rel-cl-lstm-2 / checkpoint-763200 /trainer_state.json
abhinavp's picture
Training in progress, epoch 1, checkpoint
8b34074 verified
{
"best_metric": 4.081639766693115,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/lstm/2/checkpoints/checkpoint-763200",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 763200,
"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": 10.8198,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5561,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0558,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9947,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9451,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.923,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7606,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6438,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5402,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.454,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3949,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3237,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2535,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.189,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1376,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0803,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0409,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 6.0043,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9607,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984066699730012e-05,
"loss": 5.9188,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.893,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.853,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8304,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.794,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7784,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7408,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7192,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6908,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6758,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.975684027980238e-05,
"loss": 5.6486,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.974845433229186e-05,
"loss": 5.6382,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 5.6197,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 5.5953,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5807,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5663,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 5.5425,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5386,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.5052,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4923,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4631,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4621,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4461,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.4415,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.4144,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963110020355577e-05,
"loss": 5.404,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.4009,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 5.3945,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.381,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 5.3626,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3469,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3626,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3489,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.3284,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.3075,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.3174,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.294,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.2996,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2685,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2806,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.9505360127309166e-05,
"loss": 5.2643,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2474,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.2337,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948021866358134e-05,
"loss": 5.2449,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947183271607082e-05,
"loss": 5.2028,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.2163,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.2246,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.2079,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943830530483247e-05,
"loss": 5.1992,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1745,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1702,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.166,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1767,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.1567,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.1663,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1557,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371250482355776e-05,
"loss": 5.1539,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1299,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935447858733473e-05,
"loss": 5.1271,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934609263982421e-05,
"loss": 5.1187,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933770669231369e-05,
"loss": 5.1164,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329337123606905e-05,
"loss": 5.1144,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932095117609638e-05,
"loss": 5.0977,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931256522858586e-05,
"loss": 5.0996,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930417928107534e-05,
"loss": 5.0962,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295793333564825e-05,
"loss": 5.0728,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.0795,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.0776,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.08,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262265922326474e-05,
"loss": 5.06,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925389635361968e-05,
"loss": 5.0568,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924551040610916e-05,
"loss": 5.0434,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.039,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.0406,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 5.0381,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921198299487081e-05,
"loss": 5.029,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920359704736029e-05,
"loss": 5.0322,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 5.0215,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918682515233926e-05,
"loss": 5.0058,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917843920482874e-05,
"loss": 5.0024,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 5.0052,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916168368861143e-05,
"loss": 5.0003,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915329774110091e-05,
"loss": 5.0045,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914491179359039e-05,
"loss": 4.9868,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913652584607987e-05,
"loss": 4.9794,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.9832,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9631,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9681,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9584,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.9591,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908624291862421e-05,
"loss": 4.9464,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907785697111369e-05,
"loss": 4.9484,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9386,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9421,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.9367,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.927,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.9373,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.90275576648543e-05,
"loss": 4.9338,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901917171734378e-05,
"loss": 4.9236,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901078576983326e-05,
"loss": 4.9101,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900241620112647e-05,
"loss": 4.9111,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.899403025361595e-05,
"loss": 4.9091,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.898564430610543e-05,
"loss": 4.9107,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897725835859491e-05,
"loss": 4.9052,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968872411084396e-05,
"loss": 4.8941,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.8986,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.8847,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.889,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893534499984604e-05,
"loss": 4.8754,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8818,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.8703,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.8784,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.8776,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.875,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.8523,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.8577,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.8557,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.8574,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.8464,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884314871364151e-05,
"loss": 4.8519,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883476276613099e-05,
"loss": 4.8397,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882637681862047e-05,
"loss": 4.8558,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881799087110995e-05,
"loss": 4.8237,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880960492359943e-05,
"loss": 4.8432,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880121897608891e-05,
"loss": 4.827,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.8225,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.8226,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.8076,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876769156485057e-05,
"loss": 4.813,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.8204,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.8075,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.7714524269104,
"eval_runtime": 297.4083,
"eval_samples_per_second": 1283.054,
"eval_steps_per_second": 40.096,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.8051,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873416415361222e-05,
"loss": 4.7996,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.87257782061017e-05,
"loss": 4.8108,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871739225859118e-05,
"loss": 4.8001,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.8071,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.7815,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.7906,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.7736,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.7786,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.782,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7786,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.7811,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.761,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.7732,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.7569,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.761,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.7635,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.7539,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.7551,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.7697,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.746,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856651071861674e-05,
"loss": 4.7513,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558124771106226e-05,
"loss": 4.7453,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.85497388235957e-05,
"loss": 4.7533,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854135287608518e-05,
"loss": 4.7423,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853296692857466e-05,
"loss": 4.7422,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852458098106414e-05,
"loss": 4.7251,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851619503355362e-05,
"loss": 4.7336,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.85078090860431e-05,
"loss": 4.7199,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849942313853258e-05,
"loss": 4.7314,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849103719102206e-05,
"loss": 4.7279,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848266762231527e-05,
"loss": 4.7248,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847428167480475e-05,
"loss": 4.7293,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846589572729423e-05,
"loss": 4.7181,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.7254,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.7171,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844077064237013e-05,
"loss": 4.7077,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.7007,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842399874734909e-05,
"loss": 4.6898,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841561279983857e-05,
"loss": 4.6999,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840722685232805e-05,
"loss": 4.6986,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839884090481753e-05,
"loss": 4.7042,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839045495730701e-05,
"loss": 4.6884,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838206900979649e-05,
"loss": 4.6896,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.6927,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.6852,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8356960303676126e-05,
"loss": 4.6927,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.8348574356165606e-05,
"loss": 4.6781,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.6691,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.6965,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.6895,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.6757,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.6713,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.6792,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.6635,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281486776081446e-05,
"loss": 4.6807,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.6521,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.677,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.669,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.6524,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.6486,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.6627,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222801522311535e-05,
"loss": 4.6256,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214415574801015e-05,
"loss": 4.6472,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.6587,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819766005858371e-05,
"loss": 4.6504,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189274111073184e-05,
"loss": 4.6407,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180888163562664e-05,
"loss": 4.6285,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817251859485588e-05,
"loss": 4.6327,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.6339,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815576307863857e-05,
"loss": 4.6428,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.6313,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138991183617535e-05,
"loss": 4.638,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813060523610701e-05,
"loss": 4.6433,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.6405,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811383334108597e-05,
"loss": 4.6222,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810544739357545e-05,
"loss": 4.6286,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809706144606493e-05,
