abhinavp's picture
Training in progress, epoch 0, checkpoint
831ac38 verified
raw
history blame
429 kB
{
"best_metric": 3.846700668334961,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-case/transformer/3/checkpoints/checkpoint-992160",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 1755360,
"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": 11.0367,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8185,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.184,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9671,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8129,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7096,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6119,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5405,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4592,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4127,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3528,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3116,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 5.2666,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2216,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1839,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1431,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.114,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0846,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0556,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0274,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.0138,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 4.9861,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9568,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9426,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9321,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.8954,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8774,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8643,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8494,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8265,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.8097,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.807,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7914,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 4.7853,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 4.7692,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.751,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7454,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.711,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7171,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6882,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.69,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6784,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.6817,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6593,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6528,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6478,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6296,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6398,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.6047,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 4.5971,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.61,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 4.6042,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 4.58,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5731,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 4.5749,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 4.5551,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.5765,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5389,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5482,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5369,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5224,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5299,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5116,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.5095,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4998,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5145,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4858,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4916,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4688,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.4769,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4896,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4777,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4595,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4747,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4758,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4496,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4551,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4382,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4273,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4264,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4267,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4328,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4388,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930422841748654e-05,
"loss": 4.4279,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.403,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.4092,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.4114,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927070100624819e-05,
"loss": 4.4034,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.3951,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.3913,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3853,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.3936,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.9228804026303046e-05,
"loss": 4.3807,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922041807879253e-05,
"loss": 4.3876,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921203213128201e-05,
"loss": 4.3756,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3756,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3617,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3639,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.3601,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3655,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.3654,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.343,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3502,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3424,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3447,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3323,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3311,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.3359,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3268,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.3249,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3173,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3141,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.9061134212503846e-05,
"loss": 4.3278,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3155,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3129,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.3158,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027606801265495e-05,
"loss": 4.3224,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.3072,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.2956,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.3028,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.3064,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985693442516624e-05,
"loss": 4.294,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2913,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.2907,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2907,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2851,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2884,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2803,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.2821,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2742,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.2915,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2755,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2678,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888509482999785e-05,
"loss": 4.2627,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.2739,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.2682,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.2735,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.2606,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2664,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2599,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2602,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2496,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2601,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801268112500106e-05,
"loss": 4.2458,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879289854379332e-05,
"loss": 4.2367,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87845125962828e-05,
"loss": 4.2577,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877612664877228e-05,
"loss": 4.2432,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876774070126176e-05,
"loss": 4.2427,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875935475375124e-05,
"loss": 4.2483,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875096880624072e-05,
"loss": 4.2314,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.204476833343506,
"eval_runtime": 303.8587,
"eval_samples_per_second": 1255.817,
"eval_steps_per_second": 39.245,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.2212,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.2257,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.2327,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.2252,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.2341,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.2187,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.221,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.2116,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.2237,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.206,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.2066,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.2093,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642000625015155e-05,
"loss": 4.2057,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.1971,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.1982,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.183,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.1934,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.186,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.1796,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.2064,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.1841,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.1877,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.1838,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.1972,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.1709,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853301606498585e-05,
"loss": 4.1732,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.1776,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.1772,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850787460125802e-05,
"loss": 4.1682,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.84994886537475e-05,
"loss": 4.1651,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.1736,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.1744,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847434719001968e-05,
"loss": 4.1755,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846596124250916e-05,
"loss": 4.1656,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845757529499864e-05,
"loss": 4.1605,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844918934748812e-05,
"loss": 4.1713,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844081977878133e-05,
"loss": 4.1418,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843243383127081e-05,
"loss": 4.1626,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842404788376029e-05,
"loss": 4.141,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.1523,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.8407292367542976e-05,
"loss": 4.147,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398906420032456e-05,
"loss": 4.1567,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.8390520472521936e-05,
"loss": 4.1495,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382134525011416e-05,
"loss": 4.1426,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837376495630463e-05,
"loss": 4.1497,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836537900879411e-05,
"loss": 4.1407,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835699306128359e-05,
"loss": 4.1534,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834860711377307e-05,
"loss": 4.126,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834023754506628e-05,
"loss": 4.1249,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833185159755576e-05,
"loss": 4.1454,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832346565004524e-05,
"loss": 4.1448,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831507970253472e-05,
"loss": 4.1293,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830671013382793e-05,
"loss": 4.1231,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829832418631741e-05,
"loss": 4.1329,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828993823880689e-05,
"loss": 4.1164,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828155229129637e-05,
"loss": 4.1385,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273182722589585e-05,
"loss": 4.1206,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264796775079065e-05,
"loss": 4.1287,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256410827568545e-05,
"loss": 4.1224,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248024880058025e-05,
"loss": 4.1122,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239655311351234e-05,
"loss": 4.1248,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231269363840714e-05,
"loss": 4.112,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222883416330194e-05,
"loss": 4.1103,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214497468819674e-05,
"loss": 4.1075,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820612790011288e-05,
"loss": 4.1269,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819774195260236e-05,
"loss": 4.1075,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818935600509184e-05,
"loss": 4.1093,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818097005758132e-05,
"loss": 4.0987,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817260048887454e-05,
"loss": 4.1054,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816421454136402e-05,
"loss": 4.1221,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.81558285938535e-05,
"loss": 4.1158,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814744264634298e-05,
"loss": 4.1035,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813907307763619e-05,
"loss": 4.1145,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813068713012567e-05,
"loss": 4.1172,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812230118261515e-05,
"loss": 4.1019,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811391523510463e-05,
"loss": 4.1083,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810554566639784e-05,
"loss": 4.0993,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809715971888732e-05,
"loss": 4.0869,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887737713768e-05,
"loss": 4.0918,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808038782386628e-05,
"loss": 4.0947,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807201825515949e-05,
"loss": 4.0994,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806363230764897e-05,
"loss": 4.1152,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805524636013845e-05,
"loss": 4.1032,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804686041262793e-05,
"loss": 4.0796,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803849084392114e-05,
"loss": 4.0897,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803010489641062e-05,
"loss": 4.0943,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.80217189489001e-05,
"loss": 4.0909,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801333300138958e-05,
"loss": 4.083,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800496343268279e-05,
"loss": 4.0829,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799657748517227e-05,
"loss": 4.0818,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798819153766175e-05,
"loss": 4.0869,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797980559015123e-05,
"loss": 4.0793,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.7971436021444446e-05,
"loss": 4.0872,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7963050073933926e-05,
"loss": 4.0801,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954680505227135e-05,
"loss": 4.0838,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946294557716615e-05,
"loss": 4.0685,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937908610206095e-05,
"loss": 4.0785,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929522662695575e-05,
"loss": 4.0744,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.7921136715185055e-05,
"loss": 4.0788,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912750767674535e-05,
"loss": 4.0799,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790436482016401e-05,
"loss": 4.0678,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895995251457224e-05,
"loss": 4.0691,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887609303946704e-05,
"loss": 4.0696,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879223356436184e-05,
"loss": 4.0719,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870837408925664e-05,
"loss": 4.0591,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786246784021888e-05,
"loss": 4.0633,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785408189270836e-05,
"loss": 4.0718,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784569594519783e-05,
"loss": 4.0595,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783730999768731e-05,
"loss": 4.0619,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782892405017679e-05,
"loss": 4.0545,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782053810266627e-05,
"loss": 4.0518,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781215215515575e-05,
"loss": 4.0729,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780376620764523e-05,
"loss": 4.0541,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779539663893844e-05,
"loss": 4.0627,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778701069142792e-05,
"loss": 4.0607,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.77786247439174e-05,
"loss": 4.0739,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777023879640689e-05,
"loss": 4.0594,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.77618692277001e-05,
"loss": 4.0472,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775348328018958e-05,
"loss": 4.0557,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774509733267906e-05,
"loss": 4.0595,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773672776397227e-05,
"loss": 4.0458,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728341816461747e-05,
"loss": 4.0525,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719955868951227e-05,
"loss": 4.0455,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711569921440707e-05,
"loss": 4.0572,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703183973930186e-05,
"loss": 4.0444,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694798026419666e-05,
"loss": 4.0539,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686412078909146e-05,
"loss": 4.0477,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.7678026131398626e-05,
"loss": 4.0488,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766965656269184e-05,
"loss": 4.0405,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766128699398505e-05,
"loss": 4.0625,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765290104647453e-05,
"loss": 4.0516,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764451509896401e-05,
"loss": 4.036,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763612915145349e-05,
"loss": 4.0382,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762774320394297e-05,
"loss": 4.0458,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761935725643245e-05,
"loss": 4.0474,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761098768772566e-05,
"loss": 4.0546,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760260174021514e-05,
"loss": 4.0373,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759421579270462e-05,
"loss": 4.0456,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.75858298451941e-05,
"loss": 4.0414,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757744389768358e-05,
"loss": 4.0463,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756905795017306e-05,
"loss": 4.0364,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756067200266254e-05,
"loss": 4.0407,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755228605515202e-05,
"loss": 4.0346,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543916486445236e-05,
"loss": 4.0272,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535546917738445e-05,
"loss": 4.0477,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527160970227925e-05,
"loss": 4.0385,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518775022717405e-05,
"loss": 4.0327,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510389075206885e-05,
"loss": 4.0355,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7502003127696365e-05,
"loss": 4.0255,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.034289360046387,
"eval_runtime": 302.2571,
"eval_samples_per_second": 1262.471,
"eval_steps_per_second": 39.453,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493617180185845e-05,
"loss": 4.0159,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748523123267532e-05,
"loss": 4.0195,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.74768452851648e-05,
"loss": 4.0332,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746845933765428e-05,
"loss": 4.0231,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460073390143764e-05,
"loss": 4.038,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451687442633244e-05,
"loss": 4.0201,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443301495122724e-05,
"loss": 4.0222,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434915547612204e-05,
"loss": 4.0153,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426529600101684e-05,
"loss": 4.0312,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418143652591164e-05,
"loss": 4.0147,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409757705080644e-05,
"loss": 4.0134,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740138813637385e-05,
"loss": 4.0155,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739301856766706e-05,
"loss": 4.0164,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738463262015654e-05,
"loss": 4.0082,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737624667264602e-05,
"loss": 4.0111,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.73678607251355e-05,
"loss": 4.001,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735947477762498e-05,
"loss": 4.0035,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735108883011446e-05,
"loss": 4.0001,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734271926140768e-05,
"loss": 3.9961,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733433331389716e-05,
"loss": 4.0284,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732594736638664e-05,
"loss": 4.0048,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731756141887612e-05,
"loss": 4.0019,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73091754713656e-05,
"loss": 4.0081,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730078952385508e-05,
"loss": 4.0146,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729241995514829e-05,
"loss": 3.9942,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728403400763777e-05,
"loss": 3.9988,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727564806012725e-05,
"loss": 4.0004,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726726211261673e-05,
"loss": 4.0044,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725887616510621e-05,
"loss": 3.9901,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250506596399416e-05,
"loss": 3.9934,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7242120648888896e-05,
"loss": 3.9987,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723373470137838e-05,
"loss": 4.0037,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225348753867856e-05,
"loss": 4.0104,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.7216962806357336e-05,
"loss": 3.9967,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208576858846816e-05,
"loss": 3.9905,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720020729014003e-05,
"loss": 4.0012,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.7191821342629505e-05,
"loss": 3.9819,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.7183435395118985e-05,
"loss": 3.9959,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.7175049447608465e-05,
"loss": 3.9765,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716667987890168e-05,
"loss": 3.9847,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158293931391154e-05,
"loss": 3.9867,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149907983880634e-05,
"loss": 3.997,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714152203637012e-05,
"loss": 3.9897,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71331360888596e-05,
"loss": 3.982,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712475014134908e-05,
"loss": 3.9881,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711636419383856e-05,
"loss": 3.9836,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710797824632804e-05,
"loss": 3.9916,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709960867762125e-05,
"loss": 3.9708,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709123910891446e-05,
"loss": 3.9669,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708285316140394e-05,
"loss": 3.9893,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707446721389342e-05,
"loss": 3.9856,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.70660812663829e-05,
"loss": 3.9745,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705771169767611e-05,
"loss": 3.9731,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704932575016559e-05,
"loss": 3.9775,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040939802655074e-05,
"loss": 3.9638,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032553855144554e-05,
"loss": 3.9848,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024167907634034e-05,
"loss": 3.9715,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701579833892724e-05,
"loss": 3.9788,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700741239141672e-05,
"loss": 3.9709,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.69990264439062e-05,
"loss": 3.9702,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699064049639568e-05,
"loss": 3.9697,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698227092768889e-05,
"loss": 3.9684,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697388498017837e-05,
"loss": 3.9633,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696549903266785e-05,
"loss": 3.9616,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695711308515733e-05,
"loss": 3.9781,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694872713764681e-05,
"loss": 3.9649,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694034119013629e-05,
"loss": 3.965,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693197162142951e-05,
"loss": 3.9546,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692358567391899e-05,
"loss": 3.9618,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691519972640847e-05,
"loss": 3.9789,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690681377889795e-05,
"loss": 3.973,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898444210191157e-05,
"loss": 3.9643,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890058262680636e-05,
"loss": 3.9726,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881672315170116e-05,
"loss": 3.9763,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873286367659596e-05,
"loss": 3.9586,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864900420149076e-05,
"loss": 3.968,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856530851442285e-05,
"loss": 3.9611,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848144903931765e-05,
"loss": 3.9505,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839758956421245e-05,
"loss": 3.9606,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831373008910725e-05,
"loss": 3.9528,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682300344020394e-05,
"loss": 3.9629,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681461749269342e-05,
"loss": 3.9716,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.68062315451829e-05,
"loss": 3.9699,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679784559767238e-05,
"loss": 3.9414,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678945965016186e-05,
"loss": 3.9591,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678107370265134e-05,
"loss": 3.958,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772687755140814e-05,
"loss": 3.9588,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676431818643403e-05,
"loss": 3.9527,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9467,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674754629141298e-05,
"loss": 3.9566,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673916034390246e-05,
"loss": 3.9519,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673079077519568e-05,
"loss": 3.9466,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672240482768516e-05,
"loss": 3.955,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671401888017464e-05,
"loss": 3.9486,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670563293266412e-05,
"loss": 3.9575,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.66972469851536e-05,
"loss": 3.9427,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688877416446815e-05,
"loss": 3.9452,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668049146893629e-05,
"loss": 3.9467,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667210552142577e-05,
"loss": 3.9559,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666371957391525e-05,
"loss": 3.9532,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665535000520846e-05,
"loss": 3.9429,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664696405769794e-05,
"loss": 3.944,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663857811018742e-05,
"loss": 3.9437,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.66301921626769e-05,
"loss": 3.9486,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621806215166383e-05,
"loss": 3.9315,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661343664645959e-05,
"loss": 3.9381,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660505069894907e-05,
"loss": 3.9501,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659666475143855e-05,
"loss": 3.9409,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658827880392803e-05,
"loss": 3.9339,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657989285641751e-05,
"loss": 3.9323,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657152328771072e-05,
"loss": 3.9304,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.65631373402002e-05,
"loss": 3.9481,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655475139268968e-05,
"loss": 3.9382,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654636544517916e-05,
"loss": 3.9366,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653797949766864e-05,
"loss": 3.9412,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652959355015812e-05,
"loss": 3.9547,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652122398145134e-05,
"loss": 3.9403,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651283803394082e-05,
"loss": 3.9285,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.65044520864303e-05,
"loss": 3.9372,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649606613891978e-05,
"loss": 3.9389,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487696570212986e-05,
"loss": 3.9307,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479310622702466e-05,
"loss": 3.9329,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470924675191946e-05,
"loss": 3.9282,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462538727681426e-05,
"loss": 3.9399,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454169158974635e-05,
"loss": 3.9265,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445783211464115e-05,
"loss": 3.9433,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437397263953595e-05,
"loss": 3.9257,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429011316443075e-05,
"loss": 3.9357,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642064174773629e-05,
"loss": 3.9242,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641225580022577e-05,
"loss": 3.9464,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640386985271525e-05,
"loss": 3.9383,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639548390520473e-05,
"loss": 3.9277,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638711433649794e-05,
"loss": 3.9208,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637872838898742e-05,
"loss": 3.9347,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.63703424414769e-05,
"loss": 3.93,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636195649396638e-05,
"loss": 3.9424,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635358692525959e-05,
"loss": 3.9229,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634520097774907e-05,
"loss": 3.9357,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633681503023855e-05,
"loss": 3.929,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632842908272803e-05,
"loss": 3.9405,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632004313521751e-05,
"loss": 3.9211,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311673566510724e-05,
"loss": 3.9292,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303287619000204e-05,
"loss": 3.9256,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294901671489684e-05,
"loss": 3.9186,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286532102782893e-05,
"loss": 3.9364,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6278146155272373e-05,
"loss": 3.9329,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626976020776185e-05,
"loss": 3.9196,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626137426025133e-05,
"loss": 3.928,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625298831274081e-05,
"loss": 3.9162,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.959151268005371,
"eval_runtime": 435.6911,
"eval_samples_per_second": 875.829,
"eval_steps_per_second": 27.37,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624460236523029e-05,
"loss": 3.9137,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.6236216417719766e-05,
"loss": 3.9121,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.6227830470209246e-05,
"loss": 3.9222,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219444522698726e-05,
"loss": 3.9195,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621107495399194e-05,
"loss": 3.9353,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620268900648142e-05,
"loss": 3.9093,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.61943030589709e-05,
"loss": 3.9175,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618591711146038e-05,
"loss": 3.9113,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617754754275359e-05,
"loss": 3.9299,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616916159524307e-05,
"loss": 3.9097,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616077564773255e-05,
"loss": 3.9068,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615238970022203e-05,
"loss": 3.9167,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614402013151524e-05,
"loss": 3.909,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613563418400472e-05,
"loss": 3.908,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.61272482364942e-05,
"loss": 3.9076,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611886228898368e-05,
"loss": 3.9012,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611047634147316e-05,
"loss": 3.8986,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610209039396265e-05,
"loss": 3.9018,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609370444645213e-05,
"loss": 3.897,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.6085318498941607e-05,
"loss": 3.9256,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076948930234816e-05,
"loss": 3.9026,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068562982724296e-05,
"loss": 3.9039,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6060177035213776e-05,
"loss": 3.9078,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051791087703256e-05,
"loss": 3.9123,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.6043421518996465e-05,
"loss": 3.8975,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.6035035571485945e-05,
"loss": 3.9021,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.6026649623975425e-05,
"loss": 3.8985,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018263676464904e-05,
"loss": 3.9043,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009894107758114e-05,
"loss": 3.8924,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.60015081602476e-05,
"loss": 3.8964,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599312221273708e-05,
"loss": 3.9025,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598473626522656e-05,
"loss": 3.9053,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597635031771604e-05,
"loss": 3.9123,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596798074900925e-05,
"loss": 3.904,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595959480149873e-05,
"loss": 3.8932,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595120885398821e-05,
"loss": 3.9041,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594282290647769e-05,
