abhinavp's picture
Training in progress, epoch 0, checkpoint
68e3185 verified
{
"best_metric": 3.870181083679199,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-case/transformer/1/checkpoints/checkpoint-457920",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 457920,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.8546,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8152,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1962,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9782,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8176,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.7102,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.6077,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5352,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4531,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.4052,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3446,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3026,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2566,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2091,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1715,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.1284,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1004,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0707,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0435,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0123,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 4.9999,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 4.9718,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9432,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9305,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9198,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 4.8831,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8646,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8512,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.837,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 4.8149,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7976,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.795,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.779,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7723,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7578,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7399,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7336,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.6992,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7062,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6791,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6786,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 4.6663,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 4.669,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 4.6467,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 4.6443,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 4.6357,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 4.6189,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 4.6294,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 4.5942,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.586,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 4.5986,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 4.5931,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 4.5698,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 4.5621,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 4.5636,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 4.5446,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.5664,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5268,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5372,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.5277,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 4.5117,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 4.5193,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5016,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4985,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4896,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 4.5032,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 4.4757,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.4807,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4591,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 4.467,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 4.4785,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4677,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4509,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 4.4635,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 4.465,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4384,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 4.4448,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 4.4272,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4182,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4163,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.416,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4229,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.4289,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930422841748654e-05,
"loss": 4.4166,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 4.3931,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.4001,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.4018,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927070100624819e-05,
"loss": 4.3927,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926231505873767e-05,
"loss": 4.3842,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925394549003088e-05,
"loss": 4.3814,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924555954252036e-05,
"loss": 4.3753,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923717359500984e-05,
"loss": 4.383,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.9228804026303046e-05,
"loss": 4.3712,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922041807879253e-05,
"loss": 4.3769,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921203213128201e-05,
"loss": 4.3674,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920364618377149e-05,
"loss": 4.3648,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919526023626097e-05,
"loss": 4.3516,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918687428875045e-05,
"loss": 4.3519,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917848834123993e-05,
"loss": 4.3505,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917010239372941e-05,
"loss": 4.3549,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916171644621889e-05,
"loss": 4.3532,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.3338,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3418,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3331,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3355,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3227,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911143351876323e-05,
"loss": 4.3201,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910304757125272e-05,
"loss": 4.327,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.3172,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.314,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.307,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3036,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.9061134212503846e-05,
"loss": 4.3163,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052748264993326e-05,
"loss": 4.3036,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.90443623174828e-05,
"loss": 4.3029,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903597636997228e-05,
"loss": 4.307,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027606801265495e-05,
"loss": 4.313,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019220853754975e-05,
"loss": 4.2977,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010834906244455e-05,
"loss": 4.2856,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002448958733935e-05,
"loss": 4.2913,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.2988,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985693442516624e-05,
"loss": 4.2832,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977307495006104e-05,
"loss": 4.2806,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968921547495584e-05,
"loss": 4.2808,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960535599985064e-05,
"loss": 4.2822,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952149652474544e-05,
"loss": 4.2753,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943763704964024e-05,
"loss": 4.2792,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.2714,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.2714,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.2639,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.282,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2663,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2584,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2544,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.264,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.2577,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885995336627002e-05,
"loss": 4.2639,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515674187595e-05,
"loss": 4.2487,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.2566,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.2496,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.2508,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.2409,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.2506,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.237,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879289854379332e-05,
