det-noun-lstm-2 / checkpoint-610560 /trainer_state.json
abhinavp's picture
Training in progress, epoch 0, checkpoint
c2f53d7 verified
{
"best_metric": 4.101009368896484,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/det-noun/lstm/2/checkpoints/checkpoint-610560",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 610560,
"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": 10.8216,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5604,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0668,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.999,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9512,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8869,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7317,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6248,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5301,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4596,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.4014,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3423,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2755,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.2058,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1542,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0875,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0564,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 5.9992,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9548,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984066699730012e-05,
"loss": 5.921,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8852,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 5.8459,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 5.8177,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.7829,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7633,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7281,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 5.7072,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 5.676,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6523,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6343,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6143,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 5.5968,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 5.5768,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5583,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5427,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 5.5264,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5112,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4832,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4788,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 5.439,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 5.4393,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 5.4291,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 5.4257,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 5.3887,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 5.3912,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 5.3806,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 5.3718,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.3694,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 5.3343,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3292,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3335,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 5.3224,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.3033,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2834,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.2885,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 5.2691,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 5.2891,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 5.2383,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 5.2493,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 5.2374,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 5.2352,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 5.2312,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2077,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.1907,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 5.1964,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2059,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.1761,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1756,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 5.1513,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 5.1521,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 5.1627,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 5.1606,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 5.1345,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388055134984274e-05,
"loss": 5.147,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 5.1447,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 5.134,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 5.1029,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 5.1099,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 5.0994,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 5.0918,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 5.0906,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 5.0855,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 5.087,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 5.0747,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 5.0577,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 5.0579,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 5.0578,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 5.0482,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 5.0441,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 5.0293,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.92455267849129e-05,
"loss": 5.0282,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.0182,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.0257,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 5.013,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 5.011,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.0087,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 4.9951,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 4.991,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.9818,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.9792,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.98,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.9626,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.9672,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.9631,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.9494,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.946,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111384382352036e-05,
"loss": 4.9413,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9388,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.9313,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.9328,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.9251,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9121,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.9256,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.9075,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.914,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.9065,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.9005,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901918809614751e-05,
"loss": 4.8972,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.8914,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.9066,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.893,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.8765,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.8732,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.87,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.8656,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.8584,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.8617,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893534499984604e-05,
"loss": 4.8471,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8471,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8421,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.8615,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.8528,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.8357,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.8335,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.8278,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.8382,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885990422985882e-05,
"loss": 4.8293,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515182823483e-05,
"loss": 4.8278,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.8235,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883476276613099e-05,
"loss": 4.8192,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882637681862047e-05,
"loss": 4.8152,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881799087110995e-05,
"loss": 4.8045,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880960492359943e-05,
"loss": 4.8117,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880121897608891e-05,
"loss": 4.802,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879283302857839e-05,
"loss": 4.79,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878444708106787e-05,
"loss": 4.802,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877606113355735e-05,
"loss": 4.7984,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876769156485057e-05,
"loss": 4.7985,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875930561734005e-05,
"loss": 4.7871,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.7846,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.7475996017456055,
"eval_runtime": 296.429,
"eval_samples_per_second": 1287.293,
"eval_steps_per_second": 40.229,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874255010112274e-05,
"loss": 4.7784,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873416415361222e-05,
"loss": 4.775,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.87257782061017e-05,
"loss": 4.788,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871739225859118e-05,
"loss": 4.7724,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709006311080657e-05,
"loss": 4.7751,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700620363570137e-05,
"loss": 4.7598,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692234416059616e-05,
"loss": 4.7737,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.7559,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.7576,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.755,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7629,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.7565,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.7374,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.7425,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.7336,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.7349,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.7358,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.7282,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.7318,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.7425,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.7282,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.7265,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.7191,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.7329,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.7028,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.716,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.7028,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.7057,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.7015,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.6946,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.7015,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.7093,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.6955,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.7016,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.685,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.6933,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844077064237013e-05,
"loss": 4.6781,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843238469485961e-05,
"loss": 4.6877,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842399874734909e-05,
"loss": 4.6654,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841561279983857e-05,
"loss": 4.6752,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840722685232805e-05,
"loss": 4.6717,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.6839,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.6563,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.6734,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.6692,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836531349357918e-05,