"loss": 3.889,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.59344533377709e-05,
"loss": 3.8982,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592606739026038e-05,
"loss": 3.8835,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591768144274986e-05,
"loss": 3.8891,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590929549523934e-05,
"loss": 3.8879,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900925926532554e-05,
"loss": 3.9053,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.5892539979022034e-05,
"loss": 3.8988,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5884154031511514e-05,
"loss": 3.889,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.5875768084000994e-05,
"loss": 3.8936,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867382136490474e-05,
"loss": 3.8908,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585901256778368e-05,
"loss": 3.898,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585062662027316e-05,
"loss": 3.8806,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584224067276264e-05,
"loss": 3.8722,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583385472525212e-05,
"loss": 3.8963,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582548515654533e-05,
"loss": 3.894,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581709920903481e-05,
"loss": 3.8786,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580871326152429e-05,
"loss": 3.8856,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580032731401377e-05,
"loss": 3.8902,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579195774530699e-05,
"loss": 3.8728,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578357179779647e-05,
"loss": 3.8898,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577518585028595e-05,
"loss": 3.8791,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576679990277543e-05,
"loss": 3.8925,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758430334068637e-05,
"loss": 3.8772,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5750044386558117e-05,
"loss": 3.8886,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741658439047596e-05,
"loss": 3.8766,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733272491537076e-05,
"loss": 3.8824,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724902922830286e-05,
"loss": 3.8702,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716516975319765e-05,
"loss": 3.8741,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5708131027809245e-05,
"loss": 3.8938,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.5699745080298725e-05,
"loss": 3.8736,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569137551159194e-05,
"loss": 3.8787,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568298956408142e-05,
"loss": 3.8653,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.56746036165709e-05,
"loss": 3.8772,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.5666217669060374e-05,
"loss": 3.889,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565784810035359e-05,
"loss": 3.8847,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564946215284307e-05,
"loss": 3.8814,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564107620533255e-05,
"loss": 3.8862,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563269025782202e-05,
"loss": 3.8859,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562432068911524e-05,
"loss": 3.8758,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561593474160472e-05,
"loss": 3.8811,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.56075487940942e-05,
"loss": 3.8784,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559916284658368e-05,
"loss": 3.8687,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.5590793277876895e-05,
"loss": 3.872,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582407330366375e-05,
"loss": 3.8701,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557402138285585e-05,
"loss": 3.8767,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556563543534533e-05,
"loss": 3.885,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.5557265866638544e-05,
"loss": 3.8831,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.5548879919128024e-05,
"loss": 3.8573,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.55404939716175e-05,
"loss": 3.8805,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553210802410698e-05,
"loss": 3.8746,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552373845540019e-05,
"loss": 3.8753,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515352507889666e-05,
"loss": 3.8701,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550696656037915e-05,
"loss": 3.8625,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549858061286863e-05,
"loss": 3.8735,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549021104416185e-05,
"loss": 3.867,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548182509665132e-05,
"loss": 3.8674,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.54734391491408e-05,
"loss": 3.8714,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546505320163028e-05,
"loss": 3.8683,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.54566836329235e-05,
"loss": 3.877,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544829768541297e-05,
"loss": 3.8635,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543991173790245e-05,
"loss": 3.8618,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543152579039193e-05,
"loss": 3.8645,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542315622168514e-05,
"loss": 3.8776,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541477027417462e-05,
"loss": 3.8677,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406384326664106e-05,
"loss": 3.863,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5397998379153586e-05,
"loss": 3.8606,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389628810446796e-05,
"loss": 3.8643,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5381242862936275e-05,
"loss": 3.8726,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372856915425755e-05,
"loss": 3.8572,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364470967915235e-05,
"loss": 3.8541,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5356101399208444e-05,
"loss": 3.8701,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347715451697924e-05,
"loss": 3.859,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339329504187404e-05,
"loss": 3.854,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330943556676884e-05,
"loss": 3.8521,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322573987970093e-05,
"loss": 3.8541,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314188040459573e-05,
"loss": 3.8694,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530580209294906e-05,
"loss": 3.8549,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529741614543854e-05,
"loss": 3.8602,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528903019792802e-05,
"loss": 3.8643,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528066062922123e-05,
"loss": 3.8741,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527227468171071e-05,
"loss": 3.8672,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526388873420019e-05,
"loss": 3.8488,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525550278668967e-05,
"loss": 3.8604,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524711683917915e-05,
"loss": 3.8562,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523874727047236e-05,
"loss": 3.858,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523036132296184e-05,
"loss": 3.8564,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522197537545132e-05,
"loss": 3.8498,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.52135894279408e-05,
"loss": 3.8636,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520521985923401e-05,
"loss": 3.8512,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.5196833911723494e-05,
"loss": 3.8624,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.5188447964212974e-05,
"loss": 3.8525,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5180062016702454e-05,
"loss": 3.8587,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517169244799566e-05,
"loss": 3.848,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516330650048514e-05,
"loss": 3.8738,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515492055297462e-05,
"loss": 3.8557,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.51465346054641e-05,
"loss": 3.8553,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513816503675731e-05,
"loss": 3.845,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512977908924679e-05,
"loss": 3.8613,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512139314173627e-05,
"loss": 3.8539,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511300719422575e-05,
"loss": 3.8669,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510462124671523e-05,
"loss": 3.8497,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509625167800845e-05,
"loss": 3.8588,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508786573049793e-05,
"loss": 3.8568,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507947978298741e-05,
"loss": 3.87,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507109383547689e-05,
"loss": 3.8449,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062724266770096e-05,
"loss": 3.8557,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.5054338319259576e-05,
"loss": 3.8511,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.5045952371749056e-05,
"loss": 3.8481,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.5037582803042265e-05,
"loss": 3.8602,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5029196855531745e-05,
"loss": 3.8588,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020810908021225e-05,
"loss": 3.8489,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012424960510705e-05,
"loss": 3.8517,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.5004039013000185e-05,
"loss": 3.8461,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.917680501937866,
"eval_runtime": 442.5939,
"eval_samples_per_second": 862.17,
"eval_steps_per_second": 26.943,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.4995653065489665e-05,
"loss": 3.8386,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987267117979145e-05,
"loss": 3.8367,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497888117046863e-05,
"loss": 3.8493,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970495222958105e-05,
"loss": 3.8485,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4962109275447585e-05,
"loss": 3.8629,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953723327937065e-05,
"loss": 3.8429,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945337380426545e-05,
"loss": 3.8434,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936951432916025e-05,
"loss": 3.8413,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928581864209234e-05,
"loss": 3.857,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4920195916698714e-05,
"loss": 3.8431,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911809969188194e-05,
"loss": 3.8351,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903424021677674e-05,
"loss": 3.8431,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489505445297088e-05,
"loss": 3.8389,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488666850546037e-05,
"loss": 3.8376,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487828255794985e-05,
"loss": 3.8421,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486989661043933e-05,
"loss": 3.8267,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486151066292881e-05,
"loss": 3.8315,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485312471541829e-05,
"loss": 3.8329,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484473876790777e-05,
"loss": 3.8272,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483635282039725e-05,
"loss": 3.8537,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482798325169046e-05,
"loss": 3.8395,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481959730417994e-05,
"loss": 3.8345,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481121135666942e-05,
"loss": 3.837,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.48028254091589e-05,
"loss": 3.845,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479445584045211e-05,
"loss": 3.8288,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478606989294159e-05,
"loss": 3.8357,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477768394543107e-05,
"loss": 3.8306,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476929799792055e-05,
"loss": 3.8326,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476092842921376e-05,
"loss": 3.8251,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475254248170324e-05,
"loss": 3.8313,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474415653419272e-05,
"loss": 3.8366,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.47357705866822e-05,
"loss": 3.8377,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472740101797541e-05,
"loss": 3.8435,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471901507046489e-05,
"loss": 3.8369,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471062912295437e-05,
"loss": 3.8252,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470224317544385e-05,
"loss": 3.8348,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469387360673706e-05,
"loss": 3.8274,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468548765922654e-05,
"loss": 3.8287,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467710171171602e-05,
"loss": 3.8178,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.46687157642055e-05,
"loss": 3.8237,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466034619549872e-05,
"loss": 3.8251,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.46519602479882e-05,
"loss": 3.8376,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464357430047768e-05,
"loss": 3.8314,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463518835296716e-05,
"loss": 3.8261,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462680240545664e-05,
"loss": 3.8276,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618432836749846e-05,
"loss": 3.8268,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4610046889239326e-05,
"loss": 3.8328,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601660941728806e-05,
"loss": 3.8182,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4593291373022015e-05,
"loss": 3.8062,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584905425511495e-05,
"loss": 3.8325,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576519478000975e-05,
"loss": 3.8281,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4568133530490455e-05,
"loss": 3.8137,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455974758297994e-05,
"loss": 3.8205,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455137801427315e-05,
"loss": 3.828,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454299206676263e-05,
"loss": 3.8075,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453460611925211e-05,
"loss": 3.8266,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4526220171741584e-05,
"loss": 3.8176,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.45178506030348e-05,
"loss": 3.8266,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450946465552428e-05,
"loss": 3.8149,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450107870801376e-05,
"loss": 3.8237,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449269276050323e-05,
"loss": 3.814,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448432319179645e-05,
"loss": 3.8228,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447593724428593e-05,
"loss": 3.8049,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446755129677541e-05,
"loss": 3.8155,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445916534926489e-05,
"loss": 3.8266,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.4450795780558104e-05,
"loss": 3.8153,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.4442409833047584e-05,
"loss": 3.8127,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443402388553706e-05,
"loss": 3.8039,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442563793802654e-05,
"loss": 3.8124,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441726836931975e-05,
"loss": 3.8228,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440888242180923e-05,
"loss": 3.8254,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.4400496474298706e-05,
"loss": 3.8199,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.4392110526788186e-05,
"loss": 3.8261,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.43837409580814e-05,
"loss": 3.8256,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437535501057088e-05,
"loss": 3.8136,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436696906306036e-05,
"loss": 3.8171,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435858311554984e-05,
"loss": 3.8199,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.435021354684306e-05,
"loss": 3.8062,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434182759933253e-05,
"loss": 3.8091,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433344165182201e-05,
"loss": 3.8126,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432505570431149e-05,
"loss": 3.8131,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431668613560471e-05,
"loss": 3.8261,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430830018809418e-05,
"loss": 3.8232,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429991424058366e-05,
"loss": 3.7983,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429152829307314e-05,
"loss": 3.8146,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4283158724366356e-05,
"loss": 3.8172,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274772776855836e-05,
"loss": 3.816,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266386829345316e-05,
"loss": 3.8123,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4258000881834796e-05,
"loss": 3.7996,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249631313128005e-05,
"loss": 3.8123,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4241245365617485e-05,
"loss": 3.8073,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232859418106965e-05,
"loss": 3.8082,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224473470596445e-05,
"loss": 3.8062,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4216103901889654e-05,
"loss": 3.8125,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207717954379134e-05,
"loss": 3.814,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.4199332006868614e-05,
"loss": 3.8121,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190946059358094e-05,
"loss": 3.7971,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418257649065131e-05,
"loss": 3.8078,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417419054314079e-05,
"loss": 3.8133,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416580459563027e-05,
"loss": 3.8131,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415741864811975e-05,
"loss": 3.8028,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414904907941296e-05,
"loss": 3.8044,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414066313190244e-05,
"loss": 3.8076,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413227718439192e-05,
"loss": 3.813,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.41238912368814e-05,
"loss": 3.8016,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411550528937088e-05,
"loss": 3.7988,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410713572066409e-05,
"loss": 3.8065,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409874977315357e-05,
"loss": 3.8014,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409036382564305e-05,
"loss": 3.7959,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408197787813253e-05,
"loss": 3.7945,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407360830942574e-05,
"loss": 3.7955,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406522236191522e-05,
"loss": 3.8136,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.40568364144047e-05,
"loss": 3.8002,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404845046689418e-05,
"loss": 3.7997,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.404008089818739e-05,
"loss": 3.8067,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403169495067687e-05,
"loss": 3.8192,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402330900316635e-05,
"loss": 3.8114,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401492305565583e-05,
"loss": 3.7935,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400655348694904e-05,
"loss": 3.8011,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399816753943852e-05,
"loss": 3.8001,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.3989781591928e-05,
"loss": 3.7984,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398139564441748e-05,
"loss": 3.8013,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.39730260757107e-05,
"loss": 3.7925,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396464012820018e-05,
"loss": 3.804,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3956254180689657e-05,
"loss": 3.799,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.3947868233179137e-05,
"loss": 3.8062,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.3939498664472346e-05,
"loss": 3.7937,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3931112716961826e-05,
"loss": 3.799,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.3922726769451306e-05,
"loss": 3.8001,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3914340821940786e-05,
"loss": 3.8132,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905971253233995e-05,
"loss": 3.798,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897585305723475e-05,
"loss": 3.8044,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.3889199358212955e-05,
"loss": 3.7908,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.3880813410702434e-05,
"loss": 3.8072,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872427463191914e-05,
"loss": 3.8011,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386405789448513e-05,
"loss": 3.8083,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385567194697461e-05,
"loss": 3.7935,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384728599946409e-05,
"loss": 3.8093,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383890005195357e-05,
"loss": 3.7963,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383053048324678e-05,
"loss": 3.8166,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382214453573626e-05,
"loss": 3.7922,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381375858822574e-05,
"loss": 3.8027,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380537264071522e-05,
"loss": 3.7959,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379700307200843e-05,
"loss": 3.7917,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378863350330164e-05,
"loss": 3.8068,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3780247555791124e-05,
"loss": 3.8038,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771861608280604e-05,
"loss": 3.7956,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763475660770084e-05,
"loss": 3.7935,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3755089713259564e-05,
"loss": 3.7972,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.891878843307495,
"eval_runtime": 305.7093,
"eval_samples_per_second": 1248.215,
"eval_steps_per_second": 39.008,
"step": 381600
},
{
"epoch": 0.0,
"learning_rate": 4.3746703765749044e-05,
"loss": 3.7857,
"step": 381952
},
{
"epoch": 0.0,
"learning_rate": 4.3738317818238524e-05,
"loss": 3.7822,
"step": 382464
},
{
"epoch": 0.0,
"learning_rate": 4.3729931870728004e-05,
"loss": 3.795,
"step": 382976
},
{
"epoch": 0.0,
"learning_rate": 4.3721545923217484e-05,
"loss": 3.7958,
"step": 383488
},
{
"epoch": 0.0,
"learning_rate": 4.371315997570696e-05,
"loss": 3.8053,
"step": 384000
},
{
"epoch": 0.0,
"learning_rate": 4.370477402819644e-05,
"loss": 3.7885,
"step": 384512
},
{
"epoch": 0.0,
"learning_rate": 4.369638808068592e-05,
"loss": 3.7893,
"step": 385024
},
{
"epoch": 0.0,
"learning_rate": 4.36880021331754e-05,
"loss": 3.7892,
"step": 385536
},
{
"epoch": 0.0,
"learning_rate": 4.3679632564468606e-05,
"loss": 3.8025,
"step": 386048
},
{
"epoch": 0.0,
"learning_rate": 4.3671246616958086e-05,
"loss": 3.7875,
"step": 386560
},
{
"epoch": 0.0,
"learning_rate": 4.366286066944757e-05,
"loss": 3.7855,
"step": 387072
},
{
"epoch": 0.0,
"learning_rate": 4.365447472193705e-05,
"loss": 3.7876,
"step": 387584
},
{
"epoch": 0.0,
"learning_rate": 4.3646121532034e-05,
"loss": 3.7893,
"step": 388096
},
{
"epoch": 0.0,
"learning_rate": 4.363773558452348e-05,
"loss": 3.784,
"step": 388608
},
{
"epoch": 0.0,
"learning_rate": 4.362934963701296e-05,
"loss": 3.7893,
"step": 389120
},
{
"epoch": 0.0,
"learning_rate": 4.362096368950243e-05,
"loss": 3.7764,
"step": 389632
},
{
"epoch": 0.0,
"learning_rate": 4.361257774199191e-05,
"loss": 3.7769,
"step": 390144
},
{
"epoch": 0.0,
"learning_rate": 4.360419179448139e-05,
"loss": 3.7817,
"step": 390656
},
{
"epoch": 0.0,
"learning_rate": 4.359580584697087e-05,
"loss": 3.7737,
"step": 391168
},
{
"epoch": 0.0,
"learning_rate": 4.358741989946035e-05,
"loss": 3.7995,
"step": 391680
},
{
"epoch": 0.0,
"learning_rate": 4.357905033075356e-05,
"loss": 3.788,
"step": 392192
},
{
"epoch": 0.0,
"learning_rate": 4.357066438324304e-05,
"loss": 3.7843,
"step": 392704
},
{
"epoch": 0.0,
"learning_rate": 4.3562278435732526e-05,
"loss": 3.7827,
"step": 393216
},
{
"epoch": 0.0,
"learning_rate": 4.3553892488222006e-05,
"loss": 3.7936,
"step": 393728
},
{
"epoch": 0.0,
"learning_rate": 4.3545522919515215e-05,
"loss": 3.7775,
"step": 394240
},
{
"epoch": 0.0,
"learning_rate": 4.3537136972004695e-05,
"loss": 3.7855,
"step": 394752
},
{
"epoch": 0.0,
"learning_rate": 4.3528751024494175e-05,
"loss": 3.7757,
"step": 395264
},
{
"epoch": 0.0,
"learning_rate": 4.3520365076983655e-05,
"loss": 3.7828,
"step": 395776
},
{
"epoch": 0.0,
"learning_rate": 4.3511995508276864e-05,
"loss": 3.7776,
"step": 396288
},
{
"epoch": 0.0,
"learning_rate": 4.3503609560766344e-05,
"loss": 3.7777,
"step": 396800
},
{
"epoch": 0.01,
"learning_rate": 4.3495223613255824e-05,
"loss": 3.7863,
"step": 397312
},
{
"epoch": 0.01,
"learning_rate": 4.3486837665745304e-05,
"loss": 3.7843,
"step": 397824
},
{
"epoch": 0.01,
"learning_rate": 4.347846809703851e-05,
"loss": 3.7918,
"step": 398336
},
{
"epoch": 0.01,
"learning_rate": 4.347008214952799e-05,
"loss": 3.7884,
"step": 398848
},
{
"epoch": 0.01,
"learning_rate": 4.346169620201748e-05,
"loss": 3.7738,
"step": 399360
},
{
"epoch": 0.01,
"learning_rate": 4.345332663331069e-05,
"loss": 3.7852,
"step": 399872
},
{
"epoch": 0.01,
"learning_rate": 4.344494068580017e-05,
"loss": 3.7791,
"step": 400384
},
{
"epoch": 0.01,
"learning_rate": 4.343655473828965e-05,
"loss": 3.7701,
"step": 400896
},
{
"epoch": 0.01,
"learning_rate": 4.342816879077913e-05,
"loss": 3.7739,
"step": 401408
},
{
"epoch": 0.01,
"learning_rate": 4.341979922207234e-05,
"loss": 3.7726,
"step": 401920
},
{
"epoch": 0.01,
"learning_rate": 4.341141327456182e-05,
"loss": 3.7745,
"step": 402432
},
{
"epoch": 0.01,
"learning_rate": 4.34030273270513e-05,
"loss": 3.7878,
"step": 402944
},
{
"epoch": 0.01,
"learning_rate": 4.339464137954078e-05,
"loss": 3.7785,
"step": 403456
},
{
"epoch": 0.01,
"learning_rate": 4.338627181083399e-05,
"loss": 3.776,
"step": 403968
},
{
"epoch": 0.01,
"learning_rate": 4.337788586332347e-05,
"loss": 3.7826,
"step": 404480
},
{
"epoch": 0.01,
"learning_rate": 4.336949991581295e-05,
"loss": 3.7777,
"step": 404992
},
{
"epoch": 0.01,
"learning_rate": 4.3361113968302434e-05,
"loss": 3.7786,
"step": 405504
},
{
"epoch": 0.01,
"learning_rate": 4.335274439959564e-05,
"loss": 3.7686,
"step": 406016
},
{
"epoch": 0.01,
"learning_rate": 4.334435845208512e-05,
"loss": 3.7563,
"step": 406528
},
{
"epoch": 0.01,
"learning_rate": 4.33359725045746e-05,
"loss": 3.7842,
"step": 407040
},
{
"epoch": 0.01,
"learning_rate": 4.332758655706408e-05,
"loss": 3.7761,
"step": 407552
},
{
"epoch": 0.01,
"learning_rate": 4.331921698835729e-05,
"loss": 3.7706,
"step": 408064
},
{
"epoch": 0.01,
"learning_rate": 4.331083104084677e-05,
"loss": 3.7692,
"step": 408576
},
{
"epoch": 0.01,
"learning_rate": 4.330244509333625e-05,
"loss": 3.7747,
"step": 409088
},
{
"epoch": 0.01,
"learning_rate": 4.329405914582573e-05,
"loss": 3.7585,
"step": 409600
},
{
"epoch": 0.01,
"learning_rate": 4.328567319831521e-05,
"loss": 3.7735,
"step": 410112
},
{
"epoch": 0.01,
"learning_rate": 4.327730362960842e-05,
"loss": 3.774,
"step": 410624
},
{
"epoch": 0.01,
"learning_rate": 4.32689176820979e-05,
"loss": 3.7755,
"step": 411136
},
{
"epoch": 0.01,
"learning_rate": 4.326053173458739e-05,
"loss": 3.7691,
"step": 411648
},
{
"epoch": 0.01,
"learning_rate": 4.325214578707687e-05,
"loss": 3.7717,
"step": 412160
},
{
"epoch": 0.01,
"learning_rate": 4.3243776218370076e-05,
"loss": 3.7629,
"step": 412672
},
{
"epoch": 0.01,
"learning_rate": 4.3235390270859556e-05,
"loss": 3.7754,
"step": 413184
},
{
"epoch": 0.01,
"learning_rate": 4.3227004323349036e-05,
"loss": 3.759,
"step": 413696
},
{
"epoch": 0.01,
"learning_rate": 4.3218618375838516e-05,
"loss": 3.7632,
"step": 414208
},
{
"epoch": 0.01,
"learning_rate": 4.3210248807131725e-05,
"loss": 3.7777,
"step": 414720
},
{
"epoch": 0.01,
"learning_rate": 4.3201862859621205e-05,
"loss": 3.7681,
"step": 415232
},
{
"epoch": 0.01,
"learning_rate": 4.3193476912110685e-05,
"loss": 3.7633,
"step": 415744
},
{
"epoch": 0.01,
"learning_rate": 4.3185090964600165e-05,
"loss": 3.7595,
"step": 416256
},
{
"epoch": 0.01,
"learning_rate": 4.3176721395893374e-05,
"loss": 3.7632,
"step": 416768
},
{
"epoch": 0.01,
"learning_rate": 4.3168335448382854e-05,
"loss": 3.7725,
"step": 417280
},
{
"epoch": 0.01,
"learning_rate": 4.315994950087234e-05,
"loss": 3.7775,
"step": 417792
},
{
"epoch": 0.01,
"learning_rate": 4.315156355336182e-05,
"loss": 3.7688,
"step": 418304
},
{
"epoch": 0.01,
"learning_rate": 4.314319398465503e-05,
"loss": 3.7802,
"step": 418816
},
{
"epoch": 0.01,
"learning_rate": 4.313480803714451e-05,
"loss": 3.7765,
"step": 419328
},
{
"epoch": 0.01,
"learning_rate": 4.312642208963399e-05,
"loss": 3.7741,
"step": 419840
},
{
"epoch": 0.01,
"learning_rate": 4.311803614212347e-05,
"loss": 3.7659,
"step": 420352
},
{
"epoch": 0.01,
"learning_rate": 4.310966657341668e-05,
"loss": 3.7678,
"step": 420864
},
{
"epoch": 0.01,
"learning_rate": 4.310128062590616e-05,
"loss": 3.7633,
"step": 421376
},
{
"epoch": 0.01,
"learning_rate": 4.309289467839564e-05,
"loss": 3.7585,
"step": 421888
},
{
"epoch": 0.01,
"learning_rate": 4.308450873088512e-05,
"loss": 3.7718,
"step": 422400
},
{
"epoch": 0.01,
"learning_rate": 4.307613916217833e-05,
"loss": 3.7628,
"step": 422912
},
{
"epoch": 0.01,
"learning_rate": 4.306775321466781e-05,
"loss": 3.7758,
"step": 423424
},
{
"epoch": 0.01,
"learning_rate": 4.305936726715729e-05,
"loss": 3.7789,
"step": 423936
},
{
"epoch": 0.01,
"learning_rate": 4.3050981319646775e-05,
"loss": 3.7497,
"step": 424448
},
{
"epoch": 0.01,
"learning_rate": 4.3042611750939984e-05,
"loss": 3.771,
"step": 424960
},
{
"epoch": 0.01,
"learning_rate": 4.3034225803429464e-05,
"loss": 3.7636,
"step": 425472
},
{
"epoch": 0.01,
"learning_rate": 4.3025839855918944e-05,
"loss": 3.7704,
"step": 425984
},
{
"epoch": 0.01,
"learning_rate": 4.3017453908408424e-05,
"loss": 3.7634,
"step": 426496
},
{
"epoch": 0.01,
"learning_rate": 4.300908433970163e-05,
"loss": 3.7555,
"step": 427008
},
{
"epoch": 0.02,
"learning_rate": 4.300069839219111e-05,
"loss": 3.7649,
"step": 427520
},
{
"epoch": 0.02,
"learning_rate": 4.299231244468059e-05,
"loss": 3.761,
"step": 428032
},
{
"epoch": 0.02,
"learning_rate": 4.298392649717007e-05,
"loss": 3.7638,
"step": 428544
},
{
"epoch": 0.02,
"learning_rate": 4.297555692846328e-05,
"loss": 3.7585,
"step": 429056
},
{
"epoch": 0.02,
"learning_rate": 4.296717098095276e-05,
"loss": 3.7683,
"step": 429568
},
{
"epoch": 0.02,
"learning_rate": 4.295878503344224e-05,
"loss": 3.7677,
"step": 430080
},
{
"epoch": 0.02,
"learning_rate": 4.295039908593173e-05,
"loss": 3.7651,
"step": 430592
},
{
"epoch": 0.02,
"learning_rate": 4.294202951722494e-05,
"loss": 3.7507,
"step": 431104
},
{
"epoch": 0.02,
"learning_rate": 4.293364356971442e-05,
"loss": 3.7644,
"step": 431616
},
{
"epoch": 0.02,
"learning_rate": 4.29252576222039e-05,
"loss": 3.7651,
"step": 432128
},
{
"epoch": 0.02,
"learning_rate": 4.291687167469338e-05,
"loss": 3.7697,
"step": 432640
},
{
"epoch": 0.02,
"learning_rate": 4.2908502105986586e-05,
"loss": 3.757,
"step": 433152
},
{
"epoch": 0.02,
"learning_rate": 4.2900116158476066e-05,
"loss": 3.7618,
"step": 433664
},
{
"epoch": 0.02,
"learning_rate": 4.2891730210965546e-05,
"loss": 3.7563,
"step": 434176
},
{
"epoch": 0.02,
"learning_rate": 4.2883344263455026e-05,
"loss": 3.7673,
"step": 434688
},
{
"epoch": 0.02,
"learning_rate": 4.2874974694748235e-05,
"loss": 3.7517,
"step": 435200
},
{
"epoch": 0.02,
"learning_rate": 4.2866588747237715e-05,
"loss": 3.7564,
"step": 435712
},
{
"epoch": 0.02,
"learning_rate": 4.2858202799727195e-05,
"loss": 3.7598,
"step": 436224
},
{
"epoch": 0.02,
"learning_rate": 4.284981685221668e-05,
"loss": 3.7582,
"step": 436736
},
{
"epoch": 0.02,
"learning_rate": 4.284144728350989e-05,
"loss": 3.7478,
"step": 437248
},
{
"epoch": 0.02,
"learning_rate": 4.283306133599937e-05,
"loss": 3.7549,
"step": 437760
},
{
"epoch": 0.02,
"learning_rate": 4.282467538848885e-05,
"loss": 3.7513,
"step": 438272
},
{
"epoch": 0.02,
"learning_rate": 4.281628944097833e-05,
"loss": 3.7612,
"step": 438784
},
{
"epoch": 0.02,
"learning_rate": 4.280791987227154e-05,
"loss": 3.7596,
"step": 439296
},
{
"epoch": 0.02,
"learning_rate": 4.279953392476102e-05,
"loss": 3.7511,
"step": 439808
},
{
"epoch": 0.02,
"learning_rate": 4.27911479772505e-05,
"loss": 3.7621,
"step": 440320
},
{
"epoch": 0.02,
"learning_rate": 4.278276202973998e-05,
"loss": 3.7737,
"step": 440832
},
{
"epoch": 0.02,
"learning_rate": 4.277439246103319e-05,
"loss": 3.7661,
"step": 441344
},
{
"epoch": 0.02,
"learning_rate": 4.276600651352267e-05,
"loss": 3.7488,
"step": 441856
},
{
"epoch": 0.02,
"learning_rate": 4.275762056601215e-05,
"loss": 3.7578,
"step": 442368
},
{
"epoch": 0.02,
"learning_rate": 4.2749234618501636e-05,
"loss": 3.7541,
"step": 442880
},
{
"epoch": 0.02,
"learning_rate": 4.2740865049794845e-05,
"loss": 3.7516,
"step": 443392
},
{
"epoch": 0.02,
"learning_rate": 4.2732479102284325e-05,
"loss": 3.7547,
"step": 443904
},
{
"epoch": 0.02,
"learning_rate": 4.2724093154773805e-05,
"loss": 3.7471,
"step": 444416
},
{
"epoch": 0.02,
"learning_rate": 4.2715707207263285e-05,
"loss": 3.7606,
"step": 444928
},
{
"epoch": 0.02,
"learning_rate": 4.2707337638556494e-05,
"loss": 3.7538,
"step": 445440
},
{
"epoch": 0.02,
"learning_rate": 4.2698951691045974e-05,
"loss": 3.7648,
"step": 445952
},
{
"epoch": 0.02,
"learning_rate": 4.2690565743535454e-05,
"loss": 3.7529,
"step": 446464
},
{
"epoch": 0.02,
"learning_rate": 4.268219617482866e-05,
"loss": 3.7508,
"step": 446976
},
{
"epoch": 0.02,
"learning_rate": 4.267381022731814e-05,
"loss": 3.7598,
"step": 447488
},
{
"epoch": 0.02,
"learning_rate": 4.266542427980762e-05,
"loss": 3.7639,
"step": 448000
},
{
"epoch": 0.02,
"learning_rate": 4.26570383322971e-05,
"loss": 3.7544,
"step": 448512
},
{
"epoch": 0.02,
"learning_rate": 4.264866876359032e-05,
"loss": 3.7595,
"step": 449024
},
{
"epoch": 0.02,
"learning_rate": 4.26402828160798e-05,
"loss": 3.7474,
"step": 449536
},
{
"epoch": 0.02,
"learning_rate": 4.263189686856928e-05,
"loss": 3.7633,
"step": 450048
},
{
"epoch": 0.02,
"learning_rate": 4.262351092105876e-05,
"loss": 3.7548,
"step": 450560
},
{
"epoch": 0.02,
"learning_rate": 4.261514135235197e-05,
"loss": 3.764,
"step": 451072
},
{
"epoch": 0.02,
"learning_rate": 4.260675540484145e-05,
"loss": 3.7507,
"step": 451584
},
{
"epoch": 0.02,
"learning_rate": 4.259836945733093e-05,
"loss": 3.7615,
"step": 452096
},
{
"epoch": 0.02,
"learning_rate": 4.25899835098204e-05,
"loss": 3.7521,
"step": 452608
},
{
"epoch": 0.02,
"learning_rate": 4.258159756230988e-05,
"loss": 3.7765,
"step": 453120
},
{
"epoch": 0.02,
"learning_rate": 4.2573227993603096e-05,
"loss": 3.7454,
"step": 453632
},
{
"epoch": 0.02,
"learning_rate": 4.2564842046092576e-05,
"loss": 3.7611,
"step": 454144
},
{
"epoch": 0.02,
"learning_rate": 4.2556456098582056e-05,
"loss": 3.7512,
"step": 454656
},
{
"epoch": 0.02,
"learning_rate": 4.254808652987527e-05,
"loss": 3.7498,
"step": 455168
},
{
"epoch": 0.02,
"learning_rate": 4.253971696116848e-05,
"loss": 3.7603,
"step": 455680
},
{
"epoch": 0.02,
"learning_rate": 4.253133101365796e-05,
"loss": 3.7562,
"step": 456192
},
{
"epoch": 0.02,
"learning_rate": 4.252294506614744e-05,
"loss": 3.758,
"step": 456704
},
{
"epoch": 0.02,
"learning_rate": 4.251455911863692e-05,
"loss": 3.7454,
"step": 457216
},
{
"epoch": 0.02,
"learning_rate": 4.25061731711264e-05,
"loss": 3.7556,
"step": 457728
},
{
"epoch": 0.03,
"eval_loss": 3.87576961517334,
"eval_runtime": 307.2195,
"eval_samples_per_second": 1242.079,
"eval_steps_per_second": 38.816,
"step": 457920
},
{
"epoch": 1.0,
"learning_rate": 4.2497787223615874e-05,
"loss": 3.7464,
"step": 458240
},
{
"epoch": 1.0,
"learning_rate": 4.2489401276105354e-05,
"loss": 3.7408,
"step": 458752
},
{
"epoch": 1.0,
"learning_rate": 4.2481015328594834e-05,
"loss": 3.7496,
"step": 459264
},
{
"epoch": 1.0,
"learning_rate": 4.247264575988805e-05,
"loss": 3.7545,
"step": 459776
},
{
"epoch": 1.0,
"learning_rate": 4.246425981237753e-05,
"loss": 3.7611,
"step": 460288
},
{
"epoch": 1.0,
"learning_rate": 4.245587386486701e-05,
"loss": 3.75,
"step": 460800
},
{
"epoch": 1.0,
"learning_rate": 4.244748791735649e-05,
"loss": 3.7412,
"step": 461312
},
{
"epoch": 1.0,
"learning_rate": 4.24391183486497e-05,
"loss": 3.7495,
"step": 461824
},
{
"epoch": 1.0,
"learning_rate": 4.243073240113918e-05,
"loss": 3.757,
"step": 462336
},
{
"epoch": 1.0,
"learning_rate": 4.242234645362866e-05,
"loss": 3.7472,
"step": 462848
},
{
"epoch": 1.0,
"learning_rate": 4.241396050611814e-05,
"loss": 3.7433,
"step": 463360
},
{
"epoch": 1.0,
"learning_rate": 4.240559093741135e-05,
"loss": 3.7435,
"step": 463872
},
{
"epoch": 1.0,
"learning_rate": 4.2397221368704564e-05,
"loss": 3.7489,
"step": 464384
},
{
"epoch": 1.0,
"learning_rate": 4.2388835421194044e-05,
"loss": 3.7401,
"step": 464896
},
{
"epoch": 1.0,
"learning_rate": 4.2380449473683524e-05,
"loss": 3.7485,
"step": 465408
},
{
"epoch": 1.0,
"learning_rate": 4.2372063526173004e-05,
"loss": 3.7349,
"step": 465920
},
{
"epoch": 1.0,
"learning_rate": 4.2363677578662484e-05,
"loss": 3.7339,
"step": 466432