"loss": 4.2273,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87845125962828e-05,
"loss": 4.2476,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877612664877228e-05,
"loss": 4.2333,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876774070126176e-05,
"loss": 4.2325,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875935475375124e-05,
"loss": 4.2383,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875096880624072e-05,
"loss": 4.2219,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.19382905960083,
"eval_runtime": 350.9337,
"eval_samples_per_second": 1087.359,
"eval_steps_per_second": 33.981,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.2137,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.2158,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872582734251289e-05,
"loss": 4.2212,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.2153,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.2214,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870068587878506e-05,
"loss": 4.2092,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869229993127454e-05,
"loss": 4.2096,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683913983764027e-05,
"loss": 4.2015,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.2152,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.1981,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658772520036196e-05,
"loss": 4.1967,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.8650386572525676e-05,
"loss": 4.1991,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642017003818885e-05,
"loss": 4.1946,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633631056308365e-05,
"loss": 4.1878,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625245108797845e-05,
"loss": 4.1881,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616859161287324e-05,
"loss": 4.1725,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608473213776804e-05,
"loss": 4.1837,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860008726626628e-05,
"loss": 4.1761,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591701318755764e-05,
"loss": 4.1701,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583315371245244e-05,
"loss": 4.1965,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857494580253846e-05,
"loss": 4.1733,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856655985502793e-05,
"loss": 4.1776,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855817390751741e-05,
"loss": 4.1751,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854978796000689e-05,
"loss": 4.1891,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854141839130011e-05,
"loss": 4.1604,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853303244378958e-05,
"loss": 4.1647,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852464649627906e-05,
"loss": 4.1694,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851626054876854e-05,
"loss": 4.1674,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850789098006175e-05,
"loss": 4.1577,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849950503255123e-05,
"loss": 4.1559,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849111908504072e-05,
"loss": 4.1627,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.84827331375302e-05,
"loss": 4.1628,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847434719001968e-05,
"loss": 4.1662,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846597762131289e-05,
"loss": 4.1563,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845759167380237e-05,
"loss": 4.1519,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844920572629185e-05,
"loss": 4.1597,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844081977878133e-05,
"loss": 4.1329,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.8432450210074536e-05,
"loss": 4.1532,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.8424064262564016e-05,
"loss": 4.1302,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.8415678315053496e-05,
"loss": 4.1429,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.8407292367542976e-05,
"loss": 4.1369,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398922798836185e-05,
"loss": 4.1466,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839053685132567e-05,
"loss": 4.1406,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838215090381515e-05,
"loss": 4.1317,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837376495630463e-05,
"loss": 4.141,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836539538759784e-05,
"loss": 4.1318,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835700944008732e-05,
"loss": 4.142,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.83486234925768e-05,
"loss": 4.117,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834025392387001e-05,
"loss": 4.1176,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833186797635949e-05,
"loss": 4.1338,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832348202884897e-05,
"loss": 4.1343,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831509608133845e-05,
"loss": 4.1175,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830671013382793e-05,
"loss": 4.1149,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829832418631741e-05,
"loss": 4.1232,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828993823880689e-05,
"loss": 4.1059,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828155229129637e-05,
"loss": 4.1311,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273182722589585e-05,
"loss": 4.1108,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264796775079065e-05,
"loss": 4.1188,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256410827568545e-05,
"loss": 4.1123,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8248024880058025e-05,
"loss": 4.1021,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239655311351234e-05,
"loss": 4.116,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231269363840714e-05,
"loss": 4.1023,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222883416330194e-05,
"loss": 4.101,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214497468819674e-05,
"loss": 4.0972,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820612790011288e-05,
"loss": 4.1172,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819774195260236e-05,
"loss": 4.0964,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818935600509184e-05,
"loss": 4.0988,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818097005758132e-05,
"loss": 4.0884,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817260048887454e-05,
"loss": 4.0962,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816421454136402e-05,
"loss": 4.1103,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.81558285938535e-05,
"loss": 4.1056,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814744264634298e-05,
"loss": 4.0938,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.813907307763619e-05,
"loss": 4.1045,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813068713012567e-05,
"loss": 4.1081,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812230118261515e-05,
"loss": 4.0936,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811391523510463e-05,
"loss": 4.0982,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810554566639784e-05,
"loss": 4.0889,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809715971888732e-05,
"loss": 4.0787,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887737713768e-05,
"loss": 4.0819,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808038782386628e-05,
"loss": 4.0854,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807201825515949e-05,
"loss": 4.09,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806363230764897e-05,
"loss": 4.1036,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805524636013845e-05,
"loss": 4.0916,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804686041262793e-05,
"loss": 4.0693,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803849084392114e-05,
"loss": 4.0814,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803010489641062e-05,
"loss": 4.0845,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.80217189489001e-05,
"loss": 4.0808,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801333300138958e-05,
"loss": 4.0733,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800496343268279e-05,
"loss": 4.0742,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799657748517227e-05,
"loss": 4.0728,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798819153766175e-05,
"loss": 4.0756,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797980559015123e-05,
"loss": 4.07,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797141964264071e-05,
"loss": 4.0765,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796303369513019e-05,
"loss": 4.0719,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954664126423406e-05,
"loss": 4.0758,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946278178912886e-05,
"loss": 4.0591,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793789223140236e-05,
"loss": 4.0698,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792950628389184e-05,
"loss": 4.0661,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792112033638132e-05,
"loss": 4.0693,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.79127343888708e-05,
"loss": 4.0709,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790434844136028e-05,
"loss": 4.0593,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789597887265349e-05,
"loss": 4.0607,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788759292514297e-05,
