abhinavp's picture
Training in progress, epoch 0, checkpoint
2e82723 verified
{
"best_metric": 4.389575481414795,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/lstm/1/checkpoints/checkpoint-228957",
"epoch": 0.025000278439663435,
"eval_steps": 10,
"global_step": 228957,
"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": 10.8219,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5832,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.052,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9797,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9499,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8229,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.6944,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.5888,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5088,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4229,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3653,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.2969,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2303,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.1577,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.094,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0489,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0027,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 5.9537,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9202,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984066699730012e-05,
"loss": 5.8778,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8506,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 5.8127,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 5.778,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.7559,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7247,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.6987,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.6756,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6553,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6203,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6078,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.5819,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 5.5633,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 5.5515,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5349,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5148,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5054,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.4919,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4719,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.455,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4455,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4202,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4197,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.3909,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.3909,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.3848,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3749,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.3488,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.3474,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 5.3423,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3211,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3062,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3035,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956404538107908e-05,
"loss": 5.3094,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2757,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.2972,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2573,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.2673,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2459,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2428,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2334,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.228,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.2075,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948021866358134e-05,
"loss": 5.2142,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.1975,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.2047,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.1863,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.1765,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1603,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1681,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1613,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1433,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940477789359412e-05,
"loss": 5.1449,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.93963919460836e-05,
"loss": 5.136,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.1324,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1294,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371250482355776e-05,
"loss": 5.123,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1113,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 5.0939,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346109018627945e-05,
"loss": 5.1007,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 5.0909,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 5.0932,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 5.0856,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.0745,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 5.0537,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295809712368554e-05,
"loss": 5.0601,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 5.0625,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 5.0569,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 5.047,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 5.0389,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925389635361968e-05,
"loss": 5.0285,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924551040610916e-05,
"loss": 5.022,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923712445859864e-05,
"loss": 5.019,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922873851108812e-05,
"loss": 5.0272,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92203525635776e-05,
"loss": 5.0159,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921198299487081e-05,
"loss": 4.992,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920359704736029e-05,
"loss": 4.995,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 5.0002,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918682515233926e-05,
"loss": 4.9978,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917843920482874e-05,
"loss": 4.9846,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917005325731822e-05,
"loss": 4.9839,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916168368861143e-05,
"loss": 4.9724,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915329774110091e-05,
"loss": 4.9708,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914491179359039e-05,
"loss": 4.9765,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.9716,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.9456,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9564,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111384382352036e-05,
"loss": 4.9364,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9102998434841516e-05,
"loss": 4.9402,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.9094612487330996e-05,
"loss": 4.9384,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.9086226539820476e-05,
"loss": 4.9276,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907784059230996e-05,
"loss": 4.9262,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906945464479944e-05,
"loss": 4.9166,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906108507609265e-05,
"loss": 4.9147,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905269912858213e-05,
"loss": 4.9131,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904431318107161e-05,
"loss": 4.9238,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903592723356109e-05,
"loss": 4.8985,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027541286050565e-05,
"loss": 4.8843,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019155338540045e-05,