},
{
"epoch": 1.0,
"learning_rate": 4.2355291631151963e-05,
"loss": 3.738,
"step": 466944
},
{
"epoch": 1.0,
"learning_rate": 4.2346905683641443e-05,
"loss": 3.734,
"step": 467456
},
{
"epoch": 1.0,
"learning_rate": 4.233851973613092e-05,
"loss": 3.7563,
"step": 467968
},
{
"epoch": 1.0,
"learning_rate": 4.233015016742413e-05,
"loss": 3.7488,
"step": 468480
},
{
"epoch": 1.0,
"learning_rate": 4.232176421991361e-05,
"loss": 3.7442,
"step": 468992
},
{
"epoch": 1.0,
"learning_rate": 4.231337827240309e-05,
"loss": 3.7401,
"step": 469504
},
{
"epoch": 1.0,
"learning_rate": 4.230499232489257e-05,
"loss": 3.7476,
"step": 470016
},
{
"epoch": 1.0,
"learning_rate": 4.229662275618578e-05,
"loss": 3.7368,
"step": 470528
},
{
"epoch": 1.0,
"learning_rate": 4.228823680867526e-05,
"loss": 3.7441,
"step": 471040
},
{
"epoch": 1.0,
"learning_rate": 4.227985086116474e-05,
"loss": 3.735,
"step": 471552
},
{
"epoch": 1.0,
"learning_rate": 4.227146491365422e-05,
"loss": 3.7423,
"step": 472064
},
{
"epoch": 1.0,
"learning_rate": 4.226309534494744e-05,
"loss": 3.7394,
"step": 472576
},
{
"epoch": 1.0,
"learning_rate": 4.225470939743692e-05,
"loss": 3.7344,
"step": 473088
},
{
"epoch": 1.01,
"learning_rate": 4.22463234499264e-05,
"loss": 3.745,
"step": 473600
},
{
"epoch": 1.01,
"learning_rate": 4.2237953881219606e-05,
"loss": 3.7464,
"step": 474112
},
{
"epoch": 1.01,
"learning_rate": 4.2229567933709086e-05,
"loss": 3.7441,
"step": 474624
},
{
"epoch": 1.01,
"learning_rate": 4.2221181986198566e-05,
"loss": 3.7484,
"step": 475136
},
{
"epoch": 1.01,
"learning_rate": 4.2212796038688046e-05,
"loss": 3.7332,
"step": 475648
},
{
"epoch": 1.01,
"learning_rate": 4.2204410091177526e-05,
"loss": 3.7484,
"step": 476160
},
{
"epoch": 1.01,
"learning_rate": 4.2196024143667006e-05,
"loss": 3.7365,
"step": 476672
},
{
"epoch": 1.01,
"learning_rate": 4.2187638196156486e-05,
"loss": 3.7306,
"step": 477184
},
{
"epoch": 1.01,
"learning_rate": 4.2179252248645966e-05,
"loss": 3.7337,
"step": 477696
},
{
"epoch": 1.01,
"learning_rate": 4.2170882679939175e-05,
"loss": 3.731,
"step": 478208
},
{
"epoch": 1.01,
"learning_rate": 4.2162496732428655e-05,
"loss": 3.7327,
"step": 478720
},
{
"epoch": 1.01,
"learning_rate": 4.2154110784918135e-05,
"loss": 3.7427,
"step": 479232
},
{
"epoch": 1.01,
"learning_rate": 4.214572483740762e-05,
"loss": 3.7376,
"step": 479744
},
{
"epoch": 1.01,
"learning_rate": 4.213735526870083e-05,
"loss": 3.7382,
"step": 480256
},
{
"epoch": 1.01,
"learning_rate": 4.212896932119031e-05,
"loss": 3.7409,
"step": 480768
},
{
"epoch": 1.01,
"learning_rate": 4.212058337367979e-05,
"loss": 3.7381,
"step": 481280
},
{
"epoch": 1.01,
"learning_rate": 4.2112213804973e-05,
"loss": 3.7383,
"step": 481792
},
{
"epoch": 1.01,
"learning_rate": 4.210382785746248e-05,
"loss": 3.7264,
"step": 482304
},
{
"epoch": 1.01,
"learning_rate": 4.209544190995196e-05,
"loss": 3.7156,
"step": 482816
},
{
"epoch": 1.01,
"learning_rate": 4.208705596244144e-05,
"loss": 3.7425,
"step": 483328
},
{
"epoch": 1.01,
"learning_rate": 4.207868639373465e-05,
"loss": 3.7404,
"step": 483840
},
{
"epoch": 1.01,
"learning_rate": 4.207030044622413e-05,
"loss": 3.7262,
"step": 484352
},
{
"epoch": 1.01,
"learning_rate": 4.206191449871361e-05,
"loss": 3.7343,
"step": 484864
},
{
"epoch": 1.01,
"learning_rate": 4.205352855120309e-05,
"loss": 3.7315,
"step": 485376
},
{
"epoch": 1.01,
"learning_rate": 4.2045158982496304e-05,
"loss": 3.7215,
"step": 485888
},
{
"epoch": 1.01,
"learning_rate": 4.2036773034985784e-05,
"loss": 3.7308,
"step": 486400
},
{
"epoch": 1.01,
"learning_rate": 4.2028387087475264e-05,
"loss": 3.7344,
"step": 486912
},
{
"epoch": 1.01,
"learning_rate": 4.2020001139964744e-05,
"loss": 3.7367,
"step": 487424
},
{
"epoch": 1.01,
"learning_rate": 4.2011631571257953e-05,
"loss": 3.7276,
"step": 487936
},
{
"epoch": 1.01,
"learning_rate": 4.200324562374743e-05,
"loss": 3.7339,
"step": 488448
},
{
"epoch": 1.01,
"learning_rate": 4.199485967623691e-05,
"loss": 3.7235,
"step": 488960
},
{
"epoch": 1.01,
"learning_rate": 4.198647372872639e-05,
"loss": 3.7369,
"step": 489472
},
{
"epoch": 1.01,
"learning_rate": 4.19781041600196e-05,
"loss": 3.7204,
"step": 489984
},
{
"epoch": 1.01,
"learning_rate": 4.196971821250908e-05,
"loss": 3.7236,
"step": 490496
},
{
"epoch": 1.01,
"learning_rate": 4.196133226499856e-05,
"loss": 3.7374,
"step": 491008
},
{
"epoch": 1.01,
"learning_rate": 4.195294631748804e-05,
"loss": 3.7295,
"step": 491520
},
{
"epoch": 1.01,
"learning_rate": 4.194457674878126e-05,
"loss": 3.7247,
"step": 492032
},
{
"epoch": 1.01,
"learning_rate": 4.193619080127074e-05,
"loss": 3.7218,
"step": 492544
},
{
"epoch": 1.01,
"learning_rate": 4.192780485376022e-05,
"loss": 3.7223,
"step": 493056
},
{
"epoch": 1.01,
"learning_rate": 4.19194189062497e-05,
"loss": 3.7284,
"step": 493568
},
{
"epoch": 1.01,
"learning_rate": 4.191104933754291e-05,
"loss": 3.7404,
"step": 494080
},
{
"epoch": 1.01,
"learning_rate": 4.190266339003239e-05,
"loss": 3.7289,
"step": 494592
},
{
"epoch": 1.01,
"learning_rate": 4.189427744252187e-05,
"loss": 3.7423,
"step": 495104
},
{
"epoch": 1.01,
"learning_rate": 4.188589149501135e-05,
"loss": 3.7351,
"step": 495616
},
{
"epoch": 1.01,
"learning_rate": 4.1877521926304556e-05,
"loss": 3.7375,
"step": 496128
},
{
"epoch": 1.01,
"learning_rate": 4.1869135978794036e-05,
"loss": 3.728,
"step": 496640
},
{
"epoch": 1.01,
"learning_rate": 4.1860750031283516e-05,
"loss": 3.7282,
"step": 497152
},
{
"epoch": 1.01,
"learning_rate": 4.1852364083772996e-05,
"loss": 3.7262,
"step": 497664
},
{
"epoch": 1.01,
"learning_rate": 4.184399451506621e-05,
"loss": 3.7166,
"step": 498176
},
{
"epoch": 1.01,
"learning_rate": 4.183560856755569e-05,
"loss": 3.7323,
"step": 498688
},
{
"epoch": 1.01,
"learning_rate": 4.182722262004517e-05,
"loss": 3.7261,
"step": 499200
},
{
"epoch": 1.01,
"learning_rate": 4.181883667253465e-05,
"loss": 3.7378,
"step": 499712
},
{
"epoch": 1.01,
"learning_rate": 4.181046710382786e-05,
"loss": 3.7387,
"step": 500224
},
{
"epoch": 1.01,
"learning_rate": 4.180208115631734e-05,
"loss": 3.7106,
"step": 500736
},
{
"epoch": 1.01,
"learning_rate": 4.179369520880682e-05,
"loss": 3.7348,
"step": 501248
},
{
"epoch": 1.01,
"learning_rate": 4.17853092612963e-05,
"loss": 3.7257,
"step": 501760
},
{
"epoch": 1.01,
"learning_rate": 4.177693969258951e-05,
"loss": 3.7308,
"step": 502272
},
{
"epoch": 1.01,
"learning_rate": 4.176855374507899e-05,
"loss": 3.7231,
"step": 502784
},
{
"epoch": 1.01,
"learning_rate": 4.176016779756847e-05,
"loss": 3.718,
"step": 503296
},
{
"epoch": 1.02,
"learning_rate": 4.175178185005795e-05,
"loss": 3.7278,
"step": 503808
},
{
"epoch": 1.02,
"learning_rate": 4.1743412281351165e-05,
"loss": 3.7194,
"step": 504320
},
{
"epoch": 1.02,
"learning_rate": 4.1735026333840645e-05,
"loss": 3.7229,
"step": 504832
},
{
"epoch": 1.02,
"learning_rate": 4.1726640386330125e-05,
"loss": 3.7228,
"step": 505344
},
{
"epoch": 1.02,
"learning_rate": 4.1718254438819605e-05,
"loss": 3.7305,
"step": 505856
},
{
"epoch": 1.02,
"learning_rate": 4.1709884870112814e-05,
"loss": 3.7339,
"step": 506368
},
{
"epoch": 1.02,
"learning_rate": 4.1701498922602294e-05,
"loss": 3.7204,
"step": 506880
},
{
"epoch": 1.02,
"learning_rate": 4.1693112975091774e-05,
"loss": 3.7169,
"step": 507392
},
{
"epoch": 1.02,
"learning_rate": 4.168472702758125e-05,
"loss": 3.7228,
"step": 507904
},
{
"epoch": 1.02,
"learning_rate": 4.167635745887446e-05,
"loss": 3.7248,
"step": 508416
},
{
"epoch": 1.02,
"learning_rate": 4.166797151136394e-05,
"loss": 3.7336,
"step": 508928
},
{
"epoch": 1.02,
"learning_rate": 4.165958556385342e-05,
"loss": 3.7204,
"step": 509440
},
{
"epoch": 1.02,
"learning_rate": 4.16511996163429e-05,
"loss": 3.7244,
"step": 509952
},
{
"epoch": 1.02,
"learning_rate": 4.164283004763612e-05,
"loss": 3.7212,
"step": 510464
},
{
"epoch": 1.02,
"learning_rate": 4.16344441001256e-05,
"loss": 3.7306,
"step": 510976
},
{
"epoch": 1.02,
"learning_rate": 4.162605815261508e-05,
"loss": 3.7104,
"step": 511488
},
{
"epoch": 1.02,
"learning_rate": 4.161768858390829e-05,
"loss": 3.7208,
"step": 512000
},
{
"epoch": 1.02,
"learning_rate": 4.160930263639777e-05,
"loss": 3.7214,
"step": 512512
},
{
"epoch": 1.02,
"learning_rate": 4.160091668888725e-05,
"loss": 3.7217,
"step": 513024
},
{
"epoch": 1.02,
"learning_rate": 4.159253074137672e-05,
"loss": 3.7111,
"step": 513536
},
{
"epoch": 1.02,
"learning_rate": 4.158416117266994e-05,
"loss": 3.7178,
"step": 514048
},
{
"epoch": 1.02,
"learning_rate": 4.157577522515942e-05,
"loss": 3.7119,
"step": 514560
},
{
"epoch": 1.02,
"learning_rate": 4.15673892776489e-05,
"loss": 3.7249,
"step": 515072
},
{
"epoch": 1.02,
"learning_rate": 4.155900333013838e-05,
"loss": 3.7228,
"step": 515584
},
{
"epoch": 1.02,
"learning_rate": 4.155063376143159e-05,
"loss": 3.7163,
"step": 516096
},
{
"epoch": 1.02,
"learning_rate": 4.154224781392107e-05,
"loss": 3.7211,
"step": 516608
},
{
"epoch": 1.02,
"learning_rate": 4.153386186641055e-05,
"loss": 3.7352,
"step": 517120
},
{
"epoch": 1.02,
"learning_rate": 4.1525475918900026e-05,
"loss": 3.7337,
"step": 517632
},
{
"epoch": 1.02,
"learning_rate": 4.151710635019324e-05,
"loss": 3.7122,
"step": 518144
},
{
"epoch": 1.02,
"learning_rate": 4.150872040268272e-05,
"loss": 3.7192,
"step": 518656
},
{
"epoch": 1.02,
"learning_rate": 4.1500334455172195e-05,
"loss": 3.7197,
"step": 519168
},
{
"epoch": 1.02,
"learning_rate": 4.1491948507661675e-05,
"loss": 3.7112,
"step": 519680
},
{
"epoch": 1.02,
"learning_rate": 4.148357893895489e-05,
"loss": 3.7222,
"step": 520192
},
{
"epoch": 1.02,
"learning_rate": 4.147519299144437e-05,
"loss": 3.7055,
"step": 520704
},
{
"epoch": 1.02,
"learning_rate": 4.146680704393385e-05,
"loss": 3.7286,
"step": 521216
},
{
"epoch": 1.02,
"learning_rate": 4.145842109642333e-05,
"loss": 3.7136,
"step": 521728
},
{
"epoch": 1.02,
"learning_rate": 4.1450051527716546e-05,
"loss": 3.7283,
"step": 522240
},
{
"epoch": 1.02,
"learning_rate": 4.1441665580206026e-05,
"loss": 3.7169,
"step": 522752
},
{
"epoch": 1.02,
"learning_rate": 4.14332796326955e-05,
"loss": 3.7168,
"step": 523264
},
{
"epoch": 1.02,
"learning_rate": 4.142489368518498e-05,
"loss": 3.7197,
"step": 523776
},
{
"epoch": 1.02,
"learning_rate": 4.1416524116478195e-05,
"loss": 3.7284,
"step": 524288
},
{
"epoch": 1.02,
"learning_rate": 4.140813816896767e-05,
"loss": 3.7164,
"step": 524800
},
{
"epoch": 1.02,
"learning_rate": 4.139975222145715e-05,
"loss": 3.7233,
"step": 525312
},
{
"epoch": 1.02,
"learning_rate": 4.139136627394663e-05,
"loss": 3.7099,
"step": 525824
},
{
"epoch": 1.02,
"learning_rate": 4.1382996705239844e-05,
"loss": 3.7281,
"step": 526336
},
{
"epoch": 1.02,
"learning_rate": 4.137461075772932e-05,
"loss": 3.7182,
"step": 526848
},
{
"epoch": 1.02,
"learning_rate": 4.1366224810218804e-05,
"loss": 3.7236,
"step": 527360
},
{
"epoch": 1.02,
"learning_rate": 4.1357838862708284e-05,
"loss": 3.7184,
"step": 527872
},
{
"epoch": 1.02,
"learning_rate": 4.13494692940015e-05,
"loss": 3.725,
"step": 528384
},
{
"epoch": 1.02,
"learning_rate": 4.134108334649097e-05,
"loss": 3.7185,
"step": 528896
},
{
"epoch": 1.02,
"learning_rate": 4.133269739898045e-05,
"loss": 3.7382,
"step": 529408
},
{
"epoch": 1.02,
"learning_rate": 4.132431145146993e-05,
"loss": 3.7107,
"step": 529920
},
{
"epoch": 1.02,
"learning_rate": 4.131594188276314e-05,
"loss": 3.7225,
"step": 530432
},
{
"epoch": 1.02,
"learning_rate": 4.130755593525262e-05,
"loss": 3.7165,
"step": 530944
},
{
"epoch": 1.02,
"learning_rate": 4.12991699877421e-05,
"loss": 3.719,
"step": 531456
},
{
"epoch": 1.02,
"learning_rate": 4.129080041903532e-05,
"loss": 3.7174,
"step": 531968
},
{
"epoch": 1.02,
"learning_rate": 4.128241447152479e-05,
"loss": 3.7212,
"step": 532480
},
{
"epoch": 1.02,
"learning_rate": 4.127402852401427e-05,
"loss": 3.7219,
"step": 532992
},
{
"epoch": 1.02,
"learning_rate": 4.126564257650376e-05,
"loss": 3.7111,
"step": 533504
},
{
"epoch": 1.02,
"learning_rate": 4.125725662899324e-05,
"loss": 3.7234,
"step": 534016
},
{
"epoch": 1.03,
"eval_loss": 3.8647122383117676,
"eval_runtime": 305.1376,
"eval_samples_per_second": 1250.554,
"eval_steps_per_second": 39.081,
"step": 534240
},
{
"epoch": 0.0,
"learning_rate": 4.124887068148272e-05,
"loss": 3.7101,
"step": 534528
},
{
"epoch": 0.0,
"learning_rate": 4.12404847339722e-05,
"loss": 3.706,
"step": 535040
},
{
"epoch": 0.0,
"learning_rate": 4.123209878646168e-05,
"loss": 3.7138,
"step": 535552
},
{
"epoch": 0.0,
"learning_rate": 4.122371283895116e-05,
"loss": 3.7157,
"step": 536064
},
{
"epoch": 0.0,
"learning_rate": 4.121532689144064e-05,
"loss": 3.7262,
"step": 536576
},
{
"epoch": 0.0,
"learning_rate": 4.120694094393012e-05,
"loss": 3.7189,
"step": 537088
},
{
"epoch": 0.0,
"learning_rate": 4.11985549964196e-05,
"loss": 3.709,
"step": 537600
},
{
"epoch": 0.0,
"learning_rate": 4.119016904890908e-05,
"loss": 3.7108,
"step": 538112
},
{
"epoch": 0.0,
"learning_rate": 4.118179948020229e-05,
"loss": 3.7227,
"step": 538624
},
{
"epoch": 0.0,
"learning_rate": 4.117341353269177e-05,
"loss": 3.7132,
"step": 539136
},
{
"epoch": 0.0,
"learning_rate": 4.1165027585181247e-05,
"loss": 3.7072,
"step": 539648
},
{
"epoch": 0.0,
"learning_rate": 4.1156641637670727e-05,
"loss": 3.708,
"step": 540160
},
{
"epoch": 0.0,
"learning_rate": 4.114828844776767e-05,
"loss": 3.7122,
"step": 540672
},
{
"epoch": 0.0,
"learning_rate": 4.113990250025715e-05,
"loss": 3.7052,
"step": 541184
},
{
"epoch": 0.0,
"learning_rate": 4.113151655274663e-05,
"loss": 3.713,
"step": 541696
},
{
"epoch": 0.0,
"learning_rate": 4.112313060523611e-05,
"loss": 3.6983,
"step": 542208
},
{
"epoch": 0.0,
"learning_rate": 4.111476103652932e-05,
"loss": 3.701,
"step": 542720
},
{
"epoch": 0.0,
"learning_rate": 4.11063750890188e-05,
"loss": 3.7048,
"step": 543232
},
{
"epoch": 0.0,
"learning_rate": 4.109798914150828e-05,
"loss": 3.7001,
"step": 543744
},
{
"epoch": 0.0,
"learning_rate": 4.108960319399776e-05,
"loss": 3.7193,
"step": 544256
},
{
"epoch": 0.0,
"learning_rate": 4.108121724648724e-05,
"loss": 3.7155,
"step": 544768
},
{
"epoch": 0.0,
"learning_rate": 4.107283129897672e-05,
"loss": 3.7084,
"step": 545280
},
{
"epoch": 0.0,
"learning_rate": 4.10644453514662e-05,
"loss": 3.7043,
"step": 545792
},
{
"epoch": 0.0,
"learning_rate": 4.105605940395568e-05,
"loss": 3.7134,
"step": 546304
},
{
"epoch": 0.0,
"learning_rate": 4.104768983524889e-05,
"loss": 3.7031,
"step": 546816
},
{
"epoch": 0.0,
"learning_rate": 4.1039303887738376e-05,
"loss": 3.7089,
"step": 547328
},
{
"epoch": 0.0,
"learning_rate": 4.1030917940227856e-05,
"loss": 3.6967,
"step": 547840
},
{
"epoch": 0.0,
"learning_rate": 4.102253199271733e-05,
"loss": 3.7122,
"step": 548352
},
{
"epoch": 0.0,
"learning_rate": 4.1014162424010545e-05,
"loss": 3.7089,
"step": 548864
},
{
"epoch": 0.0,
"learning_rate": 4.1005776476500025e-05,
"loss": 3.6976,
"step": 549376
},
{
"epoch": 0.01,
"learning_rate": 4.0997390528989505e-05,
"loss": 3.7098,
"step": 549888
},
{
"epoch": 0.01,
"learning_rate": 4.0989020960282714e-05,
"loss": 3.7124,
"step": 550400
},
{
"epoch": 0.01,
"learning_rate": 4.0980635012772194e-05,
"loss": 3.7073,
"step": 550912
},
{
"epoch": 0.01,
"learning_rate": 4.0972249065261674e-05,
"loss": 3.7168,
"step": 551424
},
{
"epoch": 0.01,
"learning_rate": 4.0963863117751154e-05,
"loss": 3.6987,
"step": 551936
},
{
"epoch": 0.01,
"learning_rate": 4.095547717024063e-05,
"loss": 3.7078,
"step": 552448
},
{
"epoch": 0.01,
"learning_rate": 4.0947091222730114e-05,
"loss": 3.7034,
"step": 552960
},
{
"epoch": 0.01,
"learning_rate": 4.0938705275219594e-05,
"loss": 3.6983,
"step": 553472
},
{
"epoch": 0.01,
"learning_rate": 4.0930319327709074e-05,
"loss": 3.6986,
"step": 553984
},
{
"epoch": 0.01,
"learning_rate": 4.092194975900228e-05,
"loss": 3.6979,
"step": 554496
},
{
"epoch": 0.01,
"learning_rate": 4.091356381149176e-05,
"loss": 3.697,
"step": 555008
},
{
"epoch": 0.01,
"learning_rate": 4.090517786398124e-05,
"loss": 3.7087,
"step": 555520
},
{
"epoch": 0.01,
"learning_rate": 4.089679191647072e-05,
"loss": 3.7042,
"step": 556032
},
{
"epoch": 0.01,
"learning_rate": 4.088842234776393e-05,
"loss": 3.7039,
"step": 556544
},
{
"epoch": 0.01,
"learning_rate": 4.088003640025341e-05,
"loss": 3.7079,
"step": 557056
},
{
"epoch": 0.01,
"learning_rate": 4.087165045274289e-05,
"loss": 3.7007,
"step": 557568
},
{
"epoch": 0.01,
"learning_rate": 4.08632808840361e-05,
"loss": 3.7032,
"step": 558080
},
{
"epoch": 0.01,
"learning_rate": 4.085489493652558e-05,
"loss": 3.6968,
"step": 558592
},
{
"epoch": 0.01,
"learning_rate": 4.084650898901507e-05,
"loss": 3.6762,
"step": 559104
},
{
"epoch": 0.01,
"learning_rate": 4.083812304150455e-05,
"loss": 3.714,
"step": 559616
},
{
"epoch": 0.01,
"learning_rate": 4.0829753472797757e-05,
"loss": 3.7002,
"step": 560128
},
{
"epoch": 0.01,
"learning_rate": 4.0821367525287237e-05,
"loss": 3.699,
"step": 560640
},
{
"epoch": 0.01,
"learning_rate": 4.0812981577776716e-05,
"loss": 3.6985,
"step": 561152
},
{
"epoch": 0.01,
"learning_rate": 4.0804612009069926e-05,
"loss": 3.6989,
"step": 561664
},
{
"epoch": 0.01,
"learning_rate": 4.0796226061559406e-05,
"loss": 3.6877,
"step": 562176
},
{
"epoch": 0.01,
"learning_rate": 4.0787840114048885e-05,
"loss": 3.6947,
"step": 562688
},
{
"epoch": 0.01,
"learning_rate": 4.0779454166538365e-05,
"loss": 3.7035,
"step": 563200
},
{
"epoch": 0.01,
"learning_rate": 4.0771068219027845e-05,
"loss": 3.7022,
"step": 563712
},
{
"epoch": 0.01,
"learning_rate": 4.0762682271517325e-05,
"loss": 3.7015,
"step": 564224
},
{
"epoch": 0.01,
"learning_rate": 4.0754296324006805e-05,
"loss": 3.693,
"step": 564736
},
{
"epoch": 0.01,
"learning_rate": 4.0745910376496285e-05,
"loss": 3.6898,
"step": 565248
},
{
"epoch": 0.01,
"learning_rate": 4.07375408077895e-05,
"loss": 3.7088,
"step": 565760
},
{
"epoch": 0.01,
"learning_rate": 4.072915486027898e-05,
"loss": 3.6837,
"step": 566272
},
{
"epoch": 0.01,
"learning_rate": 4.072076891276846e-05,
"loss": 3.6907,
"step": 566784
},
{
"epoch": 0.01,
"learning_rate": 4.071238296525794e-05,
"loss": 3.7017,
"step": 567296
},
{
"epoch": 0.01,
"learning_rate": 4.070401339655115e-05,
"loss": 3.6982,
"step": 567808
},
{
"epoch": 0.01,
"learning_rate": 4.069562744904063e-05,
"loss": 3.6908,
"step": 568320
},
{
"epoch": 0.01,
"learning_rate": 4.068724150153011e-05,
"loss": 3.6929,
"step": 568832
},
{
"epoch": 0.01,
"learning_rate": 4.067887193282332e-05,
"loss": 3.6864,
"step": 569344
},
{
"epoch": 0.01,
"learning_rate": 4.06704859853128e-05,
"loss": 3.6941,
"step": 569856
},
{
"epoch": 0.01,
"learning_rate": 4.066210003780228e-05,
"loss": 3.7092,
"step": 570368
},
{
"epoch": 0.01,
"learning_rate": 4.065371409029176e-05,
"loss": 3.6961,
"step": 570880
},
{
"epoch": 0.01,
"learning_rate": 4.0645344521584975e-05,
"loss": 3.7083,
"step": 571392
},
{
"epoch": 0.01,
"learning_rate": 4.0636958574074455e-05,
"loss": 3.7009,
"step": 571904
},
{
"epoch": 0.01,
"learning_rate": 4.0628572626563935e-05,
"loss": 3.7067,
"step": 572416
},
{
"epoch": 0.01,
"learning_rate": 4.0620186679053415e-05,
"loss": 3.6938,
"step": 572928
},
{
"epoch": 0.01,
"learning_rate": 4.0611817110346624e-05,
"loss": 3.6987,
"step": 573440
},
{
"epoch": 0.01,
"learning_rate": 4.0603431162836104e-05,
"loss": 3.6935,
"step": 573952
},
{
"epoch": 0.01,
"learning_rate": 4.0595045215325584e-05,
"loss": 3.6816,
"step": 574464
},
{
"epoch": 0.01,
"learning_rate": 4.0586659267815064e-05,
"loss": 3.7019,
"step": 574976
},
{
"epoch": 0.01,
"learning_rate": 4.057828969910827e-05,
"loss": 3.6943,
"step": 575488
},
{
"epoch": 0.01,
"learning_rate": 4.056990375159775e-05,
"loss": 3.7021,
"step": 576000
},
{
"epoch": 0.01,
"learning_rate": 4.056151780408723e-05,
"loss": 3.7073,
"step": 576512
},
{
"epoch": 0.01,
"learning_rate": 4.055313185657671e-05,
"loss": 3.6823,
"step": 577024
},
{
"epoch": 0.01,
"learning_rate": 4.054476228786993e-05,
"loss": 3.697,
"step": 577536
},
{
"epoch": 0.01,
"learning_rate": 4.053637634035941e-05,
"loss": 3.6914,
"step": 578048
},
{
"epoch": 0.01,
"learning_rate": 4.052799039284889e-05,
"loss": 3.6992,
"step": 578560
},
{
"epoch": 0.01,
"learning_rate": 4.051960444533837e-05,
"loss": 3.6913,
"step": 579072
},
{
"epoch": 0.01,
"learning_rate": 4.051123487663158e-05,
"loss": 3.688,
"step": 579584
},
{
"epoch": 0.02,
"learning_rate": 4.050284892912106e-05,
"loss": 3.6922,
"step": 580096
},
{
"epoch": 0.02,
"learning_rate": 4.049446298161054e-05,
"loss": 3.6894,
"step": 580608
},
{
"epoch": 0.02,
"learning_rate": 4.048607703410002e-05,
"loss": 3.6915,
"step": 581120
},
{
"epoch": 0.02,
"learning_rate": 4.0477707465393226e-05,
"loss": 3.6907,
"step": 581632
},
{
"epoch": 0.02,
"learning_rate": 4.0469321517882706e-05,
"loss": 3.7019,
"step": 582144
},
{
"epoch": 0.02,
"learning_rate": 4.0460935570372186e-05,
"loss": 3.6994,
"step": 582656
},
{
"epoch": 0.02,
"learning_rate": 4.0452549622861666e-05,
"loss": 3.6893,
"step": 583168
},
{
"epoch": 0.02,
"learning_rate": 4.0444180054154875e-05,
"loss": 3.6825,
"step": 583680
},
{
"epoch": 0.02,
"learning_rate": 4.043579410664436e-05,
"loss": 3.6908,
"step": 584192
},
{
"epoch": 0.02,
"learning_rate": 4.042740815913384e-05,
"loss": 3.6973,
"step": 584704
},
{
"epoch": 0.02,
"learning_rate": 4.041902221162332e-05,
"loss": 3.698,
"step": 585216
},
{
"epoch": 0.02,
"learning_rate": 4.041065264291653e-05,
"loss": 3.691,
"step": 585728
},
{
"epoch": 0.02,
"learning_rate": 4.040226669540601e-05,
"loss": 3.6906,
"step": 586240
},
{
"epoch": 0.02,
"learning_rate": 4.039388074789549e-05,
"loss": 3.6873,
"step": 586752
},
{
"epoch": 0.02,
"learning_rate": 4.038549480038497e-05,
"loss": 3.7026,
"step": 587264
},
{
"epoch": 0.02,
"learning_rate": 4.037712523167818e-05,
"loss": 3.6769,
"step": 587776
},
{
"epoch": 0.02,
"learning_rate": 4.036873928416766e-05,
"loss": 3.691,
"step": 588288
},
{
"epoch": 0.02,
"learning_rate": 4.036035333665714e-05,
"loss": 3.6855,
"step": 588800
},
{
"epoch": 0.02,
"learning_rate": 4.035196738914662e-05,
"loss": 3.6909,
"step": 589312
},
{
"epoch": 0.02,
"learning_rate": 4.0343614199243565e-05,
"loss": 3.6803,
"step": 589824
},
{
"epoch": 0.02,
"learning_rate": 4.0335228251733045e-05,
"loss": 3.6917,
"step": 590336
},
{
"epoch": 0.02,
"learning_rate": 4.0326842304222525e-05,
"loss": 3.6793,
"step": 590848
},
{
"epoch": 0.02,
"learning_rate": 4.0318456356712005e-05,
"loss": 3.6929,
"step": 591360
},
{
"epoch": 0.02,
"learning_rate": 4.0310070409201485e-05,
"loss": 3.6921,
"step": 591872
},
{
"epoch": 0.02,
"learning_rate": 4.0301684461690965e-05,
"loss": 3.6821,
"step": 592384
},
{
"epoch": 0.02,
"learning_rate": 4.0293298514180445e-05,
"loss": 3.6911,
"step": 592896
},
{
"epoch": 0.02,
"learning_rate": 4.0284912566669925e-05,
"loss": 3.7078,
"step": 593408
},
{
"epoch": 0.02,
"learning_rate": 4.0276542997963134e-05,
"loss": 3.6917,
"step": 593920
},
{
"epoch": 0.02,
"learning_rate": 4.0268157050452614e-05,
"loss": 3.6911,
"step": 594432
},
{
"epoch": 0.02,
"learning_rate": 4.0259771102942094e-05,
"loss": 3.6796,
"step": 594944
},
{
"epoch": 0.02,
"learning_rate": 4.0251385155431574e-05,
"loss": 3.6877,
"step": 595456
},
{
"epoch": 0.02,
"learning_rate": 4.024303196552852e-05,
"loss": 3.6885,
"step": 595968
},
{
"epoch": 0.02,
"learning_rate": 4.0234646018018e-05,
"loss": 3.6869,
"step": 596480
},
{
"epoch": 0.02,
"learning_rate": 4.022626007050748e-05,
"loss": 3.6742,
"step": 596992
},
{
"epoch": 0.02,
"learning_rate": 4.021787412299696e-05,
"loss": 3.6942,
"step": 597504
},
{
"epoch": 0.02,
"learning_rate": 4.020948817548644e-05,
"loss": 3.6852,
"step": 598016
},
{
"epoch": 0.02,
"learning_rate": 4.020110222797592e-05,
"loss": 3.6956,
"step": 598528
},
{
"epoch": 0.02,
"learning_rate": 4.01927162804654e-05,
"loss": 3.6852,
"step": 599040
},
{
"epoch": 0.02,
"learning_rate": 4.018433033295488e-05,
"loss": 3.6877,
"step": 599552
},
{
"epoch": 0.02,
"learning_rate": 4.017596076424809e-05,
"loss": 3.6845,
"step": 600064
},
{
"epoch": 0.02,
"learning_rate": 4.016757481673757e-05,
"loss": 3.7006,
"step": 600576
},
{
"epoch": 0.02,
"learning_rate": 4.015918886922705e-05,
"loss": 3.688,
"step": 601088
},
{
"epoch": 0.02,
"learning_rate": 4.015080292171653e-05,
"loss": 3.6924,
"step": 601600
},
{
"epoch": 0.02,
"learning_rate": 4.0142433353009736e-05,
"loss": 3.6763,
"step": 602112
},
{
"epoch": 0.02,
"learning_rate": 4.013406378430295e-05,
"loss": 3.6984,
"step": 602624
},
{
"epoch": 0.02,
"learning_rate": 4.012567783679243e-05,
"loss": 3.6885,
"step": 603136
},
{
"epoch": 0.02,
"learning_rate": 4.011729188928191e-05,
"loss": 3.6941,
"step": 603648
},
{
"epoch": 0.02,
"learning_rate": 4.010890594177139e-05,
"loss": 3.6877,
"step": 604160
},
{
"epoch": 0.02,
"learning_rate": 4.010051999426087e-05,
"loss": 3.6927,
"step": 604672
},
{
"epoch": 0.02,
"learning_rate": 4.009213404675035e-05,
"loss": 3.6826,
"step": 605184
},
{
"epoch": 0.02,
"learning_rate": 4.0083748099239825e-05,
"loss": 3.7073,
"step": 605696
},
{
"epoch": 0.02,
"learning_rate": 4.0075362151729305e-05,
"loss": 3.6819,
"step": 606208
},
{
"epoch": 0.02,
"learning_rate": 4.006699258302252e-05,
"loss": 3.6944,
"step": 606720
},
{
"epoch": 0.02,
"learning_rate": 4.0058606635512e-05,
"loss": 3.69,
"step": 607232
},
{
"epoch": 0.02,
"learning_rate": 4.005023706680521e-05,
"loss": 3.6847,
"step": 607744
},
{
"epoch": 0.02,
"learning_rate": 4.0041867498098426e-05,
"loss": 3.6829,
"step": 608256
},
{
"epoch": 0.02,
"learning_rate": 4.0033481550587906e-05,
"loss": 3.691,
"step": 608768
},
{
"epoch": 0.02,
"learning_rate": 4.0025095603077386e-05,
"loss": 3.6912,
"step": 609280
},
{
"epoch": 0.02,
"learning_rate": 4.0016709655566866e-05,
"loss": 3.6832,
"step": 609792
},
{
"epoch": 0.02,
"learning_rate": 4.0008323708056346e-05,
"loss": 3.6911,
"step": 610304
},
{
"epoch": 0.03,
"eval_loss": 3.8576157093048096,
"eval_runtime": 306.7702,
"eval_samples_per_second": 1243.899,
"eval_steps_per_second": 38.873,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.9999937760545826e-05,
"loss": 3.6793,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.99915518130353e-05,
"loss": 3.6758,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.998316586552478e-05,
"loss": 3.6805,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.997477991801426e-05,
"loss": 3.6881,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.996639397050374e-05,
"loss": 3.6957,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.995800802299322e-05,
"loss": 3.6834,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.994963845428643e-05,
"loss": 3.6836,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.9941252506775915e-05,
"loss": 3.6806,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.9932866559265395e-05,
"loss": 3.6884,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.9924480611754874e-05,
"loss": 3.6864,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.9916094664244354e-05,
"loss": 3.6753,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.9907708716733834e-05,
"loss": 3.6764,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.9899339148027044e-05,
"loss": 3.6874,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.9890953200516523e-05,
"loss": 3.6727,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.9882567253006003e-05,
"loss": 3.6769,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.987418130549548e-05,
"loss": 3.6705,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.986581173678869e-05,
"loss": 3.6695,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.985742578927817e-05,
"loss": 3.6773,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.984903984176765e-05,
"loss": 3.6675,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.984065389425713e-05,
"loss": 3.6875,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.983226794674661e-05,
"loss": 3.6849,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.98238819992361e-05,
"loss": 3.6822,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.981549605172558e-05,
"loss": 3.6747,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.980711010421506e-05,
"loss": 3.6781,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.979874053550827e-05,
"loss": 3.6763,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.979035458799775e-05,
"loss": 3.6781,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.978196864048723e-05,
"loss": 3.67,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.977358269297671e-05,
"loss": 3.6818,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.976521312426992e-05,
"loss": 3.6737,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.97568271767594e-05,
"loss": 3.6718,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.974844122924888e-05,
"loss": 3.6744,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.9740071660542086e-05,
"loss": 3.6861,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.9731685713031566e-05,
"loss": 3.6831,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.9723299765521046e-05,
"loss": 3.6868,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971491381801053e-05,
"loss": 3.6688,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.970652787050001e-05,
"loss": 3.6736,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.9698141922989486e-05,
"loss": 3.6807,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.9689755975478966e-05,
"loss": 3.6686,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.9681370027968446e-05,
"loss": 3.6677,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.967300045926166e-05,
"loss": 3.6679,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.9664614511751135e-05,
"loss": 3.6708,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.9656228564240615e-05,
"loss": 3.6732,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.9647842616730095e-05,
"loss": 3.6816,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.963947304802331e-05,
"loss": 3.6779,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.9631087100512784e-05,
"loss": 3.673,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.962270115300227e-05,
"loss": 3.6758,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.961431520549175e-05,
"loss": 3.6685,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.960594563678496e-05,
"loss": 3.6719,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.9597576068078175e-05,
"loss": 3.6437,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.9589190120567655e-05,
"loss": 3.6873,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.9580804173057135e-05,
"loss": 3.6701,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.957241822554661e-05,
"loss": 3.6767,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.956403227803609e-05,
"loss": 3.6698,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.9555662709329304e-05,
"loss": 3.6704,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.9547276761818784e-05,
"loss": 3.6588,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.953889081430826e-05,
"loss": 3.6627,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.953050486679774e-05,
"loss": 3.6758,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.9522118919287224e-05,
"loss": 3.67,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.9513732971776704e-05,
"loss": 3.6766,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.9505347024266184e-05,
"loss": 3.6661,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.9496961076755664e-05,
"loss": 3.6594,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.948859150804887e-05,
"loss": 3.6802,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.948020556053835e-05,
"loss": 3.6536,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.947181961302783e-05,
"loss": 3.6594,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.946345004432104e-05,
"loss": 3.6737,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.945506409681052e-05,
"loss": 3.6722,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.94466781493e-05,
"loss": 3.6567,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.943829220178948e-05,
"loss": 3.6688,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.942990625427896e-05,
"loss": 3.654,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.942152030676844e-05,
"loss": 3.6708,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.941313435925792e-05,
"loss": 3.6749,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.940474841174741e-05,
"loss": 3.6717,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.939637884304062e-05,
"loss": 3.6741,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.93879928955301e-05,
"loss": 3.6726,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.937960694801958e-05,
"loss": 3.6841,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.937122100050906e-05,
"loss": 3.6638,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.9362867810605996e-05,
"loss": 3.6725,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.9354481863095476e-05,
"loss": 3.6672,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.9346095915584956e-05,
"loss": 3.6483,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.9337709968074436e-05,
"loss": 3.6729,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.9329324020563916e-05,
"loss": 3.6697,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.9320938073053396e-05,
"loss": 3.673,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.9312552125542875e-05,
"loss": 3.6819,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.930416617803236e-05,
"loss": 3.6558,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.929579660932557e-05,
"loss": 3.6626,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.928741066181505e-05,
"loss": 3.6658,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.927902471430453e-05,
"loss": 3.6719,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.927063876679401e-05,
"loss": 3.658,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.926226919808722e-05,
"loss": 3.6651,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.92538832505767e-05,
"loss": 3.6619,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.924549730306618e-05,
"loss": 3.6624,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.923711135555566e-05,
"loss": 3.6598,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.922874178684887e-05,
"loss": 3.6656,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.922035583933835e-05,
"loss": 3.6734,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.921196989182783e-05,
"loss": 3.6649,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.9203583944317316e-05,
"loss": 3.6704,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.9195214375610525e-05,
"loss": 3.6525,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.9186828428100005e-05,
"loss": 3.6642,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.9178442480589485e-05,
"loss": 3.6678,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.9170056533078965e-05,
"loss": 3.6739,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.9161686964372174e-05,
"loss": 3.6614,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.9153301016861654e-05,
"loss": 3.6613,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.9144915069351134e-05,
"loss": 3.6652,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.9136529121840614e-05,
"loss": 3.6677,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.912815955313382e-05,
"loss": 3.6523,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.91197736056233e-05,
"loss": 3.6633,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.911138765811278e-05,
"loss": 3.6517,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.910300171060226e-05,
"loss": 3.671,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.909464852069921e-05,
"loss": 3.6536,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.908626257318869e-05,
"loss": 3.6604,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.907787662567817e-05,
"loss": 3.6524,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.906949067816765e-05,
"loss": 3.6651,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.906110473065713e-05,
"loss": 3.6654,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.905271878314661e-05,
"loss": 3.6554,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.904433283563609e-05,
"loss": 3.6613,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.903594688812556e-05,
"loss": 3.6763,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.9027577319418777e-05,
"loss": 3.668,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.9019191371908257e-05,
"loss": 3.6605,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.901082180320147e-05,
"loss": 3.6545,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.900243585569095e-05,
"loss": 3.6585,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.899404990818043e-05,
"loss": 3.6652,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.898566396066991e-05,
"loss": 3.6545,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.897727801315939e-05,
"loss": 3.6488,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.8968892065648865e-05,
"loss": 3.6667,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.8960506118138345e-05,
"loss": 3.6593,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.8952120170627825e-05,
"loss": 3.6672,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.8943750601921034e-05,
"loss": 3.6567,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.8935364654410514e-05,
"loss": 3.6597,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.892699508570373e-05,
"loss": 3.6567,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.891860913819321e-05,
"loss": 3.6717,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.891022319068269e-05,
"loss": 3.6636,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.890183724317217e-05,
"loss": 3.6634,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.8893467674465386e-05,
"loss": 3.65,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.8885081726954866e-05,
"loss": 3.6737,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.887669577944434e-05,
"loss": 3.6594,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.886830983193382e-05,
"loss": 3.6686,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.88599238844233e-05,
"loss": 3.6609,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.885153793691278e-05,
"loss": 3.6618,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884315198940226e-05,
"loss": 3.6607,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.883478242069547e-05,
"loss": 3.6779,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.882639647318495e-05,
"loss": 3.6565,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.881801052567443e-05,
"loss": 3.6673,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.880962457816391e-05,
"loss": 3.6614,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.8801255009457124e-05,
"loss": 3.6577,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.879288544075034e-05,
