abhinavp's picture
Training in progress, epoch 0, checkpoint
9e69012 verified
raw
history blame
56 kB
{
"best_metric": 3.9528229236602783,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/transformer/3/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": 10.9867,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8188,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1835,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9731,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8049,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.6919,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5929,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5265,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4448,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3876,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3349,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.2996,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.252,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 5.2013,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 5.169,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 5.1205,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1131,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0688,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0388,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0171,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0046,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.9732,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.949,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9289,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9131,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.8832,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8692,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8472,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8306,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8169,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.801,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7901,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7837,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.766,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7526,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7394,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.732,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.708,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7085,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6763,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.676,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6717,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6711,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6394,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6469,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6351,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.624,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.631,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5917,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.596,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.6007,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.5934,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5741,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5553,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 4.5644,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 4.5456,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 4.5687,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 4.5196,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5405,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5284,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.519,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5238,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5042,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4887,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4921,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5044,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4773,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4797,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4621,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4626,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4778,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4757,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4492,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4624,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.469,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4506,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4324,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4365,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4335,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4242,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4206,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.421,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4231,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.415,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.3941,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.3988,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.3989,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.3941,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.3936,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.3833,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3797,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3711,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.9228804026303046e-05,
"loss": 4.3805,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922041807879253e-05,
"loss": 4.3709,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921203213128201e-05,
"loss": 4.3724,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3711,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.356,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.36,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.3544,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3531,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.3542,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.3366,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3458,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3404,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3341,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3239,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3253,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3271,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3202,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3199,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3123,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3048,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3245,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3036,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3089,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3083,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.3084,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.2999,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.2949,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.3087,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2963,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.2821,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.284,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2797,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2796,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2748,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2781,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2666,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.2687,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2634,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891025267252941e-05,
"loss": 4.282,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890186672501889e-05,
"loss": 4.2746,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889348077750837e-05,
"loss": 4.2588,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888509482999785e-05,
"loss": 4.2572,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.2601,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.2647,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.2618,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.2571,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2547,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2523,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2486,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2392,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2481,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.2378,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.2281,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.2429,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.2358,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876774070126176e-05,