"loss": 4.6278,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808867549855441e-05,
"loss": 4.6192,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808030592984762e-05,
"loss": 4.6248,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.6148,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806353403482658e-05,
"loss": 4.6226,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.6214,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804677851860927e-05,
"loss": 4.6005,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803839257109875e-05,
"loss": 4.614,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.6118,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802162067607771e-05,
"loss": 4.6202,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801323472856719e-05,
"loss": 4.6118,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800484878105667e-05,
"loss": 4.6056,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799646283354615e-05,
"loss": 4.5995,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798807688603563e-05,
"loss": 4.5938,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797970731732884e-05,
"loss": 4.6004,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797132136981832e-05,
"loss": 4.6043,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796295180111153e-05,
"loss": 4.6009,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795456585360101e-05,
"loss": 4.6045,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794617990609049e-05,
"loss": 4.5968,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793779395857997e-05,
"loss": 4.5897,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792940801106946e-05,
"loss": 4.5867,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792102206355894e-05,
"loss": 4.5917,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.5963,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904282926145356e-05,
"loss": 4.5962,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895896978634836e-05,
"loss": 4.585,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887511031124316e-05,
"loss": 4.5777,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879125083613796e-05,
"loss": 4.5882,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870739136103276e-05,
"loss": 4.5702,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862353188592756e-05,
"loss": 4.5784,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853967241082236e-05,
"loss": 4.5739,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845581293571715e-05,
"loss": 4.5743,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837195346061195e-05,
"loss": 4.5636,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828809398550675e-05,
"loss": 4.5747,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820423451040155e-05,
"loss": 4.5618,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812037503529635e-05,
"loss": 4.5674,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803667934822844e-05,
"loss": 4.571,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795281987312324e-05,
"loss": 4.5585,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778691241860554e-05,
"loss": 4.5787,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777852647109502e-05,
"loss": 4.5747,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777014052358449e-05,
"loss": 4.5666,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776177095487771e-05,
"loss": 4.5572,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775338500736719e-05,
"loss": 4.5557,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774499905985666e-05,
"loss": 4.5621,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773661311234615e-05,
"loss": 4.5557,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772822716483563e-05,
"loss": 4.5652,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771984121732511e-05,
"loss": 4.5484,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771145526981459e-05,
"loss": 4.5556,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770306932230407e-05,
"loss": 4.5533,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769469975359728e-05,
"loss": 4.5587,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768631380608676e-05,
"loss": 4.5406,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767792785857624e-05,
"loss": 4.5523,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766954191106572e-05,
"loss": 4.5481,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.76611559635552e-05,
"loss": 4.5486,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765277001604468e-05,
"loss": 4.5538,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764438406853416e-05,
"loss": 4.5594,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763599812102364e-05,
"loss": 4.5343,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762761217351312e-05,
"loss": 4.5419,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761924260480633e-05,
"loss": 4.547,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610856657295813e-05,
"loss": 4.5437,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602470709785293e-05,
"loss": 4.5403,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594084762274773e-05,
"loss": 4.5432,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758569881476425e-05,
"loss": 4.5348,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757731286725373e-05,
"loss": 4.5525,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7568926919743206e-05,
"loss": 4.5264,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756055735103642e-05,
"loss": 4.5426,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.75521714035259e-05,
"loss": 4.5311,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543785456015375e-05,
"loss": 4.5255,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753541588730859e-05,
"loss": 4.528,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752702993979807e-05,
"loss": 4.5229,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751864399228755e-05,
"loss": 4.5232,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751025804477703e-05,
"loss": 4.5281,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750187209726651e-05,
"loss": 4.5233,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.489068508148193,
"eval_runtime": 296.8327,
"eval_samples_per_second": 1285.542,
"eval_steps_per_second": 40.174,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749348614975599e-05,
"loss": 4.5204,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748510020224547e-05,
"loss": 4.5122,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747671425473495e-05,
"loss": 4.5327,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746832830722443e-05,
"loss": 4.5205,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745994235971391e-05,
"loss": 4.532,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745155641220339e-05,
"loss": 4.508,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744317046469287e-05,
"loss": 4.5194,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743478451718235e-05,
"loss": 4.5033,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742639856967183e-05,
"loss": 4.5144,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741801262216131e-05,
"loss": 4.5129,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740962667465079e-05,
"loss": 4.5112,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401240727140264e-05,
"loss": 4.5215,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739287115843348e-05,
"loss": 4.4955,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384485210922966e-05,
"loss": 4.5135,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376099263412446e-05,
"loss": 4.497,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736771331590192e-05,
"loss": 4.4978,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359343747195135e-05,
"loss": 4.4982,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350957799684615e-05,
"loss": 4.5054,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342571852174095e-05,
"loss": 4.4969,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733418590466357e-05,
"loss": 4.5152,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732579995715305e-05,
"loss": 4.5,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731741400964253e-05,
"loss": 4.4987,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730902806213201e-05,
"loss": 4.4979,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730064211462149e-05,
"loss": 4.5085,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729225616711097e-05,
"loss": 4.4942,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728390297720791e-05,
"loss": 4.4973,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727551702969739e-05,
"loss": 4.4848,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726714746099061e-05,
"loss": 4.4904,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725876151348009e-05,
"loss": 4.4794,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725037556596957e-05,
"loss": 4.4949,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724198961845904e-05,
"loss": 4.4925,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723360367094852e-05,
"loss": 4.4892,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225217723438e-05,
"loss": 4.496,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721683177592748e-05,
"loss": 4.4847,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720844582841696e-05,
"loss": 4.4851,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720005988090644e-05,
"loss": 4.4873,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719167393339592e-05,
"loss": 4.4811,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71832879858854e-05,
"loss": 4.4732,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717490203837488e-05,
"loss": 4.462,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716651609086437e-05,
"loss": 4.4739,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715814652215758e-05,
"loss": 4.4764,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714976057464706e-05,
"loss": 4.4798,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714137462713654e-05,
"loss": 4.4697,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713298867962602e-05,
"loss": 4.4661,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712461911091923e-05,
"loss": 4.4793,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711623316340871e-05,
"loss": 4.4693,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710784721589819e-05,
"loss": 4.4708,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099461268387667e-05,
"loss": 4.4641,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091091699680876e-05,
"loss": 4.4519,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082705752170356e-05,
"loss": 4.4816,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074319804659836e-05,
"loss": 4.4749,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706593385714932e-05,
"loss": 4.4641,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705756428844253e-05,
"loss": 4.4603,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704917834093201e-05,
"loss": 4.4713,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704079239342149e-05,
"loss": 4.4507,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703240644591097e-05,
"loss": 4.4724,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702402049840045e-05,
"loss": 4.4463,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015634550889924e-05,
"loss": 4.4641,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007248603379404e-05,
"loss": 4.4698,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998862655868884e-05,
"loss": 4.4497,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.69904930871621e-05,
"loss": 4.4432,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982107139651573e-05,
"loss": 4.4605,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697372119214106e-05,
"loss": 4.4298,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696533524463054e-05,
"loss": 4.4479,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695694929712002e-05,
"loss": 4.455,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694857972841323e-05,
"loss": 4.455,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694019378090271e-05,
"loss": 4.4463,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693180783339219e-05,
"loss": 4.4331,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692342188588167e-05,
"loss": 4.4348,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691505231717488e-05,
"loss": 4.4361,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690666636966436e-05,
"loss": 4.449,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689828042215384e-05,
"loss": 4.4406,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688989447464332e-05,
"loss": 4.4477,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688152490593653e-05,
"loss": 4.4537,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873138958426014e-05,
"loss": 4.4491,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864753010915494e-05,
"loss": 4.4319,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856367063404974e-05,
"loss": 4.4385,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6847981115894454e-05,
"loss": 4.4463,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839595168383934e-05,
"loss": 4.432,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683124197848087e-05,
"loss": 4.4382,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682285603097035e-05,
"loss": 4.4331,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681447008345983e-05,
"loss": 4.4322,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680608413594931e-05,
"loss": 4.4413,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679769818843879e-05,
"loss": 4.4172,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678931224092827e-05,
"loss": 4.4358,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678092629341775e-05,
"loss": 4.4258,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677254034590723e-05,
"loss": 4.4398,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676415439839671e-05,
"loss": 4.4308,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675576845088619e-05,
"loss": 4.4277,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674738250337568e-05,
"loss": 4.4228,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673899655586516e-05,
"loss": 4.4175,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673061060835464e-05,
"loss": 4.4187,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672222466084412e-05,
"loss": 4.427,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671385509213733e-05,
"loss": 4.4356,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670546914462681e-05,
"loss": 4.4283,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669708319711629e-05,
"loss": 4.4206,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668869724960576e-05,
"loss": 4.4162,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668031130209524e-05,
"loss": 4.4171,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667192535458472e-05,
"loss": 4.4181,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663555785877936e-05,
"loss": 4.4276,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655169838367416e-05,
"loss": 4.4241,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.6646783890856896e-05,
"loss": 4.4167,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.6638397943346376e-05,
"loss": 4.4085,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663002837463959e-05,
"loss": 4.424,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621642427129065e-05,
"loss": 4.4045,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613256479618545e-05,
"loss": 4.4138,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6604870532108025e-05,
"loss": 4.4062,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596484584597505e-05,
"loss": 4.4125,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588098637086985e-05,
"loss": 4.4023,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579712689576465e-05,
"loss": 4.4137,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571326742065945e-05,
"loss": 4.4016,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656297355216288e-05,
"loss": 4.3996,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655458760465237e-05,
