abhinavp's picture
Training in progress, epoch 0, checkpoint
c20aa49 verified
{
"best_metric": 3.949995279312134,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-c-command/transformer/2/checkpoints/checkpoint-228960",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 228960,
"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": 10.9766,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8228,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1813,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9673,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8024,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.6932,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5963,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5331,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4421,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4089,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3501,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3099,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2682,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2006,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1813,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1334,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1106,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0804,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0426,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0182,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0045,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9756,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9436,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9246,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9147,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8895,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8614,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8516,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8314,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8165,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8007,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.788,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7767,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7564,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.754,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7528,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7291,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 4.6918,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 4.6965,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 4.6778,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 4.6813,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6677,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6605,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6397,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6491,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6317,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6303,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6183,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5972,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5981,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.6012,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.5797,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5709,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5617,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5593,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5431,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5645,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5313,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 4.5424,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 4.533,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 4.5063,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5142,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 4.5051,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 4.4905,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 4.4835,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.4997,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.4766,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 4.4716,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 4.4592,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 4.4729,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4778,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 4.4629,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 4.4559,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 4.4615,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.457,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 4.4481,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 4.4302,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 4.4384,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 4.4257,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 4.4239,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 4.4129,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 4.4181,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4245,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.4153,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.3883,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 4.3973,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.3992,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.3946,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3894,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3856,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3814,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3686,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3744,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 4.374,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 4.3642,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3746,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3525,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3542,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3508,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3512,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3547,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.3397,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.3358,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3329,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.3359,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.3184,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3116,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3205,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.326,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.3166,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.3152,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.3042,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.3147,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.2992,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.305,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3068,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.3051,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.2954,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.2938,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.293,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.294,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.2822,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.2869,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.2839,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2846,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.2676,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2668,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.2698,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2739,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2631,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.276,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.2686,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.2537,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.2592,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.2701,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.2598,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.2564,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.2464,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884314871364151e-05,
"loss": 4.2535,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883476276613099e-05,
