loss": 4.2185,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.314278451456174e-05,
"loss": 4.2185,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313439856705122e-05,
"loss": 4.2167,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.31260126195407e-05,
"loss": 4.2311,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311762667203018e-05,
"loss": 4.2065,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310924072451966e-05,
"loss": 4.2196,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310085477700914e-05,
"loss": 4.2152,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.309246882949862e-05,
"loss": 4.1921,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308409926079183e-05,
"loss": 4.2211,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.3075713313281316e-05,
"loss": 4.2163,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.3067327365770796e-05,
"loss": 4.2154,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.3058941418260276e-05,
"loss": 4.2117,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.3050555470749756e-05,
"loss": 4.1984,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.3042169523239236e-05,
"loss": 4.2054,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.303378357572871e-05,
"loss": 4.2089,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.302539762821819e-05,
"loss": 4.2163,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.3017044438315134e-05,
"loss": 4.2038,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.3008658490804614e-05,
"loss": 4.2151,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.3000272543294094e-05,
"loss": 4.2034,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.2991886595783574e-05,
"loss": 4.2083,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.2983500648273054e-05,
"loss": 4.2026,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.297513107956627e-05,
"loss": 4.2041,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.296674513205575e-05,
"loss": 4.2202,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.295835918454523e-05,
"loss": 4.2167,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.294997323703471e-05,
"loss": 4.2207,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294158728952418e-05,
"loss": 4.1942,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293320134201366e-05,
"loss": 4.2078,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.292481539450314e-05,
"loss": 4.2031,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.291642944699262e-05,
"loss": 4.2136,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.290805987828583e-05,
"loss": 4.2041,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.289967393077531e-05,
"loss": 4.205,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289128798326479e-05,
"loss": 4.1963,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288290203575427e-05,
"loss": 4.2117,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.287453246704749e-05,
"loss": 4.1883,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286614651953697e-05,
"loss": 4.2068,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.285777695083018e-05,
"loss": 4.1902,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.2849391003319656e-05,
"loss": 4.2082,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.2841005055809136e-05,
"loss": 4.2011,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.2832619108298616e-05,
"loss": 4.2029,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.2824233160788096e-05,
"loss": 4.2026,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.2815847213277576e-05,
"loss": 4.2006,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.2807461265767056e-05,
"loss": 4.2018,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.2799075318256536e-05,
"loss": 4.1972,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.2790722128353474e-05,
"loss": 4.2049,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.278233618084296e-05,
"loss": 4.2183,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.277396661213618e-05,
"loss": 4.2011,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276558066462566e-05,
"loss": 4.1959,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.275719471711513e-05,
"loss": 4.2015,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.274880876960461e-05,
"loss": 4.2012,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.274042282209409e-05,
"loss": 4.1938,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273203687458357e-05,
"loss": 4.203,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.272365092707305e-05,
"loss": 4.1896,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.271528135836626e-05,
"loss": 4.2076,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.270689541085574e-05,
"loss": 4.206,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.269850946334522e-05,
"loss": 4.199,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.26901235158347e-05,
"loss": 4.1895,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.268173756832418e-05,
"loss": 4.1958,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.267335162081366e-05,
"loss": 4.1941,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.2664965673303146e-05,
"loss": 4.2034,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.2656579725792626e-05,
"loss": 4.2015,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.2648193778282105e-05,
"loss": 4.202,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.2639807830771585e-05,
"loss": 4.1793,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.2631438262064795e-05,
"loss": 4.2026,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.2623052314554274e-05,
"loss": 4.1961,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.2614666367043754e-05,
"loss": 4.2079,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.2606280419533234e-05,
"loss": 4.1873,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.2597910850826443e-05,
"loss": 4.2073,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.2589524903315923e-05,
"loss": 4.1958,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.2581138955805403e-05,
"loss": 4.2036,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.257275300829488e-05,
"loss": 4.1898,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256436706078436e-05,
"loss": 4.2055,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255599749207758e-05,
"loss": 4.18,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254761154456706e-05,
"loss": 4.1979,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253922559705654e-05,
"loss": 4.1965,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253083964954602e-05,
"loss": 4.1881,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252245370203549e-05,
"loss": 4.1935,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251406775452497e-05,
"loss": 4.1908,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250569818581819e-05,
"loss": 4.1988,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 4.188170909881592,
"eval_runtime": 302.2958,
"eval_samples_per_second": 1262.31,
"eval_steps_per_second": 39.448,
"step": 457920
},
{
"epoch": 0.0,
"learning_rate": 4.249731223830766e-05,
"loss": 4.1928,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.248892629079714e-05,
"loss": 4.1818,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.248054034328662e-05,
"loss": 4.1991,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.24721543957761e-05,
"loss": 4.1877,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.246376844826558e-05,
"loss": 4.1985,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.245538250075506e-05,
"loss": 4.1879,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.244699655324455e-05,
"loss": 4.1929,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.243861060573403e-05,
"loss": 4.1932,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.243022465822351e-05,
"loss": 4.1887,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.242183871071299e-05,
"loss": 4.1912,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.241345276320247e-05,
"loss": 4.1943,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.240506681569195e-05,
"loss": 4.1949,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239669724698516e-05,
"loss": 4.1888,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.2388311299474637e-05,
"loss": 4.1838,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.2379925351964117e-05,
"loss": 4.19,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.2371539404453596e-05,
"loss": 4.1708,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.2363153456943076e-05,
"loss": 4.1891,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.235476750943255e-05,
"loss": 4.186,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.234638156192203e-05,
"loss": 4.1834,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.2337995614411516e-05,
"loss": 4.2058,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.2329609666900996e-05,
"loss": 4.1961,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.2321223719390476e-05,
"loss": 4.1984,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.2312837771879956e-05,
"loss": 4.1851,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.2304451824369436e-05,
"loss": 4.1922,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.2296082255662645e-05,
"loss": 4.1877,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.2287696308152125e-05,
"loss": 4.1861,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.2279310360641605e-05,
"loss": 4.1854,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.2270924413131085e-05,
"loss": 4.1861,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.2262554844424294e-05,
"loss": 4.1767,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.2254168896913774e-05,
"loss": 4.1795,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.2245782949403254e-05,
"loss": 4.1822,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.223741338069647e-05,
"loss": 4.1918,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.222902743318595e-05,
"loss": 4.1876,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.222064148567543e-05,
"loss": 4.1924,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.221225553816491e-05,
"loss": 4.1769,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.220386959065439e-05,
"loss": 4.1805,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.21955000219476e-05,
"loss": 4.1829,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.218711407443708e-05,
"loss": 4.1713,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.217872812692656e-05,
"loss": 4.1788,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.217034217941604e-05,
"loss": 4.1723,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.216195623190552e-05,
"loss": 4.1825,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.2153570284395e-05,
"loss": 4.1851,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.214518433688448e-05,
"loss": 4.1818,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.213681476817769e-05,
"loss": 4.1766,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.212842882066717e-05,
"loss": 4.1869,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.212004287315665e-05,
"loss": 4.1732,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.2111656925646134e-05,
"loss": 4.1862,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.2103270978135614e-05,
"loss": 4.1776,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.2094885030625094e-05,
"loss": 4.1546,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.208649908311457e-05,
"loss": 4.1976,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.207811313560405e-05,
"loss": 4.1687,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.206974356689726e-05,
"loss": 4.1801,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.2061357619386736e-05,
"loss": 4.1612,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.2052971671876216e-05,
"loss": 4.1707,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.2044585724365696e-05,
"loss": 4.1653,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.203621615565891e-05,
"loss": 4.1761,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.2027830208148385e-05,
"loss": 4.175,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.201944426063787e-05,
"loss": 4.177,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.201105831312735e-05,
"loss": 4.1866,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.200267236561683e-05,
"loss": 4.1705,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.199430279691004e-05,
"loss": 4.1586,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.198591684939952e-05,
"loss": 4.1842,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.1977530901889e-05,
"loss": 4.1606,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.196914495437848e-05,
"loss": 4.156,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196075900686796e-05,
"loss": 4.1799,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195238943816117e-05,
"loss": 4.1786,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.194400349065065e-05,
"loss": 4.1627,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.193563392194386e-05,
"loss": 4.1715,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.192724797443334e-05,
"loss": 4.155,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.1918862026922826e-05,
"loss": 4.167,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.1910476079412306e-05,
"loss": 4.1763,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.1902090131901786e-05,
"loss": 4.1742,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.1893720563194995e-05,
"loss": 4.1749,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.1885334615684475e-05,
"loss": 4.1738,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.1876948668173955e-05,
"loss": 4.1821,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.1868562720663435e-05,
"loss": 4.161,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.1860176773152915e-05,
"loss": 4.176,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.1851807204446124e-05,
"loss": 4.1659,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.1843421256935604e-05,
"loss": 4.1567,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.1835035309425084e-05,
"loss": 4.1732,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.1826649361914564e-05,
"loss": 4.1761,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.1818263414404044e-05,
"loss": 4.1717,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.1809877466893524e-05,
"loss": 4.1696,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.180149151938301e-05,
"loss": 4.1541,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.179310557187249e-05,
"loss": 4.1591,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.17847360031657e-05,
"loss": 4.1706,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.177636643445891e-05,
"loss": 4.1721,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.176798048694839e-05,
"loss": 4.1624,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.175959453943787e-05,
"loss": 4.1715,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.175120859192735e-05,
"loss": 4.1544,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.174282264441683e-05,
"loss": 4.1682,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.173443669690631e-05,
"loss": 4.1597,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.172605074939579e-05,
"loss": 4.1628,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.171766480188527e-05,
"loss": 4.1746,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.170927885437475e-05,
"loss": 4.1747,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.1700909285667964e-05,
"loss": 4.1774,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.169253971696117e-05,
"loss": 4.1523,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.168415376945065e-05,
"loss": 4.1671,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.167576782194013e-05,
"loss": 4.1577,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.166738187442961e-05,
"loss": 4.1716,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.165899592691909e-05,
"loss": 4.1617,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.165060997940857e-05,
"loss": 4.1657,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.1642224031898046e-05,
"loss": 4.1563,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.1633838084387526e-05,
"loss": 4.1662,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.1625452136877006e-05,
"loss": 4.15,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.161708256817022e-05,
"loss": 4.1632,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.160871299946343e-05,
"loss": 4.1473,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.160032705195292e-05,
"loss": 4.1662,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.159195748324613e-05,
"loss": 4.1571,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.158357153573561e-05,
"loss": 4.161,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.1575185588225087e-05,
"loss": 4.1595,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.1566799640714567e-05,
"loss": 4.1617,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.1558413693204047e-05,
"loss": 4.1605,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.155002774569352e-05,
"loss": 4.1545,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.1541641798183e-05,
"loss": 4.1658,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.153325585067248e-05,
"loss": 4.1734,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.1524886281965695e-05,
"loss": 4.1645,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.151650033445517e-05,
"loss": 4.1576,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.1508114386944655e-05,
"loss": 4.1549,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.1499728439434135e-05,
"loss": 4.1634,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.1491342491923615e-05,
"loss": 4.1536,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.1482956544413095e-05,
"loss": 4.1644,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.1474570596902575e-05,
"loss": 4.1474,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.1466184649392055e-05,
"loss": 4.1676,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.1457815080685264e-05,
"loss": 4.163,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.1449429133174744e-05,
"loss": 4.1591,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.1441043185664224e-05,
"loss": 4.1496,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.1432657238153704e-05,
"loss": 4.1544,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.1424271290643184e-05,
"loss": 4.1516,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.1415885343132664e-05,
"loss": 4.1657,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.1407499395622144e-05,
"loss": 4.1607,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.1399113448111624e-05,
"loss": 4.1596,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.139074387940483e-05,
"loss": 4.1407,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.138237431069805e-05,
"loss": 4.1642,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.137398836318753e-05,
"loss": 4.1549,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.136560241567701e-05,
"loss": 4.1672,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.135721646816649e-05,
"loss": 4.1476,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.134883052065597e-05,
"loss": 4.1642,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.134046095194918e-05,
"loss": 4.1536,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.133207500443866e-05,
"loss": 4.1696,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.132370543573187e-05,
"loss": 4.1505,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.131531948822135e-05,
"loss": 4.1611,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.130693354071083e-05,
"loss": 4.1455,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.129854759320031e-05,
"loss": 4.1583,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.129016164568979e-05,
"loss": 4.1569,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.1281775698179273e-05,
"loss": 4.1461,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.127340612947248e-05,
"loss": 4.1579,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.126502018196196e-05,
"loss": 4.1471,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.125663423445144e-05,
"loss": 4.1617,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 4.156265735626221,
"eval_runtime": 300.6979,
"eval_samples_per_second": 1269.018,
"eval_steps_per_second": 39.658,
"step": 534240
},
{
"epoch": 1.0,
"learning_rate": 4.124824828694092e-05,
"loss": 4.1541,
"step": 534528
},
{
"epoch": 1.0,
"learning_rate": 4.12398623394304e-05,
"loss": 4.142,
"step": 535040
},
{
"epoch": 1.0,
"learning_rate": 4.123147639191988e-05,
"loss": 4.1594,
"step": 535552
},
{
"epoch": 1.0,
"learning_rate": 4.1223090444409356e-05,
"loss": 4.1475,
"step": 536064
},
{
"epoch": 1.0,
"learning_rate": 4.1214704496898835e-05,
"loss": 4.1596,
"step": 536576
},
{
"epoch": 1.0,
"learning_rate": 4.1206318549388315e-05,
"loss": 4.1519,
"step": 537088
},
{
"epoch": 1.0,
"learning_rate": 4.1197932601877795e-05,
"loss": 4.1541,
"step": 537600
},
{
"epoch": 1.0,
"learning_rate": 4.1189546654367275e-05,
"loss": 4.1555,
"step": 538112
},
{
"epoch": 1.0,
"learning_rate": 4.1181160706856755e-05,
"loss": 4.149,
"step": 538624
},
{
"epoch": 1.0,
"learning_rate": 4.117279113814997e-05,
"loss": 4.1544,
"step": 539136
},
{
"epoch": 1.0,
"learning_rate": 4.116440519063945e-05,
"loss": 4.1563,
"step": 539648
},
{
"epoch": 1.0,
"learning_rate": 4.115601924312893e-05,
"loss": 4.157,
"step": 540160
},
{
"epoch": 1.0,
"learning_rate": 4.114764967442214e-05,
"loss": 4.1556,
"step": 540672
},
{
"epoch": 1.0,
"learning_rate": 4.113926372691162e-05,
"loss": 4.1431,
"step": 541184
},
{
"epoch": 1.0,
"learning_rate": 4.11308777794011e-05,
"loss": 4.1458,
"step": 541696
},
{
"epoch": 1.0,
"learning_rate": 4.112249183189058e-05,
"loss": 4.1371,
"step": 542208
},
{
"epoch": 1.0,
"learning_rate": 4.111412226318379e-05,
"loss": 4.1481,
"step": 542720
},
{
"epoch": 1.0,
"learning_rate": 4.110573631567327e-05,
"loss": 4.1514,
"step": 543232
},
{
"epoch": 1.0,
"learning_rate": 4.109735036816275e-05,
"loss": 4.1424,
"step": 543744
},
{
"epoch": 1.0,
"learning_rate": 4.108896442065223e-05,
"loss": 4.1663,
"step": 544256
},
{
"epoch": 1.0,
"learning_rate": 4.108057847314171e-05,
"loss": 4.1585,
"step": 544768
},
{
"epoch": 1.0,
"learning_rate": 4.1072192525631196e-05,
"loss": 4.1607,
"step": 545280
},
{
"epoch": 1.0,
"learning_rate": 4.1063806578120676e-05,
"loss": 4.1487,
"step": 545792
},
{
"epoch": 1.0,
"learning_rate": 4.1055420630610156e-05,
"loss": 4.151,
"step": 546304
},
{
"epoch": 1.0,
"learning_rate": 4.1047051061903365e-05,
"loss": 4.1567,
"step": 546816
},
{
"epoch": 1.0,
"learning_rate": 4.1038665114392845e-05,
"loss": 4.1461,
"step": 547328
},
{
"epoch": 1.0,
"learning_rate": 4.1030279166882325e-05,
"loss": 4.1472,
"step": 547840
},
{
"epoch": 1.0,
"learning_rate": 4.1021893219371805e-05,
"loss": 4.1537,
"step": 548352
},
{
"epoch": 1.0,
"learning_rate": 4.1013523650665014e-05,
"loss": 4.1356,
"step": 548864
},
{
"epoch": 1.0,
"learning_rate": 4.1005137703154494e-05,
"loss": 4.1419,
"step": 549376
},
{
"epoch": 1.01,
"learning_rate": 4.0996751755643974e-05,
"loss": 4.1464,
"step": 549888
},
{
"epoch": 1.01,
"learning_rate": 4.0988365808133454e-05,
"loss": 4.1496,
"step": 550400
},
{
"epoch": 1.01,
"learning_rate": 4.0979979860622933e-05,
"loss": 4.152,
"step": 550912
},
{
"epoch": 1.01,
"learning_rate": 4.0971593913112413e-05,
"loss": 4.153,
"step": 551424
},
{
"epoch": 1.01,
"learning_rate": 4.096320796560189e-05,
"loss": 4.1396,
"step": 551936
},
{
"epoch": 1.01,
"learning_rate": 4.095483839689511e-05,
"loss": 4.1419,
"step": 552448
},
{
"epoch": 1.01,
"learning_rate": 4.094645244938459e-05,
"loss": 4.1481,
"step": 552960
},
{
"epoch": 1.01,
"learning_rate": 4.09380828806778e-05,
"loss": 4.1328,
"step": 553472
},
{
"epoch": 1.01,
"learning_rate": 4.092969693316728e-05,
"loss": 4.1441,
"step": 553984
},
{
"epoch": 1.01,
"learning_rate": 4.092131098565676e-05,
"loss": 4.1329,
"step": 554496
},
{
"epoch": 1.01,
"learning_rate": 4.091292503814624e-05,
"loss": 4.1478,
"step": 555008
},
{
"epoch": 1.01,
"learning_rate": 4.090453909063572e-05,
"loss": 4.1442,
"step": 555520
},
{
"epoch": 1.01,
"learning_rate": 4.089616952192893e-05,
"loss": 4.1447,
"step": 556032
},
{
"epoch": 1.01,
"learning_rate": 4.088778357441841e-05,
"loss": 4.1445,
"step": 556544
},
{
"epoch": 1.01,
"learning_rate": 4.087939762690789e-05,
"loss": 4.1462,
"step": 557056
},
{
"epoch": 1.01,
"learning_rate": 4.087101167939737e-05,
"loss": 4.1387,
"step": 557568
},
{
"epoch": 1.01,
"learning_rate": 4.086262573188685e-05,
"loss": 4.1483,
"step": 558080
},
{
"epoch": 1.01,
"learning_rate": 4.085423978437633e-05,
"loss": 4.14,
"step": 558592
},
{
"epoch": 1.01,
"learning_rate": 4.084585383686581e-05,
"loss": 4.1211,
"step": 559104
},
{
"epoch": 1.01,
"learning_rate": 4.083746788935529e-05,
"loss": 4.1587,
"step": 559616
},
{
"epoch": 1.01,
"learning_rate": 4.082908194184477e-05,
"loss": 4.1326,
"step": 560128
},
{
"epoch": 1.01,
"learning_rate": 4.082069599433425e-05,
"loss": 4.1449,
"step": 560640
},
{
"epoch": 1.01,
"learning_rate": 4.081231004682373e-05,
"loss": 4.1306,
"step": 561152
},
{
"epoch": 1.01,
"learning_rate": 4.080392409931321e-05,
"loss": 4.1323,
"step": 561664
},
{
"epoch": 1.01,
"learning_rate": 4.079553815180269e-05,
"loss": 4.1289,
"step": 562176
},
{
"epoch": 1.01,
"learning_rate": 4.0787184961899625e-05,
"loss": 4.1367,
"step": 562688
},
{
"epoch": 1.01,
"learning_rate": 4.0778799014389105e-05,
"loss": 4.1439,
"step": 563200
},
{
"epoch": 1.01,
"learning_rate": 4.0770413066878585e-05,
"loss": 4.1359,
"step": 563712
},
{
"epoch": 1.01,
"learning_rate": 4.0762027119368065e-05,
"loss": 4.153,
"step": 564224
},
{
"epoch": 1.01,
"learning_rate": 4.075365755066128e-05,
"loss": 4.1401,
"step": 564736
},
{
"epoch": 1.01,
"learning_rate": 4.074527160315076e-05,
"loss": 4.1196,
"step": 565248
},
{
"epoch": 1.01,
"learning_rate": 4.073688565564024e-05,
"loss": 4.1447,
"step": 565760
},
{
"epoch": 1.01,
"learning_rate": 4.072849970812972e-05,
"loss": 4.1272,
"step": 566272
},
{
"epoch": 1.01,
"learning_rate": 4.07201137606192e-05,
"loss": 4.1182,
"step": 566784
},
{
"epoch": 1.01,
"learning_rate": 4.071172781310868e-05,
"loss": 4.1488,
"step": 567296
},
{
"epoch": 1.01,
"learning_rate": 4.070334186559816e-05,
"loss": 4.1412,
"step": 567808
},
{
"epoch": 1.01,
"learning_rate": 4.069497229689137e-05,
"loss": 4.1281,
"step": 568320
},
{
"epoch": 1.01,
"learning_rate": 4.068658634938085e-05,
"loss": 4.137,
"step": 568832
},
{
"epoch": 1.01,
"learning_rate": 4.067820040187033e-05,
"loss": 4.121,
"step": 569344
},
{
"epoch": 1.01,
"learning_rate": 4.066981445435981e-05,
"loss": 4.1321,
"step": 569856
},
{
"epoch": 1.01,
"learning_rate": 4.066142850684929e-05,
"loss": 4.1366,
"step": 570368
},
{
"epoch": 1.01,
"learning_rate": 4.0653058938142505e-05,
"loss": 4.1392,
"step": 570880
},
{
"epoch": 1.01,
"learning_rate": 4.0644672990631985e-05,
"loss": 4.1412,
"step": 571392
},
{
"epoch": 1.01,
"learning_rate": 4.0636287043121465e-05,
"loss": 4.1351,
"step": 571904
},
{
"epoch": 1.01,
"learning_rate": 4.0627901095610945e-05,
"loss": 4.1502,
"step": 572416
},
{
"epoch": 1.01,
"learning_rate": 4.0619515148100425e-05,
"loss": 4.1219,
"step": 572928
},
{
"epoch": 1.01,
"learning_rate": 4.0611129200589905e-05,
"loss": 4.1436,
"step": 573440
},
{
"epoch": 1.01,
"learning_rate": 4.0602759631883114e-05,
"loss": 4.128,
"step": 573952
},
{
"epoch": 1.01,
"learning_rate": 4.0594373684372594e-05,
"loss": 4.1252,
"step": 574464
},
{
"epoch": 1.01,
"learning_rate": 4.0585987736862074e-05,
"loss": 4.1372,
"step": 574976
},
{
"epoch": 1.01,
"learning_rate": 4.0577601789351554e-05,
"loss": 4.1413,
"step": 575488
},
{
"epoch": 1.01,
"learning_rate": 4.056921584184103e-05,
"loss": 4.1368,
"step": 576000
},
{
"epoch": 1.01,
"learning_rate": 4.056082989433051e-05,
"loss": 4.14,
"step": 576512
},
{
"epoch": 1.01,
"learning_rate": 4.055244394681999e-05,
"loss": 4.1162,
"step": 577024
},
{
"epoch": 1.01,
"learning_rate": 4.05440743781132e-05,
"loss": 4.1219,
"step": 577536
},
{
"epoch": 1.01,
"learning_rate": 4.053568843060268e-05,
"loss": 4.1342,
"step": 578048
},
{
"epoch": 1.01,
"learning_rate": 4.052730248309216e-05,
"loss": 4.1391,
"step": 578560
},
{
"epoch": 1.01,
"learning_rate": 4.051891653558164e-05,
"loss": 4.131,
"step": 579072
},
{
"epoch": 1.01,
"learning_rate": 4.051053058807112e-05,
"loss": 4.1362,
"step": 579584
},
{
"epoch": 1.02,
"learning_rate": 4.05021446405606e-05,
"loss": 4.1214,
"step": 580096
},
{
"epoch": 1.02,
"learning_rate": 4.049375869305008e-05,
"loss": 4.1334,
"step": 580608
},
{
"epoch": 1.02,
"learning_rate": 4.048538912434329e-05,
"loss": 4.1266,
"step": 581120
},
{
"epoch": 1.02,
"learning_rate": 4.04770195556365e-05,
"loss": 4.1269,
"step": 581632
},
{
"epoch": 1.02,
"learning_rate": 4.046863360812598e-05,
"loss": 4.14,
"step": 582144
},
{
"epoch": 1.02,
"learning_rate": 4.046024766061546e-05,
"loss": 4.1388,
"step": 582656
},
{
"epoch": 1.02,
"learning_rate": 4.045186171310494e-05,
"loss": 4.1436,
"step": 583168
},
{
"epoch": 1.02,
"learning_rate": 4.044347576559443e-05,
"loss": 4.1219,
"step": 583680
},
{
"epoch": 1.02,
"learning_rate": 4.043508981808391e-05,
"loss": 4.1293,
"step": 584192
},
{
"epoch": 1.02,
"learning_rate": 4.042670387057339e-05,
"loss": 4.1277,
"step": 584704
},
{
"epoch": 1.02,
"learning_rate": 4.041831792306287e-05,
"loss": 4.1335,
"step": 585216
},
{
"epoch": 1.02,
"learning_rate": 4.040993197555235e-05,
"loss": 4.1281,
"step": 585728
},
{
"epoch": 1.02,
"learning_rate": 4.040154602804183e-05,
"loss": 4.1333,
"step": 586240
},
{
"epoch": 1.02,
"learning_rate": 4.039316008053131e-05,
"loss": 4.1226,
"step": 586752
},
{
"epoch": 1.02,
"learning_rate": 4.038477413302079e-05,
"loss": 4.1274,
"step": 587264
},
{
"epoch": 1.02,
"learning_rate": 4.037638818551027e-05,
"loss": 4.1236,
"step": 587776
},
{
"epoch": 1.02,
"learning_rate": 4.036800223799974e-05,
"loss": 4.1262,
"step": 588288
},
{
"epoch": 1.02,
"learning_rate": 4.0359649048096685e-05,
"loss": 4.1126,
"step": 588800
},
{
"epoch": 1.02,
"learning_rate": 4.0351263100586165e-05,
"loss": 4.1342,
"step": 589312
},
{
"epoch": 1.02,
"learning_rate": 4.0342877153075645e-05,
"loss": 4.1266,
"step": 589824
},
{
"epoch": 1.02,
"learning_rate": 4.0334491205565125e-05,
"loss": 4.1267,
"step": 590336
},
{
"epoch": 1.02,
"learning_rate": 4.0326105258054605e-05,
"loss": 4.1249,
"step": 590848
},
{
"epoch": 1.02,
"learning_rate": 4.031771931054409e-05,
"loss": 4.1297,
"step": 591360
},
{
"epoch": 1.02,
"learning_rate": 4.03093497418373e-05,
"loss": 4.1293,
"step": 591872
},
{
"epoch": 1.02,
"learning_rate": 4.030096379432678e-05,
"loss": 4.1211,
"step": 592384
},
{
"epoch": 1.02,
"learning_rate": 4.029257784681626e-05,
"loss": 4.1334,
"step": 592896
},
{
"epoch": 1.02,
"learning_rate": 4.028419189930574e-05,
"loss": 4.1388,
"step": 593408
},
{
"epoch": 1.02,
"learning_rate": 4.027582233059895e-05,
"loss": 4.1258,
"step": 593920
},
{
"epoch": 1.02,
"learning_rate": 4.026743638308843e-05,
"loss": 4.1307,
"step": 594432
},
{
"epoch": 1.02,
"learning_rate": 4.025905043557791e-05,
"loss": 4.1196,
"step": 594944
},
{
"epoch": 1.02,
"learning_rate": 4.025066448806738e-05,
"loss": 4.126,
"step": 595456
},
{
"epoch": 1.02,
"learning_rate": 4.024227854055686e-05,
"loss": 4.1273,
"step": 595968
},
{
"epoch": 1.02,
"learning_rate": 4.023389259304634e-05,
"loss": 4.1278,
"step": 596480
},
{
"epoch": 1.02,
"learning_rate": 4.022550664553583e-05,
"loss": 4.1113,
"step": 596992
},
{
"epoch": 1.02,
"learning_rate": 4.021713707682904e-05,
"loss": 4.133,
"step": 597504
},
{
"epoch": 1.02,
"learning_rate": 4.020875112931852e-05,
"loss": 4.1295,
"step": 598016
},
{
"epoch": 1.02,
"learning_rate": 4.0200365181808e-05,
"loss": 4.1279,
"step": 598528
},
{
"epoch": 1.02,
"learning_rate": 4.019197923429748e-05,
"loss": 4.1165,
"step": 599040
},
{
"epoch": 1.02,
"learning_rate": 4.018359328678696e-05,
"loss": 4.1222,
"step": 599552
},
{
"epoch": 1.02,
"learning_rate": 4.017520733927644e-05,
"loss": 4.1198,
"step": 600064
},
{
"epoch": 1.02,
"learning_rate": 4.016682139176592e-05,
"loss": 4.1314,
"step": 600576
},
{
"epoch": 1.02,
"learning_rate": 4.01584354442554e-05,
"loss": 4.1289,
"step": 601088
},
{
"epoch": 1.02,
"learning_rate": 4.015006587554861e-05,
"loss": 4.1292,
"step": 601600
},
{
"epoch": 1.02,
"learning_rate": 4.014167992803809e-05,
"loss": 4.1078,
"step": 602112
},
{
"epoch": 1.02,
"learning_rate": 4.013329398052757e-05,
"loss": 4.1305,
"step": 602624
},
{
"epoch": 1.02,
"learning_rate": 4.012492441182078e-05,
"loss": 4.1235,
"step": 603136
},
{
"epoch": 1.02,
"learning_rate": 4.011653846431026e-05,
"loss": 4.135,
"step": 603648
},
{
"epoch": 1.02,
"learning_rate": 4.010815251679974e-05,
"loss": 4.1184,
"step": 604160
},
{
"epoch": 1.02,
"learning_rate": 4.009976656928922e-05,
"loss": 4.1281,
"step": 604672
},
{
"epoch": 1.02,
"learning_rate": 4.00913806217787e-05,
"loss": 4.1202,
"step": 605184
},
{
"epoch": 1.02,
"learning_rate": 4.008299467426818e-05,
"loss": 4.1395,
"step": 605696
},
{
"epoch": 1.02,
"learning_rate": 4.007460872675766e-05,
"loss": 4.1195,
"step": 606208
},
{
"epoch": 1.02,
"learning_rate": 4.006622277924714e-05,
"loss": 4.1295,
"step": 606720
},
{
"epoch": 1.02,
"learning_rate": 4.005783683173662e-05,
"loss": 4.119,
"step": 607232
},
{
"epoch": 1.02,
"learning_rate": 4.004946726302983e-05,
"loss": 4.1255,
"step": 607744
},
{
"epoch": 1.02,
"learning_rate": 4.004108131551931e-05,
"loss": 4.1199,
"step": 608256
},
{
"epoch": 1.02,
"learning_rate": 4.003269536800879e-05,
"loss": 4.1181,
"step": 608768
},
{
"epoch": 1.02,
"learning_rate": 4.002430942049827e-05,
"loss": 4.1264,
"step": 609280
},
{
"epoch": 1.02,
"learning_rate": 4.001592347298775e-05,
"loss": 4.111,
"step": 609792
},
{
"epoch": 1.02,
"learning_rate": 4.000755390428097e-05,
"loss": 4.1348,
"step": 610304
},
{
"epoch": 1.03,
"eval_loss": 4.132048606872559,
"eval_runtime": 299.9171,
"eval_samples_per_second": 1272.322,
"eval_steps_per_second": 39.761,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.999916795677045e-05,
"loss": 4.1197,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.999078200925993e-05,
"loss": 4.1127,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.99823960617494e-05,
"loss": 4.1229,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.997401011423888e-05,
"loss": 4.1185,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.996562416672836e-05,
"loss": 4.1296,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.995723821921784e-05,
"loss": 4.1216,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.994885227170732e-05,
"loss": 4.1239,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.99404663241968e-05,
"loss": 4.1227,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.993208037668628e-05,
"loss": 4.1162,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.992369442917576e-05,
"loss": 4.1237,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.991530848166524e-05,
"loss": 4.1222,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.990692253415472e-05,