"loss": 4.0603,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787920697763245e-05,
"loss": 4.0641,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870821030121935e-05,
"loss": 4.0493,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862451461415144e-05,
"loss": 4.0517,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7854065513904624e-05,
"loss": 4.0618,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845679566394104e-05,
"loss": 4.0504,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783730999768731e-05,
"loss": 4.0511,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782892405017679e-05,
"loss": 4.0465,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782053810266627e-05,
"loss": 4.0417,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781215215515575e-05,
"loss": 4.0648,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780376620764523e-05,
"loss": 4.045,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779538026013471e-05,
"loss": 4.0533,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778699431262419e-05,
"loss": 4.0499,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777860836511367e-05,
"loss": 4.0656,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777023879640689e-05,
"loss": 4.051,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776185284889637e-05,
"loss": 4.0368,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775346690138585e-05,
"loss": 4.0452,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774508095387533e-05,
"loss": 4.052,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773671138516854e-05,
"loss": 4.036,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728341816461747e-05,
"loss": 4.0426,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719955868951227e-05,
"loss": 4.0367,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711569921440707e-05,
"loss": 4.0478,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703183973930186e-05,
"loss": 4.036,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694798026419666e-05,
"loss": 4.0447,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686412078909146e-05,
"loss": 4.0387,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.7678026131398626e-05,
"loss": 4.0405,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766965656269184e-05,
"loss": 4.0317,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766127061518132e-05,
"loss": 4.0538,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.76528846676708e-05,
"loss": 4.0419,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764449872016028e-05,
"loss": 4.0269,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763612915145349e-05,
"loss": 4.0294,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762774320394297e-05,
"loss": 4.0358,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761935725643245e-05,
"loss": 4.037,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761097130892193e-05,
"loss": 4.0468,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760260174021514e-05,
"loss": 4.0271,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759421579270462e-05,
"loss": 4.0368,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.75858298451941e-05,
"loss": 4.0306,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757744389768358e-05,
"loss": 4.0367,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569074328976796e-05,
"loss": 4.0284,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560688381466276e-05,
"loss": 4.0341,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552302433955756e-05,
"loss": 4.0237,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543916486445236e-05,
"loss": 4.0192,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535546917738445e-05,
"loss": 4.0375,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527160970227925e-05,
"loss": 4.0256,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518775022717405e-05,
"loss": 4.0242,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510389075206885e-05,
"loss": 4.027,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7502003127696365e-05,
"loss": 4.0179,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.026176452636719,
"eval_runtime": 347.0521,
"eval_samples_per_second": 1099.521,
"eval_steps_per_second": 34.361,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493617180185845e-05,
"loss": 4.0104,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748523123267532e-05,
"loss": 4.0104,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.74768452851648e-05,
"loss": 4.0234,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746845933765428e-05,
"loss": 4.0124,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460073390143764e-05,
"loss": 4.027,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451687442633244e-05,
"loss": 4.0102,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443301495122724e-05,
"loss": 4.0131,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434915547612204e-05,
"loss": 4.0062,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426529600101684e-05,
"loss": 4.023,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418143652591164e-05,
"loss": 4.0077,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409757705080644e-05,
"loss": 4.005,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740138813637385e-05,
"loss": 4.0056,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739303494647079e-05,
"loss": 4.0061,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738464899896027e-05,
"loss": 3.9997,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.737626305144975e-05,
"loss": 4.0025,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736787710393923e-05,
"loss": 3.9911,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735949115642871e-05,
"loss": 3.9964,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.73511052089182e-05,
"loss": 3.9906,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734271926140768e-05,
"loss": 3.9877,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733433331389716e-05,
"loss": 4.0202,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732594736638664e-05,
"loss": 3.9942,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731756141887612e-05,
"loss": 3.9924,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73091754713656e-05,
"loss": 4.0001,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730080590265881e-05,
"loss": 4.0074,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292436333952016e-05,
"loss": 3.9851,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7284050386441496e-05,
"loss": 3.9918,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275664438930976e-05,
"loss": 3.9908,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267278491420456e-05,
"loss": 3.9955,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258892543909936e-05,
"loss": 3.981,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250506596399416e-05,
"loss": 3.9856,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7242120648888896e-05,
"loss": 3.9876,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723373470137838e-05,
"loss": 3.994,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722536513267159e-05,
"loss": 4.0011,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721697918516107e-05,
"loss": 3.9884,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720859323765055e-05,
"loss": 3.9814,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720020729014003e-05,
"loss": 3.9918,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719183772143324e-05,
"loss": 3.9722,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718345177392272e-05,
"loss": 3.9857,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.71750658264122e-05,
"loss": 3.9676,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716669625770541e-05,
"loss": 3.9759,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715831031019489e-05,
"loss": 3.9779,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714992436268437e-05,
"loss": 3.9877,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714153841517385e-05,
"loss": 3.9805,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713315246766333e-05,
"loss": 3.9737,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712476652015281e-05,
"loss": 3.9787,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711638057264229e-05,
"loss": 3.9753,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710799462513177e-05,
"loss": 3.9828,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709962505642498e-05,
"loss": 3.962,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091255487718194e-05,
"loss": 3.9604,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082869540207674e-05,
"loss": 3.9801,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074483592697154e-05,
"loss": 3.9756,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706609764518663e-05,
"loss": 3.9642,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705772807647984e-05,
"loss": 3.9645,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704934212896932e-05,
"loss": 3.9684,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.70409561814588e-05,
"loss": 3.9535,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703257023394828e-05,
"loss": 3.9767,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702418428643776e-05,
"loss": 3.963,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701579833892724e-05,
"loss": 3.9681,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700741239141672e-05,
"loss": 3.9616,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.69990264439062e-05,
"loss": 3.9598,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699065687519941e-05,
"loss": 3.9616,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698227092768889e-05,