"loss": 4.2391,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875935475375124e-05,
"loss": 4.2288,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875096880624072e-05,
"loss": 4.229,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.196639060974121,
"eval_runtime": 303.4597,
"eval_samples_per_second": 1257.468,
"eval_steps_per_second": 39.297,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.2195,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.216,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2308,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.2157,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.224,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.2076,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.2151,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.2022,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.2087,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.2036,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2122,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2067,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.1908,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.1899,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.1881,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.1862,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.1898,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.1818,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.1836,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.198,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.1833,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.1834,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.178,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.1907,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.1615,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853301606498585e-05,
"loss": 4.1778,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.1667,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.1646,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.1627,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.1577,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.1629,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.174,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.1604,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.1622,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845757529499864e-05,
"loss": 4.1519,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.1588,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.1498,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.1557,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.1361,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.1451,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.1404,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.1549,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.1322,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.1427,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.1423,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836536262999038e-05,
"loss": 4.1332,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835697668247986e-05,
"loss": 4.1457,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834859073496934e-05,
"loss": 4.1181,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834020478745882e-05,
"loss": 4.1267,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331818839948295e-05,
"loss": 4.1391,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832344927124151e-05,
"loss": 4.1309,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831506332373099e-05,
"loss": 4.1236,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830667737622047e-05,
"loss": 4.1184,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298291428709944e-05,
"loss": 4.1233,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828992186000316e-05,
"loss": 4.1115,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828153591249264e-05,
"loss": 4.1297,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827314996498212e-05,
"loss": 4.1034,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.82647640174716e-05,
"loss": 4.1173,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256394448764816e-05,
"loss": 4.1173,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248008501254296e-05,
"loss": 4.1114,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823962255374377e-05,
"loss": 4.12,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823123660623325e-05,
"loss": 4.11,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822285065872273e-05,
"loss": 4.0959,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214481090015945e-05,
"loss": 4.0978,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820609514250542e-05,
"loss": 4.1209,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.81977091949949e-05,
"loss": 4.099,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818932324748438e-05,
"loss": 4.1004,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180953678777594e-05,
"loss": 4.0928,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172567731267074e-05,
"loss": 4.0949,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164181783756554e-05,
"loss": 4.1078,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155795836246034e-05,
"loss": 4.1109,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814742626753924e-05,
"loss": 4.0962,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813904032002872e-05,
"loss": 4.1079,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.81306543725182e-05,
"loss": 4.1115,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812226842500768e-05,
"loss": 4.1053,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811388247749716e-05,
"loss": 4.0862,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810551290879037e-05,
"loss": 4.0988,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809712696127985e-05,
"loss": 4.0922,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808874101376933e-05,
"loss": 4.0919,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808035506625881e-05,
"loss": 4.0883,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807198549755203e-05,
"loss": 4.0924,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806359955004151e-05,
"loss": 4.0995,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805521360253099e-05,
"loss": 4.092,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804682765502047e-05,
"loss": 4.0732,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803844170750995e-05,
"loss": 4.0788,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.8030072138803156e-05,
"loss": 4.082,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.8021686191292636e-05,
"loss": 4.0847,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013300243782116e-05,
"loss": 4.0864,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.8004930675075325e-05,
"loss": 4.0729,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.7996544727564805e-05,
"loss": 4.0803,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.7988158780054285e-05,
"loss": 4.0633,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.7979772832543765e-05,
"loss": 4.0786,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971386885033245e-05,
"loss": 4.0778,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796301731632646e-05,
"loss": 4.0748,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795463136881594e-05,
"loss": 4.0811,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794624542130542e-05,
"loss": 4.0674,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.79378594737949e-05,
"loss": 4.0701,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792948990508811e-05,
"loss": 4.0743,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792110395757759e-05,
"loss": 4.072,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791271801006707e-05,
"loss": 4.0679,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790433206255655e-05,
"loss": 4.0625,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789596249384976e-05,
"loss": 4.0623,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788757654633924e-05,
"loss": 4.0683,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787919059882872e-05,
"loss": 4.067,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.78708046513182e-05,
"loss": 4.0473,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862451461415144e-05,