"loss": 4.6624,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835692754606866e-05,
"loss": 4.6728,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.6479,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.65,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.6661,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.6527,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.6478,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.641,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.6473,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.6375,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281486776081446e-05,
"loss": 4.6562,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.6255,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.6356,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.6344,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.6335,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823958979613631e-05,
"loss": 4.6387,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823120384862579e-05,
"loss": 4.6275,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822281790111527e-05,
"loss": 4.6092,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821443195360475e-05,
"loss": 4.6164,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.64,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.6128,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.6141,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.6072,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817251859485588e-05,
"loss": 4.6083,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.6229,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815576307863857e-05,
"loss": 4.6232,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.6074,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138991183617535e-05,
"loss": 4.6199,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813060523610701e-05,
"loss": 4.6226,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.6187,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.5928,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.6069,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097094203672393e-05,
"loss": 4.5993,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.8088708256161873e-05,
"loss": 4.6005,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.5964,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807195273994456e-05,
"loss": 4.5974,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806356679243404e-05,
"loss": 4.6049,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805518084492352e-05,
"loss": 4.5982,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046794897413e-05,
"loss": 4.5804,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803840894990248e-05,
"loss": 4.586,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803002300239196e-05,
"loss": 4.5875,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802163705488144e-05,
"loss": 4.5909,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801325110737092e-05,
"loss": 4.5899,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800488153866413e-05,
"loss": 4.5762,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799649559115361e-05,
"loss": 4.5836,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798810964364309e-05,
"loss": 4.5686,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797972369613257e-05,
"loss": 4.5845,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797133774862205e-05,
"loss": 4.5797,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796296817991526e-05,
"loss": 4.5739,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795458223240474e-05,
"loss": 4.5809,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794619628489423e-05,
"loss": 4.572,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.5677,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792942438987319e-05,
"loss": 4.5682,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.5696,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.5658,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790426654734163e-05,
"loss": 4.5572,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895880599831107e-05,
"loss": 4.5611,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887494652320587e-05,
"loss": 4.5635,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879108704810067e-05,
"loss": 4.5587,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870739136103276e-05,
"loss": 4.5431,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862353188592756e-05,
"loss": 4.5559,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853967241082236e-05,
"loss": 4.556,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845581293571715e-05,
"loss": 4.5493,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837195346061195e-05,
"loss": 4.5488,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828809398550675e-05,
"loss": 4.5484,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820423451040155e-05,
"loss": 4.5364,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781205388233337e-05,
"loss": 4.5578,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780368431362658e-05,
"loss": 4.5425,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779529836611606e-05,
"loss": 4.5465,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778691241860554e-05,
"loss": 4.5421,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777852647109502e-05,
"loss": 4.5486,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777014052358449e-05,
"loss": 4.5388,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776175457607397e-05,
"loss": 4.5412,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775336862856345e-05,
"loss": 4.5519,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774498268105293e-05,
"loss": 4.5429,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773659673354241e-05,
"loss": 4.5326,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772822716483563e-05,
"loss": 4.5328,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771984121732511e-05,
"loss": 4.5275,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771145526981459e-05,
"loss": 4.5259,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770306932230407e-05,
"loss": 4.5267,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769468337479355e-05,
"loss": 4.5245,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768631380608676e-05,
"loss": 4.5164,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767792785857624e-05,
"loss": 4.5206,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766954191106572e-05,
"loss": 4.5169,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766117234235893e-05,
"loss": 4.5342,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.5353,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764440044733789e-05,
"loss": 4.5214,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763601449982737e-05,
"loss": 4.5115,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762762855231685e-05,
"loss": 4.5181,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761924260480633e-05,
"loss": 4.5231,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610856657295813e-05,
"loss": 4.5234,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602470709785293e-05,
"loss": 4.5159,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.7594084762274773e-05,
"loss": 4.5205,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758569881476425e-05,
"loss": 4.5118,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757732924605746e-05,
"loss": 4.5136,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756894329854694e-05,
"loss": 4.5086,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756055735103642e-05,
"loss": 4.5128,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.75521714035259e-05,
"loss": 4.5053,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543785456015375e-05,
"loss": 4.5,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535399508504855e-05,
"loss": 4.508,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752702993979807e-05,
"loss": 4.5098,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751864399228755e-05,
"loss": 4.5114,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751025804477703e-05,
"loss": 4.4993,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750187209726651e-05,
"loss": 4.5007,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.469255447387695,
"eval_runtime": 295.4389,
"eval_samples_per_second": 1291.607,
"eval_steps_per_second": 40.364,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749348614975599e-05,
"loss": 4.4955,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748510020224547e-05,
"loss": 4.4918,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747671425473495e-05,
"loss": 4.5067,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746832830722443e-05,
"loss": 4.4968,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745994235971391e-05,
"loss": 4.502,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745155641220339e-05,
"loss": 4.4857,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744317046469287e-05,
"loss": 4.499,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743478451718235e-05,
"loss": 4.4848,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742639856967183e-05,
"loss": 4.4927,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741801262216131e-05,
"loss": 4.4883,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740962667465079e-05,
"loss": 4.4972,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401240727140264e-05,
"loss": 4.492,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739287115843348e-05,
"loss": 4.4758,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384485210922966e-05,
"loss": 4.4837,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376099263412446e-05,
"loss": 4.4759,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736771331590192e-05,
"loss": 4.4803,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.73593273683914e-05,
"loss": 4.4796,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735094142088088e-05,
"loss": 4.4723,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342571852174095e-05,
"loss": 4.4782,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733418590466357e-05,
"loss": 4.4935,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732579995715305e-05,
"loss": 4.4805,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731741400964253e-05,
"loss": 4.4776,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730902806213201e-05,
"loss": 4.476,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730064211462149e-05,
"loss": 4.4844,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729225616711097e-05,
"loss": 4.4594,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7283886598404184e-05,
"loss": 4.4714,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275500650893664e-05,
"loss": 4.4699,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267114703383144e-05,
"loss": 4.4649,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258728755872624e-05,
"loss": 4.4606,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250342808362104e-05,
"loss": 4.4585,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7241956860851584e-05,
"loss": 4.4659,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233570913341064e-05,
"loss": 4.4755,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225184965830544e-05,
"loss": 4.4638,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721681539712375e-05,
"loss": 4.4657,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720842944961323e-05,
"loss": 4.4576,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720004350210271e-05,
"loss": 4.4617,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719165755459219e-05,
"loss": 4.4486,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718327160708167e-05,
"loss": 4.4661,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717490203837488e-05,
"loss": 4.44,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716651609086437e-05,
"loss": 4.4525,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715813014335385e-05,
"loss": 4.4478,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714974419584333e-05,
"loss": 4.4618,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714135824833281e-05,
"loss": 4.441,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713298867962602e-05,
"loss": 4.4518,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.71246027321155e-05,
"loss": 4.4525,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711621678460498e-05,
"loss": 4.4434,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710784721589819e-05,
"loss": 4.4555,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099461268387667e-05,