"loss": 3.9593,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697388498017837e-05,
"loss": 3.9532,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696549903266785e-05,
"loss": 3.9515,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695712946396106e-05,
"loss": 3.9704,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694874351645054e-05,
"loss": 3.9534,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694035756894003e-05,
"loss": 3.9543,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693197162142951e-05,
"loss": 3.9463,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692358567391899e-05,
"loss": 3.9538,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691519972640847e-05,
"loss": 3.9699,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906830157701677e-05,
"loss": 3.9646,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898444210191157e-05,
"loss": 3.9563,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6890058262680636e-05,
"loss": 3.9637,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881672315170116e-05,
"loss": 3.9676,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873286367659596e-05,
"loss": 3.951,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864900420149076e-05,
"loss": 3.9603,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856514472638556e-05,
"loss": 3.9525,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6848144903931765e-05,
"loss": 3.9434,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683977533522498e-05,
"loss": 3.9507,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683138938771446e-05,
"loss": 3.9461,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682300344020394e-05,
"loss": 3.9553,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681461749269342e-05,
"loss": 3.9636,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680624792398663e-05,
"loss": 3.9592,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679786197647611e-05,
"loss": 3.9332,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678947602896559e-05,
"loss": 3.9493,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678109008145507e-05,
"loss": 3.9493,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677270413394455e-05,
"loss": 3.9496,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676431818643403e-05,
"loss": 3.9436,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675593223892351e-05,
"loss": 3.9373,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674756267021672e-05,
"loss": 3.9492,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.67391767227062e-05,
"loss": 3.9407,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673079077519568e-05,
"loss": 3.9401,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672240482768516e-05,
"loss": 3.9466,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671401888017464e-05,
"loss": 3.9419,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705649311467855e-05,
"loss": 3.9496,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697263363957335e-05,
"loss": 3.9349,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688877416446815e-05,
"loss": 3.9382,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668049146893629e-05,
"loss": 3.9386,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667210552142577e-05,
"loss": 3.9465,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663735952718984e-05,
"loss": 3.9444,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665535000520846e-05,
"loss": 3.9345,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664696405769794e-05,
"loss": 3.9358,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663857811018742e-05,
"loss": 3.9356,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663020854148063e-05,
"loss": 3.9395,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662182259397011e-05,
"loss": 3.9231,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661343664645959e-05,
"loss": 3.9274,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660505069894907e-05,
"loss": 3.943,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659666475143855e-05,
"loss": 3.9329,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658829518273176e-05,
"loss": 3.9269,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657990923522124e-05,
"loss": 3.9252,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657152328771072e-05,
"loss": 3.9241,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.65631373402002e-05,
"loss": 3.9406,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655475139268968e-05,
"loss": 3.9297,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654636544517916e-05,
"loss": 3.9292,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653799587647237e-05,
"loss": 3.9327,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652960992896185e-05,
"loss": 3.9469,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652122398145134e-05,
"loss": 3.9334,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651283803394082e-05,
"loss": 3.9207,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.65044520864303e-05,
"loss": 3.9294,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649606613891978e-05,
"loss": 3.9308,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487696570212986e-05,
"loss": 3.9212,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479310622702466e-05,
"loss": 3.9237,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470924675191946e-05,
"loss": 3.92,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462538727681426e-05,
"loss": 3.9329,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6454152780170906e-05,
"loss": 3.9175,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445783211464115e-05,
"loss": 3.9331,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437397263953595e-05,
"loss": 3.916,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6429011316443075e-05,
"loss": 3.9277,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420625368932555e-05,
"loss": 3.9156,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641225580022577e-05,
"loss": 3.9374,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640386985271525e-05,
"loss": 3.9298,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639548390520473e-05,
"loss": 3.9207,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638709795769421e-05,
"loss": 3.912,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637871201018369e-05,
"loss": 3.9251,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.63703424414769e-05,
"loss": 3.9218,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636195649396638e-05,
"loss": 3.9344,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635357054645586e-05,
"loss": 3.9146,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634518459894534e-05,
"loss": 3.9282,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633679865143482e-05,
"loss": 3.9202,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632841270392429e-05,
"loss": 3.9311,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.632002675641377e-05,
"loss": 3.9145,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631165718770699e-05,
"loss": 3.923,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303287619000204e-05,
"loss": 3.9164,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294901671489684e-05,
"loss": 3.9095,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286515723979164e-05,
"loss": 3.9293,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6278129776468644e-05,
"loss": 3.9225,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626974382895812e-05,
"loss": 3.9099,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626137426025133e-05,
"loss": 3.9197,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625298831274081e-05,
"loss": 3.9092,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.952585220336914,
"eval_runtime": 319.2814,
"eval_samples_per_second": 1195.156,
"eval_steps_per_second": 37.349,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624460236523029e-05,
"loss": 3.9082,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.6236216417719766e-05,
"loss": 3.903,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.6227830470209246e-05,
"loss": 3.9131,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219444522698726e-05,
"loss": 3.9114,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621105857518821e-05,
"loss": 3.9246,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620267262767769e-05,
"loss": 3.9005,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.61943030589709e-05,
"loss": 3.9095,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618591711146038e-05,
"loss": 3.9012,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617753116394986e-05,
"loss": 3.923,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616914521643934e-05,
"loss": 3.9022,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616079202653629e-05,
"loss": 3.9002,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615240607902577e-05,
"loss": 3.9074,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6144036510318976e-05,
"loss": 3.9008,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135650562808456e-05,
"loss": 3.8988,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.6127264615297936e-05,
"loss": 3.9002,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.6118878667787416e-05,
"loss": 3.8925,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.6110492720276896e-05,
"loss": 3.8921,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.6102106772766376e-05,
"loss": 3.8927,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.6093720825255856e-05,
"loss": 3.8879,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.6085334877745336e-05,