"loss": 4.0617,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854065513904624e-05,
"loss": 4.0629,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845679566394104e-05,
"loss": 4.0583,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837293618883584e-05,
"loss": 4.0527,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828907671373064e-05,
"loss": 4.0534,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820521723862544e-05,
"loss": 4.0466,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812135776352024e-05,
"loss": 4.0683,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803749828841504e-05,
"loss": 4.0499,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779538026013471e-05,
"loss": 4.0567,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778699431262419e-05,
"loss": 4.054,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777860836511367e-05,
"loss": 4.0641,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777023879640689e-05,
"loss": 4.0501,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776185284889637e-05,
"loss": 4.0531,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775346690138585e-05,
"loss": 4.0605,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774508095387533e-05,
"loss": 4.0504,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773669500636481e-05,
"loss": 4.0437,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772830905885429e-05,
"loss": 4.0455,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771992311134377e-05,
"loss": 4.0396,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771153716383325e-05,
"loss": 4.0427,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770316759512646e-05,
"loss": 4.0438,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769478164761594e-05,
"loss": 4.0426,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768639570010542e-05,
"loss": 4.0346,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.76780097525949e-05,
"loss": 4.0375,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.7669640183888106e-05,
"loss": 4.0342,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.7661254236377586e-05,
"loss": 4.0521,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765286828886707e-05,
"loss": 4.0513,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764448234135655e-05,
"loss": 4.0381,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763611277264976e-05,
"loss": 4.0268,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762772682513924e-05,
"loss": 4.0409,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761934087762872e-05,
"loss": 4.0408,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610954930118195e-05,
"loss": 4.0414,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760258536141141e-05,
"loss": 4.0351,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759419941390089e-05,
"loss": 4.0395,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758581346639037e-05,
"loss": 4.032,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577427518879844e-05,
"loss": 4.0345,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756905795017306e-05,
"loss": 4.029,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756067200266254e-05,
"loss": 4.032,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755228605515202e-05,
"loss": 4.0251,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.75439001076415e-05,
"loss": 4.0203,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535530538934716e-05,
"loss": 4.0334,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527144591424196e-05,
"loss": 4.0297,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751875864391367e-05,
"loss": 4.0321,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751037269640315e-05,
"loss": 4.0236,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7502003127696365e-05,
"loss": 4.0225,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.027788162231445,
"eval_runtime": 303.457,
"eval_samples_per_second": 1257.48,
"eval_steps_per_second": 39.297,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493617180185845e-05,
"loss": 4.0158,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748523123267532e-05,
"loss": 4.0142,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.74768452851648e-05,
"loss": 4.028,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746845933765428e-05,
"loss": 4.0171,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460073390143764e-05,
"loss": 4.0283,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451687442633244e-05,
"loss": 4.0091,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443301495122724e-05,
"loss": 4.0209,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434915547612204e-05,
"loss": 4.0089,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426529600101684e-05,
"loss": 4.0165,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418143652591164e-05,
"loss": 4.0115,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409757705080644e-05,
"loss": 4.0191,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740138813637385e-05,
"loss": 4.0151,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739301856766706e-05,
"loss": 4.0006,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738463262015654e-05,
"loss": 4.0035,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737624667264602e-05,
"loss": 4.0019,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.73678607251355e-05,
"loss": 4.0036,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735947477762498e-05,
"loss": 4.0038,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735108883011446e-05,
"loss": 3.9981,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734270288260394e-05,
"loss": 4.0003,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733433331389716e-05,
"loss": 4.0191,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732594736638664e-05,
"loss": 4.0057,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731756141887612e-05,
"loss": 4.0058,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73091754713656e-05,
"loss": 4.0033,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730080590265881e-05,
"loss": 4.0088,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729241995514829e-05,
"loss": 3.9858,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728403400763777e-05,
"loss": 4.0007,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727564806012725e-05,
"loss": 3.9984,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267278491420456e-05,
"loss": 3.9915,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258892543909936e-05,
"loss": 3.9876,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250506596399416e-05,
"loss": 3.9854,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7242120648888896e-05,
"loss": 3.9936,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723375108018211e-05,
"loss": 4.0054,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722536513267159e-05,
"loss": 3.9925,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721697918516107e-05,
"loss": 3.9946,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720859323765055e-05,
"loss": 3.9877,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720022366894376e-05,
"loss": 3.9898,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719183772143324e-05,
"loss": 3.9823,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718345177392272e-05,
"loss": 3.9958,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.71750658264122e-05,
"loss": 3.9708,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716669625770541e-05,
"loss": 3.9843,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715831031019489e-05,
"loss": 3.9782,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714992436268437e-05,
"loss": 3.9956,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714153841517385e-05,
"loss": 3.9753,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133168846467065e-05,
"loss": 3.9809,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124782898956545e-05,
"loss": 3.9846,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116396951446025e-05,
"loss": 3.9747,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7108011003935505e-05,
"loss": 3.9841,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099641435228714e-05,
"loss": 3.9657,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709127186652192e-05,
"loss": 3.9721,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.70828859190114e-05,
"loss": 3.9831,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707449997150088e-05,
"loss": 3.9738,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706611402399036e-05,
"loss": 3.9708,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705772807647984e-05,
"loss": 3.967,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704934212896932e-05,