"loss": 4.4351,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091075320877147e-05,
"loss": 4.436,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082689373366627e-05,
"loss": 4.4537,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074319804659836e-05,
"loss": 4.4385,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706593385714932e-05,
"loss": 4.4382,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.70575479096388e-05,
"loss": 4.4328,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704916196212828e-05,
"loss": 4.441,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040776014617755e-05,
"loss": 4.4269,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032390067107235e-05,
"loss": 4.4469,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024004119596715e-05,
"loss": 4.4191,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015618172086195e-05,
"loss": 4.4328,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007232224575675e-05,
"loss": 4.4365,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998862655868884e-05,
"loss": 4.4284,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990476708358364e-05,
"loss": 4.4346,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982107139651573e-05,
"loss": 4.4318,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697372119214106e-05,
"loss": 4.4104,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696533524463054e-05,
"loss": 4.421,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695694929712002e-05,
"loss": 4.4329,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694857972841323e-05,
"loss": 4.4216,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694019378090271e-05,
"loss": 4.4239,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693180783339219e-05,
"loss": 4.409,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692342188588167e-05,
"loss": 4.4147,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691503593837115e-05,
"loss": 4.4327,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690664999086063e-05,
"loss": 4.4305,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689826404335011e-05,
"loss": 4.4142,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688987809583959e-05,
"loss": 4.4308,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688149214832907e-05,
"loss": 4.4342,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687310620081855e-05,
"loss": 4.4327,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686472025330803e-05,
"loss": 4.4021,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685633430579751e-05,
"loss": 4.4229,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6847964737090725e-05,
"loss": 4.4158,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839578789580204e-05,
"loss": 4.4114,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831192842069684e-05,
"loss": 4.4149,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822823273362894e-05,
"loss": 4.4138,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.68144537046561e-05,
"loss": 4.4191,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680606775714558e-05,
"loss": 4.4215,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679768180963506e-05,
"loss": 4.3965,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678929586212454e-05,
"loss": 4.4088,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678090991461402e-05,
"loss": 4.4067,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.67725239671035e-05,
"loss": 4.4114,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676413801959298e-05,
"loss": 4.4143,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675575207208246e-05,
"loss": 4.3977,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674736612457194e-05,
"loss": 4.4074,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673899655586516e-05,
"loss": 4.396,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673062698715837e-05,
"loss": 4.4095,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672224103964785e-05,
"loss": 4.4051,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671385509213733e-05,
"loss": 4.401,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670546914462681e-05,
"loss": 4.4072,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669708319711629e-05,
"loss": 4.4041,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668869724960576e-05,
"loss": 4.3956,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668031130209524e-05,
"loss": 4.4001,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667192535458472e-05,
"loss": 4.4014,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.66635394070742e-05,
"loss": 4.3987,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665515345956368e-05,
"loss": 4.3855,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664676751205316e-05,
"loss": 4.3937,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663838156454265e-05,
"loss": 4.3985,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663002837463959e-05,
"loss": 4.3959,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621642427129065e-05,
"loss": 4.3762,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613256479618545e-05,
"loss": 4.39,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6604870532108025e-05,
"loss": 4.3961,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596484584597505e-05,
"loss": 4.3856,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588098637086985e-05,
"loss": 4.3849,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579712689576465e-05,
"loss": 4.3871,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571326742065945e-05,
"loss": 4.3774,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6562940794555425e-05,
"loss": 4.3957,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554571225848634e-05,
"loss": 4.38,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546185278338114e-05,
"loss": 4.3874,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.65377993308276e-05,
"loss": 4.3864,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652942976212081e-05,
"loss": 4.3902,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652104381461029e-05,
"loss": 4.3804,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651265786709977e-05,
"loss": 4.3877,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650427191958925e-05,
"loss": 4.3931,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649588597207873e-05,
"loss": 4.3864,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648750002456821e-05,
"loss": 4.3736,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647913045586142e-05,
"loss": 4.3779,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.64707445083509e-05,
"loss": 4.3736,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646235856084038e-05,
"loss": 4.3751,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645397261332986e-05,
"loss": 4.3714,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644558666581934e-05,
"loss": 4.3752,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643720071830882e-05,
"loss": 4.362,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.64288147707983e-05,
"loss": 4.3701,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420445202091514e-05,
"loss": 4.3649,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412059254580994e-05,
"loss": 4.3845,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403673307070474e-05,
"loss": 4.3823,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639528735955995e-05,
"loss": 4.3773,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638690141204943e-05,
"loss": 4.3624,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637851546453891e-05,
"loss": 4.3687,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637012951702839e-05,
"loss": 4.377,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636174356951787e-05,
"loss": 4.3742,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353374000811076e-05,
"loss": 4.3694,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6344988053300556e-05,
"loss": 4.3733,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336602105790036e-05,
"loss": 4.3682,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632821615827952e-05,
"loss": 4.3719,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6319830210769e-05,
"loss": 4.3579,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631146064206221e-05,
"loss": 4.3719,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630307469455169e-05,
"loss": 4.3616,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629468874704117e-05,
"loss": 4.3546,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628630279953065e-05,
"loss": 4.3643,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627793323082386e-05,
"loss": 4.3706,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626954728331334e-05,
"loss": 4.3647,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626116133580282e-05,
"loss": 4.3593,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.62527753882923e-05,
"loss": 4.3565,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.335974216461182,
"eval_runtime": 298.1892,
"eval_samples_per_second": 1279.694,
"eval_steps_per_second": 39.991,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624438944078178e-05,
"loss": 4.3657,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623600349327126e-05,
"loss": 4.3508,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622761754576074e-05,
"loss": 4.3662,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621923159825022e-05,
"loss": 4.3545,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.6210862029543436e-05,
"loss": 4.3696,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202476082032916e-05,
"loss": 4.3455,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194090134522396e-05,
"loss": 4.364,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185704187011876e-05,
"loss": 4.346,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177318239501356e-05,
"loss": 4.3594,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6168948670794565e-05,
"loss": 4.3544,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.6160562723284045e-05,
"loss": 4.3561,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.6152176775773525e-05,
"loss": 4.3635,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6143790828263005e-05,
"loss": 4.3402,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135404880752485e-05,
"loss": 4.3488,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612701893324196e-05,
"loss": 4.342,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611863298573144e-05,
"loss": 4.347,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.6110247038220925e-05,
"loss": 4.3456,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610187746951414e-05,
"loss": 4.343,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.6093491522003614e-05,
"loss": 4.3459,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.6085105574493094e-05,
"loss": 4.3612,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076719626982574e-05,
"loss": 4.3479,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068333679472054e-05,
"loss": 4.347,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6059947731961534e-05,
"loss": 4.3485,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605157816325474e-05,
"loss": 4.3531,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604320859454796e-05,
"loss": 4.3324,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603482264703743e-05,
"loss": 4.3503,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602643669952691e-05,
"loss": 4.3353,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601805075201639e-05,
"loss": 4.3363,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.600966480450588e-05,
"loss": 4.3315,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600129523579909e-05,
"loss": 4.3366,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599290928828857e-05,
"loss": 4.3354,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598452334077805e-05,
"loss": 4.3497,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597613739326753e-05,
"loss": 4.3398,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596775144575701e-05,
"loss": 4.3389,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595936549824649e-05,
"loss": 4.3303,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.5950995929539696e-05,
"loss": 4.3412,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.5942609982029176e-05,
"loss": 4.3241,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.5934224034518656e-05,
"loss": 4.3442,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.5925838087008136e-05,
"loss": 4.3165,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.5917452139497616e-05,
"loss": 4.3269,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590908257079083e-05,