"loss": 3.9184,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076965309038545e-05,
"loss": 3.8942,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068579361528025e-05,
"loss": 3.8944,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6060193414017505e-05,
"loss": 3.8998,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051807466506985e-05,
"loss": 3.9041,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.6043437897800194e-05,
"loss": 3.8899,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.6035051950289674e-05,
"loss": 3.8953,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.6026666002779154e-05,
"loss": 3.8925,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018280055268634e-05,
"loss": 3.8957,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009894107758114e-05,
"loss": 3.886,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.60015081602476e-05,
"loss": 3.8898,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599312221273708e-05,
"loss": 3.8951,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598473626522656e-05,
"loss": 3.8967,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597636669651977e-05,
"loss": 3.9039,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596799712781298e-05,
"loss": 3.8954,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595961118030246e-05,
"loss": 3.8856,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595122523279194e-05,
"loss": 3.8959,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594283928528142e-05,
"loss": 3.8813,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.59344533377709e-05,
"loss": 3.8885,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592608376906411e-05,
"loss": 3.8748,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591769782155359e-05,
"loss": 3.8819,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590931187404307e-05,
"loss": 3.8797,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900925926532554e-05,
"loss": 3.897,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.5892539979022034e-05,
"loss": 3.8908,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5884154031511514e-05,
"loss": 3.878,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587578446280472e-05,
"loss": 3.8844,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.58673985152942e-05,
"loss": 3.8832,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585901256778368e-05,
"loss": 3.8902,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585062662027316e-05,
"loss": 3.8735,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584224067276264e-05,
"loss": 3.8655,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583387110405585e-05,
"loss": 3.889,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582548515654533e-05,
"loss": 3.8846,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581709920903481e-05,
"loss": 3.8695,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580871326152429e-05,
"loss": 3.8781,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580034369281751e-05,
"loss": 3.8814,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579195774530699e-05,
"loss": 3.8639,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578357179779647e-05,
"loss": 3.8826,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577518585028595e-05,
"loss": 3.8729,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576681628157916e-05,
"loss": 3.8838,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758430334068637e-05,
"loss": 3.8681,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5750044386558117e-05,
"loss": 3.8788,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741658439047596e-05,
"loss": 3.8695,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733288870340806e-05,
"loss": 3.8721,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724902922830286e-05,
"loss": 3.8626,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716516975319765e-05,
"loss": 3.8647,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5708131027809245e-05,
"loss": 3.8866,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.5699745080298725e-05,
"loss": 3.8644,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569137551159194e-05,
"loss": 3.8687,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568298956408142e-05,
"loss": 3.8587,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.56746036165709e-05,
"loss": 3.8677,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.5666217669060374e-05,
"loss": 3.8824,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.5657831721549854e-05,
"loss": 3.8768,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564946215284307e-05,
"loss": 3.8726,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564107620533255e-05,
"loss": 3.8804,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563269025782202e-05,
"loss": 3.8777,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.56243043103115e-05,
"loss": 3.8689,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561593474160472e-05,
"loss": 3.8739,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.56075487940942e-05,
"loss": 3.8692,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559916284658368e-05,
"loss": 3.863,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559077689907316e-05,
"loss": 3.8648,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558239095156264e-05,
"loss": 3.8651,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557402138285585e-05,
"loss": 3.8692,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556563543534533e-05,
"loss": 3.8781,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555724948783481e-05,
"loss": 3.8752,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554886354032429e-05,
"loss": 3.8493,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554047759281377e-05,
"loss": 3.8706,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553210802410698e-05,
"loss": 3.8654,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552372207659646e-05,
"loss": 3.8668,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551533612908594e-05,
"loss": 3.8619,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550695018157542e-05,
"loss": 3.8545,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.54985642340649e-05,
"loss": 3.867,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.549019466535811e-05,
"loss": 3.8575,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548180871784759e-05,
"loss": 3.8597,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547342277033707e-05,
"loss": 3.8618,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546503682282655e-05,
"loss": 3.8607,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545666725411976e-05,
"loss": 3.87,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544828130660924e-05,
"loss": 3.8558,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543989535909872e-05,
"loss": 3.8543,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.54315094115882e-05,
"loss": 3.8575,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542312346407768e-05,
"loss": 3.8707,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541475389537089e-05,
"loss": 3.8618,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540636794786037e-05,
"loss": 3.8555,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539798200034985e-05,
"loss": 3.8544,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538959605283933e-05,
"loss": 3.8577,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5381226484132546e-05,
"loss": 3.8662,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372840536622026e-05,
"loss": 3.8483,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364454589111506e-05,
"loss": 3.8445,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5356068641600986e-05,
"loss": 3.8625,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347699072894195e-05,
"loss": 3.852,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339329504187404e-05,
"loss": 3.8476,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330943556676884e-05,
"loss": 3.8466,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322557609166364e-05,
"loss": 3.8492,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5314171661655844e-05,
"loss": 3.8634,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.5305785714145324e-05,
"loss": 3.8473,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297399766634804e-05,
"loss": 3.8529,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.5289013819124284e-05,
"loss": 3.8572,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528062787161377e-05,
"loss": 3.8674,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527225830290698e-05,
"loss": 3.8615,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526387235539646e-05,
"loss": 3.8418,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525548640788594e-05,
"loss": 3.8549,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524710046037542e-05,
"loss": 3.8508,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523873089166863e-05,
"loss": 3.8482,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523034494415811e-05,
"loss": 3.8481,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522195899664759e-05,
"loss": 3.8414,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521357304913707e-05,
"loss": 3.8543,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520518710162655e-05,
"loss": 3.8439,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519681753291976e-05,
"loss": 3.8536,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518843158540924e-05,
"loss": 3.8439,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5180045637898725e-05,
"loss": 3.8504,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171659690388204e-05,
"loss": 3.8401,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163290121681414e-05,