"loss": 4.8927,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010769391029525e-05,
"loss": 4.9051,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900239982232274e-05,
"loss": 4.8868,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994013874812214e-05,
"loss": 4.8939,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.89856279273017e-05,
"loss": 4.8844,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897724197979118e-05,
"loss": 4.8823,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.896885603228066e-05,
"loss": 4.8683,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.896048646357387e-05,
"loss": 4.8722,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895210051606335e-05,
"loss": 4.8667,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.894371456855283e-05,
"loss": 4.8711,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893532862104231e-05,
"loss": 4.8488,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892695905233552e-05,
"loss": 4.8591,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918573104825e-05,
"loss": 4.8556,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891018715731448e-05,
"loss": 4.8405,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890180120980396e-05,
"loss": 4.8505,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889341526229344e-05,
"loss": 4.8434,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888502931478292e-05,
"loss": 4.8477,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766433672724e-05,
"loss": 4.8431,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886825741976188e-05,
"loss": 4.8246,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.8859871472251365e-05,
"loss": 4.8204,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.8851485524740845e-05,
"loss": 4.8205,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.8843099577230325e-05,
"loss": 4.8246,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.8834713629719805e-05,
"loss": 4.8322,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.8826344061013014e-05,
"loss": 4.8195,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.8817958113502494e-05,
"loss": 4.8109,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809572165991974e-05,
"loss": 4.8084,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801186218481454e-05,
"loss": 4.804,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879281664977466e-05,
"loss": 4.8031,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878443070226414e-05,
"loss": 4.7982,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877604475475362e-05,
"loss": 4.8121,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87676588072431e-05,
"loss": 4.7979,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875927285973258e-05,
"loss": 4.7889,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.87509032910258e-05,
"loss": 4.7849,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.802191257476807,
"eval_runtime": 549.4047,
"eval_samples_per_second": 694.554,
"eval_steps_per_second": 21.705,
"step": 76319
},
{
"epoch": 1.0,
"learning_rate": 4.874251734351528e-05,
"loss": 4.7985,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873413139600475e-05,
"loss": 4.7904,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872574544849423e-05,
"loss": 4.774,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871735950098371e-05,
"loss": 4.7768,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870897355347319e-05,
"loss": 4.7674,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.87006039847664e-05,
"loss": 4.764,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869221803725588e-05,
"loss": 4.7605,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868383208974536e-05,
"loss": 4.7624,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675462521038576e-05,
"loss": 4.7589,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667076573528056e-05,
"loss": 4.7603,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658690626017536e-05,
"loss": 4.7587,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.8650304678507016e-05,
"loss": 4.7625,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8641918730996496e-05,
"loss": 4.7495,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633532783485976e-05,
"loss": 4.7405,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625146835975456e-05,
"loss": 4.7397,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616760888464936e-05,
"loss": 4.722,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608374940954416e-05,
"loss": 4.7357,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.8599988993443896e-05,
"loss": 4.7322,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591603045933376e-05,
"loss": 4.7296,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583217098422856e-05,
"loss": 4.7398,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574847529716065e-05,
"loss": 4.7277,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566461582205545e-05,
"loss": 4.7271,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558075634695025e-05,
"loss": 4.7279,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854970606598824e-05,
"loss": 4.723,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854132011847772e-05,
"loss": 4.7133,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.85329341709672e-05,
"loss": 4.7128,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852454822345668e-05,
"loss": 4.7176,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851616227594616e-05,
"loss": 4.7052,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850779270723937e-05,
"loss": 4.7066,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849940675972885e-05,
"loss": 4.6914,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849102081221833e-05,
"loss": 4.6947,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848263486470781e-05,
"loss": 4.706,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847424891719729e-05,
"loss": 4.6967,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.84658793484905e-05,
"loss": 4.6978,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845749340097998e-05,
"loss": 4.6932,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.8449123832273194e-05,
"loss": 4.6955,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.8440737884762674e-05,
"loss": 4.6921,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.8432351937252154e-05,
"loss": 4.6876,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.8423965989741634e-05,
"loss": 4.689,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.8415580042231114e-05,
"loss": 4.6759,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840719409472059e-05,
"loss": 4.6797,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839880814721007e-05,
"loss": 4.6663,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839042219969955e-05,
"loss": 4.6726,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838203625218903e-05,
"loss": 4.6833,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837365030467851e-05,
"loss": 4.6793,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836526435716799e-05,
"loss": 4.6636,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835687840965747e-05,
"loss": 4.6665,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.8348508840950676e-05,
"loss": 4.671,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834015565104763e-05,
"loss": 4.6516,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833176970353711e-05,
"loss": 4.6511,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832338375602659e-05,
"loss": 4.6536,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831499780851606e-05,
"loss": 4.6654,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830661186100554e-05,
"loss": 4.6406,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829822591349502e-05,
"loss": 4.6665,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.82898399659845e-05,
"loss": 4.6346,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828145401847398e-05,
"loss": 4.6487,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827306807096346e-05,