"loss": 3.9747,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.70409561814588e-05,
"loss": 3.9573,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703257023394828e-05,
"loss": 3.9757,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.70242006652415e-05,
"loss": 3.9536,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701581471773098e-05,
"loss": 3.9702,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700742877022045e-05,
"loss": 3.9733,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699904282270993e-05,
"loss": 3.9615,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699067325400315e-05,
"loss": 3.9682,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698228730649263e-05,
"loss": 3.9688,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.69739013589821e-05,
"loss": 3.9479,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696551541147158e-05,
"loss": 3.9562,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.69571458427648e-05,
"loss": 3.967,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694875989525428e-05,
"loss": 3.9625,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694039032654749e-05,
"loss": 3.9604,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693200437903697e-05,
"loss": 3.9467,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692361843152645e-05,
"loss": 3.9526,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915232484015926e-05,
"loss": 3.9672,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906846536505406e-05,
"loss": 3.9687,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898460588994886e-05,
"loss": 3.9533,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890074641484366e-05,
"loss": 3.9694,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881688693973846e-05,
"loss": 3.9718,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873319125267055e-05,
"loss": 3.9741,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864933177756535e-05,
"loss": 3.9432,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856547230246015e-05,
"loss": 3.9642,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848161282735495e-05,
"loss": 3.9555,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683979171402871e-05,
"loss": 3.9522,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831422145321926e-05,
"loss": 3.9557,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.68230361978114e-05,
"loss": 3.9576,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681465025030088e-05,
"loss": 3.9606,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680626430279036e-05,
"loss": 3.9599,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679787835527984e-05,
"loss": 3.938,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678949240776932e-05,
"loss": 3.9465,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.67811064602588e-05,
"loss": 3.9476,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677272051274828e-05,
"loss": 3.9519,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676435094404149e-05,
"loss": 3.9569,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675596499653097e-05,
"loss": 3.9406,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674757904902045e-05,
"loss": 3.9492,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739193101509935e-05,
"loss": 3.9345,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673083991160687e-05,
"loss": 3.9477,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672245396409635e-05,
"loss": 3.9479,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671406801658583e-05,
"loss": 3.9466,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670568206907531e-05,
"loss": 3.9512,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669729612156479e-05,
"loss": 3.9468,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668891017405427e-05,
"loss": 3.9383,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668052422654375e-05,
"loss": 3.9494,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667213827903323e-05,
"loss": 3.9465,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666376871032644e-05,
"loss": 3.9429,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665538276281592e-05,
"loss": 3.9334,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.66469968153054e-05,
"loss": 3.9384,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663861086779488e-05,
"loss": 3.9442,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66302412990881e-05,
"loss": 3.9455,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662185535157758e-05,
"loss": 3.9211,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661348578287079e-05,
"loss": 3.9367,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660509983536027e-05,
"loss": 3.9445,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659671388784975e-05,
"loss": 3.9365,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658832794033923e-05,
"loss": 3.9303,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579941992828707e-05,
"loss": 3.9347,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571556045318187e-05,
"loss": 3.9274,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6563170097807667e-05,
"loss": 3.9457,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554800529100876e-05,
"loss": 3.9293,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546414581590356e-05,
"loss": 3.9391,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6538028634079836e-05,
"loss": 3.9374,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652964268656932e-05,
"loss": 3.9415,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652127311786253e-05,
"loss": 3.9315,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651288717035201e-05,
"loss": 3.939,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650450122284149e-05,
"loss": 3.9428,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649611527533097e-05,
"loss": 3.933,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648772932782045e-05,
"loss": 3.9228,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647934338030993e-05,
"loss": 3.9287,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470957432799404e-05,
"loss": 3.9236,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646258786409262e-05,
"loss": 3.9302,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.64542019165821e-05,
"loss": 3.9255,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644581596907158e-05,
"loss": 3.9292,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643743002156106e-05,
"loss": 3.9195,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429060452854276e-05,
"loss": 3.9208,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420674505343756e-05,
"loss": 3.9211,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412304936636965e-05,
"loss": 3.9382,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403918989126445e-05,
"loss": 3.9372,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395533041615925e-05,
"loss": 3.9282,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387147094105405e-05,
"loss": 3.9151,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637876114659488e-05,
"loss": 3.9263,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370391577888094e-05,
"loss": 3.9312,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6362005630377574e-05,
"loss": 3.9278,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353619682867054e-05,
"loss": 3.9221,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634523373535653e-05,
"loss": 3.9263,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336847787846014e-05,
"loss": 3.9224,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328461840335494e-05,
"loss": 3.9317,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6320075892824974e-05,
"loss": 3.9137,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311689945314454e-05,
"loss": 3.9265,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630332037660766e-05,
"loss": 3.9153,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629493442909714e-05,
"loss": 3.91,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628654848158662e-05,
"loss": 3.9259,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.62781625340761e-05,
"loss": 3.9248,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626977658656558e-05,
"loss": 3.9218,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626139063905506e-05,
"loss": 3.9176,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625300469154454e-05,
"loss": 3.9119,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.9528229236602783,
"eval_runtime": 303.3267,
"eval_samples_per_second": 1258.02,
"eval_steps_per_second": 39.314,
"step": 228960
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.5939988909905715e+17,
"trial_name": null,
"trial_params": null
}