"loss": 3.8669,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.5154904174170894e-05,
"loss": 3.8504,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146518226660373e-05,
"loss": 3.8484,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5138132279149853e-05,
"loss": 3.8381,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512976271044306e-05,
"loss": 3.8523,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512137676293254e-05,
"loss": 3.8466,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511299081542202e-05,
"loss": 3.8575,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.51046048679115e-05,
"loss": 3.8423,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509623529920471e-05,
"loss": 3.8539,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508784935169419e-05,
"loss": 3.8486,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507946340418368e-05,
"loss": 3.861,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507107745667316e-05,
"loss": 3.837,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506270788796637e-05,
"loss": 3.8514,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505432194045585e-05,
"loss": 3.8441,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504593599294533e-05,
"loss": 3.8411,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.50375500454348e-05,
"loss": 3.8516,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502916409792428e-05,
"loss": 3.8499,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020794529217496e-05,
"loss": 3.8407,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012408581706976e-05,
"loss": 3.8441,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500402263419645e-05,
"loss": 3.8414,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 3.912287473678589,
"eval_runtime": 322.0035,
"eval_samples_per_second": 1185.052,
"eval_steps_per_second": 37.034,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499563668668593e-05,
"loss": 3.836,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987250739175416e-05,
"loss": 3.8294,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978864791664896e-05,
"loss": 3.8424,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970478844154376e-05,
"loss": 3.8418,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4962092896643856e-05,
"loss": 3.8532,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953706949133336e-05,
"loss": 3.8349,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945321001622816e-05,
"loss": 3.8351,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936935054112296e-05,
"loss": 3.8326,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928565485405505e-05,
"loss": 3.8495,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4920179537894985e-05,
"loss": 3.8365,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911793590384465e-05,
"loss": 3.8285,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903407642873945e-05,
"loss": 3.8341,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489505445297088e-05,
"loss": 3.8298,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488666850546037e-05,
"loss": 3.8321,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487828255794985e-05,
"loss": 3.8357,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486989661043933e-05,
"loss": 3.8196,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486151066292881e-05,
"loss": 3.8254,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485312471541829e-05,
"loss": 3.8233,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484473876790777e-05,
"loss": 3.8188,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483635282039725e-05,
"loss": 3.8465,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482796687288673e-05,
"loss": 3.8298,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481958092537621e-05,
"loss": 3.8263,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481119497786569e-05,
"loss": 3.8303,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480280903035516e-05,
"loss": 3.8385,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479443946164838e-05,
"loss": 3.8209,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478605351413786e-05,
"loss": 3.8282,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477766756662734e-05,
"loss": 3.8235,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476928161911682e-05,
"loss": 3.8242,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.47608956716063e-05,
"loss": 3.8189,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.4752526102899514e-05,
"loss": 3.8254,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.4744140155388994e-05,
"loss": 3.8271,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473575420787847e-05,
"loss": 3.8286,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472736826036795e-05,
"loss": 3.8372,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471898231285743e-05,
"loss": 3.8307,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710612744150636e-05,
"loss": 3.8178,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.4702226796640116e-05,
"loss": 3.8287,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693840849129596e-05,
"loss": 3.8214,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.4685454901619076e-05,
"loss": 3.8206,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4677068954108556e-05,
"loss": 3.8107,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466869938540177e-05,
"loss": 3.8167,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466031343789125e-05,
"loss": 3.8176,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465192749038073e-05,
"loss": 3.8294,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464354154287021e-05,
"loss": 3.8245,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463515559535969e-05,
"loss": 3.8155,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.46267860266529e-05,
"loss": 3.8191,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461840007914238e-05,
"loss": 3.8203,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.461001413163186e-05,
"loss": 3.8252,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460162818412134e-05,
"loss": 3.8095,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459325861541455e-05,
"loss": 3.7997,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.458487266790403e-05,
"loss": 3.8235,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457648672039351e-05,
"loss": 3.8201,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456810077288299e-05,
"loss": 3.8043,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559731204176205e-05,
"loss": 3.8137,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551345256665685e-05,
"loss": 3.8195,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542959309155165e-05,
"loss": 3.7994,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534573361644645e-05,
"loss": 3.8189,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4526187414134125e-05,
"loss": 3.8104,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.4517817845427334e-05,
"loss": 3.8177,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.4509431897916814e-05,
"loss": 3.8069,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.4501045950406294e-05,
"loss": 3.815,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.4492660002895774e-05,
"loss": 3.8078,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448429043418898e-05,
"loss": 3.814,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447590448667846e-05,
"loss": 3.7984,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446751853916794e-05,
"loss": 3.8057,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445913259165742e-05,
"loss": 3.8203,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445076302295064e-05,
"loss": 3.8052,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444237707544012e-05,
"loss": 3.8047,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.44339911279296e-05,
"loss": 3.798,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442560518041908e-05,
"loss": 3.8038,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441721923290856e-05,
"loss": 3.8156,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440884966420177e-05,
"loss": 3.8171,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440046371669125e-05,
"loss": 3.8135,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439207776918073e-05,
"loss": 3.8193,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438369182167021e-05,
"loss": 3.8191,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437532225296342e-05,
"loss": 3.8065,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.43669363054529e-05,
"loss": 3.8122,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435855035794238e-05,
"loss": 3.812,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.4350164410431864e-05,
"loss": 3.8003,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434179484172507e-05,
"loss": 3.8034,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433340889421455e-05,
"loss": 3.8053,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432502294670403e-05,
"loss": 3.8066,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431663699919351e-05,
"loss": 3.8207,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430825105168299e-05,
"loss": 3.8128,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.42998814829762e-05,
"loss": 3.7913,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429149553546568e-05,
"loss": 3.8062,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428310958795516e-05,
"loss": 3.8088,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427472364044464e-05,
"loss": 3.808,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426633769293412e-05,