"loss": 4.3277,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590069662328031e-05,
"loss": 4.3409,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589231067576979e-05,
"loss": 4.3218,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588392472825927e-05,
"loss": 4.3278,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587553878074875e-05,
"loss": 4.3297,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586715283323823e-05,
"loss": 4.3256,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585876688572771e-05,
"loss": 4.3338,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585041369582465e-05,
"loss": 4.3187,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584202774831413e-05,
"loss": 4.3121,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583364180080361e-05,
"loss": 4.3336,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582525585329309e-05,
"loss": 4.3208,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581686990578257e-05,
"loss": 4.3183,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580848395827205e-05,
"loss": 4.3176,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580009801076153e-05,
"loss": 4.3219,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791712063251017e-05,
"loss": 4.3086,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783326115740497e-05,
"loss": 4.3285,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5774956547033706e-05,
"loss": 4.3026,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766570599523186e-05,
"loss": 4.3161,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758184652012666e-05,
"loss": 4.3151,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5749798704502146e-05,
"loss": 4.3201,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574141275699162e-05,
"loss": 4.3142,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733043188284835e-05,
"loss": 4.3188,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724657240774315e-05,
"loss": 4.2944,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716271293263794e-05,
"loss": 4.3101,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570788534575327e-05,
"loss": 4.3163,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.5699499398242754e-05,
"loss": 4.3118,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.5691113450732234e-05,
"loss": 4.3036,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.5682743882025443e-05,
"loss": 4.3027,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.5674357934514923e-05,
"loss": 4.3002,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.56659719870044e-05,
"loss": 4.3146,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565758603949388e-05,
"loss": 4.3202,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564920009198336e-05,
"loss": 4.3058,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564081414447284e-05,
"loss": 4.3174,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563242819696232e-05,
"loss": 4.3238,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.56240422494518e-05,
"loss": 4.3266,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561567268074501e-05,
"loss": 4.2879,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560728673323449e-05,
"loss": 4.3095,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559890078572397e-05,
"loss": 4.3111,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559051483821345e-05,
"loss": 4.299,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558212889070293e-05,
"loss": 4.3063,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557374294319242e-05,
"loss": 4.3081,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556537337448563e-05,
"loss": 4.3138,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555698742697511e-05,
"loss": 4.3048,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554860147946459e-05,
"loss": 4.2955,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554021553195407e-05,
"loss": 4.2983,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553182958444355e-05,
"loss": 4.2975,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552346001573676e-05,
"loss": 4.3057,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551507406822624e-05,
"loss": 4.3092,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550668812071572e-05,
"loss": 4.2921,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.5498318552008926e-05,
"loss": 4.2977,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.5489932604498406e-05,
"loss": 4.2891,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.5481546656987886e-05,
"loss": 4.2987,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547316070947737e-05,
"loss": 4.3009,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546477476196685e-05,
"loss": 4.2925,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545640519326006e-05,
"loss": 4.3036,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544801924574954e-05,
"loss": 4.2984,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543963329823902e-05,
"loss": 4.2923,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.54312473507285e-05,
"loss": 4.2964,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542286140321798e-05,
"loss": 4.2978,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.5414475455707455e-05,
"loss": 4.2994,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540610588700067e-05,
"loss": 4.2811,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539771993949015e-05,
"loss": 4.2911,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538933399197963e-05,
"loss": 4.2961,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538094804446911e-05,
"loss": 4.2977,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537256209695859e-05,
"loss": 4.2777,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536417614944807e-05,
"loss": 4.2834,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535579020193755e-05,
"loss": 4.2956,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534740425442703e-05,
"loss": 4.2863,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533903468572024e-05,
"loss": 4.2837,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330665117013455e-05,
"loss": 4.2842,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532227916950293e-05,
"loss": 4.2838,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531389322199241e-05,
"loss": 4.2902,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530550727448189e-05,
"loss": 4.2846,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529712132697137e-05,
"loss": 4.2823,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528873537946085e-05,
"loss": 4.2895,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.5280365810754064e-05,
"loss": 4.2925,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.5271979863243544e-05,
"loss": 4.2899,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.5263593915733024e-05,
"loss": 4.281,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.5255207968222504e-05,
"loss": 4.2971,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.5246822020711984e-05,
"loss": 4.2887,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.5238436073201464e-05,
"loss": 4.2746,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523006650449467e-05,
"loss": 4.2813,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522169693578788e-05,
"loss": 4.2775,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521331098827736e-05,
"loss": 4.2809,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520492504076684e-05,
"loss": 4.2721,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519653909325632e-05,
"loss": 4.2825,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.51881531457458e-05,
"loss": 4.2666,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517976719823528e-05,
"loss": 4.2749,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517138125072476e-05,
"loss": 4.2697,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516299530321425e-05,
"loss": 4.2903,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515460935570373e-05,
"loss": 4.2832,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514622340819321e-05,
"loss": 4.2832,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513783746068269e-05,
"loss": 4.2669,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512945151317217e-05,
"loss": 4.2786,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512108194446538e-05,
"loss": 4.2855,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.5112712375758586e-05,
"loss": 4.2777,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104326428248066e-05,
"loss": 4.2761,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5095940480737546e-05,
"loss": 4.282,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087570912030755e-05,
"loss": 4.2765,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079184964520235e-05,
"loss": 4.2805,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070799017009715e-05,
"loss": 4.2629,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062413069499195e-05,
"loss": 4.2811,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505402712198868e-05,
"loss": 4.2686,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504564117447816e-05,
"loss": 4.2685,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503725522696764e-05,
"loss": 4.2727,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5028869279457115e-05,
"loss": 4.279,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020483331946595e-05,
"loss": 4.2713,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012097384436075e-05,
"loss": 4.2667,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.5003711436925555e-05,
"loss": 4.2691,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.253751277923584,
"eval_runtime": 299.7428,
"eval_samples_per_second": 1273.061,
"eval_steps_per_second": 39.784,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.4995325489415035e-05,
"loss": 4.2697,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4986939541904515e-05,
"loss": 4.2628,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978553594393995e-05,
"loss": 4.2739,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970167646883475e-05,
"loss": 4.2659,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4961781699372955e-05,
"loss": 4.2787,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953395751862435e-05,
"loss": 4.2629,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945009804351915e-05,
"loss": 4.2699,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936623856841395e-05,
"loss": 4.258,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492823790933088e-05,
"loss": 4.2688,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4919851961820354e-05,
"loss": 4.2712,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911466014309834e-05,
"loss": 4.2666,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903080066799314e-05,
"loss": 4.2703,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489471049809253e-05,
"loss": 4.2552,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.4886324550582003e-05,
"loss": 4.2628,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4877938603071483e-05,
"loss": 4.2566,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486955265556096e-05,
"loss": 4.2578,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486116670805044e-05,
"loss": 4.2605,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485278076053992e-05,
"loss": 4.2596,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.48443948130294e-05,
"loss": 4.2594,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483600886551888e-05,
"loss": 4.271,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482762291800836e-05,
"loss": 4.266,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481925334930158e-05,
"loss": 4.262,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481086740179106e-05,
"loss": 4.2664,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480248145428054e-05,
"loss": 4.2682,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479409550677002e-05,
"loss": 4.2472,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.47857095592595e-05,
"loss": 4.2635,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477732361174898e-05,
"loss": 4.25,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476893766423846e-05,
"loss": 4.2495,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476056809553167e-05,
"loss": 4.2468,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475219852682488e-05,
"loss": 4.2538,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474381257931436e-05,
"loss": 4.2511,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473542663180384e-05,
"loss": 4.2662,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472704068429332e-05,
"loss": 4.2585,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.4718654736782804e-05,
"loss": 4.2551,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471028516807601e-05,