"loss": 4.1248,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.989855296544793e-05,
"loss": 4.1263,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.9890167017937416e-05,
"loss": 4.1092,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.9881781070426896e-05,
"loss": 4.1194,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.9873395122916376e-05,
"loss": 4.1035,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.9865009175405856e-05,
"loss": 4.1208,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.9856623227895336e-05,
"loss": 4.1181,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.9848237280384816e-05,
"loss": 4.1104,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.983985133287429e-05,
"loss": 4.134,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.9831481764167505e-05,
"loss": 4.1276,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.9823095816656985e-05,
"loss": 4.1293,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.981470986914646e-05,
"loss": 4.1203,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.980632392163594e-05,
"loss": 4.1196,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.979793797412542e-05,
"loss": 4.1263,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.97895520266149e-05,
"loss": 4.1118,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.9781166079104385e-05,
"loss": 4.1151,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.9772780131593865e-05,
"loss": 4.1211,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.9764410562887074e-05,
"loss": 4.1081,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.9756024615376554e-05,
"loss": 4.109,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.9747638667866034e-05,
"loss": 4.1175,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.973926909915924e-05,
"loss": 4.1203,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.973088315164872e-05,
"loss": 4.1151,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.97224972041382e-05,
"loss": 4.1271,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971411125662768e-05,
"loss": 4.1087,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.970574168792089e-05,
"loss": 4.1113,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.969735574041037e-05,
"loss": 4.1162,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.968896979289985e-05,
"loss": 4.1,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.968058384538934e-05,
"loss": 4.1161,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.967219789787882e-05,
"loss": 4.1065,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.96638119503683e-05,
"loss": 4.1124,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.965542600285778e-05,
"loss": 4.1144,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.964704005534726e-05,
"loss": 4.1149,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.963867048664047e-05,
"loss": 4.1172,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.963028453912995e-05,
"loss": 4.1157,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.962189859161943e-05,
"loss": 4.1095,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.961351264410891e-05,
"loss": 4.1133,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.960512669659839e-05,
"loss": 4.1138,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.959674074908787e-05,
"loss": 4.0896,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.958835480157735e-05,
"loss": 4.1245,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.957996885406682e-05,
"loss": 4.1032,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.9571599285360036e-05,
"loss": 4.1171,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.956321333784952e-05,
"loss": 4.1006,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.9554827390339e-05,
"loss": 4.0995,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.9546441442828476e-05,
"loss": 4.1025,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.953808825292542e-05,
"loss": 4.1021,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.95297023054149e-05,
"loss": 4.1157,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.952131635790438e-05,
"loss": 4.102,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.951293041039386e-05,
"loss": 4.1238,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.950456084168707e-05,
"loss": 4.1103,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.949617489417655e-05,
"loss": 4.0882,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.948778894666603e-05,
"loss": 4.1127,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.947940299915551e-05,
"loss": 4.1049,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.947101705164499e-05,
"loss": 4.0896,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.9462647482938206e-05,
"loss": 4.1151,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.9454261535427686e-05,
"loss": 4.1102,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.9445875587917166e-05,
"loss": 4.0989,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.9437489640406646e-05,
"loss": 4.1077,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.9429103692896126e-05,
"loss": 4.0869,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.94207177453856e-05,
"loss": 4.104,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.941233179787508e-05,
"loss": 4.1086,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.9403962229168295e-05,
"loss": 4.1076,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.939557628165777e-05,
"loss": 4.1157,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.938719033414725e-05,
"loss": 4.1033,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.937880438663673e-05,
"loss": 4.1191,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.9370418439126214e-05,
"loss": 4.1008,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.9362032491615694e-05,
"loss": 4.1114,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.9353646544105174e-05,
"loss": 4.0957,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.9345260596594654e-05,
"loss": 4.0967,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.933689102788786e-05,
"loss": 4.109,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.932850508037734e-05,
"loss": 4.1113,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.932011913286682e-05,
"loss": 4.1061,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.93117331853563e-05,
"loss": 4.1116,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.930334723784578e-05,
"loss": 4.0855,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.929496129033526e-05,
"loss": 4.0927,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.928657534282474e-05,
"loss": 4.1072,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.927818939531422e-05,
"loss": 4.1069,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.92698034478037e-05,
"loss": 4.0985,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.926143387909691e-05,
"loss": 4.1049,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.925304793158639e-05,
"loss": 4.0941,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.924466198407588e-05,
"loss": 4.1027,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.923627603656536e-05,
"loss": 4.0958,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.922789008905484e-05,
"loss": 4.0994,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.921952052034805e-05,
"loss": 4.1101,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.921113457283753e-05,
"loss": 4.1104,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.920274862532701e-05,
"loss": 4.1149,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.919437905662022e-05,
"loss": 4.0944,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.91859931091097e-05,
"loss": 4.1013,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.917760716159918e-05,
"loss": 4.0986,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.916922121408866e-05,
"loss": 4.1038,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.916083526657813e-05,
"loss": 4.1006,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.9152449319067617e-05,
"loss": 4.1001,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.914407975036083e-05,
"loss": 4.0999,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.913569380285031e-05,
"loss": 4.0956,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.9127307855339786e-05,
"loss": 4.0957,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.9118921907829266e-05,
"loss": 4.0965,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.911055233912248e-05,
"loss": 4.0872,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.9102166391611955e-05,
"loss": 4.1026,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.9093780444101435e-05,
"loss": 4.0992,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.9085394496590914e-05,
"loss": 4.0939,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.9077008549080394e-05,
"loss": 4.101,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.9068622601569874e-05,
"loss": 4.0965,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.9060236654059354e-05,
"loss": 4.1006,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.9051850706548834e-05,
"loss": 4.0917,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.9043464759038314e-05,
"loss": 4.1085,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.90350788115278e-05,
"loss": 4.1104,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.902669286401728e-05,
"loss": 4.1016,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.901830691650676e-05,
"loss": 4.0994,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.90099537266037e-05,
"loss": 4.0939,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.900156777909318e-05,
"loss": 4.0951,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.899318183158266e-05,
"loss": 4.1019,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.898479588407214e-05,
"loss": 4.1009,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.897640993656162e-05,
"loss": 4.0814,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.89680239890511e-05,
"loss": 4.1079,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.895963804154058e-05,
"loss": 4.101,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.895125209403006e-05,
"loss": 4.1,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.894286614651954e-05,
"loss": 4.0901,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.8934496577812755e-05,
"loss": 4.0928,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.8926110630302235e-05,
"loss": 4.0923,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.8917724682791715e-05,
"loss": 4.1033,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.8909338735281195e-05,
"loss": 4.1009,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.8900969166574404e-05,
"loss": 4.1022,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.8892583219063884e-05,
"loss": 4.0785,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.888421365035709e-05,
"loss": 4.1028,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.887582770284657e-05,
"loss": 4.0966,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.886744175533605e-05,
"loss": 4.1104,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.885905580782553e-05,
"loss": 4.0909,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.885066986031501e-05,
"loss": 4.0949,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884230029160822e-05,
"loss": 4.0979,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.88339143440977e-05,
"loss": 4.1079,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.882552839658719e-05,
"loss": 4.0897,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.88171588278804e-05,
"loss": 4.1027,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.880877288036988e-05,
"loss": 4.0922,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.880038693285936e-05,
"loss": 4.1025,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.879200098534884e-05,
"loss": 4.0901,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.878361503783832e-05,
"loss": 4.087,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.877522909032779e-05,
"loss": 4.0962,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.876684314281727e-05,
"loss": 4.0887,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.875845719530675e-05,
"loss": 4.1044,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 4.112194061279297,
"eval_runtime": 306.7862,
"eval_samples_per_second": 1243.834,
"eval_steps_per_second": 38.871,
"step": 686880
},
{
"epoch": 1.0,
"learning_rate": 3.875007124779623e-05,
"loss": 4.091,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.874168530028571e-05,
"loss": 4.0853,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.873329935277519e-05,
"loss": 4.0954,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.8724929784068406e-05,
"loss": 4.0917,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.8716543836557886e-05,
"loss": 4.1044,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.8708157889047366e-05,
"loss": 4.0939,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.8699771941536846e-05,
"loss": 4.0906,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.8691385994026326e-05,
"loss": 4.1002,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.8683016425319535e-05,
"loss": 4.0896,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.8674630477809015e-05,
"loss": 4.0957,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.8666244530298495e-05,
"loss": 4.0987,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.8657858582787975e-05,
"loss": 4.0988,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.8649489014081184e-05,
"loss": 4.099,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.8641103066570664e-05,
"loss": 4.0843,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.8632717119060144e-05,
"loss": 4.0891,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.8624331171549624e-05,
"loss": 4.075,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.861594522403911e-05,
"loss": 4.0928,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.860755927652859e-05,
"loss": 4.0949,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.859920608662553e-05,
"loss": 4.0808,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.859082013911501e-05,
"loss": 4.1058,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.858243419160449e-05,
"loss": 4.1006,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.857404824409397e-05,
"loss": 4.0988,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.856566229658345e-05,
"loss": 4.096,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.855727634907293e-05,
"loss": 4.0952,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.854889040156241e-05,
"loss": 4.0978,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.854050445405189e-05,
"loss": 4.0936,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.853211850654137e-05,
"loss": 4.0819,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.852373255903085e-05,
"loss": 4.0964,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.851534661152033e-05,
"loss": 4.0801,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.850696066400981e-05,
"loss": 4.0864,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.849857471649929e-05,
"loss": 4.0914,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.8490205147792504e-05,
"loss": 4.094,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.848181920028198e-05,
"loss": 4.0884,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.847343325277146e-05,
"loss": 4.0997,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.846504730526094e-05,
"loss": 4.0863,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.845667773655415e-05,
"loss": 4.0827,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.8448291789043626e-05,
"loss": 4.0945,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.8439905841533106e-05,
"loss": 4.0728,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.8431519894022586e-05,
"loss": 4.0869,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.8423133946512066e-05,
"loss": 4.0874,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.8414747999001546e-05,
"loss": 4.084,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.840637843029476e-05,
"loss": 4.0878,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.839799248278424e-05,
"loss": 4.0892,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.838960653527372e-05,
"loss": 4.0889,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.83812205877632e-05,
"loss": 4.0894,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.837283464025268e-05,
"loss": 4.0832,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.836444869274216e-05,
"loss": 4.088,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.835606274523164e-05,
"loss": 4.0898,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.834767679772112e-05,
"loss": 4.0667,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.833930722901433e-05,
"loss": 4.0971,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.833092128150381e-05,
"loss": 4.0805,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.832253533399329e-05,
"loss": 4.0862,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.831414938648277e-05,
"loss": 4.0751,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.8305779817775986e-05,
"loss": 4.0751,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.8297393870265466e-05,
"loss": 4.0777,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.8289024301558675e-05,
"loss": 4.0788,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.8280638354048155e-05,
"loss": 4.0919,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.8272252406537635e-05,
"loss": 4.0771,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.8263866459027115e-05,
"loss": 4.0987,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.8255480511516595e-05,
"loss": 4.0886,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.8247094564006075e-05,
"loss": 4.0609,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.8238724995299284e-05,
"loss": 4.0839,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.8230339047788764e-05,
"loss": 4.0751,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.8221953100278244e-05,
"loss": 4.0715,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.8213567152767724e-05,
"loss": 4.087,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.8205181205257204e-05,
"loss": 4.0843,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.8196795257746684e-05,
"loss": 4.0748,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.81884256890399e-05,
"loss": 4.085,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.818003974152938e-05,
"loss": 4.0648,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.817165379401886e-05,
"loss": 4.0711,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.816326784650834e-05,
"loss": 4.0836,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.815488189899781e-05,
"loss": 4.0829,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.814651233029103e-05,
"loss": 4.0892,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.813812638278051e-05,
"loss": 4.0777,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.812974043526999e-05,
"loss": 4.0955,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.812135448775946e-05,
"loss": 4.075,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.811296854024894e-05,
"loss": 4.0913,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.810458259273842e-05,
"loss": 4.0706,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.80961966452279e-05,
"loss": 4.0744,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.808782707652112e-05,
"loss": 4.0809,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.80794411290106e-05,
"loss": 4.0887,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.807105518150008e-05,
"loss": 4.0818,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.806266923398956e-05,
"loss": 4.0877,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.805428328647904e-05,
"loss": 4.062,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.804591371777225e-05,
"loss": 4.0649,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.8037527770261727e-05,
"loss": 4.0843,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.8029141822751207e-05,
"loss": 4.0809,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.8020755875240687e-05,
"loss": 4.0757,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.8012369927730166e-05,
"loss": 4.0817,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.8003983980219646e-05,
"loss": 4.0766,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.7995598032709126e-05,
"loss": 4.0744,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.7987212085198606e-05,
"loss": 4.0736,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.797884251649182e-05,
"loss": 4.0732,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.79704565689813e-05,
"loss": 4.0867,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.796207062147078e-05,
"loss": 4.0881,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.795370105276399e-05,
"loss": 4.0888,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.794531510525347e-05,
"loss": 4.0681,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.793692915774295e-05,
"loss": 4.0776,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.792854321023243e-05,
"loss": 4.0756,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.792015726272191e-05,
"loss": 4.0807,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.791177131521139e-05,
"loss": 4.0796,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.790338536770087e-05,
"loss": 4.0738,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.789499942019035e-05,
"loss": 4.0764,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.788662985148356e-05,
"loss": 4.0691,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.787824390397304e-05,
"loss": 4.0734,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.786985795646253e-05,
"loss": 4.0727,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.7861472008952e-05,
"loss": 4.065,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.785308606144148e-05,
"loss": 4.0774,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.784470011393096e-05,
"loss": 4.0757,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.7836330545224176e-05,
"loss": 4.0719,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.782794459771365e-05,
"loss": 4.0742,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.781955865020313e-05,
"loss": 4.0743,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.781117270269261e-05,
"loss": 4.0785,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.7802803133985825e-05,
"loss": 4.0676,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.77944171864753e-05,
"loss": 4.0836,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.778603123896478e-05,
"loss": 4.0838,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.7777645291454264e-05,
"loss": 4.0796,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.7769259343943744e-05,
"loss": 4.0761,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.7760873396433224e-05,
"loss": 4.0729,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.7752503827726433e-05,
"loss": 4.0698,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.7744117880215913e-05,
"loss": 4.0797,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.7735731932705393e-05,
"loss": 4.0731,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.772734598519487e-05,
"loss": 4.0612,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.771897641648808e-05,
"loss": 4.0851,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.771059046897756e-05,
"loss": 4.0788,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.770222090027077e-05,
"loss": 4.0756,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.769383495276025e-05,
"loss": 4.0674,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.768544900524973e-05,
"loss": 4.0672,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.767706305773921e-05,
"loss": 4.0692,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.76686771102287e-05,
"loss": 4.0811,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.766029116271818e-05,
"loss": 4.0781,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.765190521520766e-05,
"loss": 4.0814,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.764351926769714e-05,
"loss": 4.0537,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.763513332018662e-05,
"loss": 4.085,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.76267473726761e-05,
"loss": 4.0709,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.761836142516558e-05,
"loss": 4.0845,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.760997547765506e-05,
"loss": 4.0709,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.760158953014454e-05,
"loss": 4.0677,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.759321996143775e-05,
"loss": 4.0752,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.758483401392723e-05,
"loss": 4.087,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.757644806641671e-05,
"loss": 4.0674,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.756806211890618e-05,
"loss": 4.0792,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.755967617139567e-05,
"loss": 4.0688,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.755130660268888e-05,
"loss": 4.0772,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.754292065517836e-05,
"loss": 4.0669,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.7534534707667836e-05,
"loss": 4.067,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.7526148760157316e-05,
"loss": 4.0757,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.7517762812646796e-05,
"loss": 4.0663,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.7509376865136276e-05,
"loss": 4.0846,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 4.096063613891602,
"eval_runtime": 319.5353,
"eval_samples_per_second": 1194.206,
"eval_steps_per_second": 37.32,
"step": 763200
},
{
"epoch": 0.0,
"learning_rate": 3.7501007296429485e-05,
"loss": 4.0681,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.7492621348918965e-05,
"loss": 4.0622,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.7484235401408445e-05,
"loss": 4.0738,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.7475849453897924e-05,
"loss": 4.0704,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.7467463506387404e-05,
"loss": 4.0807,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.7459077558876884e-05,
"loss": 4.0716,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.7450691611366364e-05,
"loss": 4.0685,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.744230566385585e-05,
"loss": 4.0789,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.743391971634533e-05,
"loss": 4.0664,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.742553376883481e-05,
"loss": 4.0664,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.741714782132429e-05,
"loss": 4.078,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.740876187381377e-05,
"loss": 4.0745,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.740039230510698e-05,
"loss": 4.0782,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.739200635759646e-05,
"loss": 4.06,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.738362041008594e-05,
"loss": 4.066,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.737523446257542e-05,
"loss": 4.0517,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.73668485150649e-05,
"loss": 4.0724,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.735846256755437e-05,
"loss": 4.0762,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.735007662004385e-05,
"loss": 4.0554,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.734169067253333e-05,
"loss": 4.0833,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.733330472502282e-05,
"loss": 4.0802,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.73249187775123e-05,
"loss": 4.077,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.731653283000178e-05,
"loss": 4.0738,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.730816326129499e-05,
"loss": 4.0724,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.729977731378447e-05,
"loss": 4.0735,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.729139136627395e-05,
"loss": 4.0696,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.728300541876343e-05,
"loss": 4.0612,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.727461947125291e-05,
"loss": 4.0752,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.726623352374239e-05,
"loss": 4.0593,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.725784757623187e-05,
"loss": 4.0597,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.724946162872135e-05,
"loss": 4.0709,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.724109206001456e-05,
"loss": 4.0677,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.723270611250404e-05,
"loss": 4.07,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.722432016499352e-05,
"loss": 4.0747,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.7215934217483e-05,
"loss": 4.0599,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.720756464877621e-05,
"loss": 4.0654,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.719917870126569e-05,
"loss": 4.0684,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.719079275375517e-05,
"loss": 4.051,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.718240680624465e-05,
"loss": 4.0649,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.717402085873413e-05,
"loss": 4.0656,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.716563491122361e-05,
"loss": 4.0584,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.7157248963713086e-05,
"loss": 4.0681,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.7148863016202566e-05,
"loss": 4.0721,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.714049344749578e-05,
"loss": 4.0635,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.713210749998526e-05,
"loss": 4.0673,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.712373793127847e-05,
"loss": 4.0604,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.711535198376795e-05,
"loss": 4.0674,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.710696603625744e-05,
"loss": 4.0644,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.709858008874691e-05,
"loss": 4.0474,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.709019414123639e-05,
"loss": 4.0719,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.708180819372587e-05,
"loss": 4.0583,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.707342224621535e-05,
"loss": 4.0669,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.706503629870483e-05,
"loss": 4.0548,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.705665035119431e-05,
"loss": 4.0509,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.704828078248752e-05,
"loss": 4.0531,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.7039894834977e-05,
"loss": 4.0546,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.703150888746648e-05,
"loss": 4.0743,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.702313931875969e-05,
"loss": 4.053,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.7014753371249176e-05,
"loss": 4.0774,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.7006367423738655e-05,
"loss": 4.0688,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.6997981476228135e-05,
"loss": 4.0421,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.6989595528717615e-05,
"loss": 4.0649,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.6981209581207095e-05,
"loss": 4.0548,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.6972823633696575e-05,
"loss": 4.0475,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.6964454064989784e-05,
"loss": 4.0626,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.6956068117479264e-05,
"loss": 4.0643,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.6947682169968744e-05,
"loss": 4.0523,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.6939296222458224e-05,
"loss": 4.0644,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.6930910274947704e-05,
"loss": 4.044,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.6922524327437184e-05,
"loss": 4.0546,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.6914138379926664e-05,
"loss": 4.06,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.6905752432416144e-05,
"loss": 4.0663,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.689738286370936e-05,
"loss": 4.0632,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.688899691619884e-05,
"loss": 4.0589,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.688061096868832e-05,
"loss": 4.0738,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.68722250211778e-05,
"loss": 4.0554,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.686385545247101e-05,
"loss": 4.0689,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.685546950496049e-05,
"loss": 4.048,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.68470999362537e-05,
"loss": 4.0543,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.683871398874318e-05,
"loss": 4.0591,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.683032804123266e-05,
"loss": 4.0619,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.682194209372214e-05,
"loss": 4.0627,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.681355614621162e-05,
"loss": 4.0668,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.680518657750483e-05,
"loss": 4.048,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.679680062999431e-05,
"loss": 4.0409,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.6788414682483794e-05,
"loss": 4.0639,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.6780028734973274e-05,
"loss": 4.0606,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.677164278746275e-05,
"loss": 4.0539,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.676325683995223e-05,
"loss": 4.0626,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.675487089244171e-05,
"loss": 4.0567,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.6746484944931187e-05,
"loss": 4.0524,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.6738115376224396e-05,
"loss": 4.0559,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.6729729428713876e-05,
"loss": 4.0519,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.6721343481203356e-05,
"loss": 4.0663,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.6712957533692836e-05,
"loss": 4.0662,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.6704571586182315e-05,
"loss": 4.0684,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.6696185638671795e-05,
"loss": 4.0465,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.668783244876875e-05,
"loss": 4.0554,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.667944650125822e-05,
"loss": 4.0566,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.66710605537477e-05,
"loss": 4.0561,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.666267460623718e-05,
"loss": 4.0603,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.665428865872666e-05,
"loss": 4.0517,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.664590271121614e-05,