"loss": 3.8045,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425796812422733e-05,
"loss": 3.793,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424958217671682e-05,
"loss": 3.807,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.42411962292063e-05,
"loss": 3.7992,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423281028169577e-05,
"loss": 3.7999,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224440712988986e-05,
"loss": 3.8011,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4216054765478466e-05,
"loss": 3.8063,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207668817967946e-05,
"loss": 3.8073,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419928287045742e-05,
"loss": 3.8056,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190913301750635e-05,
"loss": 3.7896,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182527354240115e-05,
"loss": 3.8021,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4174141406729595e-05,
"loss": 3.8056,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416575545921907e-05,
"loss": 3.808,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157369511708555e-05,
"loss": 3.7948,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414899994300177e-05,
"loss": 3.797,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.4140613995491244e-05,
"loss": 3.7994,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4132228047980724e-05,
"loss": 3.806,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123842100470204e-05,
"loss": 3.7928,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411547253176342e-05,
"loss": 3.7915,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410708658425289e-05,
"loss": 3.7994,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409870063674237e-05,
"loss": 3.7954,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409033106803559e-05,
"loss": 3.7897,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408194512052507e-05,
"loss": 3.7919,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407355917301454e-05,
"loss": 3.7908,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406517322550402e-05,
"loss": 3.8044,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405678727799351e-05,
"loss": 3.7921,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404840133048299e-05,
"loss": 3.7929,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.404001538297247e-05,
"loss": 3.7998,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403162943546195e-05,
"loss": 3.8123,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402325986675516e-05,
"loss": 3.8048,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401487391924464e-05,
"loss": 3.7868,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400648797173412e-05,
"loss": 3.7945,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.39981020242236e-05,
"loss": 3.7955,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398973245551681e-05,
"loss": 3.7915,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.3981346508006287e-05,
"loss": 3.793,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.3972960560495767e-05,
"loss": 3.785,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.3964574612985247e-05,
"loss": 3.7955,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.3956205044278456e-05,
"loss": 3.7929,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394781909676794e-05,
"loss": 3.7987,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393943314925742e-05,
"loss": 3.786,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.39310472017469e-05,
"loss": 3.791,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392267763304011e-05,
"loss": 3.7913,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391429168552959e-05,
"loss": 3.8042,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390590573801907e-05,
"loss": 3.791,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389751979050855e-05,
"loss": 3.7978,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388915022180176e-05,
"loss": 3.7833,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388076427429124e-05,
"loss": 3.8009,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387237832678072e-05,
"loss": 3.7938,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.38639923792702e-05,
"loss": 3.7997,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385560643175968e-05,
"loss": 3.785,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3847236863052896e-05,
"loss": 3.8022,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.3838850915542376e-05,
"loss": 3.7886,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830464968031856e-05,
"loss": 3.8064,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3822079020521336e-05,
"loss": 3.7858,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813709451814545e-05,
"loss": 3.797,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3805323504304025e-05,
"loss": 3.7894,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796937556793505e-05,
"loss": 3.7831,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788551609282985e-05,
"loss": 3.7991,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3780182040576194e-05,
"loss": 3.7962,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771796093065674e-05,
"loss": 3.7882,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763410145555154e-05,
"loss": 3.7862,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3755024198044634e-05,
"loss": 3.7919,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 3.88671612739563,
"eval_runtime": 304.1142,
"eval_samples_per_second": 1254.762,
"eval_steps_per_second": 39.212,
"step": 381600
},
{
"epoch": 0.0,
"learning_rate": 4.374665462933785e-05,
"loss": 3.7814,
"step": 381952
},
{
"epoch": 0.0,
"learning_rate": 4.373826868182733e-05,
"loss": 3.7771,
"step": 382464
},
{
"epoch": 0.0,
"learning_rate": 4.372988273431681e-05,
"loss": 3.7889,
"step": 382976
},
{
"epoch": 0.0,
"learning_rate": 4.372149678680629e-05,
"loss": 3.787,
"step": 383488
},
{
"epoch": 0.0,
"learning_rate": 4.371311083929577e-05,
"loss": 3.7979,
"step": 384000
},
{
"epoch": 0.0,
"learning_rate": 4.370472489178525e-05,
"loss": 3.7821,
"step": 384512
},
{
"epoch": 0.0,
"learning_rate": 4.369633894427473e-05,
"loss": 3.78,
"step": 385024
},
{
"epoch": 0.0,
"learning_rate": 4.36879529967642e-05,
"loss": 3.7793,
"step": 385536
},
{
"epoch": 0.0,
"learning_rate": 4.367958342805742e-05,
"loss": 3.7965,
"step": 386048
},
{
"epoch": 0.0,
"learning_rate": 4.36711974805469e-05,
"loss": 3.7805,
"step": 386560
},
{
"epoch": 0.0,
"learning_rate": 4.366281153303637e-05,
"loss": 3.7794,
"step": 387072
},
{
"epoch": 0.0,
"learning_rate": 4.365442558552585e-05,
"loss": 3.7792,
"step": 387584
},
{
"epoch": 0.0,
"learning_rate": 4.36460723956228e-05,
"loss": 3.7806,
"step": 388096
},
{
"epoch": 0.0,
"learning_rate": 4.363768644811228e-05,
"loss": 3.7788,
"step": 388608
},
{
"epoch": 0.0,
"learning_rate": 4.362930050060176e-05,
"loss": 3.7819,
"step": 389120
},
{
"epoch": 0.0,
"learning_rate": 4.362091455309124e-05,
"loss": 3.7689,
"step": 389632
},
{
"epoch": 0.0,
"learning_rate": 4.361252860558072e-05,
"loss": 3.7696,
"step": 390144
},
{
"epoch": 0.0,
"learning_rate": 4.36041426580702e-05,
"loss": 3.7755,
"step": 390656
},
{
"epoch": 0.0,
"learning_rate": 4.3595756710559676e-05,
"loss": 3.7658,
"step": 391168
},
{
"epoch": 0.0,
"learning_rate": 4.3587370763049156e-05,
"loss": 3.793,
"step": 391680
},
{
"epoch": 0.0,
"learning_rate": 4.357900119434237e-05,
"loss": 3.7793,
"step": 392192
},
{
"epoch": 0.0,
"learning_rate": 4.3570615246831845e-05,
"loss": 3.7766,
"step": 392704
},
{
"epoch": 0.0,
"learning_rate": 4.3562229299321325e-05,
"loss": 3.7746,
"step": 393216
},
{
"epoch": 0.0,
"learning_rate": 4.3553843351810805e-05,
"loss": 3.7863,
"step": 393728
},
{
"epoch": 0.0,
"learning_rate": 4.354547378310402e-05,
"loss": 3.7706,
"step": 394240
},
{
"epoch": 0.0,
"learning_rate": 4.35370878355935e-05,
"loss": 3.7801,
"step": 394752
},
{
"epoch": 0.0,
"learning_rate": 4.352870188808298e-05,
"loss": 3.7696,
"step": 395264
},
{
"epoch": 0.0,
"learning_rate": 4.352031594057246e-05,
"loss": 3.7757,
"step": 395776
},
{
"epoch": 0.0,
"learning_rate": 4.351194637186568e-05,
"loss": 3.7702,
"step": 396288
},
{
"epoch": 0.0,
"learning_rate": 4.350356042435515e-05,
"loss": 3.7722,
"step": 396800
},
{
"epoch": 0.01,
"learning_rate": 4.349517447684463e-05,
"loss": 3.7766,
"step": 397312
},
{
"epoch": 0.01,
"learning_rate": 4.348678852933411e-05,
"loss": 3.7781,
"step": 397824
},
{
"epoch": 0.01,
"learning_rate": 4.347841896062732e-05,
"loss": 3.7846,
"step": 398336
},
{
"epoch": 0.01,
"learning_rate": 4.34700330131168e-05,
"loss": 3.7813,
"step": 398848
},
{
"epoch": 0.01,
"learning_rate": 4.346164706560628e-05,
"loss": 3.7671,
"step": 399360
},
{
"epoch": 0.01,
"learning_rate": 4.345326111809576e-05,
"loss": 3.7796,
"step": 399872
},
{
"epoch": 0.01,
"learning_rate": 4.3444891549388975e-05,
"loss": 3.7727,
"step": 400384
},
{
"epoch": 0.01,
"learning_rate": 4.3436505601878455e-05,
"loss": 3.7629,
"step": 400896
},
{
"epoch": 0.01,
"learning_rate": 4.3428119654367935e-05,
"loss": 3.7672,
"step": 401408
},
{
"epoch": 0.01,
"learning_rate": 4.3419733706857415e-05,
"loss": 3.7645,
"step": 401920
},
{
"epoch": 0.01,
"learning_rate": 4.3411364138150624e-05,
"loss": 3.7679,
"step": 402432
},
{
"epoch": 0.01,
"learning_rate": 4.3402978190640104e-05,
"loss": 3.7818,
"step": 402944
},
{
"epoch": 0.01,
"learning_rate": 4.3394592243129584e-05,
"loss": 3.7696,
"step": 403456
},
{
"epoch": 0.01,
"learning_rate": 4.3386206295619064e-05,
"loss": 3.7653,
"step": 403968
},
{
"epoch": 0.01,
"learning_rate": 4.337783672691227e-05,
"loss": 3.7741,
"step": 404480
},
{
"epoch": 0.01,