"loss": 4.2496,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470189922056549e-05,
"loss": 4.2578,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469351327305497e-05,
"loss": 4.2502,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468512732554445e-05,
"loss": 4.2567,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467674137803393e-05,
"loss": 4.2348,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466835543052341e-05,
"loss": 4.2434,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.465996948301289e-05,
"loss": 4.2461,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651583535502366e-05,
"loss": 4.2599,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.4643197587991846e-05,
"loss": 4.245,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463482801928506e-05,
"loss": 4.2455,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462644207177454e-05,
"loss": 4.2496,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461805612426402e-05,
"loss": 4.2455,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4609702934360966e-05,
"loss": 4.2526,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601316986850446e-05,
"loss": 4.2394,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4592931039339926e-05,
"loss": 4.2322,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584545091829406e-05,
"loss": 4.2537,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576159144318886e-05,
"loss": 4.2397,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4567773196808366e-05,
"loss": 4.2415,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455938724929784e-05,
"loss": 4.2367,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455100130178732e-05,
"loss": 4.2457,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542631733080535e-05,
"loss": 4.2311,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453424578557001e-05,
"loss": 4.2441,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452585983805949e-05,
"loss": 4.2294,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.4517473890548975e-05,
"loss": 4.2357,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450910432184219e-05,
"loss": 4.2404,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.4500718374331664e-05,
"loss": 4.2394,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.4492332426821144e-05,
"loss": 4.2359,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448396285811436e-05,
"loss": 4.2462,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447557691060384e-05,
"loss": 4.2185,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446719096309331e-05,
"loss": 4.2288,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445880501558279e-05,
"loss": 4.239,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445041906807227e-05,
"loss": 4.2333,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444203312056175e-05,
"loss": 4.2315,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443364717305123e-05,
"loss": 4.2239,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442526122554071e-05,
"loss": 4.224,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441687527803019e-05,
"loss": 4.2352,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440848933051967e-05,
"loss": 4.2435,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440010338300916e-05,
"loss": 4.234,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439171743549864e-05,
"loss": 4.2402,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438333148798812e-05,
"loss": 4.2464,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.43749455404776e-05,
"loss": 4.2528,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436655959296708e-05,
"loss": 4.2188,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435820640306402e-05,
"loss": 4.2303,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.43498204555535e-05,
"loss": 4.2417,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434143450804298e-05,
"loss": 4.2186,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433304856053246e-05,
"loss": 4.2356,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432466261302194e-05,
"loss": 4.2327,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431627666551142e-05,
"loss": 4.2379,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.43078907180009e-05,
"loss": 4.235,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429950477049038e-05,
"loss": 4.22,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429111882297986e-05,
"loss": 4.2267,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428273287546934e-05,
"loss": 4.2222,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427436330676255e-05,
"loss": 4.2308,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4265977359252026e-05,
"loss": 4.2373,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257591411741506e-05,
"loss": 4.2182,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249205464230986e-05,
"loss": 4.2259,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.42408358955242e-05,
"loss": 4.2187,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423246632681741e-05,
"loss": 4.2249,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422408037930689e-05,
"loss": 4.2273,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421569443179637e-05,
"loss": 4.2246,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420730848428585e-05,
"loss": 4.2332,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419892253677533e-05,
"loss": 4.2225,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419053658926481e-05,
"loss": 4.2224,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418215064175429e-05,
"loss": 4.2231,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417376469424377e-05,
"loss": 4.2231,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416537874673325e-05,
"loss": 4.2306,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415699279922273e-05,
"loss": 4.2119,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414860685171221e-05,
"loss": 4.2206,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414022090420169e-05,
"loss": 4.2243,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413186771429863e-05,
"loss": 4.2276,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412348176678811e-05,
"loss": 4.2067,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411509581927759e-05,
"loss": 4.2152,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410670987176707e-05,
"loss": 4.2254,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409832392425655e-05,
"loss": 4.2176,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.408993797674603e-05,
"loss": 4.21,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081552029235515e-05,
"loss": 4.2205,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.4073166081724995e-05,
"loss": 4.209,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.4064796513018204e-05,
"loss": 4.2246,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.4056410565507684e-05,
"loss": 4.2141,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.4048024617997164e-05,
"loss": 4.2085,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.4039638670486644e-05,
"loss": 4.2237,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.4031252722976124e-05,
"loss": 4.2274,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402288315426933e-05,
"loss": 4.2193,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401449720675881e-05,
"loss": 4.214,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400611125924829e-05,
"loss": 4.2222,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399772531173777e-05,
"loss": 4.2201,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398933936422725e-05,
"loss": 4.2084,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398095341671673e-05,
"loss": 4.2196,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397258384800995e-05,
"loss": 4.2086,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396421427930316e-05,
"loss": 4.2117,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395582833179264e-05,
"loss": 4.2051,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394744238428212e-05,
"loss": 4.2137,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.39390564367716e-05,
"loss": 4.1996,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393067048926108e-05,
"loss": 4.2045,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392228454175056e-05,
"loss": 4.2084,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391389859424003e-05,
"loss": 4.2203,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390551264672951e-05,
"loss": 4.2189,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389714307802273e-05,
"loss": 4.2175,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388875713051221e-05,
"loss": 4.1996,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388037118300169e-05,
"loss": 4.2159,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387198523549117e-05,
"loss": 4.2173,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3863599287980647e-05,
"loss": 4.2131,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855213340470127e-05,
"loss": 4.2083,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3846827392959606e-05,
"loss": 4.2196,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.3838441445449086e-05,
"loss": 4.2074,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830055497938566e-05,
"loss": 4.2165,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3821685929231775e-05,
"loss": 4.1946,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813299981721255e-05,
"loss": 4.2201,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3804914034210735e-05,
"loss": 4.201,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796528086700215e-05,
"loss": 4.204,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788142139189695e-05,
"loss": 4.2092,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3779756191679175e-05,
"loss": 4.2081,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377138662297239e-05,
"loss": 4.212,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.37630170542656e-05,
"loss": 4.1982,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375464748555881e-05,
"loss": 4.211,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.197904109954834,
"eval_runtime": 296.9374,
"eval_samples_per_second": 1285.089,
"eval_steps_per_second": 40.16,
"step": 381600
},
{
"epoch": 0.0,
"learning_rate": 4.374626153804829e-05,
"loss": 4.2068,
"step": 381952
},
{
"epoch": 0.0,
"learning_rate": 4.373787559053777e-05,
"loss": 4.1991,
"step": 382464
},
{
"epoch": 0.0,
"learning_rate": 4.372948964302725e-05,
"loss": 4.2109,
"step": 382976
},
{
"epoch": 0.0,
"learning_rate": 4.372110369551673e-05,
"loss": 4.2017,
"step": 383488
},
{
"epoch": 0.0,
"learning_rate": 4.371271774800621e-05,
"loss": 4.2117,
"step": 384000
},
{
"epoch": 0.0,
"learning_rate": 4.370433180049569e-05,
"loss": 4.2006,
"step": 384512
},
{
"epoch": 0.0,
"learning_rate": 4.369594585298517e-05,
"loss": 4.2005,
"step": 385024
},
{
"epoch": 0.0,
"learning_rate": 4.368755990547465e-05,
"loss": 4.2005,
"step": 385536
},
{
"epoch": 0.0,
"learning_rate": 4.367917395796413e-05,
"loss": 4.2026,
"step": 386048
},
{
"epoch": 0.0,
"learning_rate": 4.367078801045361e-05,
"loss": 4.2072,
"step": 386560
},
{
"epoch": 0.0,
"learning_rate": 4.366240206294309e-05,
"loss": 4.2036,
"step": 387072
},
{
"epoch": 0.0,
"learning_rate": 4.3654016115432576e-05,
"loss": 4.2103,
"step": 387584
},
{
"epoch": 0.0,
"learning_rate": 4.364563016792205e-05,
"loss": 4.1943,
"step": 388096
},
{
"epoch": 0.0,
"learning_rate": 4.363724422041153e-05,
"loss": 4.1998,
"step": 388608
},
{
"epoch": 0.0,
"learning_rate": 4.362885827290101e-05,
"loss": 4.1982,
"step": 389120
},
{
"epoch": 0.0,
"learning_rate": 4.3620488704194225e-05,
"loss": 4.1915,
"step": 389632
},
{
"epoch": 0.0,
"learning_rate": 4.36121027566837e-05,
"loss": 4.1999,
"step": 390144
},
{
"epoch": 0.0,
"learning_rate": 4.360371680917318e-05,
"loss": 4.1929,
"step": 390656
},
{
"epoch": 0.0,
"learning_rate": 4.359533086166266e-05,
"loss": 4.1956,
"step": 391168
},
{
"epoch": 0.0,
"learning_rate": 4.358694491415214e-05,
"loss": 4.2122,
"step": 391680
},
{
"epoch": 0.0,
"learning_rate": 4.357855896664162e-05,
"loss": 4.2027,
"step": 392192
},
{
"epoch": 0.0,
"learning_rate": 4.35701730191311e-05,
"loss": 4.2067,
"step": 392704
},
{
"epoch": 0.0,
"learning_rate": 4.356178707162058e-05,
"loss": 4.2,
"step": 393216
},
{
"epoch": 0.0,
"learning_rate": 4.355340112411006e-05,
"loss": 4.2047,
"step": 393728
},
{
"epoch": 0.0,
"learning_rate": 4.354501517659954e-05,
"loss": 4.1861,
"step": 394240
},
{
"epoch": 0.0,
"learning_rate": 4.353666198669648e-05,
"loss": 4.2039,
"step": 394752
},
{
"epoch": 0.0,
"learning_rate": 4.352827603918596e-05,
"loss": 4.1928,
"step": 395264
},
{
"epoch": 0.0,
"learning_rate": 4.351989009167544e-05,
"loss": 4.1837,
"step": 395776
},
{
"epoch": 0.0,