"loss": 4.4151,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654620165714185e-05,
"loss": 4.3968,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653781570963133e-05,
"loss": 4.4194,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652944614092454e-05,
"loss": 4.4155,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652106019341402e-05,
"loss": 4.4105,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.65126742459035e-05,
"loss": 4.4003,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650430467719671e-05,
"loss": 4.3991,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649591872968619e-05,
"loss": 4.4015,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648753278217567e-05,
"loss": 4.4004,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647914683466515e-05,
"loss": 4.4089,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647076088715463e-05,
"loss": 4.393,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646237493964411e-05,
"loss": 4.4033,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645398899213359e-05,
"loss": 4.4014,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644560304462307e-05,
"loss": 4.403,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437217097112554e-05,
"loss": 4.3904,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642884752840576e-05,
"loss": 4.3978,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642046158089524e-05,
"loss": 4.3953,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641207563338472e-05,
"loss": 4.3987,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.64036896858742e-05,
"loss": 4.3996,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639530373836368e-05,
"loss": 4.4078,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638691779085316e-05,
"loss": 4.382,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637853184334264e-05,
"loss": 4.3961,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637016227463585e-05,
"loss": 4.3993,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636177632712533e-05,
"loss": 4.3931,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635339037961481e-05,
"loss": 4.3911,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634500443210429e-05,
"loss": 4.4002,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633661848459377e-05,
"loss": 4.3903,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632824891588699e-05,
"loss": 4.4058,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631986296837647e-05,
"loss": 4.3805,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631147702086595e-05,
"loss": 4.3939,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630309107335542e-05,
"loss": 4.3899,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629472150464864e-05,
"loss": 4.385,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628633555713812e-05,
"loss": 4.3829,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277949609627597e-05,
"loss": 4.3812,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626956366211707e-05,
"loss": 4.3776,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626117771460655e-05,
"loss": 4.3839,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625279176709603e-05,
"loss": 4.3831,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.353968620300293,
"eval_runtime": 291.6765,
"eval_samples_per_second": 1308.268,
"eval_steps_per_second": 40.884,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.6244422198389246e-05,
"loss": 4.3856,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.6236036250878726e-05,
"loss": 4.3704,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.6227650303368205e-05,
"loss": 4.3917,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219264355857685e-05,
"loss": 4.3768,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.6210878408347165e-05,
"loss": 4.3941,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202492460836645e-05,
"loss": 4.3722,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194122892129854e-05,
"loss": 4.381,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185736944619334e-05,
"loss": 4.3631,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177350997108814e-05,
"loss": 4.3786,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6168965049598294e-05,
"loss": 4.3783,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.6160579102087774e-05,
"loss": 4.3739,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.6152193154577254e-05,
"loss": 4.38,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614382358587046e-05,
"loss": 4.3649,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613543763835994e-05,
"loss": 4.3784,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612705169084942e-05,
"loss": 4.3655,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611866574333891e-05,
"loss": 4.3611,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611027979582839e-05,
"loss": 4.3671,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610189384831787e-05,
"loss": 4.371,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609352427961108e-05,
"loss": 4.3658,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608513833210056e-05,
"loss": 4.3813,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607676876339377e-05,
"loss": 4.3698,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606838281588325e-05,
"loss": 4.3733,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.605999686837273e-05,
"loss": 4.3646,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605161092086221e-05,
"loss": 4.3745,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604322497335169e-05,
"loss": 4.364,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.60348554046449e-05,
"loss": 4.3688,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602646945713438e-05,
"loss": 4.359,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018083509623864e-05,
"loss": 4.3553,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009697562113344e-05,
"loss": 4.3562,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001311614602824e-05,
"loss": 4.3639,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.5992925667092303e-05,
"loss": 4.3663,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.5984539719581783e-05,
"loss": 4.3609,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.5976153772071257e-05,
"loss": 4.3714,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5967767824560737e-05,
"loss": 4.3605,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595939825585395e-05,
"loss": 4.357,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595101230834343e-05,
"loss": 4.3613,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594264273963664e-05,
"loss": 4.3637,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593425679212612e-05,
"loss": 4.345,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.59258708446156e-05,
"loss": 4.3387,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591748489710508e-05,
"loss": 4.3466,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590909894959456e-05,
"loss": 4.3566,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590071300208404e-05,
"loss": 4.3549,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589232705457352e-05,
"loss": 4.3498,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5883941107063e-05,
"loss": 4.3399,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587555515955248e-05,
"loss": 4.3559,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586716921204196e-05,
"loss": 4.3499,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585878326453144e-05,
"loss": 4.3505,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585039731702092e-05,
"loss": 4.343,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584204412711786e-05,
"loss": 4.3271,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583365817960734e-05,
"loss": 4.3699,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582527223209682e-05,
"loss": 4.3525,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.58168862845863e-05,
"loss": 4.3469,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808500337075786e-05,
"loss": 4.3454,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800114389565266e-05,
"loss": 4.3476,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791728442054746e-05,
"loss": 4.3368,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783358873347955e-05,
"loss": 4.3501,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5774989304641164e-05,
"loss": 4.3313,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766603357130644e-05,
"loss": 4.3431,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758217409620124e-05,
"loss": 4.3573,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5749831462109604e-05,
"loss": 4.3329,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741445514599084e-05,
"loss": 4.3225,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733059567088564e-05,
"loss": 4.3489,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724673619578044e-05,
"loss": 4.3159,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716287672067524e-05,
"loss": 4.33,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5707901724557004e-05,
"loss": 4.3422,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.5699515777046484e-05,
"loss": 4.339,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.5691129829535963e-05,
"loss": 4.3338,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5682743882025443e-05,
"loss": 4.325,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567437431331866e-05,
"loss": 4.3162,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566600474461187e-05,
"loss": 4.3237,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565761879710135e-05,
"loss": 4.3395,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564923284959083e-05,
"loss": 4.3244,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564084690208031e-05,
"loss": 4.3379,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563246095456979e-05,
"loss": 4.3374,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562407500705927e-05,
"loss": 4.3423,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561568905954874e-05,
"loss": 4.3243,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560730311203822e-05,
"loss": 4.3248,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559893354333144e-05,
"loss": 4.337,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559054759582092e-05,
"loss": 4.3201,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.55821616483104e-05,
"loss": 4.3362,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557379207960361e-05,
"loss": 4.3227,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556540613209309e-05,
"loss": 4.3241,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.5557020184582566e-05,
"loss": 4.3332,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.5548634237072046e-05,
"loss": 4.3125,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.5540248289561526e-05,
"loss": 4.3257,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553187872085474e-05,
"loss": 4.3223,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523492773344215e-05,
"loss": 4.33,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515106825833695e-05,
"loss": 4.321,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.5506720878323175e-05,
"loss": 4.3238,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.5498334930812655e-05,
"loss": 4.314,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.548996536210587e-05,
"loss": 4.3112,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548157941459535e-05,
"loss": 4.3142,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547319346708483e-05,
"loss": 4.3197,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546480751957431e-05,
"loss": 4.33,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545642157206379e-05,
"loss": 4.3257,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544803562455327e-05,
"loss": 4.3186,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543964967704275e-05,
"loss": 4.3111,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543128010833596e-05,
"loss": 4.3124,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542289416082544e-05,
"loss": 4.3177,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541450821331492e-05,
"loss": 4.3206,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.54061222658044e-05,
"loss": 4.3212,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539773631829388e-05,
"loss": 4.3137,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538935037078336e-05,
"loss": 4.3046,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538096442327284e-05,
"loss": 4.3235,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372578475762326e-05,
"loss": 4.2993,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364208907055535e-05,
"loss": 4.316,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5355822959545015e-05,
"loss": 4.303,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347453390838224e-05,
"loss": 4.3123,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339067443327704e-05,
"loss": 4.3023,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330681495817184e-05,
"loss": 4.3106,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532231192711039e-05,
"loss": 4.3046,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531392597959987e-05,
"loss": 4.3015,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530554003208935e-05,
"loss": 4.312,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529715408457883e-05,
"loss": 4.2975,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528876813706831e-05,
"loss": 4.3188,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528038218955779e-05,
"loss": 4.3192,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527199624204728e-05,
"loss": 4.3131,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526361029453675e-05,
"loss": 4.3023,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525524072582997e-05,
"loss": 4.303,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524685477831945e-05,
"loss": 4.3004,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523846883080893e-05,
"loss": 4.3025,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.52300828832984e-05,
"loss": 4.3132,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522169693578788e-05,
"loss": 4.2911,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521331098827736e-05,
"loss": 4.3057,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520492504076684e-05,
"loss": 4.3016,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519655547206005e-05,
"loss": 4.3071,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518816952454953e-05,
"loss": 4.2939,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517978357703902e-05,
"loss": 4.3035,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.51713976295285e-05,
"loss": 4.2952,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516301168201798e-05,
"loss": 4.3089,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515462573450746e-05,
"loss": 4.3023,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146256165800667e-05,
"loss": 4.3134,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5137870218290147e-05,
"loss": 4.2867,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.5129484270779626e-05,
"loss": 4.3027,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.5121098323269106e-05,
"loss": 4.3068,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.5112712375758586e-05,
"loss": 4.2925,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104342807051795e-05,
"loss": 4.2974,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5095956859541275e-05,
"loss": 4.3068,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087570912030755e-05,
"loss": 4.3005,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079184964520235e-05,
"loss": 4.3141,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070799017009715e-05,
"loss": 4.2859,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062413069499195e-05,
"loss": 4.3035,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505402712198868e-05,
"loss": 4.2913,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504564117447816e-05,
"loss": 4.2948,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503727160577137e-05,
"loss": 4.294,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502888565826085e-05,