"learning_rate": 4.336945077940175e-05,
"loss": 3.7726,
"step": 404992
},
{
"epoch": 0.01,
"learning_rate": 4.336106483189123e-05,
"loss": 3.7696,
"step": 405504
},
{
"epoch": 0.01,
"learning_rate": 4.335267888438071e-05,
"loss": 3.7615,
"step": 406016
},
{
"epoch": 0.01,
"learning_rate": 4.334430931567393e-05,
"loss": 3.7496,
"step": 406528
},
{
"epoch": 0.01,
"learning_rate": 4.333592336816341e-05,
"loss": 3.777,
"step": 407040
},
{
"epoch": 0.01,
"learning_rate": 4.332753742065289e-05,
"loss": 3.7691,
"step": 407552
},
{
"epoch": 0.01,
"learning_rate": 4.331915147314237e-05,
"loss": 3.7622,
"step": 408064
},
{
"epoch": 0.01,
"learning_rate": 4.331078190443558e-05,
"loss": 3.7613,
"step": 408576
},
{
"epoch": 0.01,
"learning_rate": 4.330239595692506e-05,
"loss": 3.766,
"step": 409088
},
{
"epoch": 0.01,
"learning_rate": 4.329401000941454e-05,
"loss": 3.7507,
"step": 409600
},
{
"epoch": 0.01,
"learning_rate": 4.328562406190402e-05,
"loss": 3.7671,
"step": 410112
},
{
"epoch": 0.01,
"learning_rate": 4.3277254493197226e-05,
"loss": 3.7661,
"step": 410624
},
{
"epoch": 0.01,
"learning_rate": 4.3268868545686706e-05,
"loss": 3.7675,
"step": 411136
},
{
"epoch": 0.01,
"learning_rate": 4.3260482598176186e-05,
"loss": 3.7617,
"step": 411648
},
{
"epoch": 0.01,
"learning_rate": 4.3252096650665666e-05,
"loss": 3.7645,
"step": 412160
},
{
"epoch": 0.01,
"learning_rate": 4.324372708195888e-05,
"loss": 3.7564,
"step": 412672
},
{
"epoch": 0.01,
"learning_rate": 4.323534113444836e-05,
"loss": 3.7681,
"step": 413184
},
{
"epoch": 0.01,
"learning_rate": 4.322695518693784e-05,
"loss": 3.7518,
"step": 413696
},
{
"epoch": 0.01,
"learning_rate": 4.321856923942732e-05,
"loss": 3.757,
"step": 414208
},
{
"epoch": 0.01,
"learning_rate": 4.321019967072053e-05,
"loss": 3.7723,
"step": 414720
},
{
"epoch": 0.01,
"learning_rate": 4.320181372321001e-05,
"loss": 3.7597,
"step": 415232
},
{
"epoch": 0.01,
"learning_rate": 4.319342777569949e-05,
"loss": 3.7532,
"step": 415744
},
{
"epoch": 0.01,
"learning_rate": 4.318504182818897e-05,
"loss": 3.7552,
"step": 416256
},
{
"epoch": 0.01,
"learning_rate": 4.317665588067845e-05,
"loss": 3.7541,
"step": 416768
},
{
"epoch": 0.01,
"learning_rate": 4.316828631197166e-05,
"loss": 3.7665,
"step": 417280
},
{
"epoch": 0.01,
"learning_rate": 4.315990036446114e-05,
"loss": 3.7698,
"step": 417792
},
{
"epoch": 0.01,
"learning_rate": 4.315151441695062e-05,
"loss": 3.7638,
"step": 418304
},
{
"epoch": 0.01,
"learning_rate": 4.31431284694401e-05,
"loss": 3.7739,
"step": 418816
},
{
"epoch": 0.01,
"learning_rate": 4.3134758900733316e-05,
"loss": 3.7708,
"step": 419328
},
{
"epoch": 0.01,
"learning_rate": 4.3126372953222796e-05,
"loss": 3.7663,
"step": 419840
},
{
"epoch": 0.01,
"learning_rate": 4.3117987005712276e-05,
"loss": 3.7609,
"step": 420352
},
{
"epoch": 0.01,
"learning_rate": 4.3109601058201756e-05,
"loss": 3.7629,
"step": 420864
},
{
"epoch": 0.01,
"learning_rate": 4.3101231489494965e-05,
"loss": 3.7585,
"step": 421376
},
{
"epoch": 0.01,
"learning_rate": 4.3092845541984445e-05,
"loss": 3.7526,
"step": 421888
},
{
"epoch": 0.01,
"learning_rate": 4.3084459594473925e-05,
"loss": 3.7644,
"step": 422400
},
{
"epoch": 0.01,
"learning_rate": 4.3076073646963405e-05,
"loss": 3.7566,
"step": 422912
},
{
"epoch": 0.01,
"learning_rate": 4.3067704078256614e-05,
"loss": 3.769,
"step": 423424
},
{
"epoch": 0.01,
"learning_rate": 4.3059318130746094e-05,
"loss": 3.7702,
"step": 423936
},
{
"epoch": 0.01,
"learning_rate": 4.3050932183235574e-05,
"loss": 3.743,
"step": 424448
},
{
"epoch": 0.01,
"learning_rate": 4.3042546235725054e-05,
"loss": 3.7624,
"step": 424960
},
{
"epoch": 0.01,
"learning_rate": 4.303417666701827e-05,
"loss": 3.7567,
"step": 425472
},
{
"epoch": 0.01,
"learning_rate": 4.302579071950775e-05,
"loss": 3.7628,
"step": 425984
},
{
"epoch": 0.01,
"learning_rate": 4.301740477199723e-05,
"loss": 3.7567,
"step": 426496
},
{
"epoch": 0.01,
"learning_rate": 4.300901882448671e-05,
"loss": 3.7479,
"step": 427008
},
{
"epoch": 0.02,
"learning_rate": 4.300064925577992e-05,
"loss": 3.7607,
"step": 427520
},
{
"epoch": 0.02,
"learning_rate": 4.29922633082694e-05,
"loss": 3.7525,
"step": 428032
},
{
"epoch": 0.02,
"learning_rate": 4.298387736075888e-05,
"loss": 3.7568,
"step": 428544
},
{
"epoch": 0.02,
"learning_rate": 4.297550779205209e-05,
"loss": 3.7512,
"step": 429056
},
{
"epoch": 0.02,
"learning_rate": 4.296712184454157e-05,
"loss": 3.7618,
"step": 429568
},
{
"epoch": 0.02,
"learning_rate": 4.295873589703105e-05,
"loss": 3.7615,
"step": 430080
},
{
"epoch": 0.02,
"learning_rate": 4.295034994952053e-05,
"loss": 3.7609,
"step": 430592
},
{
"epoch": 0.02,
"learning_rate": 4.294198038081374e-05,
"loss": 3.7448,
"step": 431104
},
{
"epoch": 0.02,
"learning_rate": 4.293359443330322e-05,
"loss": 3.758,
"step": 431616
},
{
"epoch": 0.02,
"learning_rate": 4.29252084857927e-05,
"loss": 3.7569,
"step": 432128
},
{
"epoch": 0.02,
"learning_rate": 4.291682253828218e-05,
"loss": 3.7661,
"step": 432640
},
{
"epoch": 0.02,
"learning_rate": 4.290843659077166e-05,
"loss": 3.7503,
"step": 433152
},
{
"epoch": 0.02,
"learning_rate": 4.290006702206487e-05,
"loss": 3.7534,
"step": 433664
},
{
"epoch": 0.02,
"learning_rate": 4.289168107455435e-05,
"loss": 3.7505,
"step": 434176
},
{
"epoch": 0.02,
"learning_rate": 4.288329512704383e-05,
"loss": 3.7633,
"step": 434688
},
{
"epoch": 0.02,
"learning_rate": 4.287490917953331e-05,
"loss": 3.7444,
"step": 435200
},
{
"epoch": 0.02,
"learning_rate": 4.286653961082652e-05,
"loss": 3.749,
"step": 435712
},
{
"epoch": 0.02,
"learning_rate": 4.2858153663316e-05,
"loss": 3.7517,
"step": 436224
},
{
"epoch": 0.02,
"learning_rate": 4.284976771580548e-05,
"loss": 3.7516,
"step": 436736
},
{
"epoch": 0.02,
"learning_rate": 4.28413981470987e-05,
"loss": 3.7422,
"step": 437248
},
{
"epoch": 0.02,
"learning_rate": 4.283301219958818e-05,
"loss": 3.7508,
"step": 437760
},
{
"epoch": 0.02,
"learning_rate": 4.282462625207766e-05,
"loss": 3.7472,
"step": 438272
},
{
"epoch": 0.02,
"learning_rate": 4.281624030456714e-05,
"loss": 3.7542,
"step": 438784
},
{
"epoch": 0.02,
"learning_rate": 4.2807854357056617e-05,
"loss": 3.7537,
"step": 439296
},
{
"epoch": 0.02,
"learning_rate": 4.2799468409546097e-05,
"loss": 3.7432,
"step": 439808
},
{
"epoch": 0.02,
"learning_rate": 4.2791082462035576e-05,
"loss": 3.7564,
"step": 440320
},
{
"epoch": 0.02,
"learning_rate": 4.278269651452505e-05,
"loss": 3.7669,
"step": 440832
},
{
"epoch": 0.02,
"learning_rate": 4.2774326945818266e-05,
"loss": 3.7606,
"step": 441344
},
{
"epoch": 0.02,
"learning_rate": 4.2765940998307746e-05,
"loss": 3.7406,
"step": 441856
},
{
"epoch": 0.02,
"learning_rate": 4.2757555050797225e-05,
"loss": 3.7507,
"step": 442368
},
{
"epoch": 0.02,
"learning_rate": 4.27491691032867e-05,
"loss": 3.7489,
"step": 442880
},
{
"epoch": 0.02,
"learning_rate": 4.2740799534579915e-05,
"loss": 3.7451,
"step": 443392
},
{
"epoch": 0.02,
"learning_rate": 4.2732413587069394e-05,
"loss": 3.7492,
"step": 443904
},
{
"epoch": 0.02,
"learning_rate": 4.2724027639558874e-05,
"loss": 3.7398,
"step": 444416
},
{
"epoch": 0.02,
"learning_rate": 4.2715641692048354e-05,
"loss": 3.7518,
"step": 444928
},
{
"epoch": 0.02,
"learning_rate": 4.270727212334157e-05,
"loss": 3.7465,
"step": 445440
},
{
"epoch": 0.02,
"learning_rate": 4.269888617583105e-05,
"loss": 3.7575,
"step": 445952
},
{
"epoch": 0.02,
"learning_rate": 4.2690500228320523e-05,
"loss": 3.745,
"step": 446464
},
{
"epoch": 0.02,
"learning_rate": 4.268211428081e-05,
"loss": 3.7424,
"step": 446976
},
{
"epoch": 0.02,
"learning_rate": 4.267374471210322e-05,
"loss": 3.753,
"step": 447488
},
{
"epoch": 0.02,
"learning_rate": 4.26653587645927e-05,
"loss": 3.7578,
"step": 448000
},
{
"epoch": 0.02,
"learning_rate": 4.265697281708217e-05,
"loss": 3.7508,
"step": 448512
},
{
"epoch": 0.02,
"learning_rate": 4.264858686957165e-05,
"loss": 3.7518,
"step": 449024
},
{
"epoch": 0.02,
"learning_rate": 4.264021730086487e-05,
"loss": 3.7407,
"step": 449536
},
{
"epoch": 0.02,
"learning_rate": 4.263183135335435e-05,
"loss": 3.7562,
"step": 450048
},
{
"epoch": 0.02,
"learning_rate": 4.262344540584383e-05,
"loss": 3.7489,
"step": 450560
},
{
"epoch": 0.02,
"learning_rate": 4.261505945833331e-05,
"loss": 3.7578,
"step": 451072
},
{
"epoch": 0.02,
"learning_rate": 4.2606689889626524e-05,
"loss": 3.7419,
"step": 451584
},
{
"epoch": 0.02,
"learning_rate": 4.2598303942116e-05,
"loss": 3.756,
"step": 452096
},
{
"epoch": 0.02,
"learning_rate": 4.258991799460548e-05,
"loss": 3.7452,
"step": 452608
},
{
"epoch": 0.02,
"learning_rate": 4.258153204709496e-05,
"loss": 3.7676,
"step": 453120
},
{
"epoch": 0.02,
"learning_rate": 4.257316247838817e-05,
"loss": 3.7402,
"step": 453632
},
{
"epoch": 0.02,
"learning_rate": 4.2564776530877646e-05,
"loss": 3.7566,
"step": 454144
},
{
"epoch": 0.02,
"learning_rate": 4.2556390583367126e-05,
"loss": 3.7458,
"step": 454656
},
{
"epoch": 0.02,
"learning_rate": 4.2548004635856606e-05,
"loss": 3.742,
"step": 455168
},
{
"epoch": 0.02,
"learning_rate": 4.253963506714982e-05,
"loss": 3.7534,
"step": 455680
},
{
"epoch": 0.02,
"learning_rate": 4.25312491196393e-05,
"loss": 3.7495,
"step": 456192
},
{
"epoch": 0.02,
"learning_rate": 4.252286317212878e-05,
"loss": 3.7519,
"step": 456704
},
{
"epoch": 0.02,
"learning_rate": 4.251447722461826e-05,
"loss": 3.7409,
"step": 457216
},
{
"epoch": 0.02,
"learning_rate": 4.250610765591147e-05,
"loss": 3.7493,
"step": 457728
},
{
"epoch": 0.03,
"eval_loss": 3.870181083679199,
"eval_runtime": 305.8525,
"eval_samples_per_second": 1247.631,
"eval_steps_per_second": 38.989,
"step": 457920
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.164966159443845e+17,
"trial_name": null,
"trial_params": null
}