"loss": 4.2591,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882637681862047e-05,
"loss": 4.2454,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881799087110995e-05,
"loss": 4.2362,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.2412,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.2361,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.233,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.2422,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.231,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.2325,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.2296,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.2236,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.1937055587768555,
"eval_runtime": 307.9359,
"eval_samples_per_second": 1239.19,
"eval_steps_per_second": 38.726,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.2123,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873416415361222e-05,
"loss": 4.218,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.2272,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.2165,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.217,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.2124,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.2076,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.1962,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.2199,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.2037,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.2127,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.2119,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.1933,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.1923,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.1894,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.1826,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.1879,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.181,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.1765,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.1997,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.1823,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.1752,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.1722,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.1875,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.164,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.1628,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.1656,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.1648,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.1593,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.1592,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.1623,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.1653,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.1509,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.8465912106097964e-05,
"loss": 4.1609,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.1647,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.1592,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844077064237013e-05,
"loss": 4.134,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.1402,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842399874734909e-05,
"loss": 4.1391,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841561279983857e-05,
"loss": 4.1446,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840722685232805e-05,
"loss": 4.1387,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839884090481753e-05,
"loss": 4.1453,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.1326,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838210176740395e-05,
"loss": 4.1426,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.141,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.1408,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.1368,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.1181,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.1325,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.1364,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.1296,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.1251,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.1146,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.1236,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.1071,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.1355,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.1132,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.1258,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.1239,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824797574364683e-05,
"loss": 4.097,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823958979613631e-05,
"loss": 4.1139,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823120384862579e-05,
"loss": 4.1078,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222834279919e-05,
"loss": 4.0975,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.0948,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.1122,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.1014,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.0956,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818092092117013e-05,
"loss": 4.0869,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817253497365961e-05,
"loss": 4.1059,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816414902614909e-05,
"loss": 4.1085,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815576307863857e-05,
"loss": 4.1043,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.099,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.1096,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.1062,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122235667400224e-05,
"loss": 4.1037,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.0869,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.0996,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097094203672393e-05,
"loss": 4.092,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.8088708256161873e-05,
"loss": 4.0908,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.088,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.0895,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.102,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805518084492352e-05,
"loss": 4.0946,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046794897413e-05,
"loss": 4.0706,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803840894990248e-05,
"loss": 4.0776,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803002300239196e-05,
"loss": 4.0856,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802163705488144e-05,
"loss": 4.082,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.0813,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800488153866413e-05,
"loss": 4.0783,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799649559115361e-05,
"loss": 4.078,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798810964364309e-05,
"loss": 4.0673,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.79797400749363e-05,
"loss": 4.0764,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.0744,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796296817991526e-05,
"loss": 4.0746,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795458223240474e-05,
"loss": 4.0814,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946212663697956e-05,
"loss": 4.0723,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937826716187436e-05,
"loss": 4.0653,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929440768676916e-05,
"loss": 4.0692,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921054821166396e-05,
"loss": 4.0707,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912685252459605e-05,
"loss": 4.0736,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904299304949085e-05,
"loss": 4.0641,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895913357438565e-05,
"loss": 4.0608,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887527409928045e-05,
"loss": 4.0588,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879141462417525e-05,
"loss": 4.0672,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870771893710734e-05,
"loss": 4.0524,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786240232500395e-05,
"loss": 4.0419,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785401637749343e-05,
"loss": 4.0595,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784563042998291e-05,
"loss": 4.0604,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783724448247239e-05,
"loss": 4.0533,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782885853496187e-05,