"loss": 4.2873,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502051608955406e-05,
"loss": 4.2857,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501213014204354e-05,
"loss": 4.292,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500374419453302e-05,
"loss": 4.2934,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.271243572235107,
"eval_runtime": 291.4111,
"eval_samples_per_second": 1309.459,
"eval_steps_per_second": 40.922,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.49953582470225e-05,
"loss": 4.2932,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498697229951198e-05,
"loss": 4.2801,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497858635200146e-05,
"loss": 4.3016,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497020040449093e-05,
"loss": 4.2886,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496181445698042e-05,
"loss": 4.2995,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.49534285094699e-05,
"loss": 4.2889,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494504256195938e-05,
"loss": 4.2892,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493665661444886e-05,
"loss": 4.2762,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492827066693834e-05,
"loss": 4.2867,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.491988471942782e-05,
"loss": 4.2881,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.49114987719173e-05,
"loss": 4.2887,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490311282440678e-05,
"loss": 4.2904,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489474325569999e-05,
"loss": 4.2762,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488635730818947e-05,
"loss": 4.2924,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487797136067895e-05,
"loss": 4.2772,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486958541316843e-05,
"loss": 4.2724,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486119946565791e-05,
"loss": 4.2776,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485281351814739e-05,
"loss": 4.2844,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484442757063687e-05,
"loss": 4.2784,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483604162312635e-05,
"loss": 4.293,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482765567561583e-05,
"loss": 4.2844,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481926972810531e-05,
"loss": 4.2887,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481088378059479e-05,
"loss": 4.2778,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480249783308427e-05,
"loss": 4.2856,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479414464318121e-05,
"loss": 4.2778,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478575869567069e-05,
"loss": 4.2862,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477737274816017e-05,
"loss": 4.2747,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476898680064965e-05,
"loss": 4.2733,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.4760600853139126e-05,
"loss": 4.2694,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.4752214905628606e-05,
"loss": 4.2786,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.4743828958118086e-05,
"loss": 4.2827,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.47354593894113e-05,
"loss": 4.2775,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472707344190078e-05,
"loss": 4.284,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471868749439026e-05,
"loss": 4.2731,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471030154687974e-05,
"loss": 4.2745,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470193197817295e-05,
"loss": 4.2842,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469354603066243e-05,
"loss": 4.2806,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468516008315191e-05,
"loss": 4.2584,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467677413564139e-05,
"loss": 4.2626,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466838818813087e-05,
"loss": 4.2621,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466000224062035e-05,
"loss": 4.2675,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465161629310983e-05,
"loss": 4.2785,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464323034559931e-05,
"loss": 4.2661,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463484439808879e-05,
"loss": 4.2628,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462645845057827e-05,
"loss": 4.2737,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461807250306775e-05,
"loss": 4.2665,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460968655555724e-05,
"loss": 4.2713,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601316986850446e-05,
"loss": 4.2637,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4592947418143655e-05,
"loss": 4.2416,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584561470633135e-05,
"loss": 4.2894,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576191901926344e-05,
"loss": 4.2717,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4567805954415824e-05,
"loss": 4.2721,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559420006905304e-05,
"loss": 4.2654,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551034059394784e-05,
"loss": 4.2641,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542648111884264e-05,
"loss": 4.2577,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534262164373744e-05,
"loss": 4.2664,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4525876216863224e-05,
"loss": 4.256,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451750664815644e-05,
"loss": 4.2613,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450912070064592e-05,
"loss": 4.2791,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.45007347531354e-05,
"loss": 4.2552,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449234880562488e-05,
"loss": 4.2475,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448396285811436e-05,
"loss": 4.2707,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447557691060384e-05,
"loss": 4.2409,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446719096309331e-05,
"loss": 4.2536,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445880501558279e-05,
"loss": 4.2599,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445043544687601e-05,
"loss": 4.2627,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444204949936548e-05,
"loss": 4.2553,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443366355185496e-05,
"loss": 4.2505,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442527760434444e-05,
"loss": 4.2361,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441690803563766e-05,
"loss": 4.2488,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440852208812714e-05,
"loss": 4.2598,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440013614061662e-05,
"loss": 4.2511,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.43917501931061e-05,
"loss": 4.2582,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438336424559558e-05,
"loss": 4.2631,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437497829808506e-05,
"loss": 4.2695,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436660872937827e-05,
"loss": 4.2488,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.4358222781867747e-05,
"loss": 4.2456,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.4349836834357227e-05,
"loss": 4.2629,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.4341450886846707e-05,
"loss": 4.2404,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333064939336186e-05,
"loss": 4.2631,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4324695370629396e-05,
"loss": 4.2474,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431630942311888e-05,
"loss": 4.2492,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430792347560836e-05,
"loss": 4.2602,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429953752809784e-05,
"loss": 4.2386,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429115158058732e-05,
"loss": 4.2496,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.42827656330768e-05,
"loss": 4.2467,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427437968556628e-05,
"loss": 4.2568,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426599373805576e-05,
"loss": 4.2428,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.42576405481527e-05,
"loss": 4.2531,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424925460064218e-05,
"loss": 4.2407,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424086865313166e-05,
"loss": 4.2407,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423248270562114e-05,
"loss": 4.2375,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422409675811062e-05,
"loss": 4.2493,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.42157108106001e-05,
"loss": 4.2561,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420732486308958e-05,
"loss": 4.2498,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419893891557907e-05,
"loss": 4.2513,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190569346872276e-05,
"loss": 4.2378,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182199778165485e-05,
"loss": 4.2388,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4173813830654965e-05,
"loss": 4.2435,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.4165427883144445e-05,
"loss": 4.2516,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157041935633925e-05,
"loss": 4.2481,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.4148655988123405e-05,
"loss": 4.2421,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.4140270040612885e-05,
"loss": 4.2367,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4131884093102365e-05,
"loss": 4.2529,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123498145591845e-05,
"loss": 4.2287,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411511219808132e-05,
"loss": 4.2424,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106742629374534e-05,
"loss": 4.233,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409835668186402e-05,
"loss": 4.2407,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.408998711315723e-05,
"loss": 4.2305,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408160116564671e-05,
"loss": 4.2421,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407321521813619e-05,
"loss": 4.2325,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406482927062567e-05,
"loss": 4.2331,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405644332311514e-05,
"loss": 4.2405,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404805737560462e-05,
"loss": 4.2311,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.40396714280941e-05,
"loss": 4.2465,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403128548058358e-05,
"loss": 4.25,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402291591187679e-05,
"loss": 4.2409,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401452996436627e-05,
"loss": 4.2378,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400614401685576e-05,
"loss": 4.228,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399775806934524e-05,
"loss": 4.2353,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398937212183472e-05,
"loss": 4.2336,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.39809861743242e-05,
"loss": 4.2487,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397260022681368e-05,
"loss": 4.2197,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396423065810689e-05,
"loss": 4.2393,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395584471059637e-05,
"loss": 4.2333,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394745876308585e-05,
"loss": 4.2381,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393907281557533e-05,
"loss": 4.2288,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3930703246868536e-05,
"loss": 4.2359,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.3922317299358016e-05,
"loss": 4.2263,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3913931351847496e-05,
"loss": 4.2402,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905545404336976e-05,
"loss": 4.2385,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389717583563019e-05,
"loss": 4.2419,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388878988811967e-05,
"loss": 4.2223,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388040394060915e-05,
"loss": 4.2366,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387201799309863e-05,
"loss": 4.2404,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386363204558811e-05,
"loss": 4.2278,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385524609807759e-05,
"loss": 4.2323,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384686015056707e-05,
"loss": 4.2396,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383847420305655e-05,
"loss": 4.23,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383010463434976e-05,
"loss": 4.2509,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382171868683924e-05,
"loss": 4.223,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381333273932872e-05,
"loss": 4.2361,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.38049467918182e-05,
"loss": 4.2258,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379657722311141e-05,
"loss": 4.2262,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378819127560089e-05,
"loss": 4.2293,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3779805328090376e-05,
"loss": 4.2224,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771435759383585e-05,
"loss": 4.2248,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763049811873065e-05,
"loss": 4.2178,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3754663864362545e-05,
"loss": 4.2326,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.2147417068481445,
"eval_runtime": 301.4435,
"eval_samples_per_second": 1265.879,
"eval_steps_per_second": 39.56,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.3746277916852025e-05,
"loss": 4.2297,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.3737891969341505e-05,
"loss": 4.2153,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.372950602183098e-05,
"loss": 4.2339,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.3721136453124194e-05,
"loss": 4.2283,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.3712750505613674e-05,
"loss": 4.2325,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.370438093690688e-05,
"loss": 4.2232,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.369599498939636e-05,
"loss": 4.225,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368760904188584e-05,
"loss": 4.2134,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367922309437533e-05,
"loss": 4.2228,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367083714686481e-05,
"loss": 4.2252,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366245119935428e-05,
"loss": 4.2275,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.365406525184376e-05,
"loss": 4.2213,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.364569568313698e-05,
"loss": 4.2185,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.363730973562645e-05,
"loss": 4.2235,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.362892378811593e-05,
"loss": 4.2174,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.362053784060541e-05,
"loss": 4.2059,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.361215189309489e-05,
"loss": 4.2173,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.360376594558437e-05,
"loss": 4.2229,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.359537999807385e-05,
"loss": 4.2168,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.358699405056333e-05,
"loss": 4.2309,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.357860810305281e-05,
"loss": 4.2248,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.35702221555423e-05,
"loss": 4.2285,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.356183620803178e-05,
"loss": 4.2146,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.355345026052126e-05,
"loss": 4.2214,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.354508069181447e-05,
"loss": 4.2157,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.3536711123107677e-05,
"loss": 4.2268,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.3528325175597157e-05,
"loss": 4.2138,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.3519939228086636e-05,