"loss": 4.0584,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.663751676370562e-05,
"loss": 4.0462,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.66291308161951e-05,
"loss": 4.0534,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.662076124748831e-05,
"loss": 4.0507,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.661239167878152e-05,
"loss": 4.0487,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.6604005731271e-05,
"loss": 4.0578,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.6595619783760485e-05,
"loss": 4.0526,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.6587250215053694e-05,
"loss": 4.0501,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.6578864267543174e-05,
"loss": 4.0554,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.6570478320032654e-05,
"loss": 4.0489,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.6562092372522134e-05,
"loss": 4.0577,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.6553706425011614e-05,
"loss": 4.0523,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.6545320477501094e-05,
"loss": 4.0589,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.6536934529990574e-05,
"loss": 4.0673,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.6528548582480054e-05,
"loss": 4.0576,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.6520162634969534e-05,
"loss": 4.0535,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.651179306626274e-05,
"loss": 4.0556,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.650340711875222e-05,
"loss": 4.0491,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.64950211712417e-05,
"loss": 4.0622,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.648663522373118e-05,
"loss": 4.052,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.647824927622067e-05,
"loss": 4.0438,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.646987970751388e-05,
"loss": 4.0626,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.646149376000336e-05,
"loss": 4.0598,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.645310781249284e-05,
"loss": 4.0565,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.644472186498232e-05,
"loss": 4.0452,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.643635229627553e-05,
"loss": 4.0482,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.642796634876501e-05,
"loss": 4.0439,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.641958040125449e-05,
"loss": 4.0629,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.641119445374397e-05,
"loss": 4.0565,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.640280850623345e-05,
"loss": 4.0605,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.639442255872293e-05,
"loss": 4.0322,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.6386052990016136e-05,
"loss": 4.0671,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.637766704250562e-05,
"loss": 4.0487,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.63692810949951e-05,
"loss": 4.0694,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.636089514748458e-05,
"loss": 4.0469,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.6352509199974056e-05,
"loss": 4.0481,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.634413963126727e-05,
"loss": 4.0519,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.633575368375675e-05,
"loss": 4.0709,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.6327367736246225e-05,
"loss": 4.0455,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.6318981788735705e-05,
"loss": 4.0622,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.6310595841225185e-05,
"loss": 4.0464,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.6302209893714665e-05,
"loss": 4.0582,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.6293840325007874e-05,
"loss": 4.0475,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.628545437749736e-05,
"loss": 4.0511,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.627708480879058e-05,
"loss": 4.053,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.626869886128006e-05,
"loss": 4.0459,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.626031291376953e-05,
"loss": 4.0615,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 4.082852840423584,
"eval_runtime": 328.4034,
"eval_samples_per_second": 1161.958,
"eval_steps_per_second": 36.312,
"step": 839520
},
{
"epoch": 1.0,
"learning_rate": 3.625192696625901e-05,
"loss": 4.0502,
"step": 839680
},
{
"epoch": 1.0,
"learning_rate": 3.624354101874849e-05,
"loss": 4.0424,
"step": 840192
},
{
"epoch": 1.0,
"learning_rate": 3.623515507123797e-05,
"loss": 4.0545,
"step": 840704
},
{
"epoch": 1.0,
"learning_rate": 3.622676912372745e-05,
"loss": 4.0481,
"step": 841216
},
{
"epoch": 1.0,
"learning_rate": 3.621838317621693e-05,
"loss": 4.0637,
"step": 841728
},
{
"epoch": 1.0,
"learning_rate": 3.620999722870641e-05,
"loss": 4.053,
"step": 842240
},
{
"epoch": 1.0,
"learning_rate": 3.620161128119589e-05,
"loss": 4.0505,
"step": 842752
},
{
"epoch": 1.0,
"learning_rate": 3.619322533368537e-05,
"loss": 4.0567,
"step": 843264
},
{
"epoch": 1.0,
"learning_rate": 3.618485576497858e-05,
"loss": 4.0477,
"step": 843776
},
{
"epoch": 1.0,
"learning_rate": 3.6176486196271795e-05,
"loss": 4.0456,
"step": 844288
},
{
"epoch": 1.0,
"learning_rate": 3.6168100248761275e-05,
"loss": 4.0632,
"step": 844800
},
{
"epoch": 1.0,
"learning_rate": 3.6159714301250754e-05,
"loss": 4.0517,
"step": 845312
},
{
"epoch": 1.0,
"learning_rate": 3.6151328353740234e-05,
"loss": 4.0624,
"step": 845824
},
{
"epoch": 1.0,
"learning_rate": 3.6142942406229714e-05,
"loss": 4.0404,
"step": 846336
},
{
"epoch": 1.0,
"learning_rate": 3.6134556458719194e-05,
"loss": 4.0411,
"step": 846848
},
{
"epoch": 1.0,
"learning_rate": 3.6126170511208674e-05,
"loss": 4.0374,
"step": 847360
},
{
"epoch": 1.0,
"learning_rate": 3.611780094250188e-05,
"loss": 4.0532,
"step": 847872
},
{
"epoch": 1.0,
"learning_rate": 3.610941499499136e-05,
"loss": 4.0496,
"step": 848384
},
{
"epoch": 1.0,
"learning_rate": 3.610102904748084e-05,
"loss": 4.0425,
"step": 848896
},
{
"epoch": 1.0,
"learning_rate": 3.609264309997032e-05,
"loss": 4.0559,
"step": 849408
},
{
"epoch": 1.0,
"learning_rate": 3.60842571524598e-05,
"loss": 4.0679,
"step": 849920
},
{
"epoch": 1.0,
"learning_rate": 3.607587120494928e-05,
"loss": 4.0549,
"step": 850432
},
{
"epoch": 1.0,
"learning_rate": 3.606748525743876e-05,
"loss": 4.0536,
"step": 850944
},
{
"epoch": 1.0,
"learning_rate": 3.605909930992824e-05,
"loss": 4.0541,
"step": 851456
},
{
"epoch": 1.0,
"learning_rate": 3.605071336241772e-05,
"loss": 4.057,
"step": 851968
},
{
"epoch": 1.0,
"learning_rate": 3.60423274149072e-05,
"loss": 4.0503,
"step": 852480
},
{
"epoch": 1.0,
"learning_rate": 3.603395784620042e-05,
"loss": 4.0419,
"step": 852992
},
{
"epoch": 1.0,
"learning_rate": 3.602557189868989e-05,
"loss": 4.0538,
"step": 853504
},
{
"epoch": 1.0,
"learning_rate": 3.601718595117937e-05,
"loss": 4.0396,
"step": 854016
},
{
"epoch": 1.0,
"learning_rate": 3.600881638247259e-05,
"loss": 4.0404,
"step": 854528
},
{
"epoch": 1.01,
"learning_rate": 3.600043043496206e-05,
"loss": 4.052,
"step": 855040
},
{
"epoch": 1.01,
"learning_rate": 3.599204448745154e-05,
"loss": 4.0466,
"step": 855552
},
{
"epoch": 1.01,
"learning_rate": 3.598365853994102e-05,
"loss": 4.0538,
"step": 856064
},
{
"epoch": 1.01,
"learning_rate": 3.597528897123424e-05,
"loss": 4.0553,
"step": 856576
},
{
"epoch": 1.01,
"learning_rate": 3.596690302372372e-05,
"loss": 4.0415,
"step": 857088
},
{
"epoch": 1.01,
"learning_rate": 3.59585170762132e-05,
"loss": 4.0492,
"step": 857600
},
{
"epoch": 1.01,
"learning_rate": 3.595013112870268e-05,
"loss": 4.0474,
"step": 858112
},
{
"epoch": 1.01,
"learning_rate": 3.594174518119216e-05,
"loss": 4.0328,
"step": 858624
},
{
"epoch": 1.01,
"learning_rate": 3.5933359233681637e-05,
"loss": 4.0491,
"step": 859136
},
{
"epoch": 1.01,
"learning_rate": 3.5924973286171117e-05,
"loss": 4.0408,
"step": 859648
},
{
"epoch": 1.01,
"learning_rate": 3.5916587338660597e-05,
"loss": 4.0418,
"step": 860160
},
{
"epoch": 1.01,
"learning_rate": 3.5908201391150076e-05,
"loss": 4.0473,
"step": 860672
},
{
"epoch": 1.01,
"learning_rate": 3.5899815443639556e-05,
"loss": 4.0574,
"step": 861184
},
{
"epoch": 1.01,
"learning_rate": 3.5891429496129036e-05,
"loss": 4.0397,
"step": 861696
},
{
"epoch": 1.01,
"learning_rate": 3.5883043548618516e-05,
"loss": 4.0503,
"step": 862208
},
{
"epoch": 1.01,
"learning_rate": 3.5874673979911725e-05,
"loss": 4.045,
"step": 862720
},
{
"epoch": 1.01,
"learning_rate": 3.5866288032401205e-05,
"loss": 4.0434,
"step": 863232
},
{
"epoch": 1.01,
"learning_rate": 3.5857918463694414e-05,
"loss": 4.0471,
"step": 863744
},
{
"epoch": 1.01,
"learning_rate": 3.58495325161839e-05,
"loss": 4.0293,
"step": 864256
},
{
"epoch": 1.01,
"learning_rate": 3.584114656867338e-05,
"loss": 4.0495,
"step": 864768
},
{
"epoch": 1.01,
"learning_rate": 3.583276062116286e-05,
"loss": 4.0432,
"step": 865280
},
{
"epoch": 1.01,
"learning_rate": 3.582437467365234e-05,
"loss": 4.0499,
"step": 865792
},
{
"epoch": 1.01,
"learning_rate": 3.581598872614182e-05,
"loss": 4.0343,
"step": 866304
},
{
"epoch": 1.01,
"learning_rate": 3.58076027786313e-05,
"loss": 4.0293,
"step": 866816
},
{
"epoch": 1.01,
"learning_rate": 3.5799216831120774e-05,
"loss": 4.0347,
"step": 867328
},
{
"epoch": 1.01,
"learning_rate": 3.579084726241399e-05,
"loss": 4.0308,
"step": 867840
},
{
"epoch": 1.01,
"learning_rate": 3.578246131490347e-05,
"loss": 4.0557,
"step": 868352
},
{
"epoch": 1.01,
"learning_rate": 3.577407536739295e-05,
"loss": 4.0351,
"step": 868864
},
{
"epoch": 1.01,
"learning_rate": 3.576568941988242e-05,
"loss": 4.0576,
"step": 869376
},
{
"epoch": 1.01,
"learning_rate": 3.57573034723719e-05,
"loss": 4.0456,
"step": 869888
},
{
"epoch": 1.01,
"learning_rate": 3.574891752486138e-05,
"loss": 4.0262,
"step": 870400
},
{
"epoch": 1.01,
"learning_rate": 3.574053157735087e-05,
"loss": 4.0412,
"step": 870912
},
{
"epoch": 1.01,
"learning_rate": 3.573214562984035e-05,
"loss": 4.0346,
"step": 871424
},
{
"epoch": 1.01,
"learning_rate": 3.572375968232983e-05,
"loss": 4.0297,
"step": 871936
},
{
"epoch": 1.01,
"learning_rate": 3.571539011362304e-05,
"loss": 4.042,
"step": 872448
},
{
"epoch": 1.01,
"learning_rate": 3.570700416611252e-05,
"loss": 4.0461,
"step": 872960
},
{
"epoch": 1.01,
"learning_rate": 3.569863459740573e-05,
"loss": 4.0321,
"step": 873472
},
{
"epoch": 1.01,
"learning_rate": 3.569024864989521e-05,
"loss": 4.0459,
"step": 873984
},
{
"epoch": 1.01,
"learning_rate": 3.568186270238469e-05,
"loss": 4.0206,
"step": 874496
},
{
"epoch": 1.01,
"learning_rate": 3.567347675487417e-05,
"loss": 4.0359,
"step": 875008
},
{
"epoch": 1.01,
"learning_rate": 3.566509080736365e-05,
"loss": 4.0394,
"step": 875520
},
{
"epoch": 1.01,
"learning_rate": 3.565670485985313e-05,
"loss": 4.0475,
"step": 876032
},
{
"epoch": 1.01,
"learning_rate": 3.564833529114634e-05,
"loss": 4.0435,
"step": 876544
},
{
"epoch": 1.01,
"learning_rate": 3.5639949343635823e-05,
"loss": 4.0386,
"step": 877056
},
{
"epoch": 1.01,
"learning_rate": 3.5631563396125303e-05,
"loss": 4.0524,
"step": 877568
},
{
"epoch": 1.01,
"learning_rate": 3.562317744861478e-05,
"loss": 4.0388,
"step": 878080
},
{
"epoch": 1.01,
"learning_rate": 3.561479150110426e-05,
"loss": 4.0482,
"step": 878592
},
{
"epoch": 1.01,
"learning_rate": 3.560640555359374e-05,
"loss": 4.0321,
"step": 879104
},
{
"epoch": 1.01,
"learning_rate": 3.559801960608322e-05,
"loss": 4.0348,
"step": 879616
},
{
"epoch": 1.01,
"learning_rate": 3.558965003737643e-05,
"loss": 4.0383,
"step": 880128
},
{
"epoch": 1.01,
"learning_rate": 3.558128046866964e-05,
"loss": 4.0429,
"step": 880640
},
{
"epoch": 1.01,
"learning_rate": 3.557289452115912e-05,
"loss": 4.0416,
"step": 881152
},
{
"epoch": 1.01,
"learning_rate": 3.55645085736486e-05,
"loss": 4.0491,
"step": 881664
},
{
"epoch": 1.01,
"learning_rate": 3.555612262613808e-05,
"loss": 4.0301,
"step": 882176
},
{
"epoch": 1.01,
"learning_rate": 3.554773667862756e-05,
"loss": 4.0191,
"step": 882688
},
{
"epoch": 1.01,
"learning_rate": 3.553935073111704e-05,
"loss": 4.0394,
"step": 883200
},
{
"epoch": 1.01,
"learning_rate": 3.553096478360652e-05,
"loss": 4.0449,
"step": 883712
},
{
"epoch": 1.01,
"learning_rate": 3.5522578836096e-05,
"loss": 4.0352,
"step": 884224
},
{
"epoch": 1.01,
"learning_rate": 3.551419288858549e-05,
"loss": 4.0424,
"step": 884736
},
{
"epoch": 1.01,
"learning_rate": 3.55058233198787e-05,
"loss": 4.0365,
"step": 885248
},
{
"epoch": 1.02,
"learning_rate": 3.549743737236818e-05,
"loss": 4.0344,
"step": 885760
},
{
"epoch": 1.02,
"learning_rate": 3.548905142485766e-05,
"loss": 4.0361,
"step": 886272
},
{
"epoch": 1.02,
"learning_rate": 3.548066547734714e-05,
"loss": 4.0337,
"step": 886784
},
{
"epoch": 1.02,
"learning_rate": 3.547227952983661e-05,
"loss": 4.0457,
"step": 887296
},
{
"epoch": 1.02,
"learning_rate": 3.546389358232609e-05,
"loss": 4.0482,
"step": 887808
},
{
"epoch": 1.02,
"learning_rate": 3.545550763481557e-05,
"loss": 4.0499,
"step": 888320
},
{
"epoch": 1.02,
"learning_rate": 3.544712168730505e-05,
"loss": 4.0281,
"step": 888832
},
{
"epoch": 1.02,
"learning_rate": 3.543875211859826e-05,
"loss": 4.0389,
"step": 889344
},
{
"epoch": 1.02,
"learning_rate": 3.543036617108774e-05,
"loss": 4.0323,
"step": 889856
},
{
"epoch": 1.02,
"learning_rate": 3.5421980223577226e-05,
"loss": 4.0397,
"step": 890368
},
{
"epoch": 1.02,
"learning_rate": 3.5413594276066706e-05,
"loss": 4.0432,
"step": 890880
},
{
"epoch": 1.02,
"learning_rate": 3.5405208328556186e-05,
"loss": 4.0327,
"step": 891392
},
{
"epoch": 1.02,
"learning_rate": 3.5396838759849395e-05,
"loss": 4.0381,
"step": 891904
},
{
"epoch": 1.02,
"learning_rate": 3.5388452812338875e-05,
"loss": 4.0293,
"step": 892416
},
{
"epoch": 1.02,
"learning_rate": 3.5380066864828355e-05,
"loss": 4.0342,
"step": 892928
},
{
"epoch": 1.02,
"learning_rate": 3.5371680917317835e-05,
"loss": 4.0336,
"step": 893440
},
{
"epoch": 1.02,
"learning_rate": 3.5363311348611044e-05,
"loss": 4.0285,
"step": 893952
},
{
"epoch": 1.02,
"learning_rate": 3.5354925401100524e-05,
"loss": 4.0373,
"step": 894464
},
{
"epoch": 1.02,
"learning_rate": 3.5346539453590004e-05,
"loss": 4.0373,
"step": 894976
},
{
"epoch": 1.02,
"learning_rate": 3.5338153506079483e-05,
"loss": 4.0312,
"step": 895488
},
{
"epoch": 1.02,
"learning_rate": 3.5329767558568963e-05,
"loss": 4.0344,
"step": 896000
},
{
"epoch": 1.02,
"learning_rate": 3.532138161105844e-05,
"loss": 4.035,
"step": 896512
},
{
"epoch": 1.02,
"learning_rate": 3.531299566354792e-05,
"loss": 4.038,
"step": 897024
},
{
"epoch": 1.02,
"learning_rate": 3.530460971603741e-05,
"loss": 4.0343,
"step": 897536
},
{
"epoch": 1.02,
"learning_rate": 3.529624014733062e-05,
"loss": 4.0344,
"step": 898048
},
{
"epoch": 1.02,
"learning_rate": 3.52878541998201e-05,
"loss": 4.0468,
"step": 898560
},
{
"epoch": 1.02,
"learning_rate": 3.527946825230958e-05,
"loss": 4.0452,
"step": 899072
},
{
"epoch": 1.02,
"learning_rate": 3.527109868360279e-05,
"loss": 4.032,
"step": 899584
},
{
"epoch": 1.02,
"learning_rate": 3.526271273609227e-05,
"loss": 4.0375,
"step": 900096
},
{
"epoch": 1.02,
"learning_rate": 3.525432678858175e-05,
"loss": 4.0278,
"step": 900608
},
{
"epoch": 1.02,
"learning_rate": 3.524594084107123e-05,
"loss": 4.0417,
"step": 901120
},
{
"epoch": 1.02,
"learning_rate": 3.523757127236444e-05,
"loss": 4.0347,
"step": 901632
},
{
"epoch": 1.02,
"learning_rate": 3.522918532485392e-05,
"loss": 4.0258,
"step": 902144
},
{
"epoch": 1.02,
"learning_rate": 3.52207993773434e-05,
"loss": 4.0427,
"step": 902656
},
{
"epoch": 1.02,
"learning_rate": 3.521241342983288e-05,
"loss": 4.0403,
"step": 903168
},
{
"epoch": 1.02,
"learning_rate": 3.5204027482322364e-05,
"loss": 4.0352,
"step": 903680
},
{
"epoch": 1.02,
"learning_rate": 3.5195641534811844e-05,
"loss": 4.0336,
"step": 904192
},
{
"epoch": 1.02,
"learning_rate": 3.518727196610505e-05,
"loss": 4.0272,
"step": 904704
},
{
"epoch": 1.02,
"learning_rate": 3.517888601859453e-05,
"loss": 4.0242,
"step": 905216
},
{
"epoch": 1.02,
"learning_rate": 3.517050007108401e-05,
"loss": 4.0423,
"step": 905728
},
{
"epoch": 1.02,
"learning_rate": 3.516211412357349e-05,
"loss": 4.0377,
"step": 906240
},
{
"epoch": 1.02,
"learning_rate": 3.515372817606297e-05,
"loss": 4.0445,
"step": 906752
},
{
"epoch": 1.02,
"learning_rate": 3.5145342228552446e-05,
"loss": 4.0174,
"step": 907264
},
{
"epoch": 1.02,
"learning_rate": 3.5136956281041926e-05,
"loss": 4.0414,
"step": 907776
},
{
"epoch": 1.02,
"learning_rate": 3.512858671233514e-05,
"loss": 4.0346,
"step": 908288
},
{
"epoch": 1.02,
"learning_rate": 3.512020076482462e-05,
"loss": 4.044,
"step": 908800
},
{
"epoch": 1.02,
"learning_rate": 3.51118148173141e-05,
"loss": 4.0313,
"step": 909312
},
{
"epoch": 1.02,
"learning_rate": 3.510342886980358e-05,
"loss": 4.0291,
"step": 909824
},
{
"epoch": 1.02,
"learning_rate": 3.509504292229306e-05,
"loss": 4.0364,
"step": 910336
},
{
"epoch": 1.02,
"learning_rate": 3.508665697478254e-05,
"loss": 4.049,
"step": 910848
},
{
"epoch": 1.02,
"learning_rate": 3.507827102727202e-05,
"loss": 4.0291,
"step": 911360
},
{
"epoch": 1.02,
"learning_rate": 3.50698850797615e-05,
"loss": 4.0411,
"step": 911872
},
{
"epoch": 1.02,
"learning_rate": 3.506151551105471e-05,
"loss": 4.0305,
"step": 912384
},
{
"epoch": 1.02,
"learning_rate": 3.505312956354419e-05,
"loss": 4.0376,
"step": 912896
},
{
"epoch": 1.02,
"learning_rate": 3.504474361603367e-05,
"loss": 4.0308,
"step": 913408
},
{
"epoch": 1.02,
"learning_rate": 3.503635766852315e-05,
"loss": 4.0307,
"step": 913920
},
{
"epoch": 1.02,
"learning_rate": 3.502797172101263e-05,
"loss": 4.0321,
"step": 914432
},
{
"epoch": 1.02,
"learning_rate": 3.501961853110957e-05,
"loss": 4.0345,
"step": 914944
},
{
"epoch": 1.02,
"learning_rate": 3.501123258359905e-05,
"loss": 4.0398,
"step": 915456
},
{
"epoch": 1.03,
"eval_loss": 4.0708794593811035,
"eval_runtime": 313.3913,
"eval_samples_per_second": 1217.618,
"eval_steps_per_second": 38.051,
"step": 915840
},
{
"epoch": 0.0,
"learning_rate": 3.5002863014892264e-05,
"loss": 4.0533,
"step": 915968
},
{
"epoch": 0.0,
"learning_rate": 3.4994477067381744e-05,
"loss": 4.0173,
"step": 916480
},
{
"epoch": 0.0,
"learning_rate": 3.4986091119871224e-05,
"loss": 4.034,
"step": 916992
},
{
"epoch": 0.0,
"learning_rate": 3.4977705172360704e-05,
"loss": 4.0333,
"step": 917504
},
{
"epoch": 0.0,
"learning_rate": 3.4969319224850184e-05,
"loss": 4.0408,
"step": 918016
},
{
"epoch": 0.0,
"learning_rate": 3.4960933277339664e-05,
"loss": 4.0399,
"step": 918528
},
{
"epoch": 0.0,
"learning_rate": 3.4952547329829144e-05,
"loss": 4.0298,
"step": 919040
},
{
"epoch": 0.0,
"learning_rate": 3.4944161382318624e-05,
"loss": 4.0381,
"step": 919552
},
{
"epoch": 0.0,
"learning_rate": 3.4935775434808104e-05,
"loss": 4.0295,
"step": 920064
},
{
"epoch": 0.0,
"learning_rate": 3.4927389487297584e-05,
"loss": 4.0323,
"step": 920576
},
{
"epoch": 0.0,
"learning_rate": 3.4919003539787064e-05,
"loss": 4.0395,
"step": 921088
},
{
"epoch": 0.0,
"learning_rate": 3.4910617592276544e-05,
"loss": 4.0358,
"step": 921600
},
{
"epoch": 0.0,
"learning_rate": 3.490224802356975e-05,
"loss": 4.0443,
"step": 922112
},
{
"epoch": 0.0,
"learning_rate": 3.489386207605923e-05,
"loss": 4.0225,
"step": 922624
},
{
"epoch": 0.0,
"learning_rate": 3.488547612854872e-05,
"loss": 4.0206,
"step": 923136
},
{
"epoch": 0.0,
"learning_rate": 3.48770901810382e-05,
"loss": 4.0216,
"step": 923648
},
{
"epoch": 0.0,
"learning_rate": 3.486870423352768e-05,
"loss": 4.0361,
"step": 924160
},
{
"epoch": 0.0,
"learning_rate": 3.486031828601716e-05,
"loss": 4.031,
"step": 924672
},
{
"epoch": 0.0,
"learning_rate": 3.485193233850663e-05,
"loss": 4.026,
"step": 925184
},
{
"epoch": 0.0,
"learning_rate": 3.484354639099611e-05,
"loss": 4.0365,
"step": 925696
},
{
"epoch": 0.0,
"learning_rate": 3.483516044348559e-05,
"loss": 4.0494,
"step": 926208
},
{
"epoch": 0.0,
"learning_rate": 3.482677449597507e-05,
"loss": 4.0355,
"step": 926720
},
{
"epoch": 0.0,
"learning_rate": 3.481838854846455e-05,
"loss": 4.0353,
"step": 927232
},
{
"epoch": 0.0,
"learning_rate": 3.481001897975776e-05,
"loss": 4.0365,
"step": 927744
},
{
"epoch": 0.0,
"learning_rate": 3.480164941105098e-05,
"loss": 4.0421,
"step": 928256
},
{
"epoch": 0.0,
"learning_rate": 3.479326346354046e-05,
"loss": 4.0295,
"step": 928768
},
{
"epoch": 0.0,
"learning_rate": 3.478487751602994e-05,
"loss": 4.0259,
"step": 929280
},
{
"epoch": 0.0,
"learning_rate": 3.477649156851942e-05,
"loss": 4.0392,
"step": 929792
},
{
"epoch": 0.0,
"learning_rate": 3.47681056210089e-05,
"loss": 4.017,
"step": 930304
},
{
"epoch": 0.0,
"learning_rate": 3.475971967349838e-05,
"loss": 4.0266,
"step": 930816
},
{
"epoch": 0.01,
"learning_rate": 3.475133372598786e-05,
"loss": 4.0348,
"step": 931328
},
{
"epoch": 0.01,
"learning_rate": 3.474294777847734e-05,
"loss": 4.0283,
"step": 931840
},
{
"epoch": 0.01,
"learning_rate": 3.473456183096682e-05,
"loss": 4.0376,
"step": 932352
},
{
"epoch": 0.01,
"learning_rate": 3.4726192262260026e-05,
"loss": 4.034,
"step": 932864
},
{
"epoch": 0.01,
"learning_rate": 3.4717806314749506e-05,
"loss": 4.0288,
"step": 933376
},
{
"epoch": 0.01,
"learning_rate": 3.4709436746042715e-05,
"loss": 4.0315,
"step": 933888
},
{
"epoch": 0.01,
"learning_rate": 3.4701050798532195e-05,
"loss": 4.0301,
"step": 934400
},
{
"epoch": 0.01,
"learning_rate": 3.4692664851021675e-05,
"loss": 4.0151,
"step": 934912
},
{
"epoch": 0.01,
"learning_rate": 3.4684278903511155e-05,
"loss": 4.0326,
"step": 935424
},
{
"epoch": 0.01,
"learning_rate": 3.467589295600064e-05,
"loss": 4.0237,
"step": 935936
},
{
"epoch": 0.01,
"learning_rate": 3.466750700849012e-05,
"loss": 4.0257,
"step": 936448
},
{
"epoch": 0.01,
"learning_rate": 3.46591210609796e-05,
"loss": 4.0307,
"step": 936960
},
{
"epoch": 0.01,
"learning_rate": 3.465073511346908e-05,
"loss": 4.0398,
"step": 937472
},
{
"epoch": 0.01,
"learning_rate": 3.464234916595856e-05,
"loss": 4.0217,
"step": 937984
},
{
"epoch": 0.01,
"learning_rate": 3.463396321844804e-05,
"loss": 4.0315,
"step": 938496
},
{
"epoch": 0.01,
"learning_rate": 3.462557727093752e-05,
"loss": 4.0303,
"step": 939008
},
{
"epoch": 0.01,
"learning_rate": 3.4617191323426995e-05,
"loss": 4.0232,
"step": 939520
},
{
"epoch": 0.01,
"learning_rate": 3.4608805375916475e-05,
"loss": 4.032,
"step": 940032
},
{
"epoch": 0.01,
"learning_rate": 3.460043580720969e-05,
"loss": 4.0157,
"step": 940544
},
{
"epoch": 0.01,
"learning_rate": 3.459204985969917e-05,
"loss": 4.0256,
"step": 941056
},
{
"epoch": 0.01,
"learning_rate": 3.4583663912188644e-05,
"loss": 4.0301,
"step": 941568
},
{
"epoch": 0.01,
"learning_rate": 3.4575277964678124e-05,
"loss": 4.0309,
"step": 942080
},
{
"epoch": 0.01,
"learning_rate": 3.456690839597134e-05,
"loss": 4.019,
"step": 942592
},
{
"epoch": 0.01,
"learning_rate": 3.4558538827264555e-05,
"loss": 4.0135,
"step": 943104
},
{
"epoch": 0.01,
"learning_rate": 3.4550152879754035e-05,
"loss": 4.0169,
"step": 943616
},
{
"epoch": 0.01,
"learning_rate": 3.4541766932243515e-05,
"loss": 4.0129,
"step": 944128
},
{
"epoch": 0.01,
"learning_rate": 3.4533380984732995e-05,
"loss": 4.0422,
"step": 944640
},
{
"epoch": 0.01,
"learning_rate": 3.4525011416026204e-05,
"loss": 4.0154,
"step": 945152
},
{
"epoch": 0.01,
"learning_rate": 3.4516641847319413e-05,
"loss": 4.0404,
"step": 945664
},
{
"epoch": 0.01,
"learning_rate": 3.4508255899808893e-05,
"loss": 4.0307,
"step": 946176
},
{
"epoch": 0.01,
"learning_rate": 3.449986995229837e-05,
"loss": 4.011,
"step": 946688
},
{
"epoch": 0.01,
"learning_rate": 3.449148400478785e-05,
"loss": 4.0247,
"step": 947200
},
{
"epoch": 0.01,
"learning_rate": 3.448309805727733e-05,
"loss": 4.0205,
"step": 947712
},
{
"epoch": 0.01,
"learning_rate": 3.447471210976681e-05,
"loss": 4.0134,
"step": 948224
},
{
"epoch": 0.01,
"learning_rate": 3.446632616225629e-05,
"loss": 4.0234,
"step": 948736
},
{
"epoch": 0.01,
"learning_rate": 3.445794021474577e-05,
"loss": 4.0294,
"step": 949248
},
{
"epoch": 0.01,
"learning_rate": 3.444955426723525e-05,
"loss": 4.0197,
"step": 949760
},
{
"epoch": 0.01,
"learning_rate": 3.444118469852847e-05,
"loss": 4.0262,
"step": 950272
},
{
"epoch": 0.01,
"learning_rate": 3.443279875101794e-05,
"loss": 4.006,
"step": 950784
},
{
"epoch": 0.01,
"learning_rate": 3.442442918231116e-05,
"loss": 4.0185,
"step": 951296
},
{
"epoch": 0.01,
"learning_rate": 3.441604323480064e-05,
"loss": 4.0252,
"step": 951808
},
{
"epoch": 0.01,
"learning_rate": 3.440765728729012e-05,
"loss": 4.0329,
"step": 952320
},
{
"epoch": 0.01,
"learning_rate": 3.439927133977959e-05,
"loss": 4.0299,
"step": 952832
},
{
"epoch": 0.01,
"learning_rate": 3.439088539226907e-05,
"loss": 4.0242,
"step": 953344
},
{
"epoch": 0.01,
"learning_rate": 3.438249944475855e-05,
"loss": 4.0324,
"step": 953856
},
{
"epoch": 0.01,
"learning_rate": 3.437411349724803e-05,
"loss": 4.0223,
"step": 954368
},
{
"epoch": 0.01,
"learning_rate": 3.436572754973751e-05,
"loss": 4.0318,
"step": 954880
},
{
"epoch": 0.01,
"learning_rate": 3.4357341602227e-05,
"loss": 4.0173,
"step": 955392
},
{
"epoch": 0.01,
"learning_rate": 3.434895565471648e-05,
"loss": 4.0229,
"step": 955904
},
{
"epoch": 0.01,
"learning_rate": 3.434056970720596e-05,
"loss": 4.0179,
"step": 956416
},
{
"epoch": 0.01,
"learning_rate": 3.433218375969544e-05,
"loss": 4.0283,
"step": 956928
},
{
"epoch": 0.01,
"learning_rate": 3.432379781218492e-05,
"loss": 4.0293,
"step": 957440
},
{
"epoch": 0.01,
"learning_rate": 3.4315428243478127e-05,
"loss": 4.0322,
"step": 957952
},
{
"epoch": 0.01,
"learning_rate": 3.4307042295967607e-05,
"loss": 4.0157,
"step": 958464
},
{
"epoch": 0.01,
"learning_rate": 3.4298656348457086e-05,
"loss": 4.0009,
"step": 958976
},
{
"epoch": 0.01,
"learning_rate": 3.4290270400946566e-05,
"loss": 4.0264,
"step": 959488
},
{
"epoch": 0.01,
"learning_rate": 3.4281900832239776e-05,
"loss": 4.0284,
"step": 960000
},
{
"epoch": 0.01,
"learning_rate": 3.4273514884729256e-05,
"loss": 4.018,
"step": 960512
},
{
"epoch": 0.01,
"learning_rate": 3.4265128937218735e-05,
"loss": 4.0273,
"step": 961024
},
{
"epoch": 0.01,
"learning_rate": 3.4256742989708215e-05,
"loss": 4.0225,
"step": 961536
},
{
"epoch": 0.02,
"learning_rate": 3.424837342100143e-05,
"loss": 4.0156,
"step": 962048
},
{
"epoch": 0.02,
"learning_rate": 3.423998747349091e-05,
"loss": 4.0223,
"step": 962560
},
{
"epoch": 0.02,
"learning_rate": 3.423160152598039e-05,
"loss": 4.0179,
"step": 963072
},
{
"epoch": 0.02,
"learning_rate": 3.42232319572736e-05,
"loss": 4.0265,
"step": 963584
},
{
"epoch": 0.02,
"learning_rate": 3.421484600976308e-05,
"loss": 4.0321,
"step": 964096
},
{
"epoch": 0.02,
"learning_rate": 3.420646006225256e-05,
"loss": 4.0342,
"step": 964608
},
{
"epoch": 0.02,
"learning_rate": 3.419807411474204e-05,
"loss": 4.0118,
"step": 965120
},
{
"epoch": 0.02,
"learning_rate": 3.418968816723152e-05,
"loss": 4.0244,
"step": 965632
},
{
"epoch": 0.02,
"learning_rate": 3.4181302219721e-05,
"loss": 4.022,
"step": 966144
},
{
"epoch": 0.02,
"learning_rate": 3.417291627221048e-05,
"loss": 4.0235,
"step": 966656
},
{
"epoch": 0.02,
"learning_rate": 3.416454670350369e-05,
"loss": 4.0254,
"step": 967168
},
{
"epoch": 0.02,
"learning_rate": 3.415616075599317e-05,
"loss": 4.0176,
"step": 967680
},
{
"epoch": 0.02,
"learning_rate": 3.414777480848265e-05,
"loss": 4.0213,
"step": 968192
},
{
"epoch": 0.02,
"learning_rate": 3.413938886097213e-05,
"loss": 4.0153,
"step": 968704
},
{
"epoch": 0.02,
"learning_rate": 3.413100291346161e-05,
"loss": 4.0194,
"step": 969216
},
{
"epoch": 0.02,
"learning_rate": 3.412261696595109e-05,
"loss": 4.0174,
"step": 969728
},
{
"epoch": 0.02,
"learning_rate": 3.4114247397244305e-05,
"loss": 4.0139,
"step": 970240
},
{
"epoch": 0.02,
"learning_rate": 3.410586144973378e-05,
"loss": 4.0221,
"step": 970752
},
{
"epoch": 0.02,
"learning_rate": 3.409747550222326e-05,
"loss": 4.0187,
"step": 971264
},
{
"epoch": 0.02,
"learning_rate": 3.408908955471274e-05,
"loss": 4.0149,
"step": 971776
},
{
"epoch": 0.02,
"learning_rate": 3.408071998600595e-05,
"loss": 4.0197,
"step": 972288
},
{
"epoch": 0.02,
"learning_rate": 3.407233403849543e-05,
"loss": 4.0151,
"step": 972800
},
{
"epoch": 0.02,
"learning_rate": 3.406394809098491e-05,
"loss": 4.0253,
"step": 973312
},
{
"epoch": 0.02,
"learning_rate": 3.405556214347439e-05,
"loss": 4.0206,
"step": 973824
},
{
"epoch": 0.02,
"learning_rate": 3.4047176195963874e-05,
"loss": 4.0229,
"step": 974336
},
{
"epoch": 0.02,
"learning_rate": 3.4038790248453354e-05,
"loss": 4.0249,
"step": 974848
},
{
"epoch": 0.02,
"learning_rate": 3.403042067974656e-05,
"loss": 4.0317,
"step": 975360
},
{
"epoch": 0.02,
"learning_rate": 3.402203473223604e-05,
"loss": 4.017,
"step": 975872
},
{
"epoch": 0.02,
"learning_rate": 3.401364878472552e-05,
"loss": 4.0215,
"step": 976384
},
{
"epoch": 0.02,
"learning_rate": 3.4005262837215e-05,
"loss": 4.0149,
"step": 976896
},
{
"epoch": 0.02,
"learning_rate": 3.399687688970448e-05,
"loss": 4.0266,
"step": 977408
},
{
"epoch": 0.02,
"learning_rate": 3.398849094219396e-05,
"loss": 4.0225,
"step": 977920
},
{
"epoch": 0.02,
"learning_rate": 3.398012137348717e-05,
"loss": 4.0101,
"step": 978432
},
{
"epoch": 0.02,
"learning_rate": 3.397173542597665e-05,
"loss": 4.0226,
"step": 978944
},
{
"epoch": 0.02,
"learning_rate": 3.396334947846613e-05,
"loss": 4.0272,
"step": 979456
},
{
"epoch": 0.02,
"learning_rate": 3.395497990975934e-05,
"loss": 4.0215,
"step": 979968
},
{
"epoch": 0.02,
"learning_rate": 3.394659396224882e-05,
"loss": 4.0159,
"step": 980480
},
{
"epoch": 0.02,
"learning_rate": 3.393820801473831e-05,
"loss": 4.0099,
"step": 980992
},
{
"epoch": 0.02,
"learning_rate": 3.392982206722779e-05,
"loss": 4.0127,
"step": 981504
},
{
"epoch": 0.02,
"learning_rate": 3.392143611971727e-05,
"loss": 4.0307,
"step": 982016
},
{
"epoch": 0.02,
"learning_rate": 3.391305017220675e-05,
"loss": 4.0224,
"step": 982528
},
{
"epoch": 0.02,
"learning_rate": 3.3904680603499956e-05,
"loss": 4.0281,
"step": 983040
},
{
"epoch": 0.02,
"learning_rate": 3.3896294655989436e-05,
"loss": 3.9995,
"step": 983552
},
{
"epoch": 0.02,
"learning_rate": 3.3887908708478916e-05,
"loss": 4.0251,
"step": 984064
},
{
"epoch": 0.02,
"learning_rate": 3.3879522760968396e-05,
"loss": 4.0226,
"step": 984576
},
{
"epoch": 0.02,
"learning_rate": 3.3871136813457876e-05,
"loss": 4.0276,
"step": 985088
},
{
"epoch": 0.02,
"learning_rate": 3.3862750865947356e-05,
"loss": 4.0166,
"step": 985600
},
{
"epoch": 0.02,
"learning_rate": 3.3854364918436836e-05,
"loss": 4.0156,
"step": 986112
},
{
"epoch": 0.02,
"learning_rate": 3.384597897092631e-05,
"loss": 4.0199,
"step": 986624
},
{
"epoch": 0.02,
"learning_rate": 3.383762578102326e-05,
"loss": 4.0354,
"step": 987136
},
{
"epoch": 0.02,
"learning_rate": 3.382923983351274e-05,
"loss": 4.015,
"step": 987648
},
{
"epoch": 0.02,
"learning_rate": 3.382085388600222e-05,
"loss": 4.0232,
"step": 988160
},
{
"epoch": 0.02,
"learning_rate": 3.38124679384917e-05,
"loss": 4.0184,
"step": 988672
},
{
"epoch": 0.02,
"learning_rate": 3.380408199098118e-05,
"loss": 4.0232,
"step": 989184
},
{
"epoch": 0.02,
"learning_rate": 3.379569604347066e-05,
"loss": 4.0141,
"step": 989696
},
{
"epoch": 0.02,
"learning_rate": 3.378731009596014e-05,
"loss": 4.0214,
"step": 990208
},
{
"epoch": 0.02,
"learning_rate": 3.3778924148449614e-05,
"loss": 4.0152,
"step": 990720
},
{
"epoch": 0.02,
"learning_rate": 3.377055457974283e-05,
"loss": 4.0156,
"step": 991232
},
{
"epoch": 0.02,
"learning_rate": 3.376216863223231e-05,
"loss": 4.0253,
"step": 991744
},
{
"epoch": 0.03,
"eval_loss": 4.062292098999023,
"eval_runtime": 307.568,
"eval_samples_per_second": 1240.672,
"eval_steps_per_second": 38.772,
"step": 992160
},
{
"epoch": 1.0,
"learning_rate": 3.375378268472178e-05,
"loss": 4.0209,
"step": 992256
},
{
"epoch": 1.0,
"learning_rate": 3.374539673721126e-05,
"loss": 4.0063,
"step": 992768
},
{
"epoch": 1.0,
"learning_rate": 3.373702716850448e-05,
"loss": 4.0159,
"step": 993280
},
{
"epoch": 1.0,
"learning_rate": 3.372864122099396e-05,
"loss": 4.0241,
"step": 993792
},
{
"epoch": 1.0,
"learning_rate": 3.372025527348344e-05,
"loss": 4.0212,
"step": 994304
},
{
"epoch": 1.0,
"learning_rate": 3.371186932597292e-05,
"loss": 4.027,
"step": 994816
},
{
"epoch": 1.0,
"learning_rate": 3.3703499757266134e-05,
"loss": 4.0135,
"step": 995328
},
{
"epoch": 1.0,
"learning_rate": 3.3695113809755614e-05,
"loss": 4.0257,
"step": 995840
},
{
"epoch": 1.0,
"learning_rate": 3.368672786224509e-05,
"loss": 4.0133,
"step": 996352
},
{
"epoch": 1.0,
"learning_rate": 3.367834191473457e-05,
"loss": 4.0181,
"step": 996864
},
{
"epoch": 1.0,
"learning_rate": 3.366997234602778e-05,
"loss": 4.0231,
"step": 997376
},
{
"epoch": 1.0,
"learning_rate": 3.3661586398517256e-05,
"loss": 4.0215,
"step": 997888
},
{
"epoch": 1.0,
"learning_rate": 3.365321682981047e-05,
"loss": 4.0317,
"step": 998400
},
{
"epoch": 1.0,
"learning_rate": 3.364483088229995e-05,
"loss": 4.0085,
"step": 998912
},
{
"epoch": 1.0,
"learning_rate": 3.363644493478943e-05,
"loss": 4.0044,
"step": 999424
},
{
"epoch": 1.0,
"learning_rate": 3.362805898727891e-05,
"loss": 4.007,
"step": 999936
},
{
"epoch": 1.0,
"learning_rate": 3.361967303976839e-05,
"loss": 4.019,
"step": 1000448
},
{
"epoch": 1.0,
"learning_rate": 3.361128709225787e-05,
"loss": 4.0133,
"step": 1000960
},
{
"epoch": 1.0,
"learning_rate": 3.360290114474735e-05,
"loss": 4.0118,
"step": 1001472
},
{
"epoch": 1.0,
"learning_rate": 3.359451519723683e-05,
"loss": 4.0248,
"step": 1001984
},
{
"epoch": 1.0,
"learning_rate": 3.358612924972631e-05,
"loss": 4.0296,
"step": 1002496
},
{
"epoch": 1.0,
"learning_rate": 3.357774330221579e-05,
"loss": 4.0266,
"step": 1003008
},
{
"epoch": 1.0,
"learning_rate": 3.356935735470527e-05,
"loss": 4.0193,
"step": 1003520
},
{
"epoch": 1.0,
"learning_rate": 3.356097140719475e-05,
"loss": 4.0217,
"step": 1004032
},
{
"epoch": 1.0,
"learning_rate": 3.355260183848796e-05,
"loss": 4.0263,
"step": 1004544
},
{
"epoch": 1.0,
"learning_rate": 3.354421589097744e-05,
"loss": 4.0183,
"step": 1005056
},
{
"epoch": 1.0,
"learning_rate": 3.353582994346692e-05,
"loss": 4.0094,
"step": 1005568
},
{
"epoch": 1.0,
"learning_rate": 3.35274439959564e-05,
"loss": 4.0274,
"step": 1006080
},
{
"epoch": 1.0,
"learning_rate": 3.351905804844588e-05,
"loss": 4.0012,
"step": 1006592
},
{
"epoch": 1.0,
"learning_rate": 3.351067210093537e-05,
"loss": 4.0112,
"step": 1007104
},
{
"epoch": 1.01,
"learning_rate": 3.350228615342485e-05,
"loss": 4.0141,
"step": 1007616
},
{
"epoch": 1.01,
"learning_rate": 3.3493916584718057e-05,
"loss": 4.0191,
"step": 1008128
},
{
"epoch": 1.01,
"learning_rate": 3.3485530637207537e-05,
"loss": 4.0219,
"step": 1008640
},
{
"epoch": 1.01,
"learning_rate": 3.3477144689697016e-05,
"loss": 4.0192,
"step": 1009152
},
{
"epoch": 1.01,
"learning_rate": 3.3468758742186496e-05,
"loss": 4.0169,
"step": 1009664
},
{
"epoch": 1.01,
"learning_rate": 3.3460389173479706e-05,
"loss": 4.0171,
"step": 1010176
},
{
"epoch": 1.01,
"learning_rate": 3.3452003225969185e-05,
"loss": 4.0106,
"step": 1010688
},
{
"epoch": 1.01,
"learning_rate": 3.3443617278458665e-05,
"loss": 4.0003,
"step": 1011200
},
{
"epoch": 1.01,
"learning_rate": 3.3435231330948145e-05,
"loss": 4.0203,
"step": 1011712
},
{
"epoch": 1.01,
"learning_rate": 3.342684538343762e-05,
"loss": 4.0083,
"step": 1012224
},
{
"epoch": 1.01,
"learning_rate": 3.3418459435927105e-05,
"loss": 4.0138,