"loss": 4.6414,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826468212345294e-05,
"loss": 4.6463,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825629617594242e-05,
"loss": 4.6376,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.82479102284319e-05,
"loss": 4.6415,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823954065972511e-05,
"loss": 4.6296,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.82311547122146e-05,
"loss": 4.6374,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222785143507806e-05,
"loss": 4.6295,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214399195997286e-05,
"loss": 4.6355,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206013248486766e-05,
"loss": 4.6269,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197627300976246e-05,
"loss": 4.627,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189241353465726e-05,
"loss": 4.6079,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180855405955206e-05,
"loss": 4.633,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172485837248415e-05,
"loss": 4.6203,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164099889737895e-05,
"loss": 4.6115,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155713942227375e-05,
"loss": 4.6193,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147327994716854e-05,
"loss": 4.6142,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138958426010064e-05,
"loss": 4.6161,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813057247849955e-05,
"loss": 4.6219,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812218653098903e-05,
"loss": 4.62,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811380058347851e-05,
"loss": 4.6059,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810541463596799e-05,
"loss": 4.5991,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809702868845747e-05,
"loss": 4.606,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808864274094695e-05,
"loss": 4.6062,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808025679343642e-05,
"loss": 4.6123,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80718708459259e-05,
"loss": 4.6051,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806348489841538e-05,
"loss": 4.5997,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805509895090486e-05,
"loss": 4.5806,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804671300339434e-05,
"loss": 4.5912,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803834343468755e-05,
"loss": 4.5972,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.802995748717703e-05,
"loss": 4.594,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802157153966652e-05,
"loss": 4.5972,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013185592156e-05,
"loss": 4.5894,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800479964464548e-05,
"loss": 4.5802,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799641369713496e-05,
"loss": 4.5842,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798804412842817e-05,
"loss": 4.5771,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797965818091765e-05,
"loss": 4.5851,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797127223340713e-05,
"loss": 4.5857,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796288628589661e-05,
"loss": 4.5636,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795450033838609e-05,
"loss": 4.5673,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794611439087557e-05,
"loss": 4.5757,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793772844336505e-05,
"loss": 4.5824,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792935887465826e-05,
"loss": 4.5694,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792097292714774e-05,
"loss": 4.575,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912586979637217e-05,
"loss": 4.5663,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904201032126697e-05,
"loss": 4.5656,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789581508461618e-05,
"loss": 4.5753,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788744551590939e-05,
"loss": 4.5707,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787905956839887e-05,
"loss": 4.5514,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.787067362088835e-05,
"loss": 4.5668,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786230405218156e-05,
"loss": 4.5476,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785391810467104e-05,
"loss": 4.5528,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784553215716052e-05,
"loss": 4.5598,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783714620965e-05,
"loss": 4.5484,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782876026213948e-05,
"loss": 4.5487,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782037431462896e-05,
"loss": 4.5426,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7811988367118434e-05,
"loss": 4.5455,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780360241960792e-05,
"loss": 4.5438,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.77952164720974e-05,
"loss": 4.5584,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778683052458688e-05,
"loss": 4.5387,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777846095588009e-05,
"loss": 4.5314,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777007500836957e-05,
"loss": 4.5377,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776168906085905e-05,
"loss": 4.5459,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775330311334853e-05,
"loss": 4.54,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774491716583801e-05,
"loss": 4.542,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773653121832749e-05,
"loss": 4.5408,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772814527081697e-05,
"loss": 4.5398,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771975932330645e-05,
"loss": 4.5321,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771140613340339e-05,
"loss": 4.5275,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703036564696604e-05,
"loss": 4.5322,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694650617186084e-05,
"loss": 4.5378,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.76862810484793e-05,
"loss": 4.5212,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767789510096878e-05,
"loss": 4.5262,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766950915345826e-05,
"loss": 4.5391,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766112320594773e-05,
"loss": 4.5133,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765273725843721e-05,
"loss": 4.5276,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764435131092669e-05,
"loss": 4.5222,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763596536341617e-05,
"loss": 4.5344,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762757941590565e-05,
"loss": 4.526,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761919346839513e-05,
"loss": 4.5132,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761080752088461e-05,
"loss": 4.5114,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760242157337409e-05,
"loss": 4.5116,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759403562586357e-05,
"loss": 4.52,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758564967835306e-05,
"loss": 4.5278,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757726373084254e-05,
"loss": 4.5231,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756887778333202e-05,
"loss": 4.5065,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.75604918358215e-05,
"loss": 4.5105,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755213864591844e-05,
"loss": 4.5123,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754375269840792e-05,
"loss": 4.5103,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.75353667508974e-05,
"loss": 4.5064,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752698080338688e-05,
"loss": 4.5229,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751859485587636e-05,
"loss": 4.5039,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751020890836584e-05,
"loss": 4.5042,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750182296085532e-05,