"loss": 3.6588,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.878449949323981e-05,
"loss": 3.6644,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.877611354572929e-05,
"loss": 3.6631,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.876772759821877e-05,
"loss": 3.6601,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.875934165070825e-05,
"loss": 3.6635,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 3.8523125648498535,
"eval_runtime": 302.663,
"eval_samples_per_second": 1260.778,
"eval_steps_per_second": 39.4,
"step": 686880
},
{
"epoch": 1.0,
"learning_rate": 3.875095570319773e-05,
"loss": 3.6483,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.874256975568721e-05,
"loss": 3.6469,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.873418380817669e-05,
"loss": 3.6538,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.872579786066617e-05,
"loss": 3.6636,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.871741191315565e-05,
"loss": 3.6713,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.870902596564513e-05,
"loss": 3.6576,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.870064001813461e-05,
"loss": 3.6576,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.869227044942783e-05,
"loss": 3.6549,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.868388450191731e-05,
"loss": 3.6585,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.867549855440679e-05,
"loss": 3.6662,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.866711260689627e-05,
"loss": 3.6459,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.865874303818948e-05,
"loss": 3.6491,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.8650373469482686e-05,
"loss": 3.6644,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.8641987521972166e-05,
"loss": 3.6464,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.8633601574461646e-05,
"loss": 3.6513,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.8625215626951126e-05,
"loss": 3.6441,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.8616829679440606e-05,
"loss": 3.6447,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.8608460110733815e-05,
"loss": 3.6471,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.86000741632233e-05,
"loss": 3.6435,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.859168821571278e-05,
"loss": 3.658,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.858330226820226e-05,
"loss": 3.6598,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.857493269949547e-05,
"loss": 3.6601,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.856654675198495e-05,
"loss": 3.6478,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.855816080447443e-05,
"loss": 3.651,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.854977485696391e-05,
"loss": 3.6535,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.854138890945339e-05,
"loss": 3.6491,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.853300296194287e-05,
"loss": 3.6456,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.8524617014432344e-05,
"loss": 3.6621,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.851624744572556e-05,
"loss": 3.6451,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.850786149821504e-05,
"loss": 3.6473,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.849947555070452e-05,
"loss": 3.6484,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.8491089603194e-05,
"loss": 3.6567,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.848270365568348e-05,
"loss": 3.6582,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.847431770817296e-05,
"loss": 3.6639,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.846593176066244e-05,
"loss": 3.6404,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.845754581315192e-05,
"loss": 3.6488,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.844917624444513e-05,
"loss": 3.657,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.844079029693461e-05,
"loss": 3.6367,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.843240434942409e-05,
"loss": 3.6451,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.842401840191357e-05,
"loss": 3.6453,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.841564883320678e-05,
"loss": 3.6436,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.840726288569626e-05,
"loss": 3.6477,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.839887693818574e-05,
"loss": 3.654,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.839050736947895e-05,
"loss": 3.6521,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.838212142196843e-05,
"loss": 3.6466,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.837373547445791e-05,
"loss": 3.6488,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.836534952694739e-05,
"loss": 3.646,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.835696357943687e-05,
"loss": 3.6451,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.834859401073008e-05,
"loss": 3.6169,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.834020806321956e-05,
"loss": 3.6611,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.833182211570904e-05,
"loss": 3.6435,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.832343616819852e-05,
"loss": 3.652,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.8315050220688e-05,
"loss": 3.6438,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.830668065198121e-05,
"loss": 3.6462,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.829829470447069e-05,
"loss": 3.6343,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.828990875696017e-05,
"loss": 3.6354,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.828152280944966e-05,
"loss": 3.6544,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.827315324074287e-05,
"loss": 3.639,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.826476729323235e-05,
"loss": 3.6513,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.825638134572183e-05,
"loss": 3.6453,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.824799539821131e-05,
"loss": 3.6302,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.8239625829504516e-05,
"loss": 3.6577,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.8231239881993996e-05,
"loss": 3.6309,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.8222853934483476e-05,
"loss": 3.6377,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.8214467986972956e-05,
"loss": 3.6496,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.8206082039462436e-05,
"loss": 3.6437,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.8197696091951916e-05,
"loss": 3.6317,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.8189310144441396e-05,
"loss": 3.6448,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.818094057573461e-05,
"loss": 3.6277,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.817255462822409e-05,
"loss": 3.6479,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.816416868071357e-05,
"loss": 3.6513,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.815578273320305e-05,
"loss": 3.6422,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.814739678569253e-05,
"loss": 3.6496,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.8139010838182004e-05,
"loss": 3.6479,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.8130624890671484e-05,
"loss": 3.6606,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.8122238943160964e-05,
"loss": 3.6381,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.811388575325791e-05,
"loss": 3.6452,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.810549980574739e-05,
"loss": 3.6475,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.809711385823687e-05,
"loss": 3.6203,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.808872791072635e-05,
"loss": 3.6473,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.808034196321583e-05,
"loss": 3.6475,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.8071972394509045e-05,
"loss": 3.6455,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.8063586446998525e-05,
"loss": 3.6565,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.8055200499488005e-05,
"loss": 3.6326,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.804681455197748e-05,
"loss": 3.6382,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.803842860446696e-05,
"loss": 3.6411,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.803004265695644e-05,
"loss": 3.646,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.8021673088249654e-05,
"loss": 3.6397,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.801328714073913e-05,
"loss": 3.6384,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.800490119322861e-05,
"loss": 3.6339,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.799651524571809e-05,
"loss": 3.64,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.798812929820757e-05,
"loss": 3.637,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.797974335069705e-05,
"loss": 3.6399,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.797137378199026e-05,
"loss": 3.6492,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.796298783447974e-05,
"loss": 3.6407,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.795460188696922e-05,
"loss": 3.6465,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.79462159394587e-05,
"loss": 3.6297,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.793784637075191e-05,
"loss": 3.636,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.792946042324139e-05,
"loss": 3.6401,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.792107447573087e-05,
"loss": 3.6479,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.791268852822035e-05,
"loss": 3.6375,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.790430258070983e-05,
"loss": 3.6374,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.789591663319931e-05,
"loss": 3.6421,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.788754706449252e-05,
"loss": 3.6418,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.7879161116982e-05,
"loss": 3.6273,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.787077516947149e-05,
"loss": 3.6426,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.786238922196097e-05,
"loss": 3.6266,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.785400327445045e-05,
"loss": 3.6466,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.7845633705743656e-05,
"loss": 3.6314,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.7837247758233136e-05,
"loss": 3.6327,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.7828861810722616e-05,
"loss": 3.6267,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.7820475863212096e-05,
"loss": 3.6451,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.7812089915701576e-05,
"loss": 3.6382,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.7803720346994785e-05,
"loss": 3.6326,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.7795334399484265e-05,
"loss": 3.6409,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.7786948451973745e-05,
"loss": 3.6508,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.7778562504463225e-05,
"loss": 3.6462,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.777019293575644e-05,
"loss": 3.6345,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.776180698824592e-05,
"loss": 3.63,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.77534210407354e-05,
"loss": 3.6376,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.774503509322488e-05,
"loss": 3.6409,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.773664914571436e-05,
"loss": 3.6266,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.772827957700757e-05,
"loss": 3.6278,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.771989362949705e-05,
"loss": 3.6422,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.771150768198653e-05,
"loss": 3.6387,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.770312173447601e-05,
"loss": 3.6396,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.769473578696549e-05,
"loss": 3.6349,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.76863662182587e-05,
"loss": 3.6359,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.767798027074818e-05,
"loss": 3.6337,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.766959432323766e-05,
"loss": 3.6493,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.766120837572714e-05,
"loss": 3.6347,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.765282242821662e-05,
"loss": 3.6407,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.7644452859509835e-05,
"loss": 3.6245,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.7636066911999315e-05,
"loss": 3.6503,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.762768096448879e-05,
"loss": 3.6329,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.761929501697827e-05,
"loss": 3.6484,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.7610925448271484e-05,
"loss": 3.6372,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.7602539500760963e-05,
"loss": 3.6401,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.759415355325044e-05,
"loss": 3.6317,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.758576760573992e-05,
"loss": 3.6576,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.7577381658229397e-05,
"loss": 3.6327,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.7568995710718877e-05,
"loss": 3.6432,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.7560609763208356e-05,
"loss": 3.6385,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.755224019450157e-05,
"loss": 3.6325,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.754385424699105e-05,
"loss": 3.638,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.753546829948053e-05,
"loss": 3.6376,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.752708235197001e-05,
"loss": 3.639,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.751871278326322e-05,
"loss": 3.6365,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.75103268357527e-05,
"loss": 3.6373,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 3.8498449325561523,
"eval_runtime": 303.576,
"eval_samples_per_second": 1256.987,
"eval_steps_per_second": 39.282,
"step": 763200
},
{
"epoch": 0.0,
"learning_rate": 3.750194088824218e-05,
"loss": 3.6303,
"step": 763392
},
{
"epoch": 0.0,
"learning_rate": 3.749355494073166e-05,
"loss": 3.623,
"step": 763904
},
{
"epoch": 0.0,
"learning_rate": 3.748516899322114e-05,
"loss": 3.6292,
"step": 764416
},
{
"epoch": 0.0,
"learning_rate": 3.747678304571062e-05,
"loss": 3.6388,
"step": 764928
},
{
"epoch": 0.0,
"learning_rate": 3.746841347700383e-05,
"loss": 3.6475,
"step": 765440
},
{
"epoch": 0.0,
"learning_rate": 3.746002752949331e-05,
"loss": 3.6332,
"step": 765952
},
{
"epoch": 0.0,
"learning_rate": 3.74516415819828e-05,
"loss": 3.6324,
"step": 766464
},
{
"epoch": 0.0,
"learning_rate": 3.744325563447228e-05,
"loss": 3.634,
"step": 766976
},
{
"epoch": 0.0,
"learning_rate": 3.743486968696176e-05,
"loss": 3.6334,
"step": 767488
},
{
"epoch": 0.0,
"learning_rate": 3.7426500118254966e-05,
"loss": 3.641,
"step": 768000
},
{
"epoch": 0.0,
"learning_rate": 3.7418114170744446e-05,
"loss": 3.6254,
"step": 768512
},
{
"epoch": 0.0,
"learning_rate": 3.7409728223233926e-05,
"loss": 3.6281,
"step": 769024
},
{
"epoch": 0.0,
"learning_rate": 3.7401358654527135e-05,
"loss": 3.6422,
"step": 769536
},
{
"epoch": 0.0,
"learning_rate": 3.7392972707016615e-05,
"loss": 3.6228,
"step": 770048
},
{
"epoch": 0.0,
"learning_rate": 3.7384586759506095e-05,
"loss": 3.629,
"step": 770560
},
{
"epoch": 0.0,
"learning_rate": 3.7376200811995575e-05,
"loss": 3.6151,
"step": 771072
},
{
"epoch": 0.0,
"learning_rate": 3.7367814864485055e-05,
"loss": 3.6235,
"step": 771584
},
{
"epoch": 0.0,
"learning_rate": 3.7359428916974535e-05,
"loss": 3.6251,
"step": 772096
},
{
"epoch": 0.0,
"learning_rate": 3.7351042969464015e-05,
"loss": 3.6189,
"step": 772608
},
{
"epoch": 0.0,
"learning_rate": 3.7342657021953495e-05,
"loss": 3.6357,
"step": 773120
},
{
"epoch": 0.0,
"learning_rate": 3.733428745324671e-05,
"loss": 3.6349,
"step": 773632
},
{
"epoch": 0.0,
"learning_rate": 3.732590150573619e-05,
"loss": 3.634,
"step": 774144
},
{
"epoch": 0.0,
"learning_rate": 3.731751555822567e-05,
"loss": 3.6264,
"step": 774656
},
{
"epoch": 0.0,
"learning_rate": 3.730912961071515e-05,
"loss": 3.6297,
"step": 775168
},
{
"epoch": 0.0,
"learning_rate": 3.7300743663204624e-05,
"loss": 3.6331,
"step": 775680
},
{
"epoch": 0.0,
"learning_rate": 3.7292357715694103e-05,
"loss": 3.6254,
"step": 776192
},
{
"epoch": 0.0,
"learning_rate": 3.7283971768183583e-05,
"loss": 3.6184,
"step": 776704
},
{
"epoch": 0.0,
"learning_rate": 3.727560219947679e-05,
"loss": 3.6368,
"step": 777216
},
{
"epoch": 0.0,
"learning_rate": 3.726721625196627e-05,
"loss": 3.6237,
"step": 777728
},
{
"epoch": 0.0,
"learning_rate": 3.725883030445575e-05,
"loss": 3.6226,
"step": 778240
},
{
"epoch": 0.01,
"learning_rate": 3.725044435694523e-05,
"loss": 3.6232,
"step": 778752
},
{
"epoch": 0.01,
"learning_rate": 3.724207478823845e-05,
"loss": 3.6333,
"step": 779264
},
{
"epoch": 0.01,
"learning_rate": 3.723368884072793e-05,
"loss": 3.6283,
"step": 779776
},
{
"epoch": 0.01,
"learning_rate": 3.722530289321741e-05,
"loss": 3.6447,
"step": 780288
},
{
"epoch": 0.01,
"learning_rate": 3.721691694570689e-05,
"loss": 3.6199,
"step": 780800
},
{
"epoch": 0.01,
"learning_rate": 3.720853099819637e-05,
"loss": 3.6232,
"step": 781312
},
{
"epoch": 0.01,
"learning_rate": 3.720014505068585e-05,
"loss": 3.6372,
"step": 781824
},
{
"epoch": 0.01,
"learning_rate": 3.719177548197906e-05,
"loss": 3.6104,
"step": 782336
},
{
"epoch": 0.01,
"learning_rate": 3.718338953446854e-05,
"loss": 3.6219,
"step": 782848
},
{
"epoch": 0.01,
"learning_rate": 3.717500358695802e-05,
"loss": 3.6237,
"step": 783360
},
{
"epoch": 0.01,
"learning_rate": 3.71666176394475e-05,
"loss": 3.6178,
"step": 783872
},
{
"epoch": 0.01,
"learning_rate": 3.715823169193698e-05,
"loss": 3.6257,
"step": 784384
},
{
"epoch": 0.01,
"learning_rate": 3.714984574442646e-05,
"loss": 3.6304,
"step": 784896
},
{
"epoch": 0.01,
"learning_rate": 3.714147617571967e-05,
"loss": 3.6316,
"step": 785408
},
{
"epoch": 0.01,
"learning_rate": 3.713309022820915e-05,
"loss": 3.6211,
"step": 785920
},
{
"epoch": 0.01,
"learning_rate": 3.712470428069863e-05,
"loss": 3.6309,
"step": 786432
},
{
"epoch": 0.01,
"learning_rate": 3.711631833318811e-05,
"loss": 3.6188,
"step": 786944
},
{
"epoch": 0.01,
"learning_rate": 3.710793238567759e-05,
"loss": 3.6274,
"step": 787456
},
{
"epoch": 0.01,
"learning_rate": 3.70995628169708e-05,
"loss": 3.5945,
"step": 787968
},
{
"epoch": 0.01,
"learning_rate": 3.709117686946028e-05,
"loss": 3.634,
"step": 788480
},
{
"epoch": 0.01,
"learning_rate": 3.708279092194976e-05,
"loss": 3.6208,
"step": 788992
},
{
"epoch": 0.01,
"learning_rate": 3.707440497443924e-05,
"loss": 3.6286,
"step": 789504
},
{
"epoch": 0.01,
"learning_rate": 3.706601902692872e-05,
"loss": 3.6226,
"step": 790016
},
{
"epoch": 0.01,
"learning_rate": 3.705764945822193e-05,
"loss": 3.6237,
"step": 790528
},
{
"epoch": 0.01,
"learning_rate": 3.704926351071141e-05,
"loss": 3.6097,
"step": 791040
},
{
"epoch": 0.01,
"learning_rate": 3.704087756320089e-05,
"loss": 3.6142,
"step": 791552
},
{
"epoch": 0.01,
"learning_rate": 3.703249161569037e-05,
"loss": 3.6345,
"step": 792064
},
{
"epoch": 0.01,
"learning_rate": 3.7024122046983586e-05,
"loss": 3.6129,
"step": 792576
},
{
"epoch": 0.01,
"learning_rate": 3.7015736099473066e-05,
"loss": 3.627,
"step": 793088
},
{
"epoch": 0.01,
"learning_rate": 3.7007350151962546e-05,
"loss": 3.6254,
"step": 793600
},
{
"epoch": 0.01,
"learning_rate": 3.6998964204452026e-05,
"loss": 3.6061,
"step": 794112
},
{
"epoch": 0.01,
"learning_rate": 3.6990578256941506e-05,
"loss": 3.6313,
"step": 794624
},
{
"epoch": 0.01,
"learning_rate": 3.6982208688234715e-05,
"loss": 3.612,
"step": 795136
},
{
"epoch": 0.01,
"learning_rate": 3.6973822740724195e-05,
"loss": 3.6115,
"step": 795648
},
{
"epoch": 0.01,
"learning_rate": 3.6965436793213675e-05,
"loss": 3.6249,
"step": 796160
},
{
"epoch": 0.01,
"learning_rate": 3.6957050845703155e-05,
"loss": 3.6209,
"step": 796672
},
{
"epoch": 0.01,
"learning_rate": 3.694866489819263e-05,
"loss": 3.6113,
"step": 797184
},
{
"epoch": 0.01,
"learning_rate": 3.694027895068211e-05,
"loss": 3.6225,
"step": 797696
},
{
"epoch": 0.01,
"learning_rate": 3.6931909381975324e-05,
"loss": 3.6085,
"step": 798208
},
{
"epoch": 0.01,
"learning_rate": 3.6923523434464804e-05,
"loss": 3.6216,
"step": 798720
},
{
"epoch": 0.01,
"learning_rate": 3.6915137486954284e-05,
"loss": 3.6259,
"step": 799232
},
{
"epoch": 0.01,
"learning_rate": 3.6906751539443764e-05,
"loss": 3.6231,
"step": 799744
},
{
"epoch": 0.01,
"learning_rate": 3.6898365591933244e-05,
"loss": 3.6277,
"step": 800256
},
{
"epoch": 0.01,
"learning_rate": 3.6889979644422724e-05,
"loss": 3.625,
"step": 800768
},
{
"epoch": 0.01,
"learning_rate": 3.6881593696912204e-05,
"loss": 3.6347,
"step": 801280
},
{
"epoch": 0.01,
"learning_rate": 3.6873207749401684e-05,
"loss": 3.6161,
"step": 801792
},
{
"epoch": 0.01,
"learning_rate": 3.686485455949863e-05,
"loss": 3.6267,
"step": 802304
},
{
"epoch": 0.01,
"learning_rate": 3.68564686119881e-05,
"loss": 3.6213,
"step": 802816
},
{
"epoch": 0.01,
"learning_rate": 3.684808266447758e-05,
"loss": 3.6028,
"step": 803328
},
{
"epoch": 0.01,
"learning_rate": 3.683969671696706e-05,
"loss": 3.6231,
"step": 803840
},
{
"epoch": 0.01,
"learning_rate": 3.683131076945654e-05,
"loss": 3.6271,
"step": 804352
},
{
"epoch": 0.01,
"learning_rate": 3.682294120074976e-05,
"loss": 3.6212,
"step": 804864
},
{
"epoch": 0.01,
"learning_rate": 3.681455525323924e-05,
"loss": 3.6383,
"step": 805376
},
{
"epoch": 0.01,
"learning_rate": 3.680616930572872e-05,
"loss": 3.6061,
"step": 805888
},
{
"epoch": 0.01,
"learning_rate": 3.67977833582182e-05,
"loss": 3.6142,
"step": 806400
},
{
"epoch": 0.01,
"learning_rate": 3.678939741070768e-05,
"loss": 3.6199,
"step": 806912
},
{
"epoch": 0.01,
"learning_rate": 3.678101146319716e-05,
"loss": 3.6227,
"step": 807424
},
{
"epoch": 0.01,
"learning_rate": 3.677264189449037e-05,
"loss": 3.6172,
"step": 807936
},
{
"epoch": 0.01,
"learning_rate": 3.676425594697985e-05,
"loss": 3.616,
"step": 808448
},
{
"epoch": 0.01,
"learning_rate": 3.6755869999469327e-05,
"loss": 3.6083,
"step": 808960
},
{
"epoch": 0.02,
"learning_rate": 3.6747484051958807e-05,
"loss": 3.6179,
"step": 809472
},
{
"epoch": 0.02,
"learning_rate": 3.6739098104448286e-05,
"loss": 3.6173,
"step": 809984
},
{
"epoch": 0.02,
"learning_rate": 3.6730728535741496e-05,
"loss": 3.6162,
"step": 810496
},
{
"epoch": 0.02,
"learning_rate": 3.672234258823098e-05,
"loss": 3.6255,
"step": 811008
},
{
"epoch": 0.02,
"learning_rate": 3.671395664072046e-05,
"loss": 3.6246,
"step": 811520
},
{
"epoch": 0.02,
"learning_rate": 3.670557069320994e-05,
"loss": 3.6194,
"step": 812032
},
{
"epoch": 0.02,
"learning_rate": 3.669718474569942e-05,
"loss": 3.6092,
"step": 812544
},
{
"epoch": 0.02,
"learning_rate": 3.668881517699263e-05,
"loss": 3.6142,
"step": 813056
},
{
"epoch": 0.02,
"learning_rate": 3.668042922948211e-05,
"loss": 3.6167,
"step": 813568
},
{
"epoch": 0.02,
"learning_rate": 3.667204328197159e-05,
"loss": 3.6259,
"step": 814080
},
{
"epoch": 0.02,
"learning_rate": 3.666365733446107e-05,
"loss": 3.6161,
"step": 814592
},
{
"epoch": 0.02,
"learning_rate": 3.665527138695055e-05,
"loss": 3.6144,
"step": 815104
},
{
"epoch": 0.02,
"learning_rate": 3.664690181824376e-05,
"loss": 3.6189,
"step": 815616
},
{
"epoch": 0.02,
"learning_rate": 3.663851587073324e-05,
"loss": 3.615,
"step": 816128
},
{
"epoch": 0.02,
"learning_rate": 3.663012992322272e-05,
"loss": 3.6131,
"step": 816640
},
{
"epoch": 0.02,
"learning_rate": 3.66217439757122e-05,
"loss": 3.6169,
"step": 817152
},
{
"epoch": 0.02,
"learning_rate": 3.6613374407005416e-05,
"loss": 3.6034,
"step": 817664
},
{
"epoch": 0.02,
"learning_rate": 3.6604988459494896e-05,
"loss": 3.6262,
"step": 818176
},
{
"epoch": 0.02,
"learning_rate": 3.6596602511984376e-05,
"loss": 3.6129,
"step": 818688
},
{
"epoch": 0.02,
"learning_rate": 3.6588216564473856e-05,
"loss": 3.6066,
"step": 819200
},
{
"epoch": 0.02,
"learning_rate": 3.6579846995767065e-05,
"loss": 3.6037,
"step": 819712
},
{
"epoch": 0.02,
"learning_rate": 3.6571461048256545e-05,
"loss": 3.6191,
"step": 820224
},
{
"epoch": 0.02,
"learning_rate": 3.6563075100746025e-05,
"loss": 3.618,
"step": 820736
},
{
"epoch": 0.02,
"learning_rate": 3.6554689153235505e-05,
"loss": 3.6095,
"step": 821248
},
{
"epoch": 0.02,
"learning_rate": 3.6546303205724985e-05,
"loss": 3.6183,
"step": 821760
},
{
"epoch": 0.02,
"learning_rate": 3.6537933637018194e-05,
"loss": 3.6298,
"step": 822272
},
{
"epoch": 0.02,
"learning_rate": 3.6529547689507674e-05,
"loss": 3.6214,
"step": 822784
},
{
"epoch": 0.02,
"learning_rate": 3.6521161741997154e-05,
"loss": 3.6145,
"step": 823296
},
{
"epoch": 0.02,
"learning_rate": 3.6512775794486634e-05,
"loss": 3.6111,
"step": 823808
},
{
"epoch": 0.02,
"learning_rate": 3.650440622577985e-05,
"loss": 3.6121,
"step": 824320
},
{
"epoch": 0.02,
"learning_rate": 3.649602027826933e-05,
"loss": 3.6194,
"step": 824832
},
{
"epoch": 0.02,
"learning_rate": 3.648763433075881e-05,
"loss": 3.6042,
"step": 825344
},
{
"epoch": 0.02,
"learning_rate": 3.647924838324829e-05,
"loss": 3.6045,
"step": 825856
},
{
"epoch": 0.02,
"learning_rate": 3.64708788145415e-05,
"loss": 3.6209,
"step": 826368
},
{
"epoch": 0.02,
"learning_rate": 3.646249286703098e-05,
"loss": 3.6163,
"step": 826880
},
{
"epoch": 0.02,
"learning_rate": 3.645410691952046e-05,
"loss": 3.6162,
"step": 827392
},
{
"epoch": 0.02,
"learning_rate": 3.644572097200994e-05,
"loss": 3.6165,
"step": 827904
},
{
"epoch": 0.02,
"learning_rate": 3.643733502449941e-05,
"loss": 3.6121,
"step": 828416
},
{
"epoch": 0.02,
"learning_rate": 3.642896545579263e-05,
"loss": 3.6132,
"step": 828928
},
{
"epoch": 0.02,
"learning_rate": 3.642057950828211e-05,
"loss": 3.6264,
"step": 829440
},
{
"epoch": 0.02,
"learning_rate": 3.641219356077159e-05,
"loss": 3.6149,
"step": 829952
},
{
"epoch": 0.02,
"learning_rate": 3.640380761326107e-05,
"loss": 3.6199,
"step": 830464
},
{
"epoch": 0.02,
"learning_rate": 3.639543804455428e-05,
"loss": 3.603,
"step": 830976
},
{
"epoch": 0.02,
"learning_rate": 3.638705209704376e-05,
"loss": 3.6218,
"step": 831488
},
{
"epoch": 0.02,
"learning_rate": 3.6378666149533236e-05,
"loss": 3.6158,
"step": 832000
},
{
"epoch": 0.02,
"learning_rate": 3.6370280202022716e-05,
"loss": 3.6234,
"step": 832512
},
{
"epoch": 0.02,
"learning_rate": 3.636191063331593e-05,
"loss": 3.6175,
"step": 833024
},
{
"epoch": 0.02,
"learning_rate": 3.635352468580541e-05,
"loss": 3.6148,
"step": 833536
},
{
"epoch": 0.02,
"learning_rate": 3.6345138738294885e-05,
"loss": 3.6159,
"step": 834048
},
{
"epoch": 0.02,
"learning_rate": 3.6336752790784365e-05,
"loss": 3.6308,
"step": 834560
},
{
"epoch": 0.02,
"learning_rate": 3.6328366843273845e-05,
"loss": 3.6138,
"step": 835072
},
{
"epoch": 0.02,
"learning_rate": 3.631999727456706e-05,
"loss": 3.6167,
"step": 835584
},
{
"epoch": 0.02,
"learning_rate": 3.631161132705654e-05,
"loss": 3.6205,
"step": 836096
},
{
"epoch": 0.02,
"learning_rate": 3.630322537954602e-05,
"loss": 3.6124,
"step": 836608
},
{
"epoch": 0.02,
"learning_rate": 3.629485581083924e-05,
"loss": 3.6131,
"step": 837120
},
{
"epoch": 0.02,
"learning_rate": 3.628646986332871e-05,
"loss": 3.6193,
"step": 837632
},
{
"epoch": 0.02,
"learning_rate": 3.627808391581819e-05,
"loss": 3.6167,
"step": 838144
},
{
"epoch": 0.02,
"learning_rate": 3.626969796830767e-05,
"loss": 3.6171,
"step": 838656
},
{
"epoch": 0.02,
"learning_rate": 3.626131202079715e-05,
"loss": 3.6137,
"step": 839168
},
{
"epoch": 0.03,
"eval_loss": 3.8489737510681152,
"eval_runtime": 304.4447,
"eval_samples_per_second": 1253.4,
"eval_steps_per_second": 39.17,
"step": 839520
},
{
"epoch": 0.0,
"learning_rate": 3.625292607328663e-05,
"loss": 3.6006,
"step": 839680
},
{
"epoch": 0.0,
"learning_rate": 3.624454012577611e-05,
"loss": 3.6048,
"step": 840192
},
{
"epoch": 0.0,
"learning_rate": 3.623615417826559e-05,
"loss": 3.6094,
"step": 840704
},
{
"epoch": 0.0,
"learning_rate": 3.622776823075507e-05,
"loss": 3.6163,
"step": 841216
},
{
"epoch": 0.0,
"learning_rate": 3.621939866204828e-05,
"loss": 3.6236,
"step": 841728
},
{
"epoch": 0.0,
"learning_rate": 3.621101271453776e-05,
"loss": 3.6134,
"step": 842240
},
{
"epoch": 0.0,
"learning_rate": 3.6202626767027245e-05,
"loss": 3.6113,
"step": 842752
},
{
"epoch": 0.0,
"learning_rate": 3.6194240819516725e-05,
"loss": 3.6116,
"step": 843264
},
{
"epoch": 0.0,
"learning_rate": 3.6185871250809935e-05,
"loss": 3.6108,
"step": 843776
},
{
"epoch": 0.0,
"learning_rate": 3.6177485303299415e-05,
"loss": 3.6159,
"step": 844288
},
{
"epoch": 0.0,
"learning_rate": 3.6169099355788894e-05,
"loss": 3.6091,
"step": 844800
},
{
"epoch": 0.0,
"learning_rate": 3.6160713408278374e-05,
"loss": 3.605,
"step": 845312
},
{
"epoch": 0.0,
"learning_rate": 3.6152343839571584e-05,
"loss": 3.6192,
"step": 845824
},
{
"epoch": 0.0,
"learning_rate": 3.6143957892061063e-05,
"loss": 3.6014,
"step": 846336
},
{
"epoch": 0.0,
"learning_rate": 3.6135571944550543e-05,
"loss": 3.6091,
"step": 846848
},
{
"epoch": 0.0,
"learning_rate": 3.612718599704002e-05,
"loss": 3.5958,
"step": 847360
},
{
"epoch": 0.0,
"learning_rate": 3.611881642833323e-05,
"loss": 3.6052,
"step": 847872
},
{
"epoch": 0.0,
"learning_rate": 3.611043048082271e-05,
"loss": 3.6038,
"step": 848384
},
{
"epoch": 0.0,
"learning_rate": 3.61020445333122e-05,
"loss": 3.5969,
"step": 848896
},
{
"epoch": 0.0,
"learning_rate": 3.609365858580168e-05,
"loss": 3.6137,
"step": 849408
},
{
"epoch": 0.0,
"learning_rate": 3.608528901709489e-05,
"loss": 3.6109,
"step": 849920
},
{
"epoch": 0.0,
"learning_rate": 3.607690306958437e-05,
"loss": 3.6101,
"step": 850432
},
{
"epoch": 0.0,
"learning_rate": 3.606851712207385e-05,
"loss": 3.6067,
"step": 850944
},
{
"epoch": 0.0,
"learning_rate": 3.606013117456333e-05,
"loss": 3.6079,
"step": 851456
},
{
"epoch": 0.0,
"learning_rate": 3.605176160585654e-05,
"loss": 3.6129,
"step": 851968
},
{
"epoch": 0.0,
"learning_rate": 3.604337565834602e-05,
"loss": 3.6083,
"step": 852480
},
{
"epoch": 0.0,
"learning_rate": 3.60349897108355e-05,
"loss": 3.5922,
"step": 852992
},
{
"epoch": 0.0,
"learning_rate": 3.602660376332498e-05,
"loss": 3.6158,
"step": 853504
},
{
"epoch": 0.0,
"learning_rate": 3.6018234194618186e-05,
"loss": 3.6013,
"step": 854016
},
{
"epoch": 0.0,
"learning_rate": 3.6009848247107666e-05,
"loss": 3.6004,
"step": 854528
},
{
"epoch": 0.01,
"learning_rate": 3.600146229959715e-05,
"loss": 3.6084,
"step": 855040
},
{
"epoch": 0.01,
"learning_rate": 3.599307635208663e-05,
"loss": 3.6103,
"step": 855552
},
{
"epoch": 0.01,
"learning_rate": 3.598469040457611e-05,
"loss": 3.6069,
"step": 856064
},
{
"epoch": 0.01,
"learning_rate": 3.597630445706559e-05,
"loss": 3.6233,
"step": 856576
},
{
"epoch": 0.01,
"learning_rate": 3.596791850955507e-05,
"loss": 3.6002,
"step": 857088
},
{
"epoch": 0.01,
"learning_rate": 3.5959532562044546e-05,
"loss": 3.6028,
"step": 857600
},
{
"epoch": 0.01,
"learning_rate": 3.595116299333776e-05,
"loss": 3.6157,
"step": 858112
},
{
"epoch": 0.01,
"learning_rate": 3.594277704582724e-05,
"loss": 3.5887,
"step": 858624
},
{
"epoch": 0.01,
"learning_rate": 3.593440747712045e-05,
"loss": 3.6012,
"step": 859136
},
{
"epoch": 0.01,
"learning_rate": 3.592602152960993e-05,
"loss": 3.6039,
"step": 859648
},
{
"epoch": 0.01,
"learning_rate": 3.591763558209941e-05,
"loss": 3.5958,
"step": 860160
},
{
"epoch": 0.01,
"learning_rate": 3.590924963458889e-05,
"loss": 3.6059,
"step": 860672
},
{
"epoch": 0.01,
"learning_rate": 3.590086368707837e-05,
"loss": 3.6084,
"step": 861184
},
{
"epoch": 0.01,
"learning_rate": 3.5892494118371586e-05,
"loss": 3.6081,
"step": 861696
},
{
"epoch": 0.01,
"learning_rate": 3.5884108170861066e-05,
"loss": 3.6031,
"step": 862208
},
{
"epoch": 0.01,
"learning_rate": 3.5875722223350546e-05,
"loss": 3.6085,
"step": 862720
},
{
"epoch": 0.01,
"learning_rate": 3.586733627584002e-05,
"loss": 3.5965,
"step": 863232
},
{
"epoch": 0.01,
"learning_rate": 3.58589503283295e-05,
"loss": 3.6094,
"step": 863744
},
{
"epoch": 0.01,
"learning_rate": 3.5850580759622715e-05,
"loss": 3.5754,
"step": 864256
},
{
"epoch": 0.01,
"learning_rate": 3.5842194812112195e-05,
"loss": 3.6088,
"step": 864768
},
{
"epoch": 0.01,
"learning_rate": 3.583380886460167e-05,
"loss": 3.6015,
"step": 865280
},
{
"epoch": 0.01,
"learning_rate": 3.582542291709115e-05,
"loss": 3.6119,
"step": 865792
},
{
"epoch": 0.01,
"learning_rate": 3.581703696958063e-05,
"loss": 3.598,
"step": 866304
},
{
"epoch": 0.01,
"learning_rate": 3.5808667400873844e-05,
"loss": 3.6055,
"step": 866816
},
{
"epoch": 0.01,
"learning_rate": 3.5800281453363324e-05,
"loss": 3.5911,
"step": 867328
},
{
"epoch": 0.01,
"learning_rate": 3.5791895505852804e-05,
"loss": 3.5935,
"step": 867840
},
{
"epoch": 0.01,
"learning_rate": 3.5783509558342284e-05,
"loss": 3.6162,
"step": 868352
},
{
"epoch": 0.01,
"learning_rate": 3.577513998963549e-05,
"loss": 3.5894,
"step": 868864
},
{
"epoch": 0.01,
"learning_rate": 3.576675404212497e-05,
"loss": 3.6091,
"step": 869376
},
{
"epoch": 0.01,
"learning_rate": 3.575836809461445e-05,
"loss": 3.6076,
"step": 869888
},
{
"epoch": 0.01,
"learning_rate": 3.574998214710393e-05,
"loss": 3.5805,
"step": 870400
},
{
"epoch": 0.01,
"learning_rate": 3.574159619959341e-05,
"loss": 3.614,
"step": 870912
},
{
"epoch": 0.01,
"learning_rate": 3.573321025208289e-05,
"loss": 3.5932,
"step": 871424
},
{
"epoch": 0.01,
"learning_rate": 3.57248406833761e-05,
"loss": 3.5921,
"step": 871936
},
{
"epoch": 0.01,
"learning_rate": 3.571645473586558e-05,
"loss": 3.6023,
"step": 872448
},
{
"epoch": 0.01,
"learning_rate": 3.570806878835506e-05,
"loss": 3.6012,
"step": 872960
},
{
"epoch": 0.01,
"learning_rate": 3.569968284084454e-05,
"loss": 3.5904,
"step": 873472
},
{
"epoch": 0.01,
"learning_rate": 3.569131327213776e-05,
"loss": 3.5993,
"step": 873984
},
{
"epoch": 0.01,
"learning_rate": 3.568292732462724e-05,
"loss": 3.5871,
"step": 874496
},
{
"epoch": 0.01,
"learning_rate": 3.567454137711672e-05,
"loss": 3.6035,
"step": 875008
},
{
"epoch": 0.01,
"learning_rate": 3.56661554296062e-05,
"loss": 3.6077,
"step": 875520
},
{
"epoch": 0.01,
"learning_rate": 3.565776948209568e-05,
"loss": 3.6022,
"step": 876032
},
{
"epoch": 0.01,
"learning_rate": 3.564939991338889e-05,
"loss": 3.6046,
"step": 876544
},
{
"epoch": 0.01,
"learning_rate": 3.564101396587837e-05,
"loss": 3.6031,
"step": 877056
},
{
"epoch": 0.01,
"learning_rate": 3.563262801836785e-05,
"loss": 3.6164,
"step": 877568
},
{
"epoch": 0.01,
"learning_rate": 3.562424207085733e-05,
"loss": 3.5934,
"step": 878080
},
{
"epoch": 0.01,
"learning_rate": 3.5615872502150536e-05,
"loss": 3.6085,
"step": 878592
},
{
"epoch": 0.01,
"learning_rate": 3.5607486554640016e-05,
"loss": 3.5938,
"step": 879104
},
{
"epoch": 0.01,
"learning_rate": 3.5599100607129496e-05,
"loss": 3.5878,
"step": 879616
},
{
"epoch": 0.01,
"learning_rate": 3.5590714659618976e-05,
"loss": 3.6016,
"step": 880128
},
{
"epoch": 0.01,
"learning_rate": 3.558234509091219e-05,
"loss": 3.6051,
"step": 880640
},
{
"epoch": 0.01,
"learning_rate": 3.557395914340167e-05,
"loss": 3.602,
"step": 881152
},
{
"epoch": 0.01,
"learning_rate": 3.556557319589115e-05,
"loss": 3.6174,
"step": 881664
},
{
"epoch": 0.01,
"learning_rate": 3.555718724838063e-05,
"loss": 3.5873,
"step": 882176
},
{
"epoch": 0.01,
"learning_rate": 3.554881767967384e-05,
"loss": 3.5941,
"step": 882688
},
{
"epoch": 0.01,
"learning_rate": 3.554043173216332e-05,
"loss": 3.6005,
"step": 883200
},
{
"epoch": 0.01,
"learning_rate": 3.55320457846528e-05,
"loss": 3.5997,
"step": 883712
},
{
"epoch": 0.01,
"learning_rate": 3.552365983714228e-05,
"loss": 3.5962,
"step": 884224
},
{
"epoch": 0.01,
"learning_rate": 3.551529026843549e-05,
"loss": 3.5943,
"step": 884736
},
{
"epoch": 0.01,
"learning_rate": 3.550690432092497e-05,
"loss": 3.5945,
"step": 885248
},
{
"epoch": 0.02,
"learning_rate": 3.549851837341445e-05,
"loss": 3.5973,
"step": 885760
},
{
"epoch": 0.02,
"learning_rate": 3.549013242590393e-05,
"loss": 3.5982,
"step": 886272
},
{
"epoch": 0.02,
"learning_rate": 3.5481762857197145e-05,
"loss": 3.5948,
"step": 886784
},
{
"epoch": 0.02,
"learning_rate": 3.5473376909686625e-05,
"loss": 3.6041,
"step": 887296
},
{
"epoch": 0.02,
"learning_rate": 3.5464990962176105e-05,
"loss": 3.6048,
"step": 887808
},
{
"epoch": 0.02,
"learning_rate": 3.5456605014665585e-05,
"loss": 3.5991,
"step": 888320
},
{
"epoch": 0.02,
"learning_rate": 3.5448219067155065e-05,
"loss": 3.5892,
"step": 888832
},
{
"epoch": 0.02,
"learning_rate": 3.5439849498448274e-05,
"loss": 3.5956,
"step": 889344
},
{
"epoch": 0.02,
"learning_rate": 3.5431463550937754e-05,
"loss": 3.5975,
"step": 889856
},
{
"epoch": 0.02,
"learning_rate": 3.5423077603427234e-05,
"loss": 3.6057,
"step": 890368
},
{
"epoch": 0.02,
"learning_rate": 3.5414691655916714e-05,
"loss": 3.5969,
"step": 890880
},
{
"epoch": 0.02,
"learning_rate": 3.5406305708406194e-05,
"loss": 3.5941,
"step": 891392
},
{
"epoch": 0.02,
"learning_rate": 3.53979361396994e-05,
"loss": 3.5996,
"step": 891904
},
{
"epoch": 0.02,
"learning_rate": 3.538955019218888e-05,
"loss": 3.5973,
"step": 892416
},
{
"epoch": 0.02,
"learning_rate": 3.538116424467837e-05,
"loss": 3.5944,
"step": 892928
},
{
"epoch": 0.02,
"learning_rate": 3.537277829716785e-05,
"loss": 3.5946,
"step": 893440
},
{
"epoch": 0.02,
"learning_rate": 3.536440872846106e-05,
"loss": 3.5877,
"step": 893952
},
{
"epoch": 0.02,
"learning_rate": 3.535602278095054e-05,
"loss": 3.6043,
"step": 894464
},
{
"epoch": 0.02,
"learning_rate": 3.534763683344002e-05,
"loss": 3.5959,
"step": 894976
},
{
"epoch": 0.02,
"learning_rate": 3.53392508859295e-05,
"loss": 3.5855,
"step": 895488
},
{
"epoch": 0.02,
"learning_rate": 3.533088131722271e-05,
"loss": 3.585,
"step": 896000
},
{
"epoch": 0.02,
"learning_rate": 3.532249536971219e-05,
"loss": 3.5976,
"step": 896512
},
{
"epoch": 0.02,
"learning_rate": 3.531410942220167e-05,
"loss": 3.5993,
"step": 897024
},
{
"epoch": 0.02,
"learning_rate": 3.530572347469115e-05,
"loss": 3.589,
"step": 897536
},
{
"epoch": 0.02,
"learning_rate": 3.529735390598436e-05,
"loss": 3.6003,
"step": 898048
},
{
"epoch": 0.02,
"learning_rate": 3.528896795847384e-05,
"loss": 3.611,
"step": 898560
},
{
"epoch": 0.02,
"learning_rate": 3.528058201096332e-05,
"loss": 3.5977,
"step": 899072
},
{
"epoch": 0.02,
"learning_rate": 3.52721960634528e-05,
"loss": 3.5958,
"step": 899584
},
{
"epoch": 0.02,
"learning_rate": 3.526382649474601e-05,
"loss": 3.593,
"step": 900096
},
{
"epoch": 0.02,
"learning_rate": 3.525544054723549e-05,
"loss": 3.5949,
"step": 900608
},
{
"epoch": 0.02,
"learning_rate": 3.524705459972497e-05,
"loss": 3.602,
"step": 901120
},
{
"epoch": 0.02,