"loss": 4.2101,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.3511553280576116e-05,
"loss": 4.2091,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.3503167333065596e-05,
"loss": 4.2192,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.3494797764358805e-05,
"loss": 4.2181,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.3486411816848285e-05,
"loss": 4.2198,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.3478025869337765e-05,
"loss": 4.2215,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.346963992182725e-05,
"loss": 4.2167,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.346127035312046e-05,
"loss": 4.2153,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345290078441367e-05,
"loss": 4.222,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344451483690315e-05,
"loss": 4.2187,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.343612888939263e-05,
"loss": 4.2018,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.342774294188211e-05,
"loss": 4.2034,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.341935699437159e-05,
"loss": 4.2008,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.341097104686107e-05,
"loss": 4.2057,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.340258509935055e-05,
"loss": 4.2193,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.339419915184003e-05,
"loss": 4.2084,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338581320432951e-05,
"loss": 4.2027,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337744363562272e-05,
"loss": 4.2129,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.33690576881122e-05,
"loss": 4.2043,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.3360671740601686e-05,
"loss": 4.2132,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.3352285793091166e-05,
"loss": 4.204,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334389984558064e-05,
"loss": 4.1831,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.333551389807012e-05,
"loss": 4.2315,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.33271279505596e-05,
"loss": 4.211,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.331874200304908e-05,
"loss": 4.2166,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331037243434229e-05,
"loss": 4.2023,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.3302002865635504e-05,
"loss": 4.2099,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.329363329692871e-05,
"loss": 4.1988,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328524734941819e-05,
"loss": 4.2048,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.327687778071141e-05,
"loss": 4.2038,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326849183320089e-05,
"loss": 4.202,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326010588569037e-05,
"loss": 4.2224,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.325171993817985e-05,
"loss": 4.1964,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.324333399066933e-05,
"loss": 4.1885,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.323494804315881e-05,
"loss": 4.2147,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322656209564829e-05,
"loss": 4.1832,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.321817614813776e-05,
"loss": 4.1919,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.320979020062724e-05,
"loss": 4.2063,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.320140425311672e-05,
"loss": 4.2089,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.31930183056062e-05,
"loss": 4.1922,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.318463235809568e-05,
"loss": 4.2003,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.317624641058516e-05,
"loss": 4.1779,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.316787684187838e-05,
"loss": 4.1948,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.315949089436786e-05,
"loss": 4.2024,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.315110494685734e-05,
"loss": 4.1914,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.314271899934682e-05,
"loss": 4.2027,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.31343330518363e-05,
"loss": 4.2037,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.312594710432578e-05,
"loss": 4.215,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311756115681526e-05,
"loss": 4.1897,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310917520930474e-05,
"loss": 4.1948,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310078926179422e-05,
"loss": 4.2071,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.30924033142837e-05,
"loss": 4.1853,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308401736677318e-05,
"loss": 4.2024,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.3075647798066386e-05,
"loss": 4.195,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.3067261850555866e-05,
"loss": 4.192,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.3058875903045346e-05,
"loss": 4.2059,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.3050489955534826e-05,
"loss": 4.1845,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.3042104008024306e-05,
"loss": 4.1904,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.3033718060513786e-05,
"loss": 4.1949,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.3025332113003266e-05,
"loss": 4.2008,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.3016946165492746e-05,
"loss": 4.1893,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.3008576596785955e-05,
"loss": 4.1969,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.3000190649275435e-05,
"loss": 4.1806,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.2991804701764915e-05,
"loss": 4.1878,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.2983435133058124e-05,
"loss": 4.1848,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.2975049185547604e-05,
"loss": 4.1929,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.2966663238037084e-05,
"loss": 4.2058,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.2958277290526564e-05,
"loss": 4.1926,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.294990772181978e-05,
"loss": 4.1963,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294152177430926e-05,
"loss": 4.184,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293313582679874e-05,
"loss": 4.1842,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.292474987928822e-05,
"loss": 4.1908,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.29163639317777e-05,
"loss": 4.1984,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.290797798426718e-05,
"loss": 4.1919,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.289960841556039e-05,
"loss": 4.1953,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289122246804987e-05,
"loss": 4.1845,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288283652053935e-05,
"loss": 4.197,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.287445057302883e-05,
"loss": 4.1782,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286606462551831e-05,
"loss": 4.1897,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.285769505681152e-05,
"loss": 4.1757,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.2849309109301e-05,
"loss": 4.192,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284092316179048e-05,
"loss": 4.1791,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.2832537214279964e-05,
"loss": 4.1857,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.2824151266769444e-05,
"loss": 4.1799,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.2815765319258924e-05,
"loss": 4.1819,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.2807379371748404e-05,
"loss": 4.1845,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.2798993424237884e-05,
"loss": 4.1803,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.279064023433482e-05,
"loss": 4.1931,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.27822542868243e-05,
"loss": 4.1964,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.277388471811751e-05,
"loss": 4.1898,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276549877060699e-05,
"loss": 4.1902,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.275711282309647e-05,
"loss": 4.1737,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.274872687558595e-05,
"loss": 4.1827,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.274034092807543e-05,
"loss": 4.1836,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273195498056492e-05,
"loss": 4.1934,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.27235690330544e-05,
"loss": 4.1665,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.271518308554388e-05,
"loss": 4.1865,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.270679713803336e-05,
"loss": 4.1842,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.269841119052284e-05,
"loss": 4.181,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.269002524301231e-05,
"loss": 4.1787,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.268163929550179e-05,
"loss": 4.1868,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.2673286105598735e-05,
"loss": 4.1758,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.2664900158088215e-05,
"loss": 4.1904,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.2656514210577695e-05,
"loss": 4.1878,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.2648128263067175e-05,
"loss": 4.1891,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.2639742315556655e-05,
"loss": 4.171,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.2631356368046135e-05,
"loss": 4.184,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.2622970420535615e-05,
"loss": 4.1881,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.2614584473025095e-05,
"loss": 4.1772,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.260621490431831e-05,
"loss": 4.1814,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.2597828956807784e-05,
"loss": 4.1867,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.2589443009297264e-05,
"loss": 4.1836,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.2581057061786744e-05,
"loss": 4.1958,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.2572671114276224e-05,
"loss": 4.1768,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256430154556943e-05,
"loss": 4.1831,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255591559805891e-05,
"loss": 4.1776,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254752965054839e-05,
"loss": 4.1794,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253916008184161e-05,
"loss": 4.1755,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253077413433109e-05,
"loss": 4.1722,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252238818682057e-05,
"loss": 4.1775,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251400223931005e-05,
"loss": 4.1676,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250561629179953e-05,
"loss": 4.1845,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 4.1723713874816895,
"eval_runtime": 299.6223,
"eval_samples_per_second": 1273.573,
"eval_steps_per_second": 39.8,
"step": 457920
},
{
"epoch": 0.0,
"learning_rate": 4.249723034428901e-05,
"loss": 4.1851,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.248884439677849e-05,
"loss": 4.167,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.248045844926797e-05,
"loss": 4.1824,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.247207250175745e-05,
"loss": 4.1766,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.246368655424693e-05,
"loss": 4.1861,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.245530060673641e-05,
"loss": 4.175,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.244691465922589e-05,
"loss": 4.1773,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.243852871171537e-05,
"loss": 4.1632,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.243014276420485e-05,
"loss": 4.1741,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.242175681669432e-05,
"loss": 4.1754,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.241337086918381e-05,
"loss": 4.1779,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.240498492167329e-05,
"loss": 4.1733,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.23966153529665e-05,
"loss": 4.1686,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238822940545598e-05,
"loss": 4.1749,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.237984345794546e-05,
"loss": 4.1721,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237145751043494e-05,
"loss": 4.1575,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.236307156292442e-05,
"loss": 4.1694,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.23546856154139e-05,
"loss": 4.1722,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.234629966790338e-05,
"loss": 4.1701,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.233791372039286e-05,
"loss": 4.1794,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.232952777288234e-05,
"loss": 4.1781,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.232114182537182e-05,
"loss": 4.1809,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.23127558778613e-05,
"loss": 4.1641,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.230436993035078e-05,
"loss": 4.1735,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.2296000361643986e-05,
"loss": 4.1697,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.228761441413347e-05,
"loss": 4.1776,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.227924484542668e-05,
"loss": 4.1653,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.227085889791616e-05,
"loss": 4.1661,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.226247295040564e-05,
"loss": 4.1635,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.225408700289512e-05,
"loss": 4.1666,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.224571743418833e-05,
"loss": 4.1676,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.223733148667781e-05,
"loss": 4.1751,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.222894553916729e-05,
"loss": 4.1748,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.222055959165677e-05,
"loss": 4.1725,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.221217364414625e-05,
"loss": 4.1667,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.220380407543946e-05,
"loss": 4.1713,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.219541812792894e-05,
"loss": 4.1749,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.2187032180418426e-05,
"loss": 4.157,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.2178646232907906e-05,
"loss": 4.1535,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.2170260285397386e-05,
"loss": 4.154,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.2161890716690595e-05,
"loss": 4.1618,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.2153504769180075e-05,
"loss": 4.1683,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.2145118821669555e-05,
"loss": 4.1635,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.2136732874159035e-05,
"loss": 4.1594,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.212834692664851e-05,
"loss": 4.1645,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.211996097913799e-05,
"loss": 4.1617,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.211157503162747e-05,
"loss": 4.1655,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.210320546292068e-05,
"loss": 4.159,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.2094819515410164e-05,
"loss": 4.1383,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.2086433567899644e-05,
"loss": 4.1816,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.2078047620389124e-05,
"loss": 4.1648,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.2069661672878604e-05,
"loss": 4.174,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.2061275725368084e-05,
"loss": 4.1585,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.2052889777857564e-05,
"loss": 4.1609,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.204452020915077e-05,
"loss": 4.1557,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.203613426164025e-05,
"loss": 4.1574,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.202774831412973e-05,
"loss": 4.1609,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.201936236661921e-05,
"loss": 4.1534,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.201097641910869e-05,
"loss": 4.1777,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.200259047159817e-05,