"loss": 4.0552,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782047258745135e-05,
"loss": 4.0496,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781208663994083e-05,
"loss": 4.0573,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780370069243031e-05,
"loss": 4.0451,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779533112372352e-05,
"loss": 4.0526,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786945176213e-05,
"loss": 4.0599,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777855922870248e-05,
"loss": 4.0596,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777018965999569e-05,
"loss": 4.047,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776180371248517e-05,
"loss": 4.0467,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775341776497465e-05,
"loss": 4.0513,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7745031817464134e-05,
"loss": 4.0555,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736645869953614e-05,
"loss": 4.0369,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728259922443094e-05,
"loss": 4.0498,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719873974932574e-05,
"loss": 4.0416,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711488027422054e-05,
"loss": 4.053,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770311845871526e-05,
"loss": 4.0325,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769473251120474e-05,
"loss": 4.0343,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768634656369422e-05,
"loss": 4.038,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76779606161837e-05,
"loss": 4.0426,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766959104747691e-05,
"loss": 4.033,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766120509996639e-05,
"loss": 4.0532,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765281915245587e-05,
"loss": 4.0414,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764443320494535e-05,
"loss": 4.0314,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763606363623857e-05,
"loss": 4.032,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762767768872805e-05,
"loss": 4.0489,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761929174121753e-05,
"loss": 4.039,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761090579370701e-05,
"loss": 4.0369,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760253622500022e-05,
"loss": 4.0295,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941502774897e-05,
"loss": 4.0375,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758576432997918e-05,
"loss": 4.0403,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757737838246866e-05,
"loss": 4.0317,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569008813761866e-05,
"loss": 4.0237,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560622866251346e-05,
"loss": 4.0284,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552236918740826e-05,
"loss": 4.025,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543867350034035e-05,
"loss": 4.0225,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753548140252352e-05,
"loss": 4.036,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527095455013e-05,
"loss": 4.0231,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751870950750248e-05,
"loss": 4.026,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751032355999196e-05,
"loss": 4.0245,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501937612481435e-05,
"loss": 4.0183,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.024468898773193,
"eval_runtime": 306.7507,
"eval_samples_per_second": 1243.978,
"eval_steps_per_second": 38.875,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493551664970914e-05,
"loss": 4.0077,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485165717460394e-05,
"loss": 4.0176,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476779769949874e-05,
"loss": 4.0298,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468393822439354e-05,
"loss": 4.0185,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460007874928834e-05,
"loss": 4.0228,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451621927418314e-05,
"loss": 4.0139,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443235979907794e-05,
"loss": 4.0162,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434850032397274e-05,
"loss": 4.0019,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742648046369049e-05,
"loss": 4.0235,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741809451617997e-05,
"loss": 4.0205,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740970856866945e-05,
"loss": 4.0164,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740132262115893e-05,
"loss": 4.0214,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739293667364841e-05,
"loss": 4.0041,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738455072613789e-05,
"loss": 4.0037,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737616477862737e-05,
"loss": 4.0119,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736777883111685e-05,
"loss": 3.9931,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735940926241006e-05,
"loss": 4.0028,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735102331489954e-05,
"loss": 3.9981,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734263736738902e-05,
"loss": 3.9964,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.73342514198785e-05,
"loss": 4.0218,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732588185117171e-05,
"loss": 4.0012,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731749590366119e-05,
"loss": 4.0035,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7309109956150674e-05,
"loss": 3.9932,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300724008640154e-05,
"loss": 4.0088,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292354439933364e-05,
"loss": 3.985,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7283968492422844e-05,
"loss": 3.9911,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275582544912323e-05,
"loss": 3.9901,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.72671965974018e-05,
"loss": 3.9978,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725882702869501e-05,
"loss": 3.9882,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725044108118449e-05,
"loss": 3.9879,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724205513367397e-05,
"loss": 3.9939,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233669186163446e-05,
"loss": 3.9988,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722529961745666e-05,
"loss": 3.9788,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721691366994614e-05,
"loss": 3.995,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720852772243563e-05,
"loss": 3.994,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.72001417749251e-05,
"loss": 3.9902,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719177220621832e-05,
"loss": 3.9705,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71833862587078e-05,
"loss": 3.9802,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717500031119727e-05,
"loss": 3.9701,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716661436368675e-05,
"loss": 3.986,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158244794979966e-05,
"loss": 3.9789,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149858847469446e-05,
"loss": 3.9857,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714147289995892e-05,
"loss": 3.9747,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71330869524484e-05,
"loss": 3.9801,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124717383741615e-05,
"loss": 3.9845,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116331436231095e-05,
"loss": 3.986,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107945488720575e-05,
"loss": 3.9825,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099559541210055e-05,
"loss": 3.9604,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709118997250327e-05,
"loss": 3.9744,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082804024992744e-05,
"loss": 3.9857,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074418077482224e-05,
"loss": 3.9709,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7066032129971704e-05,
"loss": 3.9713,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705766256126492e-05,
"loss": 3.9667,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704929299255813e-05,
"loss": 3.972,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704090704504761e-05,
"loss": 3.9578,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703252109753709e-05,