"learning_rate": 3.5238668652214445e-05,
"loss": 3.5847,
"step": 901632
},
{
"epoch": 0.02,
"learning_rate": 3.5230282704703925e-05,
"loss": 3.5846,
"step": 902144
},
{
"epoch": 0.02,
"learning_rate": 3.522191313599714e-05,
"loss": 3.5989,
"step": 902656
},
{
"epoch": 0.02,
"learning_rate": 3.521352718848662e-05,
"loss": 3.5959,
"step": 903168
},
{
"epoch": 0.02,
"learning_rate": 3.5205141240976094e-05,
"loss": 3.5982,
"step": 903680
},
{
"epoch": 0.02,
"learning_rate": 3.5196755293465574e-05,
"loss": 3.5977,
"step": 904192
},
{
"epoch": 0.02,
"learning_rate": 3.518838572475879e-05,
"loss": 3.5908,
"step": 904704
},
{
"epoch": 0.02,
"learning_rate": 3.517999977724828e-05,
"loss": 3.5935,
"step": 905216
},
{
"epoch": 0.02,
"learning_rate": 3.517161382973775e-05,
"loss": 3.6056,
"step": 905728
},
{
"epoch": 0.02,
"learning_rate": 3.516322788222723e-05,
"loss": 3.5953,
"step": 906240
},
{
"epoch": 0.02,
"learning_rate": 3.515484193471671e-05,
"loss": 3.6026,
"step": 906752
},
{
"epoch": 0.02,
"learning_rate": 3.514647236600992e-05,
"loss": 3.5858,
"step": 907264
},
{
"epoch": 0.02,
"learning_rate": 3.51380864184994e-05,
"loss": 3.5992,
"step": 907776
},
{
"epoch": 0.02,
"learning_rate": 3.512970047098888e-05,
"loss": 3.5976,
"step": 908288
},
{
"epoch": 0.02,
"learning_rate": 3.512131452347836e-05,
"loss": 3.5989,
"step": 908800
},
{
"epoch": 0.02,
"learning_rate": 3.511294495477157e-05,
"loss": 3.6012,
"step": 909312
},
{
"epoch": 0.02,
"learning_rate": 3.510455900726105e-05,
"loss": 3.5937,
"step": 909824
},
{
"epoch": 0.02,
"learning_rate": 3.509617305975053e-05,
"loss": 3.5964,
"step": 910336
},
{
"epoch": 0.02,
"learning_rate": 3.5087787112240015e-05,
"loss": 3.6113,
"step": 910848
},
{
"epoch": 0.02,
"learning_rate": 3.5079401164729495e-05,
"loss": 3.5966,
"step": 911360
},
{
"epoch": 0.02,
"learning_rate": 3.5071031596022704e-05,
"loss": 3.5962,
"step": 911872
},
{
"epoch": 0.02,
"learning_rate": 3.5062645648512184e-05,
"loss": 3.6011,
"step": 912384
},
{
"epoch": 0.02,
"learning_rate": 3.5054259701001664e-05,
"loss": 3.5907,
"step": 912896
},
{
"epoch": 0.02,
"learning_rate": 3.504589013229487e-05,
"loss": 3.5937,
"step": 913408
},
{
"epoch": 0.02,
"learning_rate": 3.503750418478435e-05,
"loss": 3.6036,
"step": 913920
},
{
"epoch": 0.02,
"learning_rate": 3.502911823727383e-05,
"loss": 3.5919,
"step": 914432
},
{
"epoch": 0.02,
"learning_rate": 3.502073228976331e-05,
"loss": 3.5979,
"step": 914944
},
{
"epoch": 0.02,
"learning_rate": 3.501236272105652e-05,
"loss": 3.5941,
"step": 915456
},
{
"epoch": 0.03,
"eval_loss": 3.8470003604888916,
"eval_runtime": 304.479,
"eval_samples_per_second": 1253.259,
"eval_steps_per_second": 39.165,
"step": 915840
},
{
"epoch": 1.0,
"learning_rate": 3.5003976773546e-05,
"loss": 3.5884,
"step": 915968
},
{
"epoch": 1.0,
"learning_rate": 3.499559082603548e-05,
"loss": 3.5822,
"step": 916480
},
{
"epoch": 1.0,
"learning_rate": 3.498720487852497e-05,
"loss": 3.5884,
"step": 916992
},
{
"epoch": 1.0,
"learning_rate": 3.497881893101445e-05,
"loss": 3.5989,
"step": 917504
},
{
"epoch": 1.0,
"learning_rate": 3.497044936230766e-05,
"loss": 3.5983,
"step": 918016
},
{
"epoch": 1.0,
"learning_rate": 3.496206341479714e-05,
"loss": 3.5954,
"step": 918528
},
{
"epoch": 1.0,
"learning_rate": 3.495367746728662e-05,
"loss": 3.5969,
"step": 919040
},
{
"epoch": 1.0,
"learning_rate": 3.49452915197761e-05,
"loss": 3.5921,
"step": 919552
},
{
"epoch": 1.0,
"learning_rate": 3.4936921951069306e-05,
"loss": 3.5883,
"step": 920064
},
{
"epoch": 1.0,
"learning_rate": 3.4928536003558786e-05,
"loss": 3.597,
"step": 920576
},
{
"epoch": 1.0,
"learning_rate": 3.4920150056048266e-05,
"loss": 3.5952,
"step": 921088
},
{
"epoch": 1.0,
"learning_rate": 3.4911764108537746e-05,
"loss": 3.5829,
"step": 921600
},
{
"epoch": 1.0,
"learning_rate": 3.4903394539830955e-05,
"loss": 3.6028,
"step": 922112
},
{
"epoch": 1.0,
"learning_rate": 3.4895008592320435e-05,
"loss": 3.5829,
"step": 922624
},
{
"epoch": 1.0,
"learning_rate": 3.4886622644809915e-05,
"loss": 3.586,
"step": 923136
},
{
"epoch": 1.0,
"learning_rate": 3.48782366972994e-05,
"loss": 3.5778,
"step": 923648
},
{
"epoch": 1.0,
"learning_rate": 3.486985074978888e-05,
"loss": 3.5868,
"step": 924160
},
{
"epoch": 1.0,
"learning_rate": 3.486146480227836e-05,
"loss": 3.5828,
"step": 924672
},
{
"epoch": 1.0,
"learning_rate": 3.485307885476784e-05,
"loss": 3.581,
"step": 925184
},
{
"epoch": 1.0,
"learning_rate": 3.484469290725732e-05,
"loss": 3.5875,
"step": 925696
},
{
"epoch": 1.0,
"learning_rate": 3.483632333855053e-05,
"loss": 3.5984,
"step": 926208
},
{
"epoch": 1.0,
"learning_rate": 3.482793739104001e-05,
"loss": 3.5909,
"step": 926720
},
{
"epoch": 1.0,
"learning_rate": 3.481955144352949e-05,
"loss": 3.5842,
"step": 927232
},
{
"epoch": 1.0,
"learning_rate": 3.481116549601897e-05,
"loss": 3.5921,
"step": 927744
},
{
"epoch": 1.0,
"learning_rate": 3.480279592731218e-05,
"loss": 3.5944,
"step": 928256
},
{
"epoch": 1.0,
"learning_rate": 3.479440997980166e-05,
"loss": 3.5809,
"step": 928768
},
{
"epoch": 1.0,
"learning_rate": 3.478602403229114e-05,
"loss": 3.5774,
"step": 929280
},
{
"epoch": 1.0,
"learning_rate": 3.477763808478062e-05,
"loss": 3.5966,
"step": 929792
},
{
"epoch": 1.0,
"learning_rate": 3.47692521372701e-05,
"loss": 3.5835,
"step": 930304
},
{
"epoch": 1.0,
"learning_rate": 3.4760882568563316e-05,
"loss": 3.5785,
"step": 930816
},
{
"epoch": 1.01,
"learning_rate": 3.4752496621052796e-05,
"loss": 3.5895,
"step": 931328
},
{
"epoch": 1.01,
"learning_rate": 3.4744110673542276e-05,
"loss": 3.5887,
"step": 931840
},
{
"epoch": 1.01,
"learning_rate": 3.4735741104835485e-05,
"loss": 3.5915,
"step": 932352
},
{
"epoch": 1.01,
"learning_rate": 3.4727355157324965e-05,
"loss": 3.6042,
"step": 932864
},
{
"epoch": 1.01,
"learning_rate": 3.4718969209814445e-05,
"loss": 3.577,
"step": 933376
},
{
"epoch": 1.01,
"learning_rate": 3.4710583262303925e-05,
"loss": 3.5907,
"step": 933888
},
{
"epoch": 1.01,
"learning_rate": 3.4702197314793405e-05,
"loss": 3.5936,
"step": 934400
},
{
"epoch": 1.01,
"learning_rate": 3.469381136728288e-05,
"loss": 3.5697,
"step": 934912
},
{
"epoch": 1.01,
"learning_rate": 3.4685441798576094e-05,
"loss": 3.5853,
"step": 935424
},
{
"epoch": 1.01,
"learning_rate": 3.4677055851065574e-05,
"loss": 3.586,
"step": 935936
},
{
"epoch": 1.01,
"learning_rate": 3.4668669903555053e-05,
"loss": 3.5735,
"step": 936448
},
{
"epoch": 1.01,
"learning_rate": 3.4660283956044533e-05,
"loss": 3.5912,
"step": 936960
},
{
"epoch": 1.01,
"learning_rate": 3.465191438733775e-05,
"loss": 3.5847,
"step": 937472
},
{
"epoch": 1.01,
"learning_rate": 3.464352843982723e-05,
"loss": 3.5923,
"step": 937984
},
{
"epoch": 1.01,
"learning_rate": 3.46351424923167e-05,
"loss": 3.5818,
"step": 938496
},
{
"epoch": 1.01,
"learning_rate": 3.462675654480618e-05,
"loss": 3.5878,
"step": 939008
},
{
"epoch": 1.01,
"learning_rate": 3.461837059729566e-05,
"loss": 3.578,
"step": 939520
},
{
"epoch": 1.01,
"learning_rate": 3.461000102858888e-05,
"loss": 3.5921,
"step": 940032
},
{
"epoch": 1.01,
"learning_rate": 3.460161508107835e-05,
"loss": 3.5579,
"step": 940544
},
{
"epoch": 1.01,
"learning_rate": 3.459322913356783e-05,
"loss": 3.5863,
"step": 941056
},
{
"epoch": 1.01,
"learning_rate": 3.458484318605731e-05,
"loss": 3.582,
"step": 941568
},
{
"epoch": 1.01,
"learning_rate": 3.457647361735053e-05,
"loss": 3.5949,
"step": 942080
},
{
"epoch": 1.01,
"learning_rate": 3.456808766984001e-05,
"loss": 3.5769,
"step": 942592
},
{
"epoch": 1.01,
"learning_rate": 3.455970172232949e-05,
"loss": 3.581,
"step": 943104
},
{
"epoch": 1.01,
"learning_rate": 3.455131577481897e-05,
"loss": 3.5762,
"step": 943616
},
{
"epoch": 1.01,
"learning_rate": 3.4542946206112176e-05,
"loss": 3.5747,
"step": 944128
},
{
"epoch": 1.01,
"learning_rate": 3.4534560258601656e-05,
"loss": 3.598,
"step": 944640
},
{
"epoch": 1.01,
"learning_rate": 3.4526174311091136e-05,
"loss": 3.5679,
"step": 945152
},
{
"epoch": 1.01,
"learning_rate": 3.4517788363580616e-05,
"loss": 3.5925,
"step": 945664
},
{
"epoch": 1.01,
"learning_rate": 3.4509418794873825e-05,
"loss": 3.5869,
"step": 946176
},
{
"epoch": 1.01,
"learning_rate": 3.4501032847363305e-05,
"loss": 3.5646,
"step": 946688
},
{
"epoch": 1.01,
"learning_rate": 3.4492646899852785e-05,
"loss": 3.5938,
"step": 947200
},
{
"epoch": 1.01,
"learning_rate": 3.4484260952342265e-05,
"loss": 3.5716,
"step": 947712
},
{
"epoch": 1.01,
"learning_rate": 3.4475875004831745e-05,
"loss": 3.5754,
"step": 948224
},
{
"epoch": 1.01,
"learning_rate": 3.446750543612496e-05,
"loss": 3.5815,
"step": 948736
},
{
"epoch": 1.01,
"learning_rate": 3.445911948861444e-05,
"loss": 3.5846,
"step": 949248
},
{
"epoch": 1.01,
"learning_rate": 3.445073354110392e-05,
"loss": 3.5716,
"step": 949760
},
{
"epoch": 1.01,
"learning_rate": 3.44423475935934e-05,
"loss": 3.5843,
"step": 950272
},
{
"epoch": 1.01,
"learning_rate": 3.443396164608288e-05,
"loss": 3.5671,
"step": 950784
},
{
"epoch": 1.01,
"learning_rate": 3.442559207737609e-05,
"loss": 3.5806,
"step": 951296
},
{
"epoch": 1.01,
"learning_rate": 3.441720612986557e-05,
"loss": 3.5919,
"step": 951808
},
{
"epoch": 1.01,
"learning_rate": 3.440882018235505e-05,
"loss": 3.5805,
"step": 952320
},
{
"epoch": 1.01,
"learning_rate": 3.440043423484453e-05,
"loss": 3.5878,
"step": 952832
},
{
"epoch": 1.01,
"learning_rate": 3.439204828733401e-05,
"loss": 3.5831,
"step": 953344
},
{
"epoch": 1.01,
"learning_rate": 3.438367871862722e-05,
"loss": 3.5968,
"step": 953856
},
{
"epoch": 1.01,
"learning_rate": 3.43752927711167e-05,
"loss": 3.5782,
"step": 954368
},
{
"epoch": 1.01,
"learning_rate": 3.4366906823606185e-05,
"loss": 3.5893,
"step": 954880
},
{
"epoch": 1.01,
"learning_rate": 3.4358520876095665e-05,
"loss": 3.5763,
"step": 955392
},
{
"epoch": 1.01,
"learning_rate": 3.4350151307388874e-05,
"loss": 3.5678,
"step": 955904
},
{
"epoch": 1.01,
"learning_rate": 3.4341765359878354e-05,
"loss": 3.583,
"step": 956416
},
{
"epoch": 1.01,
"learning_rate": 3.4333379412367834e-05,
"loss": 3.5867,
"step": 956928
},
{
"epoch": 1.01,
"learning_rate": 3.4324993464857314e-05,
"loss": 3.5861,
"step": 957440
},
{
"epoch": 1.01,
"learning_rate": 3.4316607517346794e-05,
"loss": 3.5963,
"step": 957952
},
{
"epoch": 1.01,
"learning_rate": 3.430823794864e-05,
"loss": 3.5737,
"step": 958464
},
{
"epoch": 1.01,
"learning_rate": 3.429985200112948e-05,
"loss": 3.5727,
"step": 958976
},
{
"epoch": 1.01,
"learning_rate": 3.429146605361896e-05,
"loss": 3.5803,
"step": 959488
},
{
"epoch": 1.01,
"learning_rate": 3.428308010610844e-05,
"loss": 3.5883,
"step": 960000
},
{
"epoch": 1.01,
"learning_rate": 3.427471053740165e-05,
"loss": 3.5768,
"step": 960512
},
{
"epoch": 1.01,
"learning_rate": 3.426632458989113e-05,
"loss": 3.5732,
"step": 961024
},
{
"epoch": 1.01,
"learning_rate": 3.425793864238062e-05,
"loss": 3.5782,
"step": 961536
},
{
"epoch": 1.02,
"learning_rate": 3.42495526948701e-05,
"loss": 3.5763,
"step": 962048
},
{
"epoch": 1.02,
"learning_rate": 3.424116674735958e-05,
"loss": 3.578,
"step": 962560
},
{
"epoch": 1.02,
"learning_rate": 3.423279717865279e-05,
"loss": 3.5766,
"step": 963072
},
{
"epoch": 1.02,
"learning_rate": 3.422441123114227e-05,
"loss": 3.586,
"step": 963584
},
{
"epoch": 1.02,
"learning_rate": 3.421602528363175e-05,
"loss": 3.5865,
"step": 964096
},
{
"epoch": 1.02,
"learning_rate": 3.420763933612123e-05,
"loss": 3.581,
"step": 964608
},
{
"epoch": 1.02,
"learning_rate": 3.419925338861071e-05,
"loss": 3.5699,
"step": 965120
},
{
"epoch": 1.02,
"learning_rate": 3.419088381990392e-05,
"loss": 3.5759,
"step": 965632
},
{
"epoch": 1.02,
"learning_rate": 3.41824978723934e-05,
"loss": 3.5788,
"step": 966144
},
{
"epoch": 1.02,
"learning_rate": 3.417411192488288e-05,
"loss": 3.591,
"step": 966656
},
{
"epoch": 1.02,
"learning_rate": 3.416572597737236e-05,
"loss": 3.5753,
"step": 967168
},
{
"epoch": 1.02,
"learning_rate": 3.415735640866557e-05,
"loss": 3.5776,
"step": 967680
},
{
"epoch": 1.02,
"learning_rate": 3.414897046115505e-05,
"loss": 3.5834,
"step": 968192
},
{
"epoch": 1.02,
"learning_rate": 3.414058451364453e-05,
"loss": 3.5768,
"step": 968704
},
{
"epoch": 1.02,
"learning_rate": 3.413219856613401e-05,
"loss": 3.5815,
"step": 969216
},
{
"epoch": 1.02,
"learning_rate": 3.4123812618623486e-05,
"loss": 3.5767,
"step": 969728
},
{
"epoch": 1.02,
"learning_rate": 3.41154430499167e-05,
"loss": 3.5663,
"step": 970240
},
{
"epoch": 1.02,
"learning_rate": 3.410705710240618e-05,
"loss": 3.5855,
"step": 970752
},
{
"epoch": 1.02,
"learning_rate": 3.4098671154895655e-05,
"loss": 3.5737,
"step": 971264
},
{
"epoch": 1.02,
"learning_rate": 3.4090285207385135e-05,
"loss": 3.572,
"step": 971776
},
{
"epoch": 1.02,
"learning_rate": 3.408191563867835e-05,
"loss": 3.5656,
"step": 972288
},
{
"epoch": 1.02,
"learning_rate": 3.407352969116783e-05,
"loss": 3.5775,
"step": 972800
},
{
"epoch": 1.02,
"learning_rate": 3.406514374365731e-05,
"loss": 3.5836,
"step": 973312
},
{
"epoch": 1.02,
"learning_rate": 3.405675779614679e-05,
"loss": 3.5673,
"step": 973824
},
{
"epoch": 1.02,
"learning_rate": 3.4048388227440006e-05,
"loss": 3.5823,
"step": 974336
},
{
"epoch": 1.02,
"learning_rate": 3.4040002279929486e-05,
"loss": 3.5896,
"step": 974848
},
{
"epoch": 1.02,
"learning_rate": 3.403161633241896e-05,
"loss": 3.5878,
"step": 975360
},
{
"epoch": 1.02,
"learning_rate": 3.402323038490844e-05,
"loss": 3.5771,
"step": 975872
},
{
"epoch": 1.02,
"learning_rate": 3.4014860816201655e-05,
"loss": 3.573,
"step": 976384
},
{
"epoch": 1.02,
"learning_rate": 3.400647486869113e-05,
"loss": 3.5758,
"step": 976896
},
{
"epoch": 1.02,
"learning_rate": 3.399808892118061e-05,
"loss": 3.5846,
"step": 977408
},
{
"epoch": 1.02,
"learning_rate": 3.398970297367009e-05,
"loss": 3.5648,
"step": 977920
},
{
"epoch": 1.02,
"learning_rate": 3.398131702615957e-05,
"loss": 3.5721,
"step": 978432
},
{
"epoch": 1.02,
"learning_rate": 3.397294745745278e-05,
"loss": 3.5724,
"step": 978944
},
{
"epoch": 1.02,
"learning_rate": 3.3964561509942264e-05,
"loss": 3.5815,
"step": 979456
},
{
"epoch": 1.02,
"learning_rate": 3.3956175562431744e-05,
"loss": 3.5806,
"step": 979968
},
{
"epoch": 1.02,
"learning_rate": 3.3947789614921224e-05,
"loss": 3.5796,
"step": 980480
},
{
"epoch": 1.02,
"learning_rate": 3.393942004621443e-05,
"loss": 3.5699,
"step": 980992
},
{
"epoch": 1.02,
"learning_rate": 3.393103409870391e-05,
"loss": 3.5758,
"step": 981504
},
{
"epoch": 1.02,
"learning_rate": 3.392264815119339e-05,
"loss": 3.5912,
"step": 982016
},
{
"epoch": 1.02,
"learning_rate": 3.391426220368287e-05,
"loss": 3.5767,
"step": 982528
},
{
"epoch": 1.02,
"learning_rate": 3.390589263497608e-05,
"loss": 3.587,
"step": 983040
},
{
"epoch": 1.02,
"learning_rate": 3.389750668746556e-05,
"loss": 3.5631,
"step": 983552
},
{
"epoch": 1.02,
"learning_rate": 3.388912073995504e-05,
"loss": 3.5838,
"step": 984064
},
{
"epoch": 1.02,
"learning_rate": 3.388073479244452e-05,
"loss": 3.5807,
"step": 984576
},
{
"epoch": 1.02,
"learning_rate": 3.387236522373773e-05,
"loss": 3.582,
"step": 985088
},
{
"epoch": 1.02,
"learning_rate": 3.386397927622722e-05,
"loss": 3.5857,
"step": 985600
},
{
"epoch": 1.02,
"learning_rate": 3.38555933287167e-05,
"loss": 3.5722,
"step": 986112
},
{
"epoch": 1.02,
"learning_rate": 3.384720738120618e-05,
"loss": 3.5846,
"step": 986624
},
{
"epoch": 1.02,
"learning_rate": 3.383883781249939e-05,
"loss": 3.5908,
"step": 987136
},
{
"epoch": 1.02,
"learning_rate": 3.383045186498887e-05,
"loss": 3.5797,
"step": 987648
},
{
"epoch": 1.02,
"learning_rate": 3.382206591747835e-05,
"loss": 3.5768,
"step": 988160
},
{
"epoch": 1.02,
"learning_rate": 3.381367996996783e-05,
"loss": 3.5824,
"step": 988672
},
{
"epoch": 1.02,
"learning_rate": 3.3805310401261036e-05,
"loss": 3.5735,
"step": 989184
},
{
"epoch": 1.02,
"learning_rate": 3.3796924453750516e-05,
"loss": 3.5739,
"step": 989696
},
{
"epoch": 1.02,
"learning_rate": 3.3788538506239996e-05,
"loss": 3.5885,
"step": 990208
},
{
"epoch": 1.02,
"learning_rate": 3.3780152558729476e-05,
"loss": 3.5741,
"step": 990720
},
{
"epoch": 1.02,
"learning_rate": 3.3771766611218956e-05,
"loss": 3.5811,
"step": 991232
},
{
"epoch": 1.02,
"learning_rate": 3.376339704251217e-05,
"loss": 3.5757,
"step": 991744
},
{
"epoch": 1.03,
"eval_loss": 3.846700668334961,
"eval_runtime": 303.2792,
"eval_samples_per_second": 1258.217,
"eval_steps_per_second": 39.32,
"step": 992160
},
{
"epoch": 0.0,
"learning_rate": 3.375501109500165e-05,
"loss": 3.5777,
"step": 992256
},
{
"epoch": 0.0,
"learning_rate": 3.374662514749113e-05,
"loss": 3.5623,
"step": 992768
},
{
"epoch": 0.0,
"learning_rate": 3.373823919998061e-05,
"loss": 3.5727,
"step": 993280
},
{
"epoch": 0.0,
"learning_rate": 3.372985325247009e-05,
"loss": 3.5802,
"step": 993792
},
{
"epoch": 0.0,
"learning_rate": 3.37214836837633e-05,
"loss": 3.5814,
"step": 994304
},
{
"epoch": 0.0,
"learning_rate": 3.371309773625278e-05,
"loss": 3.5812,
"step": 994816
},
{
"epoch": 0.0,
"learning_rate": 3.370471178874226e-05,
"loss": 3.5736,
"step": 995328
},
{
"epoch": 0.0,
"learning_rate": 3.369632584123174e-05,
"loss": 3.5747,
"step": 995840
},
{
"epoch": 0.0,
"learning_rate": 3.368795627252495e-05,
"loss": 3.5717,
"step": 996352
},
{
"epoch": 0.0,
"learning_rate": 3.367957032501443e-05,
"loss": 3.5853,
"step": 996864
},
{
"epoch": 0.0,
"learning_rate": 3.367118437750391e-05,
"loss": 3.5688,
"step": 997376
},
{
"epoch": 0.0,
"learning_rate": 3.366279842999339e-05,
"loss": 3.5685,
"step": 997888
},
{
"epoch": 0.0,
"learning_rate": 3.3654428861286605e-05,
"loss": 3.5842,
"step": 998400
},
{
"epoch": 0.0,
"learning_rate": 3.3646042913776085e-05,
"loss": 3.5624,
"step": 998912
},
{
"epoch": 0.0,
"learning_rate": 3.3637656966265565e-05,
"loss": 3.5692,
"step": 999424
},
{
"epoch": 0.0,
"learning_rate": 3.3629271018755045e-05,
"loss": 3.5596,
"step": 999936
},
{
"epoch": 0.0,
"learning_rate": 3.3620901450048254e-05,
"loss": 3.5712,
"step": 1000448
},
{
"epoch": 0.0,
"learning_rate": 3.3612515502537734e-05,
"loss": 3.5637,
"step": 1000960
},
{
"epoch": 0.0,
"learning_rate": 3.3604129555027214e-05,
"loss": 3.5659,
"step": 1001472
},
{
"epoch": 0.0,
"learning_rate": 3.3595743607516694e-05,
"loss": 3.565,
"step": 1001984
},
{
"epoch": 0.0,
"learning_rate": 3.35873740388099e-05,
"loss": 3.5822,
"step": 1002496
},
{
"epoch": 0.0,
"learning_rate": 3.357898809129938e-05,
"loss": 3.5726,
"step": 1003008
},
{
"epoch": 0.0,
"learning_rate": 3.357060214378886e-05,
"loss": 3.5687,
"step": 1003520
},
{
"epoch": 0.0,
"learning_rate": 3.356221619627834e-05,
"loss": 3.5741,
"step": 1004032
},
{
"epoch": 0.0,
"learning_rate": 3.355384662757156e-05,
"loss": 3.5806,
"step": 1004544
},
{
"epoch": 0.0,
"learning_rate": 3.354546068006104e-05,
"loss": 3.563,
"step": 1005056
},
{
"epoch": 0.0,
"learning_rate": 3.353707473255052e-05,
"loss": 3.5613,
"step": 1005568
},
{
"epoch": 0.0,
"learning_rate": 3.352868878504e-05,
"loss": 3.5817,
"step": 1006080
},
{
"epoch": 0.0,
"learning_rate": 3.352030283752948e-05,
"loss": 3.5616,
"step": 1006592
},
{
"epoch": 0.0,
"learning_rate": 3.351193326882269e-05,
"loss": 3.5651,
"step": 1007104
},
{
"epoch": 0.01,
"learning_rate": 3.350354732131217e-05,
"loss": 3.5694,
"step": 1007616
},
{
"epoch": 0.01,
"learning_rate": 3.349516137380165e-05,
"loss": 3.5675,
"step": 1008128
},
{
"epoch": 0.01,
"learning_rate": 3.348679180509486e-05,
"loss": 3.5795,
"step": 1008640
},
{
"epoch": 0.01,
"learning_rate": 3.3478405857584337e-05,
"loss": 3.5809,
"step": 1009152
},
{
"epoch": 0.01,
"learning_rate": 3.3470019910073817e-05,
"loss": 3.5654,
"step": 1009664
},
{
"epoch": 0.01,
"learning_rate": 3.3461633962563296e-05,
"loss": 3.5695,
"step": 1010176
},
{
"epoch": 0.01,
"learning_rate": 3.3453248015052776e-05,
"loss": 3.5765,
"step": 1010688
},
{
"epoch": 0.01,
"learning_rate": 3.344487844634599e-05,
"loss": 3.554,
"step": 1011200
},
{
"epoch": 0.01,
"learning_rate": 3.343649249883547e-05,
"loss": 3.5721,
"step": 1011712
},
{
"epoch": 0.01,
"learning_rate": 3.342810655132495e-05,
"loss": 3.5631,
"step": 1012224
},
{
"epoch": 0.01,
"learning_rate": 3.341972060381443e-05,
"loss": 3.5572,
"step": 1012736
},
{
"epoch": 0.01,
"learning_rate": 3.341135103510764e-05,
"loss": 3.5722,
"step": 1013248
},
{
"epoch": 0.01,
"learning_rate": 3.340296508759712e-05,
"loss": 3.5727,
"step": 1013760
},
{
"epoch": 0.01,
"learning_rate": 3.33945791400866e-05,
"loss": 3.5717,
"step": 1014272
},
{
"epoch": 0.01,
"learning_rate": 3.338619319257608e-05,
"loss": 3.565,
"step": 1014784
},
{
"epoch": 0.01,
"learning_rate": 3.337782362386929e-05,
"loss": 3.5689,
"step": 1015296
},
{
"epoch": 0.01,
"learning_rate": 3.336943767635877e-05,
"loss": 3.564,
"step": 1015808
},
{
"epoch": 0.01,
"learning_rate": 3.336105172884825e-05,
"loss": 3.5705,
"step": 1016320
},
{
"epoch": 0.01,
"learning_rate": 3.335266578133773e-05,
"loss": 3.5435,
"step": 1016832
},
{
"epoch": 0.01,
"learning_rate": 3.3344296212630946e-05,
"loss": 3.5678,
"step": 1017344
},
{
"epoch": 0.01,
"learning_rate": 3.3335910265120426e-05,
"loss": 3.5688,
"step": 1017856
},
{
"epoch": 0.01,
"learning_rate": 3.3327524317609906e-05,
"loss": 3.5757,
"step": 1018368
},
{
"epoch": 0.01,
"learning_rate": 3.3319138370099386e-05,
"loss": 3.5619,
"step": 1018880
},
{
"epoch": 0.01,
"learning_rate": 3.331075242258886e-05,
"loss": 3.5637,
"step": 1019392
},
{
"epoch": 0.01,
"learning_rate": 3.330236647507834e-05,
"loss": 3.5563,
"step": 1019904
},
{
"epoch": 0.01,
"learning_rate": 3.3293996906371555e-05,
"loss": 3.5592,
"step": 1020416
},
{
"epoch": 0.01,
"learning_rate": 3.3285610958861035e-05,
"loss": 3.5774,
"step": 1020928
},
{
"epoch": 0.01,
"learning_rate": 3.327722501135051e-05,
"loss": 3.5477,
"step": 1021440
},
{
"epoch": 0.01,
"learning_rate": 3.326883906383999e-05,
"loss": 3.5761,
"step": 1021952
},
{
"epoch": 0.01,
"learning_rate": 3.3260469495133204e-05,
"loss": 3.5705,
"step": 1022464
},
{
"epoch": 0.01,
"learning_rate": 3.3252083547622684e-05,
"loss": 3.5508,
"step": 1022976
},
{
"epoch": 0.01,
"learning_rate": 3.3243697600112164e-05,
"loss": 3.5754,
"step": 1023488
},
{
"epoch": 0.01,
"learning_rate": 3.3235311652601644e-05,
"loss": 3.552,
"step": 1024000
},
{
"epoch": 0.01,
"learning_rate": 3.3226925705091124e-05,
"loss": 3.5568,
"step": 1024512
},
{
"epoch": 0.01,
"learning_rate": 3.321855613638433e-05,
"loss": 3.5654,
"step": 1025024
},
{
"epoch": 0.01,
"learning_rate": 3.321017018887381e-05,
"loss": 3.5695,
"step": 1025536
},
{
"epoch": 0.01,
"learning_rate": 3.320178424136329e-05,
"loss": 3.5508,
"step": 1026048
},
{
"epoch": 0.01,
"learning_rate": 3.319339829385277e-05,
"loss": 3.5734,
"step": 1026560
},
{
"epoch": 0.01,
"learning_rate": 3.318502872514598e-05,
"loss": 3.5481,
"step": 1027072
},
{
"epoch": 0.01,
"learning_rate": 3.317664277763546e-05,
"loss": 3.5609,
"step": 1027584
},
{
"epoch": 0.01,
"learning_rate": 3.316825683012494e-05,
"loss": 3.5758,
"step": 1028096
},
{
"epoch": 0.01,
"learning_rate": 3.315987088261442e-05,
"loss": 3.5647,
"step": 1028608
},
{
"epoch": 0.01,
"learning_rate": 3.315150131390764e-05,
"loss": 3.5687,
"step": 1029120
},
{
"epoch": 0.01,
"learning_rate": 3.314311536639712e-05,
"loss": 3.5683,
"step": 1029632
},
{
"epoch": 0.01,
"learning_rate": 3.31347294188866e-05,
"loss": 3.5801,
"step": 1030144
},
{
"epoch": 0.01,
"learning_rate": 3.312634347137608e-05,
"loss": 3.5614,
"step": 1030656
},
{
"epoch": 0.01,
"learning_rate": 3.3117973902669286e-05,
"loss": 3.5741,
"step": 1031168
},
{
"epoch": 0.01,
"learning_rate": 3.3109587955158766e-05,
"loss": 3.5545,
"step": 1031680
},
{
"epoch": 0.01,
"learning_rate": 3.3101202007648246e-05,
"loss": 3.5528,
"step": 1032192
},
{
"epoch": 0.01,
"learning_rate": 3.3092816060137726e-05,
"loss": 3.5666,
"step": 1032704
},
{
"epoch": 0.01,
"learning_rate": 3.3084446491430935e-05,
"loss": 3.5669,
"step": 1033216
},
{
"epoch": 0.01,
"learning_rate": 3.3076060543920415e-05,
"loss": 3.569,
"step": 1033728
},
{
"epoch": 0.01,
"learning_rate": 3.3067674596409895e-05,
"loss": 3.5798,
"step": 1034240
},
{
"epoch": 0.01,
"learning_rate": 3.3059288648899375e-05,
"loss": 3.5607,
"step": 1034752
},
{
"epoch": 0.01,
"learning_rate": 3.3050902701388855e-05,
"loss": 3.5522,
"step": 1035264
},
{
"epoch": 0.01,
"learning_rate": 3.304253313268207e-05,
"loss": 3.5591,
"step": 1035776
},
{
"epoch": 0.01,
"learning_rate": 3.303414718517155e-05,
"loss": 3.5717,
"step": 1036288
},
{
"epoch": 0.01,
"learning_rate": 3.302576123766103e-05,
"loss": 3.5574,
"step": 1036800
},
{
"epoch": 0.01,
"learning_rate": 3.301737529015051e-05,
"loss": 3.5572,
"step": 1037312
},
{
"epoch": 0.01,
"learning_rate": 3.300900572144372e-05,
"loss": 3.5607,
"step": 1037824
},
{
"epoch": 0.02,
"learning_rate": 3.30006197739332e-05,
"loss": 3.5559,
"step": 1038336
},
{
"epoch": 0.02,
"learning_rate": 3.299223382642268e-05,
"loss": 3.5629,
"step": 1038848
},
{
"epoch": 0.02,
"learning_rate": 3.298384787891216e-05,
"loss": 3.5592,
"step": 1039360
},
{
"epoch": 0.02,
"learning_rate": 3.297547831020537e-05,
"loss": 3.5704,
"step": 1039872
},
{
"epoch": 0.02,
"learning_rate": 3.296709236269485e-05,
"loss": 3.5724,
"step": 1040384
},
{
"epoch": 0.02,
"learning_rate": 3.295870641518433e-05,
"loss": 3.561,
"step": 1040896
},
{
"epoch": 0.02,
"learning_rate": 3.295032046767381e-05,
"loss": 3.5544,
"step": 1041408
},
{
"epoch": 0.02,
"learning_rate": 3.2941950898967025e-05,
"loss": 3.5578,
"step": 1041920
},
{
"epoch": 0.02,
"learning_rate": 3.2933564951456505e-05,
"loss": 3.5644,
"step": 1042432
},
{
"epoch": 0.02,
"learning_rate": 3.2925179003945985e-05,
"loss": 3.5716,
"step": 1042944
},
{
"epoch": 0.02,
"learning_rate": 3.2916793056435465e-05,
"loss": 3.5612,
"step": 1043456
},
{
"epoch": 0.02,
"learning_rate": 3.2908423487728674e-05,
"loss": 3.5563,
"step": 1043968
},
{
"epoch": 0.02,
"learning_rate": 3.2900037540218154e-05,
"loss": 3.568,
"step": 1044480
},
{
"epoch": 0.02,
"learning_rate": 3.2891651592707634e-05,
"loss": 3.5604,
"step": 1044992
},
{
"epoch": 0.02,
"learning_rate": 3.2883265645197114e-05,
"loss": 3.5586,
"step": 1045504
},
{
"epoch": 0.02,
"learning_rate": 3.2874879697686594e-05,
"loss": 3.5603,
"step": 1046016
},
{
"epoch": 0.02,
"learning_rate": 3.28665101289798e-05,
"loss": 3.5517,
"step": 1046528
},
{
"epoch": 0.02,
"learning_rate": 3.285812418146928e-05,
"loss": 3.5681,
"step": 1047040
},
{
"epoch": 0.02,
"learning_rate": 3.284973823395876e-05,
"loss": 3.5593,
"step": 1047552
},
{
"epoch": 0.02,
"learning_rate": 3.284135228644825e-05,
"loss": 3.5517,
"step": 1048064
},
{
"epoch": 0.02,
"learning_rate": 3.283298271774146e-05,
"loss": 3.5488,
"step": 1048576
},
{
"epoch": 0.02,
"learning_rate": 3.282459677023094e-05,
"loss": 3.5575,
"step": 1049088
},
{
"epoch": 0.02,
"learning_rate": 3.281621082272042e-05,
"loss": 3.5669,
"step": 1049600
},
{
"epoch": 0.02,
"learning_rate": 3.28078248752099e-05,
"loss": 3.5561,
"step": 1050112
},
{
"epoch": 0.02,
"learning_rate": 3.279943892769938e-05,
"loss": 3.5619,
"step": 1050624
},
{
"epoch": 0.02,
"learning_rate": 3.279106935899259e-05,
"loss": 3.5691,
"step": 1051136
},
{
"epoch": 0.02,
"learning_rate": 3.278268341148207e-05,
"loss": 3.5733,
"step": 1051648
},
{
"epoch": 0.02,
"learning_rate": 3.277429746397155e-05,
"loss": 3.563,
"step": 1052160
},
{
"epoch": 0.02,
"learning_rate": 3.276591151646103e-05,
"loss": 3.5534,
"step": 1052672
},
{
"epoch": 0.02,
"learning_rate": 3.2757541947754236e-05,
"loss": 3.5602,
"step": 1053184
},
{
"epoch": 0.02,
"learning_rate": 3.2749156000243716e-05,
"loss": 3.5667,
"step": 1053696
},
{
"epoch": 0.02,
"learning_rate": 3.2740770052733196e-05,
"loss": 3.549,
"step": 1054208
},
{
"epoch": 0.02,
"learning_rate": 3.273238410522268e-05,
"loss": 3.5559,
"step": 1054720
},
{
"epoch": 0.02,
"learning_rate": 3.272401453651589e-05,
"loss": 3.5557,
"step": 1055232
},
{
"epoch": 0.02,
"learning_rate": 3.271562858900537e-05,
"loss": 3.5631,
"step": 1055744
},
{
"epoch": 0.02,
"learning_rate": 3.270724264149485e-05,
"loss": 3.5611,
"step": 1056256
},
{
"epoch": 0.02,
"learning_rate": 3.269885669398433e-05,
"loss": 3.5688,
"step": 1056768
},
{
"epoch": 0.02,
"learning_rate": 3.269048712527754e-05,
"loss": 3.5499,
"step": 1057280
},
{
"epoch": 0.02,
"learning_rate": 3.268210117776702e-05,
"loss": 3.5584,
"step": 1057792
},
{
"epoch": 0.02,
"learning_rate": 3.26737152302565e-05,
"loss": 3.5743,
"step": 1058304
},
{
"epoch": 0.02,
"learning_rate": 3.266532928274598e-05,
"loss": 3.5652,
"step": 1058816
},
{
"epoch": 0.02,
"learning_rate": 3.265694333523546e-05,
"loss": 3.5678,
"step": 1059328
},
{
"epoch": 0.02,
"learning_rate": 3.264857376652867e-05,
"loss": 3.5494,
"step": 1059840
},
{
"epoch": 0.02,
"learning_rate": 3.264018781901815e-05,
"loss": 3.565,
"step": 1060352
},
{
"epoch": 0.02,
"learning_rate": 3.2631801871507637e-05,
"loss": 3.5632,
"step": 1060864
},
{
"epoch": 0.02,
"learning_rate": 3.2623415923997117e-05,
"loss": 3.5637,
"step": 1061376
},
{
"epoch": 0.02,
"learning_rate": 3.2615046355290326e-05,
"loss": 3.5621,
"step": 1061888
},
{
"epoch": 0.02,
"learning_rate": 3.2606660407779806e-05,
"loss": 3.558,
"step": 1062400
},
{
"epoch": 0.02,
"learning_rate": 3.2598274460269286e-05,
"loss": 3.5716,
"step": 1062912
},
{
"epoch": 0.02,
"learning_rate": 3.258988851275876e-05,
"loss": 3.5682,
"step": 1063424
},
{
"epoch": 0.02,
"learning_rate": 3.2581518944051975e-05,
"loss": 3.5688,
"step": 1063936
},
{
"epoch": 0.02,
"learning_rate": 3.2573132996541455e-05,
"loss": 3.5568,
"step": 1064448
},
{
"epoch": 0.02,
"learning_rate": 3.2564747049030934e-05,
"loss": 3.5676,
"step": 1064960
},
{
"epoch": 0.02,
"learning_rate": 3.255636110152041e-05,
"loss": 3.5592,
"step": 1065472
},
{
"epoch": 0.02,
"learning_rate": 3.2547991532813624e-05,
"loss": 3.5546,
"step": 1065984
},
{
"epoch": 0.02,
"learning_rate": 3.2539605585303103e-05,
"loss": 3.5746,
"step": 1066496
},
{
"epoch": 0.02,
"learning_rate": 3.253121963779259e-05,
"loss": 3.5542,
"step": 1067008
},
{
"epoch": 0.02,
"learning_rate": 3.2522833690282063e-05,
"loss": 3.5691,
"step": 1067520
},
{
"epoch": 0.02,
"learning_rate": 3.251446412157528e-05,
"loss": 3.5548,
"step": 1068032
},
{
"epoch": 0.03,
"eval_loss": 3.848128080368042,
"eval_runtime": 304.2609,
"eval_samples_per_second": 1254.157,
"eval_steps_per_second": 39.193,
"step": 1068480
},
{
"epoch": 1.0,
"learning_rate": 3.250607817406476e-05,
"loss": 3.553,
"step": 1068544
},
{
"epoch": 1.0,
"learning_rate": 3.249769222655423e-05,
"loss": 3.5512,
"step": 1069056
},
{
"epoch": 1.0,
"learning_rate": 3.248930627904371e-05,
"loss": 3.5562,
"step": 1069568
},
{
"epoch": 1.0,
"learning_rate": 3.248092033153319e-05,
"loss": 3.5608,
"step": 1070080
},
{
"epoch": 1.0,
"learning_rate": 3.247255076282641e-05,
"loss": 3.5647,
"step": 1070592
},
{
"epoch": 1.0,
"learning_rate": 3.246416481531588e-05,
"loss": 3.5639,
"step": 1071104
},
{
"epoch": 1.0,
"learning_rate": 3.245577886780536e-05,
"loss": 3.5564,
"step": 1071616
},
{
"epoch": 1.0,
"learning_rate": 3.244739292029484e-05,
"loss": 3.5555,
"step": 1072128
},
{
"epoch": 1.0,
"learning_rate": 3.243902335158806e-05,
"loss": 3.5564,
"step": 1072640
},
{
"epoch": 1.0,
"learning_rate": 3.243063740407754e-05,
"loss": 3.5686,
"step": 1073152
},
{
"epoch": 1.0,
"learning_rate": 3.242225145656702e-05,
"loss": 3.5523,
"step": 1073664
},
{
"epoch": 1.0,
"learning_rate": 3.24138655090565e-05,
"loss": 3.556,
"step": 1074176
},
{
"epoch": 1.0,
"learning_rate": 3.240551231915344e-05,
"loss": 3.5672,
"step": 1074688
},
{
"epoch": 1.0,
"learning_rate": 3.239712637164292e-05,
"loss": 3.5453,
"step": 1075200
},
{
"epoch": 1.0,
"learning_rate": 3.23887404241324e-05,
"loss": 3.5511,
"step": 1075712
},
{
"epoch": 1.0,
"learning_rate": 3.238035447662188e-05,
"loss": 3.5466,
"step": 1076224
},
{
"epoch": 1.0,
"learning_rate": 3.2371968529111355e-05,
"loss": 3.5556,
"step": 1076736
},
{
"epoch": 1.0,
"learning_rate": 3.2363582581600835e-05,
"loss": 3.5443,
"step": 1077248
},
{
"epoch": 1.0,
"learning_rate": 3.2355196634090315e-05,
"loss": 3.5494,
"step": 1077760
},
{
"epoch": 1.0,
"learning_rate": 3.2346810686579795e-05,
"loss": 3.5531,
"step": 1078272
},
{
"epoch": 1.0,
"learning_rate": 3.233842473906928e-05,
"loss": 3.5642,
"step": 1078784
},
{
"epoch": 1.0,
"learning_rate": 3.233005517036249e-05,
"loss": 3.5595,
"step": 1079296
},
{
"epoch": 1.0,
"learning_rate": 3.232166922285197e-05,
"loss": 3.5489,
"step": 1079808
},
{
"epoch": 1.0,
"learning_rate": 3.231328327534145e-05,
"loss": 3.5592,
"step": 1080320
},
{
"epoch": 1.0,
"learning_rate": 3.230491370663466e-05,
"loss": 3.5632,
"step": 1080832
},
{
"epoch": 1.0,
"learning_rate": 3.229652775912414e-05,
"loss": 3.5462,
"step": 1081344
},
{
"epoch": 1.0,
"learning_rate": 3.228814181161362e-05,
"loss": 3.5439,
"step": 1081856
},
{
"epoch": 1.0,
"learning_rate": 3.22797558641031e-05,
"loss": 3.5631,
"step": 1082368
},
{
"epoch": 1.0,
"learning_rate": 3.227136991659258e-05,
"loss": 3.5445,
"step": 1082880
},
{
"epoch": 1.0,
"learning_rate": 3.226300034788579e-05,
"loss": 3.5513,
"step": 1083392
},
{
"epoch": 1.01,
"learning_rate": 3.225461440037527e-05,
"loss": 3.5538,
"step": 1083904
},
{
"epoch": 1.01,
"learning_rate": 3.224622845286475e-05,
"loss": 3.5538,
"step": 1084416
},
{
"epoch": 1.01,
"learning_rate": 3.2237842505354235e-05,
"loss": 3.5586,
"step": 1084928
},
{
"epoch": 1.01,
"learning_rate": 3.2229472936647444e-05,
"loss": 3.5663,
"step": 1085440
},
{
"epoch": 1.01,
"learning_rate": 3.2221086989136924e-05,
"loss": 3.5523,
"step": 1085952
},
{
"epoch": 1.01,
"learning_rate": 3.2212701041626404e-05,
"loss": 3.5523,
"step": 1086464
},
{
"epoch": 1.01,
"learning_rate": 3.2204315094115884e-05,
"loss": 3.5599,
"step": 1086976
},
{
"epoch": 1.01,
"learning_rate": 3.2195945525409093e-05,
"loss": 3.5385,
"step": 1087488
},
{
"epoch": 1.01,
"learning_rate": 3.218755957789857e-05,
"loss": 3.5561,
"step": 1088000
},
{
"epoch": 1.01,
"learning_rate": 3.217917363038805e-05,
"loss": 3.5438,
"step": 1088512
},
{
"epoch": 1.01,
"learning_rate": 3.217080406168126e-05,
"loss": 3.5437,
"step": 1089024
},
{
"epoch": 1.01,
"learning_rate": 3.216241811417074e-05,
"loss": 3.554,
"step": 1089536
},
{
"epoch": 1.01,
"learning_rate": 3.215403216666022e-05,
"loss": 3.5605,
"step": 1090048
},
{
"epoch": 1.01,
"learning_rate": 3.21456462191497e-05,
"loss": 3.5505,
"step": 1090560
},
{
"epoch": 1.01,
"learning_rate": 3.213726027163919e-05,
"loss": 3.5506,
"step": 1091072
},
{
"epoch": 1.01,
"learning_rate": 3.21288907029324e-05,
"loss": 3.5522,
"step": 1091584
},
{
"epoch": 1.01,
"learning_rate": 3.212050475542188e-05,
"loss": 3.5462,
"step": 1092096
},
{
"epoch": 1.01,
"learning_rate": 3.211211880791136e-05,
"loss": 3.5547,
"step": 1092608
},
{
"epoch": 1.01,
"learning_rate": 3.210373286040084e-05,
"loss": 3.5281,
"step": 1093120
},
{
"epoch": 1.01,
"learning_rate": 3.209536329169405e-05,
"loss": 3.5498,
"step": 1093632
},
{
"epoch": 1.01,
"learning_rate": 3.208697734418353e-05,
"loss": 3.5516,
"step": 1094144
},
{
"epoch": 1.01,
"learning_rate": 3.207859139667301e-05,
"loss": 3.5608,
"step": 1094656
},
{
"epoch": 1.01,
"learning_rate": 3.207020544916249e-05,
"loss": 3.5464,
"step": 1095168
},
{
"epoch": 1.01,
"learning_rate": 3.2061835880455696e-05,
"loss": 3.544,
"step": 1095680
},
{
"epoch": 1.01,
"learning_rate": 3.2053449932945176e-05,
"loss": 3.5419,
"step": 1096192
},
{
"epoch": 1.01,
"learning_rate": 3.2045063985434656e-05,
"loss": 3.5395,
"step": 1096704
},
{
"epoch": 1.01,
"learning_rate": 3.203667803792414e-05,
"loss": 3.564,
"step": 1097216
},
{
"epoch": 1.01,
"learning_rate": 3.202830846921735e-05,
"loss": 3.5372,
"step": 1097728
},
{
"epoch": 1.01,
"learning_rate": 3.201992252170683e-05,
"loss": 3.557,
"step": 1098240
},
{
"epoch": 1.01,
"learning_rate": 3.201153657419631e-05,
"loss": 3.5526,
"step": 1098752
},
{
"epoch": 1.01,
"learning_rate": 3.200315062668579e-05,
"loss": 3.5391,
"step": 1099264
},
{
"epoch": 1.01,
"learning_rate": 3.199476467917527e-05,
"loss": 3.5576,
"step": 1099776
},
{
"epoch": 1.01,
"learning_rate": 3.198639511046848e-05,
"loss": 3.5375,
"step": 1100288
},
{
"epoch": 1.01,
"learning_rate": 3.197800916295796e-05,
"loss": 3.542,
"step": 1100800
},
{
"epoch": 1.01,
"learning_rate": 3.196962321544744e-05,
"loss": 3.5457,
"step": 1101312
},
{
"epoch": 1.01,
"learning_rate": 3.196123726793692e-05,
"loss": 3.5552,
"step": 1101824
},
{
"epoch": 1.01,
"learning_rate": 3.195286769923013e-05,
"loss": 3.5375,
"step": 1102336
},
{
"epoch": 1.01,
"learning_rate": 3.194448175171961e-05,
"loss": 3.5576,
"step": 1102848
},
{
"epoch": 1.01,
"learning_rate": 3.1936095804209096e-05,
"loss": 3.5303,
"step": 1103360
},
{
"epoch": 1.01,
"learning_rate": 3.1927709856698576e-05,
"loss": 3.5456,
"step": 1103872
},
{
"epoch": 1.01,
"learning_rate": 3.1919340287991785e-05,
"loss": 3.5603,
"step": 1104384
},
{
"epoch": 1.01,
"learning_rate": 3.1910954340481265e-05,
"loss": 3.5522,
"step": 1104896
},
{
"epoch": 1.01,
"learning_rate": 3.1902568392970745e-05,
"loss": 3.5492,
"step": 1105408
},
{
"epoch": 1.01,
"learning_rate": 3.1894182445460225e-05,
"loss": 3.5518,
"step": 1105920
},
{
"epoch": 1.01,
"learning_rate": 3.1885812876753434e-05,
"loss": 3.5624,
"step": 1106432
},
{
"epoch": 1.01,
"learning_rate": 3.1877426929242914e-05,
"loss": 3.5478,
"step": 1106944
},
{
"epoch": 1.01,
"learning_rate": 3.1869040981732394e-05,
"loss": 3.5617,
"step": 1107456
},
{
"epoch": 1.01,
"learning_rate": 3.1860655034221874e-05,
"loss": 3.5377,
"step": 1107968
},
{
"epoch": 1.01,
"learning_rate": 3.185228546551508e-05,
"loss": 3.5347,
"step": 1108480
},
{
"epoch": 1.01,
"learning_rate": 3.184389951800456e-05,
"loss": 3.5492,
"step": 1108992
},
{
"epoch": 1.01,
"learning_rate": 3.183551357049404e-05,
"loss": 3.5506,
"step": 1109504
},
{
"epoch": 1.01,
"learning_rate": 3.182712762298353e-05,
"loss": 3.5495,
"step": 1110016
},
{
"epoch": 1.01,
"learning_rate": 3.181874167547301e-05,
"loss": 3.5654,
"step": 1110528
},
{
"epoch": 1.01,
"learning_rate": 3.181037210676622e-05,
"loss": 3.5473,
"step": 1111040
},
{
"epoch": 1.01,
"learning_rate": 3.18019861592557e-05,
"loss": 3.5337,
"step": 1111552
},
{
"epoch": 1.01,
"learning_rate": 3.179360021174518e-05,
"loss": 3.5464,
"step": 1112064
},
{
"epoch": 1.01,
"learning_rate": 3.178521426423466e-05,
"loss": 3.5527,
"step": 1112576
},
{
"epoch": 1.01,
"learning_rate": 3.177684469552787e-05,
"loss": 3.5431,
"step": 1113088
},
{
"epoch": 1.01,
"learning_rate": 3.176845874801735e-05,
"loss": 3.541,
"step": 1113600
},
{
"epoch": 1.01,
"learning_rate": 3.176007280050683e-05,
"loss": 3.5476,
"step": 1114112
},
{
"epoch": 1.02,
"learning_rate": 3.175168685299631e-05,
"loss": 3.5382,
"step": 1114624
},
{
"epoch": 1.02,
"learning_rate": 3.174330090548578e-05,
"loss": 3.5496,
"step": 1115136
},
{
"epoch": 1.02,
"learning_rate": 3.1734931336779e-05,
"loss": 3.5411,
"step": 1115648
},
{
"epoch": 1.02,
"learning_rate": 3.1726545389268484e-05,
"loss": 3.5522,
"step": 1116160
},
{
"epoch": 1.02,