"loss": 4.1534,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.199422090289138e-05,
"loss": 4.1431,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.198583495538086e-05,
"loss": 4.1693,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.197744900787035e-05,
"loss": 4.1401,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.196906306035983e-05,
"loss": 4.142,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196067711284931e-05,
"loss": 4.1672,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195230754414252e-05,
"loss": 4.1631,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.1943921596632e-05,
"loss": 4.1469,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.193553564912148e-05,
"loss": 4.1579,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.192714970161096e-05,
"loss": 4.1331,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.191876375410044e-05,
"loss": 4.1518,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.191037780658992e-05,
"loss": 4.1553,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.1902024616686856e-05,
"loss": 4.152,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.1893638669176336e-05,
"loss": 4.1569,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.1885252721665816e-05,
"loss": 4.1602,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.18768667741553e-05,
"loss": 4.169,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.186848082664478e-05,
"loss": 4.1486,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.186009487913426e-05,
"loss": 4.1509,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.185172531042747e-05,
"loss": 4.162,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.184333936291695e-05,
"loss": 4.1437,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.183495341540643e-05,
"loss": 4.1585,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.182656746789591e-05,
"loss": 4.1521,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.181818152038539e-05,
"loss": 4.1471,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.180979557287487e-05,
"loss": 4.167,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.1801409625364344e-05,
"loss": 4.1391,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.1793023677853824e-05,
"loss": 4.1433,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.1784637730343304e-05,
"loss": 4.1539,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.1776251782832784e-05,
"loss": 4.1565,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.1767865835322264e-05,
"loss": 4.1476,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.175949626661548e-05,
"loss": 4.1552,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.175111031910496e-05,
"loss": 4.1362,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.174272437159444e-05,
"loss": 4.1453,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.173433842408392e-05,
"loss": 4.1432,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.17259524765734e-05,
"loss": 4.1509,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.171758290786661e-05,
"loss": 4.1618,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.170919696035609e-05,
"loss": 4.1488,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.170081101284557e-05,
"loss": 4.1536,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.169244144413878e-05,
"loss": 4.1436,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.168405549662826e-05,
"loss": 4.1421,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.167566954911774e-05,
"loss": 4.1454,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.166728360160722e-05,
"loss": 4.1586,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.1658897654096704e-05,
"loss": 4.1508,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.1650511706586184e-05,
"loss": 4.1529,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.1642125759075664e-05,
"loss": 4.1399,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.1633739811565144e-05,
"loss": 4.1527,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.1625370242858353e-05,
"loss": 4.1388,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.161698429534783e-05,
"loss": 4.1481,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.160861472664104e-05,
"loss": 4.1339,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.160022877913052e-05,
"loss": 4.1504,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.159184283162e-05,
"loss": 4.1373,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.158345688410948e-05,
"loss": 4.1451,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.157507093659896e-05,
"loss": 4.1356,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.156668498908844e-05,
"loss": 4.1458,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.155829904157792e-05,
"loss": 4.1407,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.15499130940674e-05,
"loss": 4.1369,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.154154352536062e-05,
"loss": 4.1557,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.15331575778501e-05,
"loss": 4.1557,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.152478800914331e-05,
"loss": 4.1507,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.151640206163279e-05,
"loss": 4.1453,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.150801611412227e-05,
"loss": 4.135,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.149963016661175e-05,
"loss": 4.1399,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.149124421910123e-05,
"loss": 4.1459,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.14828582715907e-05,
"loss": 4.1475,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.147447232408018e-05,
"loss": 4.1301,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.1466102755373396e-05,
"loss": 4.1463,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.1457716807862876e-05,
"loss": 4.1434,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.1449330860352356e-05,
"loss": 4.142,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.1440944912841836e-05,
"loss": 4.139,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.1432558965331316e-05,
"loss": 4.1439,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.1424173017820796e-05,
"loss": 4.1343,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.1415787070310276e-05,
"loss": 4.1519,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.1407401122799756e-05,
"loss": 4.1482,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.1399031554092965e-05,
"loss": 4.1479,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.1390645606582445e-05,
"loss": 4.1306,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.1382276037875654e-05,
"loss": 4.1472,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.1373890090365134e-05,
"loss": 4.1461,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.1365504142854614e-05,
"loss": 4.1374,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.1357118195344094e-05,
"loss": 4.145,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.134873224783358e-05,
"loss": 4.1437,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.134034630032306e-05,
"loss": 4.1427,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.133196035281254e-05,
"loss": 4.1555,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.132357440530202e-05,
"loss": 4.135,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.131520483659523e-05,
"loss": 4.1451,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.130681888908471e-05,
"loss": 4.1441,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.129844932037792e-05,
"loss": 4.1411,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.12900633728674e-05,
"loss": 4.1328,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.128167742535688e-05,
"loss": 4.1311,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.127329147784636e-05,
"loss": 4.1361,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.126490553033584e-05,
"loss": 4.1326,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.125651958282532e-05,
"loss": 4.143,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 4.140775680541992,
"eval_runtime": 316.591,
"eval_samples_per_second": 1205.312,
"eval_steps_per_second": 37.667,
"step": 534240
},
{
"epoch": 1.0,
"learning_rate": 4.1248150014118534e-05,
"loss": 4.1417,
"step": 534528
},
{
"epoch": 1.0,
"learning_rate": 4.1239764066608014e-05,
"loss": 4.1287,
"step": 535040
},
{
"epoch": 1.0,
"learning_rate": 4.1231378119097494e-05,
"loss": 4.1423,
"step": 535552
},
{
"epoch": 1.0,
"learning_rate": 4.12230085503907e-05,
"loss": 4.1393,
"step": 536064
},
{
"epoch": 1.0,
"learning_rate": 4.121462260288018e-05,
"loss": 4.1463,
"step": 536576
},
{
"epoch": 1.0,
"learning_rate": 4.120623665536966e-05,
"loss": 4.1365,
"step": 537088
},
{
"epoch": 1.0,
"learning_rate": 4.119785070785914e-05,
"loss": 4.143,
"step": 537600
},
{
"epoch": 1.0,
"learning_rate": 4.118946476034862e-05,
"loss": 4.1267,
"step": 538112
},
{
"epoch": 1.0,
"learning_rate": 4.11810788128381e-05,
"loss": 4.1276,
"step": 538624
},
{
"epoch": 1.0,
"learning_rate": 4.117269286532758e-05,
"loss": 4.1427,
"step": 539136
},
{
"epoch": 1.0,
"learning_rate": 4.116432329662079e-05,
"loss": 4.1376,
"step": 539648
},
{
"epoch": 1.0,
"learning_rate": 4.115593734911027e-05,
"loss": 4.1321,
"step": 540160
},
{
"epoch": 1.0,
"learning_rate": 4.114756778040348e-05,
"loss": 4.1406,
"step": 540672
},
{
"epoch": 1.0,
"learning_rate": 4.113918183289297e-05,
"loss": 4.1296,
"step": 541184
},
{
"epoch": 1.0,
"learning_rate": 4.113079588538245e-05,
"loss": 4.1287,
"step": 541696
},
{
"epoch": 1.0,
"learning_rate": 4.112240993787193e-05,
"loss": 4.122,
"step": 542208
},
{
"epoch": 1.0,
"learning_rate": 4.111402399036141e-05,
"loss": 4.1308,
"step": 542720
},
{
"epoch": 1.0,
"learning_rate": 4.110563804285089e-05,
"loss": 4.1352,
"step": 543232
},
{
"epoch": 1.0,
"learning_rate": 4.109725209534036e-05,
"loss": 4.1277,
"step": 543744
},
{
"epoch": 1.0,
"learning_rate": 4.108886614782984e-05,
"loss": 4.1447,
"step": 544256
},
{
"epoch": 1.0,
"learning_rate": 4.108048020031932e-05,
"loss": 4.1411,
"step": 544768
},
{
"epoch": 1.0,
"learning_rate": 4.10720942528088e-05,
"loss": 4.142,
"step": 545280
},
{
"epoch": 1.0,
"learning_rate": 4.106370830529828e-05,
"loss": 4.1307,
"step": 545792
},
{
"epoch": 1.0,
"learning_rate": 4.105532235778776e-05,
"loss": 4.133,
"step": 546304
},
{
"epoch": 1.0,
"learning_rate": 4.104693641027724e-05,
"loss": 4.1378,
"step": 546816
},
{
"epoch": 1.0,
"learning_rate": 4.103855046276672e-05,
"loss": 4.1356,
"step": 547328
},
{
"epoch": 1.0,
"learning_rate": 4.10301645152562e-05,
"loss": 4.1276,
"step": 547840
},
{
"epoch": 1.0,
"learning_rate": 4.102177856774568e-05,
"loss": 4.1306,
"step": 548352
},
{
"epoch": 1.0,
"learning_rate": 4.1013408999038896e-05,
"loss": 4.1221,
"step": 548864
},
{
"epoch": 1.0,
"learning_rate": 4.1005023051528376e-05,
"loss": 4.1307,
"step": 549376
},
{
"epoch": 1.01,
"learning_rate": 4.0996637104017856e-05,
"loss": 4.1316,
"step": 549888
},
{
"epoch": 1.01,
"learning_rate": 4.0988267535311065e-05,
"loss": 4.136,
"step": 550400
},
{
"epoch": 1.01,
"learning_rate": 4.0979881587800545e-05,
"loss": 4.1381,
"step": 550912
},
{
"epoch": 1.01,
"learning_rate": 4.0971495640290025e-05,
"loss": 4.1356,
"step": 551424
},
{
"epoch": 1.01,
"learning_rate": 4.0963109692779505e-05,
"loss": 4.1327,
"step": 551936
},
{
"epoch": 1.01,
"learning_rate": 4.0954740124072714e-05,
"loss": 4.1321,
"step": 552448
},
{
"epoch": 1.01,
"learning_rate": 4.0946354176562194e-05,
"loss": 4.1379,
"step": 552960
},
{
"epoch": 1.01,
"learning_rate": 4.0937968229051674e-05,
"loss": 4.1217,
"step": 553472
},
{
"epoch": 1.01,
"learning_rate": 4.0929582281541154e-05,
"loss": 4.119,
"step": 553984
},
{
"epoch": 1.01,
"learning_rate": 4.0921196334030634e-05,
"loss": 4.1162,
"step": 554496
},
{
"epoch": 1.01,
"learning_rate": 4.091281038652012e-05,
"loss": 4.1247,
"step": 555008
},
{
"epoch": 1.01,
"learning_rate": 4.09044244390096e-05,
"loss": 4.1261,
"step": 555520
},
{
"epoch": 1.01,
"learning_rate": 4.089605487030281e-05,
"loss": 4.129,
"step": 556032
},
{
"epoch": 1.01,
"learning_rate": 4.088768530159602e-05,
"loss": 4.1246,
"step": 556544
},
{
"epoch": 1.01,
"learning_rate": 4.08792993540855e-05,
"loss": 4.1246,
"step": 557056
},
{
"epoch": 1.01,
"learning_rate": 4.087091340657498e-05,
"loss": 4.1281,
"step": 557568
},
{
"epoch": 1.01,
"learning_rate": 4.086252745906446e-05,
"loss": 4.1333,
"step": 558080
},
{
"epoch": 1.01,
"learning_rate": 4.085414151155394e-05,
"loss": 4.1204,
"step": 558592
},
{
"epoch": 1.01,
"learning_rate": 4.084575556404342e-05,
"loss": 4.1021,
"step": 559104
},
{
"epoch": 1.01,
"learning_rate": 4.08373696165329e-05,
"loss": 4.1401,
"step": 559616
},
{
"epoch": 1.01,
"learning_rate": 4.082898366902237e-05,
"loss": 4.1307,
"step": 560128
},
{
"epoch": 1.01,
"learning_rate": 4.082059772151186e-05,
"loss": 4.1378,
"step": 560640
},
{
"epoch": 1.01,
"learning_rate": 4.081221177400134e-05,
"loss": 4.124,
"step": 561152
},
{
"epoch": 1.01,
"learning_rate": 4.080382582649082e-05,
"loss": 4.1241,
"step": 561664
},
{
"epoch": 1.01,
"learning_rate": 4.07954398789803e-05,
"loss": 4.1214,
"step": 562176
},
{
"epoch": 1.01,
"learning_rate": 4.078705393146978e-05,
"loss": 4.12,
"step": 562688
},
{
"epoch": 1.01,
"learning_rate": 4.077868436276299e-05,
"loss": 4.1286,
"step": 563200
},
{
"epoch": 1.01,
"learning_rate": 4.077029841525247e-05,
"loss": 4.1117,
"step": 563712
},
{
"epoch": 1.01,
"learning_rate": 4.076191246774195e-05,
"loss": 4.1438,
"step": 564224
},
{
"epoch": 1.01,
"learning_rate": 4.075352652023143e-05,
"loss": 4.1244,
"step": 564736
},
{
"epoch": 1.01,
"learning_rate": 4.0745156951524636e-05,
"loss": 4.1029,
"step": 565248
},
{
"epoch": 1.01,
"learning_rate": 4.0736771004014116e-05,
"loss": 4.1332,
"step": 565760
},
{
"epoch": 1.01,
"learning_rate": 4.0728385056503596e-05,
"loss": 4.1073,
"step": 566272
},
{
"epoch": 1.01,
"learning_rate": 4.0719999108993076e-05,
"loss": 4.1069,
"step": 566784
},
{
"epoch": 1.01,
"learning_rate": 4.071162954028629e-05,
"loss": 4.1324,
"step": 567296
},
{
"epoch": 1.01,
"learning_rate": 4.070324359277577e-05,
"loss": 4.1248,
"step": 567808
},
{
"epoch": 1.01,
"learning_rate": 4.069489040287272e-05,
"loss": 4.1125,
"step": 568320
},
{
"epoch": 1.01,
"learning_rate": 4.06865044553622e-05,
"loss": 4.1215,
"step": 568832
},
{
"epoch": 1.01,
"learning_rate": 4.067811850785167e-05,
"loss": 4.1015,
"step": 569344
},
{
"epoch": 1.01,
"learning_rate": 4.066973256034115e-05,
"loss": 4.114,
"step": 569856
},
{
"epoch": 1.01,
"learning_rate": 4.066134661283063e-05,
"loss": 4.1206,
"step": 570368
},
{
"epoch": 1.01,
"learning_rate": 4.065296066532011e-05,
"loss": 4.1155,
"step": 570880
},
{
"epoch": 1.01,
"learning_rate": 4.064457471780959e-05,
"loss": 4.1235,
"step": 571392
},
{
"epoch": 1.01,
"learning_rate": 4.063618877029907e-05,
"loss": 4.1219,
"step": 571904
},
{
"epoch": 1.01,
"learning_rate": 4.062780282278855e-05,
"loss": 4.1324,
"step": 572416
},
{
"epoch": 1.01,
"learning_rate": 4.0619433254081766e-05,
"loss": 4.1142,
"step": 572928
},
{
"epoch": 1.01,
"learning_rate": 4.0611047306571246e-05,
"loss": 4.1181,
"step": 573440
},
{
"epoch": 1.01,
"learning_rate": 4.0602661359060726e-05,
"loss": 4.1258,
"step": 573952
},
{
"epoch": 1.01,
"learning_rate": 4.0594275411550206e-05,
"loss": 4.111,
"step": 574464
},
{
"epoch": 1.01,
"learning_rate": 4.0585889464039686e-05,
"loss": 4.1241,
"step": 574976
},
{
"epoch": 1.01,
"learning_rate": 4.0577503516529166e-05,
"loss": 4.1195,
"step": 575488
},
{
"epoch": 1.01,
"learning_rate": 4.0569117569018645e-05,
"loss": 4.1111,
"step": 576000
},
{
"epoch": 1.01,
"learning_rate": 4.0560748000311855e-05,
"loss": 4.1322,
"step": 576512
},
{
"epoch": 1.01,
"learning_rate": 4.0552362052801335e-05,
"loss": 4.1051,
"step": 577024
},
{
"epoch": 1.01,
"learning_rate": 4.0543976105290814e-05,
"loss": 4.1079,
"step": 577536
},
{
"epoch": 1.01,
"learning_rate": 4.0535590157780294e-05,
"loss": 4.1231,
"step": 578048
},
{
"epoch": 1.01,
"learning_rate": 4.0527204210269774e-05,
"loss": 4.1199,
"step": 578560
},
{
"epoch": 1.01,
"learning_rate": 4.0518818262759254e-05,
"loss": 4.1132,
"step": 579072
},
{
"epoch": 1.01,
"learning_rate": 4.0510448694052463e-05,
"loss": 4.124,
"step": 579584
},
{
"epoch": 1.02,
"learning_rate": 4.0502062746541943e-05,
"loss": 4.1017,
"step": 580096
},
{
"epoch": 1.02,