"loss": 3.9788,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702413515002657e-05,
"loss": 3.9676,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701574920251605e-05,
"loss": 3.9726,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700736325500553e-05,
"loss": 3.9803,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699897730749501e-05,
"loss": 3.9486,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699059135998449e-05,
"loss": 3.9669,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.69822217912777e-05,
"loss": 3.9598,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697383584376718e-05,
"loss": 3.9557,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696544989625666e-05,
"loss": 3.9501,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695706394874614e-05,
"loss": 3.9673,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694869438003935e-05,
"loss": 3.9605,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694030843252883e-05,
"loss": 3.9512,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931922485018307e-05,
"loss": 3.9442,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.6923536537507787e-05,
"loss": 3.9634,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915166968801e-05,
"loss": 3.9703,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690678102129048e-05,
"loss": 3.9622,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689839507377996e-05,
"loss": 3.961,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.689000912626944e-05,
"loss": 3.9707,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688163955756265e-05,
"loss": 3.9658,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687325361005213e-05,
"loss": 3.9683,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686486766254161e-05,
"loss": 3.9458,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685648171503109e-05,
"loss": 3.9625,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848128525128036e-05,
"loss": 3.9592,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683974257761751e-05,
"loss": 3.9511,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831356630106996e-05,
"loss": 3.9559,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822970682596476e-05,
"loss": 3.9554,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814584735085956e-05,
"loss": 3.9671,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806198787575436e-05,
"loss": 3.9575,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.6797812840064916e-05,
"loss": 3.936,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789426892554396e-05,
"loss": 3.9413,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.6781057323847605e-05,
"loss": 3.9516,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772671376337085e-05,
"loss": 3.9537,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764285428826565e-05,
"loss": 3.9511,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755899481316045e-05,
"loss": 3.9441,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747529912609254e-05,
"loss": 3.9491,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739143965098734e-05,
"loss": 3.9368,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730758017588214e-05,
"loss": 3.9495,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722372070077694e-05,
"loss": 3.9423,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713986122567174e-05,
"loss": 3.9482,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670561655386039e-05,
"loss": 3.9551,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669723060634987e-05,
"loss": 3.9476,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668884465883935e-05,
"loss": 3.9387,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668045871132883e-05,
"loss": 3.9433,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667207276381831e-05,
"loss": 3.9438,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666368681630779e-05,
"loss": 3.9473,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665530086879727e-05,
"loss": 3.9409,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664691492128675e-05,
"loss": 3.9372,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663854535257996e-05,
"loss": 3.9333,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663015940506944e-05,
"loss": 3.9437,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662177345755892e-05,
"loss": 3.9314,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.66133875100484e-05,
"loss": 3.9211,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660503432014534e-05,
"loss": 3.9346,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659664837263482e-05,
"loss": 3.938,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.65882624251243e-05,
"loss": 3.9287,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657989285641751e-05,
"loss": 3.9393,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657150690890699e-05,
"loss": 3.9246,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656312096139647e-05,
"loss": 3.9396,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655473501388595e-05,
"loss": 3.9262,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654634906637543e-05,
"loss": 3.93,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653797949766864e-05,
"loss": 3.9444,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652959355015812e-05,
"loss": 3.9405,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.65212076026476e-05,
"loss": 3.9304,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651282165513708e-05,
"loss": 3.9324,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650443570762657e-05,
"loss": 3.9294,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649604976011605e-05,
"loss": 3.9356,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648768019140926e-05,
"loss": 3.9218,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647929424389874e-05,
"loss": 3.9353,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647090829638822e-05,
"loss": 3.9257,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.64625223488777e-05,
"loss": 3.9366,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454152780170906e-05,
"loss": 3.9146,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445766832660386e-05,
"loss": 3.9255,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437380885149866e-05,
"loss": 3.9209,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428994937639346e-05,
"loss": 3.926,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642060899012882e-05,
"loss": 3.9195,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412223042618306e-05,
"loss": 3.9427,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640385347391152e-05,
"loss": 3.9287,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395467526401e-05,
"loss": 3.922,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387081578890475e-05,
"loss": 3.9128,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378695631379955e-05,
"loss": 3.9355,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637032606267317e-05,
"loss": 3.9287,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636194011516265e-05,
"loss": 3.9275,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353554167652124e-05,
"loss": 3.9209,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345168220141604e-05,
"loss": 3.9251,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633679865143482e-05,
"loss": 3.9301,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632841270392429e-05,
"loss": 3.9212,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632002675641377e-05,
"loss": 3.9171,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631164080890326e-05,
"loss": 3.921,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303271240196475e-05,
"loss": 3.9181,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629488529268595e-05,
"loss": 3.9116,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628649934517543e-05,
"loss": 3.9242,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627811339766491e-05,
"loss": 3.9235,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626974382895812e-05,
"loss": 3.9168,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.62613578814476e-05,
"loss": 3.9151,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625297193393708e-05,
"loss": 3.9082,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.949995279312134,
"eval_runtime": 303.7283,
"eval_samples_per_second": 1256.357,
"eval_steps_per_second": 39.262,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.6001973826759066e+17,
"trial_name": null,
"trial_params": null
}