"learning_rate": 3.1718159441757964e-05,
"loss": 3.5599,
"step": 1116672
},
{
"epoch": 1.02,
"learning_rate": 3.170977349424744e-05,
"loss": 3.5477,
"step": 1117184
},
{
"epoch": 1.02,
"learning_rate": 3.170138754673692e-05,
"loss": 3.5371,
"step": 1117696
},
{
"epoch": 1.02,
"learning_rate": 3.169301797803013e-05,
"loss": 3.5446,
"step": 1118208
},
{
"epoch": 1.02,
"learning_rate": 3.1684632030519606e-05,
"loss": 3.5466,
"step": 1118720
},
{
"epoch": 1.02,
"learning_rate": 3.1676246083009086e-05,
"loss": 3.5556,
"step": 1119232
},
{
"epoch": 1.02,
"learning_rate": 3.1667860135498566e-05,
"loss": 3.5452,
"step": 1119744
},
{
"epoch": 1.02,
"learning_rate": 3.165949056679178e-05,
"loss": 3.5414,
"step": 1120256
},
{
"epoch": 1.02,
"learning_rate": 3.1651104619281255e-05,
"loss": 3.5482,
"step": 1120768
},
{
"epoch": 1.02,
"learning_rate": 3.1642718671770735e-05,
"loss": 3.5453,
"step": 1121280
},
{
"epoch": 1.02,
"learning_rate": 3.163433272426022e-05,
"loss": 3.5469,
"step": 1121792
},
{
"epoch": 1.02,
"learning_rate": 3.162596315555344e-05,
"loss": 3.5435,
"step": 1122304
},
{
"epoch": 1.02,
"learning_rate": 3.161757720804291e-05,
"loss": 3.5406,
"step": 1122816
},
{
"epoch": 1.02,
"learning_rate": 3.160919126053239e-05,
"loss": 3.5492,
"step": 1123328
},
{
"epoch": 1.02,
"learning_rate": 3.160080531302187e-05,
"loss": 3.5439,
"step": 1123840
},
{
"epoch": 1.02,
"learning_rate": 3.159241936551135e-05,
"loss": 3.5345,
"step": 1124352
},
{
"epoch": 1.02,
"learning_rate": 3.158404979680456e-05,
"loss": 3.535,
"step": 1124864
},
{
"epoch": 1.02,
"learning_rate": 3.157566384929404e-05,
"loss": 3.5388,
"step": 1125376
},
{
"epoch": 1.02,
"learning_rate": 3.156727790178352e-05,
"loss": 3.5544,
"step": 1125888
},
{
"epoch": 1.02,
"learning_rate": 3.1558891954273e-05,
"loss": 3.5415,
"step": 1126400
},
{
"epoch": 1.02,
"learning_rate": 3.155050600676248e-05,
"loss": 3.5462,
"step": 1126912
},
{
"epoch": 1.02,
"learning_rate": 3.154213643805569e-05,
"loss": 3.5478,
"step": 1127424
},
{
"epoch": 1.02,
"learning_rate": 3.1533750490545175e-05,
"loss": 3.5604,
"step": 1127936
},
{
"epoch": 1.02,
"learning_rate": 3.1525364543034655e-05,
"loss": 3.546,
"step": 1128448
},
{
"epoch": 1.02,
"learning_rate": 3.1516978595524135e-05,
"loss": 3.5368,
"step": 1128960
},
{
"epoch": 1.02,
"learning_rate": 3.1508609026817344e-05,
"loss": 3.5462,
"step": 1129472
},
{
"epoch": 1.02,
"learning_rate": 3.1500223079306824e-05,
"loss": 3.5476,
"step": 1129984
},
{
"epoch": 1.02,
"learning_rate": 3.1491837131796304e-05,
"loss": 3.5318,
"step": 1130496
},
{
"epoch": 1.02,
"learning_rate": 3.1483451184285784e-05,
"loss": 3.539,
"step": 1131008
},
{
"epoch": 1.02,
"learning_rate": 3.147508161557899e-05,
"loss": 3.5409,
"step": 1131520
},
{
"epoch": 1.02,
"learning_rate": 3.146669566806847e-05,
"loss": 3.5471,
"step": 1132032
},
{
"epoch": 1.02,
"learning_rate": 3.145830972055795e-05,
"loss": 3.5392,
"step": 1132544
},
{
"epoch": 1.02,
"learning_rate": 3.144992377304743e-05,
"loss": 3.5522,
"step": 1133056
},
{
"epoch": 1.02,
"learning_rate": 3.144155420434064e-05,
"loss": 3.541,
"step": 1133568
},
{
"epoch": 1.02,
"learning_rate": 3.143316825683013e-05,
"loss": 3.5443,
"step": 1134080
},
{
"epoch": 1.02,
"learning_rate": 3.142478230931961e-05,
"loss": 3.5564,
"step": 1134592
},
{
"epoch": 1.02,
"learning_rate": 3.141639636180909e-05,
"loss": 3.5507,
"step": 1135104
},
{
"epoch": 1.02,
"learning_rate": 3.14080267931023e-05,
"loss": 3.549,
"step": 1135616
},
{
"epoch": 1.02,
"learning_rate": 3.139964084559178e-05,
"loss": 3.5377,
"step": 1136128
},
{
"epoch": 1.02,
"learning_rate": 3.139125489808126e-05,
"loss": 3.5478,
"step": 1136640
},
{
"epoch": 1.02,
"learning_rate": 3.138286895057074e-05,
"loss": 3.5493,
"step": 1137152
},
{
"epoch": 1.02,
"learning_rate": 3.137449938186395e-05,
"loss": 3.5457,
"step": 1137664
},
{
"epoch": 1.02,
"learning_rate": 3.136611343435343e-05,
"loss": 3.551,
"step": 1138176
},
{
"epoch": 1.02,
"learning_rate": 3.135772748684291e-05,
"loss": 3.5403,
"step": 1138688
},
{
"epoch": 1.02,
"learning_rate": 3.1349341539332387e-05,
"loss": 3.5568,
"step": 1139200
},
{
"epoch": 1.02,
"learning_rate": 3.1340971970625596e-05,
"loss": 3.5517,
"step": 1139712
},
{
"epoch": 1.02,
"learning_rate": 3.133258602311508e-05,
"loss": 3.5526,
"step": 1140224
},
{
"epoch": 1.02,
"learning_rate": 3.132420007560456e-05,
"loss": 3.5423,
"step": 1140736
},
{
"epoch": 1.02,
"learning_rate": 3.131581412809404e-05,
"loss": 3.5501,
"step": 1141248
},
{
"epoch": 1.02,
"learning_rate": 3.130744455938725e-05,
"loss": 3.5411,
"step": 1141760
},
{
"epoch": 1.02,
"learning_rate": 3.129905861187673e-05,
"loss": 3.5391,
"step": 1142272
},
{
"epoch": 1.02,
"learning_rate": 3.129067266436621e-05,
"loss": 3.5575,
"step": 1142784
},
{
"epoch": 1.02,
"learning_rate": 3.128228671685569e-05,
"loss": 3.5392,
"step": 1143296
},
{
"epoch": 1.02,
"learning_rate": 3.12739171481489e-05,
"loss": 3.5513,
"step": 1143808
},
{
"epoch": 1.02,
"learning_rate": 3.126553120063838e-05,
"loss": 3.5424,
"step": 1144320
},
{
"epoch": 1.03,
"eval_loss": 3.8487377166748047,
"eval_runtime": 304.346,
"eval_samples_per_second": 1253.807,
"eval_steps_per_second": 39.182,
"step": 1144800
},
{
"epoch": 0.0,
"learning_rate": 3.125714525312786e-05,
"loss": 3.5216,
"step": 1144832
},
{
"epoch": 0.0,
"learning_rate": 3.124875930561734e-05,
"loss": 3.5346,
"step": 1145344
},
{
"epoch": 0.0,
"learning_rate": 3.124037335810682e-05,
"loss": 3.5395,
"step": 1145856
},
{
"epoch": 0.0,
"learning_rate": 3.12319874105963e-05,
"loss": 3.5488,
"step": 1146368
},
{
"epoch": 0.0,
"learning_rate": 3.122360146308578e-05,
"loss": 3.5455,
"step": 1146880
},
{
"epoch": 0.0,
"learning_rate": 3.1215231894378996e-05,
"loss": 3.5507,
"step": 1147392
},
{
"epoch": 0.0,
"learning_rate": 3.1206845946868476e-05,
"loss": 3.5405,
"step": 1147904
},
{
"epoch": 0.0,
"learning_rate": 3.1198459999357956e-05,
"loss": 3.5392,
"step": 1148416
},
{
"epoch": 0.0,
"learning_rate": 3.1190074051847436e-05,
"loss": 3.5407,
"step": 1148928
},
{
"epoch": 0.0,
"learning_rate": 3.1181704483140645e-05,
"loss": 3.5534,
"step": 1149440
},
{
"epoch": 0.0,
"learning_rate": 3.1173318535630125e-05,
"loss": 3.5343,
"step": 1149952
},
{
"epoch": 0.0,
"learning_rate": 3.1164932588119605e-05,
"loss": 3.5417,
"step": 1150464
},
{
"epoch": 0.0,
"learning_rate": 3.1156563019412814e-05,
"loss": 3.5493,
"step": 1150976
},
{
"epoch": 0.0,
"learning_rate": 3.1148177071902294e-05,
"loss": 3.5357,
"step": 1151488
},
{
"epoch": 0.0,
"learning_rate": 3.1139791124391774e-05,
"loss": 3.5371,
"step": 1152000
},
{
"epoch": 0.0,
"learning_rate": 3.1131405176881254e-05,
"loss": 3.5328,
"step": 1152512
},
{
"epoch": 0.0,
"learning_rate": 3.1123019229370734e-05,
"loss": 3.5341,
"step": 1153024
},
{
"epoch": 0.0,
"learning_rate": 3.1114633281860214e-05,
"loss": 3.5337,
"step": 1153536
},
{
"epoch": 0.0,
"learning_rate": 3.1106247334349694e-05,
"loss": 3.5353,
"step": 1154048
},
{
"epoch": 0.0,
"learning_rate": 3.1097861386839174e-05,
"loss": 3.5358,
"step": 1154560
},
{
"epoch": 0.0,
"learning_rate": 3.1089475439328654e-05,
"loss": 3.548,
"step": 1155072
},
{
"epoch": 0.0,
"learning_rate": 3.108110587062186e-05,
"loss": 3.5389,
"step": 1155584
},
{
"epoch": 0.0,
"learning_rate": 3.107271992311134e-05,
"loss": 3.5373,
"step": 1156096
},
{
"epoch": 0.0,
"learning_rate": 3.106433397560082e-05,
"loss": 3.5442,
"step": 1156608
},
{
"epoch": 0.0,
"learning_rate": 3.10559480280903e-05,
"loss": 3.5508,
"step": 1157120
},
{
"epoch": 0.0,
"learning_rate": 3.104757845938351e-05,
"loss": 3.5284,
"step": 1157632
},
{
"epoch": 0.0,
"learning_rate": 3.103919251187299e-05,
"loss": 3.5319,
"step": 1158144
},
{
"epoch": 0.0,
"learning_rate": 3.103080656436247e-05,
"loss": 3.5444,
"step": 1158656
},
{
"epoch": 0.0,
"learning_rate": 3.102242061685195e-05,
"loss": 3.5322,
"step": 1159168
},
{
"epoch": 0.0,
"learning_rate": 3.101405104814517e-05,
"loss": 3.5341,
"step": 1159680
},
{
"epoch": 0.01,
"learning_rate": 3.100566510063465e-05,
"loss": 3.5347,
"step": 1160192
},
{
"epoch": 0.01,
"learning_rate": 3.099727915312413e-05,
"loss": 3.5414,
"step": 1160704
},
{
"epoch": 0.01,
"learning_rate": 3.098889320561361e-05,
"loss": 3.5444,
"step": 1161216
},
{
"epoch": 0.01,
"learning_rate": 3.0980523636906816e-05,
"loss": 3.5484,
"step": 1161728
},
{
"epoch": 0.01,
"learning_rate": 3.0972137689396296e-05,
"loss": 3.5388,
"step": 1162240
},
{
"epoch": 0.01,
"learning_rate": 3.0963751741885776e-05,
"loss": 3.5338,
"step": 1162752
},
{
"epoch": 0.01,
"learning_rate": 3.0955365794375256e-05,
"loss": 3.542,
"step": 1163264
},
{
"epoch": 0.01,
"learning_rate": 3.0946996225668465e-05,
"loss": 3.525,
"step": 1163776
},
{
"epoch": 0.01,
"learning_rate": 3.0938610278157945e-05,
"loss": 3.5446,
"step": 1164288
},
{
"epoch": 0.01,
"learning_rate": 3.0930224330647425e-05,
"loss": 3.528,
"step": 1164800
},
{
"epoch": 0.01,
"learning_rate": 3.0921838383136905e-05,
"loss": 3.53,
"step": 1165312
},
{
"epoch": 0.01,
"learning_rate": 3.091346881443012e-05,
"loss": 3.5345,
"step": 1165824
},
{
"epoch": 0.01,
"learning_rate": 3.09050828669196e-05,
"loss": 3.5446,
"step": 1166336
},
{
"epoch": 0.01,
"learning_rate": 3.089669691940908e-05,
"loss": 3.5375,
"step": 1166848
},
{
"epoch": 0.01,
"learning_rate": 3.088831097189856e-05,
"loss": 3.5377,
"step": 1167360
},
{
"epoch": 0.01,
"learning_rate": 3.087994140319177e-05,
"loss": 3.5365,
"step": 1167872
},
{
"epoch": 0.01,
"learning_rate": 3.087155545568125e-05,
"loss": 3.5335,
"step": 1168384
},
{
"epoch": 0.01,
"learning_rate": 3.086316950817073e-05,
"loss": 3.5429,
"step": 1168896
},
{
"epoch": 0.01,
"learning_rate": 3.085478356066021e-05,
"loss": 3.51,
"step": 1169408
},
{
"epoch": 0.01,
"learning_rate": 3.084639761314969e-05,
"loss": 3.5309,
"step": 1169920
},
{
"epoch": 0.01,
"learning_rate": 3.08380280444429e-05,
"loss": 3.5436,
"step": 1170432
},
{
"epoch": 0.01,
"learning_rate": 3.082964209693238e-05,
"loss": 3.54,
"step": 1170944
},
{
"epoch": 0.01,
"learning_rate": 3.082125614942186e-05,
"loss": 3.5274,
"step": 1171456
},
{
"epoch": 0.01,
"learning_rate": 3.0812870201911346e-05,
"loss": 3.5333,
"step": 1171968
},
{
"epoch": 0.01,
"learning_rate": 3.0804500633204555e-05,
"loss": 3.5271,
"step": 1172480
},
{
"epoch": 0.01,
"learning_rate": 3.0796114685694035e-05,
"loss": 3.5235,
"step": 1172992
},
{
"epoch": 0.01,
"learning_rate": 3.0787728738183515e-05,
"loss": 3.551,
"step": 1173504
},
{
"epoch": 0.01,
"learning_rate": 3.0779342790672995e-05,
"loss": 3.5206,
"step": 1174016
},
{
"epoch": 0.01,
"learning_rate": 3.0770973221966204e-05,
"loss": 3.5405,
"step": 1174528
},
{
"epoch": 0.01,
"learning_rate": 3.0762587274455684e-05,
"loss": 3.5332,
"step": 1175040
},
{
"epoch": 0.01,
"learning_rate": 3.0754201326945164e-05,
"loss": 3.5278,
"step": 1175552
},
{
"epoch": 0.01,
"learning_rate": 3.0745815379434644e-05,
"loss": 3.5385,
"step": 1176064
},
{
"epoch": 0.01,
"learning_rate": 3.073744581072785e-05,
"loss": 3.5248,
"step": 1176576
},
{
"epoch": 0.01,
"learning_rate": 3.072905986321733e-05,
"loss": 3.5285,
"step": 1177088
},
{
"epoch": 0.01,
"learning_rate": 3.072067391570681e-05,
"loss": 3.5268,
"step": 1177600
},
{
"epoch": 0.01,
"learning_rate": 3.07122879681963e-05,
"loss": 3.5439,
"step": 1178112
},
{
"epoch": 0.01,
"learning_rate": 3.070390202068578e-05,
"loss": 3.5193,
"step": 1178624
},
{
"epoch": 0.01,
"learning_rate": 3.069553245197899e-05,
"loss": 3.5402,
"step": 1179136
},
{
"epoch": 0.01,
"learning_rate": 3.068714650446847e-05,
"loss": 3.5166,
"step": 1179648
},
{
"epoch": 0.01,
"learning_rate": 3.067876055695795e-05,
"loss": 3.5288,
"step": 1180160
},
{
"epoch": 0.01,
"learning_rate": 3.067037460944743e-05,
"loss": 3.5431,
"step": 1180672
},
{
"epoch": 0.01,
"learning_rate": 3.066200504074064e-05,
"loss": 3.5418,
"step": 1181184
},
{
"epoch": 0.01,
"learning_rate": 3.065361909323012e-05,
"loss": 3.5322,
"step": 1181696
},
{
"epoch": 0.01,
"learning_rate": 3.06452331457196e-05,
"loss": 3.5367,
"step": 1182208
},
{
"epoch": 0.01,
"learning_rate": 3.063684719820908e-05,
"loss": 3.5499,
"step": 1182720
},
{
"epoch": 0.01,
"learning_rate": 3.0628477629502286e-05,
"loss": 3.5281,
"step": 1183232
},
{
"epoch": 0.01,
"learning_rate": 3.0620091681991766e-05,
"loss": 3.5451,
"step": 1183744
},
{
"epoch": 0.01,
"learning_rate": 3.061170573448125e-05,
"loss": 3.5251,
"step": 1184256
},
{
"epoch": 0.01,
"learning_rate": 3.060331978697073e-05,
"loss": 3.5214,
"step": 1184768
},
{
"epoch": 0.01,
"learning_rate": 3.059493383946021e-05,
"loss": 3.5285,
"step": 1185280
},
{
"epoch": 0.01,
"learning_rate": 3.058656427075342e-05,
"loss": 3.5361,
"step": 1185792
},
{
"epoch": 0.01,
"learning_rate": 3.05781783232429e-05,
"loss": 3.5386,
"step": 1186304
},
{
"epoch": 0.01,
"learning_rate": 3.056979237573238e-05,
"loss": 3.5474,
"step": 1186816
},
{
"epoch": 0.01,
"learning_rate": 3.056140642822186e-05,
"loss": 3.5402,
"step": 1187328
},
{
"epoch": 0.01,
"learning_rate": 3.055303685951507e-05,
"loss": 3.5161,
"step": 1187840
},
{
"epoch": 0.01,
"learning_rate": 3.054465091200455e-05,
"loss": 3.5276,
"step": 1188352
},
{
"epoch": 0.01,
"learning_rate": 3.053626496449403e-05,
"loss": 3.539,
"step": 1188864
},
{
"epoch": 0.01,
"learning_rate": 3.052787901698351e-05,
"loss": 3.5323,
"step": 1189376
},
{
"epoch": 0.01,
"learning_rate": 3.051950944827672e-05,
"loss": 3.5272,
"step": 1189888
},
{
"epoch": 0.01,
"learning_rate": 3.0511123500766203e-05,
"loss": 3.5318,
"step": 1190400
},
{
"epoch": 0.02,
"learning_rate": 3.0502737553255683e-05,
"loss": 3.5242,
"step": 1190912
},
{
"epoch": 0.02,
"learning_rate": 3.0494351605745163e-05,
"loss": 3.5339,
"step": 1191424
},
{
"epoch": 0.02,
"learning_rate": 3.0485982037038376e-05,
"loss": 3.5285,
"step": 1191936
},
{
"epoch": 0.02,
"learning_rate": 3.0477596089527856e-05,
"loss": 3.5355,
"step": 1192448
},
{
"epoch": 0.02,
"learning_rate": 3.0469210142017336e-05,
"loss": 3.5393,
"step": 1192960
},
{
"epoch": 0.02,
"learning_rate": 3.0460824194506815e-05,
"loss": 3.5334,
"step": 1193472
},
{
"epoch": 0.02,
"learning_rate": 3.045243824699629e-05,
"loss": 3.5242,
"step": 1193984
},
{
"epoch": 0.02,
"learning_rate": 3.0444068678289505e-05,
"loss": 3.5287,
"step": 1194496
},
{
"epoch": 0.02,
"learning_rate": 3.0435682730778985e-05,
"loss": 3.5334,
"step": 1195008
},
{
"epoch": 0.02,
"learning_rate": 3.0427296783268468e-05,
"loss": 3.5393,
"step": 1195520
},
{
"epoch": 0.02,
"learning_rate": 3.041891083575794e-05,
"loss": 3.5308,
"step": 1196032
},
{
"epoch": 0.02,
"learning_rate": 3.0410541267051157e-05,
"loss": 3.5263,
"step": 1196544
},
{
"epoch": 0.02,
"learning_rate": 3.0402155319540637e-05,
"loss": 3.5336,
"step": 1197056
},
{
"epoch": 0.02,
"learning_rate": 3.0393769372030117e-05,
"loss": 3.533,
"step": 1197568
},
{
"epoch": 0.02,
"learning_rate": 3.0385383424519593e-05,
"loss": 3.533,
"step": 1198080
},
{
"epoch": 0.02,
"learning_rate": 3.037701385581281e-05,
"loss": 3.5279,
"step": 1198592
},
{
"epoch": 0.02,
"learning_rate": 3.036862790830229e-05,
"loss": 3.5243,
"step": 1199104
},
{
"epoch": 0.02,
"learning_rate": 3.0360241960791762e-05,
"loss": 3.5378,
"step": 1199616
},
{
"epoch": 0.02,
"learning_rate": 3.0351856013281242e-05,
"loss": 3.5313,
"step": 1200128
},
{
"epoch": 0.02,
"learning_rate": 3.0343486444574458e-05,
"loss": 3.5174,
"step": 1200640
},
{
"epoch": 0.02,
"learning_rate": 3.0335100497063938e-05,
"loss": 3.522,
"step": 1201152
},
{
"epoch": 0.02,
"learning_rate": 3.0326714549553415e-05,
"loss": 3.5208,
"step": 1201664
},
{
"epoch": 0.02,
"learning_rate": 3.0318328602042895e-05,
"loss": 3.5395,
"step": 1202176
},
{
"epoch": 0.02,
"learning_rate": 3.030995903333611e-05,
"loss": 3.5279,
"step": 1202688
},
{
"epoch": 0.02,
"learning_rate": 3.030157308582559e-05,
"loss": 3.5296,
"step": 1203200
},
{
"epoch": 0.02,
"learning_rate": 3.0293187138315067e-05,
"loss": 3.5363,
"step": 1203712
},
{
"epoch": 0.02,
"learning_rate": 3.0284801190804547e-05,
"loss": 3.5469,
"step": 1204224
},
{
"epoch": 0.02,
"learning_rate": 3.0276431622097763e-05,
"loss": 3.5304,
"step": 1204736
},
{
"epoch": 0.02,
"learning_rate": 3.0268045674587236e-05,
"loss": 3.5211,
"step": 1205248
},
{
"epoch": 0.02,
"learning_rate": 3.0259659727076716e-05,
"loss": 3.5357,
"step": 1205760
},
{
"epoch": 0.02,
"learning_rate": 3.0251273779566196e-05,
"loss": 3.5282,
"step": 1206272
},
{
"epoch": 0.02,
"learning_rate": 3.0242904210859412e-05,
"loss": 3.5213,
"step": 1206784
},
{
"epoch": 0.02,
"learning_rate": 3.023451826334889e-05,
"loss": 3.5211,
"step": 1207296
},
{
"epoch": 0.02,
"learning_rate": 3.022613231583837e-05,
"loss": 3.5288,
"step": 1207808
},
{
"epoch": 0.02,
"learning_rate": 3.021774636832785e-05,
"loss": 3.5332,
"step": 1208320
},
{
"epoch": 0.02,
"learning_rate": 3.0209376799621064e-05,
"loss": 3.5265,
"step": 1208832
},
{
"epoch": 0.02,
"learning_rate": 3.0200990852110537e-05,
"loss": 3.5375,
"step": 1209344
},
{
"epoch": 0.02,
"learning_rate": 3.019260490460002e-05,
"loss": 3.527,
"step": 1209856
},
{
"epoch": 0.02,
"learning_rate": 3.01842189570895e-05,
"loss": 3.5314,
"step": 1210368
},
{
"epoch": 0.02,
"learning_rate": 3.017584938838271e-05,
"loss": 3.5332,
"step": 1210880
},
{
"epoch": 0.02,
"learning_rate": 3.016746344087219e-05,
"loss": 3.5398,
"step": 1211392
},
{
"epoch": 0.02,
"learning_rate": 3.015907749336167e-05,
"loss": 3.536,
"step": 1211904
},
{
"epoch": 0.02,
"learning_rate": 3.015069154585115e-05,
"loss": 3.5194,
"step": 1212416
},
{
"epoch": 0.02,
"learning_rate": 3.014230559834063e-05,
"loss": 3.5303,
"step": 1212928
},
{
"epoch": 0.02,
"learning_rate": 3.0133936029633842e-05,
"loss": 3.5359,
"step": 1213440
},
{
"epoch": 0.02,
"learning_rate": 3.0125550082123322e-05,
"loss": 3.5295,
"step": 1213952
},
{
"epoch": 0.02,
"learning_rate": 3.0117164134612802e-05,
"loss": 3.5372,
"step": 1214464
},
{
"epoch": 0.02,
"learning_rate": 3.0108778187102282e-05,
"loss": 3.5259,
"step": 1214976
},
{
"epoch": 0.02,
"learning_rate": 3.010040861839549e-05,
"loss": 3.5409,
"step": 1215488
},
{
"epoch": 0.02,
"learning_rate": 3.0092022670884974e-05,
"loss": 3.5354,
"step": 1216000
},
{
"epoch": 0.02,
"learning_rate": 3.0083636723374454e-05,
"loss": 3.5374,
"step": 1216512
},
{
"epoch": 0.02,
"learning_rate": 3.0075250775863934e-05,
"loss": 3.5287,
"step": 1217024
},
{
"epoch": 0.02,
"learning_rate": 3.0066881207157143e-05,
"loss": 3.538,
"step": 1217536
},
{
"epoch": 0.02,
"learning_rate": 3.0058495259646623e-05,
"loss": 3.5284,
"step": 1218048
},
{
"epoch": 0.02,
"learning_rate": 3.0050125690939836e-05,
"loss": 3.5217,
"step": 1218560
},
{
"epoch": 0.02,
"learning_rate": 3.0041739743429316e-05,
"loss": 3.5463,
"step": 1219072
},
{
"epoch": 0.02,
"learning_rate": 3.0033353795918796e-05,
"loss": 3.5278,
"step": 1219584
},
{
"epoch": 0.02,
"learning_rate": 3.0024967848408276e-05,
"loss": 3.5338,
"step": 1220096
},
{
"epoch": 0.02,
"learning_rate": 3.0016581900897756e-05,
"loss": 3.5278,
"step": 1220608
},
{
"epoch": 0.03,
"learning_rate": 3.0008195953387236e-05,
"loss": 3.5221,
"step": 1221120
},
{
"epoch": 0.03,
"eval_loss": 3.8502492904663086,
"eval_runtime": 304.6498,
"eval_samples_per_second": 1252.556,
"eval_steps_per_second": 39.143,
"step": 1221120
},
{
"epoch": 1.0,
"learning_rate": 2.9999810005876716e-05,
"loss": 3.5191,
"step": 1221632
},
{
"epoch": 1.0,
"learning_rate": 2.9991424058366196e-05,
"loss": 3.5242,
"step": 1222144
},
{
"epoch": 1.0,
"learning_rate": 2.9983054489659408e-05,
"loss": 3.532,
"step": 1222656
},
{
"epoch": 1.0,
"learning_rate": 2.9974668542148888e-05,
"loss": 3.5307,
"step": 1223168
},
{
"epoch": 1.0,
"learning_rate": 2.9966282594638368e-05,
"loss": 3.5379,
"step": 1223680
},
{
"epoch": 1.0,
"learning_rate": 2.9957896647127848e-05,
"loss": 3.5253,
"step": 1224192
},
{
"epoch": 1.0,
"learning_rate": 2.9949527078421057e-05,
"loss": 3.5272,
"step": 1224704
},
{
"epoch": 1.0,
"learning_rate": 2.9941141130910537e-05,
"loss": 3.5233,
"step": 1225216
},
{
"epoch": 1.0,
"learning_rate": 2.9932755183400017e-05,
"loss": 3.5436,
"step": 1225728
},
{
"epoch": 1.0,
"learning_rate": 2.99243692358895e-05,
"loss": 3.5211,
"step": 1226240
},
{
"epoch": 1.0,
"learning_rate": 2.991598328837898e-05,
"loss": 3.5269,
"step": 1226752
},
{
"epoch": 1.0,
"learning_rate": 2.990763009847592e-05,
"loss": 3.5346,
"step": 1227264
},
{
"epoch": 1.0,
"learning_rate": 2.98992441509654e-05,
"loss": 3.5229,
"step": 1227776
},
{
"epoch": 1.0,
"learning_rate": 2.9890858203454882e-05,
"loss": 3.5205,
"step": 1228288
},
{
"epoch": 1.0,
"learning_rate": 2.9882472255944362e-05,
"loss": 3.5165,
"step": 1228800
},
{
"epoch": 1.0,
"learning_rate": 2.987408630843384e-05,
"loss": 3.5165,
"step": 1229312
},
{
"epoch": 1.0,
"learning_rate": 2.986570036092332e-05,
"loss": 3.5206,
"step": 1229824
},
{
"epoch": 1.0,
"learning_rate": 2.98573144134128e-05,
"loss": 3.5229,
"step": 1230336
},
{
"epoch": 1.0,
"learning_rate": 2.984892846590228e-05,
"loss": 3.5168,
"step": 1230848
},
{
"epoch": 1.0,
"learning_rate": 2.984054251839176e-05,
"loss": 3.5376,
"step": 1231360
},
{
"epoch": 1.0,
"learning_rate": 2.983217294968497e-05,
"loss": 3.5235,
"step": 1231872
},
{
"epoch": 1.0,
"learning_rate": 2.9823787002174454e-05,
"loss": 3.5203,
"step": 1232384
},
{
"epoch": 1.0,
"learning_rate": 2.9815401054663934e-05,
"loss": 3.5288,
"step": 1232896
},
{
"epoch": 1.0,
"learning_rate": 2.9807015107153414e-05,
"loss": 3.5358,
"step": 1233408
},
{
"epoch": 1.0,
"learning_rate": 2.9798645538446623e-05,
"loss": 3.5157,
"step": 1233920
},
{
"epoch": 1.0,
"learning_rate": 2.9790259590936103e-05,
"loss": 3.5193,
"step": 1234432
},
{
"epoch": 1.0,
"learning_rate": 2.9781873643425583e-05,
"loss": 3.5256,
"step": 1234944
},
{
"epoch": 1.0,
"learning_rate": 2.9773487695915063e-05,
"loss": 3.5245,
"step": 1235456
},
{
"epoch": 1.0,
"learning_rate": 2.9765118127208275e-05,
"loss": 3.5176,
"step": 1235968
},
{
"epoch": 1.01,
"learning_rate": 2.9756732179697755e-05,
"loss": 3.5188,
"step": 1236480
},
{
"epoch": 1.01,
"learning_rate": 2.9748346232187235e-05,
"loss": 3.5287,
"step": 1236992
},
{
"epoch": 1.01,
"learning_rate": 2.9739960284676715e-05,
"loss": 3.5291,
"step": 1237504
},
{
"epoch": 1.01,
"learning_rate": 2.9731590715969924e-05,
"loss": 3.5303,
"step": 1238016
},
{
"epoch": 1.01,
"learning_rate": 2.9723204768459408e-05,
"loss": 3.5272,
"step": 1238528
},
{
"epoch": 1.01,
"learning_rate": 2.9714818820948888e-05,
"loss": 3.5218,
"step": 1239040
},
{
"epoch": 1.01,
"learning_rate": 2.9706432873438368e-05,
"loss": 3.5238,
"step": 1239552
},
{
"epoch": 1.01,
"learning_rate": 2.9698063304731577e-05,
"loss": 3.5118,
"step": 1240064
},
{
"epoch": 1.01,
"learning_rate": 2.9689677357221057e-05,
"loss": 3.5296,
"step": 1240576
},
{
"epoch": 1.01,
"learning_rate": 2.9681291409710537e-05,
"loss": 3.5144,
"step": 1241088
},
{
"epoch": 1.01,
"learning_rate": 2.9672905462200016e-05,
"loss": 3.5159,
"step": 1241600
},
{
"epoch": 1.01,
"learning_rate": 2.966453589349323e-05,
"loss": 3.5191,
"step": 1242112
},
{
"epoch": 1.01,
"learning_rate": 2.965614994598271e-05,
"loss": 3.5325,
"step": 1242624
},
{
"epoch": 1.01,
"learning_rate": 2.964776399847219e-05,
"loss": 3.5243,
"step": 1243136
},
{
"epoch": 1.01,
"learning_rate": 2.963937805096167e-05,
"loss": 3.5207,
"step": 1243648
},
{
"epoch": 1.01,
"learning_rate": 2.9631008482254878e-05,
"loss": 3.5256,
"step": 1244160
},
{
"epoch": 1.01,
"learning_rate": 2.962262253474436e-05,
"loss": 3.5163,
"step": 1244672
},
{
"epoch": 1.01,
"learning_rate": 2.961423658723384e-05,
"loss": 3.5306,
"step": 1245184
},
{
"epoch": 1.01,
"learning_rate": 2.9605850639723314e-05,
"loss": 3.4985,
"step": 1245696
},
{
"epoch": 1.01,
"learning_rate": 2.9597464692212794e-05,
"loss": 3.5131,
"step": 1246208
},
{
"epoch": 1.01,
"learning_rate": 2.958909512350601e-05,
"loss": 3.5266,
"step": 1246720
},
{
"epoch": 1.01,
"learning_rate": 2.958070917599549e-05,
"loss": 3.5275,
"step": 1247232
},
{
"epoch": 1.01,
"learning_rate": 2.9572323228484967e-05,
"loss": 3.5163,
"step": 1247744
},
{
"epoch": 1.01,
"learning_rate": 2.9563937280974447e-05,
"loss": 3.5156,
"step": 1248256
},
{
"epoch": 1.01,
"learning_rate": 2.9555567712267663e-05,
"loss": 3.5179,
"step": 1248768
},
{
"epoch": 1.01,
"learning_rate": 2.9547181764757143e-05,
"loss": 3.5041,
"step": 1249280
},
{
"epoch": 1.01,
"learning_rate": 2.9538795817246616e-05,
"loss": 3.5353,
"step": 1249792
},
{
"epoch": 1.01,
"learning_rate": 2.95304098697361e-05,
"loss": 3.5118,
"step": 1250304
},
{
"epoch": 1.01,
"learning_rate": 2.9522040301029315e-05,
"loss": 3.5264,
"step": 1250816
},
{
"epoch": 1.01,
"learning_rate": 2.9513654353518788e-05,
"loss": 3.52,
"step": 1251328
},
{
"epoch": 1.01,
"learning_rate": 2.9505268406008268e-05,
"loss": 3.5112,
"step": 1251840
},
{
"epoch": 1.01,
"learning_rate": 2.9496882458497748e-05,
"loss": 3.5214,
"step": 1252352
},
{
"epoch": 1.01,
"learning_rate": 2.9488512889790964e-05,
"loss": 3.5122,
"step": 1252864
},
{
"epoch": 1.01,
"learning_rate": 2.948012694228044e-05,
"loss": 3.5144,
"step": 1253376
},
{
"epoch": 1.01,
"learning_rate": 2.947174099476992e-05,
"loss": 3.508,
"step": 1253888
},
{
"epoch": 1.01,
"learning_rate": 2.94633550472594e-05,
"loss": 3.5322,
"step": 1254400
},
{
"epoch": 1.01,
"learning_rate": 2.9454985478552616e-05,
"loss": 3.5106,
"step": 1254912
},
{
"epoch": 1.01,
"learning_rate": 2.944659953104209e-05,
"loss": 3.5222,
"step": 1255424
},
{
"epoch": 1.01,
"learning_rate": 2.943821358353157e-05,
"loss": 3.5028,
"step": 1255936
},
{
"epoch": 1.01,
"learning_rate": 2.9429827636021053e-05,
"loss": 3.5179,
"step": 1256448
},
{
"epoch": 1.01,
"learning_rate": 2.9421458067314262e-05,
"loss": 3.5287,
"step": 1256960
},
{
"epoch": 1.01,
"learning_rate": 2.9413072119803742e-05,
"loss": 3.5254,
"step": 1257472
},
{
"epoch": 1.01,
"learning_rate": 2.9404686172293222e-05,
"loss": 3.5167,
"step": 1257984
},
{
"epoch": 1.01,
"learning_rate": 2.93963002247827e-05,
"loss": 3.5266,
"step": 1258496
},
{
"epoch": 1.01,
"learning_rate": 2.9387930656075914e-05,
"loss": 3.5341,
"step": 1259008
},
{
"epoch": 1.01,
"learning_rate": 2.9379544708565394e-05,
"loss": 3.5165,
"step": 1259520
},
{
"epoch": 1.01,
"learning_rate": 2.9371158761054874e-05,
"loss": 3.5282,
"step": 1260032
},
{
"epoch": 1.01,
"learning_rate": 2.9362772813544354e-05,
"loss": 3.5166,
"step": 1260544
},
{
"epoch": 1.01,
"learning_rate": 2.9354403244837563e-05,
"loss": 3.5079,
"step": 1261056
},
{
"epoch": 1.01,
"learning_rate": 2.9346017297327043e-05,
"loss": 3.517,
"step": 1261568
},
{
"epoch": 1.01,
"learning_rate": 2.9337631349816523e-05,
"loss": 3.519,
"step": 1262080
},
{
"epoch": 1.01,
"learning_rate": 2.9329245402306006e-05,
"loss": 3.5258,
"step": 1262592
},
{
"epoch": 1.01,
"learning_rate": 2.9320875833599215e-05,
"loss": 3.534,
"step": 1263104
},
{
"epoch": 1.01,
"learning_rate": 2.9312489886088695e-05,
"loss": 3.5271,
"step": 1263616
},
{
"epoch": 1.01,
"learning_rate": 2.9304103938578175e-05,
"loss": 3.5017,
"step": 1264128
},
{
"epoch": 1.01,
"learning_rate": 2.9295717991067655e-05,
"loss": 3.5169,
"step": 1264640
},
{
"epoch": 1.01,
"learning_rate": 2.9287348422360868e-05,
"loss": 3.5205,
"step": 1265152
},
{
"epoch": 1.01,
"learning_rate": 2.9278962474850348e-05,
"loss": 3.5194,
"step": 1265664
},
{
"epoch": 1.01,
"learning_rate": 2.9270576527339828e-05,
"loss": 3.5129,
"step": 1266176
},
{
"epoch": 1.01,
"learning_rate": 2.9262190579829308e-05,
"loss": 3.5151,
"step": 1266688
},
{
"epoch": 1.02,
"learning_rate": 2.9253804632318788e-05,
"loss": 3.5104,
"step": 1267200
},
{
"epoch": 1.02,
"learning_rate": 2.9245435063611997e-05,
"loss": 3.5201,
"step": 1267712
},
{
"epoch": 1.02,
"learning_rate": 2.9237049116101477e-05,
"loss": 3.5163,
"step": 1268224
},
{
"epoch": 1.02,
"learning_rate": 2.922866316859096e-05,
"loss": 3.5241,
"step": 1268736
},
{
"epoch": 1.02,
"learning_rate": 2.922029359988417e-05,
"loss": 3.5224,
"step": 1269248
},
{
"epoch": 1.02,
"learning_rate": 2.921190765237365e-05,
"loss": 3.524,
"step": 1269760
},
{
"epoch": 1.02,
"learning_rate": 2.920352170486313e-05,
"loss": 3.5059,
"step": 1270272
},
{
"epoch": 1.02,
"learning_rate": 2.919513575735261e-05,
"loss": 3.5143,
"step": 1270784
},
{
"epoch": 1.02,
"learning_rate": 2.918676618864582e-05,
"loss": 3.5221,
"step": 1271296
},
{
"epoch": 1.02,
"learning_rate": 2.91783802411353e-05,
"loss": 3.5238,
"step": 1271808
},
{
"epoch": 1.02,
"learning_rate": 2.916999429362478e-05,
"loss": 3.5221,
"step": 1272320
},
{
"epoch": 1.02,
"learning_rate": 2.916160834611426e-05,
"loss": 3.5106,
"step": 1272832
},
{
"epoch": 1.02,
"learning_rate": 2.915323877740747e-05,
"loss": 3.5174,
"step": 1273344
},
{
"epoch": 1.02,
"learning_rate": 2.914485282989695e-05,
"loss": 3.5166,
"step": 1273856
},
{
"epoch": 1.02,
"learning_rate": 2.913646688238643e-05,
"loss": 3.5213,
"step": 1274368
},
{
"epoch": 1.02,
"learning_rate": 2.9128080934875914e-05,
"loss": 3.5121,
"step": 1274880
},
{
"epoch": 1.02,
"learning_rate": 2.9119711366169123e-05,
"loss": 3.5103,
"step": 1275392
},
{
"epoch": 1.02,
"learning_rate": 2.9111325418658603e-05,
"loss": 3.524,
"step": 1275904
},
{
"epoch": 1.02,
"learning_rate": 2.9102939471148083e-05,
"loss": 3.5139,
"step": 1276416
},
{
"epoch": 1.02,
"learning_rate": 2.9094553523637563e-05,
"loss": 3.5052,
"step": 1276928
},
{
"epoch": 1.02,
"learning_rate": 2.9086183954930775e-05,
"loss": 3.5078,
"step": 1277440
},
{
"epoch": 1.02,
"learning_rate": 2.9077798007420255e-05,
"loss": 3.5082,
"step": 1277952
},
{
"epoch": 1.02,
"learning_rate": 2.9069412059909735e-05,
"loss": 3.5239,
"step": 1278464
},
{
"epoch": 1.02,
"learning_rate": 2.9061026112399215e-05,
"loss": 3.5151,
"step": 1278976
},
{
"epoch": 1.02,
"learning_rate": 2.9052640164888695e-05,
"loss": 3.5176,
"step": 1279488
},
{
"epoch": 1.02,
"learning_rate": 2.9044270596181904e-05,
"loss": 3.5235,
"step": 1280000
},
{
"epoch": 1.02,
"learning_rate": 2.9035884648671384e-05,
"loss": 3.5326,
"step": 1280512
},
{
"epoch": 1.02,
"learning_rate": 2.9027498701160864e-05,
"loss": 3.5138,
"step": 1281024
},
{
"epoch": 1.02,
"learning_rate": 2.9019112753650347e-05,
"loss": 3.5093,
"step": 1281536
},
{
"epoch": 1.02,
"learning_rate": 2.9010743184943556e-05,
"loss": 3.518,
"step": 1282048
},
{
"epoch": 1.02,
"learning_rate": 2.9002357237433036e-05,
"loss": 3.5179,
"step": 1282560
},
{
"epoch": 1.02,
"learning_rate": 2.8993971289922516e-05,
"loss": 3.5062,
"step": 1283072
},
{
"epoch": 1.02,
"learning_rate": 2.8985585342411996e-05,
"loss": 3.5105,
"step": 1283584
},
{
"epoch": 1.02,
"learning_rate": 2.897721577370521e-05,
"loss": 3.5107,
"step": 1284096
},
{
"epoch": 1.02,
"learning_rate": 2.896882982619469e-05,
"loss": 3.5205,
"step": 1284608
},
{
"epoch": 1.02,
"learning_rate": 2.896044387868417e-05,
"loss": 3.513,
"step": 1285120
},
{
"epoch": 1.02,
"learning_rate": 2.895205793117365e-05,
"loss": 3.5211,
"step": 1285632
},
{
"epoch": 1.02,
"learning_rate": 2.894367198366313e-05,
"loss": 3.5136,
"step": 1286144
},
{
"epoch": 1.02,
"learning_rate": 2.8935302414956338e-05,
"loss": 3.5156,
"step": 1286656
},
{
"epoch": 1.02,
"learning_rate": 2.8926916467445818e-05,
"loss": 3.5165,
"step": 1287168
},
{
"epoch": 1.02,
"learning_rate": 2.89185305199353e-05,
"loss": 3.5286,
"step": 1287680
},
{
"epoch": 1.02,
"learning_rate": 2.891014457242478e-05,
"loss": 3.5203,
"step": 1288192
},
{
"epoch": 1.02,
"learning_rate": 2.890177500371799e-05,
"loss": 3.5127,
"step": 1288704
},
{
"epoch": 1.02,
"learning_rate": 2.889338905620747e-05,
"loss": 3.5096,
"step": 1289216
},
{
"epoch": 1.02,
"learning_rate": 2.888500310869695e-05,
"loss": 3.522,
"step": 1289728
},
{
"epoch": 1.02,
"learning_rate": 2.887661716118643e-05,
"loss": 3.5172,
"step": 1290240
},
{
"epoch": 1.02,
"learning_rate": 2.8868247592479642e-05,
"loss": 3.5253,
"step": 1290752
},
{
"epoch": 1.02,
"learning_rate": 2.8859861644969122e-05,
"loss": 3.5127,
"step": 1291264
},
{
"epoch": 1.02,
"learning_rate": 2.8851475697458602e-05,
"loss": 3.527,
"step": 1291776
},
{
"epoch": 1.02,
"learning_rate": 2.8843089749948082e-05,
"loss": 3.5186,
"step": 1292288
},
{
"epoch": 1.02,
"learning_rate": 2.883472018124129e-05,
"loss": 3.522,
"step": 1292800
},
{
"epoch": 1.02,
"learning_rate": 2.882633423373077e-05,
"loss": 3.518,
"step": 1293312
},
{
"epoch": 1.02,
"learning_rate": 2.8817948286220255e-05,
"loss": 3.5242,
"step": 1293824
},
{
"epoch": 1.02,
"learning_rate": 2.8809562338709735e-05,
"loss": 3.5177,
"step": 1294336
},
{
"epoch": 1.02,
"learning_rate": 2.8801192770002944e-05,
"loss": 3.5055,
"step": 1294848
},
{
"epoch": 1.02,
"learning_rate": 2.8792806822492424e-05,
"loss": 3.5294,
"step": 1295360
},
{
"epoch": 1.02,
"learning_rate": 2.8784420874981904e-05,
"loss": 3.5199,
"step": 1295872
},
{
"epoch": 1.02,
"learning_rate": 2.8776034927471384e-05,
"loss": 3.5201,
"step": 1296384
},
{
"epoch": 1.02,
"learning_rate": 2.8767665358764596e-05,
"loss": 3.5155,
"step": 1296896
},
{
"epoch": 1.02,
"learning_rate": 2.8759279411254076e-05,
"loss": 3.5058,
"step": 1297408
},
{
"epoch": 1.03,
"eval_loss": 3.8516314029693604,
"eval_runtime": 303.9356,
"eval_samples_per_second": 1255.499,
"eval_steps_per_second": 39.235,
"step": 1297440
},
{
"epoch": 0.0,
"learning_rate": 2.8750893463743556e-05,
"loss": 3.5054,
"step": 1297920
},
{
"epoch": 0.0,
"learning_rate": 2.8742507516233036e-05,
"loss": 3.512,
"step": 1298432
},
{
"epoch": 0.0,
"learning_rate": 2.8734121568722516e-05,
"loss": 3.5217,
"step": 1298944
},
{
"epoch": 0.0,
"learning_rate": 2.8725735621211992e-05,
"loss": 3.512,
"step": 1299456
},
{
"epoch": 0.0,
"learning_rate": 2.871736605250521e-05,
"loss": 3.5273,
"step": 1299968
},
{
"epoch": 0.0,
"learning_rate": 2.870898010499469e-05,
"loss": 3.5098,
"step": 1300480
},
{
"epoch": 0.0,
"learning_rate": 2.8700594157484168e-05,
"loss": 3.5143,
"step": 1300992
},
{
"epoch": 0.0,
"learning_rate": 2.869220820997364e-05,
"loss": 3.51,
"step": 1301504
},
{
"epoch": 0.0,
"learning_rate": 2.8683838641266857e-05,
"loss": 3.5278,
"step": 1302016
},
{
"epoch": 0.0,
"learning_rate": 2.8675452693756337e-05,
"loss": 3.5102,
"step": 1302528
},
{
"epoch": 0.0,
"learning_rate": 2.8667066746245814e-05,
"loss": 3.5092,
"step": 1303040
},
{
"epoch": 0.0,
"learning_rate": 2.8658680798735294e-05,
"loss": 3.5161,
"step": 1303552
},
{
"epoch": 0.0,
"learning_rate": 2.865031123002851e-05,
"loss": 3.5137,
"step": 1304064
},
{
"epoch": 0.0,
"learning_rate": 2.864192528251799e-05,
"loss": 3.5074,
"step": 1304576
},
{
"epoch": 0.0,
"learning_rate": 2.8633539335007463e-05,
"loss": 3.5097,
"step": 1305088
},
{
"epoch": 0.0,
"learning_rate": 2.8625153387496946e-05,
"loss": 3.4982,
"step": 1305600
},
{
"epoch": 0.0,
"learning_rate": 2.8616767439986426e-05,
"loss": 3.5085,
"step": 1306112
},
{
"epoch": 0.0,
"learning_rate": 2.8608381492475906e-05,
"loss": 3.5072,
"step": 1306624
},
{
"epoch": 0.0,
"learning_rate": 2.8599995544965386e-05,
"loss": 3.5014,
"step": 1307136
},
{
"epoch": 0.0,
"learning_rate": 2.8591609597454866e-05,
"loss": 3.5306,
"step": 1307648
},
{
"epoch": 0.0,
"learning_rate": 2.8583240028748075e-05,
"loss": 3.5058,
"step": 1308160
},
{
"epoch": 0.0,
"learning_rate": 2.8574854081237555e-05,
"loss": 3.5146,
"step": 1308672
},
{
"epoch": 0.0,
"learning_rate": 2.856646813372704e-05,
"loss": 3.5111,
"step": 1309184
},
{
"epoch": 0.0,
"learning_rate": 2.855808218621652e-05,
"loss": 3.5227,
"step": 1309696
},
{
"epoch": 0.0,
"learning_rate": 2.8549712617509727e-05,
"loss": 3.4999,
"step": 1310208
},
{
"epoch": 0.0,
"learning_rate": 2.8541326669999207e-05,
"loss": 3.5062,
"step": 1310720
},
{
"epoch": 0.0,
"learning_rate": 2.8532940722488687e-05,
"loss": 3.5106,
"step": 1311232
},
{
"epoch": 0.0,
"learning_rate": 2.8524554774978167e-05,
"loss": 3.5105,
"step": 1311744
},
{
"epoch": 0.0,
"learning_rate": 2.851618520627138e-05,
"loss": 3.505,
"step": 1312256
},
{
"epoch": 0.01,
"learning_rate": 2.850779925876086e-05,
"loss": 3.5042,
"step": 1312768
},
{
"epoch": 0.01,
"learning_rate": 2.849941331125034e-05,
"loss": 3.5167,
"step": 1313280
},
{
"epoch": 0.01,
"learning_rate": 2.849102736373982e-05,
"loss": 3.515,
"step": 1313792
},
{
"epoch": 0.01,
"learning_rate": 2.848265779503303e-05,
"loss": 3.518,
"step": 1314304
},
{
"epoch": 0.01,
"learning_rate": 2.847427184752251e-05,
"loss": 3.5131,
"step": 1314816
},
{
"epoch": 0.01,
"learning_rate": 2.8465885900011992e-05,
"loss": 3.5037,
"step": 1315328
},
{
"epoch": 0.01,
"learning_rate": 2.8457499952501472e-05,
"loss": 3.5153,
"step": 1315840
},
{
"epoch": 0.01,
"learning_rate": 2.844913038379468e-05,
"loss": 3.4955,
"step": 1316352
},
{
"epoch": 0.01,
"learning_rate": 2.844074443628416e-05,
"loss": 3.5191,
"step": 1316864
},
{
"epoch": 0.01,
"learning_rate": 2.843235848877364e-05,
"loss": 3.4985,
"step": 1317376
},
{
"epoch": 0.01,
"learning_rate": 2.842397254126312e-05,
"loss": 3.505,
"step": 1317888
},
{
"epoch": 0.01,
"learning_rate": 2.8415602972556333e-05,
"loss": 3.5042,
"step": 1318400
},
{
"epoch": 0.01,
"learning_rate": 2.8407217025045813e-05,
"loss": 3.5177,
"step": 1318912
},
{
"epoch": 0.01,
"learning_rate": 2.8398831077535293e-05,
"loss": 3.5135,
"step": 1319424
},
{
"epoch": 0.01,
"learning_rate": 2.8390445130024773e-05,
"loss": 3.506,
"step": 1319936
},
{
"epoch": 0.01,
"learning_rate": 2.8382075561317982e-05,
"loss": 3.511,
"step": 1320448
},
{
"epoch": 0.01,
"learning_rate": 2.8373689613807462e-05,
"loss": 3.5055,
"step": 1320960
},
{
"epoch": 0.01,
"learning_rate": 2.8365303666296946e-05,
"loss": 3.5153,
"step": 1321472
},
{
"epoch": 0.01,
"learning_rate": 2.8356917718786426e-05,
"loss": 3.4884,
"step": 1321984
},
{
"epoch": 0.01,
"learning_rate": 2.8348548150079635e-05,
"loss": 3.4996,
"step": 1322496
},
{
"epoch": 0.01,
"learning_rate": 2.8340162202569115e-05,
"loss": 3.5136,
"step": 1323008
},
{
"epoch": 0.01,
"learning_rate": 2.8331776255058595e-05,
"loss": 3.5151,
"step": 1323520
},
{
"epoch": 0.01,
"learning_rate": 2.8323390307548075e-05,
"loss": 3.5019,
"step": 1324032
},
{
"epoch": 0.01,
"learning_rate": 2.8315020738841287e-05,
"loss": 3.4981,
"step": 1324544
},
{
"epoch": 0.01,
"learning_rate": 2.8306634791330767e-05,
"loss": 3.5063,
"step": 1325056
},
{
"epoch": 0.01,
"learning_rate": 2.8298248843820247e-05,
"loss": 3.4896,
"step": 1325568
},
{
"epoch": 0.01,
"learning_rate": 2.8289862896309727e-05,
"loss": 3.5169,
"step": 1326080
},
{
"epoch": 0.01,
"learning_rate": 2.8281476948799207e-05,
"loss": 3.5055,
"step": 1326592
},
{
"epoch": 0.01,
"learning_rate": 2.8273107380092416e-05,
"loss": 3.5098,
"step": 1327104
},
{
"epoch": 0.01,
"learning_rate": 2.8264721432581896e-05,
"loss": 3.5046,
"step": 1327616
},
{
"epoch": 0.01,
"learning_rate": 2.825633548507138e-05,
"loss": 3.4976,
"step": 1328128
},
{
"epoch": 0.01,
"learning_rate": 2.824794953756086e-05,
"loss": 3.5099,
"step": 1328640
},
{
"epoch": 0.01,
"learning_rate": 2.823957996885407e-05,
"loss": 3.4997,
"step": 1329152
},
{
"epoch": 0.01,
"learning_rate": 2.823119402134355e-05,
"loss": 3.5008,
"step": 1329664
},
{
"epoch": 0.01,