"learning_rate": 4.049367679903143e-05,
"loss": 4.108,
"step": 580608
},
{
"epoch": 1.02,
"learning_rate": 4.048529085152091e-05,
"loss": 4.1117,
"step": 581120
},
{
"epoch": 1.02,
"learning_rate": 4.047692128281412e-05,
"loss": 4.1137,
"step": 581632
},
{
"epoch": 1.02,
"learning_rate": 4.04685353353036e-05,
"loss": 4.1303,
"step": 582144
},
{
"epoch": 1.02,
"learning_rate": 4.046016576659681e-05,
"loss": 4.1158,
"step": 582656
},
{
"epoch": 1.02,
"learning_rate": 4.045177981908629e-05,
"loss": 4.1205,
"step": 583168
},
{
"epoch": 1.02,
"learning_rate": 4.044339387157577e-05,
"loss": 4.1094,
"step": 583680
},
{
"epoch": 1.02,
"learning_rate": 4.043500792406525e-05,
"loss": 4.1086,
"step": 584192
},
{
"epoch": 1.02,
"learning_rate": 4.042663835535846e-05,
"loss": 4.1131,
"step": 584704
},
{
"epoch": 1.02,
"learning_rate": 4.041825240784794e-05,
"loss": 4.1211,
"step": 585216
},
{
"epoch": 1.02,
"learning_rate": 4.040986646033742e-05,
"loss": 4.1181,
"step": 585728
},
{
"epoch": 1.02,
"learning_rate": 4.04014805128269e-05,
"loss": 4.1204,
"step": 586240
},
{
"epoch": 1.02,
"learning_rate": 4.0393094565316384e-05,
"loss": 4.1099,
"step": 586752
},
{
"epoch": 1.02,
"learning_rate": 4.038470861780586e-05,
"loss": 4.1142,
"step": 587264
},
{
"epoch": 1.02,
"learning_rate": 4.037632267029534e-05,
"loss": 4.1105,
"step": 587776
},
{
"epoch": 1.02,
"learning_rate": 4.036793672278482e-05,
"loss": 4.11,
"step": 588288
},
{
"epoch": 1.02,
"learning_rate": 4.035956715407803e-05,
"loss": 4.1002,
"step": 588800
},
{
"epoch": 1.02,
"learning_rate": 4.0351181206567506e-05,
"loss": 4.1195,
"step": 589312
},
{
"epoch": 1.02,
"learning_rate": 4.0342795259056986e-05,
"loss": 4.1032,
"step": 589824
},
{
"epoch": 1.02,
"learning_rate": 4.0334409311546466e-05,
"loss": 4.1105,
"step": 590336
},
{
"epoch": 1.02,
"learning_rate": 4.032603974283968e-05,
"loss": 4.103,
"step": 590848
},
{
"epoch": 1.02,
"learning_rate": 4.0317653795329155e-05,
"loss": 4.1112,
"step": 591360
},
{
"epoch": 1.02,
"learning_rate": 4.0309267847818635e-05,
"loss": 4.108,
"step": 591872
},
{
"epoch": 1.02,
"learning_rate": 4.030088190030812e-05,
"loss": 4.1047,
"step": 592384
},
{
"epoch": 1.02,
"learning_rate": 4.02924959527976e-05,
"loss": 4.118,
"step": 592896
},
{
"epoch": 1.02,
"learning_rate": 4.028411000528708e-05,
"loss": 4.1236,
"step": 593408
},
{
"epoch": 1.02,
"learning_rate": 4.027572405777656e-05,
"loss": 4.1225,
"step": 593920
},
{
"epoch": 1.02,
"learning_rate": 4.026733811026604e-05,
"loss": 4.1101,
"step": 594432
},
{
"epoch": 1.02,
"learning_rate": 4.025896854155925e-05,
"loss": 4.1033,
"step": 594944
},
{
"epoch": 1.02,
"learning_rate": 4.025058259404873e-05,
"loss": 4.1072,
"step": 595456
},
{
"epoch": 1.02,
"learning_rate": 4.024221302534194e-05,
"loss": 4.1141,
"step": 595968
},
{
"epoch": 1.02,
"learning_rate": 4.023382707783142e-05,
"loss": 4.1156,
"step": 596480
},
{
"epoch": 1.02,
"learning_rate": 4.02254411303209e-05,
"loss": 4.0974,
"step": 596992
},
{
"epoch": 1.02,
"learning_rate": 4.021705518281038e-05,
"loss": 4.1154,
"step": 597504
},
{
"epoch": 1.02,
"learning_rate": 4.020866923529986e-05,
"loss": 4.1131,
"step": 598016
},
{
"epoch": 1.02,
"learning_rate": 4.0200299666593075e-05,
"loss": 4.1072,
"step": 598528
},
{
"epoch": 1.02,
"learning_rate": 4.0191913719082555e-05,
"loss": 4.1076,
"step": 599040
},
{
"epoch": 1.02,
"learning_rate": 4.0183527771572035e-05,
"loss": 4.1138,
"step": 599552
},
{
"epoch": 1.02,
"learning_rate": 4.0175141824061515e-05,
"loss": 4.1026,
"step": 600064
},
{
"epoch": 1.02,
"learning_rate": 4.0166755876550995e-05,
"loss": 4.1176,
"step": 600576
},
{
"epoch": 1.02,
"learning_rate": 4.0158369929040475e-05,
"loss": 4.1124,
"step": 601088
},
{
"epoch": 1.02,
"learning_rate": 4.0149983981529955e-05,
"loss": 4.1178,
"step": 601600
},
{
"epoch": 1.02,
"learning_rate": 4.0141598034019435e-05,
"loss": 4.0979,
"step": 602112
},
{
"epoch": 1.02,
"learning_rate": 4.013324484411637e-05,
"loss": 4.1156,
"step": 602624
},
{
"epoch": 1.02,
"learning_rate": 4.012485889660585e-05,
"loss": 4.1152,
"step": 603136
},
{
"epoch": 1.02,
"learning_rate": 4.011647294909533e-05,
"loss": 4.1071,
"step": 603648
},
{
"epoch": 1.02,
"learning_rate": 4.010808700158481e-05,
"loss": 4.1118,
"step": 604160
},
{
"epoch": 1.02,
"learning_rate": 4.009970105407429e-05,
"loss": 4.1095,
"step": 604672
},
{
"epoch": 1.02,
"learning_rate": 4.009131510656377e-05,
"loss": 4.1128,
"step": 605184
},
{
"epoch": 1.02,
"learning_rate": 4.008292915905325e-05,
"loss": 4.1261,
"step": 605696
},
{
"epoch": 1.02,
"learning_rate": 4.007454321154274e-05,
"loss": 4.1004,
"step": 606208
},
{
"epoch": 1.02,
"learning_rate": 4.006615726403222e-05,
"loss": 4.1157,
"step": 606720
},
{
"epoch": 1.02,
"learning_rate": 4.005777131652169e-05,
"loss": 4.1115,
"step": 607232
},
{
"epoch": 1.02,
"learning_rate": 4.004938536901117e-05,
"loss": 4.1086,
"step": 607744
},
{
"epoch": 1.02,
"learning_rate": 4.004101580030439e-05,
"loss": 4.1027,
"step": 608256
},
{
"epoch": 1.02,
"learning_rate": 4.003262985279387e-05,
"loss": 4.0967,
"step": 608768
},
{
"epoch": 1.02,
"learning_rate": 4.002424390528334e-05,
"loss": 4.1068,
"step": 609280
},
{
"epoch": 1.02,
"learning_rate": 4.001585795777282e-05,
"loss": 4.098,
"step": 609792
},
{
"epoch": 1.02,
"learning_rate": 4.00074720102623e-05,
"loss": 4.1105,
"step": 610304
},
{
"epoch": 1.03,
"eval_loss": 4.117621898651123,
"eval_runtime": 335.8472,
"eval_samples_per_second": 1136.204,
"eval_steps_per_second": 35.507,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.999908606275178e-05,
"loss": 4.1061,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.999070011524126e-05,
"loss": 4.1014,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.998231416773074e-05,
"loss": 4.11,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.997392822022022e-05,
"loss": 4.1081,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.996554227270971e-05,
"loss": 4.1149,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.995715632519919e-05,
"loss": 4.1058,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.994877037768867e-05,
"loss": 4.1135,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.994038443017815e-05,
"loss": 4.096,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.993199848266763e-05,
"loss": 4.0979,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.992361253515711e-05,
"loss": 4.1126,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.991522658764658e-05,
"loss": 4.1064,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.990684064013606e-05,
"loss": 4.1018,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.989847107142928e-05,
"loss": 4.1096,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.989008512391876e-05,
"loss": 4.0973,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.988169917640823e-05,
"loss": 4.1002,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.987331322889771e-05,
"loss": 4.0865,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.986492728138719e-05,
"loss": 4.1016,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.985654133387668e-05,
"loss": 4.1093,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.984815538636616e-05,
"loss": 4.0949,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.983976943885564e-05,
"loss": 4.1127,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.983138349134512e-05,
"loss": 4.1116,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.9822997543834597e-05,
"loss": 4.1101,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.9814611596324077e-05,
"loss": 4.1032,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.9806225648813557e-05,
"loss": 4.1052,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.9797856080106766e-05,
"loss": 4.1051,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.9789486511399975e-05,
"loss": 4.1058,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.9781100563889455e-05,
"loss": 4.0955,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.9772714616378935e-05,
"loss": 4.103,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.9764328668868415e-05,
"loss": 4.0932,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.9755942721357895e-05,
"loss": 4.0982,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.9747556773847374e-05,
"loss": 4.1029,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.973917082633686e-05,
"loss": 4.1029,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.973078487882634e-05,
"loss": 4.1093,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.972239893131582e-05,
"loss": 4.1106,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971402936260903e-05,
"loss": 4.0959,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.970565979390224e-05,
"loss": 4.1033,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.969727384639172e-05,
"loss": 4.1077,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.96888878988812e-05,
"loss": 4.0892,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.968050195137068e-05,
"loss": 4.0907,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.967211600386016e-05,
"loss": 4.0904,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.966373005634964e-05,
"loss": 4.0893,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.965534410883912e-05,
"loss": 4.0999,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.96469581613286e-05,
"loss": 4.1001,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.963858859262181e-05,
"loss": 4.0935,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.9630202645111295e-05,
"loss": 4.0947,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.962181669760077e-05,
"loss": 4.096,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.961343075009025e-05,
"loss": 4.1055,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.960504480257973e-05,
"loss": 4.0878,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.9596675233872944e-05,
"loss": 4.0767,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.958828928636242e-05,
"loss": 4.1071,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.957991971765563e-05,
"loss": 4.0998,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.957153377014511e-05,
"loss": 4.1076,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.956314782263459e-05,
"loss": 4.0938,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.9554761875124066e-05,
"loss": 4.0928,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.9546375927613546e-05,
"loss": 4.0929,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.953798998010303e-05,
"loss": 4.0918,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.952960403259251e-05,
"loss": 4.0991,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.952121808508199e-05,
"loss": 4.0824,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.951286489517894e-05,
"loss": 4.1175,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.950447894766842e-05,
"loss": 4.0911,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.949609300015789e-05,
"loss": 4.0737,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.948770705264737e-05,
"loss": 4.104,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.947932110513685e-05,
"loss": 4.0833,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.947093515762633e-05,
"loss": 4.0754,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.946254921011581e-05,
"loss": 4.0997,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.945416326260529e-05,
"loss": 4.097,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.94457936938985e-05,
"loss": 4.087,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.9437424125191715e-05,
"loss": 4.0887,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.9429038177681195e-05,
"loss": 4.0709,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.9420652230170675e-05,
"loss": 4.0832,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.9412266282660155e-05,
"loss": 4.0934,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.9403880335149635e-05,
"loss": 4.0874,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.9395494387639115e-05,
"loss": 4.0917,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.9387124818932324e-05,
"loss": 4.089,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.9378738871421804e-05,
"loss": 4.1035,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.937036930271501e-05,
"loss": 4.0868,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.936198335520449e-05,
"loss": 4.0887,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.935359740769397e-05,
"loss": 4.0942,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.934521146018345e-05,
"loss": 4.0854,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.933682551267294e-05,
"loss": 4.095,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.932843956516242e-05,
"loss": 4.0893,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.93200536176519e-05,
"loss": 4.0856,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.931166767014138e-05,
"loss": 4.1013,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.930329810143459e-05,
"loss": 4.0769,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.929491215392407e-05,
"loss": 4.0814,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.928652620641355e-05,
"loss": 4.0914,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.927814025890303e-05,
"loss": 4.0908,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.926975431139251e-05,
"loss": 4.0797,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.926136836388199e-05,
"loss": 4.0948,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.92529987951752e-05,
"loss": 4.0797,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.924461284766468e-05,
"loss": 4.079,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.923622690015416e-05,
"loss": 4.079,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.922784095264364e-05,
"loss": 4.0862,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.9219455005133124e-05,
"loss": 4.1004,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.9211085436426334e-05,
"loss": 4.0873,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.9202699488915813e-05,
"loss": 4.0903,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.9194313541405293e-05,
"loss": 4.082,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.918592759389477e-05,
"loss": 4.0797,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.917755802518798e-05,
"loss": 4.0829,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.916917207767746e-05,
"loss": 4.0935,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.916078613016694e-05,
"loss": 4.0897,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.915240018265642e-05,
"loss": 4.088,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.9144014235145896e-05,
"loss": 4.0884,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.9135628287635375e-05,
"loss": 4.0845,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.912724234012486e-05,
"loss": 4.0821,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.911885639261434e-05,
"loss": 4.0824,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.911048682390755e-05,
"loss": 4.0736,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.9102133634004496e-05,
"loss": 4.0884,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.9093747686493976e-05,
"loss": 4.0765,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.9085361738983456e-05,
"loss": 4.0809,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.9076975791472936e-05,
"loss": 4.0776,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.9068589843962416e-05,
"loss": 4.0797,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.9060203896451896e-05,
"loss": 4.0819,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.905181794894137e-05,
"loss": 4.0774,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.904343200143085e-05,
"loss": 4.0959,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.903504605392033e-05,
"loss": 4.0924,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.9026660106409816e-05,
"loss": 4.0918,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.9018274158899296e-05,
"loss": 4.0825,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.9009888211388776e-05,
"loss": 4.08,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.9001518642681985e-05,
"loss": 4.078,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.8993132695171465e-05,