"learning_rate": 4.351150414416492e-05,
"loss": 4.1879,
"step": 396288
},
{
"epoch": 0.0,
"learning_rate": 4.35031181966544e-05,
"loss": 4.1915,
"step": 396800
},
{
"epoch": 0.01,
"learning_rate": 4.349473224914388e-05,
"loss": 4.1937,
"step": 397312
},
{
"epoch": 0.01,
"learning_rate": 4.348634630163336e-05,
"loss": 4.2028,
"step": 397824
},
{
"epoch": 0.01,
"learning_rate": 4.347796035412284e-05,
"loss": 4.2018,
"step": 398336
},
{
"epoch": 0.01,
"learning_rate": 4.346959078541605e-05,
"loss": 4.1937,
"step": 398848
},
{
"epoch": 0.01,
"learning_rate": 4.346122121670926e-05,
"loss": 4.1902,
"step": 399360
},
{
"epoch": 0.01,
"learning_rate": 4.345283526919875e-05,
"loss": 4.194,
"step": 399872
},
{
"epoch": 0.01,
"learning_rate": 4.344444932168823e-05,
"loss": 4.1899,
"step": 400384
},
{
"epoch": 0.01,
"learning_rate": 4.343606337417771e-05,
"loss": 4.195,
"step": 400896
},
{
"epoch": 0.01,
"learning_rate": 4.342767742666719e-05,
"loss": 4.1813,
"step": 401408
},
{
"epoch": 0.01,
"learning_rate": 4.341929147915667e-05,
"loss": 4.1815,
"step": 401920
},
{
"epoch": 0.01,
"learning_rate": 4.341090553164615e-05,
"loss": 4.1882,
"step": 402432
},
{
"epoch": 0.01,
"learning_rate": 4.3402535962939356e-05,
"loss": 4.1983,
"step": 402944
},
{
"epoch": 0.01,
"learning_rate": 4.3394150015428836e-05,
"loss": 4.188,
"step": 403456
},
{
"epoch": 0.01,
"learning_rate": 4.3385764067918316e-05,
"loss": 4.1857,
"step": 403968
},
{
"epoch": 0.01,
"learning_rate": 4.3377378120407796e-05,
"loss": 4.1918,
"step": 404480
},
{
"epoch": 0.01,
"learning_rate": 4.3368992172897276e-05,
"loss": 4.1847,
"step": 404992
},
{
"epoch": 0.01,
"learning_rate": 4.3360606225386756e-05,
"loss": 4.1942,
"step": 405504
},
{
"epoch": 0.01,
"learning_rate": 4.335222027787623e-05,
"loss": 4.1809,
"step": 406016
},
{
"epoch": 0.01,
"learning_rate": 4.3343834330365716e-05,
"loss": 4.1732,
"step": 406528
},
{
"epoch": 0.01,
"learning_rate": 4.333546476165893e-05,
"loss": 4.1935,
"step": 407040
},
{
"epoch": 0.01,
"learning_rate": 4.332707881414841e-05,
"loss": 4.1857,
"step": 407552
},
{
"epoch": 0.01,
"learning_rate": 4.3318692866637885e-05,
"loss": 4.1819,
"step": 408064
},
{
"epoch": 0.01,
"learning_rate": 4.33103232979311e-05,
"loss": 4.1842,
"step": 408576
},
{
"epoch": 0.01,
"learning_rate": 4.330193735042058e-05,
"loss": 4.182,
"step": 409088
},
{
"epoch": 0.01,
"learning_rate": 4.3293551402910054e-05,
"loss": 4.1773,
"step": 409600
},
{
"epoch": 0.01,
"learning_rate": 4.3285165455399534e-05,
"loss": 4.1807,
"step": 410112
},
{
"epoch": 0.01,
"learning_rate": 4.327679588669275e-05,
"loss": 4.1737,
"step": 410624
},
{
"epoch": 0.01,
"learning_rate": 4.326840993918223e-05,
"loss": 4.1764,
"step": 411136
},
{
"epoch": 0.01,
"learning_rate": 4.32600239916717e-05,
"loss": 4.1881,
"step": 411648
},
{
"epoch": 0.01,
"learning_rate": 4.325163804416118e-05,
"loss": 4.1787,
"step": 412160
},
{
"epoch": 0.01,
"learning_rate": 4.324325209665067e-05,
"loss": 4.1799,
"step": 412672
},
{
"epoch": 0.01,
"learning_rate": 4.3234882527943885e-05,
"loss": 4.1897,
"step": 413184
},
{
"epoch": 0.01,
"learning_rate": 4.322649658043336e-05,
"loss": 4.1663,
"step": 413696
},
{
"epoch": 0.01,
"learning_rate": 4.321811063292284e-05,
"loss": 4.1709,
"step": 414208
},
{
"epoch": 0.01,
"learning_rate": 4.320972468541232e-05,
"loss": 4.1786,
"step": 414720
},
{
"epoch": 0.01,
"learning_rate": 4.32013387379018e-05,
"loss": 4.1819,
"step": 415232
},
{
"epoch": 0.01,
"learning_rate": 4.319296916919501e-05,
"loss": 4.1706,
"step": 415744
},
{
"epoch": 0.01,
"learning_rate": 4.318458322168449e-05,
"loss": 4.1719,
"step": 416256
},
{
"epoch": 0.01,
"learning_rate": 4.317619727417397e-05,
"loss": 4.1638,
"step": 416768
},
{
"epoch": 0.01,
"learning_rate": 4.316781132666345e-05,
"loss": 4.18,
"step": 417280
},
{
"epoch": 0.01,
"learning_rate": 4.315942537915293e-05,
"loss": 4.1862,
"step": 417792
},
{
"epoch": 0.01,
"learning_rate": 4.3151055810446136e-05,
"loss": 4.1799,
"step": 418304
},
{
"epoch": 0.01,
"learning_rate": 4.314266986293562e-05,
"loss": 4.1842,
"step": 418816
},
{
"epoch": 0.01,
"learning_rate": 4.31342839154251e-05,
"loss": 4.1844,
"step": 419328
},
{
"epoch": 0.01,
"learning_rate": 4.312589796791458e-05,
"loss": 4.2035,
"step": 419840
},
{
"epoch": 0.01,
"learning_rate": 4.311751202040406e-05,
"loss": 4.1656,
"step": 420352
},
{
"epoch": 0.01,
"learning_rate": 4.310912607289354e-05,
"loss": 4.1738,
"step": 420864
},
{
"epoch": 0.01,
"learning_rate": 4.310074012538302e-05,
"loss": 4.1889,
"step": 421376
},
{
"epoch": 0.01,
"learning_rate": 4.30923541778725e-05,
"loss": 4.162,
"step": 421888
},
{
"epoch": 0.01,
"learning_rate": 4.308396823036198e-05,
"loss": 4.181,
"step": 422400
},
{
"epoch": 0.01,
"learning_rate": 4.307559866165519e-05,
"loss": 4.1777,
"step": 422912
},
{
"epoch": 0.01,
"learning_rate": 4.306721271414467e-05,
"loss": 4.1808,
"step": 423424
},
{
"epoch": 0.01,
"learning_rate": 4.305882676663415e-05,
"loss": 4.1797,
"step": 423936
},
{
"epoch": 0.01,
"learning_rate": 4.305044081912363e-05,
"loss": 4.1643,
"step": 424448
},
{
"epoch": 0.01,
"learning_rate": 4.304205487161311e-05,
"loss": 4.1794,
"step": 424960
},
{
"epoch": 0.01,
"learning_rate": 4.303368530290632e-05,
"loss": 4.1631,
"step": 425472
},
{
"epoch": 0.01,
"learning_rate": 4.30252993553958e-05,
"loss": 4.1785,
"step": 425984
},
{
"epoch": 0.01,
"learning_rate": 4.301691340788529e-05,
"loss": 4.1839,
"step": 426496
},
{
"epoch": 0.01,
"learning_rate": 4.3008543839178496e-05,
"loss": 4.1607,
"step": 427008
},
{
"epoch": 0.02,
"learning_rate": 4.3000157891667976e-05,
"loss": 4.174,
"step": 427520
},
{
"epoch": 0.02,
"learning_rate": 4.2991788322961185e-05,
"loss": 4.1663,
"step": 428032
},
{
"epoch": 0.02,
"learning_rate": 4.2983402375450665e-05,
"loss": 4.1683,
"step": 428544
},
{
"epoch": 0.02,
"learning_rate": 4.2975016427940145e-05,
"loss": 4.17,
"step": 429056
},
{
"epoch": 0.02,
"learning_rate": 4.2966630480429625e-05,
"loss": 4.178,
"step": 429568
},
{
"epoch": 0.02,
"learning_rate": 4.2958244532919105e-05,
"loss": 4.1814,
"step": 430080
},
{
"epoch": 0.02,
"learning_rate": 4.2949858585408585e-05,
"loss": 4.1648,
"step": 430592
},
{
"epoch": 0.02,
"learning_rate": 4.2941472637898065e-05,
"loss": 4.1664,
"step": 431104
},
{
"epoch": 0.02,
"learning_rate": 4.293308669038754e-05,
"loss": 4.1744,
"step": 431616
},
{
"epoch": 0.02,
"learning_rate": 4.2924700742877025e-05,
"loss": 4.1685,
"step": 432128
},
{
"epoch": 0.02,
"learning_rate": 4.2916314795366505e-05,
"loss": 4.1806,
"step": 432640
},
{
"epoch": 0.02,
"learning_rate": 4.2907928847855985e-05,
"loss": 4.1609,
"step": 433152
},
{
"epoch": 0.02,
"learning_rate": 4.2899542900345465e-05,
"loss": 4.1649,
"step": 433664
},
{
"epoch": 0.02,
"learning_rate": 4.2891156952834945e-05,
"loss": 4.1716,
"step": 434176
},
{
"epoch": 0.02,
"learning_rate": 4.2882787384128154e-05,
"loss": 4.1758,
"step": 434688
},
{
"epoch": 0.02,
"learning_rate": 4.2874401436617634e-05,
"loss": 4.1538,
"step": 435200
},
{
"epoch": 0.02,
"learning_rate": 4.2866015489107114e-05,
"loss": 4.1634,
"step": 435712
},
{
"epoch": 0.02,
"learning_rate": 4.2857629541596594e-05,
"loss": 4.1688,
"step": 436224
},
{
"epoch": 0.02,
"learning_rate": 4.28492599728898e-05,
"loss": 4.1683,
"step": 436736
},
{
"epoch": 0.02,
"learning_rate": 4.284087402537928e-05,
"loss": 4.1557,
"step": 437248
},
{
"epoch": 0.02,
"learning_rate": 4.283248807786876e-05,
"loss": 4.1749,
"step": 437760
},
{
"epoch": 0.02,
"learning_rate": 4.282410213035824e-05,
"loss": 4.1553,
"step": 438272
},
{
"epoch": 0.02,
"learning_rate": 4.281571618284772e-05,
"loss": 4.1679,
"step": 438784
},
{
"epoch": 0.02,
"learning_rate": 4.280733023533721e-05,
"loss": 4.1645,
"step": 439296
},
{
"epoch": 0.02,
"learning_rate": 4.279896066663042e-05,
"loss": 4.1584,
"step": 439808
},
{
"epoch": 0.02,
"learning_rate": 4.27905747191199e-05,
"loss": 4.17,
"step": 440320
},
{
"epoch": 0.02,
"learning_rate": 4.278218877160938e-05,
"loss": 4.1764,
"step": 440832
},
{
"epoch": 0.02,
"learning_rate": 4.277380282409886e-05,
"loss": 4.1682,
"step": 441344
},
{
"epoch": 0.02,
"learning_rate": 4.276541687658834e-05,
"loss": 4.1631,
"step": 441856
},
{
"epoch": 0.02,
"learning_rate": 4.275704730788155e-05,
"loss": 4.1714,
"step": 442368
},
{
"epoch": 0.02,
"learning_rate": 4.274866136037103e-05,
"loss": 4.169,
"step": 442880
},
{
"epoch": 0.02,
"learning_rate": 4.274027541286051e-05,
"loss": 4.1575,
"step": 443392
},
{
"epoch": 0.02,
"learning_rate": 4.273188946534999e-05,
"loss": 4.1653,
"step": 443904
},
{
"epoch": 0.02,
"learning_rate": 4.272350351783947e-05,
"loss": 4.1587,
"step": 444416
},
{
"epoch": 0.02,
"learning_rate": 4.271511757032895e-05,
"loss": 4.1595,
"step": 444928
},
{
"epoch": 0.02,
"learning_rate": 4.270673162281843e-05,
"loss": 4.1602,
"step": 445440
},
{
"epoch": 0.02,
"learning_rate": 4.269834567530791e-05,
"loss": 4.1592,
"step": 445952
},
{
"epoch": 0.02,
"learning_rate": 4.268995972779739e-05,
"loss": 4.155,
"step": 446464
},
{
"epoch": 0.02,
"learning_rate": 4.268157378028687e-05,
"loss": 4.1516,
"step": 446976
},
{
"epoch": 0.02,
"learning_rate": 4.2673204211580076e-05,
"loss": 4.1579,
"step": 447488
},
{
"epoch": 0.02,
"learning_rate": 4.2664818264069556e-05,
"loss": 4.168,
"step": 448000
},
{
"epoch": 0.02,
"learning_rate": 4.2656432316559036e-05,
"loss": 4.1662,
"step": 448512
},
{
"epoch": 0.02,
"learning_rate": 4.2648046369048516e-05,
"loss": 4.1686,
"step": 449024
},
{
"epoch": 0.02,
"learning_rate": 4.2639676800341725e-05,
"loss": 4.1474,
"step": 449536
},
{
"epoch": 0.02,
"learning_rate": 4.2631290852831205e-05,
"loss": 4.1684,
"step": 450048
},
{
"epoch": 0.02,
"learning_rate": 4.2622904905320685e-05,
"loss": 4.1666,
"step": 450560
},
{
"epoch": 0.02,
"learning_rate": 4.2614518957810165e-05,
"loss": 4.1617,
"step": 451072
},
{
"epoch": 0.02,
"learning_rate": 4.260614938910338e-05,
"loss": 4.1631,
"step": 451584
},
{
"epoch": 0.02,
"learning_rate": 4.259776344159286e-05,
"loss": 4.165,
"step": 452096
},
{
"epoch": 0.02,
"learning_rate": 4.258937749408234e-05,
"loss": 4.1575,
"step": 452608
},
{
"epoch": 0.02,
"learning_rate": 4.258099154657182e-05,
"loss": 4.1725,
"step": 453120
},
{
"epoch": 0.02,
"learning_rate": 4.257262197786503e-05,
"loss": 4.1429,
"step": 453632
},
{
"epoch": 0.02,
"learning_rate": 4.256423603035451e-05,
"loss": 4.1678,
"step": 454144
},
{
"epoch": 0.02,
"learning_rate": 4.255585008284399e-05,
"loss": 4.1508,
"step": 454656
},
{
"epoch": 0.02,
"learning_rate": 4.25474805141372e-05,
"loss": 4.1558,
"step": 455168
},
{
"epoch": 0.02,
"learning_rate": 4.253909456662668e-05,
"loss": 4.1602,
"step": 455680
},
{
"epoch": 0.02,
"learning_rate": 4.253070861911616e-05,
"loss": 4.1537,
"step": 456192
},
{
"epoch": 0.02,
"learning_rate": 4.252232267160564e-05,
"loss": 4.1689,
"step": 456704
},
{
"epoch": 0.02,
"learning_rate": 4.251393672409512e-05,
"loss": 4.1429,
"step": 457216
},
{
"epoch": 0.02,
"learning_rate": 4.25055507765846e-05,
"loss": 4.1623,
"step": 457728
},
{
"epoch": 0.03,
"eval_loss": 4.156124591827393,
"eval_runtime": 283.8799,
"eval_samples_per_second": 1344.199,
"eval_steps_per_second": 42.007,
"step": 457920
},
{
"epoch": 1.0,
"learning_rate": 4.2497164829074085e-05,
"loss": 4.1592,
"step": 458240
},
{
"epoch": 1.0,
"learning_rate": 4.2488778881563565e-05,
"loss": 4.1477,
"step": 458752
},
{
"epoch": 1.0,
"learning_rate": 4.2480392934053045e-05,
"loss": 4.1611,
"step": 459264
},
{
"epoch": 1.0,
"learning_rate": 4.2472006986542525e-05,
"loss": 4.1546,
"step": 459776
},
{
"epoch": 1.0,
"learning_rate": 4.2463621039032005e-05,
"loss": 4.1601,
"step": 460288
},
{
"epoch": 1.0,
"learning_rate": 4.2455235091521485e-05,
"loss": 4.1535,
"step": 460800
},
{
"epoch": 1.0,
"learning_rate": 4.2446849144010965e-05,
"loss": 4.1491,
"step": 461312
},
{
"epoch": 1.0,
"learning_rate": 4.2438479575304174e-05,
"loss": 4.1535,
"step": 461824
},
{
"epoch": 1.0,
"learning_rate": 4.243011000659738e-05,
"loss": 4.1536,
"step": 462336
},
{
"epoch": 1.0,
"learning_rate": 4.242172405908686e-05,
"loss": 4.1571,
"step": 462848
},
{
"epoch": 1.0,
"learning_rate": 4.241333811157634e-05,
"loss": 4.157,
"step": 463360
},
{
"epoch": 1.0,
"learning_rate": 4.240495216406582e-05,
"loss": 4.1571,
"step": 463872
},
{
"epoch": 1.0,
"learning_rate": 4.23965662165553e-05,
"loss": 4.1509,
"step": 464384
},
{
"epoch": 1.0,
"learning_rate": 4.238819664784852e-05,
"loss": 4.1492,
"step": 464896
},
{
"epoch": 1.0,
"learning_rate": 4.2379810700338e-05,
"loss": 4.15,
"step": 465408
},
{
"epoch": 1.0,
"learning_rate": 4.237142475282748e-05,
"loss": 4.1417,
"step": 465920
},
{
"epoch": 1.0,
"learning_rate": 4.236303880531696e-05,
"loss": 4.1511,
"step": 466432
},
{
"epoch": 1.0,
"learning_rate": 4.235465285780644e-05,
"loss": 4.1444,
"step": 466944
},
{
"epoch": 1.0,
"learning_rate": 4.234626691029591e-05,
"loss": 4.1474,
"step": 467456
},
{
"epoch": 1.0,