"step": 1012736
},
{
"epoch": 1.01,
"learning_rate": 3.3410073488416585e-05,
"loss": 4.0134,
"step": 1013248
},
{
"epoch": 1.01,
"learning_rate": 3.3401687540906065e-05,
"loss": 4.0232,
"step": 1013760
},
{
"epoch": 1.01,
"learning_rate": 3.3393301593395545e-05,
"loss": 4.0117,
"step": 1014272
},
{
"epoch": 1.01,
"learning_rate": 3.3384915645885025e-05,
"loss": 4.016,
"step": 1014784
},
{
"epoch": 1.01,
"learning_rate": 3.3376529698374505e-05,
"loss": 4.0147,
"step": 1015296
},
{
"epoch": 1.01,
"learning_rate": 3.3368143750863985e-05,
"loss": 4.0104,
"step": 1015808
},
{
"epoch": 1.01,
"learning_rate": 3.335979056096092e-05,
"loss": 4.0147,
"step": 1016320
},
{
"epoch": 1.01,
"learning_rate": 3.33514046134504e-05,
"loss": 4.001,
"step": 1016832
},
{
"epoch": 1.01,
"learning_rate": 3.334301866593988e-05,
"loss": 4.0112,
"step": 1017344
},
{
"epoch": 1.01,
"learning_rate": 3.333463271842936e-05,
"loss": 4.0177,
"step": 1017856
},
{
"epoch": 1.01,
"learning_rate": 3.332624677091884e-05,
"loss": 4.0127,
"step": 1018368
},
{
"epoch": 1.01,
"learning_rate": 3.331786082340832e-05,
"loss": 4.0023,
"step": 1018880
},
{
"epoch": 1.01,
"learning_rate": 3.33094748758978e-05,
"loss": 3.998,
"step": 1019392
},
{
"epoch": 1.01,
"learning_rate": 3.330108892838728e-05,
"loss": 4.0044,
"step": 1019904
},
{
"epoch": 1.01,
"learning_rate": 3.32927193596805e-05,
"loss": 3.9977,
"step": 1020416
},
{
"epoch": 1.01,
"learning_rate": 3.328433341216998e-05,
"loss": 4.0303,
"step": 1020928
},
{
"epoch": 1.01,
"learning_rate": 3.327594746465946e-05,
"loss": 3.9996,
"step": 1021440
},
{
"epoch": 1.01,
"learning_rate": 3.326756151714894e-05,
"loss": 4.0283,
"step": 1021952
},
{
"epoch": 1.01,
"learning_rate": 3.325917556963842e-05,
"loss": 4.0116,
"step": 1022464
},
{
"epoch": 1.01,
"learning_rate": 3.32507896221279e-05,
"loss": 3.9983,
"step": 1022976
},
{
"epoch": 1.01,
"learning_rate": 3.324240367461738e-05,
"loss": 4.0057,
"step": 1023488
},
{
"epoch": 1.01,
"learning_rate": 3.323401772710686e-05,
"loss": 4.0058,
"step": 1024000
},
{
"epoch": 1.01,
"learning_rate": 3.322564815840007e-05,
"loss": 4.0034,
"step": 1024512
},
{
"epoch": 1.01,
"learning_rate": 3.321726221088955e-05,
"loss": 4.0045,
"step": 1025024
},
{
"epoch": 1.01,
"learning_rate": 3.320889264218276e-05,
"loss": 4.019,
"step": 1025536
},
{
"epoch": 1.01,
"learning_rate": 3.320050669467224e-05,
"loss": 4.0084,
"step": 1026048
},
{
"epoch": 1.01,
"learning_rate": 3.319212074716172e-05,
"loss": 4.0082,
"step": 1026560
},
{
"epoch": 1.01,
"learning_rate": 3.31837347996512e-05,
"loss": 3.9949,
"step": 1027072
},
{
"epoch": 1.01,
"learning_rate": 3.317534885214068e-05,
"loss": 4.0026,
"step": 1027584
},
{
"epoch": 1.01,
"learning_rate": 3.316696290463016e-05,
"loss": 4.0064,
"step": 1028096
},
{
"epoch": 1.01,
"learning_rate": 3.315859333592337e-05,
"loss": 4.0216,
"step": 1028608
},
{
"epoch": 1.01,
"learning_rate": 3.315020738841285e-05,
"loss": 4.0134,
"step": 1029120
},
{
"epoch": 1.01,
"learning_rate": 3.314182144090233e-05,
"loss": 4.0118,
"step": 1029632
},
{
"epoch": 1.01,
"learning_rate": 3.3133435493391805e-05,
"loss": 4.0147,
"step": 1030144
},
{
"epoch": 1.01,
"learning_rate": 3.3125049545881285e-05,
"loss": 4.0103,
"step": 1030656
},
{
"epoch": 1.01,
"learning_rate": 3.3116663598370765e-05,
"loss": 4.0145,
"step": 1031168
},
{
"epoch": 1.01,
"learning_rate": 3.3108277650860245e-05,
"loss": 4.0038,
"step": 1031680
},
{
"epoch": 1.01,
"learning_rate": 3.3099891703349725e-05,
"loss": 4.0105,
"step": 1032192
},
{
"epoch": 1.01,
"learning_rate": 3.3091505755839205e-05,
"loss": 4.0038,
"step": 1032704
},
{
"epoch": 1.01,
"learning_rate": 3.308313618713242e-05,
"loss": 4.0124,
"step": 1033216
},
{
"epoch": 1.01,
"learning_rate": 3.30747502396219e-05,
"loss": 4.0172,
"step": 1033728
},
{
"epoch": 1.01,
"learning_rate": 3.306636429211138e-05,
"loss": 4.0169,
"step": 1034240
},
{
"epoch": 1.01,
"learning_rate": 3.305797834460086e-05,
"loss": 4.0055,
"step": 1034752
},
{
"epoch": 1.01,
"learning_rate": 3.304960877589407e-05,
"loss": 3.9814,
"step": 1035264
},
{
"epoch": 1.01,
"learning_rate": 3.304122282838355e-05,
"loss": 4.0126,
"step": 1035776
},
{
"epoch": 1.01,
"learning_rate": 3.303283688087303e-05,
"loss": 4.0115,
"step": 1036288
},
{
"epoch": 1.01,
"learning_rate": 3.302446731216624e-05,
"loss": 4.0071,
"step": 1036800
},
{
"epoch": 1.01,
"learning_rate": 3.301608136465572e-05,
"loss": 4.0073,
"step": 1037312
},
{
"epoch": 1.01,
"learning_rate": 3.30076954171452e-05,
"loss": 4.013,
"step": 1037824
},
{
"epoch": 1.02,
"learning_rate": 3.299930946963468e-05,
"loss": 4.0,
"step": 1038336
},
{
"epoch": 1.02,
"learning_rate": 3.299092352212416e-05,
"loss": 4.007,
"step": 1038848
},
{
"epoch": 1.02,
"learning_rate": 3.2982537574613646e-05,
"loss": 4.0026,
"step": 1039360
},
{
"epoch": 1.02,
"learning_rate": 3.2974151627103126e-05,
"loss": 4.011,
"step": 1039872
},
{
"epoch": 1.02,
"learning_rate": 3.2965782058396335e-05,
"loss": 4.0167,
"step": 1040384
},
{
"epoch": 1.02,
"learning_rate": 3.2957396110885815e-05,
"loss": 4.0182,
"step": 1040896
},
{
"epoch": 1.02,
"learning_rate": 3.2949010163375295e-05,
"loss": 4.0008,
"step": 1041408
},
{
"epoch": 1.02,
"learning_rate": 3.2940624215864775e-05,
"loss": 4.0078,
"step": 1041920
},
{
"epoch": 1.02,
"learning_rate": 3.2932238268354254e-05,
"loss": 4.0084,
"step": 1042432
},
{
"epoch": 1.02,
"learning_rate": 3.2923852320843734e-05,
"loss": 4.01,
"step": 1042944
},
{
"epoch": 1.02,
"learning_rate": 3.2915466373333214e-05,
"loss": 4.0102,
"step": 1043456
},
{
"epoch": 1.02,
"learning_rate": 3.2907080425822694e-05,
"loss": 4.0054,
"step": 1043968
},
{
"epoch": 1.02,
"learning_rate": 3.2898710857115903e-05,
"loss": 4.0057,
"step": 1044480
},
{
"epoch": 1.02,
"learning_rate": 3.2890324909605383e-05,
"loss": 3.9992,
"step": 1044992
},
{
"epoch": 1.02,
"learning_rate": 3.288193896209486e-05,
"loss": 4.0106,
"step": 1045504
},
{
"epoch": 1.02,
"learning_rate": 3.287355301458434e-05,
"loss": 3.9971,
"step": 1046016
},
{
"epoch": 1.02,
"learning_rate": 3.286518344587756e-05,
"loss": 4.0013,
"step": 1046528
},
{
"epoch": 1.02,
"learning_rate": 3.285679749836704e-05,
"loss": 4.0075,
"step": 1047040
},
{
"epoch": 1.02,
"learning_rate": 3.284841155085652e-05,
"loss": 4.001,
"step": 1047552
},
{
"epoch": 1.02,
"learning_rate": 3.284002560334599e-05,
"loss": 4.004,
"step": 1048064
},
{
"epoch": 1.02,
"learning_rate": 3.283165603463921e-05,
"loss": 4.011,
"step": 1048576
},
{
"epoch": 1.02,
"learning_rate": 3.282327008712869e-05,
"loss": 3.9991,
"step": 1049088
},
{
"epoch": 1.02,
"learning_rate": 3.281488413961817e-05,
"loss": 4.0112,
"step": 1049600
},
{
"epoch": 1.02,
"learning_rate": 3.280649819210764e-05,
"loss": 4.0056,
"step": 1050112
},
{
"epoch": 1.02,
"learning_rate": 3.279811224459712e-05,
"loss": 4.0059,
"step": 1050624
},
{
"epoch": 1.02,
"learning_rate": 3.27897262970866e-05,
"loss": 4.0127,
"step": 1051136
},
{
"epoch": 1.02,
"learning_rate": 3.2781373107183546e-05,
"loss": 4.0198,
"step": 1051648
},
{
"epoch": 1.02,
"learning_rate": 3.277298715967303e-05,
"loss": 4.0052,
"step": 1052160
},
{
"epoch": 1.02,
"learning_rate": 3.276460121216251e-05,
"loss": 4.0068,
"step": 1052672
},
{
"epoch": 1.02,
"learning_rate": 3.275621526465199e-05,
"loss": 4.0006,
"step": 1053184
},
{
"epoch": 1.02,
"learning_rate": 3.2747829317141466e-05,
"loss": 4.0098,
"step": 1053696
},
{
"epoch": 1.02,
"learning_rate": 3.2739443369630946e-05,
"loss": 4.0042,
"step": 1054208
},
{
"epoch": 1.02,
"learning_rate": 3.2731057422120426e-05,
"loss": 3.9994,
"step": 1054720
},
{
"epoch": 1.02,
"learning_rate": 3.2722671474609906e-05,
"loss": 4.0048,
"step": 1055232
},
{
"epoch": 1.02,
"learning_rate": 3.2714301905903115e-05,
"loss": 4.0147,
"step": 1055744
},
{
"epoch": 1.02,
"learning_rate": 3.2705915958392595e-05,
"loss": 4.0072,
"step": 1056256
},
{
"epoch": 1.02,
"learning_rate": 3.2697530010882075e-05,
"loss": 4.0049,
"step": 1056768
},
{
"epoch": 1.02,
"learning_rate": 3.268916044217529e-05,
"loss": 3.9952,
"step": 1057280
},
{
"epoch": 1.02,
"learning_rate": 3.268077449466477e-05,
"loss": 3.9988,
"step": 1057792
},
{
"epoch": 1.02,
"learning_rate": 3.267238854715425e-05,
"loss": 4.0113,
"step": 1058304
},
{
"epoch": 1.02,
"learning_rate": 3.266400259964373e-05,
"loss": 4.0078,
"step": 1058816
},
{
"epoch": 1.02,
"learning_rate": 3.265563303093694e-05,
"loss": 4.0148,
"step": 1059328
},
{
"epoch": 1.02,
"learning_rate": 3.264724708342642e-05,
"loss": 3.9893,
"step": 1059840
},
{
"epoch": 1.02,
"learning_rate": 3.2638877514719636e-05,
"loss": 4.0106,
"step": 1060352
},
{
"epoch": 1.02,
"learning_rate": 3.2630491567209115e-05,
"loss": 4.009,
"step": 1060864
},
{
"epoch": 1.02,
"learning_rate": 3.262210561969859e-05,
"loss": 4.0117,
"step": 1061376
},
{
"epoch": 1.02,
"learning_rate": 3.261371967218807e-05,
"loss": 4.001,
"step": 1061888
},
{
"epoch": 1.02,
"learning_rate": 3.260533372467755e-05,
"loss": 4.0022,
"step": 1062400
},
{
"epoch": 1.02,
"learning_rate": 3.259694777716703e-05,
"loss": 4.0127,
"step": 1062912
},
{
"epoch": 1.02,
"learning_rate": 3.258856182965651e-05,
"loss": 4.0205,
"step": 1063424
},
{
"epoch": 1.02,
"learning_rate": 3.258017588214599e-05,
"loss": 4.0026,
"step": 1063936
},
{
"epoch": 1.02,
"learning_rate": 3.2571806313439204e-05,
"loss": 4.0064,
"step": 1064448
},
{
"epoch": 1.02,
"learning_rate": 3.2563420365928684e-05,
"loss": 4.0049,
"step": 1064960
},
{
"epoch": 1.02,
"learning_rate": 3.2555034418418164e-05,
"loss": 4.0081,
"step": 1065472
},
{
"epoch": 1.02,
"learning_rate": 3.2546648470907644e-05,
"loss": 4.002,
"step": 1065984
},
{
"epoch": 1.02,
"learning_rate": 3.253827890220085e-05,
"loss": 4.0084,
"step": 1066496
},
{
"epoch": 1.02,
"learning_rate": 3.252989295469033e-05,
"loss": 3.9988,
"step": 1067008
},
{
"epoch": 1.02,
"learning_rate": 3.252150700717981e-05,
"loss": 4.0023,
"step": 1067520
},
{
"epoch": 1.02,
"learning_rate": 3.251312105966929e-05,
"loss": 4.009,
"step": 1068032
},
{
"epoch": 1.03,
"eval_loss": 4.053941249847412,
"eval_runtime": 332.4431,
"eval_samples_per_second": 1147.839,
"eval_steps_per_second": 35.871,
"step": 1068480
},
{
"epoch": 0.0,
"learning_rate": 3.250473511215877e-05,
"loss": 3.9981,
"step": 1068544
},
{
"epoch": 0.0,
"learning_rate": 3.249634916464825e-05,
"loss": 3.999,
"step": 1069056
},
{
"epoch": 0.0,
"learning_rate": 3.248796321713773e-05,
"loss": 4.0001,
"step": 1069568
},
{
"epoch": 0.0,
"learning_rate": 3.247957726962721e-05,
"loss": 4.0115,
"step": 1070080
},
{
"epoch": 0.0,
"learning_rate": 3.247119132211669e-05,
"loss": 4.0074,
"step": 1070592
},
{
"epoch": 0.0,
"learning_rate": 3.246280537460617e-05,
"loss": 4.0146,
"step": 1071104
},
{
"epoch": 0.0,
"learning_rate": 3.245441942709565e-05,
"loss": 3.9976,
"step": 1071616
},
{
"epoch": 0.0,
"learning_rate": 3.244603347958513e-05,
"loss": 4.0103,
"step": 1072128
},
{
"epoch": 0.0,
"learning_rate": 3.243764753207461e-05,
"loss": 4.001,
"step": 1072640
},
{
"epoch": 0.0,
"learning_rate": 3.242926158456409e-05,
"loss": 4.0048,
"step": 1073152
},
{
"epoch": 0.0,
"learning_rate": 3.242087563705357e-05,
"loss": 4.005,
"step": 1073664
},
{
"epoch": 0.0,
"learning_rate": 3.241248968954305e-05,
"loss": 4.0075,
"step": 1074176
},
{
"epoch": 0.0,
"learning_rate": 3.240412012083626e-05,
"loss": 4.0196,
"step": 1074688
},
{
"epoch": 0.0,
"learning_rate": 3.239573417332574e-05,
"loss": 3.9988,
"step": 1075200
},
{
"epoch": 0.0,
"learning_rate": 3.238734822581522e-05,
"loss": 3.9865,
"step": 1075712
},
{
"epoch": 0.0,
"learning_rate": 3.23789622783047e-05,
"loss": 3.9973,
"step": 1076224
},
{
"epoch": 0.0,
"learning_rate": 3.237057633079418e-05,
"loss": 4.0027,
"step": 1076736
},
{
"epoch": 0.0,
"learning_rate": 3.236219038328366e-05,
"loss": 4.0024,
"step": 1077248
},
{
"epoch": 0.0,
"learning_rate": 3.235380443577314e-05,
"loss": 3.9975,
"step": 1077760
},
{
"epoch": 0.0,
"learning_rate": 3.234541848826262e-05,
"loss": 4.0094,
"step": 1078272
},
{
"epoch": 0.0,
"learning_rate": 3.23370325407521e-05,
"loss": 4.0187,
"step": 1078784
},
{
"epoch": 0.0,
"learning_rate": 3.232864659324159e-05,
"loss": 4.0068,
"step": 1079296
},
{
"epoch": 0.0,
"learning_rate": 3.232026064573107e-05,
"loss": 4.0088,
"step": 1079808
},
{
"epoch": 0.0,
"learning_rate": 3.231187469822054e-05,
"loss": 4.0063,
"step": 1080320
},
{
"epoch": 0.0,
"learning_rate": 3.230350512951376e-05,
"loss": 4.0148,
"step": 1080832
},
{
"epoch": 0.0,
"learning_rate": 3.229511918200324e-05,
"loss": 4.0003,
"step": 1081344
},
{
"epoch": 0.0,
"learning_rate": 3.228673323449272e-05,
"loss": 4.002,
"step": 1081856
},
{
"epoch": 0.0,
"learning_rate": 3.227834728698219e-05,
"loss": 4.0079,
"step": 1082368
},
{
"epoch": 0.0,
"learning_rate": 3.226996133947167e-05,
"loss": 3.9906,
"step": 1082880
},
{
"epoch": 0.0,
"learning_rate": 3.2261591770764886e-05,
"loss": 3.9947,
"step": 1083392
},
{
"epoch": 0.01,
"learning_rate": 3.2253205823254366e-05,
"loss": 4.0017,
"step": 1083904
},
{
"epoch": 0.01,
"learning_rate": 3.2244836254547575e-05,
"loss": 4.0036,
"step": 1084416
},
{
"epoch": 0.01,
"learning_rate": 3.2236450307037055e-05,
"loss": 4.0112,
"step": 1084928
},
{
"epoch": 0.01,
"learning_rate": 3.222806435952654e-05,
"loss": 3.9994,
"step": 1085440
},
{
"epoch": 0.01,
"learning_rate": 3.2219678412016015e-05,
"loss": 4.01,
"step": 1085952
},
{
"epoch": 0.01,
"learning_rate": 3.221130884330923e-05,
"loss": 3.9997,
"step": 1086464
},
{
"epoch": 0.01,
"learning_rate": 3.220292289579871e-05,
"loss": 3.9961,
"step": 1086976
},
{
"epoch": 0.01,
"learning_rate": 3.219453694828819e-05,
"loss": 3.9873,
"step": 1087488
},
{
"epoch": 0.01,
"learning_rate": 3.2186151000777664e-05,
"loss": 4.0055,
"step": 1088000
},
{
"epoch": 0.01,
"learning_rate": 3.2177765053267144e-05,
"loss": 3.9908,
"step": 1088512
},
{
"epoch": 0.01,
"learning_rate": 3.216939548456036e-05,
"loss": 3.9975,
"step": 1089024
},
{
"epoch": 0.01,
"learning_rate": 3.216100953704984e-05,
"loss": 4.0043,
"step": 1089536
},
{
"epoch": 0.01,
"learning_rate": 3.215262358953931e-05,
"loss": 4.0111,
"step": 1090048
},
{
"epoch": 0.01,
"learning_rate": 3.214423764202879e-05,
"loss": 3.9958,
"step": 1090560
},
{
"epoch": 0.01,
"learning_rate": 3.213585169451828e-05,
"loss": 4.0041,
"step": 1091072
},
{
"epoch": 0.01,
"learning_rate": 3.212746574700776e-05,
"loss": 4.0026,
"step": 1091584
},
{
"epoch": 0.01,
"learning_rate": 3.211907979949724e-05,
"loss": 3.9941,
"step": 1092096
},
{
"epoch": 0.01,
"learning_rate": 3.211071023079045e-05,
"loss": 4.0006,
"step": 1092608
},
{
"epoch": 0.01,
"learning_rate": 3.210232428327993e-05,
"loss": 3.9903,
"step": 1093120
},
{
"epoch": 0.01,
"learning_rate": 3.209393833576941e-05,
"loss": 3.9936,
"step": 1093632
},
{
"epoch": 0.01,
"learning_rate": 3.208555238825889e-05,
"loss": 4.0102,
"step": 1094144
},
{
"epoch": 0.01,
"learning_rate": 3.207716644074837e-05,
"loss": 3.997,
"step": 1094656
},
{
"epoch": 0.01,
"learning_rate": 3.206878049323785e-05,
"loss": 3.992,
"step": 1095168
},
{
"epoch": 0.01,
"learning_rate": 3.206039454572733e-05,
"loss": 3.9796,
"step": 1095680
},
{
"epoch": 0.01,
"learning_rate": 3.205202497702054e-05,
"loss": 3.9971,
"step": 1096192
},
{
"epoch": 0.01,
"learning_rate": 3.204363902951002e-05,
"loss": 3.9784,
"step": 1096704
},
{
"epoch": 0.01,
"learning_rate": 3.20352530819995e-05,
"loss": 4.0191,
"step": 1097216
},
{
"epoch": 0.01,
"learning_rate": 3.202686713448898e-05,
"loss": 3.9861,
"step": 1097728
},
{
"epoch": 0.01,
"learning_rate": 3.2018481186978464e-05,
"loss": 4.0147,
"step": 1098240
},
{
"epoch": 0.01,
"learning_rate": 3.2010095239467944e-05,
"loss": 3.999,
"step": 1098752
},
{
"epoch": 0.01,
"learning_rate": 3.2001709291957424e-05,
"loss": 3.9817,
"step": 1099264
},
{
"epoch": 0.01,
"learning_rate": 3.1993323344446904e-05,
"loss": 3.9917,
"step": 1099776
},
{
"epoch": 0.01,
"learning_rate": 3.198493739693638e-05,
"loss": 3.9977,
"step": 1100288
},
{
"epoch": 0.01,
"learning_rate": 3.197655144942586e-05,
"loss": 3.9877,
"step": 1100800
},
{
"epoch": 0.01,
"learning_rate": 3.196818188071907e-05,
"loss": 3.9826,
"step": 1101312
},
{
"epoch": 0.01,
"learning_rate": 3.195979593320855e-05,
"loss": 4.008,
"step": 1101824
},
{
"epoch": 0.01,
"learning_rate": 3.1951409985698026e-05,
"loss": 4.0017,
"step": 1102336
},
{
"epoch": 0.01,
"learning_rate": 3.1943024038187506e-05,
"loss": 3.9895,
"step": 1102848
},
{
"epoch": 0.01,
"learning_rate": 3.193465446948072e-05,
"loss": 3.9827,
"step": 1103360
},
{
"epoch": 0.01,
"learning_rate": 3.19262685219702e-05,
"loss": 3.9895,
"step": 1103872
},
{
"epoch": 0.01,
"learning_rate": 3.191788257445968e-05,
"loss": 3.9936,
"step": 1104384
},
{
"epoch": 0.01,
"learning_rate": 3.190949662694916e-05,
"loss": 4.007,
"step": 1104896
},
{
"epoch": 0.01,
"learning_rate": 3.190112705824238e-05,
"loss": 3.9987,
"step": 1105408
},
{
"epoch": 0.01,
"learning_rate": 3.189274111073185e-05,
"loss": 4.0006,
"step": 1105920
},
{
"epoch": 0.01,
"learning_rate": 3.188435516322133e-05,
"loss": 4.0018,
"step": 1106432
},
{
"epoch": 0.01,
"learning_rate": 3.187596921571081e-05,
"loss": 3.9959,
"step": 1106944
},
{
"epoch": 0.01,
"learning_rate": 3.186758326820029e-05,
"loss": 4.0019,
"step": 1107456
},
{
"epoch": 0.01,
"learning_rate": 3.185919732068977e-05,
"loss": 3.9901,
"step": 1107968
},
{
"epoch": 0.01,
"learning_rate": 3.185081137317925e-05,
"loss": 3.9991,
"step": 1108480
},
{
"epoch": 0.01,
"learning_rate": 3.184242542566873e-05,
"loss": 3.9916,
"step": 1108992
},
{
"epoch": 0.01,
"learning_rate": 3.183403947815821e-05,
"loss": 3.9934,
"step": 1109504
},
{
"epoch": 0.01,
"learning_rate": 3.1825686288255155e-05,
"loss": 4.0033,
"step": 1110016
},
{
"epoch": 0.01,
"learning_rate": 3.1817300340744635e-05,
"loss": 4.0077,
"step": 1110528
},
{
"epoch": 0.01,
"learning_rate": 3.1808914393234115e-05,
"loss": 3.9895,
"step": 1111040
},
{
"epoch": 0.01,
"learning_rate": 3.1800528445723595e-05,
"loss": 3.9718,
"step": 1111552
},
{
"epoch": 0.01,
"learning_rate": 3.1792142498213075e-05,
"loss": 4.0012,
"step": 1112064
},
{
"epoch": 0.01,
"learning_rate": 3.1783756550702555e-05,
"loss": 3.9936,
"step": 1112576
},
{
"epoch": 0.01,
"learning_rate": 3.1775370603192035e-05,
"loss": 3.9991,
"step": 1113088
},
{
"epoch": 0.01,
"learning_rate": 3.1766984655681515e-05,
"loss": 3.9929,
"step": 1113600
},
{
"epoch": 0.01,
"learning_rate": 3.1758615086974724e-05,
"loss": 3.9969,
"step": 1114112
},
{
"epoch": 0.02,
"learning_rate": 3.1750229139464204e-05,
"loss": 3.9912,
"step": 1114624
},
{
"epoch": 0.02,
"learning_rate": 3.1741843191953684e-05,
"loss": 3.9918,
"step": 1115136
},
{
"epoch": 0.02,
"learning_rate": 3.1733457244443164e-05,
"loss": 3.9907,
"step": 1115648
},
{
"epoch": 0.02,
"learning_rate": 3.172508767573637e-05,
"loss": 3.9965,
"step": 1116160
},
{
"epoch": 0.02,
"learning_rate": 3.171671810702959e-05,
"loss": 4.0038,
"step": 1116672
},
{
"epoch": 0.02,
"learning_rate": 3.170833215951907e-05,
"loss": 4.0071,
"step": 1117184
},
{
"epoch": 0.02,
"learning_rate": 3.169994621200855e-05,
"loss": 3.989,
"step": 1117696
},
{
"epoch": 0.02,
"learning_rate": 3.169156026449803e-05,
"loss": 3.9951,
"step": 1118208
},
{
"epoch": 0.02,
"learning_rate": 3.168317431698751e-05,
"loss": 3.9963,
"step": 1118720
},
{
"epoch": 0.02,
"learning_rate": 3.167478836947699e-05,
"loss": 3.9972,
"step": 1119232
},
{
"epoch": 0.02,
"learning_rate": 3.166640242196647e-05,
"loss": 3.994,
"step": 1119744
},
{
"epoch": 0.02,
"learning_rate": 3.165801647445595e-05,
"loss": 3.9932,
"step": 1120256
},
{
"epoch": 0.02,
"learning_rate": 3.164964690574916e-05,
"loss": 3.9927,
"step": 1120768
},
{
"epoch": 0.02,
"learning_rate": 3.164126095823864e-05,
"loss": 3.9841,
"step": 1121280
},
{
"epoch": 0.02,
"learning_rate": 3.163287501072812e-05,
"loss": 4.0005,
"step": 1121792
},
{
"epoch": 0.02,
"learning_rate": 3.16244890632176e-05,
"loss": 3.9812,
"step": 1122304
},
{
"epoch": 0.02,
"learning_rate": 3.161611949451081e-05,
"loss": 3.9885,
"step": 1122816
},
{
"epoch": 0.02,
"learning_rate": 3.160773354700029e-05,
"loss": 3.9992,
"step": 1123328
},
{
"epoch": 0.02,
"learning_rate": 3.1599347599489773e-05,
"loss": 3.9882,
"step": 1123840
},
{
"epoch": 0.02,
"learning_rate": 3.1590961651979253e-05,
"loss": 3.9885,
"step": 1124352
},
{
"epoch": 0.02,
"learning_rate": 3.1582575704468733e-05,
"loss": 4.0003,
"step": 1124864
},
{
"epoch": 0.02,
"learning_rate": 3.157420613576194e-05,
"loss": 3.9838,
"step": 1125376
},
{
"epoch": 0.02,
"learning_rate": 3.156582018825142e-05,
"loss": 3.9973,
"step": 1125888
},
{
"epoch": 0.02,
"learning_rate": 3.15574342407409e-05,
"loss": 3.9917,
"step": 1126400
},
{
"epoch": 0.02,
"learning_rate": 3.154904829323038e-05,
"loss": 3.993,
"step": 1126912
},
{
"epoch": 0.02,
"learning_rate": 3.154067872452359e-05,
"loss": 3.9988,
"step": 1127424
},
{
"epoch": 0.02,
"learning_rate": 3.15323091558168e-05,
"loss": 4.0034,
"step": 1127936
},
{
"epoch": 0.02,
"learning_rate": 3.152392320830628e-05,
"loss": 3.9963,
"step": 1128448
},
{
"epoch": 0.02,
"learning_rate": 3.151553726079576e-05,
"loss": 3.991,
"step": 1128960
},
{
"epoch": 0.02,
"learning_rate": 3.150715131328524e-05,
"loss": 3.9896,
"step": 1129472
},
{
"epoch": 0.02,
"learning_rate": 3.149876536577473e-05,
"loss": 3.9995,
"step": 1129984
},
{
"epoch": 0.02,
"learning_rate": 3.149037941826421e-05,
"loss": 3.9903,
"step": 1130496
},
{
"epoch": 0.02,
"learning_rate": 3.148199347075369e-05,
"loss": 3.9909,
"step": 1131008
},
{
"epoch": 0.02,
"learning_rate": 3.1473623902046896e-05,
"loss": 3.9912,
"step": 1131520
},
{
"epoch": 0.02,
"learning_rate": 3.1465237954536376e-05,
"loss": 4.0006,
"step": 1132032
},
{
"epoch": 0.02,
"learning_rate": 3.1456852007025856e-05,
"loss": 3.9924,
"step": 1132544
},
{
"epoch": 0.02,
"learning_rate": 3.1448466059515336e-05,
"loss": 3.9927,
"step": 1133056
},
{
"epoch": 0.02,
"learning_rate": 3.144008011200481e-05,
"loss": 3.9856,
"step": 1133568
},
{
"epoch": 0.02,
"learning_rate": 3.1431726922101754e-05,
"loss": 3.9873,
"step": 1134080
},
{
"epoch": 0.02,
"learning_rate": 3.1423340974591234e-05,
"loss": 3.9917,
"step": 1134592
},
{
"epoch": 0.02,
"learning_rate": 3.1414955027080714e-05,
"loss": 3.9986,
"step": 1135104
},
{
"epoch": 0.02,
"learning_rate": 3.1406569079570194e-05,
"loss": 3.9997,
"step": 1135616
},
{
"epoch": 0.02,
"learning_rate": 3.139818313205968e-05,
"loss": 3.9806,
"step": 1136128
},
{
"epoch": 0.02,
"learning_rate": 3.138981356335289e-05,
"loss": 3.9993,
"step": 1136640
},
{
"epoch": 0.02,
"learning_rate": 3.138142761584237e-05,
"loss": 3.9947,
"step": 1137152
},
{
"epoch": 0.02,
"learning_rate": 3.137304166833185e-05,
"loss": 3.9972,
"step": 1137664
},
{
"epoch": 0.02,
"learning_rate": 3.136465572082133e-05,
"loss": 3.9872,
"step": 1138176
},
{
"epoch": 0.02,
"learning_rate": 3.135626977331081e-05,
"loss": 3.9909,
"step": 1138688
},
{
"epoch": 0.02,
"learning_rate": 3.134788382580028e-05,
"loss": 3.9977,
"step": 1139200
},
{
"epoch": 0.02,
"learning_rate": 3.133949787828976e-05,
"loss": 4.0054,
"step": 1139712
},
{
"epoch": 0.02,
"learning_rate": 3.133111193077924e-05,
"loss": 3.9915,
"step": 1140224
},
{
"epoch": 0.02,
"learning_rate": 3.132274236207245e-05,
"loss": 3.9924,
"step": 1140736
},
{
"epoch": 0.02,
"learning_rate": 3.131435641456193e-05,
"loss": 3.9957,
"step": 1141248
},
{
"epoch": 0.02,
"learning_rate": 3.130597046705142e-05,
"loss": 3.9906,
"step": 1141760
},
{
"epoch": 0.02,
"learning_rate": 3.12975845195409e-05,
"loss": 3.9865,
"step": 1142272
},
{
"epoch": 0.02,
"learning_rate": 3.128921495083411e-05,
"loss": 3.9983,
"step": 1142784
},
{
"epoch": 0.02,
"learning_rate": 3.128082900332359e-05,
"loss": 3.9827,
"step": 1143296
},
{
"epoch": 0.02,
"learning_rate": 3.1272459434616803e-05,
"loss": 3.9981,
"step": 1143808
},
{
"epoch": 0.02,
"learning_rate": 3.1264073487106283e-05,
"loss": 3.9899,
"step": 1144320
},
{
"epoch": 0.03,
"eval_loss": 4.046820163726807,
"eval_runtime": 293.3769,
"eval_samples_per_second": 1300.685,
"eval_steps_per_second": 40.647,
"step": 1144800
},
{
"epoch": 0.0,
"learning_rate": 3.125570391839949e-05,
"loss": 3.9719,
"step": 1144832
},
{
"epoch": 0.0,
"learning_rate": 3.124731797088897e-05,
"loss": 3.9883,
"step": 1145344
},
{
"epoch": 0.0,
"learning_rate": 3.123893202337845e-05,
"loss": 3.9841,
"step": 1145856
},
{
"epoch": 0.0,
"learning_rate": 3.1230546075867926e-05,
"loss": 3.9974,
"step": 1146368
},
{
"epoch": 0.0,
"learning_rate": 3.1222160128357406e-05,
"loss": 3.9937,
"step": 1146880
},
{
"epoch": 0.0,
"learning_rate": 3.1213774180846886e-05,
"loss": 4.0015,
"step": 1147392
},
{
"epoch": 0.0,
"learning_rate": 3.120538823333637e-05,
"loss": 3.9866,
"step": 1147904
},
{
"epoch": 0.0,
"learning_rate": 3.119700228582585e-05,
"loss": 3.9986,
"step": 1148416
},
{
"epoch": 0.0,
"learning_rate": 3.118861633831533e-05,
"loss": 3.987,
"step": 1148928
},
{
"epoch": 0.0,
"learning_rate": 3.118024676960854e-05,
"loss": 3.9934,
"step": 1149440
},
{
"epoch": 0.0,
"learning_rate": 3.117186082209802e-05,
"loss": 3.992,
"step": 1149952
},
{
"epoch": 0.0,
"learning_rate": 3.11634748745875e-05,
"loss": 3.9976,
"step": 1150464
},
{
"epoch": 0.0,
"learning_rate": 3.115508892707698e-05,
"loss": 3.9988,
"step": 1150976
},
{
"epoch": 0.0,
"learning_rate": 3.114670297956646e-05,
"loss": 3.9914,
"step": 1151488
},
{
"epoch": 0.0,
"learning_rate": 3.113831703205594e-05,
"loss": 3.9781,
"step": 1152000
},
{
"epoch": 0.0,
"learning_rate": 3.112993108454542e-05,
"loss": 3.9849,
"step": 1152512
},
{
"epoch": 0.0,
"learning_rate": 3.11215451370349e-05,
"loss": 3.9836,
"step": 1153024
},
{
"epoch": 0.0,
"learning_rate": 3.111315918952438e-05,
"loss": 3.9892,
"step": 1153536
},
{
"epoch": 0.0,
"learning_rate": 3.110477324201386e-05,
"loss": 3.9865,
"step": 1154048
},
{
"epoch": 0.0,
"learning_rate": 3.109638729450334e-05,
"loss": 3.992,
"step": 1154560
},
{
"epoch": 0.0,
"learning_rate": 3.108800134699282e-05,
"loss": 4.0084,
"step": 1155072
},
{
"epoch": 0.0,
"learning_rate": 3.107963177828604e-05,
"loss": 3.9933,
"step": 1155584
},
{
"epoch": 0.0,
"learning_rate": 3.107124583077552e-05,
"loss": 3.9966,
"step": 1156096
},
{
"epoch": 0.0,
"learning_rate": 3.1062859883264997e-05,
"loss": 3.9953,
"step": 1156608
},
{
"epoch": 0.0,
"learning_rate": 3.105447393575447e-05,
"loss": 4.0032,
"step": 1157120
},
{
"epoch": 0.0,
"learning_rate": 3.104608798824395e-05,
"loss": 3.9853,
"step": 1157632
},
{
"epoch": 0.0,
"learning_rate": 3.103770204073343e-05,
"loss": 3.9897,
"step": 1158144
},
{
"epoch": 0.0,
"learning_rate": 3.102931609322291e-05,
"loss": 3.9938,
"step": 1158656
},
{
"epoch": 0.0,
"learning_rate": 3.102093014571239e-05,
"loss": 3.9836,
"step": 1159168
},
{
"epoch": 0.0,
"learning_rate": 3.1012576955809335e-05,
"loss": 3.9775,
"step": 1159680
},
{
"epoch": 0.01,
"learning_rate": 3.1004191008298815e-05,
"loss": 3.9874,
"step": 1160192
},
{
"epoch": 0.01,
"learning_rate": 3.099580506078829e-05,
"loss": 3.9938,
"step": 1160704
},
{
"epoch": 0.01,
"learning_rate": 3.0987419113277774e-05,
"loss": 3.9946,
"step": 1161216
},
{
"epoch": 0.01,
"learning_rate": 3.0979033165767254e-05,
"loss": 3.9886,
"step": 1161728
},
{
"epoch": 0.01,
"learning_rate": 3.0970647218256734e-05,
"loss": 3.994,
"step": 1162240
},
{
"epoch": 0.01,
"learning_rate": 3.0962277649549943e-05,
"loss": 3.9888,
"step": 1162752
},
{
"epoch": 0.01,
"learning_rate": 3.0953891702039423e-05,
"loss": 3.9829,
"step": 1163264
},
{
"epoch": 0.01,
"learning_rate": 3.09455057545289e-05,
"loss": 3.9758,
"step": 1163776
},
{
"epoch": 0.01,
"learning_rate": 3.093711980701838e-05,
"loss": 3.9928,
"step": 1164288
},
{
"epoch": 0.01,
"learning_rate": 3.092873385950786e-05,
"loss": 3.9786,
"step": 1164800
},
{
"epoch": 0.01,
"learning_rate": 3.092034791199734e-05,
"loss": 3.9877,
"step": 1165312
},
{
"epoch": 0.01,
"learning_rate": 3.091196196448682e-05,
"loss": 3.9857,
"step": 1165824
},
{
"epoch": 0.01,
"learning_rate": 3.09035760169763e-05,
"loss": 4.0024,
"step": 1166336
},
{
"epoch": 0.01,
"learning_rate": 3.089519006946578e-05,
"loss": 3.9809,
"step": 1166848
},
{
"epoch": 0.01,
"learning_rate": 3.088682050075899e-05,
"loss": 3.9896,
"step": 1167360
},
{
"epoch": 0.01,
"learning_rate": 3.087843455324847e-05,
"loss": 3.991,
"step": 1167872
},
{
"epoch": 0.01,
"learning_rate": 3.087004860573796e-05,
"loss": 3.9791,
"step": 1168384
},
{
"epoch": 0.01,
"learning_rate": 3.086166265822744e-05,
"loss": 3.9915,
"step": 1168896
},
{
"epoch": 0.01,
"learning_rate": 3.085327671071692e-05,
"loss": 3.9756,
"step": 1169408
},
{
"epoch": 0.01,
"learning_rate": 3.084490714201013e-05,
"loss": 3.9833,
"step": 1169920
},
{
"epoch": 0.01,
"learning_rate": 3.083652119449961e-05,
"loss": 3.9929,
"step": 1170432
},
{
"epoch": 0.01,
"learning_rate": 3.082813524698909e-05,
"loss": 3.9857,
"step": 1170944
},
{
"epoch": 0.01,
"learning_rate": 3.081974929947857e-05,
"loss": 3.981,
"step": 1171456
},
{
"epoch": 0.01,
"learning_rate": 3.081136335196805e-05,
"loss": 3.9672,
"step": 1171968
},
{
"epoch": 0.01,
"learning_rate": 3.080299378326126e-05,
"loss": 3.9865,
"step": 1172480
},
{
"epoch": 0.01,
"learning_rate": 3.0794624214554466e-05,
"loss": 3.9675,
"step": 1172992
},
{
"epoch": 0.01,
"learning_rate": 3.0786238267043946e-05,
"loss": 4.0035,
"step": 1173504
},
{
"epoch": 0.01,
"learning_rate": 3.077786869833716e-05,
"loss": 3.978,
"step": 1174016
},
{
"epoch": 0.01,
"learning_rate": 3.076948275082664e-05,
"loss": 3.9964,
"step": 1174528
},
{
"epoch": 0.01,
"learning_rate": 3.076109680331612e-05,
"loss": 3.993,
"step": 1175040
},
{
"epoch": 0.01,
"learning_rate": 3.07527108558056e-05,
"loss": 3.9725,
"step": 1175552
},
{
"epoch": 0.01,
"learning_rate": 3.074432490829508e-05,
"loss": 3.9764,
"step": 1176064
},
{
"epoch": 0.01,
"learning_rate": 3.073593896078456e-05,
"loss": 3.9855,
"step": 1176576
},
{
"epoch": 0.01,
"learning_rate": 3.072755301327404e-05,
"loss": 3.9746,
"step": 1177088
},
{
"epoch": 0.01,
"learning_rate": 3.071916706576352e-05,
"loss": 3.9691,
"step": 1177600
},
{
"epoch": 0.01,
"learning_rate": 3.0710781118253e-05,
"loss": 3.9957,
"step": 1178112
},
{
"epoch": 0.01,
"learning_rate": 3.0702395170742475e-05,
"loss": 3.9932,
"step": 1178624
},
{
"epoch": 0.01,
"learning_rate": 3.0694009223231955e-05,
"loss": 3.9784,
"step": 1179136
},
{
"epoch": 0.01,
"learning_rate": 3.0685623275721434e-05,
"loss": 3.9673,
"step": 1179648
},
{
"epoch": 0.01,
"learning_rate": 3.067725370701465e-05,
"loss": 3.9762,
"step": 1180160
},
{
"epoch": 0.01,
"learning_rate": 3.0668884138307866e-05,
"loss": 3.9828,
"step": 1180672
},
{
"epoch": 0.01,
"learning_rate": 3.0660498190797346e-05,
"loss": 3.9974,
"step": 1181184
},
{
"epoch": 0.01,
"learning_rate": 3.0652112243286826e-05,
"loss": 3.9862,
"step": 1181696
},
{
"epoch": 0.01,
"learning_rate": 3.0643726295776306e-05,
"loss": 3.9869,
"step": 1182208
},
{
"epoch": 0.01,
"learning_rate": 3.063534034826578e-05,
"loss": 3.9851,
"step": 1182720
},
{
"epoch": 0.01,
"learning_rate": 3.062695440075526e-05,
"loss": 3.9885,
"step": 1183232
},
{
"epoch": 0.01,
"learning_rate": 3.061856845324474e-05,
"loss": 3.986,
"step": 1183744
},
{
"epoch": 0.01,
"learning_rate": 3.061018250573422e-05,
"loss": 3.9815,
"step": 1184256
},
{
"epoch": 0.01,
"learning_rate": 3.060181293702743e-05,
"loss": 3.9873,
"step": 1184768
},
{
"epoch": 0.01,
"learning_rate": 3.0593443368320644e-05,
"loss": 3.9767,
"step": 1185280
},
{
"epoch": 0.01,
"learning_rate": 3.0585057420810124e-05,
"loss": 3.9821,
"step": 1185792
},
{
"epoch": 0.01,
"learning_rate": 3.0576671473299604e-05,
"loss": 3.9918,
"step": 1186304
},
{
"epoch": 0.01,
"learning_rate": 3.0568285525789084e-05,
"loss": 3.9909,
"step": 1186816
},
{
"epoch": 0.01,
"learning_rate": 3.0559899578278564e-05,
"loss": 3.9803,
"step": 1187328
},
{
"epoch": 0.01,
"learning_rate": 3.0551513630768044e-05,
"loss": 3.959,
"step": 1187840
},
{
"epoch": 0.01,
"learning_rate": 3.0543127683257524e-05,
"loss": 3.9878,
"step": 1188352
},
{
"epoch": 0.01,
"learning_rate": 3.0534741735747004e-05,
"loss": 3.9845,
"step": 1188864
},
{
"epoch": 0.01,
"learning_rate": 3.052637216704021e-05,
"loss": 3.9821,
"step": 1189376
},
{
"epoch": 0.01,
"learning_rate": 3.051798621952969e-05,
"loss": 3.9849,
"step": 1189888
},
{
"epoch": 0.01,
"learning_rate": 3.0509600272019173e-05,
"loss": 3.9847,
"step": 1190400
},
{
"epoch": 0.02,
"learning_rate": 3.0501214324508653e-05,
"loss": 3.9812,
"step": 1190912
},
{
"epoch": 0.02,
"learning_rate": 3.0492844755801865e-05,
"loss": 3.9738,
"step": 1191424
},
{
"epoch": 0.02,
"learning_rate": 3.0484458808291345e-05,
"loss": 3.9788,
"step": 1191936
},
{
"epoch": 0.02,
"learning_rate": 3.0476072860780825e-05,
"loss": 3.9861,
"step": 1192448
},
{
"epoch": 0.02,
"learning_rate": 3.0467686913270305e-05,
"loss": 3.9927,
"step": 1192960
},
{
"epoch": 0.02,
"learning_rate": 3.0459300965759785e-05,
"loss": 3.992,
"step": 1193472
},
{
"epoch": 0.02,
"learning_rate": 3.0450931397052994e-05,
"loss": 3.9851,
"step": 1193984
},
{
"epoch": 0.02,
"learning_rate": 3.0442561828346207e-05,
"loss": 3.9776,
"step": 1194496
},
{
"epoch": 0.02,
"learning_rate": 3.0434175880835687e-05,
"loss": 3.9835,
"step": 1195008
},
{
"epoch": 0.02,
"learning_rate": 3.0425789933325167e-05,
"loss": 3.9875,
"step": 1195520
},
{
"epoch": 0.02,
"learning_rate": 3.0417403985814647e-05,
"loss": 3.9842,
"step": 1196032
},
{
"epoch": 0.02,
"learning_rate": 3.0409018038304126e-05,
"loss": 3.9804,
"step": 1196544
},
{
"epoch": 0.02,
"learning_rate": 3.0400632090793606e-05,
"loss": 3.9809,
"step": 1197056
},
{
"epoch": 0.02,
"learning_rate": 3.0392246143283086e-05,
"loss": 3.969,
"step": 1197568
},
{
"epoch": 0.02,
"learning_rate": 3.0383860195772566e-05,
"loss": 3.9888,
"step": 1198080
},
{
"epoch": 0.02,
"learning_rate": 3.037547424826205e-05,
"loss": 3.9655,
"step": 1198592
},
{
"epoch": 0.02,
"learning_rate": 3.0367121058358988e-05,
"loss": 3.9771,
"step": 1199104
},
{
"epoch": 0.02,
"learning_rate": 3.0358735110848468e-05,
"loss": 3.9859,
"step": 1199616
},
{
"epoch": 0.02,
"learning_rate": 3.0350349163337948e-05,
"loss": 3.9797,
"step": 1200128
},
{
"epoch": 0.02,
"learning_rate": 3.0341963215827428e-05,
"loss": 3.9758,
"step": 1200640
},
{
"epoch": 0.02,
"learning_rate": 3.033357726831691e-05,
"loss": 3.9823,
"step": 1201152
},
{
"epoch": 0.02,
"learning_rate": 3.032519132080639e-05,
"loss": 3.9793,
"step": 1201664
},
{
"epoch": 0.02,
"learning_rate": 3.03168217520996e-05,
"loss": 3.9838,
"step": 1202176
},
{
"epoch": 0.02,
"learning_rate": 3.030843580458908e-05,
"loss": 3.9809,
"step": 1202688
},
{
"epoch": 0.02,
"learning_rate": 3.030004985707856e-05,
"loss": 3.9822,
"step": 1203200
},
{
"epoch": 0.02,
"learning_rate": 3.029166390956804e-05,
"loss": 3.9867,
"step": 1203712
},
{
"epoch": 0.02,
"learning_rate": 3.028327796205752e-05,
"loss": 3.9943,
"step": 1204224
},
{
"epoch": 0.02,
"learning_rate": 3.0274908393350732e-05,
"loss": 3.9818,
"step": 1204736
},
{
"epoch": 0.02,
"learning_rate": 3.0266522445840212e-05,
"loss": 3.9774,
"step": 1205248
},
{
"epoch": 0.02,
"learning_rate": 3.0258136498329692e-05,
"loss": 3.9817,
"step": 1205760
},
{
"epoch": 0.02,
"learning_rate": 3.0249750550819172e-05,
"loss": 3.9842,
"step": 1206272
},
{
"epoch": 0.02,
"learning_rate": 3.0241364603308652e-05,
"loss": 3.977,
"step": 1206784
},
{
"epoch": 0.02,
"learning_rate": 3.0232978655798132e-05,
"loss": 3.9774,
"step": 1207296
},
{
"epoch": 0.02,
"learning_rate": 3.0224609087091345e-05,
"loss": 3.9802,
"step": 1207808
},
{
"epoch": 0.02,
"learning_rate": 3.0216223139580825e-05,