"learning_rate": 2.8222808073833028e-05,
"loss": 3.4943,
"step": 1330176
},
{
"epoch": 0.01,
"learning_rate": 2.8214422126322508e-05,
"loss": 3.5178,
"step": 1330688
},
{
"epoch": 0.01,
"learning_rate": 2.820605255761572e-05,
"loss": 3.5004,
"step": 1331200
},
{
"epoch": 0.01,
"learning_rate": 2.81976666101052e-05,
"loss": 3.5046,
"step": 1331712
},
{
"epoch": 0.01,
"learning_rate": 2.818928066259468e-05,
"loss": 3.493,
"step": 1332224
},
{
"epoch": 0.01,
"learning_rate": 2.818089471508416e-05,
"loss": 3.5019,
"step": 1332736
},
{
"epoch": 0.01,
"learning_rate": 2.817252514637737e-05,
"loss": 3.514,
"step": 1333248
},
{
"epoch": 0.01,
"learning_rate": 2.816413919886685e-05,
"loss": 3.5121,
"step": 1333760
},
{
"epoch": 0.01,
"learning_rate": 2.8155753251356333e-05,
"loss": 3.504,
"step": 1334272
},
{
"epoch": 0.01,
"learning_rate": 2.8147367303845813e-05,
"loss": 3.5115,
"step": 1334784
},
{
"epoch": 0.01,
"learning_rate": 2.8138997735139022e-05,
"loss": 3.5173,
"step": 1335296
},
{
"epoch": 0.01,
"learning_rate": 2.8130611787628502e-05,
"loss": 3.5069,
"step": 1335808
},
{
"epoch": 0.01,
"learning_rate": 2.8122225840117982e-05,
"loss": 3.5121,
"step": 1336320
},
{
"epoch": 0.01,
"learning_rate": 2.8113839892607462e-05,
"loss": 3.5058,
"step": 1336832
},
{
"epoch": 0.01,
"learning_rate": 2.8105470323900674e-05,
"loss": 3.4937,
"step": 1337344
},
{
"epoch": 0.01,
"learning_rate": 2.8097084376390154e-05,
"loss": 3.5036,
"step": 1337856
},
{
"epoch": 0.01,
"learning_rate": 2.8088698428879634e-05,
"loss": 3.5066,
"step": 1338368
},
{
"epoch": 0.01,
"learning_rate": 2.8080312481369114e-05,
"loss": 3.5101,
"step": 1338880
},
{
"epoch": 0.01,
"learning_rate": 2.8071942912662323e-05,
"loss": 3.5206,
"step": 1339392
},
{
"epoch": 0.01,
"learning_rate": 2.8063556965151803e-05,
"loss": 3.5136,
"step": 1339904
},
{
"epoch": 0.01,
"learning_rate": 2.8055171017641287e-05,
"loss": 3.4888,
"step": 1340416
},
{
"epoch": 0.01,
"learning_rate": 2.8046785070130767e-05,
"loss": 3.5013,
"step": 1340928
},
{
"epoch": 0.01,
"learning_rate": 2.8038415501423976e-05,
"loss": 3.5079,
"step": 1341440
},
{
"epoch": 0.01,
"learning_rate": 2.8030029553913456e-05,
"loss": 3.5066,
"step": 1341952
},
{
"epoch": 0.01,
"learning_rate": 2.8021643606402936e-05,
"loss": 3.5001,
"step": 1342464
},
{
"epoch": 0.01,
"learning_rate": 2.8013257658892416e-05,
"loss": 3.5007,
"step": 1342976
},
{
"epoch": 0.02,
"learning_rate": 2.8004888090185628e-05,
"loss": 3.5008,
"step": 1343488
},
{
"epoch": 0.02,
"learning_rate": 2.7996502142675108e-05,
"loss": 3.5049,
"step": 1344000
},
{
"epoch": 0.02,
"learning_rate": 2.7988116195164588e-05,
"loss": 3.4982,
"step": 1344512
},
{
"epoch": 0.02,
"learning_rate": 2.7979730247654068e-05,
"loss": 3.5114,
"step": 1345024
},
{
"epoch": 0.02,
"learning_rate": 2.7971360678947277e-05,
"loss": 3.5085,
"step": 1345536
},
{
"epoch": 0.02,
"learning_rate": 2.7962974731436757e-05,
"loss": 3.5095,
"step": 1346048
},
{
"epoch": 0.02,
"learning_rate": 2.795458878392624e-05,
"loss": 3.4939,
"step": 1346560
},
{
"epoch": 0.02,
"learning_rate": 2.7946202836415714e-05,
"loss": 3.5033,
"step": 1347072
},
{
"epoch": 0.02,
"learning_rate": 2.793783326770893e-05,
"loss": 3.509,
"step": 1347584
},
{
"epoch": 0.02,
"learning_rate": 2.792944732019841e-05,
"loss": 3.5102,
"step": 1348096
},
{
"epoch": 0.02,
"learning_rate": 2.792106137268789e-05,
"loss": 3.5059,
"step": 1348608
},
{
"epoch": 0.02,
"learning_rate": 2.7912675425177366e-05,
"loss": 3.5018,
"step": 1349120
},
{
"epoch": 0.02,
"learning_rate": 2.7904305856470582e-05,
"loss": 3.5019,
"step": 1349632
},
{
"epoch": 0.02,
"learning_rate": 2.789591990896006e-05,
"loss": 3.5064,
"step": 1350144
},
{
"epoch": 0.02,
"learning_rate": 2.788753396144954e-05,
"loss": 3.5067,
"step": 1350656
},
{
"epoch": 0.02,
"learning_rate": 2.7879148013939015e-05,
"loss": 3.4951,
"step": 1351168
},
{
"epoch": 0.02,
"learning_rate": 2.787077844523223e-05,
"loss": 3.4989,
"step": 1351680
},
{
"epoch": 0.02,
"learning_rate": 2.786239249772171e-05,
"loss": 3.5118,
"step": 1352192
},
{
"epoch": 0.02,
"learning_rate": 2.7854006550211187e-05,
"loss": 3.4995,
"step": 1352704
},
{
"epoch": 0.02,
"learning_rate": 2.7845620602700667e-05,
"loss": 3.4949,
"step": 1353216
},
{
"epoch": 0.02,
"learning_rate": 2.7837251033993883e-05,
"loss": 3.4929,
"step": 1353728
},
{
"epoch": 0.02,
"learning_rate": 2.7828865086483363e-05,
"loss": 3.4917,
"step": 1354240
},
{
"epoch": 0.02,
"learning_rate": 2.782047913897284e-05,
"loss": 3.5132,
"step": 1354752
},
{
"epoch": 0.02,
"learning_rate": 2.781209319146232e-05,
"loss": 3.4998,
"step": 1355264
},
{
"epoch": 0.02,
"learning_rate": 2.7803723622755535e-05,
"loss": 3.5057,
"step": 1355776
},
{
"epoch": 0.02,
"learning_rate": 2.7795337675245015e-05,
"loss": 3.5069,
"step": 1356288
},
{
"epoch": 0.02,
"learning_rate": 2.778695172773449e-05,
"loss": 3.5196,
"step": 1356800
},
{
"epoch": 0.02,
"learning_rate": 2.777856578022397e-05,
"loss": 3.5036,
"step": 1357312
},
{
"epoch": 0.02,
"learning_rate": 2.777017983271345e-05,
"loss": 3.4952,
"step": 1357824
},
{
"epoch": 0.02,
"learning_rate": 2.776181026400666e-05,
"loss": 3.5065,
"step": 1358336
},
{
"epoch": 0.02,
"learning_rate": 2.775342431649614e-05,
"loss": 3.5033,
"step": 1358848
},
{
"epoch": 0.02,
"learning_rate": 2.774503836898562e-05,
"loss": 3.4927,
"step": 1359360
},
{
"epoch": 0.02,
"learning_rate": 2.77366524214751e-05,
"loss": 3.4969,
"step": 1359872
},
{
"epoch": 0.02,
"learning_rate": 2.772828285276831e-05,
"loss": 3.4972,
"step": 1360384
},
{
"epoch": 0.02,
"learning_rate": 2.7719896905257793e-05,
"loss": 3.5104,
"step": 1360896
},
{
"epoch": 0.02,
"learning_rate": 2.7711510957747273e-05,
"loss": 3.4954,
"step": 1361408
},
{
"epoch": 0.02,
"learning_rate": 2.7703125010236753e-05,
"loss": 3.508,
"step": 1361920
},
{
"epoch": 0.02,
"learning_rate": 2.7694755441529962e-05,
"loss": 3.4996,
"step": 1362432
},
{
"epoch": 0.02,
"learning_rate": 2.7686369494019442e-05,
"loss": 3.5039,
"step": 1362944
},
{
"epoch": 0.02,
"learning_rate": 2.7677983546508922e-05,
"loss": 3.4987,
"step": 1363456
},
{
"epoch": 0.02,
"learning_rate": 2.7669597598998402e-05,
"loss": 3.5184,
"step": 1363968
},
{
"epoch": 0.02,
"learning_rate": 2.7661228030291615e-05,
"loss": 3.5079,
"step": 1364480
},
{
"epoch": 0.02,
"learning_rate": 2.7652842082781095e-05,
"loss": 3.4955,
"step": 1364992
},
{
"epoch": 0.02,
"learning_rate": 2.7644456135270575e-05,
"loss": 3.4983,
"step": 1365504
},
{
"epoch": 0.02,
"learning_rate": 2.7636070187760054e-05,
"loss": 3.5061,
"step": 1366016
},
{
"epoch": 0.02,
"learning_rate": 2.7627700619053264e-05,
"loss": 3.5078,
"step": 1366528
},
{
"epoch": 0.02,
"learning_rate": 2.7619314671542747e-05,
"loss": 3.5148,
"step": 1367040
},
{
"epoch": 0.02,
"learning_rate": 2.7610928724032227e-05,
"loss": 3.4982,
"step": 1367552
},
{
"epoch": 0.02,
"learning_rate": 2.7602542776521707e-05,
"loss": 3.5111,
"step": 1368064
},
{
"epoch": 0.02,
"learning_rate": 2.7594173207814916e-05,
"loss": 3.5041,
"step": 1368576
},
{
"epoch": 0.02,
"learning_rate": 2.7585787260304396e-05,
"loss": 3.5128,
"step": 1369088
},
{
"epoch": 0.02,
"learning_rate": 2.7577401312793876e-05,
"loss": 3.5036,
"step": 1369600
},
{
"epoch": 0.02,
"learning_rate": 2.7569031744087088e-05,
"loss": 3.5077,
"step": 1370112
},
{
"epoch": 0.02,
"learning_rate": 2.7560645796576568e-05,
"loss": 3.5047,
"step": 1370624
},
{
"epoch": 0.02,
"learning_rate": 2.7552259849066048e-05,
"loss": 3.4956,
"step": 1371136
},
{
"epoch": 0.02,
"learning_rate": 2.7543890280359257e-05,
"loss": 3.5154,
"step": 1371648
},
{
"epoch": 0.02,
"learning_rate": 2.7535504332848737e-05,
"loss": 3.507,
"step": 1372160
},
{
"epoch": 0.02,
"learning_rate": 2.7527118385338217e-05,
"loss": 3.5054,
"step": 1372672
},
{
"epoch": 0.02,
"learning_rate": 2.75187324378277e-05,
"loss": 3.4992,
"step": 1373184
},
{
"epoch": 0.02,
"learning_rate": 2.751034649031718e-05,
"loss": 3.4945,
"step": 1373696
},
{
"epoch": 0.03,
"eval_loss": 3.853289842605591,
"eval_runtime": 312.3417,
"eval_samples_per_second": 1221.71,
"eval_steps_per_second": 38.179,
"step": 1373760
},
{
"epoch": 0.0,
"learning_rate": 2.750196054280666e-05,
"loss": 3.4912,
"step": 1374208
},
{
"epoch": 0.0,
"learning_rate": 2.749357459529614e-05,
"loss": 3.4972,
"step": 1374720
},
{
"epoch": 0.0,
"learning_rate": 2.748518864778562e-05,
"loss": 3.5084,
"step": 1375232
},
{
"epoch": 0.0,
"learning_rate": 2.74768027002751e-05,
"loss": 3.4973,
"step": 1375744
},
{
"epoch": 0.0,
"learning_rate": 2.746843313156831e-05,
"loss": 3.5182,
"step": 1376256
},
{
"epoch": 0.0,
"learning_rate": 2.746004718405779e-05,
"loss": 3.498,
"step": 1376768
},
{
"epoch": 0.0,
"learning_rate": 2.7451661236547273e-05,
"loss": 3.4996,
"step": 1377280
},
{
"epoch": 0.0,
"learning_rate": 2.7443275289036753e-05,
"loss": 3.4965,
"step": 1377792
},
{
"epoch": 0.0,
"learning_rate": 2.7434905720329962e-05,
"loss": 3.5138,
"step": 1378304
},
{
"epoch": 0.0,
"learning_rate": 2.7426519772819442e-05,
"loss": 3.4989,
"step": 1378816
},
{
"epoch": 0.0,
"learning_rate": 2.7418133825308922e-05,
"loss": 3.4949,
"step": 1379328
},
{
"epoch": 0.0,
"learning_rate": 2.74097478777984e-05,
"loss": 3.4976,
"step": 1379840
},
{
"epoch": 0.0,
"learning_rate": 2.7401378309091614e-05,
"loss": 3.5002,
"step": 1380352
},
{
"epoch": 0.0,
"learning_rate": 2.7392992361581094e-05,
"loss": 3.4925,
"step": 1380864
},
{
"epoch": 0.0,
"learning_rate": 2.7384606414070574e-05,
"loss": 3.498,
"step": 1381376
},
{
"epoch": 0.0,
"learning_rate": 2.7376220466560054e-05,
"loss": 3.4889,
"step": 1381888
},
{
"epoch": 0.0,
"learning_rate": 2.7367850897853263e-05,
"loss": 3.4918,
"step": 1382400
},
{
"epoch": 0.0,
"learning_rate": 2.7359464950342743e-05,
"loss": 3.494,
"step": 1382912
},
{
"epoch": 0.0,
"learning_rate": 2.7351079002832226e-05,
"loss": 3.4883,
"step": 1383424
},
{
"epoch": 0.0,
"learning_rate": 2.7342693055321706e-05,
"loss": 3.5215,
"step": 1383936
},
{
"epoch": 0.0,
"learning_rate": 2.7334323486614915e-05,
"loss": 3.4957,
"step": 1384448
},
{
"epoch": 0.0,
"learning_rate": 2.7325937539104395e-05,
"loss": 3.4934,
"step": 1384960
},
{
"epoch": 0.0,
"learning_rate": 2.7317551591593875e-05,
"loss": 3.5024,
"step": 1385472
},
{
"epoch": 0.0,
"learning_rate": 2.7309165644083355e-05,
"loss": 3.5071,
"step": 1385984
},
{
"epoch": 0.0,
"learning_rate": 2.7300796075376568e-05,
"loss": 3.4899,
"step": 1386496
},
{
"epoch": 0.0,
"learning_rate": 2.7292410127866048e-05,
"loss": 3.494,
"step": 1387008
},
{
"epoch": 0.0,
"learning_rate": 2.7284024180355528e-05,
"loss": 3.4971,
"step": 1387520
},
{
"epoch": 0.0,
"learning_rate": 2.7275638232845008e-05,
"loss": 3.5021,
"step": 1388032
},
{
"epoch": 0.0,
"learning_rate": 2.7267268664138217e-05,
"loss": 3.4867,
"step": 1388544
},
{
"epoch": 0.01,
"learning_rate": 2.7258882716627697e-05,
"loss": 3.4927,
"step": 1389056
},
{
"epoch": 0.01,
"learning_rate": 2.725049676911718e-05,
"loss": 3.5013,
"step": 1389568
},
{
"epoch": 0.01,
"learning_rate": 2.724211082160666e-05,
"loss": 3.5024,
"step": 1390080
},
{
"epoch": 0.01,
"learning_rate": 2.723374125289987e-05,
"loss": 3.5095,
"step": 1390592
},
{
"epoch": 0.01,
"learning_rate": 2.722535530538935e-05,
"loss": 3.5003,
"step": 1391104
},
{
"epoch": 0.01,
"learning_rate": 2.721696935787883e-05,
"loss": 3.4904,
"step": 1391616
},
{
"epoch": 0.01,
"learning_rate": 2.720858341036831e-05,
"loss": 3.4998,
"step": 1392128
},
{
"epoch": 0.01,
"learning_rate": 2.720021384166152e-05,
"loss": 3.4862,
"step": 1392640
},
{
"epoch": 0.01,
"learning_rate": 2.7191827894151e-05,
"loss": 3.5028,
"step": 1393152
},
{
"epoch": 0.01,
"learning_rate": 2.718344194664048e-05,
"loss": 3.4861,
"step": 1393664
},
{
"epoch": 0.01,
"learning_rate": 2.717505599912996e-05,
"loss": 3.4893,
"step": 1394176
},
{
"epoch": 0.01,
"learning_rate": 2.716668643042317e-05,
"loss": 3.4943,
"step": 1394688
},
{
"epoch": 0.01,
"learning_rate": 2.715830048291265e-05,
"loss": 3.5051,
"step": 1395200
},
{
"epoch": 0.01,
"learning_rate": 2.7149914535402134e-05,
"loss": 3.4977,
"step": 1395712
},
{
"epoch": 0.01,
"learning_rate": 2.7141528587891614e-05,
"loss": 3.4925,
"step": 1396224
},
{
"epoch": 0.01,
"learning_rate": 2.7133142640381094e-05,
"loss": 3.4976,
"step": 1396736
},
{
"epoch": 0.01,
"learning_rate": 2.7124773071674303e-05,
"loss": 3.4941,
"step": 1397248
},
{
"epoch": 0.01,
"learning_rate": 2.7116387124163783e-05,
"loss": 3.5017,
"step": 1397760
},
{
"epoch": 0.01,
"learning_rate": 2.7108001176653263e-05,
"loss": 3.4802,
"step": 1398272
},
{
"epoch": 0.01,
"learning_rate": 2.709961522914274e-05,
"loss": 3.4833,
"step": 1398784
},
{
"epoch": 0.01,
"learning_rate": 2.7091245660435955e-05,
"loss": 3.5017,
"step": 1399296
},
{
"epoch": 0.01,
"learning_rate": 2.7082859712925435e-05,
"loss": 3.4991,
"step": 1399808
},
{
"epoch": 0.01,
"learning_rate": 2.7074473765414915e-05,
"loss": 3.4894,
"step": 1400320
},
{
"epoch": 0.01,
"learning_rate": 2.7066087817904388e-05,
"loss": 3.4902,
"step": 1400832
},
{
"epoch": 0.01,
"learning_rate": 2.7057718249197604e-05,
"loss": 3.4931,
"step": 1401344
},
{
"epoch": 0.01,
"learning_rate": 2.7049332301687087e-05,
"loss": 3.4783,
"step": 1401856
},
{
"epoch": 0.01,
"learning_rate": 2.7040946354176567e-05,
"loss": 3.5006,
"step": 1402368
},
{
"epoch": 0.01,
"learning_rate": 2.703256040666604e-05,
"loss": 3.4914,
"step": 1402880
},
{
"epoch": 0.01,
"learning_rate": 2.7024190837959256e-05,
"loss": 3.4982,
"step": 1403392
},
{
"epoch": 0.01,
"learning_rate": 2.7015804890448736e-05,
"loss": 3.4894,
"step": 1403904
},
{
"epoch": 0.01,
"learning_rate": 2.7007418942938213e-05,
"loss": 3.4919,
"step": 1404416
},
{
"epoch": 0.01,
"learning_rate": 2.6999032995427693e-05,
"loss": 3.4886,
"step": 1404928
},
{
"epoch": 0.01,
"learning_rate": 2.699066342672091e-05,
"loss": 3.4894,
"step": 1405440
},
{
"epoch": 0.01,
"learning_rate": 2.698227747921039e-05,
"loss": 3.4889,
"step": 1405952
},
{
"epoch": 0.01,
"learning_rate": 2.6973891531699862e-05,
"loss": 3.4814,
"step": 1406464
},
{
"epoch": 0.01,
"learning_rate": 2.6965505584189342e-05,
"loss": 3.5012,
"step": 1406976
},
{
"epoch": 0.01,
"learning_rate": 2.6957136015482558e-05,
"loss": 3.4899,
"step": 1407488
},
{
"epoch": 0.01,
"learning_rate": 2.694875006797204e-05,
"loss": 3.4928,
"step": 1408000
},
{
"epoch": 0.01,
"learning_rate": 2.6940364120461514e-05,
"loss": 3.4794,
"step": 1408512
},
{
"epoch": 0.01,
"learning_rate": 2.6931978172950994e-05,
"loss": 3.4903,
"step": 1409024
},
{
"epoch": 0.01,
"learning_rate": 2.692360860424421e-05,
"loss": 3.5011,
"step": 1409536
},
{
"epoch": 0.01,
"learning_rate": 2.6915222656733687e-05,
"loss": 3.4979,
"step": 1410048
},
{
"epoch": 0.01,
"learning_rate": 2.6906836709223167e-05,
"loss": 3.4922,
"step": 1410560
},
{
"epoch": 0.01,
"learning_rate": 2.6898450761712647e-05,
"loss": 3.5005,
"step": 1411072
},
{
"epoch": 0.01,
"learning_rate": 2.6890081193005862e-05,
"loss": 3.5021,
"step": 1411584
},
{
"epoch": 0.01,
"learning_rate": 2.6881695245495336e-05,
"loss": 3.4919,
"step": 1412096
},
{
"epoch": 0.01,
"learning_rate": 2.6873309297984816e-05,
"loss": 3.4988,
"step": 1412608
},
{
"epoch": 0.01,
"learning_rate": 2.6864923350474296e-05,
"loss": 3.4936,
"step": 1413120
},
{
"epoch": 0.01,
"learning_rate": 2.685655378176751e-05,
"loss": 3.4845,
"step": 1413632
},
{
"epoch": 0.01,
"learning_rate": 2.6848167834256988e-05,
"loss": 3.4943,
"step": 1414144
},
{
"epoch": 0.01,
"learning_rate": 2.6839781886746468e-05,
"loss": 3.4903,
"step": 1414656
},
{
"epoch": 0.01,
"learning_rate": 2.6831395939235948e-05,
"loss": 3.4966,
"step": 1415168
},
{
"epoch": 0.01,
"learning_rate": 2.6823026370529157e-05,
"loss": 3.5031,
"step": 1415680
},
{
"epoch": 0.01,
"learning_rate": 2.681464042301864e-05,
"loss": 3.5043,
"step": 1416192
},
{
"epoch": 0.01,
"learning_rate": 2.680625447550812e-05,
"loss": 3.4751,
"step": 1416704
},
{
"epoch": 0.01,
"learning_rate": 2.67978685279976e-05,
"loss": 3.4917,
"step": 1417216
},
{
"epoch": 0.01,
"learning_rate": 2.678949895929081e-05,
"loss": 3.4943,
"step": 1417728
},
{
"epoch": 0.01,
"learning_rate": 2.678111301178029e-05,
"loss": 3.4956,
"step": 1418240
},
{
"epoch": 0.01,
"learning_rate": 2.677272706426977e-05,
"loss": 3.4888,
"step": 1418752
},
{
"epoch": 0.01,
"learning_rate": 2.676434111675925e-05,
"loss": 3.4842,
"step": 1419264
},
{
"epoch": 0.02,
"learning_rate": 2.675597154805246e-05,
"loss": 3.4916,
"step": 1419776
},
{
"epoch": 0.02,
"learning_rate": 2.674758560054194e-05,
"loss": 3.4879,
"step": 1420288
},
{
"epoch": 0.02,
"learning_rate": 2.673919965303142e-05,
"loss": 3.4858,
"step": 1420800
},
{
"epoch": 0.02,
"learning_rate": 2.67308137055209e-05,
"loss": 3.4965,
"step": 1421312
},
{
"epoch": 0.02,
"learning_rate": 2.672244413681411e-05,
"loss": 3.4935,
"step": 1421824
},
{
"epoch": 0.02,
"learning_rate": 2.6714058189303594e-05,
"loss": 3.4995,
"step": 1422336
},
{
"epoch": 0.02,
"learning_rate": 2.6705672241793074e-05,
"loss": 3.4869,
"step": 1422848
},
{
"epoch": 0.02,
"learning_rate": 2.6697286294282554e-05,
"loss": 3.4874,
"step": 1423360
},
{
"epoch": 0.02,
"learning_rate": 2.6688916725575763e-05,
"loss": 3.4948,
"step": 1423872
},
{
"epoch": 0.02,
"learning_rate": 2.6680530778065243e-05,
"loss": 3.4995,
"step": 1424384
},
{
"epoch": 0.02,
"learning_rate": 2.6672144830554723e-05,
"loss": 3.4924,
"step": 1424896
},
{
"epoch": 0.02,
"learning_rate": 2.6663758883044203e-05,
"loss": 3.4881,
"step": 1425408
},
{
"epoch": 0.02,
"learning_rate": 2.6655389314337415e-05,
"loss": 3.4906,
"step": 1425920
},
{
"epoch": 0.02,
"learning_rate": 2.6647003366826895e-05,
"loss": 3.4929,
"step": 1426432
},
{
"epoch": 0.02,
"learning_rate": 2.6638617419316375e-05,
"loss": 3.4956,
"step": 1426944
},
{
"epoch": 0.02,
"learning_rate": 2.6630231471805855e-05,
"loss": 3.4798,
"step": 1427456
},
{
"epoch": 0.02,
"learning_rate": 2.6621861903099064e-05,
"loss": 3.4838,
"step": 1427968
},
{
"epoch": 0.02,
"learning_rate": 2.6613475955588548e-05,
"loss": 3.5002,
"step": 1428480
},
{
"epoch": 0.02,
"learning_rate": 2.6605090008078028e-05,
"loss": 3.4901,
"step": 1428992
},
{
"epoch": 0.02,
"learning_rate": 2.6596704060567508e-05,
"loss": 3.4804,
"step": 1429504
},
{
"epoch": 0.02,
"learning_rate": 2.6588334491860717e-05,
"loss": 3.484,
"step": 1430016
},
{
"epoch": 0.02,
"learning_rate": 2.6579948544350197e-05,
"loss": 3.4805,
"step": 1430528
},
{
"epoch": 0.02,
"learning_rate": 2.6571562596839677e-05,
"loss": 3.4966,
"step": 1431040
},
{
"epoch": 0.02,
"learning_rate": 2.6563176649329157e-05,
"loss": 3.4901,
"step": 1431552
},
{
"epoch": 0.02,
"learning_rate": 2.655480708062237e-05,
"loss": 3.4872,
"step": 1432064
},
{
"epoch": 0.02,
"learning_rate": 2.654642113311185e-05,
"loss": 3.4932,
"step": 1432576
},
{
"epoch": 0.02,
"learning_rate": 2.653803518560133e-05,
"loss": 3.5071,
"step": 1433088
},
{
"epoch": 0.02,
"learning_rate": 2.652964923809081e-05,
"loss": 3.4936,
"step": 1433600
},
{
"epoch": 0.02,
"learning_rate": 2.652126329058029e-05,
"loss": 3.4829,
"step": 1434112
},
{
"epoch": 0.02,
"learning_rate": 2.6512893721873498e-05,
"loss": 3.4941,
"step": 1434624
},
{
"epoch": 0.02,
"learning_rate": 2.650450777436298e-05,
"loss": 3.4895,
"step": 1435136
},
{
"epoch": 0.02,
"learning_rate": 2.649612182685246e-05,
"loss": 3.4832,
"step": 1435648
},
{
"epoch": 0.02,
"learning_rate": 2.648773587934194e-05,
"loss": 3.4852,
"step": 1436160
},
{
"epoch": 0.02,
"learning_rate": 2.647936631063515e-05,
"loss": 3.4816,
"step": 1436672
},
{
"epoch": 0.02,
"learning_rate": 2.647098036312463e-05,
"loss": 3.4977,
"step": 1437184
},
{
"epoch": 0.02,
"learning_rate": 2.646259441561411e-05,
"loss": 3.4826,
"step": 1437696
},
{
"epoch": 0.02,
"learning_rate": 2.645420846810359e-05,
"loss": 3.5008,
"step": 1438208
},
{
"epoch": 0.02,
"learning_rate": 2.6445838899396803e-05,
"loss": 3.4822,
"step": 1438720
},
{
"epoch": 0.02,
"learning_rate": 2.6437452951886283e-05,
"loss": 3.4923,
"step": 1439232
},
{
"epoch": 0.02,
"learning_rate": 2.6429067004375763e-05,
"loss": 3.4867,
"step": 1439744
},
{
"epoch": 0.02,
"learning_rate": 2.6420681056865243e-05,
"loss": 3.5026,
"step": 1440256
},
{
"epoch": 0.02,
"learning_rate": 2.641231148815845e-05,
"loss": 3.4971,
"step": 1440768
},
{
"epoch": 0.02,
"learning_rate": 2.6403925540647935e-05,
"loss": 3.4885,
"step": 1441280
},
{
"epoch": 0.02,
"learning_rate": 2.6395539593137415e-05,
"loss": 3.4815,
"step": 1441792
},
{
"epoch": 0.02,
"learning_rate": 2.6387153645626895e-05,
"loss": 3.4951,
"step": 1442304
},
{
"epoch": 0.02,
"learning_rate": 2.6378784076920104e-05,
"loss": 3.4919,
"step": 1442816
},
{
"epoch": 0.02,
"learning_rate": 2.6370398129409584e-05,
"loss": 3.5017,
"step": 1443328
},
{
"epoch": 0.02,
"learning_rate": 2.6362012181899064e-05,
"loss": 3.4849,
"step": 1443840
},
{
"epoch": 0.02,
"learning_rate": 2.6353626234388544e-05,
"loss": 3.499,
"step": 1444352
},
{
"epoch": 0.02,
"learning_rate": 2.6345256665681756e-05,
"loss": 3.4921,
"step": 1444864
},
{
"epoch": 0.02,
"learning_rate": 2.6336870718171236e-05,
"loss": 3.5055,
"step": 1445376
},
{
"epoch": 0.02,
"learning_rate": 2.6328484770660716e-05,
"loss": 3.4877,
"step": 1445888
},
{
"epoch": 0.02,
"learning_rate": 2.6320098823150196e-05,
"loss": 3.4938,
"step": 1446400
},
{
"epoch": 0.02,
"learning_rate": 2.6311729254443405e-05,
"loss": 3.4927,
"step": 1446912
},
{
"epoch": 0.02,
"learning_rate": 2.630334330693289e-05,
"loss": 3.4838,
"step": 1447424
},
{
"epoch": 0.02,
"learning_rate": 2.6294973738226098e-05,
"loss": 3.5008,
"step": 1447936
},
{
"epoch": 0.02,
"learning_rate": 2.6286587790715578e-05,
"loss": 3.501,
"step": 1448448
},
{
"epoch": 0.02,
"learning_rate": 2.6278201843205058e-05,
"loss": 3.4884,
"step": 1448960
},
{
"epoch": 0.02,
"learning_rate": 2.6269815895694538e-05,
"loss": 3.4908,
"step": 1449472
},
{
"epoch": 0.02,
"learning_rate": 2.6261429948184018e-05,
"loss": 3.4803,
"step": 1449984
},
{
"epoch": 0.03,
"eval_loss": 3.8544347286224365,
"eval_runtime": 306.151,
"eval_samples_per_second": 1246.414,
"eval_steps_per_second": 38.951,
"step": 1450080
},
{
"epoch": 1.0,
"learning_rate": 2.6253044000673497e-05,
"loss": 3.4824,
"step": 1450496
},
{
"epoch": 1.0,
"learning_rate": 2.624465805316298e-05,
"loss": 3.4839,
"step": 1451008
},
{
"epoch": 1.0,
"learning_rate": 2.623627210565246e-05,
"loss": 3.4918,
"step": 1451520
},
{
"epoch": 1.0,
"learning_rate": 2.622790253694567e-05,
"loss": 3.49,
"step": 1452032
},
{
"epoch": 1.0,
"learning_rate": 2.621951658943515e-05,
"loss": 3.5085,
"step": 1452544
},
{
"epoch": 1.0,
"learning_rate": 2.621113064192463e-05,
"loss": 3.4824,
"step": 1453056
},
{
"epoch": 1.0,
"learning_rate": 2.6202761073217842e-05,
"loss": 3.4882,
"step": 1453568
},
{
"epoch": 1.0,
"learning_rate": 2.6194375125707322e-05,
"loss": 3.4837,
"step": 1454080
},
{
"epoch": 1.0,
"learning_rate": 2.6185989178196802e-05,
"loss": 3.5026,
"step": 1454592
},
{
"epoch": 1.0,
"learning_rate": 2.6177603230686282e-05,
"loss": 3.4844,
"step": 1455104
},
{
"epoch": 1.0,
"learning_rate": 2.6169217283175762e-05,
"loss": 3.4787,
"step": 1455616
},
{
"epoch": 1.0,
"learning_rate": 2.616084771446897e-05,
"loss": 3.4935,
"step": 1456128
},
{
"epoch": 1.0,
"learning_rate": 2.6152478145762184e-05,
"loss": 3.4851,
"step": 1456640
},
{
"epoch": 1.0,
"learning_rate": 2.6144092198251664e-05,
"loss": 3.4812,
"step": 1457152
},
{
"epoch": 1.0,
"learning_rate": 2.6135706250741144e-05,
"loss": 3.4842,
"step": 1457664
},
{
"epoch": 1.0,
"learning_rate": 2.6127320303230624e-05,
"loss": 3.4796,
"step": 1458176
},
{
"epoch": 1.0,
"learning_rate": 2.6118934355720104e-05,
"loss": 3.4763,
"step": 1458688
},
{
"epoch": 1.0,
"learning_rate": 2.6110548408209583e-05,
"loss": 3.4798,
"step": 1459200
},
{
"epoch": 1.0,
"learning_rate": 2.6102162460699063e-05,
"loss": 3.4807,
"step": 1459712
},
{
"epoch": 1.0,
"learning_rate": 2.609377651318854e-05,
"loss": 3.5065,
"step": 1460224
},
{
"epoch": 1.0,
"learning_rate": 2.6085406944481756e-05,
"loss": 3.4823,
"step": 1460736
},
{
"epoch": 1.0,
"learning_rate": 2.6077020996971236e-05,
"loss": 3.4846,
"step": 1461248
},
{
"epoch": 1.0,
"learning_rate": 2.606863504946071e-05,
"loss": 3.4892,
"step": 1461760
},
{
"epoch": 1.0,
"learning_rate": 2.606024910195019e-05,
"loss": 3.4905,
"step": 1462272
},
{
"epoch": 1.0,
"learning_rate": 2.6051879533243405e-05,
"loss": 3.4796,
"step": 1462784
},
{
"epoch": 1.0,
"learning_rate": 2.6043493585732888e-05,
"loss": 3.4849,
"step": 1463296
},
{
"epoch": 1.0,
"learning_rate": 2.603510763822236e-05,
"loss": 3.4812,
"step": 1463808
},
{
"epoch": 1.0,
"learning_rate": 2.602672169071184e-05,
"loss": 3.487,
"step": 1464320
},
{
"epoch": 1.0,
"learning_rate": 2.6018352122005057e-05,
"loss": 3.4776,
"step": 1464832
},
{
"epoch": 1.01,
"learning_rate": 2.6009966174494534e-05,
"loss": 3.4815,
"step": 1465344
},
{
"epoch": 1.01,
"learning_rate": 2.6001580226984014e-05,
"loss": 3.4919,
"step": 1465856
},
{
"epoch": 1.01,
"learning_rate": 2.5993194279473494e-05,
"loss": 3.49,
"step": 1466368
},
{
"epoch": 1.01,
"learning_rate": 2.598482471076671e-05,
"loss": 3.4952,
"step": 1466880
},
{
"epoch": 1.01,
"learning_rate": 2.5976438763256183e-05,
"loss": 3.4912,
"step": 1467392
},
{
"epoch": 1.01,
"learning_rate": 2.5968052815745663e-05,
"loss": 3.4774,
"step": 1467904
},
{
"epoch": 1.01,
"learning_rate": 2.5959666868235143e-05,
"loss": 3.4894,
"step": 1468416
},
{
"epoch": 1.01,
"learning_rate": 2.595129729952836e-05,
"loss": 3.4764,
"step": 1468928
},
{
"epoch": 1.01,
"learning_rate": 2.5942911352017835e-05,
"loss": 3.487,
"step": 1469440
},
{
"epoch": 1.01,
"learning_rate": 2.5934525404507315e-05,
"loss": 3.4729,
"step": 1469952
},
{
"epoch": 1.01,
"learning_rate": 2.5926139456996795e-05,
"loss": 3.4783,
"step": 1470464
},
{
"epoch": 1.01,
"learning_rate": 2.5917769888290004e-05,
"loss": 3.4787,
"step": 1470976
},
{
"epoch": 1.01,
"learning_rate": 2.5909383940779487e-05,
"loss": 3.495,
"step": 1471488
},
{
"epoch": 1.01,
"learning_rate": 2.5900997993268967e-05,
"loss": 3.4909,
"step": 1472000
},
{
"epoch": 1.01,
"learning_rate": 2.5892612045758447e-05,
"loss": 3.4802,
"step": 1472512
},
{
"epoch": 1.01,
"learning_rate": 2.5884242477051656e-05,
"loss": 3.4848,
"step": 1473024
},
{
"epoch": 1.01,
"learning_rate": 2.5875856529541136e-05,
"loss": 3.4826,
"step": 1473536
},
{
"epoch": 1.01,
"learning_rate": 2.5867470582030616e-05,
"loss": 3.4862,
"step": 1474048
},
{
"epoch": 1.01,
"learning_rate": 2.5859084634520096e-05,
"loss": 3.471,
"step": 1474560
},
{
"epoch": 1.01,
"learning_rate": 2.585071506581331e-05,
"loss": 3.4648,
"step": 1475072
},
{
"epoch": 1.01,
"learning_rate": 2.584232911830279e-05,
"loss": 3.4881,
"step": 1475584
},
{
"epoch": 1.01,
"learning_rate": 2.583394317079227e-05,
"loss": 3.4901,
"step": 1476096
},
{
"epoch": 1.01,
"learning_rate": 2.582555722328175e-05,
"loss": 3.474,
"step": 1476608
},
{
"epoch": 1.01,
"learning_rate": 2.5817187654574958e-05,
"loss": 3.4796,
"step": 1477120
},
{
"epoch": 1.01,
"learning_rate": 2.580880170706444e-05,
"loss": 3.4836,
"step": 1477632
},
{
"epoch": 1.01,
"learning_rate": 2.580041575955392e-05,
"loss": 3.4681,
"step": 1478144
},
{
"epoch": 1.01,
"learning_rate": 2.57920298120434e-05,
"loss": 3.4845,
"step": 1478656
},
{
"epoch": 1.01,
"learning_rate": 2.578366024333661e-05,
"loss": 3.4793,
"step": 1479168
},
{
"epoch": 1.01,
"learning_rate": 2.577527429582609e-05,
"loss": 3.4891,
"step": 1479680
},
{
"epoch": 1.01,
"learning_rate": 2.576688834831557e-05,
"loss": 3.4745,
"step": 1480192
},
{
"epoch": 1.01,
"learning_rate": 2.575850240080505e-05,
"loss": 3.4856,
"step": 1480704
},
{
"epoch": 1.01,
"learning_rate": 2.5750132832098262e-05,
"loss": 3.4729,
"step": 1481216
},
{
"epoch": 1.01,
"learning_rate": 2.5741746884587742e-05,
"loss": 3.4783,
"step": 1481728
},
{
"epoch": 1.01,
"learning_rate": 2.5733360937077222e-05,
"loss": 3.4714,
"step": 1482240
},
{
"epoch": 1.01,
"learning_rate": 2.5724974989566702e-05,
"loss": 3.4725,
"step": 1482752
},
{
"epoch": 1.01,
"learning_rate": 2.571660542085991e-05,
"loss": 3.4915,
"step": 1483264
},
{
"epoch": 1.01,
"learning_rate": 2.5708219473349395e-05,
"loss": 3.4761,
"step": 1483776
},
{
"epoch": 1.01,
"learning_rate": 2.5699833525838875e-05,
"loss": 3.4809,
"step": 1484288
},
{
"epoch": 1.01,
"learning_rate": 2.5691447578328355e-05,
"loss": 3.4644,
"step": 1484800
},
{
"epoch": 1.01,
"learning_rate": 2.5683078009621564e-05,
"loss": 3.4774,
"step": 1485312
},
{
"epoch": 1.01,
"learning_rate": 2.5674692062111044e-05,
"loss": 3.4893,
"step": 1485824
},
{
"epoch": 1.01,
"learning_rate": 2.5666306114600524e-05,
"loss": 3.485,
"step": 1486336
},
{
"epoch": 1.01,
"learning_rate": 2.5657920167090004e-05,
"loss": 3.4813,
"step": 1486848
},
{
"epoch": 1.01,
"learning_rate": 2.5649550598383216e-05,
"loss": 3.4876,
"step": 1487360
},
{
"epoch": 1.01,
"learning_rate": 2.5641164650872696e-05,
"loss": 3.4867,
"step": 1487872
},
{
"epoch": 1.01,
"learning_rate": 2.5632778703362176e-05,
"loss": 3.4812,
"step": 1488384
},
{
"epoch": 1.01,
"learning_rate": 2.5624392755851656e-05,
"loss": 3.4839,
"step": 1488896
},
{
"epoch": 1.01,
"learning_rate": 2.5616023187144865e-05,
"loss": 3.4823,
"step": 1489408
},
{
"epoch": 1.01,
"learning_rate": 2.5607637239634345e-05,
"loss": 3.4744,
"step": 1489920
},
{
"epoch": 1.01,
"learning_rate": 2.559925129212383e-05,
"loss": 3.4782,
"step": 1490432
},
{
"epoch": 1.01,
"learning_rate": 2.559086534461331e-05,
"loss": 3.4785,
"step": 1490944
},
{
"epoch": 1.01,
"learning_rate": 2.5582495775906517e-05,
"loss": 3.4825,
"step": 1491456
},
{
"epoch": 1.01,
"learning_rate": 2.5574109828395997e-05,
"loss": 3.4885,
"step": 1491968
},
{
"epoch": 1.01,
"learning_rate": 2.5565723880885477e-05,
"loss": 3.4894,
"step": 1492480
},
{
"epoch": 1.01,
"learning_rate": 2.5557337933374957e-05,
"loss": 3.4612,
"step": 1492992
},
{
"epoch": 1.01,
"learning_rate": 2.554896836466817e-05,
"loss": 3.4834,
"step": 1493504
},
{
"epoch": 1.01,
"learning_rate": 2.554058241715765e-05,
"loss": 3.4819,
"step": 1494016
},
{
"epoch": 1.01,
"learning_rate": 2.553219646964713e-05,
"loss": 3.4836,
"step": 1494528
},
{
"epoch": 1.01,
"learning_rate": 2.552381052213661e-05,
"loss": 3.4781,
"step": 1495040
},
{
"epoch": 1.01,
"learning_rate": 2.551544095342982e-05,
"loss": 3.4707,
"step": 1495552
},
{
"epoch": 1.02,
"learning_rate": 2.55070550059193e-05,
"loss": 3.4804,
"step": 1496064
},
{
"epoch": 1.02,
"learning_rate": 2.5498669058408782e-05,
"loss": 3.4772,
"step": 1496576
},
{
"epoch": 1.02,
"learning_rate": 2.5490283110898262e-05,
"loss": 3.4763,
"step": 1497088
},
{
"epoch": 1.02,
"learning_rate": 2.548191354219147e-05,
"loss": 3.4835,
"step": 1497600
},
{
"epoch": 1.02,
"learning_rate": 2.547352759468095e-05,
"loss": 3.4813,
"step": 1498112
},
{
"epoch": 1.02,
"learning_rate": 2.546514164717043e-05,
"loss": 3.4881,
"step": 1498624
},
{
"epoch": 1.02,
"learning_rate": 2.545675569965991e-05,
"loss": 3.4762,
"step": 1499136
},
{
"epoch": 1.02,
"learning_rate": 2.5448386130953123e-05,
"loss": 3.472,
"step": 1499648
},
{
"epoch": 1.02,
"learning_rate": 2.5440000183442603e-05,
"loss": 3.48,
"step": 1500160
},
{
"epoch": 1.02,
"learning_rate": 2.5431614235932083e-05,
"loss": 3.4902,
"step": 1500672
},
{
"epoch": 1.02,
"learning_rate": 2.5423228288421563e-05,
"loss": 3.4782,
"step": 1501184
},
{
"epoch": 1.02,
"learning_rate": 2.5414858719714772e-05,
"loss": 3.4774,
"step": 1501696
},
{
"epoch": 1.02,
"learning_rate": 2.5406472772204252e-05,
"loss": 3.4768,
"step": 1502208
},
{
"epoch": 1.02,
"learning_rate": 2.5398086824693736e-05,
"loss": 3.4813,
"step": 1502720
},
{
"epoch": 1.02,
"learning_rate": 2.5389700877183216e-05,
"loss": 3.4883,
"step": 1503232
},
{
"epoch": 1.02,
"learning_rate": 2.5381331308476425e-05,
"loss": 3.473,
"step": 1503744
},
{
"epoch": 1.02,
"learning_rate": 2.5372945360965905e-05,
"loss": 3.4711,
"step": 1504256
},
{
"epoch": 1.02,
"learning_rate": 2.5364559413455385e-05,
"loss": 3.485,
"step": 1504768
},
{
"epoch": 1.02,
"learning_rate": 2.5356173465944865e-05,
"loss": 3.4738,
"step": 1505280
},
{
"epoch": 1.02,
"learning_rate": 2.5347803897238077e-05,
"loss": 3.4682,
"step": 1505792
},
{
"epoch": 1.02,
"learning_rate": 2.5339417949727557e-05,
"loss": 3.4692,
"step": 1506304
},
{
"epoch": 1.02,
"learning_rate": 2.5331032002217037e-05,
"loss": 3.4717,
"step": 1506816
},
{
"epoch": 1.02,
"learning_rate": 2.5322646054706517e-05,
"loss": 3.4849,
"step": 1507328
},
{
"epoch": 1.02,
"learning_rate": 2.5314276485999726e-05,
"loss": 3.475,
"step": 1507840
},
{
"epoch": 1.02,
"learning_rate": 2.5305890538489206e-05,
"loss": 3.4764,
"step": 1508352
},
{
"epoch": 1.02,
"learning_rate": 2.529750459097869e-05,
"loss": 3.4824,
"step": 1508864
},
{
"epoch": 1.02,
"learning_rate": 2.528911864346817e-05,
"loss": 3.493,
"step": 1509376
},
{
"epoch": 1.02,
"learning_rate": 2.528074907476138e-05,
"loss": 3.4862,
"step": 1509888
},
{
"epoch": 1.02,
"learning_rate": 2.527236312725086e-05,
"loss": 3.4695,
"step": 1510400
},
{
"epoch": 1.02,
"learning_rate": 2.526397717974034e-05,
"loss": 3.484,
"step": 1510912
},
{
"epoch": 1.02,
"learning_rate": 2.5255591232229818e-05,
"loss": 3.4741,
"step": 1511424
},
{
"epoch": 1.02,
"learning_rate": 2.524722166352303e-05,
"loss": 3.4743,
"step": 1511936
},
{
"epoch": 1.02,
"learning_rate": 2.523883571601251e-05,
"loss": 3.4729,
"step": 1512448
},
{
"epoch": 1.02,
"learning_rate": 2.523044976850199e-05,
"loss": 3.4719,
"step": 1512960
},
{
"epoch": 1.02,
"learning_rate": 2.522206382099147e-05,
"loss": 3.4811,
"step": 1513472
},
{
"epoch": 1.02,
"learning_rate": 2.521369425228468e-05,
"loss": 3.4723,
"step": 1513984
},
{
"epoch": 1.02,
"learning_rate": 2.520530830477416e-05,
"loss": 3.4853,
"step": 1514496
},
{
"epoch": 1.02,
"learning_rate": 2.5196922357263643e-05,
"loss": 3.4729,
"step": 1515008
},
{
"epoch": 1.02,
"learning_rate": 2.5188536409753123e-05,
"loss": 3.4809,
"step": 1515520
},
{
"epoch": 1.02,
"learning_rate": 2.5180166841046332e-05,
"loss": 3.4722,
"step": 1516032
},
{
"epoch": 1.02,
"learning_rate": 2.5171780893535812e-05,
"loss": 3.4962,
"step": 1516544
},
{
"epoch": 1.02,
"learning_rate": 2.5163394946025292e-05,
"loss": 3.4806,
"step": 1517056
},
{
"epoch": 1.02,
"learning_rate": 2.5155008998514772e-05,
"loss": 3.4798,
"step": 1517568
},
{
"epoch": 1.02,
"learning_rate": 2.5146639429807984e-05,
"loss": 3.4695,
"step": 1518080
},
{
"epoch": 1.02,
"learning_rate": 2.5138253482297464e-05,
"loss": 3.4844,
"step": 1518592
},
{
"epoch": 1.02,
"learning_rate": 2.5129867534786944e-05,
"loss": 3.4792,
"step": 1519104
},
{
"epoch": 1.02,
"learning_rate": 2.5121481587276424e-05,
"loss": 3.4886,
"step": 1519616
},
{
"epoch": 1.02,
"learning_rate": 2.5113112018569633e-05,
"loss": 3.474,
"step": 1520128
},
{
"epoch": 1.02,
"learning_rate": 2.5104726071059113e-05,
"loss": 3.484,
"step": 1520640
},
{
"epoch": 1.02,
"learning_rate": 2.5096340123548597e-05,
"loss": 3.4816,
"step": 1521152
},
{
"epoch": 1.02,
"learning_rate": 2.5087954176038077e-05,
"loss": 3.495,
"step": 1521664
},
{
"epoch": 1.02,
"learning_rate": 2.5079584607331286e-05,
"loss": 3.4739,
"step": 1522176
},
{
"epoch": 1.02,
"learning_rate": 2.5071198659820766e-05,
"loss": 3.4821,
"step": 1522688
},
{
"epoch": 1.02,
"learning_rate": 2.5062812712310246e-05,
"loss": 3.4798,
"step": 1523200
},
{
"epoch": 1.02,
"learning_rate": 2.5054426764799726e-05,
"loss": 3.4771,
"step": 1523712
},
{
"epoch": 1.02,
"learning_rate": 2.5046057196092938e-05,
"loss": 3.482,
"step": 1524224
},
{
"epoch": 1.02,
"learning_rate": 2.5037671248582418e-05,
"loss": 3.4872,
"step": 1524736
},
{
"epoch": 1.02,
"learning_rate": 2.5029285301071898e-05,
"loss": 3.4772,
"step": 1525248
},
{
"epoch": 1.02,
"learning_rate": 2.5020899353561378e-05,
"loss": 3.4762,
"step": 1525760
},
{
"epoch": 1.02,
"learning_rate": 2.5012529784854587e-05,
"loss": 3.4734,
"step": 1526272
},
{
"epoch": 1.03,
"eval_loss": 3.8558645248413086,
"eval_runtime": 305.6513,
"eval_samples_per_second": 1248.452,
"eval_steps_per_second": 39.015,
"step": 1526400
},
{
"epoch": 0.0,
"learning_rate": 2.5004143837344067e-05,
"loss": 3.4692,
"step": 1526784
},
{
"epoch": 0.0,
"learning_rate": 2.4995757889833547e-05,
"loss": 3.4688,
"step": 1527296
},
{
"epoch": 0.0,
"learning_rate": 2.4987371942323027e-05,
"loss": 3.4774,
"step": 1527808
},
{
"epoch": 0.0,
"learning_rate": 2.4978985994812507e-05,
"loss": 3.4787,
"step": 1528320
},
{
"epoch": 0.0,
"learning_rate": 2.4970616426105716e-05,
"loss": 3.4939,
"step": 1528832
},
{
"epoch": 0.0,
"learning_rate": 2.4962230478595196e-05,
"loss": 3.4754,
"step": 1529344
},
{
"epoch": 0.0,
"learning_rate": 2.4953844531084676e-05,
"loss": 3.4716,
"step": 1529856
},
{
"epoch": 0.0,
"learning_rate": 2.494545858357416e-05,
"loss": 3.4732,
"step": 1530368
},
{
"epoch": 0.0,
"learning_rate": 2.493708901486737e-05,
"loss": 3.4885,
"step": 1530880
},
{
"epoch": 0.0,
"learning_rate": 2.4928703067356848e-05,
"loss": 3.4761,
"step": 1531392
},
{
"epoch": 0.0,
"learning_rate": 2.4920317119846328e-05,
"loss": 3.4685,
"step": 1531904
},
{
"epoch": 0.0,
"learning_rate": 2.4911931172335808e-05,
"loss": 3.4779,
"step": 1532416
},
{
"epoch": 0.0,
"learning_rate": 2.490356160362902e-05,
"loss": 3.4735,
"step": 1532928
},
{
"epoch": 0.0,
"learning_rate": 2.48951756561185e-05,
"loss": 3.47,
"step": 1533440
},
{
"epoch": 0.0,
"learning_rate": 2.488678970860798e-05,
"loss": 3.4759,
"step": 1533952
},
{
"epoch": 0.0,
"learning_rate": 2.487840376109746e-05,
"loss": 3.4655,
"step": 1534464
},
{
"epoch": 0.0,
"learning_rate": 2.487003419239067e-05,
"loss": 3.4658,
"step": 1534976
},
{
"epoch": 0.0,
"learning_rate": 2.486164824488015e-05,
"loss": 3.4672,
"step": 1535488
},
{
"epoch": 0.0,
"learning_rate": 2.485326229736963e-05,
"loss": 3.4666,
"step": 1536000
},
{
"epoch": 0.0,
"learning_rate": 2.4844876349859113e-05,
"loss": 3.492,
"step": 1536512
},
{
"epoch": 0.0,
"learning_rate": 2.4836506781152322e-05,
"loss": 3.4739,
"step": 1537024
},
{
"epoch": 0.0,
"learning_rate": 2.4828120833641802e-05,
"loss": 3.4696,
"step": 1537536
},
{
"epoch": 0.0,
"learning_rate": 2.4819734886131282e-05,
"loss": 3.4752,
"step": 1538048
},
{
"epoch": 0.0,
"learning_rate": 2.4811348938620762e-05,
"loss": 3.4825,
"step": 1538560
},
{
"epoch": 0.0,
"learning_rate": 2.4802979369913974e-05,
"loss": 3.4654,
"step": 1539072
},
{
"epoch": 0.0,
"learning_rate": 2.4794593422403454e-05,
"loss": 3.4745,
"step": 1539584
},
{
"epoch": 0.0,
"learning_rate": 2.4786207474892934e-05,
"loss": 3.4688,
"step": 1540096
},
{
"epoch": 0.0,
"learning_rate": 2.4777821527382414e-05,
"loss": 3.4726,
"step": 1540608
},
{
"epoch": 0.0,
"learning_rate": 2.4769451958675623e-05,
"loss": 3.4652,
"step": 1541120
},
{
"epoch": 0.0,
"learning_rate": 2.4761066011165103e-05,
"loss": 3.4712,
"step": 1541632
},
{
"epoch": 0.01,
"learning_rate": 2.4752680063654583e-05,
"loss": 3.4783,
"step": 1542144
},
{
"epoch": 0.01,
"learning_rate": 2.4744294116144067e-05,
"loss": 3.4766,
"step": 1542656
},
{
"epoch": 0.01,