"learning_rate": 4.233788096278539e-05,
"loss": 4.1621,
"step": 467968
},
{
"epoch": 1.0,
"learning_rate": 4.232949501527487e-05,
"loss": 4.1571,
"step": 468480
},
{
"epoch": 1.0,
"learning_rate": 4.232112544656809e-05,
"loss": 4.1581,
"step": 468992
},
{
"epoch": 1.0,
"learning_rate": 4.231273949905756e-05,
"loss": 4.1523,
"step": 469504
},
{
"epoch": 1.0,
"learning_rate": 4.230435355154704e-05,
"loss": 4.1585,
"step": 470016
},
{
"epoch": 1.0,
"learning_rate": 4.229596760403652e-05,
"loss": 4.1374,
"step": 470528
},
{
"epoch": 1.0,
"learning_rate": 4.2287581656526e-05,
"loss": 4.157,
"step": 471040
},
{
"epoch": 1.0,
"learning_rate": 4.227921208781922e-05,
"loss": 4.1442,
"step": 471552
},
{
"epoch": 1.0,
"learning_rate": 4.227084251911243e-05,
"loss": 4.1355,
"step": 472064
},
{
"epoch": 1.0,
"learning_rate": 4.226245657160191e-05,
"loss": 4.1423,
"step": 472576
},
{
"epoch": 1.0,
"learning_rate": 4.2254070624091386e-05,
"loss": 4.1464,
"step": 473088
},
{
"epoch": 1.01,
"learning_rate": 4.2245684676580866e-05,
"loss": 4.1466,
"step": 473600
},
{
"epoch": 1.01,
"learning_rate": 4.2237298729070346e-05,
"loss": 4.1565,
"step": 474112
},
{
"epoch": 1.01,
"learning_rate": 4.2228912781559826e-05,
"loss": 4.1528,
"step": 474624
},
{
"epoch": 1.01,
"learning_rate": 4.2220526834049306e-05,
"loss": 4.1497,
"step": 475136
},
{
"epoch": 1.01,
"learning_rate": 4.2212157265342515e-05,
"loss": 4.1383,
"step": 475648
},
{
"epoch": 1.01,
"learning_rate": 4.2203771317831995e-05,
"loss": 4.1498,
"step": 476160
},
{
"epoch": 1.01,
"learning_rate": 4.2195385370321475e-05,
"loss": 4.1484,
"step": 476672
},
{
"epoch": 1.01,
"learning_rate": 4.2186999422810955e-05,
"loss": 4.1408,
"step": 477184
},
{
"epoch": 1.01,
"learning_rate": 4.217861347530044e-05,
"loss": 4.1376,
"step": 477696
},
{
"epoch": 1.01,
"learning_rate": 4.217022752778992e-05,
"loss": 4.1326,
"step": 478208
},
{
"epoch": 1.01,
"learning_rate": 4.21618415802794e-05,
"loss": 4.1435,
"step": 478720
},
{
"epoch": 1.01,
"learning_rate": 4.215345563276888e-05,
"loss": 4.15,
"step": 479232
},
{
"epoch": 1.01,
"learning_rate": 4.214508606406209e-05,
"loss": 4.1444,
"step": 479744
},
{
"epoch": 1.01,
"learning_rate": 4.213670011655157e-05,
"loss": 4.1389,
"step": 480256
},
{
"epoch": 1.01,
"learning_rate": 4.212831416904105e-05,
"loss": 4.1459,
"step": 480768
},
{
"epoch": 1.01,
"learning_rate": 4.211994460033426e-05,
"loss": 4.1373,
"step": 481280
},
{
"epoch": 1.01,
"learning_rate": 4.211155865282374e-05,
"loss": 4.1504,
"step": 481792
},
{
"epoch": 1.01,
"learning_rate": 4.210317270531322e-05,
"loss": 4.1352,
"step": 482304
},
{
"epoch": 1.01,
"learning_rate": 4.20947867578027e-05,
"loss": 4.1228,
"step": 482816
},
{
"epoch": 1.01,
"learning_rate": 4.208640081029218e-05,
"loss": 4.1502,
"step": 483328
},
{
"epoch": 1.01,
"learning_rate": 4.207801486278166e-05,
"loss": 4.1398,
"step": 483840
},
{
"epoch": 1.01,
"learning_rate": 4.206962891527114e-05,
"loss": 4.1403,
"step": 484352
},
{
"epoch": 1.01,
"learning_rate": 4.2061242967760626e-05,
"loss": 4.135,
"step": 484864
},
{
"epoch": 1.01,
"learning_rate": 4.2052873399053835e-05,
"loss": 4.1336,
"step": 485376
},
{
"epoch": 1.01,
"learning_rate": 4.2044487451543315e-05,
"loss": 4.1352,
"step": 485888
},
{
"epoch": 1.01,
"learning_rate": 4.2036101504032795e-05,
"loss": 4.1345,
"step": 486400
},
{
"epoch": 1.01,
"learning_rate": 4.2027715556522275e-05,
"loss": 4.1299,
"step": 486912
},
{
"epoch": 1.01,
"learning_rate": 4.201932960901175e-05,
"loss": 4.1353,
"step": 487424
},
{
"epoch": 1.01,
"learning_rate": 4.2010960040304964e-05,
"loss": 4.1389,
"step": 487936
},
{
"epoch": 1.01,
"learning_rate": 4.2002574092794444e-05,
"loss": 4.1331,
"step": 488448
},
{
"epoch": 1.01,
"learning_rate": 4.1994188145283924e-05,
"loss": 4.1318,
"step": 488960
},
{
"epoch": 1.01,
"learning_rate": 4.19858021977734e-05,
"loss": 4.15,
"step": 489472
},
{
"epoch": 1.01,
"learning_rate": 4.197741625026288e-05,
"loss": 4.1175,
"step": 489984
},
{
"epoch": 1.01,
"learning_rate": 4.196904668155609e-05,
"loss": 4.1238,
"step": 490496
},
{
"epoch": 1.01,
"learning_rate": 4.196066073404557e-05,
"loss": 4.1351,
"step": 491008
},
{
"epoch": 1.01,
"learning_rate": 4.195227478653505e-05,
"loss": 4.1405,
"step": 491520
},
{
"epoch": 1.01,
"learning_rate": 4.194388883902453e-05,
"loss": 4.1279,
"step": 492032
},
{
"epoch": 1.01,
"learning_rate": 4.193550289151401e-05,
"loss": 4.128,
"step": 492544
},
{
"epoch": 1.01,
"learning_rate": 4.192713332280722e-05,
"loss": 4.1187,
"step": 493056
},
{
"epoch": 1.01,
"learning_rate": 4.19187473752967e-05,
"loss": 4.1338,
"step": 493568
},
{
"epoch": 1.01,
"learning_rate": 4.191036142778618e-05,
"loss": 4.1438,
"step": 494080
},
{
"epoch": 1.01,
"learning_rate": 4.19019918590794e-05,
"loss": 4.1344,
"step": 494592
},
{
"epoch": 1.01,
"learning_rate": 4.189360591156887e-05,
"loss": 4.1344,
"step": 495104
},
{
"epoch": 1.01,
"learning_rate": 4.188521996405835e-05,
"loss": 4.145,
"step": 495616
},
{
"epoch": 1.01,
"learning_rate": 4.187683401654783e-05,
"loss": 4.1578,
"step": 496128
},
{
"epoch": 1.01,
"learning_rate": 4.186844806903731e-05,
"loss": 4.1253,
"step": 496640
},
{
"epoch": 1.01,
"learning_rate": 4.1860078500330526e-05,
"loss": 4.1312,
"step": 497152
},
{
"epoch": 1.01,
"learning_rate": 4.1851692552820006e-05,
"loss": 4.1428,
"step": 497664
},
{
"epoch": 1.01,
"learning_rate": 4.1843306605309486e-05,
"loss": 4.1184,
"step": 498176
},
{
"epoch": 1.01,
"learning_rate": 4.1834920657798966e-05,
"loss": 4.1358,
"step": 498688
},
{
"epoch": 1.01,
"learning_rate": 4.1826534710288446e-05,
"loss": 4.1348,
"step": 499200
},
{
"epoch": 1.01,
"learning_rate": 4.1818148762777926e-05,
"loss": 4.1379,
"step": 499712
},
{
"epoch": 1.01,
"learning_rate": 4.1809762815267406e-05,
"loss": 4.1399,
"step": 500224
},
{
"epoch": 1.01,
"learning_rate": 4.1801376867756886e-05,
"loss": 4.1213,
"step": 500736
},
{
"epoch": 1.01,
"learning_rate": 4.1792990920246366e-05,
"loss": 4.1338,
"step": 501248
},
{
"epoch": 1.01,
"learning_rate": 4.1784604972735846e-05,
"loss": 4.1252,
"step": 501760
},
{
"epoch": 1.01,
"learning_rate": 4.1776219025225326e-05,
"loss": 4.1326,
"step": 502272
},
{
"epoch": 1.01,
"learning_rate": 4.1767833077714806e-05,
"loss": 4.1385,
"step": 502784
},
{
"epoch": 1.01,
"learning_rate": 4.1759463509008015e-05,
"loss": 4.1206,
"step": 503296
},
{
"epoch": 1.02,
"learning_rate": 4.1751077561497495e-05,
"loss": 4.1304,
"step": 503808
},
{
"epoch": 1.02,
"learning_rate": 4.174270799279071e-05,
"loss": 4.1238,
"step": 504320
},
{
"epoch": 1.02,
"learning_rate": 4.173432204528019e-05,
"loss": 4.123,
"step": 504832
},
{
"epoch": 1.02,
"learning_rate": 4.172593609776967e-05,
"loss": 4.1313,
"step": 505344
},
{
"epoch": 1.02,
"learning_rate": 4.171755015025915e-05,
"loss": 4.1331,
"step": 505856
},
{
"epoch": 1.02,
"learning_rate": 4.170916420274863e-05,
"loss": 4.1391,
"step": 506368
},
{
"epoch": 1.02,
"learning_rate": 4.170077825523811e-05,
"loss": 4.1253,
"step": 506880
},
{
"epoch": 1.02,
"learning_rate": 4.1692392307727584e-05,
"loss": 4.1246,
"step": 507392
},
{
"epoch": 1.02,
"learning_rate": 4.1684006360217064e-05,
"loss": 4.131,
"step": 507904
},
{
"epoch": 1.02,
"learning_rate": 4.1675620412706544e-05,
"loss": 4.1281,
"step": 508416
},
{
"epoch": 1.02,
"learning_rate": 4.166725084399975e-05,
"loss": 4.1344,
"step": 508928
},
{
"epoch": 1.02,
"learning_rate": 4.165886489648923e-05,
"loss": 4.1228,
"step": 509440
},
{
"epoch": 1.02,
"learning_rate": 4.165047894897872e-05,
"loss": 4.1213,
"step": 509952
},
{
"epoch": 1.02,
"learning_rate": 4.16420930014682e-05,
"loss": 4.1276,
"step": 510464
},
{
"epoch": 1.02,
"learning_rate": 4.163370705395768e-05,
"loss": 4.1382,
"step": 510976
},
{
"epoch": 1.02,
"learning_rate": 4.162532110644716e-05,
"loss": 4.1086,
"step": 511488
},
{
"epoch": 1.02,
"learning_rate": 4.161693515893664e-05,
"loss": 4.1248,
"step": 512000
},
{
"epoch": 1.02,
"learning_rate": 4.160856559022985e-05,
"loss": 4.125,
"step": 512512
},
{
"epoch": 1.02,
"learning_rate": 4.160017964271933e-05,
"loss": 4.1281,
"step": 513024
},
{
"epoch": 1.02,
"learning_rate": 4.159179369520881e-05,
"loss": 4.1135,
"step": 513536
},
{
"epoch": 1.02,
"learning_rate": 4.158342412650202e-05,
"loss": 4.1299,
"step": 514048
},
{
"epoch": 1.02,
"learning_rate": 4.15750381789915e-05,
"loss": 4.1213,
"step": 514560
},
{
"epoch": 1.02,
"learning_rate": 4.156665223148098e-05,
"loss": 4.122,
"step": 515072
},
{
"epoch": 1.02,
"learning_rate": 4.155826628397046e-05,
"loss": 4.1288,
"step": 515584
},
{
"epoch": 1.02,
"learning_rate": 4.154988033645994e-05,
"loss": 4.1173,
"step": 516096
},
{
"epoch": 1.02,
"learning_rate": 4.154149438894942e-05,
"loss": 4.1247,
"step": 516608
},
{
"epoch": 1.02,
"learning_rate": 4.1533108441438904e-05,
"loss": 4.1388,
"step": 517120
},
{
"epoch": 1.02,
"learning_rate": 4.1524722493928384e-05,
"loss": 4.1289,
"step": 517632
},
{
"epoch": 1.02,
"learning_rate": 4.1516336546417864e-05,
"loss": 4.1199,
"step": 518144
},
{
"epoch": 1.02,
"learning_rate": 4.150796697771107e-05,
"loss": 4.1314,
"step": 518656
},
{
"epoch": 1.02,
"learning_rate": 4.149958103020055e-05,
"loss": 4.128,
"step": 519168
},
{
"epoch": 1.02,
"learning_rate": 4.149121146149376e-05,
"loss": 4.1129,
"step": 519680
},
{
"epoch": 1.02,
"learning_rate": 4.148282551398324e-05,
"loss": 4.1285,
"step": 520192
},
{
"epoch": 1.02,
"learning_rate": 4.147443956647272e-05,
"loss": 4.1166,
"step": 520704
},
{
"epoch": 1.02,
"learning_rate": 4.14660536189622e-05,
"loss": 4.1172,
"step": 521216
},
{
"epoch": 1.02,
"learning_rate": 4.145766767145168e-05,
"loss": 4.1196,
"step": 521728
},
{
"epoch": 1.02,
"learning_rate": 4.144928172394116e-05,
"loss": 4.1192,
"step": 522240
},
{
"epoch": 1.02,
"learning_rate": 4.144089577643064e-05,
"loss": 4.1158,
"step": 522752
},
{
"epoch": 1.02,
"learning_rate": 4.143250982892012e-05,
"loss": 4.115,
"step": 523264
},
{
"epoch": 1.02,
"learning_rate": 4.14241238814096e-05,
"loss": 4.1154,
"step": 523776
},
{
"epoch": 1.02,
"learning_rate": 4.141573793389908e-05,
"loss": 4.131,
"step": 524288
},
{
"epoch": 1.02,
"learning_rate": 4.140735198638856e-05,
"loss": 4.1233,
"step": 524800
},
{
"epoch": 1.02,
"learning_rate": 4.139896603887804e-05,
"loss": 4.1257,
"step": 525312
},
{
"epoch": 1.02,
"learning_rate": 4.139058009136752e-05,
"loss": 4.1073,
"step": 525824
},
{
"epoch": 1.02,
"learning_rate": 4.138221052266073e-05,
"loss": 4.1337,
"step": 526336
},
{
"epoch": 1.02,
"learning_rate": 4.137382457515021e-05,
"loss": 4.1252,
"step": 526848
},
{
"epoch": 1.02,
"learning_rate": 4.136543862763969e-05,
"loss": 4.1234,
"step": 527360
},
{
"epoch": 1.02,
"learning_rate": 4.1357085437736635e-05,
"loss": 4.1233,
"step": 527872
},
{
"epoch": 1.02,
"learning_rate": 4.1348699490226115e-05,
"loss": 4.1258,
"step": 528384
},
{
"epoch": 1.02,
"learning_rate": 4.1340313542715595e-05,
"loss": 4.1161,
"step": 528896
},
{
"epoch": 1.02,
"learning_rate": 4.1331927595205075e-05,
"loss": 4.1363,
"step": 529408
},
{
"epoch": 1.02,
"learning_rate": 4.1323541647694555e-05,
"loss": 4.1048,
"step": 529920
},
{
"epoch": 1.02,
"learning_rate": 4.1315155700184035e-05,
"loss": 4.1258,
"step": 530432
},
{
"epoch": 1.02,
"learning_rate": 4.1306769752673515e-05,
"loss": 4.1155,
"step": 530944
},
{
"epoch": 1.02,
"learning_rate": 4.1298400183966724e-05,
"loss": 4.1161,
"step": 531456
},
{
"epoch": 1.02,
"learning_rate": 4.1290014236456204e-05,
"loss": 4.1178,
"step": 531968
},
{
"epoch": 1.02,
"learning_rate": 4.128164466774942e-05,
"loss": 4.1146,
"step": 532480
},
{
"epoch": 1.02,
"learning_rate": 4.127325872023889e-05,
"loss": 4.1301,
"step": 532992
},
{
"epoch": 1.02,
"learning_rate": 4.126487277272837e-05,
"loss": 4.1084,
"step": 533504
},
{
"epoch": 1.02,
"learning_rate": 4.125648682521785e-05,
"loss": 4.124,
"step": 534016
},
{
"epoch": 1.03,
"eval_loss": 4.125783443450928,
"eval_runtime": 283.4627,
"eval_samples_per_second": 1346.177,
"eval_steps_per_second": 42.069,
"step": 534240
},
{
"epoch": 0.0,
"learning_rate": 4.124810087770733e-05,
"loss": 4.124,
"step": 534528
},
{
"epoch": 0.0,
"learning_rate": 4.123971493019681e-05,
"loss": 4.1092,
"step": 535040
},
{
"epoch": 0.0,
"learning_rate": 4.123132898268629e-05,
"loss": 4.1231,
"step": 535552
},
{
"epoch": 0.0,
"learning_rate": 4.122294303517577e-05,
"loss": 4.1169,
"step": 536064
},
{
"epoch": 0.0,
"learning_rate": 4.121455708766526e-05,
"loss": 4.1192,
"step": 536576
},
{
"epoch": 0.0,
"learning_rate": 4.120617114015474e-05,
"loss": 4.1148,
"step": 537088
},
{
"epoch": 0.0,
"learning_rate": 4.119778519264422e-05,
"loss": 4.1165,
"step": 537600
},
{
"epoch": 0.0,
"learning_rate": 4.11893992451337e-05,
"loss": 4.1099,
"step": 538112
},
{
"epoch": 0.0,
"learning_rate": 4.118101329762318e-05,
"loss": 4.1189,
"step": 538624
},
{
"epoch": 0.0,
"learning_rate": 4.117262735011266e-05,
"loss": 4.1209,
"step": 539136
},
{
"epoch": 0.0,