"loss": 3.9893,
"step": 1208320
},
{
"epoch": 0.02,
"learning_rate": 3.0207837192070305e-05,
"loss": 3.9812,
"step": 1208832
},
{
"epoch": 0.02,
"learning_rate": 3.0199451244559785e-05,
"loss": 3.9805,
"step": 1209344
},
{
"epoch": 0.02,
"learning_rate": 3.0191065297049258e-05,
"loss": 3.972,
"step": 1209856
},
{
"epoch": 0.02,
"learning_rate": 3.0182679349538738e-05,
"loss": 3.9791,
"step": 1210368
},
{
"epoch": 0.02,
"learning_rate": 3.017429340202822e-05,
"loss": 3.9767,
"step": 1210880
},
{
"epoch": 0.02,
"learning_rate": 3.01659074545177e-05,
"loss": 3.9903,
"step": 1211392
},
{
"epoch": 0.02,
"learning_rate": 3.015753788581091e-05,
"loss": 3.9876,
"step": 1211904
},
{
"epoch": 0.02,
"learning_rate": 3.014915193830039e-05,
"loss": 3.9678,
"step": 1212416
},
{
"epoch": 0.02,
"learning_rate": 3.014076599078987e-05,
"loss": 3.9819,
"step": 1212928
},
{
"epoch": 0.02,
"learning_rate": 3.013238004327935e-05,
"loss": 3.9884,
"step": 1213440
},
{
"epoch": 0.02,
"learning_rate": 3.01240268533763e-05,
"loss": 3.985,
"step": 1213952
},
{
"epoch": 0.02,
"learning_rate": 3.011564090586578e-05,
"loss": 3.979,
"step": 1214464
},
{
"epoch": 0.02,
"learning_rate": 3.010725495835526e-05,
"loss": 3.9766,
"step": 1214976
},
{
"epoch": 0.02,
"learning_rate": 3.009886901084473e-05,
"loss": 3.9859,
"step": 1215488
},
{
"epoch": 0.02,
"learning_rate": 3.009048306333421e-05,
"loss": 3.9932,
"step": 1216000
},
{
"epoch": 0.02,
"learning_rate": 3.008209711582369e-05,
"loss": 3.9792,
"step": 1216512
},
{
"epoch": 0.02,
"learning_rate": 3.0073711168313175e-05,
"loss": 3.9815,
"step": 1217024
},
{
"epoch": 0.02,
"learning_rate": 3.0065325220802655e-05,
"loss": 3.9819,
"step": 1217536
},
{
"epoch": 0.02,
"learning_rate": 3.0056955652095864e-05,
"loss": 3.9773,
"step": 1218048
},
{
"epoch": 0.02,
"learning_rate": 3.0048569704585344e-05,
"loss": 3.977,
"step": 1218560
},
{
"epoch": 0.02,
"learning_rate": 3.0040183757074824e-05,
"loss": 3.9884,
"step": 1219072
},
{
"epoch": 0.02,
"learning_rate": 3.0031797809564304e-05,
"loss": 3.9722,
"step": 1219584
},
{
"epoch": 0.02,
"learning_rate": 3.0023428240857516e-05,
"loss": 3.9849,
"step": 1220096
},
{
"epoch": 0.02,
"learning_rate": 3.0015042293346996e-05,
"loss": 3.978,
"step": 1220608
},
{
"epoch": 0.03,
"learning_rate": 3.0006656345836476e-05,
"loss": 3.9844,
"step": 1221120
},
{
"epoch": 0.03,
"eval_loss": 4.040874481201172,
"eval_runtime": 305.9268,
"eval_samples_per_second": 1247.328,
"eval_steps_per_second": 38.98,
"step": 1221120
},
{
"epoch": 1.0,
"learning_rate": 2.9998270398325956e-05,
"loss": 3.9724,
"step": 1221632
},
{
"epoch": 1.0,
"learning_rate": 2.9989900829619165e-05,
"loss": 3.9732,
"step": 1222144
},
{
"epoch": 1.0,
"learning_rate": 2.9981514882108645e-05,
"loss": 3.9884,
"step": 1222656
},
{
"epoch": 1.0,
"learning_rate": 2.997312893459813e-05,
"loss": 3.9811,
"step": 1223168
},
{
"epoch": 1.0,
"learning_rate": 2.996474298708761e-05,
"loss": 3.9923,
"step": 1223680
},
{
"epoch": 1.0,
"learning_rate": 2.995635703957709e-05,
"loss": 3.9737,
"step": 1224192
},
{
"epoch": 1.0,
"learning_rate": 2.9947987470870297e-05,
"loss": 3.9853,
"step": 1224704
},
{
"epoch": 1.0,
"learning_rate": 2.9939601523359777e-05,
"loss": 3.9775,
"step": 1225216
},
{
"epoch": 1.0,
"learning_rate": 2.9931215575849257e-05,
"loss": 3.9817,
"step": 1225728
},
{
"epoch": 1.0,
"learning_rate": 2.9922829628338737e-05,
"loss": 3.9795,
"step": 1226240
},
{
"epoch": 1.0,
"learning_rate": 2.991444368082822e-05,
"loss": 3.9865,
"step": 1226752
},
{
"epoch": 1.0,
"learning_rate": 2.99060577333177e-05,
"loss": 3.9873,
"step": 1227264
},
{
"epoch": 1.0,
"learning_rate": 2.989768816461091e-05,
"loss": 3.977,
"step": 1227776
},
{
"epoch": 1.0,
"learning_rate": 2.988930221710039e-05,
"loss": 3.9692,
"step": 1228288
},
{
"epoch": 1.0,
"learning_rate": 2.988091626958987e-05,
"loss": 3.9746,
"step": 1228800
},
{
"epoch": 1.0,
"learning_rate": 2.987253032207935e-05,
"loss": 3.9678,
"step": 1229312
},
{
"epoch": 1.0,
"learning_rate": 2.9864160753372562e-05,
"loss": 3.9795,
"step": 1229824
},
{
"epoch": 1.0,
"learning_rate": 2.9855774805862042e-05,
"loss": 3.9761,
"step": 1230336
},
{
"epoch": 1.0,
"learning_rate": 2.9847388858351522e-05,
"loss": 3.9793,
"step": 1230848
},
{
"epoch": 1.0,
"learning_rate": 2.9839002910841002e-05,
"loss": 4.001,
"step": 1231360
},
{
"epoch": 1.0,
"learning_rate": 2.9830616963330482e-05,
"loss": 3.983,
"step": 1231872
},
{
"epoch": 1.0,
"learning_rate": 2.9822231015819962e-05,
"loss": 3.9859,
"step": 1232384
},
{
"epoch": 1.0,
"learning_rate": 2.9813861447113174e-05,
"loss": 3.9808,
"step": 1232896
},
{
"epoch": 1.0,
"learning_rate": 2.9805475499602654e-05,
"loss": 3.9913,
"step": 1233408
},
{
"epoch": 1.0,
"learning_rate": 2.9797089552092134e-05,
"loss": 3.979,
"step": 1233920
},
{
"epoch": 1.0,
"learning_rate": 2.9788703604581614e-05,
"loss": 3.975,
"step": 1234432
},
{
"epoch": 1.0,
"learning_rate": 2.9780317657071094e-05,
"loss": 3.9824,
"step": 1234944
},
{
"epoch": 1.0,
"learning_rate": 2.9771931709560567e-05,
"loss": 3.9751,
"step": 1235456
},
{
"epoch": 1.0,
"learning_rate": 2.976354576205005e-05,
"loss": 3.9643,
"step": 1235968
},
{
"epoch": 1.01,
"learning_rate": 2.9755176193343267e-05,
"loss": 3.9768,
"step": 1236480
},
{
"epoch": 1.01,
"learning_rate": 2.974679024583274e-05,
"loss": 3.9807,
"step": 1236992
},
{
"epoch": 1.01,
"learning_rate": 2.973840429832222e-05,
"loss": 3.9852,
"step": 1237504
},
{
"epoch": 1.01,
"learning_rate": 2.97300183508117e-05,
"loss": 3.9799,
"step": 1238016
},
{
"epoch": 1.01,
"learning_rate": 2.972163240330118e-05,
"loss": 3.9851,
"step": 1238528
},
{
"epoch": 1.01,
"learning_rate": 2.9713262834594392e-05,
"loss": 3.9737,
"step": 1239040
},
{
"epoch": 1.01,
"learning_rate": 2.9704876887083872e-05,
"loss": 3.9747,
"step": 1239552
},
{
"epoch": 1.01,
"learning_rate": 2.9696507318377088e-05,
"loss": 3.9609,
"step": 1240064
},
{
"epoch": 1.01,
"learning_rate": 2.9688121370866568e-05,
"loss": 3.98,
"step": 1240576
},
{
"epoch": 1.01,
"learning_rate": 2.9679751802159777e-05,
"loss": 3.9707,
"step": 1241088
},
{
"epoch": 1.01,
"learning_rate": 2.9671365854649257e-05,
"loss": 3.9769,
"step": 1241600
},
{
"epoch": 1.01,
"learning_rate": 2.9662979907138737e-05,
"loss": 3.9758,
"step": 1242112
},
{
"epoch": 1.01,
"learning_rate": 2.9654593959628213e-05,
"loss": 3.9849,
"step": 1242624
},
{
"epoch": 1.01,
"learning_rate": 2.9646208012117693e-05,
"loss": 3.9777,
"step": 1243136
},
{
"epoch": 1.01,
"learning_rate": 2.9637822064607173e-05,
"loss": 3.9753,
"step": 1243648
},
{
"epoch": 1.01,
"learning_rate": 2.9629436117096653e-05,
"loss": 3.9815,
"step": 1244160
},
{
"epoch": 1.01,
"learning_rate": 2.9621050169586133e-05,
"loss": 3.9683,
"step": 1244672
},
{
"epoch": 1.01,
"learning_rate": 2.9612664222075613e-05,
"loss": 3.9824,
"step": 1245184
},
{
"epoch": 1.01,
"learning_rate": 2.9604278274565093e-05,
"loss": 3.9661,
"step": 1245696
},
{
"epoch": 1.01,
"learning_rate": 2.9595892327054577e-05,
"loss": 3.9699,
"step": 1246208
},
{
"epoch": 1.01,
"learning_rate": 2.9587506379544056e-05,
"loss": 3.9834,
"step": 1246720
},
{
"epoch": 1.01,
"learning_rate": 2.9579120432033536e-05,
"loss": 3.9713,
"step": 1247232
},
{
"epoch": 1.01,
"learning_rate": 2.9570734484523016e-05,
"loss": 3.9706,
"step": 1247744
},
{
"epoch": 1.01,
"learning_rate": 2.9562364915816225e-05,
"loss": 3.9604,
"step": 1248256
},
{
"epoch": 1.01,
"learning_rate": 2.9553978968305705e-05,
"loss": 3.9724,
"step": 1248768
},
{
"epoch": 1.01,
"learning_rate": 2.9545593020795185e-05,
"loss": 3.9538,
"step": 1249280
},
{
"epoch": 1.01,
"learning_rate": 2.953720707328467e-05,
"loss": 3.9932,
"step": 1249792
},
{
"epoch": 1.01,
"learning_rate": 2.952882112577415e-05,
"loss": 3.964,
"step": 1250304
},
{
"epoch": 1.01,
"learning_rate": 2.952043517826363e-05,
"loss": 3.985,
"step": 1250816
},
{
"epoch": 1.01,
"learning_rate": 2.9512049230753102e-05,
"loss": 3.9796,
"step": 1251328
},
{
"epoch": 1.01,
"learning_rate": 2.9503663283242582e-05,
"loss": 3.964,
"step": 1251840
},
{
"epoch": 1.01,
"learning_rate": 2.9495293714535798e-05,
"loss": 3.9617,
"step": 1252352
},
{
"epoch": 1.01,
"learning_rate": 2.9486907767025278e-05,
"loss": 3.9747,
"step": 1252864
},
{
"epoch": 1.01,
"learning_rate": 2.9478521819514754e-05,
"loss": 3.9628,
"step": 1253376
},
{
"epoch": 1.01,
"learning_rate": 2.9470135872004234e-05,
"loss": 3.9582,
"step": 1253888
},
{
"epoch": 1.01,
"learning_rate": 2.946178268210118e-05,
"loss": 3.9851,
"step": 1254400
},
{
"epoch": 1.01,
"learning_rate": 2.945339673459066e-05,
"loss": 3.9787,
"step": 1254912
},
{
"epoch": 1.01,
"learning_rate": 2.944501078708014e-05,
"loss": 3.9688,
"step": 1255424
},
{
"epoch": 1.01,
"learning_rate": 2.9436624839569622e-05,
"loss": 3.9575,
"step": 1255936
},
{
"epoch": 1.01,
"learning_rate": 2.9428238892059102e-05,
"loss": 3.962,
"step": 1256448
},
{
"epoch": 1.01,
"learning_rate": 2.9419852944548576e-05,
"loss": 3.9752,
"step": 1256960
},
{
"epoch": 1.01,
"learning_rate": 2.9411466997038055e-05,
"loss": 3.9808,
"step": 1257472
},
{
"epoch": 1.01,
"learning_rate": 2.940309742833127e-05,
"loss": 3.9777,
"step": 1257984
},
{
"epoch": 1.01,
"learning_rate": 2.939471148082075e-05,
"loss": 3.9757,
"step": 1258496
},
{
"epoch": 1.01,
"learning_rate": 2.9386325533310228e-05,
"loss": 3.9768,
"step": 1259008
},
{
"epoch": 1.01,
"learning_rate": 2.9377939585799708e-05,
"loss": 3.9776,
"step": 1259520
},
{
"epoch": 1.01,
"learning_rate": 2.9369570017092924e-05,
"loss": 3.9729,
"step": 1260032
},
{
"epoch": 1.01,
"learning_rate": 2.9361184069582404e-05,
"loss": 3.9732,
"step": 1260544
},
{
"epoch": 1.01,
"learning_rate": 2.9352798122071877e-05,
"loss": 3.9742,
"step": 1261056
},
{
"epoch": 1.01,
"learning_rate": 2.934441217456136e-05,
"loss": 3.9691,
"step": 1261568
},
{
"epoch": 1.01,
"learning_rate": 2.933602622705084e-05,
"loss": 3.9707,
"step": 1262080
},
{
"epoch": 1.01,
"learning_rate": 2.932764027954032e-05,
"loss": 3.977,
"step": 1262592
},
{
"epoch": 1.01,
"learning_rate": 2.93192543320298e-05,
"loss": 3.9845,
"step": 1263104
},
{
"epoch": 1.01,
"learning_rate": 2.931086838451928e-05,
"loss": 3.9673,
"step": 1263616
},
{
"epoch": 1.01,
"learning_rate": 2.930249881581249e-05,
"loss": 3.9512,
"step": 1264128
},
{
"epoch": 1.01,
"learning_rate": 2.929411286830197e-05,
"loss": 3.9733,
"step": 1264640
},
{
"epoch": 1.01,
"learning_rate": 2.9285726920791452e-05,
"loss": 3.9744,
"step": 1265152
},
{
"epoch": 1.01,
"learning_rate": 2.9277340973280932e-05,
"loss": 3.9727,
"step": 1265664
},
{
"epoch": 1.01,
"learning_rate": 2.9268955025770412e-05,
"loss": 3.9731,
"step": 1266176
},
{
"epoch": 1.01,
"learning_rate": 2.926060183586735e-05,
"loss": 3.9744,
"step": 1266688
},
{
"epoch": 1.02,
"learning_rate": 2.925221588835683e-05,
"loss": 3.967,
"step": 1267200
},
{
"epoch": 1.02,
"learning_rate": 2.9243829940846314e-05,
"loss": 3.9635,
"step": 1267712
},
{
"epoch": 1.02,
"learning_rate": 2.9235443993335794e-05,
"loss": 3.9696,
"step": 1268224
},
{
"epoch": 1.02,
"learning_rate": 2.9227058045825274e-05,
"loss": 3.9726,
"step": 1268736
},
{
"epoch": 1.02,
"learning_rate": 2.9218672098314754e-05,
"loss": 3.9804,
"step": 1269248
},
{
"epoch": 1.02,
"learning_rate": 2.9210286150804234e-05,
"loss": 3.9812,
"step": 1269760
},
{
"epoch": 1.02,
"learning_rate": 2.9201900203293714e-05,
"loss": 3.9812,
"step": 1270272
},
{
"epoch": 1.02,
"learning_rate": 2.9193530634586923e-05,
"loss": 3.9629,
"step": 1270784
},
{
"epoch": 1.02,
"learning_rate": 2.9185144687076406e-05,
"loss": 3.9725,
"step": 1271296
},
{
"epoch": 1.02,
"learning_rate": 2.9176758739565886e-05,
"loss": 3.9748,
"step": 1271808
},
{
"epoch": 1.02,
"learning_rate": 2.9168372792055366e-05,
"loss": 3.974,
"step": 1272320
},
{
"epoch": 1.02,
"learning_rate": 2.9159986844544846e-05,
"loss": 3.9685,
"step": 1272832
},
{
"epoch": 1.02,
"learning_rate": 2.9151617275838055e-05,
"loss": 3.9672,
"step": 1273344
},
{
"epoch": 1.02,
"learning_rate": 2.9143231328327535e-05,
"loss": 3.9603,
"step": 1273856
},
{
"epoch": 1.02,
"learning_rate": 2.9134845380817015e-05,
"loss": 3.9806,
"step": 1274368
},
{
"epoch": 1.02,
"learning_rate": 2.9126459433306498e-05,
"loss": 3.9544,
"step": 1274880
},
{
"epoch": 1.02,
"learning_rate": 2.9118089864599707e-05,
"loss": 3.9685,
"step": 1275392
},
{
"epoch": 1.02,
"learning_rate": 2.9109703917089187e-05,
"loss": 3.9754,
"step": 1275904
},
{
"epoch": 1.02,
"learning_rate": 2.9101317969578667e-05,
"loss": 3.9658,
"step": 1276416
},
{
"epoch": 1.02,
"learning_rate": 2.9092932022068147e-05,
"loss": 3.9653,
"step": 1276928
},
{
"epoch": 1.02,
"learning_rate": 2.9084546074557627e-05,
"loss": 3.9728,
"step": 1277440
},
{
"epoch": 1.02,
"learning_rate": 2.9076160127047107e-05,
"loss": 3.9651,
"step": 1277952
},
{
"epoch": 1.02,
"learning_rate": 2.9067774179536587e-05,
"loss": 3.9751,
"step": 1278464
},
{
"epoch": 1.02,
"learning_rate": 2.9059388232026064e-05,
"loss": 3.9682,
"step": 1278976
},
{
"epoch": 1.02,
"learning_rate": 2.905101866331928e-05,
"loss": 3.9699,
"step": 1279488
},
{
"epoch": 1.02,
"learning_rate": 2.904263271580876e-05,
"loss": 3.9722,
"step": 1280000
},
{
"epoch": 1.02,
"learning_rate": 2.9034246768298236e-05,
"loss": 3.9849,
"step": 1280512
},
{
"epoch": 1.02,
"learning_rate": 2.902587719959145e-05,
"loss": 3.9694,
"step": 1281024
},
{
"epoch": 1.02,
"learning_rate": 2.9017491252080932e-05,
"loss": 3.9654,
"step": 1281536
},
{
"epoch": 1.02,
"learning_rate": 2.9009105304570412e-05,
"loss": 3.9712,
"step": 1282048
},
{
"epoch": 1.02,
"learning_rate": 2.9000719357059885e-05,
"loss": 3.974,
"step": 1282560
},
{
"epoch": 1.02,
"learning_rate": 2.8992333409549365e-05,
"loss": 3.9684,
"step": 1283072
},
{
"epoch": 1.02,
"learning_rate": 2.8983947462038845e-05,
"loss": 3.9625,
"step": 1283584
},
{
"epoch": 1.02,
"learning_rate": 2.897557789333206e-05,
"loss": 3.9706,
"step": 1284096
},
{
"epoch": 1.02,
"learning_rate": 2.8967191945821537e-05,
"loss": 3.9779,
"step": 1284608
},
{
"epoch": 1.02,
"learning_rate": 2.8958822377114753e-05,
"loss": 3.9738,
"step": 1285120
},
{
"epoch": 1.02,
"learning_rate": 2.8950436429604233e-05,
"loss": 3.9691,
"step": 1285632
},
{
"epoch": 1.02,
"learning_rate": 2.8942050482093706e-05,
"loss": 3.9626,
"step": 1286144
},
{
"epoch": 1.02,
"learning_rate": 2.8933664534583186e-05,
"loss": 3.9665,
"step": 1286656
},
{
"epoch": 1.02,
"learning_rate": 2.892527858707267e-05,
"loss": 3.9651,
"step": 1287168
},
{
"epoch": 1.02,
"learning_rate": 2.891689263956215e-05,
"loss": 3.9816,
"step": 1287680
},
{
"epoch": 1.02,
"learning_rate": 2.890850669205163e-05,
"loss": 3.9787,
"step": 1288192
},
{
"epoch": 1.02,
"learning_rate": 2.890013712334484e-05,
"loss": 3.9588,
"step": 1288704
},
{
"epoch": 1.02,
"learning_rate": 2.889175117583432e-05,
"loss": 3.9701,
"step": 1289216
},
{
"epoch": 1.02,
"learning_rate": 2.88833652283238e-05,
"loss": 3.9735,
"step": 1289728
},
{
"epoch": 1.02,
"learning_rate": 2.887497928081328e-05,
"loss": 3.9698,
"step": 1290240
},
{
"epoch": 1.02,
"learning_rate": 2.8866593333302762e-05,
"loss": 3.9768,
"step": 1290752
},
{
"epoch": 1.02,
"learning_rate": 2.8858207385792242e-05,
"loss": 3.9628,
"step": 1291264
},
{
"epoch": 1.02,
"learning_rate": 2.884983781708545e-05,
"loss": 3.978,
"step": 1291776
},
{
"epoch": 1.02,
"learning_rate": 2.884145186957493e-05,
"loss": 3.9779,
"step": 1292288
},
{
"epoch": 1.02,
"learning_rate": 2.883306592206441e-05,
"loss": 3.97,
"step": 1292800
},
{
"epoch": 1.02,
"learning_rate": 2.882467997455389e-05,
"loss": 3.9701,
"step": 1293312
},
{
"epoch": 1.02,
"learning_rate": 2.881629402704337e-05,
"loss": 3.9738,
"step": 1293824
},
{
"epoch": 1.02,
"learning_rate": 2.8807908079532854e-05,
"loss": 3.9649,
"step": 1294336
},
{
"epoch": 1.02,
"learning_rate": 2.8799522132022334e-05,
"loss": 3.9684,
"step": 1294848
},
{
"epoch": 1.02,
"learning_rate": 2.8791136184511814e-05,
"loss": 3.979,
"step": 1295360
},
{
"epoch": 1.02,
"learning_rate": 2.8782750237001294e-05,
"loss": 3.9604,
"step": 1295872
},
{
"epoch": 1.02,
"learning_rate": 2.8774364289490774e-05,
"loss": 3.9702,
"step": 1296384
},
{
"epoch": 1.02,
"learning_rate": 2.8765978341980247e-05,
"loss": 3.9713,
"step": 1296896
},
{
"epoch": 1.02,
"learning_rate": 2.875759239446973e-05,
"loss": 3.9692,
"step": 1297408
},
{
"epoch": 1.03,
"eval_loss": 4.034730434417725,
"eval_runtime": 301.5834,
"eval_samples_per_second": 1265.292,
"eval_steps_per_second": 39.541,
"step": 1297440
},
{
"epoch": 0.0,
"learning_rate": 2.874920644695921e-05,
"loss": 3.9623,
"step": 1297920
},
{
"epoch": 0.0,
"learning_rate": 2.874082049944869e-05,
"loss": 3.9642,
"step": 1298432
},
{
"epoch": 0.0,
"learning_rate": 2.873243455193817e-05,
"loss": 3.9812,
"step": 1298944
},
{
"epoch": 0.0,
"learning_rate": 2.872404860442765e-05,
"loss": 3.9679,
"step": 1299456
},
{
"epoch": 0.0,
"learning_rate": 2.871566265691713e-05,
"loss": 3.9814,
"step": 1299968
},
{
"epoch": 0.0,
"learning_rate": 2.870727670940661e-05,
"loss": 3.96,
"step": 1300480
},
{
"epoch": 0.0,
"learning_rate": 2.869889076189609e-05,
"loss": 3.9773,
"step": 1300992
},
{
"epoch": 0.0,
"learning_rate": 2.869050481438557e-05,
"loss": 3.9647,
"step": 1301504
},
{
"epoch": 0.0,
"learning_rate": 2.8682118866875053e-05,
"loss": 3.9702,
"step": 1302016
},
{
"epoch": 0.0,
"learning_rate": 2.8673732919364533e-05,
"loss": 3.9718,
"step": 1302528
},
{
"epoch": 0.0,
"learning_rate": 2.8665346971854013e-05,
"loss": 3.9727,
"step": 1303040
},
{
"epoch": 0.0,
"learning_rate": 2.8656961024343487e-05,
"loss": 3.9792,
"step": 1303552
},
{
"epoch": 0.0,
"learning_rate": 2.8648591455636702e-05,
"loss": 3.964,
"step": 1304064
},
{
"epoch": 0.0,
"learning_rate": 2.8640205508126182e-05,
"loss": 3.9609,
"step": 1304576
},
{
"epoch": 0.0,
"learning_rate": 2.8631819560615662e-05,
"loss": 3.9622,
"step": 1305088
},
{
"epoch": 0.0,
"learning_rate": 2.862343361310514e-05,
"loss": 3.9651,
"step": 1305600
},
{
"epoch": 0.0,
"learning_rate": 2.861504766559462e-05,
"loss": 3.9622,
"step": 1306112
},
{
"epoch": 0.0,
"learning_rate": 2.86066617180841e-05,
"loss": 3.9653,
"step": 1306624
},
{
"epoch": 0.0,
"learning_rate": 2.859827577057358e-05,
"loss": 3.9692,
"step": 1307136
},
{
"epoch": 0.0,
"learning_rate": 2.858988982306306e-05,
"loss": 3.9927,
"step": 1307648
},
{
"epoch": 0.0,
"learning_rate": 2.858150387555254e-05,
"loss": 3.9694,
"step": 1308160
},
{
"epoch": 0.0,
"learning_rate": 2.857311792804202e-05,
"loss": 3.9774,
"step": 1308672
},
{
"epoch": 0.0,
"learning_rate": 2.8564731980531502e-05,
"loss": 3.9687,
"step": 1309184
},
{
"epoch": 0.0,
"learning_rate": 2.8556346033020982e-05,
"loss": 3.977,
"step": 1309696
},
{
"epoch": 0.0,
"learning_rate": 2.8547960085510462e-05,
"loss": 3.9686,
"step": 1310208
},
{
"epoch": 0.0,
"learning_rate": 2.853959051680367e-05,
"loss": 3.9686,
"step": 1310720
},
{
"epoch": 0.0,
"learning_rate": 2.853120456929315e-05,
"loss": 3.9683,
"step": 1311232
},
{
"epoch": 0.0,
"learning_rate": 2.852281862178263e-05,
"loss": 3.9662,
"step": 1311744
},
{
"epoch": 0.0,
"learning_rate": 2.851443267427211e-05,
"loss": 3.9495,
"step": 1312256
},
{
"epoch": 0.01,
"learning_rate": 2.8506063105565323e-05,
"loss": 3.9715,
"step": 1312768
},
{
"epoch": 0.01,
"learning_rate": 2.8497677158054803e-05,
"loss": 3.9685,
"step": 1313280
},
{
"epoch": 0.01,
"learning_rate": 2.8489291210544283e-05,
"loss": 3.9754,
"step": 1313792
},
{
"epoch": 0.01,
"learning_rate": 2.8480905263033763e-05,
"loss": 3.9705,
"step": 1314304
},
{
"epoch": 0.01,
"learning_rate": 2.8472519315523243e-05,
"loss": 3.9736,
"step": 1314816
},
{
"epoch": 0.01,
"learning_rate": 2.8464166125620185e-05,
"loss": 3.9643,
"step": 1315328
},
{
"epoch": 0.01,
"learning_rate": 2.8455780178109665e-05,
"loss": 3.9649,
"step": 1315840
},
{
"epoch": 0.01,
"learning_rate": 2.8447410609402874e-05,
"loss": 3.954,
"step": 1316352
},
{
"epoch": 0.01,
"learning_rate": 2.8439024661892354e-05,
"loss": 3.9663,
"step": 1316864
},
{
"epoch": 0.01,
"learning_rate": 2.8430638714381834e-05,
"loss": 3.9634,
"step": 1317376
},
{
"epoch": 0.01,
"learning_rate": 2.8422252766871317e-05,
"loss": 3.9614,
"step": 1317888
},
{
"epoch": 0.01,
"learning_rate": 2.8413866819360797e-05,
"loss": 3.9689,
"step": 1318400
},
{
"epoch": 0.01,
"learning_rate": 2.8405497250654006e-05,
"loss": 3.9741,
"step": 1318912
},
{
"epoch": 0.01,
"learning_rate": 2.8397111303143486e-05,
"loss": 3.9677,
"step": 1319424
},
{
"epoch": 0.01,
"learning_rate": 2.8388725355632966e-05,
"loss": 3.9676,
"step": 1319936
},
{
"epoch": 0.01,
"learning_rate": 2.8380339408122446e-05,
"loss": 3.9727,
"step": 1320448
},
{
"epoch": 0.01,
"learning_rate": 2.8371953460611926e-05,
"loss": 3.9588,
"step": 1320960
},
{
"epoch": 0.01,
"learning_rate": 2.836358389190514e-05,
"loss": 3.9695,
"step": 1321472
},
{
"epoch": 0.01,
"learning_rate": 2.835519794439462e-05,
"loss": 3.9582,
"step": 1321984
},
{
"epoch": 0.01,
"learning_rate": 2.83468119968841e-05,
"loss": 3.9555,
"step": 1322496
},
{
"epoch": 0.01,
"learning_rate": 2.833842604937358e-05,
"loss": 3.9742,
"step": 1323008
},
{
"epoch": 0.01,
"learning_rate": 2.8330040101863058e-05,
"loss": 3.9611,
"step": 1323520
},
{
"epoch": 0.01,
"learning_rate": 2.8321654154352538e-05,
"loss": 3.9581,
"step": 1324032
},
{
"epoch": 0.01,
"learning_rate": 2.8313268206842018e-05,
"loss": 3.9522,
"step": 1324544
},
{
"epoch": 0.01,
"learning_rate": 2.83048822593315e-05,
"loss": 3.9602,
"step": 1325056
},
{
"epoch": 0.01,
"learning_rate": 2.8296496311820975e-05,
"loss": 3.9484,
"step": 1325568
},
{
"epoch": 0.01,
"learning_rate": 2.828812674311419e-05,
"loss": 3.9781,
"step": 1326080
},
{
"epoch": 0.01,
"learning_rate": 2.827974079560367e-05,
"loss": 3.9571,
"step": 1326592
},
{
"epoch": 0.01,
"learning_rate": 2.8271354848093147e-05,
"loss": 3.9719,
"step": 1327104
},
{
"epoch": 0.01,
"learning_rate": 2.8262968900582627e-05,
"loss": 3.9705,
"step": 1327616
},
{
"epoch": 0.01,
"learning_rate": 2.8254582953072107e-05,
"loss": 3.957,
"step": 1328128
},
{
"epoch": 0.01,
"learning_rate": 2.8246197005561587e-05,
"loss": 3.9506,
"step": 1328640
},
{
"epoch": 0.01,
"learning_rate": 2.8237811058051067e-05,
"loss": 3.9646,
"step": 1329152
},
{
"epoch": 0.01,
"learning_rate": 2.8229425110540547e-05,
"loss": 3.9537,
"step": 1329664
},
{
"epoch": 0.01,
"learning_rate": 2.8221039163030027e-05,
"loss": 3.9482,
"step": 1330176
},
{
"epoch": 0.01,
"learning_rate": 2.821266959432324e-05,
"loss": 3.9706,
"step": 1330688
},
{
"epoch": 0.01,
"learning_rate": 2.820428364681272e-05,
"loss": 3.9705,
"step": 1331200
},
{
"epoch": 0.01,
"learning_rate": 2.819591407810593e-05,
"loss": 3.9564,
"step": 1331712
},
{
"epoch": 0.01,
"learning_rate": 2.818752813059541e-05,
"loss": 3.9515,
"step": 1332224
},
{
"epoch": 0.01,
"learning_rate": 2.8179142183084888e-05,
"loss": 3.952,
"step": 1332736
},
{
"epoch": 0.01,
"learning_rate": 2.8170756235574368e-05,
"loss": 3.9643,
"step": 1333248
},
{
"epoch": 0.01,
"learning_rate": 2.816238666686758e-05,
"loss": 3.9667,
"step": 1333760
},
{
"epoch": 0.01,
"learning_rate": 2.815400071935706e-05,
"loss": 3.9686,
"step": 1334272
},
{
"epoch": 0.01,
"learning_rate": 2.814561477184654e-05,
"loss": 3.9664,
"step": 1334784
},
{
"epoch": 0.01,
"learning_rate": 2.813722882433602e-05,
"loss": 3.9665,
"step": 1335296
},
{
"epoch": 0.01,
"learning_rate": 2.81288428768255e-05,
"loss": 3.971,
"step": 1335808
},
{
"epoch": 0.01,
"learning_rate": 2.812045692931498e-05,
"loss": 3.9589,
"step": 1336320
},
{
"epoch": 0.01,
"learning_rate": 2.811207098180446e-05,
"loss": 3.9672,
"step": 1336832
},
{
"epoch": 0.01,
"learning_rate": 2.810368503429394e-05,
"loss": 3.9663,
"step": 1337344
},
{
"epoch": 0.01,
"learning_rate": 2.8095315465587153e-05,
"loss": 3.9528,
"step": 1337856
},
{
"epoch": 0.01,
"learning_rate": 2.8086929518076633e-05,
"loss": 3.9665,
"step": 1338368
},
{
"epoch": 0.01,
"learning_rate": 2.8078543570566113e-05,
"loss": 3.9679,
"step": 1338880
},
{
"epoch": 0.01,
"learning_rate": 2.8070157623055593e-05,
"loss": 3.9738,
"step": 1339392
},
{
"epoch": 0.01,
"learning_rate": 2.8061771675545073e-05,
"loss": 3.9531,
"step": 1339904
},
{
"epoch": 0.01,
"learning_rate": 2.8053385728034553e-05,
"loss": 3.9436,
"step": 1340416
},
{
"epoch": 0.01,
"learning_rate": 2.8045016159327765e-05,
"loss": 3.9644,
"step": 1340928
},
{
"epoch": 0.01,
"learning_rate": 2.8036630211817245e-05,
"loss": 3.9622,
"step": 1341440
},
{
"epoch": 0.01,
"learning_rate": 2.8028244264306725e-05,
"loss": 3.967,
"step": 1341952
},
{
"epoch": 0.01,
"learning_rate": 2.8019874695599934e-05,
"loss": 3.9615,
"step": 1342464
},
{
"epoch": 0.01,
"learning_rate": 2.8011505126893147e-05,
"loss": 3.9628,
"step": 1342976
},
{
"epoch": 0.02,
"learning_rate": 2.8003135558186356e-05,
"loss": 3.9601,
"step": 1343488
},
{
"epoch": 0.02,
"learning_rate": 2.7994749610675836e-05,
"loss": 3.9523,
"step": 1344000
},
{
"epoch": 0.02,
"learning_rate": 2.7986363663165316e-05,
"loss": 3.9596,
"step": 1344512
},
{
"epoch": 0.02,
"learning_rate": 2.7977977715654796e-05,
"loss": 3.9611,
"step": 1345024
},
{
"epoch": 0.02,
"learning_rate": 2.7969591768144276e-05,
"loss": 3.9708,
"step": 1345536
},
{
"epoch": 0.02,
"learning_rate": 2.7961205820633756e-05,
"loss": 3.9732,
"step": 1346048
},
{
"epoch": 0.02,
"learning_rate": 2.7952819873123236e-05,
"loss": 3.9697,
"step": 1346560
},
{
"epoch": 0.02,
"learning_rate": 2.794443392561272e-05,
"loss": 3.9543,
"step": 1347072
},
{
"epoch": 0.02,
"learning_rate": 2.79360479781022e-05,
"loss": 3.9637,
"step": 1347584
},
{
"epoch": 0.02,
"learning_rate": 2.792766203059168e-05,
"loss": 3.961,
"step": 1348096
},
{
"epoch": 0.02,
"learning_rate": 2.791927608308116e-05,
"loss": 3.9715,
"step": 1348608
},
{
"epoch": 0.02,
"learning_rate": 2.7910890135570632e-05,
"loss": 3.9574,
"step": 1349120
},
{
"epoch": 0.02,
"learning_rate": 2.7902504188060112e-05,
"loss": 3.9566,
"step": 1349632
},
{
"epoch": 0.02,
"learning_rate": 2.7894118240549595e-05,
"loss": 3.9529,
"step": 1350144
},
{
"epoch": 0.02,
"learning_rate": 2.7885732293039075e-05,
"loss": 3.9706,
"step": 1350656
},
{
"epoch": 0.02,
"learning_rate": 2.7877346345528555e-05,
"loss": 3.9453,
"step": 1351168
},
{
"epoch": 0.02,
"learning_rate": 2.7868976776821764e-05,
"loss": 3.9581,
"step": 1351680
},
{
"epoch": 0.02,
"learning_rate": 2.786060720811498e-05,
"loss": 3.9668,
"step": 1352192
},
{
"epoch": 0.02,
"learning_rate": 2.7852221260604457e-05,
"loss": 3.9549,
"step": 1352704
},
{
"epoch": 0.02,
"learning_rate": 2.7843835313093937e-05,
"loss": 3.9546,
"step": 1353216
},
{
"epoch": 0.02,
"learning_rate": 2.7835449365583417e-05,
"loss": 3.9661,
"step": 1353728
},
{
"epoch": 0.02,
"learning_rate": 2.7827063418072897e-05,
"loss": 3.9558,
"step": 1354240
},
{
"epoch": 0.02,
"learning_rate": 2.7818677470562376e-05,
"loss": 3.961,
"step": 1354752
},
{
"epoch": 0.02,
"learning_rate": 2.7810291523051856e-05,
"loss": 3.9639,
"step": 1355264
},
{
"epoch": 0.02,
"learning_rate": 2.7801905575541336e-05,
"loss": 3.9594,
"step": 1355776
},
{
"epoch": 0.02,
"learning_rate": 2.7793519628030816e-05,
"loss": 3.9655,
"step": 1356288
},
{
"epoch": 0.02,
"learning_rate": 2.7785133680520296e-05,
"loss": 3.9759,
"step": 1356800
},
{
"epoch": 0.02,
"learning_rate": 2.7776780490617238e-05,
"loss": 3.9612,
"step": 1357312
},
{
"epoch": 0.02,
"learning_rate": 2.7768394543106718e-05,
"loss": 3.9564,
"step": 1357824
},
{
"epoch": 0.02,
"learning_rate": 2.7760008595596198e-05,
"loss": 3.9632,
"step": 1358336
},
{
"epoch": 0.02,
"learning_rate": 2.7751622648085678e-05,
"loss": 3.9624,
"step": 1358848
},
{
"epoch": 0.02,
"learning_rate": 2.7743236700575158e-05,
"loss": 3.9568,
"step": 1359360
},
{
"epoch": 0.02,
"learning_rate": 2.773486713186837e-05,
"loss": 3.9562,
"step": 1359872
},
{
"epoch": 0.02,
"learning_rate": 2.772648118435785e-05,
"loss": 3.9568,
"step": 1360384
},
{
"epoch": 0.02,
"learning_rate": 2.771809523684733e-05,
"loss": 3.972,
"step": 1360896
},
{
"epoch": 0.02,
"learning_rate": 2.770970928933681e-05,
"loss": 3.9613,
"step": 1361408
},
{
"epoch": 0.02,
"learning_rate": 2.770132334182629e-05,
"loss": 3.9605,
"step": 1361920
},
{
"epoch": 0.02,
"learning_rate": 2.769293739431577e-05,
"loss": 3.9517,
"step": 1362432
},
{
"epoch": 0.02,
"learning_rate": 2.7684567825608982e-05,
"loss": 3.9556,
"step": 1362944
},
{
"epoch": 0.02,
"learning_rate": 2.7676181878098462e-05,
"loss": 3.9546,
"step": 1363456
},
{
"epoch": 0.02,
"learning_rate": 2.7667795930587942e-05,
"loss": 3.9724,
"step": 1363968
},
{
"epoch": 0.02,
"learning_rate": 2.7659409983077422e-05,
"loss": 3.9697,
"step": 1364480
},
{
"epoch": 0.02,
"learning_rate": 2.7651024035566902e-05,
"loss": 3.9506,
"step": 1364992
},
{
"epoch": 0.02,
"learning_rate": 2.7642638088056382e-05,
"loss": 3.9566,
"step": 1365504
},
{
"epoch": 0.02,
"learning_rate": 2.7634252140545862e-05,
"loss": 3.9641,
"step": 1366016
},
{
"epoch": 0.02,
"learning_rate": 2.7625882571839075e-05,
"loss": 3.963,
"step": 1366528
},
{
"epoch": 0.02,
"learning_rate": 2.7617496624328555e-05,
"loss": 3.9671,
"step": 1367040
},
{
"epoch": 0.02,
"learning_rate": 2.7609110676818035e-05,
"loss": 3.9546,
"step": 1367552
},
{
"epoch": 0.02,
"learning_rate": 2.7600724729307515e-05,
"loss": 3.9649,
"step": 1368064
},
{
"epoch": 0.02,
"learning_rate": 2.7592338781796995e-05,
"loss": 3.9684,
"step": 1368576
},
{
"epoch": 0.02,
"learning_rate": 2.758395283428647e-05,
"loss": 3.9604,
"step": 1369088
},
{
"epoch": 0.02,
"learning_rate": 2.757556688677595e-05,
"loss": 3.9611,
"step": 1369600
},
{
"epoch": 0.02,
"learning_rate": 2.756718093926543e-05,
"loss": 3.9673,
"step": 1370112
},
{
"epoch": 0.02,
"learning_rate": 2.755881137055864e-05,
"loss": 3.9566,
"step": 1370624
},
{
"epoch": 0.02,
"learning_rate": 2.7550441801851856e-05,
"loss": 3.9585,
"step": 1371136
},
{
"epoch": 0.02,
"learning_rate": 2.7542055854341336e-05,
"loss": 3.9694,
"step": 1371648
},
{
"epoch": 0.02,
"learning_rate": 2.7533669906830816e-05,
"loss": 3.9526,
"step": 1372160
},
{
"epoch": 0.02,
"learning_rate": 2.752530033812403e-05,
"loss": 3.9628,
"step": 1372672
},
{
"epoch": 0.02,
"learning_rate": 2.751691439061351e-05,
"loss": 3.9622,
"step": 1373184
},
{
"epoch": 0.02,
"learning_rate": 2.7508528443102988e-05,
"loss": 3.9603,
"step": 1373696
},
{
"epoch": 0.03,
"eval_loss": 4.030179023742676,
"eval_runtime": 301.0616,
"eval_samples_per_second": 1267.485,
"eval_steps_per_second": 39.61,
"step": 1373760
},
{
"epoch": 1.0,
"learning_rate": 2.750014249559246e-05,
"loss": 3.9557,
"step": 1374208
},
{
"epoch": 1.0,
"learning_rate": 2.749175654808194e-05,
"loss": 3.957,
"step": 1374720
},
{
"epoch": 1.0,
"learning_rate": 2.7483370600571425e-05,
"loss": 3.9706,
"step": 1375232
},
{
"epoch": 1.0,
"learning_rate": 2.7474984653060905e-05,
"loss": 3.9544,
"step": 1375744
},
{
"epoch": 1.0,
"learning_rate": 2.7466598705550385e-05,
"loss": 3.9744,
"step": 1376256
},
{
"epoch": 1.0,
"learning_rate": 2.7458229136843594e-05,
"loss": 3.9525,
"step": 1376768
},
{
"epoch": 1.0,
"learning_rate": 2.7449843189333074e-05,
"loss": 3.9683,
"step": 1377280
},
{
"epoch": 1.0,
"learning_rate": 2.7441457241822554e-05,
"loss": 3.9508,
"step": 1377792
},
{
"epoch": 1.0,
"learning_rate": 2.7433087673115766e-05,
"loss": 3.9667,
"step": 1378304
},
{
"epoch": 1.0,
"learning_rate": 2.7424701725605246e-05,
"loss": 3.9607,
"step": 1378816
},
{
"epoch": 1.0,
"learning_rate": 2.7416315778094726e-05,
"loss": 3.9613,
"step": 1379328
},
{
"epoch": 1.0,
"learning_rate": 2.7407929830584206e-05,
"loss": 3.9714,
"step": 1379840
},
{
"epoch": 1.0,
"learning_rate": 2.7399543883073686e-05,
"loss": 3.9552,
"step": 1380352
},
{
"epoch": 1.0,
"learning_rate": 2.7391157935563166e-05,
"loss": 3.9542,
"step": 1380864
},
{
"epoch": 1.0,
"learning_rate": 2.7382771988052646e-05,
"loss": 3.9526,
"step": 1381376
},
{
"epoch": 1.0,
"learning_rate": 2.7374386040542126e-05,
"loss": 3.9511,
"step": 1381888
},
{
"epoch": 1.0,
"learning_rate": 2.7366000093031606e-05,
"loss": 3.9557,
"step": 1382400
},
{
"epoch": 1.0,
"learning_rate": 2.735761414552109e-05,
"loss": 3.9579,
"step": 1382912
},
{
"epoch": 1.0,
"learning_rate": 2.734922819801057e-05,
"loss": 3.9579,
"step": 1383424
},
{
"epoch": 1.0,
"learning_rate": 2.7340858629303778e-05,
"loss": 3.982,
"step": 1383936
},
{
"epoch": 1.0,
"learning_rate": 2.7332472681793258e-05,
"loss": 3.9612,
"step": 1384448
},
{
"epoch": 1.0,
"learning_rate": 2.7324086734282738e-05,
"loss": 3.9685,
"step": 1384960
},
{
"epoch": 1.0,
"learning_rate": 2.7315700786772218e-05,
"loss": 3.9602,
"step": 1385472
},
{
"epoch": 1.0,
"learning_rate": 2.7307314839261698e-05,
"loss": 3.9678,
"step": 1385984
},
{
"epoch": 1.0,
"learning_rate": 2.729892889175118e-05,
"loss": 3.9596,
"step": 1386496
},
{
"epoch": 1.0,
"learning_rate": 2.7290542944240655e-05,
"loss": 3.9578,
"step": 1387008
},
{
"epoch": 1.0,
"learning_rate": 2.728217337553387e-05,
"loss": 3.961,
"step": 1387520
},
{
"epoch": 1.0,
"learning_rate": 2.727378742802335e-05,
"loss": 3.9553,
"step": 1388032
},
{
"epoch": 1.0,
"learning_rate": 2.7265401480512827e-05,
"loss": 3.9425,
"step": 1388544
},
{
"epoch": 1.01,
"learning_rate": 2.7257015533002307e-05,
"loss": 3.9578,
"step": 1389056
},
{
"epoch": 1.01,
"learning_rate": 2.7248629585491787e-05,
"loss": 3.9648,
"step": 1389568
},
{
"epoch": 1.01,
"learning_rate": 2.7240243637981267e-05,
"loss": 3.9629,
"step": 1390080
},
{
"epoch": 1.01,
"learning_rate": 2.7231857690470747e-05,
"loss": 3.9628,
"step": 1390592
},
{
"epoch": 1.01,
"learning_rate": 2.7223471742960227e-05,
"loss": 3.9654,
"step": 1391104
},
{
"epoch": 1.01,
"learning_rate": 2.7215118553057172e-05,
"loss": 3.9559,
"step": 1391616
},
{
"epoch": 1.01,
"learning_rate": 2.720673260554665e-05,
"loss": 3.9557,
"step": 1392128
},
{
"epoch": 1.01,
"learning_rate": 2.7198346658036128e-05,
"loss": 3.9504,
"step": 1392640
},
{
"epoch": 1.01,
"learning_rate": 2.7189960710525608e-05,
"loss": 3.9542,
"step": 1393152
},
{
"epoch": 1.01,
"learning_rate": 2.7181574763015088e-05,
"loss": 3.9518,
"step": 1393664
},
{
"epoch": 1.01,
"learning_rate": 2.7173188815504568e-05,
"loss": 3.9529,
"step": 1394176
},
{
"epoch": 1.01,
"learning_rate": 2.7164802867994048e-05,
"loss": 3.9605,
"step": 1394688
},
{
"epoch": 1.01,
"learning_rate": 2.7156416920483528e-05,
"loss": 3.9669,
"step": 1395200
},
{
"epoch": 1.01,
"learning_rate": 2.714803097297301e-05,
"loss": 3.9546,
"step": 1395712
},
{
"epoch": 1.01,
"learning_rate": 2.713966140426622e-05,
"loss": 3.9597,
"step": 1396224
},
{
"epoch": 1.01,
"learning_rate": 2.71312754567557e-05,
"loss": 3.9656,
"step": 1396736
},
{
"epoch": 1.01,
"learning_rate": 2.712288950924518e-05,
"loss": 3.9477,
"step": 1397248
},
{
"epoch": 1.01,
"learning_rate": 2.711450356173466e-05,
"loss": 3.9619,
"step": 1397760
},
{
"epoch": 1.01,
"learning_rate": 2.7106133993027873e-05,
"loss": 3.9539,
"step": 1398272
},
{
"epoch": 1.01,
"learning_rate": 2.7097748045517353e-05,
"loss": 3.9416,
"step": 1398784
},
{
"epoch": 1.01,
"learning_rate": 2.7089362098006833e-05,
"loss": 3.9633,
"step": 1399296
},
{
"epoch": 1.01,
"learning_rate": 2.7080976150496313e-05,
"loss": 3.9552,
"step": 1399808
},
{
"epoch": 1.01,
"learning_rate": 2.7072606581789522e-05,
"loss": 3.9498,
"step": 1400320
},
{
"epoch": 1.01,
"learning_rate": 2.7064220634279002e-05,
"loss": 3.9485,
"step": 1400832
},
{
"epoch": 1.01,
"learning_rate": 2.7055834686768482e-05,
"loss": 3.9503,
"step": 1401344
},
{
"epoch": 1.01,
"learning_rate": 2.7047448739257965e-05,
"loss": 3.9373,
"step": 1401856
},
{
"epoch": 1.01,
"learning_rate": 2.7039079170551174e-05,