"learning_rate": 2.4735924547437276e-05,
"loss": 3.4818,
"step": 1543168
},
{
"epoch": 0.01,
"learning_rate": 2.4727538599926756e-05,
"loss": 3.4797,
"step": 1543680
},
{
"epoch": 0.01,
"learning_rate": 2.4719152652416236e-05,
"loss": 3.4668,
"step": 1544192
},
{
"epoch": 0.01,
"learning_rate": 2.4710766704905716e-05,
"loss": 3.4739,
"step": 1544704
},
{
"epoch": 0.01,
"learning_rate": 2.4702397136198928e-05,
"loss": 3.4692,
"step": 1545216
},
{
"epoch": 0.01,
"learning_rate": 2.4694011188688408e-05,
"loss": 3.4718,
"step": 1545728
},
{
"epoch": 0.01,
"learning_rate": 2.4685641619981617e-05,
"loss": 3.4632,
"step": 1546240
},
{
"epoch": 0.01,
"learning_rate": 2.4677255672471097e-05,
"loss": 3.4659,
"step": 1546752
},
{
"epoch": 0.01,
"learning_rate": 2.4668869724960577e-05,
"loss": 3.4675,
"step": 1547264
},
{
"epoch": 0.01,
"learning_rate": 2.4660483777450057e-05,
"loss": 3.4809,
"step": 1547776
},
{
"epoch": 0.01,
"learning_rate": 2.4652097829939537e-05,
"loss": 3.4766,
"step": 1548288
},
{
"epoch": 0.01,
"learning_rate": 2.4643711882429017e-05,
"loss": 3.4689,
"step": 1548800
},
{
"epoch": 0.01,
"learning_rate": 2.4635325934918497e-05,
"loss": 3.4725,
"step": 1549312
},
{
"epoch": 0.01,
"learning_rate": 2.4626939987407977e-05,
"loss": 3.473,
"step": 1549824
},
{
"epoch": 0.01,
"learning_rate": 2.461857041870119e-05,
"loss": 3.477,
"step": 1550336
},
{
"epoch": 0.01,
"learning_rate": 2.4610184471190666e-05,
"loss": 3.4604,
"step": 1550848
},
{
"epoch": 0.01,
"learning_rate": 2.4601798523680146e-05,
"loss": 3.4502,
"step": 1551360
},
{
"epoch": 0.01,
"learning_rate": 2.459341257616963e-05,
"loss": 3.4746,
"step": 1551872
},
{
"epoch": 0.01,
"learning_rate": 2.4585043007462838e-05,
"loss": 3.4765,
"step": 1552384
},
{
"epoch": 0.01,
"learning_rate": 2.4576657059952318e-05,
"loss": 3.4609,
"step": 1552896
},
{
"epoch": 0.01,
"learning_rate": 2.4568271112441798e-05,
"loss": 3.4696,
"step": 1553408
},
{
"epoch": 0.01,
"learning_rate": 2.4559885164931278e-05,
"loss": 3.4727,
"step": 1553920
},
{
"epoch": 0.01,
"learning_rate": 2.455151559622449e-05,
"loss": 3.4544,
"step": 1554432
},
{
"epoch": 0.01,
"learning_rate": 2.454312964871397e-05,
"loss": 3.4722,
"step": 1554944
},
{
"epoch": 0.01,
"learning_rate": 2.453474370120345e-05,
"loss": 3.4702,
"step": 1555456
},
{
"epoch": 0.01,
"learning_rate": 2.452635775369293e-05,
"loss": 3.4735,
"step": 1555968
},
{
"epoch": 0.01,
"learning_rate": 2.451797180618241e-05,
"loss": 3.4651,
"step": 1556480
},
{
"epoch": 0.01,
"learning_rate": 2.450960223747562e-05,
"loss": 3.4738,
"step": 1556992
},
{
"epoch": 0.01,
"learning_rate": 2.45012162899651e-05,
"loss": 3.4618,
"step": 1557504
},
{
"epoch": 0.01,
"learning_rate": 2.4492830342454583e-05,
"loss": 3.4706,
"step": 1558016
},
{
"epoch": 0.01,
"learning_rate": 2.4484444394944063e-05,
"loss": 3.4575,
"step": 1558528
},
{
"epoch": 0.01,
"learning_rate": 2.4476074826237272e-05,
"loss": 3.4633,
"step": 1559040
},
{
"epoch": 0.01,
"learning_rate": 2.4467688878726752e-05,
"loss": 3.4764,
"step": 1559552
},
{
"epoch": 0.01,
"learning_rate": 2.4459302931216232e-05,
"loss": 3.4662,
"step": 1560064
},
{
"epoch": 0.01,
"learning_rate": 2.4450916983705712e-05,
"loss": 3.4662,
"step": 1560576
},
{
"epoch": 0.01,
"learning_rate": 2.4442547414998924e-05,
"loss": 3.4532,
"step": 1561088
},
{
"epoch": 0.01,
"learning_rate": 2.4434161467488404e-05,
"loss": 3.4653,
"step": 1561600
},
{
"epoch": 0.01,
"learning_rate": 2.4425775519977884e-05,
"loss": 3.4718,
"step": 1562112
},
{
"epoch": 0.01,
"learning_rate": 2.4417389572467364e-05,
"loss": 3.4768,
"step": 1562624
},
{
"epoch": 0.01,
"learning_rate": 2.4409020003760573e-05,
"loss": 3.471,
"step": 1563136
},
{
"epoch": 0.01,
"learning_rate": 2.4400634056250053e-05,
"loss": 3.4784,
"step": 1563648
},
{
"epoch": 0.01,
"learning_rate": 2.4392248108739536e-05,
"loss": 3.4776,
"step": 1564160
},
{
"epoch": 0.01,
"learning_rate": 2.4383862161229016e-05,
"loss": 3.4681,
"step": 1564672
},
{
"epoch": 0.01,
"learning_rate": 2.4375492592522225e-05,
"loss": 3.4693,
"step": 1565184
},
{
"epoch": 0.01,
"learning_rate": 2.4367106645011705e-05,
"loss": 3.4728,
"step": 1565696
},
{
"epoch": 0.01,
"learning_rate": 2.4358720697501185e-05,
"loss": 3.4619,
"step": 1566208
},
{
"epoch": 0.01,
"learning_rate": 2.4350334749990665e-05,
"loss": 3.4647,
"step": 1566720
},
{
"epoch": 0.01,
"learning_rate": 2.4341965181283878e-05,
"loss": 3.4714,
"step": 1567232
},
{
"epoch": 0.01,
"learning_rate": 2.4333579233773358e-05,
"loss": 3.4676,
"step": 1567744
},
{
"epoch": 0.01,
"learning_rate": 2.4325193286262838e-05,
"loss": 3.4808,
"step": 1568256
},
{
"epoch": 0.01,
"learning_rate": 2.4316807338752318e-05,
"loss": 3.4782,
"step": 1568768
},
{
"epoch": 0.01,
"learning_rate": 2.4308437770045527e-05,
"loss": 3.451,
"step": 1569280
},
{
"epoch": 0.01,
"learning_rate": 2.4300051822535007e-05,
"loss": 3.4667,
"step": 1569792
},
{
"epoch": 0.01,
"learning_rate": 2.429166587502449e-05,
"loss": 3.4719,
"step": 1570304
},
{
"epoch": 0.01,
"learning_rate": 2.4283279927513967e-05,
"loss": 3.4711,
"step": 1570816
},
{
"epoch": 0.01,
"learning_rate": 2.427491035880718e-05,
"loss": 3.4679,
"step": 1571328
},
{
"epoch": 0.01,
"learning_rate": 2.426652441129666e-05,
"loss": 3.4593,
"step": 1571840
},
{
"epoch": 0.02,
"learning_rate": 2.425813846378614e-05,
"loss": 3.4664,
"step": 1572352
},
{
"epoch": 0.02,
"learning_rate": 2.4249752516275616e-05,
"loss": 3.464,
"step": 1572864
},
{
"epoch": 0.02,
"learning_rate": 2.424138294756883e-05,
"loss": 3.4657,
"step": 1573376
},
{
"epoch": 0.02,
"learning_rate": 2.423299700005831e-05,
"loss": 3.4658,
"step": 1573888
},
{
"epoch": 0.02,
"learning_rate": 2.422461105254779e-05,
"loss": 3.4746,
"step": 1574400
},
{
"epoch": 0.02,
"learning_rate": 2.4216225105037268e-05,
"loss": 3.4724,
"step": 1574912
},
{
"epoch": 0.02,
"learning_rate": 2.420785553633048e-05,
"loss": 3.4709,
"step": 1575424
},
{
"epoch": 0.02,
"learning_rate": 2.419946958881996e-05,
"loss": 3.4546,
"step": 1575936
},
{
"epoch": 0.02,
"learning_rate": 2.419108364130944e-05,
"loss": 3.4723,
"step": 1576448
},
{
"epoch": 0.02,
"learning_rate": 2.418269769379892e-05,
"loss": 3.4733,
"step": 1576960
},
{
"epoch": 0.02,
"learning_rate": 2.4174328125092133e-05,
"loss": 3.4723,
"step": 1577472
},
{
"epoch": 0.02,
"learning_rate": 2.4165942177581613e-05,
"loss": 3.4634,
"step": 1577984
},
{
"epoch": 0.02,
"learning_rate": 2.415755623007109e-05,
"loss": 3.4663,
"step": 1578496
},
{
"epoch": 0.02,
"learning_rate": 2.414917028256057e-05,
"loss": 3.4684,
"step": 1579008
},
{
"epoch": 0.02,
"learning_rate": 2.4140800713853785e-05,
"loss": 3.4758,
"step": 1579520
},
{
"epoch": 0.02,
"learning_rate": 2.4132414766343265e-05,
"loss": 3.4615,
"step": 1580032
},
{
"epoch": 0.02,
"learning_rate": 2.4124028818832742e-05,
"loss": 3.4626,
"step": 1580544
},
{
"epoch": 0.02,
"learning_rate": 2.411564287132222e-05,
"loss": 3.4673,
"step": 1581056
},
{
"epoch": 0.02,
"learning_rate": 2.4107273302615434e-05,
"loss": 3.4649,
"step": 1581568
},
{
"epoch": 0.02,
"learning_rate": 2.4098887355104914e-05,
"loss": 3.4583,
"step": 1582080
},
{
"epoch": 0.02,
"learning_rate": 2.4090501407594394e-05,
"loss": 3.4615,
"step": 1582592
},
{
"epoch": 0.02,
"learning_rate": 2.4082115460083874e-05,
"loss": 3.4574,
"step": 1583104
},
{
"epoch": 0.02,
"learning_rate": 2.4073745891377086e-05,
"loss": 3.4731,
"step": 1583616
},
{
"epoch": 0.02,
"learning_rate": 2.4065359943866563e-05,
"loss": 3.4647,
"step": 1584128
},
{
"epoch": 0.02,
"learning_rate": 2.4056973996356043e-05,
"loss": 3.4625,
"step": 1584640
},
{
"epoch": 0.02,
"learning_rate": 2.4048588048845523e-05,
"loss": 3.4699,
"step": 1585152
},
{
"epoch": 0.02,
"learning_rate": 2.4040218480138735e-05,
"loss": 3.4837,
"step": 1585664
},
{
"epoch": 0.02,
"learning_rate": 2.4031832532628215e-05,
"loss": 3.475,
"step": 1586176
},
{
"epoch": 0.02,
"learning_rate": 2.4023446585117695e-05,
"loss": 3.4596,
"step": 1586688
},
{
"epoch": 0.02,
"learning_rate": 2.4015060637607175e-05,
"loss": 3.4668,
"step": 1587200
},
{
"epoch": 0.02,
"learning_rate": 2.4006691068900384e-05,
"loss": 3.4666,
"step": 1587712
},
{
"epoch": 0.02,
"learning_rate": 2.3998305121389868e-05,
"loss": 3.4618,
"step": 1588224
},
{
"epoch": 0.02,
"learning_rate": 2.3989919173879348e-05,
"loss": 3.462,
"step": 1588736
},
{
"epoch": 0.02,
"learning_rate": 2.3981533226368828e-05,
"loss": 3.4591,
"step": 1589248
},
{
"epoch": 0.02,
"learning_rate": 2.3973163657662037e-05,
"loss": 3.4697,
"step": 1589760
},
{
"epoch": 0.02,
"learning_rate": 2.3964777710151517e-05,
"loss": 3.4657,
"step": 1590272
},
{
"epoch": 0.02,
"learning_rate": 2.3956391762640997e-05,
"loss": 3.471,
"step": 1590784
},
{
"epoch": 0.02,
"learning_rate": 2.3948005815130477e-05,
"loss": 3.458,
"step": 1591296
},
{
"epoch": 0.02,
"learning_rate": 2.393963624642369e-05,
"loss": 3.4671,
"step": 1591808
},
{
"epoch": 0.02,
"learning_rate": 2.393125029891317e-05,
"loss": 3.4669,
"step": 1592320
},
{
"epoch": 0.02,
"learning_rate": 2.392286435140265e-05,
"loss": 3.476,
"step": 1592832
},
{
"epoch": 0.02,
"learning_rate": 2.391447840389213e-05,
"loss": 3.4672,
"step": 1593344
},
{
"epoch": 0.02,
"learning_rate": 2.3906108835185338e-05,
"loss": 3.4705,
"step": 1593856
},
{
"epoch": 0.02,
"learning_rate": 2.389772288767482e-05,
"loss": 3.4605,
"step": 1594368
},
{
"epoch": 0.02,
"learning_rate": 2.38893369401643e-05,
"loss": 3.4739,
"step": 1594880
},
{
"epoch": 0.02,
"learning_rate": 2.388095099265378e-05,
"loss": 3.4687,
"step": 1595392
},
{
"epoch": 0.02,
"learning_rate": 2.387258142394699e-05,
"loss": 3.4748,
"step": 1595904
},
{
"epoch": 0.02,
"learning_rate": 2.386419547643647e-05,
"loss": 3.4619,
"step": 1596416
},
{
"epoch": 0.02,
"learning_rate": 2.385580952892595e-05,
"loss": 3.4753,
"step": 1596928
},
{
"epoch": 0.02,
"learning_rate": 2.384742358141543e-05,
"loss": 3.4649,
"step": 1597440
},
{
"epoch": 0.02,
"learning_rate": 2.3839054012708643e-05,
"loss": 3.4853,
"step": 1597952
},
{
"epoch": 0.02,
"learning_rate": 2.3830668065198123e-05,
"loss": 3.4618,
"step": 1598464
},
{
"epoch": 0.02,
"learning_rate": 2.3822282117687603e-05,
"loss": 3.4723,
"step": 1598976
},
{
"epoch": 0.02,
"learning_rate": 2.3813896170177083e-05,
"loss": 3.469,
"step": 1599488
},
{
"epoch": 0.02,
"learning_rate": 2.3805526601470292e-05,
"loss": 3.4632,
"step": 1600000
},
{
"epoch": 0.02,
"learning_rate": 2.3797140653959775e-05,
"loss": 3.4719,
"step": 1600512
},
{
"epoch": 0.02,
"learning_rate": 2.3788754706449255e-05,
"loss": 3.4751,
"step": 1601024
},
{
"epoch": 0.02,
"learning_rate": 2.3780368758938735e-05,
"loss": 3.4651,
"step": 1601536
},
{
"epoch": 0.02,
"learning_rate": 2.3771999190231944e-05,
"loss": 3.4619,
"step": 1602048
},
{
"epoch": 0.02,
"learning_rate": 2.3763613242721424e-05,
"loss": 3.4661,
"step": 1602560
},
{
"epoch": 0.03,
"eval_loss": 3.8583500385284424,
"eval_runtime": 306.3194,
"eval_samples_per_second": 1245.729,
"eval_steps_per_second": 38.93,
"step": 1602720
},
{
"epoch": 1.0,
"learning_rate": 2.3755227295210904e-05,
"loss": 3.4586,
"step": 1603072
},
{
"epoch": 1.0,
"learning_rate": 2.3746841347700384e-05,
"loss": 3.4577,
"step": 1603584
},
{
"epoch": 1.0,
"learning_rate": 2.3738471778993596e-05,
"loss": 3.4679,
"step": 1604096
},
{
"epoch": 1.0,
"learning_rate": 2.3730085831483076e-05,
"loss": 3.4679,
"step": 1604608
},
{
"epoch": 1.0,
"learning_rate": 2.3721699883972556e-05,
"loss": 3.4791,
"step": 1605120
},
{
"epoch": 1.0,
"learning_rate": 2.3713313936462036e-05,
"loss": 3.4631,
"step": 1605632
},
{
"epoch": 1.0,
"learning_rate": 2.3704944367755245e-05,
"loss": 3.4588,
"step": 1606144
},
{
"epoch": 1.0,
"learning_rate": 2.369655842024473e-05,
"loss": 3.4621,
"step": 1606656
},
{
"epoch": 1.0,
"learning_rate": 2.368817247273421e-05,
"loss": 3.4758,
"step": 1607168
},
{
"epoch": 1.0,
"learning_rate": 2.367978652522369e-05,
"loss": 3.4626,
"step": 1607680
},
{
"epoch": 1.0,
"learning_rate": 2.3671416956516898e-05,
"loss": 3.4587,
"step": 1608192
},
{
"epoch": 1.0,
"learning_rate": 2.3663031009006378e-05,
"loss": 3.4651,
"step": 1608704
},
{
"epoch": 1.0,
"learning_rate": 2.365466144029959e-05,
"loss": 3.463,
"step": 1609216
},
{
"epoch": 1.0,
"learning_rate": 2.364627549278907e-05,
"loss": 3.4582,
"step": 1609728
},
{
"epoch": 1.0,
"learning_rate": 2.363788954527855e-05,
"loss": 3.4632,
"step": 1610240
},
{
"epoch": 1.0,
"learning_rate": 2.362950359776803e-05,
"loss": 3.4542,
"step": 1610752
},
{
"epoch": 1.0,
"learning_rate": 2.362111765025751e-05,
"loss": 3.4531,
"step": 1611264
},
{
"epoch": 1.0,
"learning_rate": 2.3612731702746987e-05,
"loss": 3.457,
"step": 1611776
},
{
"epoch": 1.0,
"learning_rate": 2.3604345755236467e-05,
"loss": 3.4541,
"step": 1612288
},
{
"epoch": 1.0,
"learning_rate": 2.3595959807725947e-05,
"loss": 3.4772,
"step": 1612800
},
{
"epoch": 1.0,
"learning_rate": 2.3587590239019162e-05,
"loss": 3.4657,
"step": 1613312
},
{
"epoch": 1.0,
"learning_rate": 2.357920429150864e-05,
"loss": 3.4612,
"step": 1613824
},
{
"epoch": 1.0,
"learning_rate": 2.357081834399812e-05,
"loss": 3.4594,
"step": 1614336
},
{
"epoch": 1.0,
"learning_rate": 2.35624323964876e-05,
"loss": 3.4697,
"step": 1614848
},
{
"epoch": 1.0,
"learning_rate": 2.3554062827780808e-05,
"loss": 3.4553,
"step": 1615360
},
{
"epoch": 1.0,
"learning_rate": 2.354567688027029e-05,
"loss": 3.4659,
"step": 1615872
},
{
"epoch": 1.0,
"learning_rate": 2.353729093275977e-05,
"loss": 3.4543,
"step": 1616384
},
{
"epoch": 1.0,
"learning_rate": 2.352890498524925e-05,
"loss": 3.4614,
"step": 1616896
},
{
"epoch": 1.0,
"learning_rate": 2.352053541654246e-05,
"loss": 3.457,
"step": 1617408
},
{
"epoch": 1.0,
"learning_rate": 2.351214946903194e-05,
"loss": 3.4587,
"step": 1617920
},
{
"epoch": 1.01,
"learning_rate": 2.350376352152142e-05,
"loss": 3.4672,
"step": 1618432
},
{
"epoch": 1.01,
"learning_rate": 2.34953775740109e-05,
"loss": 3.4651,
"step": 1618944
},
{
"epoch": 1.01,
"learning_rate": 2.3487008005304113e-05,
"loss": 3.4686,
"step": 1619456
},
{
"epoch": 1.01,
"learning_rate": 2.3478622057793593e-05,
"loss": 3.4676,
"step": 1619968
},
{
"epoch": 1.01,
"learning_rate": 2.3470236110283073e-05,
"loss": 3.4529,
"step": 1620480
},
{
"epoch": 1.01,
"learning_rate": 2.3461850162772553e-05,
"loss": 3.4638,
"step": 1620992
},
{
"epoch": 1.01,
"learning_rate": 2.345348059406576e-05,
"loss": 3.461,
"step": 1621504
},
{
"epoch": 1.01,
"learning_rate": 2.3445094646555245e-05,
"loss": 3.4527,
"step": 1622016
},
{
"epoch": 1.01,
"learning_rate": 2.3436708699044725e-05,
"loss": 3.4567,
"step": 1622528
},
{
"epoch": 1.01,
"learning_rate": 2.3428339130337934e-05,
"loss": 3.4549,
"step": 1623040
},
{
"epoch": 1.01,
"learning_rate": 2.3419953182827414e-05,
"loss": 3.4572,
"step": 1623552
},
{
"epoch": 1.01,
"learning_rate": 2.3411567235316894e-05,
"loss": 3.4707,
"step": 1624064
},
{
"epoch": 1.01,
"learning_rate": 2.3403181287806374e-05,
"loss": 3.4604,
"step": 1624576
},
{
"epoch": 1.01,
"learning_rate": 2.3394795340295854e-05,
"loss": 3.4568,
"step": 1625088
},
{
"epoch": 1.01,
"learning_rate": 2.3386425771589066e-05,
"loss": 3.4654,
"step": 1625600
},
{
"epoch": 1.01,
"learning_rate": 2.3378039824078546e-05,
"loss": 3.4607,
"step": 1626112
},
{
"epoch": 1.01,
"learning_rate": 2.3369653876568026e-05,
"loss": 3.4606,
"step": 1626624
},
{
"epoch": 1.01,
"learning_rate": 2.3361267929057506e-05,
"loss": 3.4495,
"step": 1627136
},
{
"epoch": 1.01,
"learning_rate": 2.3352898360350715e-05,
"loss": 3.4374,
"step": 1627648
},
{
"epoch": 1.01,
"learning_rate": 2.33445124128402e-05,
"loss": 3.4672,
"step": 1628160
},
{
"epoch": 1.01,
"learning_rate": 2.333612646532968e-05,
"loss": 3.4621,
"step": 1628672
},
{
"epoch": 1.01,
"learning_rate": 2.332774051781916e-05,
"loss": 3.4567,
"step": 1629184
},
{
"epoch": 1.01,
"learning_rate": 2.3319370949112368e-05,
"loss": 3.4553,
"step": 1629696
},
{
"epoch": 1.01,
"learning_rate": 2.3310985001601848e-05,
"loss": 3.4588,
"step": 1630208
},
{
"epoch": 1.01,
"learning_rate": 2.3302599054091328e-05,
"loss": 3.4432,
"step": 1630720
},
{
"epoch": 1.01,
"learning_rate": 2.329422948538454e-05,
"loss": 3.4579,
"step": 1631232
},
{
"epoch": 1.01,
"learning_rate": 2.328584353787402e-05,
"loss": 3.4609,
"step": 1631744
},
{
"epoch": 1.01,
"learning_rate": 2.32774575903635e-05,
"loss": 3.4602,
"step": 1632256
},
{
"epoch": 1.01,
"learning_rate": 2.326907164285298e-05,
"loss": 3.4567,
"step": 1632768
},
{
"epoch": 1.01,
"learning_rate": 2.326070207414619e-05,
"loss": 3.4594,
"step": 1633280
},
{
"epoch": 1.01,
"learning_rate": 2.325231612663567e-05,
"loss": 3.4497,
"step": 1633792
},
{
"epoch": 1.01,
"learning_rate": 2.3243930179125152e-05,
"loss": 3.461,
"step": 1634304
},
{
"epoch": 1.01,
"learning_rate": 2.3235544231614632e-05,
"loss": 3.4486,
"step": 1634816
},
{
"epoch": 1.01,
"learning_rate": 2.3227158284104112e-05,
"loss": 3.4515,
"step": 1635328
},
{
"epoch": 1.01,
"learning_rate": 2.321878871539732e-05,
"loss": 3.4645,
"step": 1635840
},
{
"epoch": 1.01,
"learning_rate": 2.32104027678868e-05,
"loss": 3.4576,
"step": 1636352
},
{
"epoch": 1.01,
"learning_rate": 2.320201682037628e-05,
"loss": 3.4533,
"step": 1636864
},
{
"epoch": 1.01,
"learning_rate": 2.319363087286576e-05,
"loss": 3.4454,
"step": 1637376
},
{
"epoch": 1.01,
"learning_rate": 2.3185261304158974e-05,
"loss": 3.4512,
"step": 1637888
},
{
"epoch": 1.01,
"learning_rate": 2.3176875356648454e-05,
"loss": 3.4602,
"step": 1638400
},
{
"epoch": 1.01,
"learning_rate": 2.3168489409137934e-05,
"loss": 3.4638,
"step": 1638912
},
{
"epoch": 1.01,
"learning_rate": 2.316010346162741e-05,
"loss": 3.4568,
"step": 1639424
},
{
"epoch": 1.01,
"learning_rate": 2.3151733892920623e-05,
"loss": 3.4689,
"step": 1639936
},
{
"epoch": 1.01,
"learning_rate": 2.3143347945410106e-05,
"loss": 3.4633,
"step": 1640448
},
{
"epoch": 1.01,
"learning_rate": 2.3134961997899586e-05,
"loss": 3.4651,
"step": 1640960
},
{
"epoch": 1.01,
"learning_rate": 2.3126592429192795e-05,
"loss": 3.4556,
"step": 1641472
},
{
"epoch": 1.01,
"learning_rate": 2.3118206481682275e-05,
"loss": 3.4571,
"step": 1641984
},
{
"epoch": 1.01,
"learning_rate": 2.3109820534171755e-05,
"loss": 3.4543,
"step": 1642496
},
{
"epoch": 1.01,
"learning_rate": 2.310143458666123e-05,
"loss": 3.4501,
"step": 1643008
},
{
"epoch": 1.01,
"learning_rate": 2.3093048639150715e-05,
"loss": 3.464,
"step": 1643520
},
{
"epoch": 1.01,
"learning_rate": 2.3084679070443927e-05,
"loss": 3.453,
"step": 1644032
},
{
"epoch": 1.01,
"learning_rate": 2.3076293122933407e-05,
"loss": 3.4652,
"step": 1644544
},
{
"epoch": 1.01,
"learning_rate": 2.3067907175422884e-05,
"loss": 3.4695,
"step": 1645056
},
{
"epoch": 1.01,
"learning_rate": 2.3059521227912364e-05,
"loss": 3.4391,
"step": 1645568
},
{
"epoch": 1.01,
"learning_rate": 2.3051151659205576e-05,
"loss": 3.4576,
"step": 1646080
},
{
"epoch": 1.01,
"learning_rate": 2.3042765711695056e-05,
"loss": 3.4553,
"step": 1646592
},
{
"epoch": 1.01,
"learning_rate": 2.3034379764184536e-05,
"loss": 3.4597,
"step": 1647104
},
{
"epoch": 1.01,
"learning_rate": 2.3025993816674016e-05,
"loss": 3.4542,
"step": 1647616
},
{
"epoch": 1.01,
"learning_rate": 2.301762424796723e-05,
"loss": 3.4493,
"step": 1648128
},
{
"epoch": 1.02,
"learning_rate": 2.3009238300456705e-05,
"loss": 3.4552,
"step": 1648640
},
{
"epoch": 1.02,
"learning_rate": 2.3000852352946185e-05,
"loss": 3.454,
"step": 1649152
},
{
"epoch": 1.02,
"learning_rate": 2.29924827842394e-05,
"loss": 3.4551,
"step": 1649664
},
{
"epoch": 1.02,
"learning_rate": 2.298409683672888e-05,
"loss": 3.4544,
"step": 1650176
},
{
"epoch": 1.02,
"learning_rate": 2.2975710889218358e-05,
"loss": 3.4643,
"step": 1650688
},
{
"epoch": 1.02,
"learning_rate": 2.2967324941707838e-05,
"loss": 3.4598,
"step": 1651200
},
{
"epoch": 1.02,
"learning_rate": 2.295895537300105e-05,
"loss": 3.4598,
"step": 1651712
},
{
"epoch": 1.02,
"learning_rate": 2.295056942549053e-05,
"loss": 3.4423,
"step": 1652224
},
{
"epoch": 1.02,
"learning_rate": 2.294218347798001e-05,
"loss": 3.4602,
"step": 1652736
},
{
"epoch": 1.02,
"learning_rate": 2.293379753046949e-05,
"loss": 3.4579,
"step": 1653248
},
{
"epoch": 1.02,
"learning_rate": 2.2925427961762702e-05,
"loss": 3.4638,
"step": 1653760
},
{
"epoch": 1.02,
"learning_rate": 2.291704201425218e-05,
"loss": 3.4507,
"step": 1654272
},
{
"epoch": 1.02,
"learning_rate": 2.290865606674166e-05,
"loss": 3.4595,
"step": 1654784
},
{
"epoch": 1.02,
"learning_rate": 2.290027011923114e-05,
"loss": 3.4541,
"step": 1655296
},
{
"epoch": 1.02,
"learning_rate": 2.2891900550524355e-05,
"loss": 3.4631,
"step": 1655808
},
{
"epoch": 1.02,
"learning_rate": 2.288351460301383e-05,
"loss": 3.4468,
"step": 1656320
},
{
"epoch": 1.02,
"learning_rate": 2.287512865550331e-05,
"loss": 3.4559,
"step": 1656832
},
{
"epoch": 1.02,
"learning_rate": 2.286674270799279e-05,
"loss": 3.4552,
"step": 1657344
},
{
"epoch": 1.02,
"learning_rate": 2.2858373139286004e-05,
"loss": 3.454,
"step": 1657856
},
{
"epoch": 1.02,
"learning_rate": 2.2849987191775484e-05,
"loss": 3.4446,
"step": 1658368
},
{
"epoch": 1.02,
"learning_rate": 2.2841601244264964e-05,
"loss": 3.4542,
"step": 1658880
},
{
"epoch": 1.02,
"learning_rate": 2.2833215296754444e-05,
"loss": 3.4467,
"step": 1659392
},
{
"epoch": 1.02,
"learning_rate": 2.2824845728047653e-05,
"loss": 3.4579,
"step": 1659904
},
{
"epoch": 1.02,
"learning_rate": 2.2816459780537133e-05,
"loss": 3.4568,
"step": 1660416
},
{
"epoch": 1.02,
"learning_rate": 2.2808073833026613e-05,
"loss": 3.4474,
"step": 1660928
},
{
"epoch": 1.02,
"learning_rate": 2.2799687885516093e-05,
"loss": 3.4616,
"step": 1661440
},
{
"epoch": 1.02,
"learning_rate": 2.2791318316809305e-05,
"loss": 3.4732,
"step": 1661952
},
{
"epoch": 1.02,
"learning_rate": 2.2782932369298785e-05,
"loss": 3.4654,
"step": 1662464
},
{
"epoch": 1.02,
"learning_rate": 2.2774546421788265e-05,
"loss": 3.446,
"step": 1662976
},
{
"epoch": 1.02,
"learning_rate": 2.2766160474277745e-05,
"loss": 3.457,
"step": 1663488
},
{
"epoch": 1.02,
"learning_rate": 2.2757790905570954e-05,
"loss": 3.4531,
"step": 1664000
},
{
"epoch": 1.02,
"learning_rate": 2.2749404958060437e-05,
"loss": 3.4483,
"step": 1664512
},
{
"epoch": 1.02,
"learning_rate": 2.2741019010549917e-05,
"loss": 3.452,
"step": 1665024
},
{
"epoch": 1.02,
"learning_rate": 2.2732633063039397e-05,
"loss": 3.4446,
"step": 1665536
},
{
"epoch": 1.02,
"learning_rate": 2.2724263494332606e-05,
"loss": 3.4606,
"step": 1666048
},
{
"epoch": 1.02,
"learning_rate": 2.2715877546822086e-05,
"loss": 3.4517,
"step": 1666560
},
{
"epoch": 1.02,
"learning_rate": 2.2707491599311566e-05,
"loss": 3.4609,
"step": 1667072
},
{
"epoch": 1.02,
"learning_rate": 2.2699105651801046e-05,
"loss": 3.4503,
"step": 1667584
},
{
"epoch": 1.02,
"learning_rate": 2.269073608309426e-05,
"loss": 3.4526,
"step": 1668096
},
{
"epoch": 1.02,
"learning_rate": 2.268235013558374e-05,
"loss": 3.4608,
"step": 1668608
},
{
"epoch": 1.02,
"learning_rate": 2.267396418807322e-05,
"loss": 3.462,
"step": 1669120
},
{
"epoch": 1.02,
"learning_rate": 2.26655782405627e-05,
"loss": 3.4561,
"step": 1669632
},
{
"epoch": 1.02,
"learning_rate": 2.2657208671855908e-05,
"loss": 3.4582,
"step": 1670144
},
{
"epoch": 1.02,
"learning_rate": 2.264882272434539e-05,
"loss": 3.4462,
"step": 1670656
},
{
"epoch": 1.02,
"learning_rate": 2.264043677683487e-05,
"loss": 3.4635,
"step": 1671168
},
{
"epoch": 1.02,
"learning_rate": 2.263205082932435e-05,
"loss": 3.4553,
"step": 1671680
},
{
"epoch": 1.02,
"learning_rate": 2.262368126061756e-05,
"loss": 3.4642,
"step": 1672192
},
{
"epoch": 1.02,
"learning_rate": 2.261529531310704e-05,
"loss": 3.4506,
"step": 1672704
},
{
"epoch": 1.02,
"learning_rate": 2.260690936559652e-05,
"loss": 3.461,
"step": 1673216
},
{
"epoch": 1.02,
"learning_rate": 2.2598523418086e-05,
"loss": 3.4516,
"step": 1673728
},
{
"epoch": 1.02,
"learning_rate": 2.2590153849379212e-05,
"loss": 3.4788,
"step": 1674240
},
{
"epoch": 1.02,
"learning_rate": 2.2581767901868692e-05,
"loss": 3.4492,
"step": 1674752
},
{
"epoch": 1.02,
"learning_rate": 2.2573381954358172e-05,
"loss": 3.4623,
"step": 1675264
},
{
"epoch": 1.02,
"learning_rate": 2.2564996006847652e-05,
"loss": 3.4548,
"step": 1675776
},
{
"epoch": 1.02,
"learning_rate": 2.255662643814086e-05,
"loss": 3.4541,
"step": 1676288
},
{
"epoch": 1.02,
"learning_rate": 2.254824049063034e-05,
"loss": 3.458,
"step": 1676800
},
{
"epoch": 1.02,
"learning_rate": 2.2539854543119825e-05,
"loss": 3.4597,
"step": 1677312
},
{
"epoch": 1.02,
"learning_rate": 2.2531468595609305e-05,
"loss": 3.4603,
"step": 1677824
},
{
"epoch": 1.02,
"learning_rate": 2.2523099026902514e-05,
"loss": 3.4477,
"step": 1678336
},
{
"epoch": 1.02,
"learning_rate": 2.2514713079391994e-05,
"loss": 3.4567,
"step": 1678848
},
{
"epoch": 1.03,
"eval_loss": 3.859640598297119,
"eval_runtime": 306.9907,
"eval_samples_per_second": 1243.005,
"eval_steps_per_second": 38.845,
"step": 1679040
},
{
"epoch": 0.0,
"learning_rate": 2.2506327131881474e-05,
"loss": 3.452,
"step": 1679360
},
{
"epoch": 0.0,
"learning_rate": 2.2497941184370954e-05,
"loss": 3.4476,
"step": 1679872
},
{
"epoch": 0.0,
"learning_rate": 2.2489555236860433e-05,
"loss": 3.4518,
"step": 1680384
},
{
"epoch": 0.0,
"learning_rate": 2.2481169289349913e-05,
"loss": 3.4578,
"step": 1680896
},
{
"epoch": 0.0,
"learning_rate": 2.2472799720643126e-05,
"loss": 3.4662,
"step": 1681408
},
{
"epoch": 0.0,
"learning_rate": 2.2464413773132602e-05,
"loss": 3.4571,
"step": 1681920
},
{
"epoch": 0.0,
"learning_rate": 2.2456027825622082e-05,
"loss": 3.4414,
"step": 1682432
},
{
"epoch": 0.0,
"learning_rate": 2.2447641878111562e-05,
"loss": 3.4543,
"step": 1682944
},
{
"epoch": 0.0,
"learning_rate": 2.2439272309404778e-05,
"loss": 3.461,
"step": 1683456
},
{
"epoch": 0.0,
"learning_rate": 2.2430886361894255e-05,
"loss": 3.4538,
"step": 1683968
},
{
"epoch": 0.0,
"learning_rate": 2.2422500414383735e-05,
"loss": 3.4479,
"step": 1684480
},
{
"epoch": 0.0,
"learning_rate": 2.2414114466873215e-05,
"loss": 3.4517,
"step": 1684992
},
{
"epoch": 0.0,
"learning_rate": 2.2405761276970156e-05,
"loss": 3.4549,
"step": 1685504
},
{
"epoch": 0.0,
"learning_rate": 2.239737532945964e-05,
"loss": 3.4448,
"step": 1686016
},
{
"epoch": 0.0,
"learning_rate": 2.238898938194912e-05,
"loss": 3.453,
"step": 1686528
},
{
"epoch": 0.0,
"learning_rate": 2.23806034344386e-05,
"loss": 3.4438,
"step": 1687040
},
{
"epoch": 0.0,
"learning_rate": 2.2372217486928076e-05,
"loss": 3.4408,
"step": 1687552
},
{
"epoch": 0.0,
"learning_rate": 2.2363831539417556e-05,
"loss": 3.4452,
"step": 1688064
},
{
"epoch": 0.0,
"learning_rate": 2.2355445591907036e-05,
"loss": 3.4429,
"step": 1688576
},
{
"epoch": 0.0,
"learning_rate": 2.2347059644396516e-05,
"loss": 3.465,
"step": 1689088
},
{
"epoch": 0.0,
"learning_rate": 2.233869007568973e-05,
"loss": 3.4574,
"step": 1689600
},
{
"epoch": 0.0,
"learning_rate": 2.233030412817921e-05,
"loss": 3.4502,
"step": 1690112
},
{
"epoch": 0.0,
"learning_rate": 2.232191818066869e-05,
"loss": 3.4482,
"step": 1690624
},
{
"epoch": 0.0,
"learning_rate": 2.231353223315817e-05,
"loss": 3.4574,
"step": 1691136
},
{
"epoch": 0.0,
"learning_rate": 2.2305162664451378e-05,
"loss": 3.4457,
"step": 1691648
},
{
"epoch": 0.0,
"learning_rate": 2.229677671694086e-05,
"loss": 3.4544,
"step": 1692160
},
{
"epoch": 0.0,
"learning_rate": 2.228839076943034e-05,
"loss": 3.4427,
"step": 1692672
},
{
"epoch": 0.0,
"learning_rate": 2.228000482191982e-05,
"loss": 3.4512,
"step": 1693184
},
{
"epoch": 0.0,
"learning_rate": 2.227163525321303e-05,
"loss": 3.4496,
"step": 1693696
},
{
"epoch": 0.0,
"learning_rate": 2.226324930570251e-05,
"loss": 3.4442,
"step": 1694208
},
{
"epoch": 0.01,
"learning_rate": 2.225486335819199e-05,
"loss": 3.4557,
"step": 1694720
},
{
"epoch": 0.01,
"learning_rate": 2.224647741068147e-05,
"loss": 3.455,
"step": 1695232
},
{
"epoch": 0.01,
"learning_rate": 2.2238107841974682e-05,
"loss": 3.4523,
"step": 1695744
},
{
"epoch": 0.01,
"learning_rate": 2.2229721894464162e-05,
"loss": 3.4567,
"step": 1696256
},
{
"epoch": 0.01,
"learning_rate": 2.2221335946953642e-05,
"loss": 3.4421,
"step": 1696768
},
{
"epoch": 0.01,
"learning_rate": 2.2212949999443122e-05,
"loss": 3.4568,
"step": 1697280
},
{
"epoch": 0.01,
"learning_rate": 2.220458043073633e-05,
"loss": 3.4448,
"step": 1697792
},
{
"epoch": 0.01,
"learning_rate": 2.2196194483225815e-05,
"loss": 3.4415,
"step": 1698304
},
{
"epoch": 0.01,
"learning_rate": 2.2187808535715294e-05,
"loss": 3.4446,
"step": 1698816
},
{
"epoch": 0.01,
"learning_rate": 2.2179438967008504e-05,
"loss": 3.4425,
"step": 1699328
},
{
"epoch": 0.01,
"learning_rate": 2.2171053019497984e-05,
"loss": 3.4476,
"step": 1699840
},
{
"epoch": 0.01,
"learning_rate": 2.2162667071987463e-05,
"loss": 3.4539,
"step": 1700352
},
{
"epoch": 0.01,
"learning_rate": 2.2154281124476943e-05,
"loss": 3.4505,
"step": 1700864
},
{
"epoch": 0.01,
"learning_rate": 2.2145895176966423e-05,
"loss": 3.4476,
"step": 1701376
},
{
"epoch": 0.01,
"learning_rate": 2.2137509229455903e-05,
"loss": 3.454,
"step": 1701888
},
{
"epoch": 0.01,
"learning_rate": 2.2129123281945383e-05,
"loss": 3.4498,
"step": 1702400
},
{
"epoch": 0.01,
"learning_rate": 2.2120737334434863e-05,
"loss": 3.4498,
"step": 1702912
},
{
"epoch": 0.01,
"learning_rate": 2.2112367765728076e-05,
"loss": 3.4364,
"step": 1703424
},
{
"epoch": 0.01,
"learning_rate": 2.2103981818217552e-05,
"loss": 3.4262,
"step": 1703936
},
{
"epoch": 0.01,
"learning_rate": 2.2095595870707032e-05,
"loss": 3.4561,
"step": 1704448
},
{
"epoch": 0.01,
"learning_rate": 2.2087209923196516e-05,
"loss": 3.4539,
"step": 1704960
},
{
"epoch": 0.01,
"learning_rate": 2.2078840354489728e-05,
"loss": 3.4426,
"step": 1705472
},
{
"epoch": 0.01,
"learning_rate": 2.2070454406979205e-05,
"loss": 3.4494,
"step": 1705984
},
{
"epoch": 0.01,
"learning_rate": 2.2062068459468685e-05,
"loss": 3.446,
"step": 1706496
},
{
"epoch": 0.01,
"learning_rate": 2.2053682511958165e-05,
"loss": 3.4326,
"step": 1707008
},
{
"epoch": 0.01,
"learning_rate": 2.2045312943251377e-05,
"loss": 3.4429,
"step": 1707520
},
{
"epoch": 0.01,
"learning_rate": 2.2036926995740857e-05,
"loss": 3.4504,
"step": 1708032
},
{
"epoch": 0.01,
"learning_rate": 2.2028541048230337e-05,
"loss": 3.4483,
"step": 1708544
},
{
"epoch": 0.01,
"learning_rate": 2.2020155100719817e-05,
"loss": 3.4443,
"step": 1709056
},
{
"epoch": 0.01,
"learning_rate": 2.2011785532013026e-05,
"loss": 3.4482,
"step": 1709568
},
{
"epoch": 0.01,
"learning_rate": 2.2003399584502506e-05,
"loss": 3.4384,
"step": 1710080
},
{
"epoch": 0.01,
"learning_rate": 2.1995013636991986e-05,
"loss": 3.4503,
"step": 1710592
},
{
"epoch": 0.01,
"learning_rate": 2.198662768948147e-05,
"loss": 3.4373,
"step": 1711104
},
{
"epoch": 0.01,
"learning_rate": 2.197825812077468e-05,
"loss": 3.4388,
"step": 1711616
},
{
"epoch": 0.01,
"learning_rate": 2.196987217326416e-05,
"loss": 3.4528,
"step": 1712128
},
{
"epoch": 0.01,
"learning_rate": 2.1961486225753638e-05,
"loss": 3.4458,
"step": 1712640
},
{
"epoch": 0.01,
"learning_rate": 2.1953100278243118e-05,
"loss": 3.4455,
"step": 1713152
},
{
"epoch": 0.01,
"learning_rate": 2.194473070953633e-05,
"loss": 3.4356,
"step": 1713664
},
{
"epoch": 0.01,
"learning_rate": 2.193634476202581e-05,
"loss": 3.4399,
"step": 1714176
},
{
"epoch": 0.01,
"learning_rate": 2.192795881451529e-05,
"loss": 3.443,
"step": 1714688
},
{
"epoch": 0.01,
"learning_rate": 2.191957286700477e-05,
"loss": 3.4552,
"step": 1715200
},
{
"epoch": 0.01,
"learning_rate": 2.191120329829798e-05,
"loss": 3.4449,
"step": 1715712
},
{
"epoch": 0.01,
"learning_rate": 2.190281735078746e-05,
"loss": 3.4591,
"step": 1716224
},
{
"epoch": 0.01,
"learning_rate": 2.189443140327694e-05,
"loss": 3.4488,
"step": 1716736
},
{
"epoch": 0.01,
"learning_rate": 2.1886045455766423e-05,
"loss": 3.4565,
"step": 1717248
},
{
"epoch": 0.01,
"learning_rate": 2.1877675887059632e-05,
"loss": 3.4452,
"step": 1717760
},
{
"epoch": 0.01,
"learning_rate": 2.1869289939549112e-05,
"loss": 3.4468,
"step": 1718272
},
{
"epoch": 0.01,
"learning_rate": 2.1860903992038592e-05,
"loss": 3.4436,
"step": 1718784
},
{
"epoch": 0.01,
"learning_rate": 2.1852518044528072e-05,
"loss": 3.4366,
"step": 1719296
},
{
"epoch": 0.01,
"learning_rate": 2.1844148475821284e-05,
"loss": 3.4538,
"step": 1719808
},
{
"epoch": 0.01,
"learning_rate": 2.1835762528310764e-05,
"loss": 3.4441,
"step": 1720320
},
{
"epoch": 0.01,
"learning_rate": 2.1827376580800244e-05,
"loss": 3.4552,
"step": 1720832
},
{
"epoch": 0.01,
"learning_rate": 2.1818990633289724e-05,
"loss": 3.4551,
"step": 1721344
},
{
"epoch": 0.01,
"learning_rate": 2.1810621064582933e-05,
"loss": 3.4291,
"step": 1721856
},
{
"epoch": 0.01,
"learning_rate": 2.1802235117072413e-05,
"loss": 3.449,
"step": 1722368
},
{
"epoch": 0.01,
"learning_rate": 2.1793849169561893e-05,
"loss": 3.4447,
"step": 1722880
},
{
"epoch": 0.01,
"learning_rate": 2.1785463222051373e-05,
"loss": 3.4487,
"step": 1723392
},
{
"epoch": 0.01,
"learning_rate": 2.1777093653344586e-05,
"loss": 3.4426,
"step": 1723904
},
{
"epoch": 0.01,
"learning_rate": 2.1768707705834066e-05,
"loss": 3.4388,
"step": 1724416
},
{
"epoch": 0.02,
"learning_rate": 2.1760321758323546e-05,
"loss": 3.4455,
"step": 1724928
},
{
"epoch": 0.02,
"learning_rate": 2.1751935810813026e-05,
"loss": 3.4411,
"step": 1725440
},
{
"epoch": 0.02,
"learning_rate": 2.1743566242106238e-05,
"loss": 3.4428,
"step": 1725952
},
{
"epoch": 0.02,
"learning_rate": 2.1735180294595718e-05,
"loss": 3.4457,
"step": 1726464
},
{
"epoch": 0.02,
"learning_rate": 2.1726794347085198e-05,
"loss": 3.4526,
"step": 1726976
},
{
"epoch": 0.02,
"learning_rate": 2.1718408399574678e-05,
"loss": 3.4566,
"step": 1727488
},
{
"epoch": 0.02,
"learning_rate": 2.1710038830867887e-05,
"loss": 3.4404,
"step": 1728000
},
{
"epoch": 0.02,
"learning_rate": 2.1701652883357367e-05,
"loss": 3.4361,
"step": 1728512
},
{
"epoch": 0.02,
"learning_rate": 2.1693266935846847e-05,
"loss": 3.4486,
"step": 1729024
},
{
"epoch": 0.02,
"learning_rate": 2.1684880988336327e-05,
"loss": 3.4471,
"step": 1729536
},
{
"epoch": 0.02,
"learning_rate": 2.167651141962954e-05,
"loss": 3.4536,
"step": 1730048
},
{
"epoch": 0.02,
"learning_rate": 2.166812547211902e-05,
"loss": 3.441,
"step": 1730560
},
{
"epoch": 0.02,
"learning_rate": 2.16597395246085e-05,
"loss": 3.447,
"step": 1731072
},
{
"epoch": 0.02,
"learning_rate": 2.165135357709798e-05,
"loss": 3.4445,
"step": 1731584
},
{
"epoch": 0.02,
"learning_rate": 2.164298400839119e-05,
"loss": 3.4511,
"step": 1732096
},
{
"epoch": 0.02,
"learning_rate": 2.163459806088067e-05,
"loss": 3.4338,
"step": 1732608
},
{
"epoch": 0.02,
"learning_rate": 2.162621211337015e-05,
"loss": 3.4449,
"step": 1733120
},
{
"epoch": 0.02,
"learning_rate": 2.1617826165859628e-05,
"loss": 3.4412,
"step": 1733632
},
{
"epoch": 0.02,
"learning_rate": 2.160945659715284e-05,
"loss": 3.4449,
"step": 1734144
},
{
"epoch": 0.02,
"learning_rate": 2.160107064964232e-05,
"loss": 3.4337,
"step": 1734656
},
{
"epoch": 0.02,
"learning_rate": 2.15926847021318e-05,
"loss": 3.4419,
"step": 1735168
},
{
"epoch": 0.02,
"learning_rate": 2.1584315133425013e-05,
"loss": 3.4363,
"step": 1735680
},
{
"epoch": 0.02,
"learning_rate": 2.1575929185914493e-05,
"loss": 3.4489,
"step": 1736192
},
{
"epoch": 0.02,
"learning_rate": 2.1567543238403973e-05,
"loss": 3.4454,
"step": 1736704
},
{
"epoch": 0.02,
"learning_rate": 2.1559157290893453e-05,
"loss": 3.4402,
"step": 1737216
},
{
"epoch": 0.02,
"learning_rate": 2.1550787722186662e-05,
"loss": 3.4432,
"step": 1737728
},
{
"epoch": 0.02,
"learning_rate": 2.1542401774676142e-05,
"loss": 3.4596,
"step": 1738240
},
{
"epoch": 0.02,
"learning_rate": 2.1534015827165625e-05,
"loss": 3.4561,
"step": 1738752
},
{
"epoch": 0.02,
"learning_rate": 2.1525629879655102e-05,
"loss": 3.4383,
"step": 1739264
},
{
"epoch": 0.02,
"learning_rate": 2.1517260310948314e-05,
"loss": 3.4425,
"step": 1739776
},
{
"epoch": 0.02,
"learning_rate": 2.1508874363437794e-05,
"loss": 3.4449,
"step": 1740288
},
{
"epoch": 0.02,
"learning_rate": 2.1500488415927274e-05,
"loss": 3.436,
"step": 1740800
},
{
"epoch": 0.02,
"learning_rate": 2.1492102468416754e-05,
"loss": 3.4426,
"step": 1741312
},
{
"epoch": 0.02,
"learning_rate": 2.1483732899709967e-05,
"loss": 3.43,
"step": 1741824
},
{
"epoch": 0.02,
"learning_rate": 2.1475346952199447e-05,
"loss": 3.4521,
"step": 1742336
},
{
"epoch": 0.02,
"learning_rate": 2.1466961004688927e-05,
"loss": 3.4376,
"step": 1742848
},
{
"epoch": 0.02,
"learning_rate": 2.1458575057178403e-05,
"loss": 3.4505,
"step": 1743360
},
{
"epoch": 0.02,
"learning_rate": 2.1450205488471616e-05,
"loss": 3.4407,
"step": 1743872
},
{
"epoch": 0.02,
"learning_rate": 2.1441819540961096e-05,
"loss": 3.4427,
"step": 1744384
},
{
"epoch": 0.02,
"learning_rate": 2.1433433593450576e-05,
"loss": 3.4449,
"step": 1744896
},
{
"epoch": 0.02,
"learning_rate": 2.1425047645940056e-05,
"loss": 3.4524,
"step": 1745408
},
{
"epoch": 0.02,
"learning_rate": 2.1416678077233268e-05,
"loss": 3.444,
"step": 1745920
},
{
"epoch": 0.02,
"learning_rate": 2.1408292129722748e-05,
"loss": 3.4487,
"step": 1746432
},
{
"epoch": 0.02,
"learning_rate": 2.1399906182212225e-05,
"loss": 3.4366,
"step": 1746944
},
{
"epoch": 0.02,
"learning_rate": 2.1391520234701708e-05,
"loss": 3.454,
"step": 1747456
},
{
"epoch": 0.02,
"learning_rate": 2.138315066599492e-05,
"loss": 3.442,
"step": 1747968
},
{
"epoch": 0.02,
"learning_rate": 2.1374764718484397e-05,
"loss": 3.4502,
"step": 1748480
},
{
"epoch": 0.02,
"learning_rate": 2.1366378770973877e-05,
"loss": 3.442,
"step": 1748992
},
{
"epoch": 0.02,
"learning_rate": 2.1357992823463357e-05,
"loss": 3.4528,
"step": 1749504
},
{
"epoch": 0.02,
"learning_rate": 2.134962325475657e-05,
"loss": 3.4424,
"step": 1750016
},
{
"epoch": 0.02,
"learning_rate": 2.134123730724605e-05,
"loss": 3.4647,
"step": 1750528
},
{
"epoch": 0.02,
"learning_rate": 2.133285135973553e-05,
"loss": 3.4384,
"step": 1751040
},
{
"epoch": 0.02,
"learning_rate": 2.132446541222501e-05,
"loss": 3.4499,
"step": 1751552
},
{
"epoch": 0.02,
"learning_rate": 2.1316095843518222e-05,
"loss": 3.4447,
"step": 1752064
},
{
"epoch": 0.02,
"learning_rate": 2.1307709896007698e-05,
"loss": 3.4468,
"step": 1752576
},
{
"epoch": 0.02,
"learning_rate": 2.1299323948497178e-05,
"loss": 3.4408,
"step": 1753088
},
{
"epoch": 0.02,
"learning_rate": 2.129093800098666e-05,
"loss": 3.4485,
"step": 1753600
},
{
"epoch": 0.02,
"learning_rate": 2.128256843227987e-05,
"loss": 3.4499,
"step": 1754112
},
{
"epoch": 0.02,
"learning_rate": 2.127418248476935e-05,
"loss": 3.4379,
"step": 1754624
},
{
"epoch": 0.02,
"learning_rate": 2.126579653725883e-05,
"loss": 3.449,
"step": 1755136
},
{
"epoch": 0.03,
"eval_loss": 3.8611629009246826,
"eval_runtime": 304.5277,
"eval_samples_per_second": 1253.059,
"eval_steps_per_second": 39.159,
"step": 1755360
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.2132370277868073e+18,
"trial_name": null,
"trial_params": null
}