"learning_rate": 4.116424140260213e-05,
"loss": 4.1188,
"step": 539648
},
{
"epoch": 0.0,
"learning_rate": 4.115585545509161e-05,
"loss": 4.1169,
"step": 540160
},
{
"epoch": 0.0,
"learning_rate": 4.114748588638483e-05,
"loss": 4.114,
"step": 540672
},
{
"epoch": 0.0,
"learning_rate": 4.11390999388743e-05,
"loss": 4.1115,
"step": 541184
},
{
"epoch": 0.0,
"learning_rate": 4.113071399136378e-05,
"loss": 4.114,
"step": 541696
},
{
"epoch": 0.0,
"learning_rate": 4.112232804385326e-05,
"loss": 4.1037,
"step": 542208
},
{
"epoch": 0.0,
"learning_rate": 4.111394209634274e-05,
"loss": 4.1117,
"step": 542720
},
{
"epoch": 0.0,
"learning_rate": 4.110555614883223e-05,
"loss": 4.1111,
"step": 543232
},
{
"epoch": 0.0,
"learning_rate": 4.109718658012544e-05,
"loss": 4.1112,
"step": 543744
},
{
"epoch": 0.0,
"learning_rate": 4.108880063261492e-05,
"loss": 4.1201,
"step": 544256
},
{
"epoch": 0.0,
"learning_rate": 4.10804146851044e-05,
"loss": 4.1232,
"step": 544768
},
{
"epoch": 0.0,
"learning_rate": 4.107202873759388e-05,
"loss": 4.1195,
"step": 545280
},
{
"epoch": 0.0,
"learning_rate": 4.106364279008336e-05,
"loss": 4.1135,
"step": 545792
},
{
"epoch": 0.0,
"learning_rate": 4.1055273221376566e-05,
"loss": 4.1186,
"step": 546304
},
{
"epoch": 0.0,
"learning_rate": 4.1046887273866046e-05,
"loss": 4.1035,
"step": 546816
},
{
"epoch": 0.0,
"learning_rate": 4.1038501326355526e-05,
"loss": 4.1201,
"step": 547328
},
{
"epoch": 0.0,
"learning_rate": 4.1030131757648735e-05,
"loss": 4.1065,
"step": 547840
},
{
"epoch": 0.0,
"learning_rate": 4.1021745810138215e-05,
"loss": 4.101,
"step": 548352
},
{
"epoch": 0.0,
"learning_rate": 4.1013359862627695e-05,
"loss": 4.1048,
"step": 548864
},
{
"epoch": 0.0,
"learning_rate": 4.100497391511718e-05,
"loss": 4.1107,
"step": 549376
},
{
"epoch": 0.01,
"learning_rate": 4.099658796760666e-05,
"loss": 4.109,
"step": 549888
},
{
"epoch": 0.01,
"learning_rate": 4.098820202009614e-05,
"loss": 4.1194,
"step": 550400
},
{
"epoch": 0.01,
"learning_rate": 4.097981607258562e-05,
"loss": 4.1173,
"step": 550912
},
{
"epoch": 0.01,
"learning_rate": 4.09714301250751e-05,
"loss": 4.1093,
"step": 551424
},
{
"epoch": 0.01,
"learning_rate": 4.096306055636831e-05,
"loss": 4.1043,
"step": 551936
},
{
"epoch": 0.01,
"learning_rate": 4.095467460885779e-05,
"loss": 4.1153,
"step": 552448
},
{
"epoch": 0.01,
"learning_rate": 4.094628866134727e-05,
"loss": 4.1123,
"step": 552960
},
{
"epoch": 0.01,
"learning_rate": 4.093790271383675e-05,
"loss": 4.1053,
"step": 553472
},
{
"epoch": 0.01,
"learning_rate": 4.092951676632623e-05,
"loss": 4.1035,
"step": 553984
},
{
"epoch": 0.01,
"learning_rate": 4.092113081881571e-05,
"loss": 4.0947,
"step": 554496
},
{
"epoch": 0.01,
"learning_rate": 4.091274487130519e-05,
"loss": 4.1047,
"step": 555008
},
{
"epoch": 0.01,
"learning_rate": 4.0904358923794664e-05,
"loss": 4.1175,
"step": 555520
},
{
"epoch": 0.01,
"learning_rate": 4.089597297628415e-05,
"loss": 4.1076,
"step": 556032
},
{
"epoch": 0.01,
"learning_rate": 4.088758702877363e-05,
"loss": 4.1022,
"step": 556544
},
{
"epoch": 0.01,
"learning_rate": 4.087920108126311e-05,
"loss": 4.111,
"step": 557056
},
{
"epoch": 0.01,
"learning_rate": 4.087081513375259e-05,
"loss": 4.0991,
"step": 557568
},
{
"epoch": 0.01,
"learning_rate": 4.08624455650458e-05,
"loss": 4.115,
"step": 558080
},
{
"epoch": 0.01,
"learning_rate": 4.0854075996339015e-05,
"loss": 4.1037,
"step": 558592
},
{
"epoch": 0.01,
"learning_rate": 4.0845690048828495e-05,
"loss": 4.0846,
"step": 559104
},
{
"epoch": 0.01,
"learning_rate": 4.083730410131797e-05,
"loss": 4.113,
"step": 559616
},
{
"epoch": 0.01,
"learning_rate": 4.082891815380745e-05,
"loss": 4.1039,
"step": 560128
},
{
"epoch": 0.01,
"learning_rate": 4.082053220629693e-05,
"loss": 4.1065,
"step": 560640
},
{
"epoch": 0.01,
"learning_rate": 4.081216263759014e-05,
"loss": 4.0983,
"step": 561152
},
{
"epoch": 0.01,
"learning_rate": 4.080377669007962e-05,
"loss": 4.0973,
"step": 561664
},
{
"epoch": 0.01,
"learning_rate": 4.07953907425691e-05,
"loss": 4.0992,
"step": 562176
},
{
"epoch": 0.01,
"learning_rate": 4.078702117386231e-05,
"loss": 4.0965,
"step": 562688
},
{
"epoch": 0.01,
"learning_rate": 4.077863522635179e-05,
"loss": 4.0994,
"step": 563200
},
{
"epoch": 0.01,
"learning_rate": 4.077024927884127e-05,
"loss": 4.0968,
"step": 563712
},
{
"epoch": 0.01,
"learning_rate": 4.076186333133075e-05,
"loss": 4.1109,
"step": 564224
},
{
"epoch": 0.01,
"learning_rate": 4.075349376262397e-05,
"loss": 4.092,
"step": 564736
},
{
"epoch": 0.01,
"learning_rate": 4.074510781511344e-05,
"loss": 4.0999,
"step": 565248
},
{
"epoch": 0.01,
"learning_rate": 4.073672186760292e-05,
"loss": 4.1127,
"step": 565760
},
{
"epoch": 0.01,
"learning_rate": 4.07283359200924e-05,
"loss": 4.0828,
"step": 566272
},
{
"epoch": 0.01,
"learning_rate": 4.071994997258188e-05,
"loss": 4.0873,
"step": 566784
},
{
"epoch": 0.01,
"learning_rate": 4.071156402507136e-05,
"loss": 4.1039,
"step": 567296
},
{
"epoch": 0.01,
"learning_rate": 4.070317807756084e-05,
"loss": 4.103,
"step": 567808
},
{
"epoch": 0.01,
"learning_rate": 4.069479213005032e-05,
"loss": 4.0916,
"step": 568320
},
{
"epoch": 0.01,
"learning_rate": 4.06864061825398e-05,
"loss": 4.0958,
"step": 568832
},
{
"epoch": 0.01,
"learning_rate": 4.067805299263675e-05,
"loss": 4.0835,
"step": 569344
},
{
"epoch": 0.01,
"learning_rate": 4.066966704512623e-05,
"loss": 4.1017,
"step": 569856
},
{
"epoch": 0.01,
"learning_rate": 4.066128109761571e-05,
"loss": 4.1041,
"step": 570368
},
{
"epoch": 0.01,
"learning_rate": 4.065289515010519e-05,
"loss": 4.1004,
"step": 570880
},
{
"epoch": 0.01,
"learning_rate": 4.064450920259467e-05,
"loss": 4.1004,
"step": 571392
},
{
"epoch": 0.01,
"learning_rate": 4.0636123255084147e-05,
"loss": 4.1105,
"step": 571904
},
{
"epoch": 0.01,
"learning_rate": 4.0627737307573627e-05,
"loss": 4.1205,
"step": 572416
},
{
"epoch": 0.01,
"learning_rate": 4.0619351360063106e-05,
"loss": 4.0904,
"step": 572928
},
{
"epoch": 0.01,
"learning_rate": 4.0610965412552586e-05,
"loss": 4.0949,
"step": 573440
},
{
"epoch": 0.01,
"learning_rate": 4.0602595843845796e-05,
"loss": 4.1097,
"step": 573952
},
{
"epoch": 0.01,
"learning_rate": 4.0594209896335276e-05,
"loss": 4.087,
"step": 574464
},
{
"epoch": 0.01,
"learning_rate": 4.058584032762849e-05,
"loss": 4.0971,
"step": 574976
},
{
"epoch": 0.01,
"learning_rate": 4.057745438011797e-05,
"loss": 4.1007,
"step": 575488
},
{
"epoch": 0.01,
"learning_rate": 4.056906843260745e-05,
"loss": 4.1048,
"step": 576000
},
{
"epoch": 0.01,
"learning_rate": 4.056068248509693e-05,
"loss": 4.1073,
"step": 576512
},
{
"epoch": 0.01,
"learning_rate": 4.055229653758641e-05,
"loss": 4.0878,
"step": 577024
},
{
"epoch": 0.01,
"learning_rate": 4.054391059007589e-05,
"loss": 4.0969,
"step": 577536
},
{
"epoch": 0.01,
"learning_rate": 4.053552464256537e-05,
"loss": 4.0908,
"step": 578048
},
{
"epoch": 0.01,
"learning_rate": 4.052713869505485e-05,
"loss": 4.099,
"step": 578560
},
{
"epoch": 0.01,
"learning_rate": 4.0518752747544324e-05,
"loss": 4.1007,
"step": 579072
},
{
"epoch": 0.01,
"learning_rate": 4.0510366800033804e-05,
"loss": 4.0895,
"step": 579584
},
{
"epoch": 0.02,
"learning_rate": 4.0501980852523284e-05,
"loss": 4.0949,
"step": 580096
},
{
"epoch": 0.02,
"learning_rate": 4.04936112838165e-05,
"loss": 4.0921,
"step": 580608
},
{
"epoch": 0.02,
"learning_rate": 4.048524171510971e-05,
"loss": 4.0889,
"step": 581120
},
{
"epoch": 0.02,
"learning_rate": 4.047685576759919e-05,
"loss": 4.0964,
"step": 581632
},
{
"epoch": 0.02,
"learning_rate": 4.0468469820088676e-05,
"loss": 4.0984,
"step": 582144
},
{
"epoch": 0.02,
"learning_rate": 4.0460083872578156e-05,
"loss": 4.1045,
"step": 582656
},
{
"epoch": 0.02,
"learning_rate": 4.045169792506763e-05,
"loss": 4.0949,
"step": 583168
},
{
"epoch": 0.02,
"learning_rate": 4.044331197755711e-05,
"loss": 4.0875,
"step": 583680
},
{
"epoch": 0.02,
"learning_rate": 4.043492603004659e-05,
"loss": 4.0975,
"step": 584192
},
{
"epoch": 0.02,
"learning_rate": 4.04265564613398e-05,
"loss": 4.0961,
"step": 584704
},
{
"epoch": 0.02,
"learning_rate": 4.041817051382928e-05,
"loss": 4.0969,
"step": 585216
},
{
"epoch": 0.02,
"learning_rate": 4.040978456631876e-05,
"loss": 4.0923,
"step": 585728
},
{
"epoch": 0.02,
"learning_rate": 4.0401414997611974e-05,
"loss": 4.0883,
"step": 586240
},
{
"epoch": 0.02,
"learning_rate": 4.039302905010145e-05,
"loss": 4.093,
"step": 586752
},
{
"epoch": 0.02,
"learning_rate": 4.038464310259093e-05,
"loss": 4.1065,
"step": 587264
},
{
"epoch": 0.02,
"learning_rate": 4.0376257155080414e-05,
"loss": 4.0777,
"step": 587776
},
{
"epoch": 0.02,
"learning_rate": 4.0367871207569894e-05,
"loss": 4.0913,
"step": 588288
},
{
"epoch": 0.02,
"learning_rate": 4.0359485260059374e-05,
"loss": 4.0897,
"step": 588800
},
{
"epoch": 0.02,
"learning_rate": 4.0351099312548853e-05,
"loss": 4.094,
"step": 589312
},
{
"epoch": 0.02,
"learning_rate": 4.0342713365038333e-05,
"loss": 4.084,
"step": 589824
},
{
"epoch": 0.02,
"learning_rate": 4.033432741752781e-05,
"loss": 4.0982,
"step": 590336
},
{
"epoch": 0.02,
"learning_rate": 4.032595784882102e-05,
"loss": 4.0828,
"step": 590848
},
{
"epoch": 0.02,
"learning_rate": 4.031758828011423e-05,
"loss": 4.0923,
"step": 591360
},
{
"epoch": 0.02,
"learning_rate": 4.030920233260371e-05,
"loss": 4.0967,
"step": 591872
},
{
"epoch": 0.02,
"learning_rate": 4.030081638509319e-05,
"loss": 4.0817,
"step": 592384
},
{
"epoch": 0.02,
"learning_rate": 4.029243043758267e-05,
"loss": 4.0922,
"step": 592896
},
{
"epoch": 0.02,
"learning_rate": 4.028404449007215e-05,
"loss": 4.1042,
"step": 593408
},
{
"epoch": 0.02,
"learning_rate": 4.027565854256163e-05,
"loss": 4.095,
"step": 593920
},
{
"epoch": 0.02,
"learning_rate": 4.026727259505111e-05,
"loss": 4.0883,
"step": 594432
},
{
"epoch": 0.02,
"learning_rate": 4.025888664754059e-05,
"loss": 4.0939,
"step": 594944
},
{
"epoch": 0.02,
"learning_rate": 4.025050070003008e-05,
"loss": 4.0985,
"step": 595456
},
{
"epoch": 0.02,
"learning_rate": 4.024211475251956e-05,
"loss": 4.0831,
"step": 595968
},
{
"epoch": 0.02,
"learning_rate": 4.0233761562616496e-05,
"loss": 4.0951,
"step": 596480
},
{
"epoch": 0.02,
"learning_rate": 4.0225375615105976e-05,
"loss": 4.0797,
"step": 596992
},
{
"epoch": 0.02,
"learning_rate": 4.0216989667595456e-05,
"loss": 4.0857,
"step": 597504
},
{
"epoch": 0.02,
"learning_rate": 4.0208603720084936e-05,
"loss": 4.084,
"step": 598016
},
{
"epoch": 0.02,
"learning_rate": 4.0200217772574416e-05,
"loss": 4.0882,
"step": 598528
},
{
"epoch": 0.02,
"learning_rate": 4.0191831825063896e-05,
"loss": 4.0831,
"step": 599040
},
{
"epoch": 0.02,
"learning_rate": 4.0183445877553376e-05,
"loss": 4.0844,
"step": 599552
},
{
"epoch": 0.02,
"learning_rate": 4.0175059930042856e-05,
"loss": 4.0795,
"step": 600064
},
{
"epoch": 0.02,
"learning_rate": 4.0166673982532336e-05,
"loss": 4.0989,
"step": 600576
},
{
"epoch": 0.02,
"learning_rate": 4.0158304413825545e-05,
"loss": 4.0952,
"step": 601088
},
{
"epoch": 0.02,
"learning_rate": 4.014991846631503e-05,
"loss": 4.0937,
"step": 601600
},
{
"epoch": 0.02,
"learning_rate": 4.014154889760824e-05,
"loss": 4.0763,
"step": 602112
},
{
"epoch": 0.02,
"learning_rate": 4.013316295009772e-05,
"loss": 4.102,
"step": 602624
},
{
"epoch": 0.02,
"learning_rate": 4.01247770025872e-05,
"loss": 4.0878,
"step": 603136
},
{
"epoch": 0.02,
"learning_rate": 4.011639105507668e-05,
"loss": 4.0919,
"step": 603648
},
{
"epoch": 0.02,
"learning_rate": 4.010800510756616e-05,
"loss": 4.0961,
"step": 604160
},
{
"epoch": 0.02,
"learning_rate": 4.0099619160055634e-05,
"loss": 4.0877,
"step": 604672
},
{
"epoch": 0.02,
"learning_rate": 4.0091233212545114e-05,
"loss": 4.0837,
"step": 605184
},
{
"epoch": 0.02,
"learning_rate": 4.0082847265034594e-05,
"loss": 4.1032,
"step": 605696
},
{
"epoch": 0.02,
"learning_rate": 4.0074461317524074e-05,
"loss": 4.0747,
"step": 606208
},
{
"epoch": 0.02,
"learning_rate": 4.006609174881728e-05,
"loss": 4.0942,
"step": 606720
},
{
"epoch": 0.02,
"learning_rate": 4.005770580130677e-05,
"loss": 4.0832,
"step": 607232
},
{
"epoch": 0.02,
"learning_rate": 4.004931985379625e-05,
"loss": 4.0865,
"step": 607744
},
{
"epoch": 0.02,
"learning_rate": 4.004093390628573e-05,
"loss": 4.0831,
"step": 608256
},
{
"epoch": 0.02,
"learning_rate": 4.003256433757894e-05,
"loss": 4.082,
"step": 608768
},
{
"epoch": 0.02,
"learning_rate": 4.002417839006842e-05,
"loss": 4.0955,
"step": 609280
},
{
"epoch": 0.02,
"learning_rate": 4.0015808821361634e-05,
"loss": 4.0813,
"step": 609792
},
{
"epoch": 0.02,
"learning_rate": 4.000742287385111e-05,
"loss": 4.0886,
"step": 610304
},
{
"epoch": 0.03,
"eval_loss": 4.101009368896484,
"eval_runtime": 290.5251,
"eval_samples_per_second": 1313.453,
"eval_steps_per_second": 41.046,
"step": 610560
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 2.5232662109985002e+17,
"trial_name": null,
"trial_params": null
}