"loss": 4.0868,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.8984746747660945e-05,
"loss": 4.0901,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.8976360800150425e-05,
"loss": 4.0717,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.8967991231443634e-05,
"loss": 4.0837,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.8959605283933114e-05,
"loss": 4.0834,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.8951219336422594e-05,
"loss": 4.082,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.8942833388912074e-05,
"loss": 4.0769,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.8934447441401554e-05,
"loss": 4.0844,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.8926061493891034e-05,
"loss": 4.0742,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.8917675546380514e-05,
"loss": 4.0911,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.8909289598869994e-05,
"loss": 4.0843,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.890090365135948e-05,
"loss": 4.0945,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.889255046145642e-05,
"loss": 4.0729,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.88841645139459e-05,
"loss": 4.0841,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.887579494523911e-05,
"loss": 4.0897,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.886740899772859e-05,
"loss": 4.0811,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.885902305021807e-05,
"loss": 4.0816,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.885063710270755e-05,
"loss": 4.084,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884225115519703e-05,
"loss": 4.082,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.883386520768651e-05,
"loss": 4.0988,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.882547926017599e-05,
"loss": 4.0771,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.881709331266547e-05,
"loss": 4.0878,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.880870736515495e-05,
"loss": 4.0858,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.8800321417644434e-05,
"loss": 4.0809,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.8791935470133914e-05,
"loss": 4.074,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.878354952262339e-05,
"loss": 4.0708,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.87751799539166e-05,
"loss": 4.0765,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.876679400640608e-05,
"loss": 4.0785,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.875842443769929e-05,
"loss": 4.081,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 4.097553253173828,
"eval_runtime": 300.4264,
"eval_samples_per_second": 1270.165,
"eval_steps_per_second": 39.694,
"step": 686880
},
{
"epoch": 1.0,
"learning_rate": 3.875003849018877e-05,
"loss": 4.0787,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.874165254267825e-05,
"loss": 4.0747,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.873326659516773e-05,
"loss": 4.0784,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.8724880647657205e-05,
"loss": 4.0859,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.8716494700146685e-05,
"loss": 4.0915,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.870810875263617e-05,
"loss": 4.0796,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.869972280512565e-05,
"loss": 4.0827,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.869135323641886e-05,
"loss": 4.0713,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.868296728890834e-05,
"loss": 4.0719,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.867458134139782e-05,
"loss": 4.082,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.86661953938873e-05,
"loss": 4.0818,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.865780944637678e-05,
"loss": 4.0751,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.8649456256473726e-05,
"loss": 4.0847,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.8641070308963206e-05,
"loss": 4.0724,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.8632700740256415e-05,
"loss": 4.0727,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.8624314792745895e-05,
"loss": 4.0577,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.8615928845235375e-05,
"loss": 4.0801,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.8607542897724855e-05,
"loss": 4.0811,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.8599156950214334e-05,
"loss": 4.0672,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.8590771002703814e-05,
"loss": 4.0833,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.8582385055193294e-05,
"loss": 4.0839,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.8573999107682774e-05,
"loss": 4.0853,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.8565613160172254e-05,
"loss": 4.0784,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.8557227212661734e-05,
"loss": 4.0792,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.8548841265151214e-05,
"loss": 4.0756,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.8540455317640694e-05,
"loss": 4.0836,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.8532069370130174e-05,
"loss": 4.0637,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.852369980142338e-05,
"loss": 4.0768,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.851531385391286e-05,
"loss": 4.0655,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.850692790640234e-05,
"loss": 4.0735,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.849854195889182e-05,
"loss": 4.0771,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.849015601138131e-05,
"loss": 4.0798,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.848178644267452e-05,
"loss": 4.076,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.8473400495164e-05,
"loss": 4.0884,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.846501454765348e-05,
"loss": 4.072,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.845664497894669e-05,
"loss": 4.0782,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.84482754102399e-05,
"loss": 4.0828,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.843988946272938e-05,
"loss": 4.06,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.843150351521886e-05,
"loss": 4.0668,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.842311756770834e-05,
"loss": 4.0664,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.841473162019782e-05,
"loss": 4.0614,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.84063456726873e-05,
"loss": 4.0724,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.839795972517678e-05,
"loss": 4.0785,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.838957377766626e-05,
"loss": 4.0638,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.8381187830155743e-05,
"loss": 4.0714,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.837281826144895e-05,
"loss": 4.0692,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.836443231393843e-05,
"loss": 4.0758,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.835604636642791e-05,
"loss": 4.0617,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.834766041891739e-05,
"loss": 4.0522,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.8339274471406866e-05,
"loss": 4.0818,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.8330888523896346e-05,
"loss": 4.0753,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.832251895518956e-05,
"loss": 4.0874,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.831414938648277e-05,
"loss": 4.0662,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.830576343897225e-05,
"loss": 4.0665,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.829737749146173e-05,
"loss": 4.0695,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.828899154395121e-05,
"loss": 4.0638,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.82806055964407e-05,
"loss": 4.0777,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.827221964893017e-05,
"loss": 4.0533,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.8263850080223386e-05,
"loss": 4.0944,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.8255464132712866e-05,
"loss": 4.0684,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.824707818520234e-05,
"loss": 4.0471,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.823869223769182e-05,
"loss": 4.0744,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.82303062901813e-05,
"loss": 4.062,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.822192034267078e-05,
"loss": 4.0501,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.821353439516026e-05,
"loss": 4.0732,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.820514844764974e-05,
"loss": 4.0765,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.819676250013922e-05,
"loss": 4.0584,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.81883765526287e-05,
"loss": 4.0679,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.817999060511818e-05,
"loss": 4.0448,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.8171621036411395e-05,
"loss": 4.0592,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.8163235088900875e-05,
"loss": 4.0661,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.8154849141390355e-05,
"loss": 4.06,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.8146463193879835e-05,
"loss": 4.0727,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.8138077246369315e-05,
"loss": 4.0607,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.8129707677662524e-05,
"loss": 4.0818,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.8121321730152004e-05,
"loss": 4.0628,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.8112935782641484e-05,
"loss": 4.066,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.8104549835130964e-05,
"loss": 4.0676,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.8096163887620444e-05,
"loss": 4.06,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.8087777940109924e-05,
"loss": 4.0699,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.807940837140313e-05,
"loss": 4.0613,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.807102242389262e-05,
"loss": 4.0671,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.80626364763821e-05,
"loss": 4.072,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.805425052887158e-05,
"loss": 4.0614,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.804586458136105e-05,
"loss": 4.0503,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.803749501265427e-05,
"loss": 4.0638,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.802910906514375e-05,
"loss": 4.0704,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.802072311763323e-05,
"loss": 4.057,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.80123371701227e-05,
"loss": 4.068,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.800396760141592e-05,
"loss": 4.0555,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.79955816539054e-05,
"loss": 4.0565,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.798719570639488e-05,
"loss": 4.0561,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.797880975888436e-05,
"loss": 4.0621,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.797042381137384e-05,
"loss": 4.0735,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.796203786386332e-05,
"loss": 4.0648,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.79536519163528e-05,
"loss": 4.0671,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.794526596884228e-05,
"loss": 4.058,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.7936896400135486e-05,
"loss": 4.057,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.7928510452624966e-05,
"loss": 4.059,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.7920124505114446e-05,
"loss": 4.0671,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.7911738557603926e-05,
"loss": 4.0682,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.7903368988897135e-05,
"loss": 4.066,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.7894983041386615e-05,
"loss": 4.0633,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.7886597093876095e-05,
"loss": 4.058,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.7878211146365575e-05,
"loss": 4.0627,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.786984157765879e-05,
"loss": 4.0564,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.786145563014827e-05,
"loss": 4.0536,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.785306968263775e-05,
"loss": 4.0609,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.784468373512723e-05,
"loss": 4.0531,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.783629778761671e-05,
"loss": 4.0564,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.782791184010619e-05,
"loss": 4.0515,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.78195422713994e-05,
"loss": 4.0549,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.781115632388888e-05,
"loss": 4.0609,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.780277037637836e-05,
"loss": 4.0527,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.779438442886784e-05,
"loss": 4.0683,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.778599848135732e-05,
"loss": 4.0671,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.777762891265053e-05,
"loss": 4.0713,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.776924296514001e-05,
"loss": 4.0599,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.776085701762949e-05,
"loss": 4.0577,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.7752471070118975e-05,
"loss": 4.0531,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.7744101501412184e-05,
"loss": 4.0666,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.7735715553901664e-05,
"loss": 4.0626,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.7727329606391144e-05,
"loss": 4.0479,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.7718943658880624e-05,
"loss": 4.0603,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.7710557711370104e-05,
"loss": 4.0603,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.7702171763859584e-05,
"loss": 4.0604,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.769380219515279e-05,
"loss": 4.0548,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.768541624764227e-05,
"loss": 4.0587,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.767703030013175e-05,
"loss": 4.0518,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.766864435262123e-05,
"loss": 4.0698,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.766025840511071e-05,
"loss": 4.0603,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.765187245760019e-05,
"loss": 4.0688,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.764350288889341e-05,
"loss": 4.0515,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.763511694138289e-05,
"loss": 4.0631,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.762673099387236e-05,
"loss": 4.0665,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.761834504636184e-05,
"loss": 4.0538,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.760997547765506e-05,
"loss": 4.0587,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.760158953014454e-05,
"loss": 4.0594,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.759320358263401e-05,
"loss": 4.0639,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.758481763512349e-05,
"loss": 4.0701,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.757643168761297e-05,
"loss": 4.0577,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.756804574010245e-05,
"loss": 4.0613,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.755965979259193e-05,
"loss": 4.0639,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.755127384508141e-05,
"loss": 4.0584,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.75428878975709e-05,
"loss": 4.0538,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.7534518328864107e-05,
"loss": 4.0508,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.7526132381353586e-05,
"loss": 4.0527,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.7517746433843066e-05,
"loss": 4.0553,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.7509360486332546e-05,
"loss": 4.0578,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 4.081639766693115,
"eval_runtime": 296.2092,
"eval_samples_per_second": 1288.248,
"eval_steps_per_second": 40.259,
"step": 763200
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.093764494341568e+17,
"trial_name": null,
"trial_params": null
}