"loss": 3.9645,
"step": 1402368
},
{
"epoch": 1.01,
"learning_rate": 2.7030693223040654e-05,
"loss": 3.9509,
"step": 1402880
},
{
"epoch": 1.01,
"learning_rate": 2.7022307275530134e-05,
"loss": 3.9608,
"step": 1403392
},
{
"epoch": 1.01,
"learning_rate": 2.7013937706823343e-05,
"loss": 3.9645,
"step": 1403904
},
{
"epoch": 1.01,
"learning_rate": 2.7005551759312826e-05,
"loss": 3.9474,
"step": 1404416
},
{
"epoch": 1.01,
"learning_rate": 2.6997165811802306e-05,
"loss": 3.9405,
"step": 1404928
},
{
"epoch": 1.01,
"learning_rate": 2.6988779864291786e-05,
"loss": 3.9596,
"step": 1405440
},
{
"epoch": 1.01,
"learning_rate": 2.6980393916781266e-05,
"loss": 3.9443,
"step": 1405952
},
{
"epoch": 1.01,
"learning_rate": 2.6972007969270746e-05,
"loss": 3.9396,
"step": 1406464
},
{
"epoch": 1.01,
"learning_rate": 2.6963622021760226e-05,
"loss": 3.9622,
"step": 1406976
},
{
"epoch": 1.01,
"learning_rate": 2.6955236074249706e-05,
"loss": 3.9632,
"step": 1407488
},
{
"epoch": 1.01,
"learning_rate": 2.6946850126739186e-05,
"loss": 3.9463,
"step": 1408000
},
{
"epoch": 1.01,
"learning_rate": 2.6938464179228663e-05,
"loss": 3.9407,
"step": 1408512
},
{
"epoch": 1.01,
"learning_rate": 2.6930078231718143e-05,
"loss": 3.9437,
"step": 1409024
},
{
"epoch": 1.01,
"learning_rate": 2.6921692284207623e-05,
"loss": 3.9517,
"step": 1409536
},
{
"epoch": 1.01,
"learning_rate": 2.691332271550084e-05,
"loss": 3.958,
"step": 1410048
},
{
"epoch": 1.01,
"learning_rate": 2.6904953146794048e-05,
"loss": 3.9562,
"step": 1410560
},
{
"epoch": 1.01,
"learning_rate": 2.6896567199283528e-05,
"loss": 3.9602,
"step": 1411072
},
{
"epoch": 1.01,
"learning_rate": 2.6888181251773008e-05,
"loss": 3.9553,
"step": 1411584
},
{
"epoch": 1.01,
"learning_rate": 2.6879795304262484e-05,
"loss": 3.9643,
"step": 1412096
},
{
"epoch": 1.01,
"learning_rate": 2.6871409356751964e-05,
"loss": 3.95,
"step": 1412608
},
{
"epoch": 1.01,
"learning_rate": 2.6863023409241444e-05,
"loss": 3.9563,
"step": 1413120
},
{
"epoch": 1.01,
"learning_rate": 2.6854637461730924e-05,
"loss": 3.9591,
"step": 1413632
},
{
"epoch": 1.01,
"learning_rate": 2.6846251514220404e-05,
"loss": 3.9429,
"step": 1414144
},
{
"epoch": 1.01,
"learning_rate": 2.6837881945513616e-05,
"loss": 3.9573,
"step": 1414656
},
{
"epoch": 1.01,
"learning_rate": 2.6829495998003096e-05,
"loss": 3.9629,
"step": 1415168
},
{
"epoch": 1.01,
"learning_rate": 2.6821126429296312e-05,
"loss": 3.9624,
"step": 1415680
},
{
"epoch": 1.01,
"learning_rate": 2.6812740481785785e-05,
"loss": 3.9467,
"step": 1416192
},
{
"epoch": 1.01,
"learning_rate": 2.6804354534275265e-05,
"loss": 3.9343,
"step": 1416704
},
{
"epoch": 1.01,
"learning_rate": 2.6795968586764745e-05,
"loss": 3.955,
"step": 1417216
},
{
"epoch": 1.01,
"learning_rate": 2.6787599018057958e-05,
"loss": 3.9464,
"step": 1417728
},
{
"epoch": 1.01,
"learning_rate": 2.6779213070547438e-05,
"loss": 3.9618,
"step": 1418240
},
{
"epoch": 1.01,
"learning_rate": 2.6770827123036918e-05,
"loss": 3.9527,
"step": 1418752
},
{
"epoch": 1.01,
"learning_rate": 2.6762441175526398e-05,
"loss": 3.9546,
"step": 1419264
},
{
"epoch": 1.02,
"learning_rate": 2.6754055228015878e-05,
"loss": 3.9504,
"step": 1419776
},
{
"epoch": 1.02,
"learning_rate": 2.6745669280505358e-05,
"loss": 3.9434,
"step": 1420288
},
{
"epoch": 1.02,
"learning_rate": 2.6737283332994838e-05,
"loss": 3.9519,
"step": 1420800
},
{
"epoch": 1.02,
"learning_rate": 2.672889738548432e-05,
"loss": 3.9512,
"step": 1421312
},
{
"epoch": 1.02,
"learning_rate": 2.672052781677753e-05,
"loss": 3.9648,
"step": 1421824
},
{
"epoch": 1.02,
"learning_rate": 2.671214186926701e-05,
"loss": 3.9654,
"step": 1422336
},
{
"epoch": 1.02,
"learning_rate": 2.670375592175649e-05,
"loss": 3.9589,
"step": 1422848
},
{
"epoch": 1.02,
"learning_rate": 2.669536997424597e-05,
"loss": 3.943,
"step": 1423360
},
{
"epoch": 1.02,
"learning_rate": 2.668698402673545e-05,
"loss": 3.9564,
"step": 1423872
},
{
"epoch": 1.02,
"learning_rate": 2.6678614458028662e-05,
"loss": 3.9504,
"step": 1424384
},
{
"epoch": 1.02,
"learning_rate": 2.6670228510518142e-05,
"loss": 3.9613,
"step": 1424896
},
{
"epoch": 1.02,
"learning_rate": 2.6661842563007622e-05,
"loss": 3.9478,
"step": 1425408
},
{
"epoch": 1.02,
"learning_rate": 2.6653456615497102e-05,
"loss": 3.9505,
"step": 1425920
},
{
"epoch": 1.02,
"learning_rate": 2.6645070667986582e-05,
"loss": 3.9424,
"step": 1426432
},
{
"epoch": 1.02,
"learning_rate": 2.6636684720476062e-05,
"loss": 3.9619,
"step": 1426944
},
{
"epoch": 1.02,
"learning_rate": 2.6628298772965542e-05,
"loss": 3.9364,
"step": 1427456
},
{
"epoch": 1.02,
"learning_rate": 2.6619912825455022e-05,
"loss": 3.9536,
"step": 1427968
},
{
"epoch": 1.02,
"learning_rate": 2.6611543256748234e-05,
"loss": 3.9497,
"step": 1428480
},
{
"epoch": 1.02,
"learning_rate": 2.6603157309237714e-05,
"loss": 3.951,
"step": 1428992
},
{
"epoch": 1.02,
"learning_rate": 2.6594771361727194e-05,
"loss": 3.9473,
"step": 1429504
},
{
"epoch": 1.02,
"learning_rate": 2.6586385414216674e-05,
"loss": 3.957,
"step": 1430016
},
{
"epoch": 1.02,
"learning_rate": 2.6578015845509883e-05,
"loss": 3.9539,
"step": 1430528
},
{
"epoch": 1.02,
"learning_rate": 2.6569629897999367e-05,
"loss": 3.9497,
"step": 1431040
},
{
"epoch": 1.02,
"learning_rate": 2.6561243950488847e-05,
"loss": 3.9539,
"step": 1431552
},
{
"epoch": 1.02,
"learning_rate": 2.655285800297832e-05,
"loss": 3.945,
"step": 1432064
},
{
"epoch": 1.02,
"learning_rate": 2.65444720554678e-05,
"loss": 3.963,
"step": 1432576
},
{
"epoch": 1.02,
"learning_rate": 2.6536102486761016e-05,
"loss": 3.9703,
"step": 1433088
},
{
"epoch": 1.02,
"learning_rate": 2.6527716539250496e-05,
"loss": 3.9496,
"step": 1433600
},
{
"epoch": 1.02,
"learning_rate": 2.6519330591739972e-05,
"loss": 3.9472,
"step": 1434112
},
{
"epoch": 1.02,
"learning_rate": 2.6510944644229452e-05,
"loss": 3.9522,
"step": 1434624
},
{
"epoch": 1.02,
"learning_rate": 2.6502575075522668e-05,
"loss": 3.9541,
"step": 1435136
},
{
"epoch": 1.02,
"learning_rate": 2.6494189128012148e-05,
"loss": 3.9473,
"step": 1435648
},
{
"epoch": 1.02,
"learning_rate": 2.6485819559305357e-05,
"loss": 3.9497,
"step": 1436160
},
{
"epoch": 1.02,
"learning_rate": 2.6477433611794837e-05,
"loss": 3.9463,
"step": 1436672
},
{
"epoch": 1.02,
"learning_rate": 2.646904766428432e-05,
"loss": 3.9647,
"step": 1437184
},
{
"epoch": 1.02,
"learning_rate": 2.6460661716773794e-05,
"loss": 3.9533,
"step": 1437696
},
{
"epoch": 1.02,
"learning_rate": 2.6452275769263274e-05,
"loss": 3.9504,
"step": 1438208
},
{
"epoch": 1.02,
"learning_rate": 2.6443889821752754e-05,
"loss": 3.9426,
"step": 1438720
},
{
"epoch": 1.02,
"learning_rate": 2.643552025304597e-05,
"loss": 3.9485,
"step": 1439232
},
{
"epoch": 1.02,
"learning_rate": 2.6427134305535446e-05,
"loss": 3.9434,
"step": 1439744
},
{
"epoch": 1.02,
"learning_rate": 2.6418748358024926e-05,
"loss": 3.966,
"step": 1440256
},
{
"epoch": 1.02,
"learning_rate": 2.6410362410514406e-05,
"loss": 3.9616,
"step": 1440768
},
{
"epoch": 1.02,
"learning_rate": 2.6401976463003886e-05,
"loss": 3.9464,
"step": 1441280
},
{
"epoch": 1.02,
"learning_rate": 2.6393590515493366e-05,
"loss": 3.9444,
"step": 1441792
},
{
"epoch": 1.02,
"learning_rate": 2.6385204567982846e-05,
"loss": 3.956,
"step": 1442304
},
{
"epoch": 1.02,
"learning_rate": 2.6376818620472326e-05,
"loss": 3.9505,
"step": 1442816
},
{
"epoch": 1.02,
"learning_rate": 2.6368432672961806e-05,
"loss": 3.9636,
"step": 1443328
},
{
"epoch": 1.02,
"learning_rate": 2.6360063104255018e-05,
"loss": 3.9436,
"step": 1443840
},
{
"epoch": 1.02,
"learning_rate": 2.6351677156744498e-05,
"loss": 3.9604,
"step": 1444352
},
{
"epoch": 1.02,
"learning_rate": 2.6343291209233978e-05,
"loss": 3.955,
"step": 1444864
},
{
"epoch": 1.02,
"learning_rate": 2.6334921640527187e-05,
"loss": 3.9553,
"step": 1445376
},
{
"epoch": 1.02,
"learning_rate": 2.6326535693016667e-05,
"loss": 3.9539,
"step": 1445888
},
{
"epoch": 1.02,
"learning_rate": 2.6318149745506147e-05,
"loss": 3.9576,
"step": 1446400
},
{
"epoch": 1.02,
"learning_rate": 2.630976379799563e-05,
"loss": 3.9464,
"step": 1446912
},
{
"epoch": 1.02,
"learning_rate": 2.630139422928884e-05,
"loss": 3.9525,
"step": 1447424
},
{
"epoch": 1.02,
"learning_rate": 2.629302466058205e-05,
"loss": 3.958,
"step": 1447936
},
{
"epoch": 1.02,
"learning_rate": 2.628463871307153e-05,
"loss": 3.9488,
"step": 1448448
},
{
"epoch": 1.02,
"learning_rate": 2.6276252765561012e-05,
"loss": 3.9498,
"step": 1448960
},
{
"epoch": 1.02,
"learning_rate": 2.6267866818050492e-05,
"loss": 3.954,
"step": 1449472
},
{
"epoch": 1.02,
"learning_rate": 2.6259480870539972e-05,
"loss": 3.9517,
"step": 1449984
},
{
"epoch": 1.03,
"eval_loss": 4.025777339935303,
"eval_runtime": 306.2865,
"eval_samples_per_second": 1245.863,
"eval_steps_per_second": 38.934,
"step": 1450080
},
{
"epoch": 0.0,
"learning_rate": 2.6251094923029452e-05,
"loss": 3.9434,
"step": 1450496
},
{
"epoch": 0.0,
"learning_rate": 2.6242708975518932e-05,
"loss": 3.9447,
"step": 1451008
},
{
"epoch": 0.0,
"learning_rate": 2.623432302800841e-05,
"loss": 3.963,
"step": 1451520
},
{
"epoch": 0.0,
"learning_rate": 2.622593708049789e-05,
"loss": 3.9454,
"step": 1452032
},
{
"epoch": 0.0,
"learning_rate": 2.621755113298737e-05,
"loss": 3.9697,
"step": 1452544
},
{
"epoch": 0.0,
"learning_rate": 2.620916518547685e-05,
"loss": 3.9419,
"step": 1453056
},
{
"epoch": 0.0,
"learning_rate": 2.620077923796633e-05,
"loss": 3.9611,
"step": 1453568
},
{
"epoch": 0.0,
"learning_rate": 2.6192393290455808e-05,
"loss": 3.9452,
"step": 1454080
},
{
"epoch": 0.0,
"learning_rate": 2.6184007342945288e-05,
"loss": 3.9535,
"step": 1454592
},
{
"epoch": 0.0,
"learning_rate": 2.6175621395434768e-05,
"loss": 3.9549,
"step": 1455104
},
{
"epoch": 0.0,
"learning_rate": 2.6167235447924248e-05,
"loss": 3.9529,
"step": 1455616
},
{
"epoch": 0.0,
"learning_rate": 2.6158849500413728e-05,
"loss": 3.9605,
"step": 1456128
},
{
"epoch": 0.0,
"learning_rate": 2.615047993170694e-05,
"loss": 3.9472,
"step": 1456640
},
{
"epoch": 0.0,
"learning_rate": 2.614209398419642e-05,
"loss": 3.944,
"step": 1457152
},
{
"epoch": 0.0,
"learning_rate": 2.61337080366859e-05,
"loss": 3.9489,
"step": 1457664
},
{
"epoch": 0.0,
"learning_rate": 2.612532208917538e-05,
"loss": 3.9393,
"step": 1458176
},
{
"epoch": 0.0,
"learning_rate": 2.611693614166486e-05,
"loss": 3.9472,
"step": 1458688
},
{
"epoch": 0.0,
"learning_rate": 2.610855019415434e-05,
"loss": 3.9511,
"step": 1459200
},
{
"epoch": 0.0,
"learning_rate": 2.610016424664382e-05,
"loss": 3.9475,
"step": 1459712
},
{
"epoch": 0.0,
"learning_rate": 2.60917782991333e-05,
"loss": 3.9708,
"step": 1460224
},
{
"epoch": 0.0,
"learning_rate": 2.6083392351622783e-05,
"loss": 3.9558,
"step": 1460736
},
{
"epoch": 0.0,
"learning_rate": 2.6075006404112263e-05,
"loss": 3.9621,
"step": 1461248
},
{
"epoch": 0.0,
"learning_rate": 2.6066620456601743e-05,
"loss": 3.95,
"step": 1461760
},
{
"epoch": 0.0,
"learning_rate": 2.6058234509091223e-05,
"loss": 3.9577,
"step": 1462272
},
{
"epoch": 0.0,
"learning_rate": 2.604988131918816e-05,
"loss": 3.9507,
"step": 1462784
},
{
"epoch": 0.0,
"learning_rate": 2.6041495371677645e-05,
"loss": 3.9511,
"step": 1463296
},
{
"epoch": 0.0,
"learning_rate": 2.6033109424167125e-05,
"loss": 3.9526,
"step": 1463808
},
{
"epoch": 0.0,
"learning_rate": 2.6024723476656605e-05,
"loss": 3.9454,
"step": 1464320
},
{
"epoch": 0.0,
"learning_rate": 2.6016337529146085e-05,
"loss": 3.941,
"step": 1464832
},
{
"epoch": 0.01,
"learning_rate": 2.6007951581635565e-05,
"loss": 3.9449,
"step": 1465344
},
{
"epoch": 0.01,
"learning_rate": 2.5999565634125045e-05,
"loss": 3.9567,
"step": 1465856
},
{
"epoch": 0.01,
"learning_rate": 2.599117968661452e-05,
"loss": 3.9558,
"step": 1466368
},
{
"epoch": 0.01,
"learning_rate": 2.5982793739104e-05,
"loss": 3.9573,
"step": 1466880
},
{
"epoch": 0.01,
"learning_rate": 2.597440779159348e-05,
"loss": 3.9588,
"step": 1467392
},
{
"epoch": 0.01,
"learning_rate": 2.5966054601690426e-05,
"loss": 3.9421,
"step": 1467904
},
{
"epoch": 0.01,
"learning_rate": 2.5957668654179906e-05,
"loss": 3.9475,
"step": 1468416
},
{
"epoch": 0.01,
"learning_rate": 2.5949282706669386e-05,
"loss": 3.9462,
"step": 1468928
},
{
"epoch": 0.01,
"learning_rate": 2.5940896759158866e-05,
"loss": 3.9408,
"step": 1469440
},
{
"epoch": 0.01,
"learning_rate": 2.5932510811648343e-05,
"loss": 3.9453,
"step": 1469952
},
{
"epoch": 0.01,
"learning_rate": 2.592414124294156e-05,
"loss": 3.9423,
"step": 1470464
},
{
"epoch": 0.01,
"learning_rate": 2.591575529543104e-05,
"loss": 3.954,
"step": 1470976
},
{
"epoch": 0.01,
"learning_rate": 2.590736934792052e-05,
"loss": 3.9562,
"step": 1471488
},
{
"epoch": 0.01,
"learning_rate": 2.5898999779213727e-05,
"loss": 3.9505,
"step": 1472000
},
{
"epoch": 0.01,
"learning_rate": 2.5890613831703207e-05,
"loss": 3.9471,
"step": 1472512
},
{
"epoch": 0.01,
"learning_rate": 2.588222788419269e-05,
"loss": 3.9598,
"step": 1473024
},
{
"epoch": 0.01,
"learning_rate": 2.587384193668217e-05,
"loss": 3.941,
"step": 1473536
},
{
"epoch": 0.01,
"learning_rate": 2.5865455989171644e-05,
"loss": 3.9525,
"step": 1474048
},
{
"epoch": 0.01,
"learning_rate": 2.5857070041661124e-05,
"loss": 3.9457,
"step": 1474560
},
{
"epoch": 0.01,
"learning_rate": 2.5848684094150604e-05,
"loss": 3.9338,
"step": 1475072
},
{
"epoch": 0.01,
"learning_rate": 2.5840298146640084e-05,
"loss": 3.9562,
"step": 1475584
},
{
"epoch": 0.01,
"learning_rate": 2.5831912199129564e-05,
"loss": 3.9447,
"step": 1476096
},
{
"epoch": 0.01,
"learning_rate": 2.5823526251619047e-05,
"loss": 3.9454,
"step": 1476608
},
{
"epoch": 0.01,
"learning_rate": 2.5815156682912256e-05,
"loss": 3.9363,
"step": 1477120
},
{
"epoch": 0.01,
"learning_rate": 2.5806770735401736e-05,
"loss": 3.9408,
"step": 1477632
},
{
"epoch": 0.01,
"learning_rate": 2.5798384787891216e-05,
"loss": 3.9317,
"step": 1478144
},
{
"epoch": 0.01,
"learning_rate": 2.5789998840380696e-05,
"loss": 3.9528,
"step": 1478656
},
{
"epoch": 0.01,
"learning_rate": 2.5781612892870176e-05,
"loss": 3.9448,
"step": 1479168
},
{
"epoch": 0.01,
"learning_rate": 2.5773226945359656e-05,
"loss": 3.9493,
"step": 1479680
},
{
"epoch": 0.01,
"learning_rate": 2.576484099784914e-05,
"loss": 3.9562,
"step": 1480192
},
{
"epoch": 0.01,
"learning_rate": 2.575647142914235e-05,
"loss": 3.9417,
"step": 1480704
},
{
"epoch": 0.01,
"learning_rate": 2.574808548163183e-05,
"loss": 3.9312,
"step": 1481216
},
{
"epoch": 0.01,
"learning_rate": 2.5739699534121308e-05,
"loss": 3.9542,
"step": 1481728
},
{
"epoch": 0.01,
"learning_rate": 2.5731313586610788e-05,
"loss": 3.9363,
"step": 1482240
},
{
"epoch": 0.01,
"learning_rate": 2.5722927639100268e-05,
"loss": 3.9339,
"step": 1482752
},
{
"epoch": 0.01,
"learning_rate": 2.5714541691589748e-05,
"loss": 3.9535,
"step": 1483264
},
{
"epoch": 0.01,
"learning_rate": 2.570615574407923e-05,
"loss": 3.953,
"step": 1483776
},
{
"epoch": 0.01,
"learning_rate": 2.569778617537244e-05,
"loss": 3.9415,
"step": 1484288
},
{
"epoch": 0.01,
"learning_rate": 2.568940022786192e-05,
"loss": 3.939,
"step": 1484800
},
{
"epoch": 0.01,
"learning_rate": 2.56810142803514e-05,
"loss": 3.9295,
"step": 1485312
},
{
"epoch": 0.01,
"learning_rate": 2.567262833284088e-05,
"loss": 3.9402,
"step": 1485824
},
{
"epoch": 0.01,
"learning_rate": 2.5664242385330357e-05,
"loss": 3.9524,
"step": 1486336
},
{
"epoch": 0.01,
"learning_rate": 2.5655856437819837e-05,
"loss": 3.952,
"step": 1486848
},
{
"epoch": 0.01,
"learning_rate": 2.5647470490309317e-05,
"loss": 3.9513,
"step": 1487360
},
{
"epoch": 0.01,
"learning_rate": 2.5639084542798797e-05,
"loss": 3.9444,
"step": 1487872
},
{
"epoch": 0.01,
"learning_rate": 2.5630698595288277e-05,
"loss": 3.9617,
"step": 1488384
},
{
"epoch": 0.01,
"learning_rate": 2.5622329026581486e-05,
"loss": 3.9387,
"step": 1488896
},
{
"epoch": 0.01,
"learning_rate": 2.5613959457874702e-05,
"loss": 3.9516,
"step": 1489408
},
{
"epoch": 0.01,
"learning_rate": 2.560557351036418e-05,
"loss": 3.947,
"step": 1489920
},
{
"epoch": 0.01,
"learning_rate": 2.559718756285366e-05,
"loss": 3.9316,
"step": 1490432
},
{
"epoch": 0.01,
"learning_rate": 2.5588801615343138e-05,
"loss": 3.9536,
"step": 1490944
},
{
"epoch": 0.01,
"learning_rate": 2.5580415667832618e-05,
"loss": 3.9536,
"step": 1491456
},
{
"epoch": 0.01,
"learning_rate": 2.5572029720322098e-05,
"loss": 3.9492,
"step": 1491968
},
{
"epoch": 0.01,
"learning_rate": 2.5563643772811578e-05,
"loss": 3.9421,
"step": 1492480
},
{
"epoch": 0.01,
"learning_rate": 2.555527420410479e-05,
"loss": 3.9302,
"step": 1492992
},
{
"epoch": 0.01,
"learning_rate": 2.554688825659427e-05,
"loss": 3.9466,
"step": 1493504
},
{
"epoch": 0.01,
"learning_rate": 2.553850230908375e-05,
"loss": 3.9442,
"step": 1494016
},
{
"epoch": 0.01,
"learning_rate": 2.553011636157323e-05,
"loss": 3.9513,
"step": 1494528
},
{
"epoch": 0.01,
"learning_rate": 2.5521763171670176e-05,
"loss": 3.9428,
"step": 1495040
},
{
"epoch": 0.01,
"learning_rate": 2.5513377224159652e-05,
"loss": 3.9503,
"step": 1495552
},
{
"epoch": 0.02,
"learning_rate": 2.5504991276649132e-05,
"loss": 3.941,
"step": 1496064
},
{
"epoch": 0.02,
"learning_rate": 2.5496605329138612e-05,
"loss": 3.9402,
"step": 1496576
},
{
"epoch": 0.02,
"learning_rate": 2.5488219381628092e-05,
"loss": 3.9394,
"step": 1497088
},
{
"epoch": 0.02,
"learning_rate": 2.54798498129213e-05,
"loss": 3.9386,
"step": 1497600
},
{
"epoch": 0.02,
"learning_rate": 2.5471463865410784e-05,
"loss": 3.957,
"step": 1498112
},
{
"epoch": 0.02,
"learning_rate": 2.5463077917900264e-05,
"loss": 3.9546,
"step": 1498624
},
{
"epoch": 0.02,
"learning_rate": 2.5454691970389744e-05,
"loss": 3.9561,
"step": 1499136
},
{
"epoch": 0.02,
"learning_rate": 2.5446306022879224e-05,
"loss": 3.9329,
"step": 1499648
},
{
"epoch": 0.02,
"learning_rate": 2.5437920075368704e-05,
"loss": 3.9495,
"step": 1500160
},
{
"epoch": 0.02,
"learning_rate": 2.5429534127858184e-05,
"loss": 3.9433,
"step": 1500672
},
{
"epoch": 0.02,
"learning_rate": 2.5421148180347664e-05,
"loss": 3.9507,
"step": 1501184
},
{
"epoch": 0.02,
"learning_rate": 2.5412762232837144e-05,
"loss": 3.9412,
"step": 1501696
},
{
"epoch": 0.02,
"learning_rate": 2.5404376285326624e-05,
"loss": 3.9413,
"step": 1502208
},
{
"epoch": 0.02,
"learning_rate": 2.5396006716619837e-05,
"loss": 3.9336,
"step": 1502720
},
{
"epoch": 0.02,
"learning_rate": 2.5387620769109316e-05,
"loss": 3.9539,
"step": 1503232
},
{
"epoch": 0.02,
"learning_rate": 2.5379234821598796e-05,
"loss": 3.9293,
"step": 1503744
},
{
"epoch": 0.02,
"learning_rate": 2.5370848874088276e-05,
"loss": 3.9436,
"step": 1504256
},
{
"epoch": 0.02,
"learning_rate": 2.5362479305381485e-05,
"loss": 3.9422,
"step": 1504768
},
{
"epoch": 0.02,
"learning_rate": 2.535409335787097e-05,
"loss": 3.9425,
"step": 1505280
},
{
"epoch": 0.02,
"learning_rate": 2.534570741036045e-05,
"loss": 3.9381,
"step": 1505792
},
{
"epoch": 0.02,
"learning_rate": 2.533732146284993e-05,
"loss": 3.9519,
"step": 1506304
},
{
"epoch": 0.02,
"learning_rate": 2.532893551533941e-05,
"loss": 3.9436,
"step": 1506816
},
{
"epoch": 0.02,
"learning_rate": 2.532054956782889e-05,
"loss": 3.9407,
"step": 1507328
},
{
"epoch": 0.02,
"learning_rate": 2.5312163620318362e-05,
"loss": 3.9495,
"step": 1507840
},
{
"epoch": 0.02,
"learning_rate": 2.5303777672807845e-05,
"loss": 3.9378,
"step": 1508352
},
{
"epoch": 0.02,
"learning_rate": 2.5295391725297325e-05,
"loss": 3.9528,
"step": 1508864
},
{
"epoch": 0.02,
"learning_rate": 2.5287005777786805e-05,
"loss": 3.9611,
"step": 1509376
},
{
"epoch": 0.02,
"learning_rate": 2.5278636209080014e-05,
"loss": 3.9461,
"step": 1509888
},
{
"epoch": 0.02,
"learning_rate": 2.5270250261569494e-05,
"loss": 3.9398,
"step": 1510400
},
{
"epoch": 0.02,
"learning_rate": 2.5261864314058974e-05,
"loss": 3.9417,
"step": 1510912
},
{
"epoch": 0.02,
"learning_rate": 2.5253478366548454e-05,
"loss": 3.945,
"step": 1511424
},
{
"epoch": 0.02,
"learning_rate": 2.5245092419037934e-05,
"loss": 3.9422,
"step": 1511936
},
{
"epoch": 0.02,
"learning_rate": 2.5236706471527417e-05,
"loss": 3.9495,
"step": 1512448
},
{
"epoch": 0.02,
"learning_rate": 2.5228336902820626e-05,
"loss": 3.9334,
"step": 1512960
},
{
"epoch": 0.02,
"learning_rate": 2.5219950955310106e-05,
"loss": 3.9562,
"step": 1513472
},
{
"epoch": 0.02,
"learning_rate": 2.5211565007799586e-05,
"loss": 3.9492,
"step": 1513984
},
{
"epoch": 0.02,
"learning_rate": 2.5203179060289066e-05,
"loss": 3.9457,
"step": 1514496
},
{
"epoch": 0.02,
"learning_rate": 2.5194793112778546e-05,
"loss": 3.9323,
"step": 1515008
},
{
"epoch": 0.02,
"learning_rate": 2.518642354407176e-05,
"loss": 3.9431,
"step": 1515520
},
{
"epoch": 0.02,
"learning_rate": 2.517803759656124e-05,
"loss": 3.9377,
"step": 1516032
},
{
"epoch": 0.02,
"learning_rate": 2.516965164905072e-05,
"loss": 3.9524,
"step": 1516544
},
{
"epoch": 0.02,
"learning_rate": 2.51612657015402e-05,
"loss": 3.9575,
"step": 1517056
},
{
"epoch": 0.02,
"learning_rate": 2.515287975402968e-05,
"loss": 3.9441,
"step": 1517568
},
{
"epoch": 0.02,
"learning_rate": 2.514449380651916e-05,
"loss": 3.9288,
"step": 1518080
},
{
"epoch": 0.02,
"learning_rate": 2.513610785900864e-05,
"loss": 3.9504,
"step": 1518592
},
{
"epoch": 0.02,
"learning_rate": 2.512772191149812e-05,
"loss": 3.9414,
"step": 1519104
},
{
"epoch": 0.02,
"learning_rate": 2.511935234279133e-05,
"loss": 3.9568,
"step": 1519616
},
{
"epoch": 0.02,
"learning_rate": 2.511096639528081e-05,
"loss": 3.9343,
"step": 1520128
},
{
"epoch": 0.02,
"learning_rate": 2.510259682657402e-05,
"loss": 3.9496,
"step": 1520640
},
{
"epoch": 0.02,
"learning_rate": 2.50942108790635e-05,
"loss": 3.9486,
"step": 1521152
},
{
"epoch": 0.02,
"learning_rate": 2.508582493155298e-05,
"loss": 3.9495,
"step": 1521664
},
{
"epoch": 0.02,
"learning_rate": 2.5077438984042463e-05,
"loss": 3.9459,
"step": 1522176
},
{
"epoch": 0.02,
"learning_rate": 2.5069053036531943e-05,
"loss": 3.948,
"step": 1522688
},
{
"epoch": 0.02,
"learning_rate": 2.5060667089021423e-05,
"loss": 3.9395,
"step": 1523200
},
{
"epoch": 0.02,
"learning_rate": 2.5052297520314632e-05,
"loss": 3.9449,
"step": 1523712
},
{
"epoch": 0.02,
"learning_rate": 2.5043911572804112e-05,
"loss": 3.9475,
"step": 1524224
},
{
"epoch": 0.02,
"learning_rate": 2.5035525625293592e-05,
"loss": 3.9449,
"step": 1524736
},
{
"epoch": 0.02,
"learning_rate": 2.5027156056586805e-05,
"loss": 3.9397,
"step": 1525248
},
{
"epoch": 0.02,
"learning_rate": 2.5018770109076285e-05,
"loss": 3.9469,
"step": 1525760
},
{
"epoch": 0.02,
"learning_rate": 2.5010384161565765e-05,
"loss": 3.9412,
"step": 1526272
},
{
"epoch": 0.03,
"eval_loss": 4.022004127502441,
"eval_runtime": 298.4179,
"eval_samples_per_second": 1278.714,
"eval_steps_per_second": 39.961,
"step": 1526400
},
{
"epoch": 0.0,
"learning_rate": 2.5001998214055244e-05,
"loss": 3.9352,
"step": 1526784
},
{
"epoch": 0.0,
"learning_rate": 2.499361226654472e-05,
"loss": 3.9399,
"step": 1527296
},
{
"epoch": 0.0,
"learning_rate": 2.49852263190342e-05,
"loss": 3.9539,
"step": 1527808
},
{
"epoch": 0.0,
"learning_rate": 2.497684037152368e-05,
"loss": 3.9394,
"step": 1528320
},
{
"epoch": 0.0,
"learning_rate": 2.4968454424013164e-05,
"loss": 3.9563,
"step": 1528832
},
{
"epoch": 0.0,
"learning_rate": 2.496006847650264e-05,
"loss": 3.9398,
"step": 1529344
},
{
"epoch": 0.0,
"learning_rate": 2.495168252899212e-05,
"loss": 3.9485,
"step": 1529856
},
{
"epoch": 0.0,
"learning_rate": 2.49432965814816e-05,
"loss": 3.9423,
"step": 1530368
},
{
"epoch": 0.0,
"learning_rate": 2.493491063397108e-05,
"loss": 3.9438,
"step": 1530880
},
{
"epoch": 0.0,
"learning_rate": 2.492652468646056e-05,
"loss": 3.9457,
"step": 1531392
},
{
"epoch": 0.0,
"learning_rate": 2.491813873895004e-05,
"loss": 3.9459,
"step": 1531904
},
{
"epoch": 0.0,
"learning_rate": 2.4909752791439524e-05,
"loss": 3.9526,
"step": 1532416
},
{
"epoch": 0.0,
"learning_rate": 2.4901383222732733e-05,
"loss": 3.9406,
"step": 1532928
},
{
"epoch": 0.0,
"learning_rate": 2.4892997275222213e-05,
"loss": 3.9365,
"step": 1533440
},
{
"epoch": 0.0,
"learning_rate": 2.4884611327711693e-05,
"loss": 3.9413,
"step": 1533952
},
{
"epoch": 0.0,
"learning_rate": 2.4876225380201173e-05,
"loss": 3.9313,
"step": 1534464
},
{
"epoch": 0.0,
"learning_rate": 2.486783943269065e-05,
"loss": 3.9422,
"step": 1534976
},
{
"epoch": 0.0,
"learning_rate": 2.4859453485180133e-05,
"loss": 3.9419,
"step": 1535488
},
{
"epoch": 0.0,
"learning_rate": 2.4851067537669613e-05,
"loss": 3.9405,
"step": 1536000
},
{
"epoch": 0.0,
"learning_rate": 2.4842681590159093e-05,
"loss": 3.9636,
"step": 1536512
},
{
"epoch": 0.0,
"learning_rate": 2.4834295642648573e-05,
"loss": 3.9481,
"step": 1537024
},
{
"epoch": 0.0,
"learning_rate": 2.4825909695138053e-05,
"loss": 3.9542,
"step": 1537536
},
{
"epoch": 0.0,
"learning_rate": 2.481752374762753e-05,
"loss": 3.9438,
"step": 1538048
},
{
"epoch": 0.0,
"learning_rate": 2.4809154178920742e-05,
"loss": 3.9498,
"step": 1538560
},
{
"epoch": 0.0,
"learning_rate": 2.4800768231410225e-05,
"loss": 3.9411,
"step": 1539072
},
{
"epoch": 0.0,
"learning_rate": 2.4792382283899705e-05,
"loss": 3.9488,
"step": 1539584
},
{
"epoch": 0.0,
"learning_rate": 2.478399633638918e-05,
"loss": 3.9419,
"step": 1540096
},
{
"epoch": 0.0,
"learning_rate": 2.477561038887866e-05,
"loss": 3.9376,
"step": 1540608
},
{
"epoch": 0.0,
"learning_rate": 2.476722444136814e-05,
"loss": 3.9357,
"step": 1541120
},
{
"epoch": 0.0,
"learning_rate": 2.475883849385762e-05,
"loss": 3.9361,
"step": 1541632
},
{
"epoch": 0.01,
"learning_rate": 2.47504525463471e-05,
"loss": 3.946,
"step": 1542144
},
{
"epoch": 0.01,
"learning_rate": 2.4742082977640314e-05,
"loss": 3.9492,
"step": 1542656
},
{
"epoch": 0.01,
"learning_rate": 2.4733697030129794e-05,
"loss": 3.9471,
"step": 1543168
},
{
"epoch": 0.01,
"learning_rate": 2.4725311082619274e-05,
"loss": 3.9481,
"step": 1543680
},
{
"epoch": 0.01,
"learning_rate": 2.4716941513912483e-05,
"loss": 3.9339,
"step": 1544192
},
{
"epoch": 0.01,
"learning_rate": 2.4708571945205695e-05,
"loss": 3.9418,
"step": 1544704
},
{
"epoch": 0.01,
"learning_rate": 2.470018599769518e-05,
"loss": 3.9411,
"step": 1545216
},
{
"epoch": 0.01,
"learning_rate": 2.4691800050184655e-05,
"loss": 3.931,
"step": 1545728
},
{
"epoch": 0.01,
"learning_rate": 2.4683414102674135e-05,
"loss": 3.9405,
"step": 1546240
},
{
"epoch": 0.01,
"learning_rate": 2.4675028155163615e-05,
"loss": 3.9333,
"step": 1546752
},
{
"epoch": 0.01,
"learning_rate": 2.4666642207653095e-05,
"loss": 3.9465,
"step": 1547264
},
{
"epoch": 0.01,
"learning_rate": 2.4658256260142575e-05,
"loss": 3.9478,
"step": 1547776
},
{
"epoch": 0.01,
"learning_rate": 2.4649870312632055e-05,
"loss": 3.9432,
"step": 1548288
},
{
"epoch": 0.01,
"learning_rate": 2.4641484365121535e-05,
"loss": 3.9349,
"step": 1548800
},
{
"epoch": 0.01,
"learning_rate": 2.4633098417611015e-05,
"loss": 3.953,
"step": 1549312
},
{
"epoch": 0.01,
"learning_rate": 2.4624712470100495e-05,
"loss": 3.9312,
"step": 1549824
},
{
"epoch": 0.01,
"learning_rate": 2.4616342901393707e-05,
"loss": 3.9479,
"step": 1550336
},
{
"epoch": 0.01,
"learning_rate": 2.4607956953883184e-05,
"loss": 3.9367,
"step": 1550848
},
{
"epoch": 0.01,
"learning_rate": 2.4599571006372664e-05,
"loss": 3.9253,
"step": 1551360
},
{
"epoch": 0.01,
"learning_rate": 2.459120143766588e-05,
"loss": 3.949,
"step": 1551872
},
{
"epoch": 0.01,
"learning_rate": 2.458281549015536e-05,
"loss": 3.935,
"step": 1552384
},
{
"epoch": 0.01,
"learning_rate": 2.4574429542644836e-05,
"loss": 3.9343,
"step": 1552896
},
{
"epoch": 0.01,
"learning_rate": 2.4566043595134316e-05,
"loss": 3.9315,
"step": 1553408
},
{
"epoch": 0.01,
"learning_rate": 2.4557657647623796e-05,
"loss": 3.9304,
"step": 1553920
},
{
"epoch": 0.01,
"learning_rate": 2.4549271700113276e-05,
"loss": 3.9274,
"step": 1554432
},
{
"epoch": 0.01,
"learning_rate": 2.4540885752602756e-05,
"loss": 3.9402,
"step": 1554944
},
{
"epoch": 0.01,
"learning_rate": 2.4532499805092236e-05,
"loss": 3.9421,
"step": 1555456
},
{
"epoch": 0.01,
"learning_rate": 2.4524113857581716e-05,
"loss": 3.9423,
"step": 1555968
},
{
"epoch": 0.01,
"learning_rate": 2.4515727910071196e-05,
"loss": 3.9479,
"step": 1556480
},
{
"epoch": 0.01,
"learning_rate": 2.450735834136441e-05,
"loss": 3.9353,
"step": 1556992
},
{
"epoch": 0.01,
"learning_rate": 2.4498988772657618e-05,
"loss": 3.9238,
"step": 1557504
},
{
"epoch": 0.01,
"learning_rate": 2.4490602825147098e-05,
"loss": 3.9454,
"step": 1558016
},
{
"epoch": 0.01,
"learning_rate": 2.448221687763658e-05,
"loss": 3.9282,
"step": 1558528
},
{
"epoch": 0.01,
"learning_rate": 2.447383093012606e-05,
"loss": 3.9227,
"step": 1559040
},
{
"epoch": 0.01,
"learning_rate": 2.446544498261554e-05,
"loss": 3.9488,
"step": 1559552
},
{
"epoch": 0.01,
"learning_rate": 2.4457059035105017e-05,
"loss": 3.9432,
"step": 1560064
},
{
"epoch": 0.01,
"learning_rate": 2.4448673087594497e-05,
"loss": 3.9347,
"step": 1560576
},
{
"epoch": 0.01,
"learning_rate": 2.4440287140083977e-05,
"loss": 3.9324,
"step": 1561088
},
{
"epoch": 0.01,
"learning_rate": 2.443191757137719e-05,
"loss": 3.9203,
"step": 1561600
},
{
"epoch": 0.01,
"learning_rate": 2.442353162386667e-05,
"loss": 3.9331,
"step": 1562112
},
{
"epoch": 0.01,
"learning_rate": 2.441514567635615e-05,
"loss": 3.9468,
"step": 1562624
},
{
"epoch": 0.01,
"learning_rate": 2.440675972884563e-05,
"loss": 3.9418,
"step": 1563136
},
{
"epoch": 0.01,
"learning_rate": 2.439837378133511e-05,
"loss": 3.942,
"step": 1563648
},
{
"epoch": 0.01,
"learning_rate": 2.439000421262832e-05,
"loss": 3.9367,
"step": 1564160
},
{
"epoch": 0.01,
"learning_rate": 2.4381634643921535e-05,
"loss": 3.9566,
"step": 1564672
},
{
"epoch": 0.01,
"learning_rate": 2.4373248696411015e-05,
"loss": 3.9322,
"step": 1565184
},
{
"epoch": 0.01,
"learning_rate": 2.436486274890049e-05,
"loss": 3.9454,
"step": 1565696
},
{
"epoch": 0.01,
"learning_rate": 2.435647680138997e-05,
"loss": 3.9388,
"step": 1566208
},
{
"epoch": 0.01,
"learning_rate": 2.434809085387945e-05,
"loss": 3.9186,
"step": 1566720
},
{
"epoch": 0.01,
"learning_rate": 2.4339721285172664e-05,
"loss": 3.9489,
"step": 1567232
},
{
"epoch": 0.01,
"learning_rate": 2.4331335337662143e-05,
"loss": 3.9444,
"step": 1567744
},
{
"epoch": 0.01,
"learning_rate": 2.4322949390151623e-05,
"loss": 3.9414,
"step": 1568256
},
{
"epoch": 0.01,
"learning_rate": 2.4314563442641103e-05,
"loss": 3.9362,
"step": 1568768
},
{
"epoch": 0.01,
"learning_rate": 2.4306177495130583e-05,
"loss": 3.9214,
"step": 1569280
},
{
"epoch": 0.01,
"learning_rate": 2.4297807926423792e-05,
"loss": 3.9406,
"step": 1569792
},
{
"epoch": 0.01,
"learning_rate": 2.4289421978913272e-05,
"loss": 3.935,
"step": 1570304
},
{
"epoch": 0.01,
"learning_rate": 2.4281036031402756e-05,
"loss": 3.9452,
"step": 1570816
},
{
"epoch": 0.01,
"learning_rate": 2.4272666462695965e-05,
"loss": 3.9345,
"step": 1571328
},
{
"epoch": 0.01,
"learning_rate": 2.4264280515185445e-05,
"loss": 3.9406,
"step": 1571840
},
{
"epoch": 0.02,
"learning_rate": 2.4255894567674925e-05,
"loss": 3.9333,
"step": 1572352
},
{
"epoch": 0.02,
"learning_rate": 2.4247508620164405e-05,
"loss": 3.9337,
"step": 1572864
},
{
"epoch": 0.02,
"learning_rate": 2.4239122672653885e-05,
"loss": 3.9295,
"step": 1573376
},
{
"epoch": 0.02,
"learning_rate": 2.4230736725143365e-05,
"loss": 3.9325,
"step": 1573888
},
{
"epoch": 0.02,
"learning_rate": 2.4222350777632845e-05,
"loss": 3.9488,
"step": 1574400
},
{
"epoch": 0.02,
"learning_rate": 2.4213964830122325e-05,
"loss": 3.9462,
"step": 1574912
},
{
"epoch": 0.02,
"learning_rate": 2.4205578882611804e-05,
"loss": 3.953,
"step": 1575424
},
{
"epoch": 0.02,
"learning_rate": 2.4197192935101284e-05,
"loss": 3.9245,
"step": 1575936
},
{
"epoch": 0.02,
"learning_rate": 2.4188823366394494e-05,
"loss": 3.9412,
"step": 1576448
},
{
"epoch": 0.02,
"learning_rate": 2.4180437418883974e-05,
"loss": 3.9367,
"step": 1576960
},
{
"epoch": 0.02,
"learning_rate": 2.417206785017719e-05,
"loss": 3.9413,
"step": 1577472
},
{
"epoch": 0.02,
"learning_rate": 2.416368190266667e-05,
"loss": 3.9379,
"step": 1577984
},
{
"epoch": 0.02,
"learning_rate": 2.4155295955156146e-05,
"loss": 3.93,
"step": 1578496
},
{
"epoch": 0.02,
"learning_rate": 2.4146910007645626e-05,
"loss": 3.9315,
"step": 1579008
},
{
"epoch": 0.02,
"learning_rate": 2.4138524060135106e-05,
"loss": 3.9465,
"step": 1579520
},
{
"epoch": 0.02,
"learning_rate": 2.4130138112624586e-05,
"loss": 3.922,
"step": 1580032
},
{
"epoch": 0.02,
"learning_rate": 2.4121752165114066e-05,
"loss": 3.9366,
"step": 1580544
},
{
"epoch": 0.02,
"learning_rate": 2.411336621760355e-05,
"loss": 3.9317,
"step": 1581056
},
{
"epoch": 0.02,
"learning_rate": 2.4104980270093026e-05,
"loss": 3.9395,
"step": 1581568
},
{
"epoch": 0.02,
"learning_rate": 2.4096594322582506e-05,
"loss": 3.932,
"step": 1582080
},
{
"epoch": 0.02,
"learning_rate": 2.4088208375071986e-05,
"loss": 3.9423,
"step": 1582592
},
{
"epoch": 0.02,
"learning_rate": 2.4079822427561466e-05,
"loss": 3.9396,
"step": 1583104
},
{
"epoch": 0.02,
"learning_rate": 2.4071452858854675e-05,
"loss": 3.9328,
"step": 1583616
},
{
"epoch": 0.02,
"learning_rate": 2.4063066911344158e-05,
"loss": 3.9402,
"step": 1584128
},
{
"epoch": 0.02,
"learning_rate": 2.4054680963833638e-05,
"loss": 3.9316,
"step": 1584640
},
{
"epoch": 0.02,
"learning_rate": 2.4046295016323118e-05,
"loss": 3.9454,
"step": 1585152
},
{
"epoch": 0.02,
"learning_rate": 2.4037909068812598e-05,
"loss": 3.9517,
"step": 1585664
},
{
"epoch": 0.02,
"learning_rate": 2.4029539500105807e-05,
"loss": 3.9367,
"step": 1586176
},
{
"epoch": 0.02,
"learning_rate": 2.4021153552595287e-05,
"loss": 3.9314,
"step": 1586688
},
{
"epoch": 0.02,
"learning_rate": 2.4012767605084767e-05,
"loss": 3.9349,
"step": 1587200
},
{
"epoch": 0.02,
"learning_rate": 2.400438165757425e-05,
"loss": 3.9361,
"step": 1587712
},
{
"epoch": 0.02,
"learning_rate": 2.399599571006373e-05,
"loss": 3.935,
"step": 1588224
},
{
"epoch": 0.02,
"learning_rate": 2.3987609762553207e-05,
"loss": 3.9373,
"step": 1588736
},
{
"epoch": 0.02,
"learning_rate": 2.397924019384642e-05,
"loss": 3.9286,
"step": 1589248
},
{
"epoch": 0.02,
"learning_rate": 2.39708542463359e-05,
"loss": 3.9485,
"step": 1589760
},
{
"epoch": 0.02,
"learning_rate": 2.396246829882538e-05,
"loss": 3.9408,
"step": 1590272
},
{
"epoch": 0.02,
"learning_rate": 2.395409873011859e-05,
"loss": 3.9419,
"step": 1590784
},
{
"epoch": 0.02,
"learning_rate": 2.394571278260807e-05,
"loss": 3.9266,
"step": 1591296
},
{
"epoch": 0.02,
"learning_rate": 2.393734321390128e-05,
"loss": 3.9343,
"step": 1591808
},
{
"epoch": 0.02,
"learning_rate": 2.392895726639076e-05,
"loss": 3.9285,
"step": 1592320
},
{
"epoch": 0.02,
"learning_rate": 2.392057131888024e-05,
"loss": 3.9412,
"step": 1592832
},
{
"epoch": 0.02,
"learning_rate": 2.391218537136972e-05,
"loss": 3.9466,
"step": 1593344
},
{
"epoch": 0.02,
"learning_rate": 2.3903799423859204e-05,
"loss": 3.9396,
"step": 1593856
},
{
"epoch": 0.02,
"learning_rate": 2.389541347634868e-05,
"loss": 3.9217,
"step": 1594368
},
{
"epoch": 0.02,
"learning_rate": 2.3887043907641893e-05,
"loss": 3.9432,
"step": 1594880
},
{
"epoch": 0.02,
"learning_rate": 2.3878657960131373e-05,
"loss": 3.9344,
"step": 1595392
},
{
"epoch": 0.02,
"learning_rate": 2.3870272012620853e-05,
"loss": 3.9479,
"step": 1595904
},
{
"epoch": 0.02,
"learning_rate": 2.386188606511033e-05,
"loss": 3.9273,
"step": 1596416
},
{
"epoch": 0.02,
"learning_rate": 2.3853500117599813e-05,
"loss": 3.9456,
"step": 1596928
},
{
"epoch": 0.02,
"learning_rate": 2.3845114170089293e-05,
"loss": 3.9411,
"step": 1597440
},
{
"epoch": 0.02,
"learning_rate": 2.3836728222578773e-05,
"loss": 3.9441,
"step": 1597952
},
{
"epoch": 0.02,
"learning_rate": 2.3828342275068253e-05,
"loss": 3.9358,
"step": 1598464
},
{
"epoch": 0.02,
"learning_rate": 2.381997270636146e-05,
"loss": 3.9411,
"step": 1598976
},
{
"epoch": 0.02,
"learning_rate": 2.381158675885094e-05,
"loss": 3.9311,
"step": 1599488
},
{
"epoch": 0.02,
"learning_rate": 2.380320081134042e-05,
"loss": 3.9398,
"step": 1600000
},
{
"epoch": 0.02,
"learning_rate": 2.3794814863829905e-05,
"loss": 3.9389,
"step": 1600512
},
{
"epoch": 0.02,
"learning_rate": 2.3786428916319385e-05,
"loss": 3.9387,
"step": 1601024
},
{
"epoch": 0.02,
"learning_rate": 2.377804296880886e-05,
"loss": 3.9328,
"step": 1601536
},
{
"epoch": 0.02,
"learning_rate": 2.3769673400102074e-05,
"loss": 3.9363,
"step": 1602048
},
{
"epoch": 0.02,
"learning_rate": 2.3761287452591554e-05,
"loss": 3.9384,
"step": 1602560
},
{
"epoch": 0.03,
"eval_loss": 4.018955230712891,
"eval_runtime": 300.3274,
"eval_samples_per_second": 1270.584,
"eval_steps_per_second": 39.707,
"step": 1602720
},
{
"epoch": 1.0,
"learning_rate": 2.3752901505081034e-05,
"loss": 3.934,
"step": 1603072
},
{
"epoch": 1.0,
"learning_rate": 2.3744515557570514e-05,
"loss": 3.9308,
"step": 1603584
},
{
"epoch": 1.0,
"learning_rate": 2.3736145988863726e-05,
"loss": 3.9465,
"step": 1604096
},
{
"epoch": 1.0,
"learning_rate": 2.3727760041353206e-05,
"loss": 3.9319,
"step": 1604608
},
{
"epoch": 1.0,
"learning_rate": 2.3719374093842683e-05,
"loss": 3.9457,
"step": 1605120
},
{
"epoch": 1.0,
"learning_rate": 2.3710988146332163e-05,
"loss": 3.934,
"step": 1605632
},
{
"epoch": 1.0,
"learning_rate": 2.3702602198821643e-05,
"loss": 3.9389,
"step": 1606144
},
{
"epoch": 1.0,
"learning_rate": 2.369423263011486e-05,
"loss": 3.9388,
"step": 1606656
},
{
"epoch": 1.0,
"learning_rate": 2.3685846682604335e-05,
"loss": 3.9363,
"step": 1607168
},
{
"epoch": 1.0,
"learning_rate": 2.3677460735093815e-05,
"loss": 3.9369,
"step": 1607680
},
{
"epoch": 1.0,
"learning_rate": 2.3669074787583295e-05,
"loss": 3.9428,
"step": 1608192
},
{
"epoch": 1.0,
"learning_rate": 2.3660688840072775e-05,
"loss": 3.9444,
"step": 1608704
},
{
"epoch": 1.0,
"learning_rate": 2.3652319271365984e-05,
"loss": 3.9345,
"step": 1609216
},
{
"epoch": 1.0,
"learning_rate": 2.3643933323855467e-05,
"loss": 3.9287,
"step": 1609728
},
{
"epoch": 1.0,
"learning_rate": 2.3635547376344947e-05,
"loss": 3.9362,
"step": 1610240
},
{
"epoch": 1.0,
"learning_rate": 2.3627161428834427e-05,
"loss": 3.9221,
"step": 1610752
},
{
"epoch": 1.0,
"learning_rate": 2.3618775481323907e-05,
"loss": 3.935,
"step": 1611264
},
{
"epoch": 1.0,
"learning_rate": 2.3610389533813387e-05,
"loss": 3.9335,
"step": 1611776
},
{
"epoch": 1.0,
"learning_rate": 2.3602003586302864e-05,
"loss": 3.9352,
"step": 1612288
},
{
"epoch": 1.0,
"learning_rate": 2.3593617638792344e-05,
"loss": 3.9541,
"step": 1612800
},
{
"epoch": 1.0,
"learning_rate": 2.3585231691281827e-05,
"loss": 3.942,
"step": 1613312
},
{
"epoch": 1.0,
"learning_rate": 2.3576845743771307e-05,
"loss": 3.9463,
"step": 1613824
},
{
"epoch": 1.0,
"learning_rate": 2.3568459796260787e-05,
"loss": 3.9377,
"step": 1614336
},
{
"epoch": 1.0,
"learning_rate": 2.3560090227553996e-05,
"loss": 3.9399,
"step": 1614848
},
{
"epoch": 1.0,
"learning_rate": 2.3551704280043476e-05,
"loss": 3.9353,
"step": 1615360
},
{
"epoch": 1.0,
"learning_rate": 2.3543318332532956e-05,
"loss": 3.9395,
"step": 1615872
},
{
"epoch": 1.0,
"learning_rate": 2.3534932385022436e-05,
"loss": 3.9346,
"step": 1616384
},
{
"epoch": 1.0,
"learning_rate": 2.3526546437511916e-05,
"loss": 3.934,
"step": 1616896
},
{
"epoch": 1.0,
"learning_rate": 2.351817686880513e-05,
"loss": 3.9301,
"step": 1617408
},
{
"epoch": 1.0,
"learning_rate": 2.350979092129461e-05,
"loss": 3.9296,
"step": 1617920
},
{
"epoch": 1.01,
"learning_rate": 2.350140497378409e-05,
"loss": 3.9363,
"step": 1618432
},
{
"epoch": 1.01,
"learning_rate": 2.349301902627357e-05,
"loss": 3.9425,
"step": 1618944
},
{
"epoch": 1.01,
"learning_rate": 2.3484633078763045e-05,
"loss": 3.9399,
"step": 1619456
},
{
"epoch": 1.01,
"learning_rate": 2.3476247131252528e-05,
"loss": 3.9433,
"step": 1619968
},
{
"epoch": 1.01,
"learning_rate": 2.3467861183742008e-05,
"loss": 3.9285,
"step": 1620480
},
{
"epoch": 1.01,
"learning_rate": 2.345949161503522e-05,
"loss": 3.9356,
"step": 1620992
},
{
"epoch": 1.01,
"learning_rate": 2.3451105667524697e-05,
"loss": 3.933,
"step": 1621504
},
{
"epoch": 1.01,
"learning_rate": 2.3442719720014177e-05,
"loss": 3.9244,
"step": 1622016
},
{
"epoch": 1.01,
"learning_rate": 2.3434333772503657e-05,
"loss": 3.9344,
"step": 1622528
},
{
"epoch": 1.01,
"learning_rate": 2.342596420379687e-05,
"loss": 3.9219,
"step": 1623040
},
{
"epoch": 1.01,
"learning_rate": 2.341757825628635e-05,
"loss": 3.9382,
"step": 1623552
},
{
"epoch": 1.01,
"learning_rate": 2.340919230877583e-05,
"loss": 3.9407,
"step": 1624064
},
{
"epoch": 1.01,
"learning_rate": 2.340080636126531e-05,
"loss": 3.9379,
"step": 1624576
},
{
"epoch": 1.01,
"learning_rate": 2.339242041375479e-05,
"loss": 3.9297,
"step": 1625088
},
{
"epoch": 1.01,
"learning_rate": 2.338403446624427e-05,
"loss": 3.9466,
"step": 1625600
},
{
"epoch": 1.01,
"learning_rate": 2.337564851873375e-05,
"loss": 3.9233,
"step": 1626112
},
{
"epoch": 1.01,
"learning_rate": 2.3367278950026962e-05,
"loss": 3.9425,
"step": 1626624
},
{
"epoch": 1.01,
"learning_rate": 2.3358893002516442e-05,
"loss": 3.9306,
"step": 1627136
},
{
"epoch": 1.01,
"learning_rate": 2.3350507055005922e-05,
"loss": 3.9113,
"step": 1627648
},
{
"epoch": 1.01,
"learning_rate": 2.3342121107495402e-05,
"loss": 3.9477,
"step": 1628160
},
{
"epoch": 1.01,
"learning_rate": 2.3333735159984878e-05,
"loss": 3.9275,
"step": 1628672
},
{
"epoch": 1.01,
"learning_rate": 2.3325349212474358e-05,
"loss": 3.9354,
"step": 1629184
},
{
"epoch": 1.01,
"learning_rate": 2.3316963264963838e-05,
"loss": 3.9221,
"step": 1629696
},
{
"epoch": 1.01,
"learning_rate": 2.330857731745332e-05,
"loss": 3.9214,
"step": 1630208
},
{
"epoch": 1.01,
"learning_rate": 2.330020774874653e-05,
"loss": 3.9251,
"step": 1630720
},
{
"epoch": 1.01,
"learning_rate": 2.3291838180039743e-05,
"loss": 3.9283,
"step": 1631232
},
{
"epoch": 1.01,
"learning_rate": 2.3283452232529223e-05,
"loss": 3.9348,
"step": 1631744
},
{
"epoch": 1.01,
"learning_rate": 2.32750662850187e-05,
"loss": 3.9338,
"step": 1632256
},
{
"epoch": 1.01,
"learning_rate": 2.3266680337508183e-05,
"loss": 3.9444,
"step": 1632768
},
{
"epoch": 1.01,
"learning_rate": 2.3258294389997663e-05,
"loss": 3.9276,
"step": 1633280
},
{
"epoch": 1.01,
"learning_rate": 2.3249908442487143e-05,
"loss": 3.9183,
"step": 1633792
},
{
"epoch": 1.01,
"learning_rate": 2.3241522494976623e-05,
"loss": 3.9388,
"step": 1634304
},
{
"epoch": 1.01,
"learning_rate": 2.3233136547466103e-05,
"loss": 3.919,
"step": 1634816
},
{
"epoch": 1.01,
"learning_rate": 2.3224750599955583e-05,
"loss": 3.9187,
"step": 1635328
},
{
"epoch": 1.01,
"learning_rate": 2.321636465244506e-05,
"loss": 3.9404,
"step": 1635840
},
{
"epoch": 1.01,
"learning_rate": 2.320797870493454e-05,
"loss": 3.9382,
"step": 1636352
},
{
"epoch": 1.01,
"learning_rate": 2.3199592757424023e-05,
"loss": 3.9241,
"step": 1636864
},
{
"epoch": 1.01,
"learning_rate": 2.3191239567520964e-05,
"loss": 3.9281,
"step": 1637376
},
{
"epoch": 1.01,
"learning_rate": 2.3182853620010444e-05,
"loss": 3.9154,
"step": 1637888
},
{
"epoch": 1.01,
"learning_rate": 2.3174467672499924e-05,
"loss": 3.9241,
"step": 1638400
},
{
"epoch": 1.01,
"learning_rate": 2.3166081724989404e-05,
"loss": 3.9404,
"step": 1638912
},
{
"epoch": 1.01,
"learning_rate": 2.3157695777478884e-05,
"loss": 3.9351,
"step": 1639424
},
{
"epoch": 1.01,
"learning_rate": 2.3149309829968364e-05,
"loss": 3.9356,
"step": 1639936
},
{
"epoch": 1.01,
"learning_rate": 2.3140923882457844e-05,
"loss": 3.9313,
"step": 1640448
},
{
"epoch": 1.01,
"learning_rate": 2.3132554313751056e-05,
"loss": 3.947,
"step": 1640960
},
{
"epoch": 1.01,
"learning_rate": 2.3124168366240533e-05,
"loss": 3.9247,
"step": 1641472
},
{
"epoch": 1.01,
"learning_rate": 2.3115782418730013e-05,
"loss": 3.9377,
"step": 1641984
},
{
"epoch": 1.01,
"learning_rate": 2.3107396471219493e-05,
"loss": 3.9325,
"step": 1642496
},
{
"epoch": 1.01,
"learning_rate": 2.3099010523708976e-05,
"loss": 3.9148,
"step": 1643008
},
{
"epoch": 1.01,
"learning_rate": 2.3090624576198456e-05,
"loss": 3.9402,
"step": 1643520
},
{
"epoch": 1.01,
"learning_rate": 2.3082238628687936e-05,
"loss": 3.9386,
"step": 1644032
},
{
"epoch": 1.01,
"learning_rate": 2.3073852681177413e-05,
"loss": 3.935,
"step": 1644544
},
{
"epoch": 1.01,
"learning_rate": 2.3065483112470625e-05,
"loss": 3.9327,
"step": 1645056
},
{
"epoch": 1.01,
"learning_rate": 2.3057097164960105e-05,
"loss": 3.917,
"step": 1645568
},
{
"epoch": 1.01,
"learning_rate": 2.3048711217449585e-05,
"loss": 3.926,
"step": 1646080
},
{
"epoch": 1.01,
"learning_rate": 2.3040325269939065e-05,
"loss": 3.9283,
"step": 1646592
},
{
"epoch": 1.01,
"learning_rate": 2.3031972080036007e-05,
"loss": 3.9379,
"step": 1647104
},
{
"epoch": 1.01,
"learning_rate": 2.302360251132922e-05,
"loss": 3.9273,
"step": 1647616
},
{
"epoch": 1.01,
"learning_rate": 2.30152165638187e-05,
"loss": 3.9359,
"step": 1648128
},
{
"epoch": 1.02,
"learning_rate": 2.300683061630818e-05,
"loss": 3.925,
"step": 1648640
},
{
"epoch": 1.02,
"learning_rate": 2.299844466879766e-05,
"loss": 3.9294,
"step": 1649152
},
{
"epoch": 1.02,
"learning_rate": 2.299005872128714e-05,
"loss": 3.9221,
"step": 1649664
},
{
"epoch": 1.02,
"learning_rate": 2.298167277377662e-05,
"loss": 3.9264,
"step": 1650176
},
{
"epoch": 1.02,
"learning_rate": 2.29732868262661e-05,
"loss": 3.9414,
"step": 1650688
},
{
"epoch": 1.02,
"learning_rate": 2.296490087875558e-05,
"loss": 3.94,
"step": 1651200
},
{
"epoch": 1.02,
"learning_rate": 2.295651493124506e-05,
"loss": 3.9449,
"step": 1651712
},
{
"epoch": 1.02,
"learning_rate": 2.294812898373454e-05,
"loss": 3.9166,
"step": 1652224
},
{
"epoch": 1.02,
"learning_rate": 2.293974303622402e-05,
"loss": 3.9358,
"step": 1652736
},
{
"epoch": 1.02,
"learning_rate": 2.29313570887135e-05,
"loss": 3.9255,
"step": 1653248
},
{
"epoch": 1.02,
"learning_rate": 2.292298752000671e-05,
"loss": 3.9385,
"step": 1653760
},
{
"epoch": 1.02,
"learning_rate": 2.2914601572496188e-05,
"loss": 3.9294,
"step": 1654272
},
{
"epoch": 1.02,
"learning_rate": 2.29062320037894e-05,
"loss": 3.9289,
"step": 1654784
},
{
"epoch": 1.02,
"learning_rate": 2.2897846056278884e-05,
"loss": 3.9225,
"step": 1655296
},
{
"epoch": 1.02,
"learning_rate": 2.288946010876836e-05,
"loss": 3.9359,
"step": 1655808
},
{
"epoch": 1.02,
"learning_rate": 2.288107416125784e-05,
"loss": 3.9158,
"step": 1656320
},
{
"epoch": 1.02,
"learning_rate": 2.287268821374732e-05,
"loss": 3.9318,
"step": 1656832
},
{
"epoch": 1.02,
"learning_rate": 2.2864318645040533e-05,
"loss": 3.9184,
"step": 1657344
},
{
"epoch": 1.02,
"learning_rate": 2.2855932697530013e-05,
"loss": 3.9347,
"step": 1657856
},
{
"epoch": 1.02,
"learning_rate": 2.2847546750019493e-05,
"loss": 3.9278,
"step": 1658368
},
{
"epoch": 1.02,
"learning_rate": 2.2839160802508972e-05,
"loss": 3.9297,
"step": 1658880
},
{
"epoch": 1.02,
"learning_rate": 2.2830774854998452e-05,
"loss": 3.9314,
"step": 1659392
},
{
"epoch": 1.02,
"learning_rate": 2.282240528629166e-05,
"loss": 3.933,
"step": 1659904
},
{
"epoch": 1.02,
"learning_rate": 2.281401933878114e-05,
"loss": 3.9309,
"step": 1660416
},
{
"epoch": 1.02,
"learning_rate": 2.280563339127062e-05,
"loss": 3.9271,
"step": 1660928
},
{
"epoch": 1.02,
"learning_rate": 2.27972474437601e-05,
"loss": 3.9335,
"step": 1661440
},
{
"epoch": 1.02,
"learning_rate": 2.2788861496249585e-05,
"loss": 3.9482,
"step": 1661952
},
{
"epoch": 1.02,
"learning_rate": 2.2780508306346526e-05,
"loss": 3.9306,
"step": 1662464
},
{
"epoch": 1.02,
"learning_rate": 2.2772122358836006e-05,
"loss": 3.9234,
"step": 1662976
},
{
"epoch": 1.02,
"learning_rate": 2.2763736411325483e-05,
"loss": 3.9299,
"step": 1663488
},
{
"epoch": 1.02,
"learning_rate": 2.2755350463814963e-05,
"loss": 3.931,
"step": 1664000
},
{
"epoch": 1.02,
"learning_rate": 2.2746964516304446e-05,
"loss": 3.9239,
"step": 1664512
},
{
"epoch": 1.02,
"learning_rate": 2.2738578568793926e-05,
"loss": 3.9344,
"step": 1665024
},
{
"epoch": 1.02,
"learning_rate": 2.2730192621283406e-05,
"loss": 3.9202,
"step": 1665536
},
{
"epoch": 1.02,
"learning_rate": 2.2721806673772886e-05,
"loss": 3.9393,
"step": 1666048
},
{
"epoch": 1.02,
"learning_rate": 2.2713420726262363e-05,
"loss": 3.9369,
"step": 1666560
},
{
"epoch": 1.02,
"learning_rate": 2.2705051157555575e-05,
"loss": 3.9301,
"step": 1667072
},
{
"epoch": 1.02,
"learning_rate": 2.2696665210045055e-05,
"loss": 3.9239,
"step": 1667584
},
{
"epoch": 1.02,
"learning_rate": 2.2688295641338268e-05,
"loss": 3.9256,
"step": 1668096
},
{
"epoch": 1.02,
"learning_rate": 2.2679909693827748e-05,
"loss": 3.9268,
"step": 1668608
},
{
"epoch": 1.02,
"learning_rate": 2.2671523746317227e-05,
"loss": 3.9374,
"step": 1669120
},
{
"epoch": 1.02,
"learning_rate": 2.2663137798806707e-05,
"loss": 3.9349,
"step": 1669632
},
{
"epoch": 1.02,
"learning_rate": 2.2654751851296187e-05,
"loss": 3.9366,
"step": 1670144
},
{
"epoch": 1.02,
"learning_rate": 2.2646365903785667e-05,
"loss": 3.9128,
"step": 1670656
},
{
"epoch": 1.02,
"learning_rate": 2.2637979956275147e-05,
"loss": 3.9364,
"step": 1671168
},
{
"epoch": 1.02,
"learning_rate": 2.2629594008764627e-05,
"loss": 3.9295,
"step": 1671680
},
{
"epoch": 1.02,
"learning_rate": 2.2621208061254107e-05,
"loss": 3.9405,
"step": 1672192
},
{
"epoch": 1.02,
"learning_rate": 2.2612822113743587e-05,
"loss": 3.9213,
"step": 1672704
},
{
"epoch": 1.02,
"learning_rate": 2.2604452545036796e-05,
"loss": 3.9416,
"step": 1673216
},
{
"epoch": 1.02,
"learning_rate": 2.2596066597526276e-05,
"loss": 3.9315,
"step": 1673728
},
{
"epoch": 1.02,
"learning_rate": 2.2587680650015756e-05,
"loss": 3.9388,
"step": 1674240
},
{
"epoch": 1.02,
"learning_rate": 2.257929470250524e-05,
"loss": 3.9241,
"step": 1674752
},
{
"epoch": 1.02,
"learning_rate": 2.257090875499472e-05,
"loss": 3.9408,
"step": 1675264
},
{
"epoch": 1.02,
"learning_rate": 2.2562522807484196e-05,
"loss": 3.9178,
"step": 1675776
},
{
"epoch": 1.02,
"learning_rate": 2.2554136859973676e-05,
"loss": 3.9342,
"step": 1676288
},
{
"epoch": 1.02,
"learning_rate": 2.254576729126689e-05,
"loss": 3.9328,
"step": 1676800
},
{
"epoch": 1.02,
"learning_rate": 2.253738134375637e-05,
"loss": 3.9268,
"step": 1677312
},
{
"epoch": 1.02,
"learning_rate": 2.252899539624585e-05,
"loss": 3.9316,
"step": 1677824
},
{
"epoch": 1.02,
"learning_rate": 2.252060944873533e-05,
"loss": 3.9263,
"step": 1678336
},
{
"epoch": 1.02,
"learning_rate": 2.251223988002854e-05,
"loss": 3.933,
"step": 1678848
},
{
"epoch": 1.03,
"eval_loss": 4.016176223754883,
"eval_runtime": 300.8567,
"eval_samples_per_second": 1268.348,
"eval_steps_per_second": 39.637,
"step": 1679040
},
{
"epoch": 0.0,
"learning_rate": 2.2503853932518017e-05,
"loss": 3.9329,
"step": 1679360
},
{
"epoch": 0.0,
"learning_rate": 2.2495467985007497e-05,
"loss": 3.9229,
"step": 1679872
},
{
"epoch": 0.0,
"learning_rate": 2.2487082037496977e-05,
"loss": 3.9367,
"step": 1680384
},
{
"epoch": 0.0,
"learning_rate": 2.247869608998646e-05,
"loss": 3.9257,
"step": 1680896
},
{
"epoch": 0.0,
"learning_rate": 2.247031014247594e-05,
"loss": 3.9397,
"step": 1681408
},
{
"epoch": 0.0,
"learning_rate": 2.246192419496542e-05,
"loss": 3.9291,
"step": 1681920
},
{
"epoch": 0.0,
"learning_rate": 2.24535382474549e-05,
"loss": 3.9329,
"step": 1682432
},
{
"epoch": 0.0,
"learning_rate": 2.2445152299944377e-05,
"loss": 3.9315,
"step": 1682944
},
{
"epoch": 0.0,
"learning_rate": 2.2436766352433857e-05,
"loss": 3.9291,
"step": 1683456
},
{
"epoch": 0.0,
"learning_rate": 2.2428380404923337e-05,
"loss": 3.9298,
"step": 1683968
},
{
"epoch": 0.0,
"learning_rate": 2.2419994457412817e-05,
"loss": 3.9335,
"step": 1684480
},
{
"epoch": 0.0,
"learning_rate": 2.24116085099023e-05,
"loss": 3.9357,
"step": 1684992
},
{
"epoch": 0.0,
"learning_rate": 2.240323894119551e-05,
"loss": 3.9283,
"step": 1685504
},
{
"epoch": 0.0,
"learning_rate": 2.239485299368499e-05,
"loss": 3.9236,
"step": 1686016
},
{
"epoch": 0.0,
"learning_rate": 2.238646704617447e-05,
"loss": 3.929,
"step": 1686528
},
{
"epoch": 0.0,
"learning_rate": 2.237808109866395e-05,
"loss": 3.9141,
"step": 1687040
},
{
"epoch": 0.0,
"learning_rate": 2.236969515115343e-05,
"loss": 3.9283,
"step": 1687552
},
{
"epoch": 0.0,
"learning_rate": 2.236130920364291e-05,
"loss": 3.9252,
"step": 1688064
},
{
"epoch": 0.0,
"learning_rate": 2.235292325613239e-05,
"loss": 3.9256,
"step": 1688576
},
{
"epoch": 0.0,
"learning_rate": 2.234453730862187e-05,
"loss": 3.9486,
"step": 1689088
},
{
"epoch": 0.0,
"learning_rate": 2.233616773991508e-05,
"loss": 3.9382,
"step": 1689600
},
{
"epoch": 0.0,
"learning_rate": 2.2327781792404558e-05,
"loss": 3.9422,
"step": 1690112
},
{
"epoch": 0.0,
"learning_rate": 2.2319395844894038e-05,
"loss": 3.9268,
"step": 1690624
},
{
"epoch": 0.0,
"learning_rate": 2.2311009897383518e-05,
"loss": 3.932,
"step": 1691136
},
{
"epoch": 0.0,
"learning_rate": 2.2302623949873e-05,
"loss": 3.9302,
"step": 1691648
},
{
"epoch": 0.0,
"learning_rate": 2.229425438116621e-05,
"loss": 3.9336,
"step": 1692160
},
{
"epoch": 0.0,
"learning_rate": 2.228586843365569e-05,
"loss": 3.9275,
"step": 1692672
},
{
"epoch": 0.0,
"learning_rate": 2.227748248614517e-05,
"loss": 3.9294,
"step": 1693184
},
{
"epoch": 0.0,
"learning_rate": 2.226909653863465e-05,
"loss": 3.9197,
"step": 1693696
},
{
"epoch": 0.0,
"learning_rate": 2.2260726969927863e-05,
"loss": 3.9231,
"step": 1694208
},
{
"epoch": 0.01,
"learning_rate": 2.2252341022417343e-05,
"loss": 3.9263,
"step": 1694720
},
{
"epoch": 0.01,
"learning_rate": 2.2243955074906823e-05,
"loss": 3.9374,
"step": 1695232
},
{
"epoch": 0.01,
"learning_rate": 2.2235569127396303e-05,
"loss": 3.93,
"step": 1695744
},
{
"epoch": 0.01,
"learning_rate": 2.2227183179885783e-05,
"loss": 3.9382,
"step": 1696256
},
{
"epoch": 0.01,
"learning_rate": 2.2218797232375263e-05,
"loss": 3.9221,
"step": 1696768
},
{
"epoch": 0.01,
"learning_rate": 2.221042766366847e-05,
"loss": 3.9263,
"step": 1697280
},
{
"epoch": 0.01,
"learning_rate": 2.2202041716157955e-05,
"loss": 3.9295,
"step": 1697792
},
{
"epoch": 0.01,
"learning_rate": 2.2193655768647435e-05,
"loss": 3.9176,
"step": 1698304
},
{
"epoch": 0.01,
"learning_rate": 2.218526982113691e-05,
"loss": 3.9255,
"step": 1698816
},
{
"epoch": 0.01,
"learning_rate": 2.217688387362639e-05,
"loss": 3.9185,
"step": 1699328
},
{
"epoch": 0.01,
"learning_rate": 2.216849792611587e-05,
"loss": 3.9287,
"step": 1699840
},
{
"epoch": 0.01,
"learning_rate": 2.216011197860535e-05,
"loss": 3.9343,
"step": 1700352
},
{
"epoch": 0.01,
"learning_rate": 2.215172603109483e-05,
"loss": 3.9302,
"step": 1700864
},
{
"epoch": 0.01,
"learning_rate": 2.2143356462388044e-05,
"loss": 3.9266,
"step": 1701376
},
{
"epoch": 0.01,
"learning_rate": 2.2134970514877524e-05,
"loss": 3.9358,
"step": 1701888
},
{
"epoch": 0.01,
"learning_rate": 2.2126584567367004e-05,
"loss": 3.9207,
"step": 1702400
},
{
"epoch": 0.01,
"learning_rate": 2.2118198619856484e-05,
"loss": 3.9339,
"step": 1702912
},
{
"epoch": 0.01,
"learning_rate": 2.2109845429953425e-05,
"loss": 3.9244,
"step": 1703424
},
{
"epoch": 0.01,
"learning_rate": 2.210145948244291e-05,
"loss": 3.9054,
"step": 1703936
},
{
"epoch": 0.01,
"learning_rate": 2.2093073534932385e-05,
"loss": 3.9484,
"step": 1704448
},
{
"epoch": 0.01,
"learning_rate": 2.2084687587421865e-05,
"loss": 3.918,
"step": 1704960
},
{
"epoch": 0.01,
"learning_rate": 2.2076301639911345e-05,
"loss": 3.9299,
"step": 1705472
},
{
"epoch": 0.01,
"learning_rate": 2.2067915692400825e-05,
"loss": 3.9114,
"step": 1705984
},
{
"epoch": 0.01,
"learning_rate": 2.2059529744890305e-05,
"loss": 3.9194,
"step": 1706496
},
{
"epoch": 0.01,
"learning_rate": 2.2051143797379785e-05,
"loss": 3.9122,
"step": 1707008
},
{
"epoch": 0.01,
"learning_rate": 2.2042774228672998e-05,
"loss": 3.9243,
"step": 1707520
},
{
"epoch": 0.01,
"learning_rate": 2.2034388281162477e-05,
"loss": 3.9281,
"step": 1708032
},
{
"epoch": 0.01,
"learning_rate": 2.2026002333651957e-05,
"loss": 3.9285,
"step": 1708544
},
{
"epoch": 0.01,
"learning_rate": 2.2017616386141437e-05,
"loss": 3.9365,
"step": 1709056
},
{
"epoch": 0.01,
"learning_rate": 2.2009230438630917e-05,
"loss": 3.9221,
"step": 1709568
},
{
"epoch": 0.01,
"learning_rate": 2.2000860869924126e-05,
"loss": 3.9099,
"step": 1710080
},
{
"epoch": 0.01,
"learning_rate": 2.199247492241361e-05,
"loss": 3.9357,
"step": 1710592
},
{
"epoch": 0.01,
"learning_rate": 2.198408897490309e-05,
"loss": 3.9115,
"step": 1711104
},
{
"epoch": 0.01,
"learning_rate": 2.1975703027392566e-05,
"loss": 3.9074,
"step": 1711616
},
{
"epoch": 0.01,
"learning_rate": 2.1967317079882046e-05,
"loss": 3.9339,
"step": 1712128
},
{
"epoch": 0.01,
"learning_rate": 2.195894751117526e-05,
"loss": 3.9314,
"step": 1712640
},
{
"epoch": 0.01,
"learning_rate": 2.195056156366474e-05,
"loss": 3.9179,
"step": 1713152
},
{
"epoch": 0.01,
"learning_rate": 2.194217561615422e-05,
"loss": 3.9236,
"step": 1713664
},
{
"epoch": 0.01,
"learning_rate": 2.193380604744743e-05,
"loss": 3.9075,
"step": 1714176
},
{
"epoch": 0.01,
"learning_rate": 2.192542009993691e-05,
"loss": 3.9185,
"step": 1714688
},
{
"epoch": 0.01,
"learning_rate": 2.191703415242639e-05,
"loss": 3.9304,
"step": 1715200
},
{
"epoch": 0.01,
"learning_rate": 2.1908648204915868e-05,
"loss": 3.9287,
"step": 1715712
},
{
"epoch": 0.01,
"learning_rate": 2.1900262257405348e-05,
"loss": 3.9304,
"step": 1716224
},
{
"epoch": 0.01,
"learning_rate": 2.189187630989483e-05,
"loss": 3.9272,
"step": 1716736
},
{
"epoch": 0.01,
"learning_rate": 2.188349036238431e-05,
"loss": 3.9377,
"step": 1717248
},
{
"epoch": 0.01,
"learning_rate": 2.187510441487379e-05,
"loss": 3.917,
"step": 1717760
},
{
"epoch": 0.01,
"learning_rate": 2.1866734846167e-05,
"loss": 3.9342,
"step": 1718272
},
{
"epoch": 0.01,
"learning_rate": 2.185834889865648e-05,
"loss": 3.9207,
"step": 1718784
},
{
"epoch": 0.01,
"learning_rate": 2.184996295114596e-05,
"loss": 3.9148,
"step": 1719296
},
{
"epoch": 0.01,
"learning_rate": 2.184157700363544e-05,
"loss": 3.9325,
"step": 1719808
},
{
"epoch": 0.01,
"learning_rate": 2.183319105612492e-05,
"loss": 3.9336,
"step": 1720320
},
{
"epoch": 0.01,
"learning_rate": 2.18248051086144e-05,
"loss": 3.9285,
"step": 1720832
},
{
"epoch": 0.01,
"learning_rate": 2.181641916110388e-05,
"loss": 3.9286,
"step": 1721344
},
{
"epoch": 0.01,
"learning_rate": 2.180803321359336e-05,
"loss": 3.91,
"step": 1721856
},
{
"epoch": 0.01,
"learning_rate": 2.179964726608284e-05,
"loss": 3.916,
"step": 1722368
},
{
"epoch": 0.01,
"learning_rate": 2.179126131857232e-05,
"loss": 3.9249,
"step": 1722880
},
{
"epoch": 0.01,
"learning_rate": 2.17828753710618e-05,
"loss": 3.9314,
"step": 1723392
},
{
"epoch": 0.01,
"learning_rate": 2.1774505802355012e-05,
"loss": 3.9209,
"step": 1723904
},
{
"epoch": 0.01,
"learning_rate": 2.1766119854844492e-05,
"loss": 3.9286,
"step": 1724416
},
{
"epoch": 0.02,
"learning_rate": 2.1757733907333972e-05,
"loss": 3.9128,
"step": 1724928
},
{
"epoch": 0.02,
"learning_rate": 2.1749347959823452e-05,
"loss": 3.926,
"step": 1725440
},
{
"epoch": 0.02,
"learning_rate": 2.174096201231293e-05,
"loss": 3.9169,
"step": 1725952
},
{
"epoch": 0.02,
"learning_rate": 2.173257606480241e-05,
"loss": 3.92,
"step": 1726464
},
{
"epoch": 0.02,
"learning_rate": 2.1724206496095624e-05,
"loss": 3.9345,
"step": 1726976
},
{
"epoch": 0.02,
"learning_rate": 2.1715820548585104e-05,
"loss": 3.9343,
"step": 1727488
},
{
"epoch": 0.02,
"learning_rate": 2.170743460107458e-05,
"loss": 3.9373,
"step": 1728000
},
{
"epoch": 0.02,
"learning_rate": 2.169904865356406e-05,
"loss": 3.9113,
"step": 1728512
},
{
"epoch": 0.02,
"learning_rate": 2.1690679084857273e-05,
"loss": 3.9291,
"step": 1729024
},
{
"epoch": 0.02,
"learning_rate": 2.168229313734675e-05,
"loss": 3.9174,
"step": 1729536
},
{
"epoch": 0.02,
"learning_rate": 2.1673907189836233e-05,
"loss": 3.9331,
"step": 1730048
},
{
"epoch": 0.02,
"learning_rate": 2.1665537621129446e-05,
"loss": 3.9221,
"step": 1730560
},
{
"epoch": 0.02,
"learning_rate": 2.1657151673618926e-05,
"loss": 3.9254,
"step": 1731072
},
{
"epoch": 0.02,
"learning_rate": 2.1648765726108402e-05,
"loss": 3.9168,
"step": 1731584
},
{
"epoch": 0.02,
"learning_rate": 2.1640379778597882e-05,
"loss": 3.9249,
"step": 1732096
},
{
"epoch": 0.02,
"learning_rate": 2.1631993831087362e-05,
"loss": 3.9129,
"step": 1732608
},
{
"epoch": 0.02,
"learning_rate": 2.1623607883576842e-05,
"loss": 3.9244,
"step": 1733120
},
{
"epoch": 0.02,
"learning_rate": 2.1615238314870054e-05,
"loss": 3.9109,
"step": 1733632
},
{
"epoch": 0.02,
"learning_rate": 2.1606852367359534e-05,
"loss": 3.9306,
"step": 1734144
},
{
"epoch": 0.02,
"learning_rate": 2.1598466419849014e-05,
"loss": 3.9209,
"step": 1734656
},
{
"epoch": 0.02,
"learning_rate": 2.1590080472338494e-05,
"loss": 3.9214,
"step": 1735168
},
{
"epoch": 0.02,
"learning_rate": 2.1581694524827974e-05,
"loss": 3.9218,
"step": 1735680
},
{
"epoch": 0.02,
"learning_rate": 2.1573308577317454e-05,
"loss": 3.9289,
"step": 1736192
},
{
"epoch": 0.02,
"learning_rate": 2.1564922629806934e-05,
"loss": 3.9248,
"step": 1736704
},
{
"epoch": 0.02,
"learning_rate": 2.1556536682296414e-05,
"loss": 3.9184,
"step": 1737216
},
{
"epoch": 0.02,
"learning_rate": 2.1548167113589627e-05,
"loss": 3.9302,
"step": 1737728
},
{
"epoch": 0.02,
"learning_rate": 2.1539781166079107e-05,
"loss": 3.9378,
"step": 1738240
},
{
"epoch": 0.02,
"learning_rate": 2.1531411597372316e-05,
"loss": 3.9285,
"step": 1738752
},
{
"epoch": 0.02,
"learning_rate": 2.1523025649861796e-05,
"loss": 3.9182,
"step": 1739264
},
{
"epoch": 0.02,
"learning_rate": 2.151463970235128e-05,
"loss": 3.9199,
"step": 1739776
},
{
"epoch": 0.02,
"learning_rate": 2.150625375484076e-05,
"loss": 3.9286,
"step": 1740288
},
{
"epoch": 0.02,
"learning_rate": 2.1497867807330236e-05,
"loss": 3.9175,
"step": 1740800
},
{
"epoch": 0.02,
"learning_rate": 2.1489481859819715e-05,
"loss": 3.9285,
"step": 1741312
},
{
"epoch": 0.02,
"learning_rate": 2.1481095912309195e-05,
"loss": 3.913,
"step": 1741824
},
{
"epoch": 0.02,
"learning_rate": 2.1472726343602405e-05,
"loss": 3.9335,
"step": 1742336
},
{
"epoch": 0.02,
"learning_rate": 2.1464340396091888e-05,
"loss": 3.9272,
"step": 1742848
},
{
"epoch": 0.02,
"learning_rate": 2.1455954448581368e-05,
"loss": 3.926,
"step": 1743360
},
{
"epoch": 0.02,
"learning_rate": 2.1447568501070848e-05,
"loss": 3.9157,
"step": 1743872
},
{
"epoch": 0.02,
"learning_rate": 2.1439182553560328e-05,
"loss": 3.9191,
"step": 1744384
},
{
"epoch": 0.02,
"learning_rate": 2.1430812984853537e-05,
"loss": 3.9201,
"step": 1744896
},
{
"epoch": 0.02,
"learning_rate": 2.1422427037343017e-05,
"loss": 3.9336,
"step": 1745408
},
{
"epoch": 0.02,
"learning_rate": 2.1414041089832497e-05,
"loss": 3.9282,
"step": 1745920
},
{
"epoch": 0.02,
"learning_rate": 2.140565514232198e-05,
"loss": 3.9273,
"step": 1746432
},
{
"epoch": 0.02,
"learning_rate": 2.139726919481146e-05,
"loss": 3.9094,
"step": 1746944
},
{
"epoch": 0.02,
"learning_rate": 2.138888324730094e-05,
"loss": 3.9301,
"step": 1747456
},
{
"epoch": 0.02,
"learning_rate": 2.138051367859415e-05,
"loss": 3.9218,
"step": 1747968
},
{
"epoch": 0.02,
"learning_rate": 2.137212773108363e-05,
"loss": 3.9358,
"step": 1748480
},
{
"epoch": 0.02,
"learning_rate": 2.136374178357311e-05,
"loss": 3.9152,
"step": 1748992
},
{
"epoch": 0.02,
"learning_rate": 2.135535583606259e-05,
"loss": 3.9328,
"step": 1749504
},
{
"epoch": 0.02,
"learning_rate": 2.134696988855207e-05,
"loss": 3.9236,
"step": 1750016
},
{
"epoch": 0.02,
"learning_rate": 2.133858394104155e-05,
"loss": 3.9388,
"step": 1750528
},
{
"epoch": 0.02,
"learning_rate": 2.133019799353103e-05,
"loss": 3.9187,
"step": 1751040
},
{
"epoch": 0.02,
"learning_rate": 2.1321828424824238e-05,
"loss": 3.9306,
"step": 1751552
},
{
"epoch": 0.02,
"learning_rate": 2.1313442477313718e-05,
"loss": 3.9152,
"step": 1752064
},
{
"epoch": 0.02,
"learning_rate": 2.13050565298032e-05,
"loss": 3.9267,
"step": 1752576
},
{
"epoch": 0.02,
"learning_rate": 2.129667058229268e-05,
"loss": 3.926,
"step": 1753088
},
{
"epoch": 0.02,
"learning_rate": 2.128828463478216e-05,
"loss": 3.9177,
"step": 1753600
},
{
"epoch": 0.02,
"learning_rate": 2.127989868727164e-05,
"loss": 3.9295,
"step": 1754112
},
{
"epoch": 0.02,
"learning_rate": 2.127151273976112e-05,
"loss": 3.9152,
"step": 1754624
},
{
"epoch": 0.02,
"learning_rate": 2.126314317105433e-05,
"loss": 3.9305,
"step": 1755136
},
{
"epoch": 0.03,
"eval_loss": 4.0140061378479,
"eval_runtime": 295.993,
"eval_samples_per_second": 1289.189,
"eval_steps_per_second": 40.288,
"step": 1755360
},
{
"epoch": 0.0,
"learning_rate": 2.125475722354381e-05,
"loss": 3.923,
"step": 1755648
},
{
"epoch": 0.0,
"learning_rate": 2.124637127603329e-05,
"loss": 3.915,
"step": 1756160
},
{
"epoch": 0.0,
"learning_rate": 2.123798532852277e-05,
"loss": 3.9297,
"step": 1756672
},
{
"epoch": 0.0,
"learning_rate": 2.122959938101225e-05,
"loss": 3.9204,
"step": 1757184
},
{
"epoch": 0.0,
"learning_rate": 2.122121343350173e-05,
"loss": 3.9328,
"step": 1757696
},
{
"epoch": 0.0,
"learning_rate": 2.121282748599121e-05,
"loss": 3.923,
"step": 1758208
},
{
"epoch": 0.0,
"learning_rate": 2.120444153848069e-05,
"loss": 3.9262,
"step": 1758720
},
{
"epoch": 0.0,
"learning_rate": 2.119605559097017e-05,
"loss": 3.9266,
"step": 1759232
},
{
"epoch": 0.0,
"learning_rate": 2.118766964345965e-05,
"loss": 3.9205,
"step": 1759744
},
{
"epoch": 0.0,
"learning_rate": 2.117928369594913e-05,
"loss": 3.9247,
"step": 1760256
},
{
"epoch": 0.0,
"learning_rate": 2.117089774843861e-05,
"loss": 3.9282,
"step": 1760768
},
{
"epoch": 0.0,
"learning_rate": 2.116251180092809e-05,
"loss": 3.9296,
"step": 1761280
},
{
"epoch": 0.0,
"learning_rate": 2.1154142232221302e-05,
"loss": 3.927,
"step": 1761792
},
{
"epoch": 0.0,
"learning_rate": 2.114575628471078e-05,
"loss": 3.9159,
"step": 1762304
},
{
"epoch": 0.0,
"learning_rate": 2.113737033720026e-05,
"loss": 3.9194,
"step": 1762816
},
{
"epoch": 0.0,
"learning_rate": 2.1128984389689742e-05,
"loss": 3.9126,
"step": 1763328
},
{
"epoch": 0.0,
"learning_rate": 2.1120598442179222e-05,
"loss": 3.9203,
"step": 1763840
},
{
"epoch": 0.0,
"learning_rate": 2.1112212494668702e-05,
"loss": 3.9222,
"step": 1764352
},
{
"epoch": 0.0,
"learning_rate": 2.1103826547158182e-05,
"loss": 3.916,
"step": 1764864
},
{
"epoch": 0.0,
"learning_rate": 2.109544059964766e-05,
"loss": 3.9404,
"step": 1765376
},
{
"epoch": 0.0,
"learning_rate": 2.108705465213714e-05,
"loss": 3.9321,
"step": 1765888
},
{
"epoch": 0.0,
"learning_rate": 2.107866870462662e-05,
"loss": 3.9367,
"step": 1766400
},
{
"epoch": 0.0,
"learning_rate": 2.1070282757116098e-05,
"loss": 3.9222,
"step": 1766912
},
{
"epoch": 0.0,
"learning_rate": 2.106191318840931e-05,
"loss": 3.9227,
"step": 1767424
},
{
"epoch": 0.0,
"learning_rate": 2.105352724089879e-05,
"loss": 3.9294,
"step": 1767936
},
{
"epoch": 0.0,
"learning_rate": 2.104514129338827e-05,
"loss": 3.9245,
"step": 1768448
},
{
"epoch": 0.0,
"learning_rate": 2.103675534587775e-05,
"loss": 3.9211,
"step": 1768960
},
{
"epoch": 0.0,
"learning_rate": 2.102836939836723e-05,
"loss": 3.9274,
"step": 1769472
},
{
"epoch": 0.0,
"learning_rate": 2.1019999829660443e-05,
"loss": 3.9128,
"step": 1769984
},
{
"epoch": 0.0,
"learning_rate": 2.1011613882149923e-05,
"loss": 3.9167,
"step": 1770496
},
{
"epoch": 0.01,
"learning_rate": 2.1003227934639403e-05,
"loss": 3.9234,
"step": 1771008
},
{
"epoch": 0.01,
"learning_rate": 2.0994841987128883e-05,
"loss": 3.927,
"step": 1771520
},
{
"epoch": 0.01,
"learning_rate": 2.0986456039618363e-05,
"loss": 3.9288,
"step": 1772032
},
{
"epoch": 0.01,
"learning_rate": 2.097807009210784e-05,
"loss": 3.9305,
"step": 1772544
},
{
"epoch": 0.01,
"learning_rate": 2.0969700523401052e-05,
"loss": 3.917,
"step": 1773056
},
{
"epoch": 0.01,
"learning_rate": 2.0961330954694264e-05,
"loss": 3.9195,
"step": 1773568
},
{
"epoch": 0.01,
"learning_rate": 2.0952945007183744e-05,
"loss": 3.9253,
"step": 1774080
},
{
"epoch": 0.01,
"learning_rate": 2.0944559059673224e-05,
"loss": 3.9114,
"step": 1774592
},
{
"epoch": 0.01,
"learning_rate": 2.0936173112162704e-05,
"loss": 3.9225,
"step": 1775104
},
{
"epoch": 0.01,
"learning_rate": 2.0927787164652184e-05,
"loss": 3.9101,
"step": 1775616
},
{
"epoch": 0.01,
"learning_rate": 2.0919401217141664e-05,
"loss": 3.9274,
"step": 1776128
},
{
"epoch": 0.01,
"learning_rate": 2.0911015269631144e-05,
"loss": 3.9216,
"step": 1776640
},
{
"epoch": 0.01,
"learning_rate": 2.0902629322120624e-05,
"loss": 3.9255,
"step": 1777152
},
{
"epoch": 0.01,
"learning_rate": 2.0894259753413837e-05,
"loss": 3.9226,
"step": 1777664
},
{
"epoch": 0.01,
"learning_rate": 2.0885873805903313e-05,
"loss": 3.9268,
"step": 1778176
},
{
"epoch": 0.01,
"learning_rate": 2.0877487858392793e-05,
"loss": 3.9186,
"step": 1778688
},
{
"epoch": 0.01,
"learning_rate": 2.0869101910882273e-05,
"loss": 3.9257,
"step": 1779200
},
{
"epoch": 0.01,
"learning_rate": 2.0860715963371753e-05,
"loss": 3.919,
"step": 1779712
},
{
"epoch": 0.01,
"learning_rate": 2.0852330015861236e-05,
"loss": 3.8992,
"step": 1780224
},
{
"epoch": 0.01,
"learning_rate": 2.0843944068350716e-05,
"loss": 3.9384,
"step": 1780736
},
{
"epoch": 0.01,
"learning_rate": 2.0835558120840196e-05,
"loss": 3.911,
"step": 1781248
},
{
"epoch": 0.01,
"learning_rate": 2.0827188552133405e-05,
"loss": 3.9237,
"step": 1781760
},
{
"epoch": 0.01,
"learning_rate": 2.0818818983426618e-05,
"loss": 3.9128,
"step": 1782272
},
{
"epoch": 0.01,
"learning_rate": 2.0810433035916098e-05,
"loss": 3.9118,
"step": 1782784
},
{
"epoch": 0.01,
"learning_rate": 2.0802047088405578e-05,
"loss": 3.906,
"step": 1783296
},
{
"epoch": 0.01,
"learning_rate": 2.0793661140895058e-05,
"loss": 3.9153,
"step": 1783808
},
{
"epoch": 0.01,
"learning_rate": 2.0785291572188267e-05,
"loss": 3.9252,
"step": 1784320
},
{
"epoch": 0.01,
"learning_rate": 2.0776905624677747e-05,
"loss": 3.9173,
"step": 1784832
},
{
"epoch": 0.01,
"learning_rate": 2.0768519677167227e-05,
"loss": 3.9321,
"step": 1785344
},
{
"epoch": 0.01,
"learning_rate": 2.0760133729656707e-05,
"loss": 3.9211,
"step": 1785856
},
{
"epoch": 0.01,
"learning_rate": 2.075174778214619e-05,
"loss": 3.9016,
"step": 1786368
},
{
"epoch": 0.01,
"learning_rate": 2.074336183463567e-05,
"loss": 3.9251,
"step": 1786880
},
{
"epoch": 0.01,
"learning_rate": 2.0734975887125147e-05,
"loss": 3.909,
"step": 1787392
},
{
"epoch": 0.01,
"learning_rate": 2.0726589939614627e-05,
"loss": 3.8983,
"step": 1787904
},
{
"epoch": 0.01,
"learning_rate": 2.071822037090784e-05,
"loss": 3.9323,
"step": 1788416
},
{
"epoch": 0.01,
"learning_rate": 2.070983442339732e-05,
"loss": 3.9243,
"step": 1788928
},
{
"epoch": 0.01,
"learning_rate": 2.070146485469053e-05,
"loss": 3.9103,
"step": 1789440
},
{
"epoch": 0.01,
"learning_rate": 2.069307890718001e-05,
"loss": 3.9189,
"step": 1789952
},
{
"epoch": 0.01,
"learning_rate": 2.068469295966949e-05,
"loss": 3.9028,
"step": 1790464
},
{
"epoch": 0.01,
"learning_rate": 2.0676307012158968e-05,
"loss": 3.9118,
"step": 1790976
},
{
"epoch": 0.01,
"learning_rate": 2.0667921064648448e-05,
"loss": 3.9209,
"step": 1791488
},
{
"epoch": 0.01,
"learning_rate": 2.0659535117137928e-05,
"loss": 3.9216,
"step": 1792000
},
{
"epoch": 0.01,
"learning_rate": 2.065114916962741e-05,
"loss": 3.9258,
"step": 1792512
},
{
"epoch": 0.01,
"learning_rate": 2.064276322211689e-05,
"loss": 3.9173,
"step": 1793024
},
{
"epoch": 0.01,
"learning_rate": 2.063437727460637e-05,
"loss": 3.933,
"step": 1793536
},
{
"epoch": 0.01,
"learning_rate": 2.062599132709585e-05,
"loss": 3.909,
"step": 1794048
},
{
"epoch": 0.01,
"learning_rate": 2.0617605379585328e-05,
"loss": 3.9306,
"step": 1794560
},
{
"epoch": 0.01,
"learning_rate": 2.0609219432074808e-05,
"loss": 3.9154,
"step": 1795072
},
{
"epoch": 0.01,
"learning_rate": 2.060084986336802e-05,
"loss": 3.9121,
"step": 1795584
},
{
"epoch": 0.01,
"learning_rate": 2.05924639158575e-05,
"loss": 3.9238,
"step": 1796096
},
{
"epoch": 0.01,
"learning_rate": 2.058407796834698e-05,
"loss": 3.9275,
"step": 1796608
},
{
"epoch": 0.01,
"learning_rate": 2.057569202083646e-05,
"loss": 3.922,
"step": 1797120
},
{
"epoch": 0.01,
"learning_rate": 2.0567322452129672e-05,
"loss": 3.9254,
"step": 1797632
},
{
"epoch": 0.01,
"learning_rate": 2.055893650461915e-05,
"loss": 3.901,
"step": 1798144
},
{
"epoch": 0.01,
"learning_rate": 2.055055055710863e-05,
"loss": 3.9088,
"step": 1798656
},
{
"epoch": 0.01,
"learning_rate": 2.0542164609598112e-05,
"loss": 3.9191,
"step": 1799168
},
{
"epoch": 0.01,
"learning_rate": 2.0533778662087592e-05,
"loss": 3.9267,
"step": 1799680
},
{
"epoch": 0.01,
"learning_rate": 2.0525392714577072e-05,
"loss": 3.9153,
"step": 1800192
},
{
"epoch": 0.01,
"learning_rate": 2.051702314587028e-05,
"loss": 3.922,
"step": 1800704
},
{
"epoch": 0.02,
"learning_rate": 2.050863719835976e-05,
"loss": 3.9088,
"step": 1801216
},
{
"epoch": 0.02,
"learning_rate": 2.050025125084924e-05,
"loss": 3.9206,
"step": 1801728
},
{
"epoch": 0.02,
"learning_rate": 2.049186530333872e-05,
"loss": 3.9137,
"step": 1802240
},
{
"epoch": 0.02,
"learning_rate": 2.0483495734631934e-05,
"loss": 3.9131,
"step": 1802752
},
{
"epoch": 0.02,
"learning_rate": 2.0475109787121414e-05,
"loss": 3.928,
"step": 1803264
},
{
"epoch": 0.02,
"learning_rate": 2.0466723839610894e-05,
"loss": 3.9253,
"step": 1803776
},
{
"epoch": 0.02,
"learning_rate": 2.0458337892100373e-05,
"loss": 3.932,
"step": 1804288
},
{
"epoch": 0.02,
"learning_rate": 2.0449951944589853e-05,
"loss": 3.9094,
"step": 1804800
},
{
"epoch": 0.02,
"learning_rate": 2.0441598754686795e-05,
"loss": 3.9203,
"step": 1805312
},
{
"epoch": 0.02,
"learning_rate": 2.0433212807176275e-05,
"loss": 3.9131,
"step": 1805824
},
{
"epoch": 0.02,
"learning_rate": 2.0424826859665755e-05,
"loss": 3.9229,
"step": 1806336
},
{
"epoch": 0.02,
"learning_rate": 2.0416440912155235e-05,
"loss": 3.9181,
"step": 1806848
},
{
"epoch": 0.02,
"learning_rate": 2.0408054964644715e-05,
"loss": 3.9206,
"step": 1807360
},
{
"epoch": 0.02,
"learning_rate": 2.0399669017134195e-05,
"loss": 3.9102,
"step": 1807872
},
{
"epoch": 0.02,
"learning_rate": 2.0391283069623675e-05,
"loss": 3.9168,
"step": 1808384
},
{
"epoch": 0.02,
"learning_rate": 2.0382897122113155e-05,
"loss": 3.9134,
"step": 1808896
},
{
"epoch": 0.02,
"learning_rate": 2.0374527553406367e-05,
"loss": 3.9165,
"step": 1809408
},
{
"epoch": 0.02,
"learning_rate": 2.0366157984699576e-05,
"loss": 3.9043,
"step": 1809920
},
{
"epoch": 0.02,
"learning_rate": 2.0357772037189056e-05,
"loss": 3.9245,
"step": 1810432
},
{
"epoch": 0.02,
"learning_rate": 2.0349386089678536e-05,
"loss": 3.9166,
"step": 1810944
},
{
"epoch": 0.02,
"learning_rate": 2.034100014216802e-05,
"loss": 3.9181,
"step": 1811456
},
{
"epoch": 0.02,
"learning_rate": 2.03326141946575e-05,
"loss": 3.9164,
"step": 1811968
},
{
"epoch": 0.02,
"learning_rate": 2.0324228247146976e-05,
"loss": 3.9216,
"step": 1812480
},
{
"epoch": 0.02,
"learning_rate": 2.0315842299636456e-05,
"loss": 3.9185,
"step": 1812992
},
{
"epoch": 0.02,
"learning_rate": 2.0307456352125936e-05,
"loss": 3.9134,
"step": 1813504
},
{
"epoch": 0.02,
"learning_rate": 2.0299070404615416e-05,
"loss": 3.925,
"step": 1814016
},
{
"epoch": 0.02,
"learning_rate": 2.0290684457104896e-05,
"loss": 3.931,
"step": 1814528
},
{
"epoch": 0.02,
"learning_rate": 2.028233126720184e-05,
"loss": 3.918,
"step": 1815040
},
{
"epoch": 0.02,
"learning_rate": 2.027394531969132e-05,
"loss": 3.9198,
"step": 1815552
},
{
"epoch": 0.02,
"learning_rate": 2.02655593721808e-05,
"loss": 3.9126,
"step": 1816064
},
{
"epoch": 0.02,
"learning_rate": 2.0257173424670277e-05,
"loss": 3.9177,
"step": 1816576
},
{
"epoch": 0.02,
"learning_rate": 2.0248787477159757e-05,
"loss": 3.9189,
"step": 1817088
},
{
"epoch": 0.02,
"learning_rate": 2.0240401529649237e-05,
"loss": 3.922,
"step": 1817600
},
{
"epoch": 0.02,
"learning_rate": 2.023201558213872e-05,
"loss": 3.9053,
"step": 1818112
},
{
"epoch": 0.02,
"learning_rate": 2.02236296346282e-05,
"loss": 3.9267,
"step": 1818624
},
{
"epoch": 0.02,
"learning_rate": 2.021524368711768e-05,
"loss": 3.9201,
"step": 1819136
},
{
"epoch": 0.02,
"learning_rate": 2.020687411841089e-05,
"loss": 3.9199,
"step": 1819648
},
{
"epoch": 0.02,
"learning_rate": 2.01985045497041e-05,
"loss": 3.9114,
"step": 1820160
},
{
"epoch": 0.02,
"learning_rate": 2.0190118602193582e-05,
"loss": 3.9128,
"step": 1820672
},
{
"epoch": 0.02,
"learning_rate": 2.0181732654683062e-05,
"loss": 3.9115,
"step": 1821184
},
{
"epoch": 0.02,
"learning_rate": 2.0173346707172542e-05,
"loss": 3.9258,
"step": 1821696
},
{
"epoch": 0.02,
"learning_rate": 2.0164960759662022e-05,
"loss": 3.9226,
"step": 1822208
},
{
"epoch": 0.02,
"learning_rate": 2.0156574812151502e-05,
"loss": 3.9257,
"step": 1822720
},
{
"epoch": 0.02,
"learning_rate": 2.0148188864640982e-05,
"loss": 3.9034,
"step": 1823232
},
{
"epoch": 0.02,
"learning_rate": 2.013980291713046e-05,
"loss": 3.9232,
"step": 1823744
},
{
"epoch": 0.02,
"learning_rate": 2.013141696961994e-05,
"loss": 3.9163,
"step": 1824256
},
{
"epoch": 0.02,
"learning_rate": 2.0123031022109422e-05,
"loss": 3.9301,
"step": 1824768
},
{
"epoch": 0.02,
"learning_rate": 2.0114645074598902e-05,
"loss": 3.9121,
"step": 1825280
},
{
"epoch": 0.02,
"learning_rate": 2.010627550589211e-05,
"loss": 3.9223,
"step": 1825792
},
{
"epoch": 0.02,
"learning_rate": 2.009788955838159e-05,
"loss": 3.9168,
"step": 1826304
},
{
"epoch": 0.02,
"learning_rate": 2.008950361087107e-05,
"loss": 3.9335,
"step": 1826816
},
{
"epoch": 0.02,
"learning_rate": 2.008111766336055e-05,
"loss": 3.9137,
"step": 1827328
},
{
"epoch": 0.02,
"learning_rate": 2.007273171585003e-05,
"loss": 3.9229,
"step": 1827840
},
{
"epoch": 0.02,
"learning_rate": 2.0064345768339514e-05,
"loss": 3.9142,
"step": 1828352
},
{
"epoch": 0.02,
"learning_rate": 2.005595982082899e-05,
"loss": 3.9234,
"step": 1828864
},
{
"epoch": 0.02,
"learning_rate": 2.004757387331847e-05,
"loss": 3.9152,
"step": 1829376
},
{
"epoch": 0.02,
"learning_rate": 2.003918792580795e-05,
"loss": 3.9135,
"step": 1829888
},
{
"epoch": 0.02,
"learning_rate": 2.0030834735904892e-05,
"loss": 3.9223,
"step": 1830400
},
{
"epoch": 0.02,
"learning_rate": 2.0022448788394375e-05,
"loss": 3.905,
"step": 1830912
},
{
"epoch": 0.02,
"learning_rate": 2.0014062840883855e-05,
"loss": 3.9288,
"step": 1831424
},
{
"epoch": 0.03,
"eval_loss": 4.011756420135498,
"eval_runtime": 290.4067,
"eval_samples_per_second": 1313.988,
"eval_steps_per_second": 41.063,
"step": 1831680
},
{
"epoch": 1.0,
"learning_rate": 2.0005676893373335e-05,
"loss": 3.9145,
"step": 1831936
},
{
"epoch": 1.0,
"learning_rate": 1.9997290945862812e-05,
"loss": 3.9107,
"step": 1832448
},
{
"epoch": 1.0,
"learning_rate": 1.9988904998352292e-05,
"loss": 3.9205,
"step": 1832960
},
{
"epoch": 1.0,
"learning_rate": 1.9980535429645504e-05,
"loss": 3.9158,
"step": 1833472
},
{
"epoch": 1.0,
"learning_rate": 1.9972149482134984e-05,
"loss": 3.9276,
"step": 1833984
},
{
"epoch": 1.0,
"learning_rate": 1.9963763534624464e-05,
"loss": 3.9181,
"step": 1834496
},
{
"epoch": 1.0,
"learning_rate": 1.9955377587113944e-05,
"loss": 3.9209,
"step": 1835008
},
{
"epoch": 1.0,
"learning_rate": 1.9947008018407157e-05,
"loss": 3.9211,
"step": 1835520
},
{
"epoch": 1.0,
"learning_rate": 1.9938622070896633e-05,
"loss": 3.914,
"step": 1836032
},
{
"epoch": 1.0,
"learning_rate": 1.9930236123386113e-05,
"loss": 3.9218,
"step": 1836544
},
{
"epoch": 1.0,
"learning_rate": 1.9921850175875593e-05,
"loss": 3.9216,
"step": 1837056
},
{
"epoch": 1.0,
"learning_rate": 1.9913464228365077e-05,
"loss": 3.9247,
"step": 1837568
},
{
"epoch": 1.0,
"learning_rate": 1.9905094659658286e-05,
"loss": 3.9243,
"step": 1838080
},
{
"epoch": 1.0,
"learning_rate": 1.9896708712147766e-05,
"loss": 3.9049,
"step": 1838592
},
{
"epoch": 1.0,
"learning_rate": 1.9888322764637246e-05,
"loss": 3.9151,
"step": 1839104
},
{
"epoch": 1.0,
"learning_rate": 1.9879936817126726e-05,
"loss": 3.9036,
"step": 1839616
},
{
"epoch": 1.0,
"learning_rate": 1.9871567248419938e-05,
"loss": 3.9167,
"step": 1840128
},
{
"epoch": 1.0,
"learning_rate": 1.9863181300909418e-05,
"loss": 3.9168,
"step": 1840640
},
{
"epoch": 1.0,
"learning_rate": 1.9854795353398898e-05,
"loss": 3.9099,
"step": 1841152
},
{
"epoch": 1.0,
"learning_rate": 1.9846409405888378e-05,
"loss": 3.9331,
"step": 1841664
},
{
"epoch": 1.0,
"learning_rate": 1.9838023458377858e-05,
"loss": 3.9292,
"step": 1842176
},
{
"epoch": 1.0,
"learning_rate": 1.9829637510867338e-05,
"loss": 3.9282,
"step": 1842688
},
{
"epoch": 1.0,
"learning_rate": 1.9821251563356814e-05,
"loss": 3.9208,
"step": 1843200
},
{
"epoch": 1.0,
"learning_rate": 1.981288199465003e-05,
"loss": 3.9182,
"step": 1843712
},
{
"epoch": 1.0,
"learning_rate": 1.980449604713951e-05,
"loss": 3.9255,
"step": 1844224
},
{
"epoch": 1.0,
"learning_rate": 1.979611009962899e-05,
"loss": 3.9143,
"step": 1844736
},
{
"epoch": 1.0,
"learning_rate": 1.9787724152118467e-05,
"loss": 3.9148,
"step": 1845248
},
{
"epoch": 1.0,
"learning_rate": 1.9779338204607947e-05,
"loss": 3.9219,
"step": 1845760
},
{
"epoch": 1.0,
"learning_rate": 1.9770952257097427e-05,
"loss": 3.9079,
"step": 1846272
},
{
"epoch": 1.0,
"learning_rate": 1.9762566309586907e-05,
"loss": 3.9095,
"step": 1846784
},
{
"epoch": 1.01,
"learning_rate": 1.975418036207639e-05,
"loss": 3.9177,
"step": 1847296
},
{
"epoch": 1.01,
"learning_rate": 1.974582717217333e-05,
"loss": 3.9216,
"step": 1847808
},
{
"epoch": 1.01,
"learning_rate": 1.973744122466281e-05,
"loss": 3.9158,
"step": 1848320
},
{
"epoch": 1.01,
"learning_rate": 1.9729055277152288e-05,
"loss": 3.9306,
"step": 1848832
},
{
"epoch": 1.01,
"learning_rate": 1.9720669329641768e-05,
"loss": 3.9103,
"step": 1849344
},
{
"epoch": 1.01,
"learning_rate": 1.9712299760934984e-05,
"loss": 3.9144,
"step": 1849856
},
{
"epoch": 1.01,
"learning_rate": 1.9703913813424464e-05,
"loss": 3.9181,
"step": 1850368
},
{
"epoch": 1.01,
"learning_rate": 1.969552786591394e-05,
"loss": 3.9027,
"step": 1850880
},
{
"epoch": 1.01,
"learning_rate": 1.968714191840342e-05,
"loss": 3.9178,
"step": 1851392
},
{
"epoch": 1.01,
"learning_rate": 1.96787559708929e-05,
"loss": 3.9062,
"step": 1851904
},
{
"epoch": 1.01,
"learning_rate": 1.967037002338238e-05,
"loss": 3.9172,
"step": 1852416
},
{
"epoch": 1.01,
"learning_rate": 1.966198407587186e-05,
"loss": 3.9177,
"step": 1852928
},
{
"epoch": 1.01,
"learning_rate": 1.965359812836134e-05,
"loss": 3.9188,
"step": 1853440
},
{
"epoch": 1.01,
"learning_rate": 1.9645228559654553e-05,
"loss": 3.9198,
"step": 1853952
},
{
"epoch": 1.01,
"learning_rate": 1.9636842612144033e-05,
"loss": 3.9201,
"step": 1854464
},
{
"epoch": 1.01,
"learning_rate": 1.9628456664633513e-05,
"loss": 3.9135,
"step": 1854976
},
{
"epoch": 1.01,
"learning_rate": 1.9620070717122993e-05,
"loss": 3.9161,
"step": 1855488
},
{
"epoch": 1.01,
"learning_rate": 1.961168476961247e-05,
"loss": 3.9178,
"step": 1856000
},
{
"epoch": 1.01,
"learning_rate": 1.9603298822101952e-05,
"loss": 3.8936,
"step": 1856512
},
{
"epoch": 1.01,
"learning_rate": 1.9594912874591432e-05,
"loss": 3.9284,
"step": 1857024
},
{
"epoch": 1.01,
"learning_rate": 1.9586526927080912e-05,
"loss": 3.9061,
"step": 1857536
},
{
"epoch": 1.01,
"learning_rate": 1.957815735837412e-05,
"loss": 3.9201,
"step": 1858048
},
{
"epoch": 1.01,
"learning_rate": 1.95697714108636e-05,
"loss": 3.904,
"step": 1858560
},
{
"epoch": 1.01,
"learning_rate": 1.956138546335308e-05,
"loss": 3.9051,
"step": 1859072
},
{
"epoch": 1.01,
"learning_rate": 1.955299951584256e-05,
"loss": 3.9042,
"step": 1859584
},
{
"epoch": 1.01,
"learning_rate": 1.9544629947135774e-05,
"loss": 3.9051,
"step": 1860096
},
{
"epoch": 1.01,
"learning_rate": 1.9536243999625254e-05,
"loss": 3.9232,
"step": 1860608
},
{
"epoch": 1.01,
"learning_rate": 1.9527874430918466e-05,
"loss": 3.9068,
"step": 1861120
},
{
"epoch": 1.01,
"learning_rate": 1.9519488483407943e-05,
"loss": 3.9289,
"step": 1861632
},
{
"epoch": 1.01,
"learning_rate": 1.9511102535897423e-05,
"loss": 3.9178,
"step": 1862144
},
{
"epoch": 1.01,
"learning_rate": 1.9502716588386906e-05,
"loss": 3.895,
"step": 1862656
},
{
"epoch": 1.01,
"learning_rate": 1.9494330640876386e-05,
"loss": 3.9169,
"step": 1863168
},
{
"epoch": 1.01,
"learning_rate": 1.9485944693365866e-05,
"loss": 3.9091,
"step": 1863680
},
{
"epoch": 1.01,
"learning_rate": 1.9477558745855346e-05,
"loss": 3.8939,
"step": 1864192
},
{
"epoch": 1.01,
"learning_rate": 1.9469189177148555e-05,
"loss": 3.9228,
"step": 1864704
},
{
"epoch": 1.01,
"learning_rate": 1.9460803229638035e-05,
"loss": 3.9164,
"step": 1865216
},
{
"epoch": 1.01,
"learning_rate": 1.9452417282127515e-05,
"loss": 3.9058,
"step": 1865728
},
{
"epoch": 1.01,
"learning_rate": 1.9444047713420727e-05,
"loss": 3.9134,
"step": 1866240
},
{
"epoch": 1.01,
"learning_rate": 1.9435661765910207e-05,
"loss": 3.8941,
"step": 1866752
},
{
"epoch": 1.01,
"learning_rate": 1.9427275818399687e-05,
"loss": 3.9086,
"step": 1867264
},
{
"epoch": 1.01,
"learning_rate": 1.9418889870889167e-05,
"loss": 3.9151,
"step": 1867776
},
{
"epoch": 1.01,
"learning_rate": 1.9410503923378647e-05,
"loss": 3.9136,
"step": 1868288
},
{
"epoch": 1.01,
"learning_rate": 1.9402117975868124e-05,
"loss": 3.923,
"step": 1868800
},
{
"epoch": 1.01,
"learning_rate": 1.9393732028357607e-05,
"loss": 3.91,
"step": 1869312
},
{
"epoch": 1.01,
"learning_rate": 1.9385346080847087e-05,
"loss": 3.9266,
"step": 1869824
},
{
"epoch": 1.01,
"learning_rate": 1.9376960133336567e-05,
"loss": 3.9092,
"step": 1870336
},
{
"epoch": 1.01,
"learning_rate": 1.9368574185826047e-05,
"loss": 3.9225,
"step": 1870848
},
{
"epoch": 1.01,
"learning_rate": 1.9360188238315527e-05,
"loss": 3.906,
"step": 1871360
},
{
"epoch": 1.01,
"learning_rate": 1.9351802290805007e-05,
"loss": 3.907,
"step": 1871872
},
{
"epoch": 1.01,
"learning_rate": 1.9343416343294484e-05,
"loss": 3.9176,
"step": 1872384
},
{
"epoch": 1.01,
"learning_rate": 1.93350467745877e-05,
"loss": 3.9225,
"step": 1872896
},
{
"epoch": 1.01,
"learning_rate": 1.932667720588091e-05,
"loss": 3.9142,
"step": 1873408
},
{
"epoch": 1.01,
"learning_rate": 1.931829125837039e-05,
"loss": 3.9213,
"step": 1873920
},
{
"epoch": 1.01,
"learning_rate": 1.930990531085987e-05,
"loss": 3.8942,
"step": 1874432
},
{
"epoch": 1.01,
"learning_rate": 1.930151936334935e-05,
"loss": 3.9017,
"step": 1874944
},
{
"epoch": 1.01,
"learning_rate": 1.929313341583883e-05,
"loss": 3.9163,
"step": 1875456
},
{
"epoch": 1.01,
"learning_rate": 1.928476384713204e-05,
"loss": 3.9152,
"step": 1875968
},
{
"epoch": 1.01,
"learning_rate": 1.927637789962152e-05,
"loss": 3.9089,
"step": 1876480
},
{
"epoch": 1.01,
"learning_rate": 1.9267991952111e-05,
"loss": 3.9178,
"step": 1876992
},
{
"epoch": 1.02,
"learning_rate": 1.925960600460048e-05,
"loss": 3.9039,
"step": 1877504
},
{
"epoch": 1.02,
"learning_rate": 1.9251220057089957e-05,
"loss": 3.9142,
"step": 1878016
},
{
"epoch": 1.02,
"learning_rate": 1.9242834109579437e-05,
"loss": 3.906,
"step": 1878528
},
{
"epoch": 1.02,
"learning_rate": 1.9234448162068917e-05,
"loss": 3.9086,
"step": 1879040
},
{
"epoch": 1.02,
"learning_rate": 1.92260622145584e-05,
"loss": 3.9216,
"step": 1879552
},
{
"epoch": 1.02,
"learning_rate": 1.921767626704788e-05,
"loss": 3.9221,
"step": 1880064
},
{
"epoch": 1.02,
"learning_rate": 1.920929031953736e-05,
"loss": 3.9257,
"step": 1880576
},
{
"epoch": 1.02,
"learning_rate": 1.920092075083057e-05,
"loss": 3.904,
"step": 1881088
},
{
"epoch": 1.02,
"learning_rate": 1.919253480332005e-05,
"loss": 3.9134,
"step": 1881600
},
{
"epoch": 1.02,
"learning_rate": 1.918414885580953e-05,
"loss": 3.9097,
"step": 1882112
},
{
"epoch": 1.02,
"learning_rate": 1.9175779287102742e-05,
"loss": 3.9158,
"step": 1882624
},
{
"epoch": 1.02,
"learning_rate": 1.9167393339592222e-05,
"loss": 3.913,
"step": 1883136
},
{
"epoch": 1.02,
"learning_rate": 1.9159007392081702e-05,
"loss": 3.9123,
"step": 1883648
},
{
"epoch": 1.02,
"learning_rate": 1.9150621444571182e-05,
"loss": 3.9096,
"step": 1884160
},
{
"epoch": 1.02,
"learning_rate": 1.9142235497060662e-05,
"loss": 3.9083,
"step": 1884672
},
{
"epoch": 1.02,
"learning_rate": 1.913386592835387e-05,
"loss": 3.9068,
"step": 1885184
},
{
"epoch": 1.02,
"learning_rate": 1.9125479980843354e-05,
"loss": 3.9089,
"step": 1885696
},
{
"epoch": 1.02,
"learning_rate": 1.9117094033332834e-05,
"loss": 3.9002,
"step": 1886208
},
{
"epoch": 1.02,
"learning_rate": 1.910870808582231e-05,
"loss": 3.9171,
"step": 1886720
},
{
"epoch": 1.02,
"learning_rate": 1.910032213831179e-05,
"loss": 3.912,
"step": 1887232
},
{
"epoch": 1.02,
"learning_rate": 1.909193619080127e-05,
"loss": 3.9065,
"step": 1887744
},
{
"epoch": 1.02,
"learning_rate": 1.908355024329075e-05,
"loss": 3.9144,
"step": 1888256
},
{
"epoch": 1.02,
"learning_rate": 1.907516429578023e-05,
"loss": 3.9116,
"step": 1888768
},
{
"epoch": 1.02,
"learning_rate": 1.9066794727073443e-05,
"loss": 3.9146,
"step": 1889280
},
{
"epoch": 1.02,
"learning_rate": 1.9058408779562923e-05,
"loss": 3.9077,
"step": 1889792
},
{
"epoch": 1.02,
"learning_rate": 1.9050022832052403e-05,
"loss": 3.921,
"step": 1890304
},
{
"epoch": 1.02,
"learning_rate": 1.9041636884541883e-05,
"loss": 3.9247,
"step": 1890816
},
{
"epoch": 1.02,
"learning_rate": 1.9033267315835092e-05,
"loss": 3.9162,
"step": 1891328
},
{
"epoch": 1.02,
"learning_rate": 1.9024897747128308e-05,
"loss": 3.9098,
"step": 1891840
},
{
"epoch": 1.02,
"learning_rate": 1.9016511799617784e-05,
"loss": 3.9078,
"step": 1892352
},
{
"epoch": 1.02,
"learning_rate": 1.9008125852107264e-05,
"loss": 3.9098,
"step": 1892864
},
{
"epoch": 1.02,
"learning_rate": 1.8999739904596744e-05,
"loss": 3.9133,
"step": 1893376
},
{
"epoch": 1.02,
"learning_rate": 1.8991353957086224e-05,
"loss": 3.9157,
"step": 1893888
},
{
"epoch": 1.02,
"learning_rate": 1.8982968009575704e-05,
"loss": 3.8977,
"step": 1894400
},
{
"epoch": 1.02,
"learning_rate": 1.8974598440868917e-05,
"loss": 3.9227,
"step": 1894912
},
{
"epoch": 1.02,
"learning_rate": 1.8966212493358397e-05,
"loss": 3.9148,
"step": 1895424
},
{
"epoch": 1.02,
"learning_rate": 1.8957826545847877e-05,
"loss": 3.9176,
"step": 1895936
},
{
"epoch": 1.02,
"learning_rate": 1.8949440598337357e-05,
"loss": 3.9067,
"step": 1896448
},
{
"epoch": 1.02,
"learning_rate": 1.8941054650826837e-05,
"loss": 3.9071,
"step": 1896960
},
{
"epoch": 1.02,
"learning_rate": 1.8932701460923778e-05,
"loss": 3.9071,
"step": 1897472
},
{
"epoch": 1.02,
"learning_rate": 1.8924315513413258e-05,
"loss": 3.9179,
"step": 1897984
},
{
"epoch": 1.02,
"learning_rate": 1.8915929565902738e-05,
"loss": 3.9169,
"step": 1898496
},
{
"epoch": 1.02,
"learning_rate": 1.8907543618392218e-05,
"loss": 3.9198,
"step": 1899008
},
{
"epoch": 1.02,
"learning_rate": 1.8899157670881698e-05,
"loss": 3.8962,
"step": 1899520
},
{
"epoch": 1.02,
"learning_rate": 1.8890771723371178e-05,
"loss": 3.9194,
"step": 1900032
},
{
"epoch": 1.02,
"learning_rate": 1.8882385775860658e-05,
"loss": 3.9116,
"step": 1900544
},
{
"epoch": 1.02,
"learning_rate": 1.8873999828350138e-05,
"loss": 3.9256,
"step": 1901056
},
{
"epoch": 1.02,
"learning_rate": 1.886563025964335e-05,
"loss": 3.9072,
"step": 1901568
},
{
"epoch": 1.02,
"learning_rate": 1.885724431213283e-05,
"loss": 3.9106,
"step": 1902080
},
{
"epoch": 1.02,
"learning_rate": 1.884885836462231e-05,
"loss": 3.9136,
"step": 1902592
},
{
"epoch": 1.02,
"learning_rate": 1.884047241711179e-05,
"loss": 3.9258,
"step": 1903104
},
{
"epoch": 1.02,
"learning_rate": 1.8832086469601267e-05,
"loss": 3.9061,
"step": 1903616
},
{
"epoch": 1.02,
"learning_rate": 1.8823700522090747e-05,
"loss": 3.919,
"step": 1904128
},
{
"epoch": 1.02,
"learning_rate": 1.8815330953383963e-05,
"loss": 3.909,
"step": 1904640
},
{
"epoch": 1.02,
"learning_rate": 1.880694500587344e-05,
"loss": 3.9204,
"step": 1905152
},
{
"epoch": 1.02,
"learning_rate": 1.879855905836292e-05,
"loss": 3.9073,
"step": 1905664
},
{
"epoch": 1.02,
"learning_rate": 1.87901731108524e-05,
"loss": 3.9081,
"step": 1906176
},
{
"epoch": 1.02,
"learning_rate": 1.878178716334188e-05,
"loss": 3.9153,
"step": 1906688
},
{
"epoch": 1.02,
"learning_rate": 1.8773433973438824e-05,
"loss": 3.9067,
"step": 1907200
},
{
"epoch": 1.02,
"learning_rate": 1.8765048025928304e-05,
"loss": 3.921,
"step": 1907712
},
{
"epoch": 1.03,
"eval_loss": 4.009287357330322,
"eval_runtime": 281.3709,
"eval_samples_per_second": 1356.185,
"eval_steps_per_second": 42.382,
"step": 1908000
},
{
"epoch": 0.0,
"learning_rate": 1.8756662078417784e-05,
"loss": 3.9079,
"step": 1908224
},
{
"epoch": 0.0,
"learning_rate": 1.874827613090726e-05,
"loss": 3.9044,
"step": 1908736
},
{
"epoch": 0.0,
"learning_rate": 1.873989018339674e-05,
"loss": 3.9139,
"step": 1909248
},
{
"epoch": 0.0,
"learning_rate": 1.873150423588622e-05,
"loss": 3.913,
"step": 1909760
},
{
"epoch": 0.0,
"learning_rate": 1.87231182883757e-05,
"loss": 3.9232,
"step": 1910272
},
{
"epoch": 0.0,
"learning_rate": 1.871473234086518e-05,
"loss": 3.912,
"step": 1910784
},
{
"epoch": 0.0,
"learning_rate": 1.8706346393354664e-05,
"loss": 3.9104,
"step": 1911296
},
{
"epoch": 0.0,
"learning_rate": 1.8697960445844144e-05,
"loss": 3.9186,
"step": 1911808
},
{
"epoch": 0.0,
"learning_rate": 1.868957449833362e-05,
"loss": 3.9086,
"step": 1912320
},
{
"epoch": 0.0,
"learning_rate": 1.86811885508231e-05,
"loss": 3.9134,
"step": 1912832
},
{
"epoch": 0.0,
"learning_rate": 1.867280260331258e-05,
"loss": 3.9151,
"step": 1913344
},
{
"epoch": 0.0,
"learning_rate": 1.866441665580206e-05,
"loss": 3.918,
"step": 1913856
},
{
"epoch": 0.0,
"learning_rate": 1.8656047087095273e-05,
"loss": 3.9182,
"step": 1914368
},
{
"epoch": 0.0,
"learning_rate": 1.8647661139584753e-05,
"loss": 3.9019,
"step": 1914880
},
{
"epoch": 0.0,
"learning_rate": 1.8639275192074232e-05,
"loss": 3.9083,
"step": 1915392
},
{
"epoch": 0.0,
"learning_rate": 1.8630889244563712e-05,
"loss": 3.8965,
"step": 1915904
},
{
"epoch": 0.0,
"learning_rate": 1.8622503297053192e-05,
"loss": 3.9128,
"step": 1916416
},
{
"epoch": 0.0,
"learning_rate": 1.8614117349542672e-05,
"loss": 3.9177,
"step": 1916928
},
{
"epoch": 0.0,
"learning_rate": 1.860573140203215e-05,
"loss": 3.902,
"step": 1917440
},
{
"epoch": 0.0,
"learning_rate": 1.8597345454521632e-05,
"loss": 3.9265,
"step": 1917952
},
{
"epoch": 0.0,
"learning_rate": 1.8588975885814845e-05,
"loss": 3.9221,
"step": 1918464
},
{
"epoch": 0.0,
"learning_rate": 1.8580606317108054e-05,
"loss": 3.9199,
"step": 1918976
},
{
"epoch": 0.0,
"learning_rate": 1.8572220369597534e-05,
"loss": 3.9157,
"step": 1919488
},
{
"epoch": 0.0,
"learning_rate": 1.8563834422087014e-05,
"loss": 3.913,
"step": 1920000
},
{
"epoch": 0.0,
"learning_rate": 1.8555448474576494e-05,
"loss": 3.9162,
"step": 1920512
},
{
"epoch": 0.0,
"learning_rate": 1.8547062527065974e-05,
"loss": 3.9147,
"step": 1921024
},
{
"epoch": 0.0,
"learning_rate": 1.8538676579555454e-05,
"loss": 3.903,
"step": 1921536
},
{
"epoch": 0.0,
"learning_rate": 1.8530290632044934e-05,
"loss": 3.9184,
"step": 1922048
},
{
"epoch": 0.0,
"learning_rate": 1.8521904684534414e-05,
"loss": 3.9007,
"step": 1922560
},
{
"epoch": 0.0,
"learning_rate": 1.8513518737023893e-05,
"loss": 3.907,
"step": 1923072
},
{
"epoch": 0.01,
"learning_rate": 1.8505132789513373e-05,
"loss": 3.9154,
"step": 1923584
},
{
"epoch": 0.01,
"learning_rate": 1.8496746842002853e-05,
"loss": 3.9155,
"step": 1924096
},
{
"epoch": 0.01,
"learning_rate": 1.8488360894492333e-05,
"loss": 3.9113,
"step": 1924608
},
{
"epoch": 0.01,
"learning_rate": 1.8479974946981813e-05,
"loss": 3.9219,
"step": 1925120
},
{
"epoch": 0.01,
"learning_rate": 1.8471588999471293e-05,
"loss": 3.9095,
"step": 1925632
},
{
"epoch": 0.01,
"learning_rate": 1.8463235809568235e-05,
"loss": 3.9053,
"step": 1926144
},
{
"epoch": 0.01,
"learning_rate": 1.8454849862057715e-05,
"loss": 3.9165,
"step": 1926656
},
{
"epoch": 0.01,
"learning_rate": 1.8446463914547195e-05,
"loss": 3.8947,
"step": 1927168
},
{
"epoch": 0.01,
"learning_rate": 1.8438077967036678e-05,
"loss": 3.9117,
"step": 1927680
},
{
"epoch": 0.01,
"learning_rate": 1.8429692019526158e-05,
"loss": 3.9085,
"step": 1928192
},
{
"epoch": 0.01,
"learning_rate": 1.8421306072015635e-05,
"loss": 3.9084,
"step": 1928704
},
{
"epoch": 0.01,
"learning_rate": 1.8412920124505115e-05,
"loss": 3.9104,
"step": 1929216
},
{
"epoch": 0.01,
"learning_rate": 1.8404534176994595e-05,
"loss": 3.9172,
"step": 1929728
},
{
"epoch": 0.01,
"learning_rate": 1.8396164608287804e-05,
"loss": 3.9126,
"step": 1930240
},
{
"epoch": 0.01,
"learning_rate": 1.8387778660777287e-05,
"loss": 3.9133,
"step": 1930752
},
{
"epoch": 0.01,
"learning_rate": 1.8379392713266767e-05,
"loss": 3.9085,
"step": 1931264
},
{
"epoch": 0.01,
"learning_rate": 1.8371006765756247e-05,
"loss": 3.9113,
"step": 1931776
},
{
"epoch": 0.01,
"learning_rate": 1.8362637197049456e-05,
"loss": 3.9112,
"step": 1932288
},
{
"epoch": 0.01,
"learning_rate": 1.8354251249538936e-05,
"loss": 3.8908,
"step": 1932800
},
{
"epoch": 0.01,
"learning_rate": 1.8345865302028416e-05,
"loss": 3.9211,
"step": 1933312
},
{
"epoch": 0.01,
"learning_rate": 1.8337479354517896e-05,
"loss": 3.903,
"step": 1933824
},
{
"epoch": 0.01,
"learning_rate": 1.832909340700738e-05,
"loss": 3.9102,
"step": 1934336
},
{
"epoch": 0.01,
"learning_rate": 1.832072383830059e-05,
"loss": 3.9003,
"step": 1934848
},
{
"epoch": 0.01,
"learning_rate": 1.8312337890790068e-05,
"loss": 3.8965,
"step": 1935360
},
{
"epoch": 0.01,
"learning_rate": 1.8303951943279548e-05,
"loss": 3.9011,
"step": 1935872
},
{
"epoch": 0.01,
"learning_rate": 1.8295565995769028e-05,
"loss": 3.9005,
"step": 1936384
},
{
"epoch": 0.01,
"learning_rate": 1.8287212805865973e-05,
"loss": 3.9186,
"step": 1936896
},
{
"epoch": 0.01,
"learning_rate": 1.8278826858355453e-05,
"loss": 3.9039,
"step": 1937408
},
{
"epoch": 0.01,
"learning_rate": 1.827044091084493e-05,
"loss": 3.9226,
"step": 1937920
},
{
"epoch": 0.01,
"learning_rate": 1.826205496333441e-05,
"loss": 3.9142,
"step": 1938432
},
{
"epoch": 0.01,
"learning_rate": 1.825366901582389e-05,
"loss": 3.8887,
"step": 1938944
},
{
"epoch": 0.01,
"learning_rate": 1.824528306831337e-05,
"loss": 3.9093,
"step": 1939456
},
{
"epoch": 0.01,
"learning_rate": 1.823689712080285e-05,
"loss": 3.9001,
"step": 1939968
},
{
"epoch": 0.01,
"learning_rate": 1.8228511173292333e-05,
"loss": 3.8952,
"step": 1940480
},
{
"epoch": 0.01,
"learning_rate": 1.8220125225781813e-05,
"loss": 3.9135,
"step": 1940992
},
{
"epoch": 0.01,
"learning_rate": 1.8211755657075022e-05,
"loss": 3.9109,
"step": 1941504
},
{
"epoch": 0.01,
"learning_rate": 1.820338608836823e-05,
"loss": 3.9015,
"step": 1942016
},
{
"epoch": 0.01,
"learning_rate": 1.819500014085771e-05,
"loss": 3.9105,
"step": 1942528
},
{
"epoch": 0.01,
"learning_rate": 1.8186614193347194e-05,
"loss": 3.8915,
"step": 1943040
},
{
"epoch": 0.01,
"learning_rate": 1.8178228245836674e-05,
"loss": 3.8973,
"step": 1943552
},
{
"epoch": 0.01,
"learning_rate": 1.8169842298326154e-05,
"loss": 3.9105,
"step": 1944064
},
{
"epoch": 0.01,
"learning_rate": 1.8161456350815634e-05,
"loss": 3.9113,
"step": 1944576
},
{
"epoch": 0.01,
"learning_rate": 1.8153086782108843e-05,
"loss": 3.9161,
"step": 1945088
},
{
"epoch": 0.01,
"learning_rate": 1.8144700834598323e-05,
"loss": 3.9043,
"step": 1945600
},
{
"epoch": 0.01,
"learning_rate": 1.8136314887087803e-05,
"loss": 3.9239,
"step": 1946112
},
{
"epoch": 0.01,
"learning_rate": 1.8127928939577283e-05,
"loss": 3.9022,
"step": 1946624
},
{
"epoch": 0.01,
"learning_rate": 1.8119542992066763e-05,
"loss": 3.9203,
"step": 1947136
},
{
"epoch": 0.01,
"learning_rate": 1.8111157044556243e-05,
"loss": 3.8984,
"step": 1947648
},
{
"epoch": 0.01,
"learning_rate": 1.8102771097045723e-05,
"loss": 3.9018,
"step": 1948160
},
{
"epoch": 0.01,
"learning_rate": 1.8094385149535203e-05,
"loss": 3.9098,
"step": 1948672
},
{
"epoch": 0.01,
"learning_rate": 1.8085999202024683e-05,
"loss": 3.9179,
"step": 1949184
},
{
"epoch": 0.01,
"learning_rate": 1.8077629633317895e-05,
"loss": 3.9089,
"step": 1949696
},
{
"epoch": 0.01,
"learning_rate": 1.8069243685807375e-05,
"loss": 3.9178,
"step": 1950208
},
{
"epoch": 0.01,
"learning_rate": 1.8060857738296855e-05,
"loss": 3.8904,
"step": 1950720
},
{
"epoch": 0.01,
"learning_rate": 1.8052471790786335e-05,
"loss": 3.8942,
"step": 1951232
},
{
"epoch": 0.01,
"learning_rate": 1.8044085843275815e-05,
"loss": 3.9135,
"step": 1951744
},
{
"epoch": 0.01,
"learning_rate": 1.8035716274569024e-05,
"loss": 3.909,
"step": 1952256
},
{
"epoch": 0.01,
"learning_rate": 1.8027330327058504e-05,
"loss": 3.9022,
"step": 1952768
},
{
"epoch": 0.01,
"learning_rate": 1.8018960758351717e-05,
"loss": 3.9125,
"step": 1953280
},
{
"epoch": 0.02,
"learning_rate": 1.8010574810841197e-05,
"loss": 3.9046,
"step": 1953792
},
{
"epoch": 0.02,
"learning_rate": 1.8002188863330677e-05,
"loss": 3.9031,
"step": 1954304
},
{
"epoch": 0.02,
"learning_rate": 1.7993802915820157e-05,
"loss": 3.9013,
"step": 1954816
},
{
"epoch": 0.02,
"learning_rate": 1.7985416968309637e-05,
"loss": 3.904,
"step": 1955328
},
{
"epoch": 0.02,
"learning_rate": 1.7977031020799117e-05,
"loss": 3.9152,
"step": 1955840
},
{
"epoch": 0.02,
"learning_rate": 1.7968645073288597e-05,
"loss": 3.9192,
"step": 1956352
},
{
"epoch": 0.02,
"learning_rate": 1.7960259125778076e-05,
"loss": 3.9197,
"step": 1956864
},
{
"epoch": 0.02,
"learning_rate": 1.7951905935875018e-05,
"loss": 3.8987,
"step": 1957376
},
{
"epoch": 0.02,
"learning_rate": 1.7943519988364498e-05,
"loss": 3.9067,
"step": 1957888
},
{
"epoch": 0.02,
"learning_rate": 1.7935134040853978e-05,
"loss": 3.9034,
"step": 1958400
},
{
"epoch": 0.02,
"learning_rate": 1.7926748093343458e-05,
"loss": 3.9106,
"step": 1958912
},
{
"epoch": 0.02,
"learning_rate": 1.7918362145832938e-05,
"loss": 3.9101,
"step": 1959424
},
{
"epoch": 0.02,
"learning_rate": 1.7909976198322418e-05,
"loss": 3.9042,
"step": 1959936
},
{
"epoch": 0.02,
"learning_rate": 1.7901590250811898e-05,
"loss": 3.9058,
"step": 1960448
},
{
"epoch": 0.02,
"learning_rate": 1.7893204303301378e-05,
"loss": 3.8983,
"step": 1960960
},
{
"epoch": 0.02,
"learning_rate": 1.7884818355790858e-05,
"loss": 3.9053,
"step": 1961472
},
{
"epoch": 0.02,
"learning_rate": 1.7876465165887803e-05,
"loss": 3.9028,
"step": 1961984
},
{
"epoch": 0.02,
"learning_rate": 1.7868095597181012e-05,
"loss": 3.8982,
"step": 1962496
},
{
"epoch": 0.02,
"learning_rate": 1.7859709649670492e-05,
"loss": 3.9103,
"step": 1963008
},
{
"epoch": 0.02,
"learning_rate": 1.7851323702159972e-05,
"loss": 3.908,
"step": 1963520
},
{
"epoch": 0.02,
"learning_rate": 1.7842937754649452e-05,
"loss": 3.903,
"step": 1964032
},
{
"epoch": 0.02,
"learning_rate": 1.7834551807138932e-05,
"loss": 3.9045,
"step": 1964544
},
{
"epoch": 0.02,
"learning_rate": 1.782616585962841e-05,
"loss": 3.9062,
"step": 1965056
},
{
"epoch": 0.02,
"learning_rate": 1.781777991211789e-05,
"loss": 3.9107,
"step": 1965568
},
{
"epoch": 0.02,
"learning_rate": 1.780939396460737e-05,
"loss": 3.901,
"step": 1966080
},
{
"epoch": 0.02,
"learning_rate": 1.780100801709685e-05,
"loss": 3.9161,
"step": 1966592
},
{
"epoch": 0.02,
"learning_rate": 1.779262206958633e-05,
"loss": 3.9181,
"step": 1967104
},
{
"epoch": 0.02,
"learning_rate": 1.778423612207581e-05,
"loss": 3.9109,
"step": 1967616
},
{
"epoch": 0.02,
"learning_rate": 1.777586655336902e-05,
"loss": 3.9056,
"step": 1968128
},
{
"epoch": 0.02,
"learning_rate": 1.7767480605858504e-05,
"loss": 3.904,
"step": 1968640
},
{
"epoch": 0.02,
"learning_rate": 1.7759094658347984e-05,
"loss": 3.9016,
"step": 1969152
},
{
"epoch": 0.02,
"learning_rate": 1.7750708710837464e-05,
"loss": 3.9137,
"step": 1969664
},
{
"epoch": 0.02,
"learning_rate": 1.7742339142130673e-05,
"loss": 3.9047,
"step": 1970176
},
{
"epoch": 0.02,
"learning_rate": 1.7733953194620153e-05,
"loss": 3.8964,
"step": 1970688
},
{
"epoch": 0.02,
"learning_rate": 1.7725567247109633e-05,
"loss": 3.9178,
"step": 1971200
},
{
"epoch": 0.02,
"learning_rate": 1.7717181299599113e-05,
"loss": 3.9095,
"step": 1971712
},
{
"epoch": 0.02,
"learning_rate": 1.7708795352088593e-05,
"loss": 3.91,
"step": 1972224
},
{
"epoch": 0.02,
"learning_rate": 1.7700409404578073e-05,
"loss": 3.9017,
"step": 1972736
},
{
"epoch": 0.02,
"learning_rate": 1.7692039835871285e-05,
"loss": 3.9008,
"step": 1973248
},
{
"epoch": 0.02,
"learning_rate": 1.7683653888360765e-05,
"loss": 3.9035,
"step": 1973760
},
{
"epoch": 0.02,
"learning_rate": 1.767526794085024e-05,
"loss": 3.9141,
"step": 1974272
},
{
"epoch": 0.02,
"learning_rate": 1.7666881993339725e-05,
"loss": 3.9114,
"step": 1974784
},
{
"epoch": 0.02,
"learning_rate": 1.7658512424632937e-05,
"loss": 3.9155,
"step": 1975296
},
{
"epoch": 0.02,
"learning_rate": 1.7650126477122417e-05,
"loss": 3.8907,
"step": 1975808
},
{
"epoch": 0.02,
"learning_rate": 1.7641740529611894e-05,
"loss": 3.9168,
"step": 1976320
},
{
"epoch": 0.02,
"learning_rate": 1.7633354582101374e-05,
"loss": 3.905,
"step": 1976832
},
{
"epoch": 0.02,
"learning_rate": 1.7624985013394586e-05,
"loss": 3.9178,
"step": 1977344
},
{
"epoch": 0.02,
"learning_rate": 1.7616599065884066e-05,
"loss": 3.9046,
"step": 1977856
},
{
"epoch": 0.02,
"learning_rate": 1.7608213118373546e-05,
"loss": 3.9017,
"step": 1978368
},
{
"epoch": 0.02,
"learning_rate": 1.7599827170863026e-05,
"loss": 3.9096,
"step": 1978880
},
{
"epoch": 0.02,
"learning_rate": 1.7591441223352506e-05,
"loss": 3.9225,
"step": 1979392
},
{
"epoch": 0.02,
"learning_rate": 1.7583055275841986e-05,
"loss": 3.9017,
"step": 1979904
},
{
"epoch": 0.02,
"learning_rate": 1.7574669328331466e-05,
"loss": 3.9128,
"step": 1980416
},
{
"epoch": 0.02,
"learning_rate": 1.7566283380820946e-05,
"loss": 3.9028,
"step": 1980928
},
{
"epoch": 0.02,
"learning_rate": 1.755791381211416e-05,
"loss": 3.9138,
"step": 1981440
},
{
"epoch": 0.02,
"learning_rate": 1.7549544243407368e-05,
"loss": 3.902,
"step": 1981952
},
{
"epoch": 0.02,
"learning_rate": 1.7541158295896848e-05,
"loss": 3.9027,
"step": 1982464
},
{
"epoch": 0.02,
"learning_rate": 1.7532772348386328e-05,
"loss": 3.9099,
"step": 1982976
},
{
"epoch": 0.02,
"learning_rate": 1.7524386400875808e-05,
"loss": 3.9024,
"step": 1983488
},
{
"epoch": 0.02,
"learning_rate": 1.7516000453365288e-05,
"loss": 3.9189,
"step": 1984000
},
{
"epoch": 0.03,
"eval_loss": 4.007462501525879,
"eval_runtime": 307.0635,
"eval_samples_per_second": 1242.71,
"eval_steps_per_second": 38.836,
"step": 1984320
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 8.153519415427434e+17,
"trial_name": null,
"trial_params": null
}