"loss": 4.5004,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.522709369659424,
"eval_runtime": 543.2723,
"eval_samples_per_second": 702.394,
"eval_steps_per_second": 21.95,
"step": 152638
},
{
"epoch": 0.0,
"learning_rate": 4.74934370133448e-05,
"loss": 4.5152,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748505106583428e-05,
"loss": 4.5104,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747666511832376e-05,
"loss": 4.4948,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746827917081324e-05,
"loss": 4.4974,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745989322330272e-05,
"loss": 4.4887,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.74515072757922e-05,
"loss": 4.492,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744312132828168e-05,
"loss": 4.49,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743473538077116e-05,
"loss": 4.4917,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426349433260637e-05,
"loss": 4.489,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7417979864553846e-05,
"loss": 4.4933,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409593917043326e-05,
"loss": 4.4949,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401207969532806e-05,
"loss": 4.4987,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392822022022286e-05,
"loss": 4.4855,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384436074511766e-05,
"loss": 4.4767,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376050127001245e-05,
"loss": 4.4845,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367664179490725e-05,
"loss": 4.4629,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359278231980205e-05,
"loss": 4.4805,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350892284469685e-05,
"loss": 4.4774,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342506336959165e-05,
"loss": 4.4749,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.7334120389448645e-05,
"loss": 4.4896,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325734441938125e-05,
"loss": 4.4794,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317348494427605e-05,
"loss": 4.4783,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7308962546917085e-05,
"loss": 4.4809,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300576599406565e-05,
"loss": 4.4756,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292190651896045e-05,
"loss": 4.4707,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7283821083189254e-05,
"loss": 4.4684,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275435135678734e-05,
"loss": 4.4742,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726706556697194e-05,
"loss": 4.4659,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725867961946143e-05,
"loss": 4.4672,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725029367195091e-05,
"loss": 4.4519,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724190772444039e-05,
"loss": 4.4586,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723352177692987e-05,
"loss": 4.4722,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722513582941935e-05,
"loss": 4.4579,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721674988190883e-05,
"loss": 4.4659,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720838031320204e-05,
"loss": 4.4607,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720001074449525e-05,
"loss": 4.465,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719162479698473e-05,
"loss": 4.4665,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718323884947421e-05,
"loss": 4.4634,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717485290196369e-05,
"loss": 4.4614,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716646695445317e-05,
"loss": 4.4507,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715808100694265e-05,
"loss": 4.4561,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714969505943213e-05,
"loss": 4.4432,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141309111921614e-05,
"loss": 4.4587,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7132923164411094e-05,
"loss": 4.4577,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124537216900574e-05,
"loss": 4.4592,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711615126939005e-05,
"loss": 4.4449,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710776532187953e-05,
"loss": 4.4477,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709937937436901e-05,
"loss": 4.4548,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709100980566222e-05,
"loss": 4.4366,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082623858151696e-05,
"loss": 4.4392,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074237910641176e-05,
"loss": 4.4369,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7065851963130656e-05,
"loss": 4.4553,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057482394423865e-05,
"loss": 4.4309,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704911282571708e-05,
"loss": 4.4571,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.70407432570103e-05,
"loss": 4.4277,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703235730949978e-05,
"loss": 4.4354,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702397136198926e-05,
"loss": 4.4383,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701558541447874e-05,
"loss": 4.4373,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700719946696822e-05,
"loss": 4.4336,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.69988135194577e-05,
"loss": 4.4454,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990443950750906e-05,
"loss": 4.419,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982058003240386e-05,
"loss": 4.4346,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973672055729866e-05,
"loss": 4.4294,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696528610821934e-05,
"loss": 4.4374,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956916539512555e-05,
"loss": 4.4263,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.6948530592002035e-05,
"loss": 4.4291,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.6940144644491515e-05,
"loss": 4.4099,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931758696980995e-05,
"loss": 4.4368,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.6923372749470475e-05,
"loss": 4.427,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6914986801959955e-05,
"loss": 4.4196,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906600854449435e-05,
"loss": 4.4239,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.6898214906938915e-05,
"loss": 4.4213,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.6889828959428395e-05,
"loss": 4.4217,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.6881459390721604e-05,
"loss": 4.4332,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.6873073443211084e-05,
"loss": 4.4319,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864687495700564e-05,
"loss": 4.4201,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856301548190044e-05,
"loss": 4.4112,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6847915600679524e-05,
"loss": 4.4165,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683954603197274e-05,
"loss": 4.4212,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683116008446222e-05,
"loss": 4.4252,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.68227741369517e-05,
"loss": 4.4181,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681438818944118e-05,
"loss": 4.4208,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680600224193066e-05,
"loss": 4.3994,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679761629442014e-05,
"loss": 4.4112,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678923034690962e-05,
"loss": 4.4073,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.67808443993991e-05,
"loss": 4.4132,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677249120949604e-05,
"loss": 4.4207,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676410526198552e-05,
"loss": 4.4106,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755719314475e-05,
"loss": 4.3997,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674733336696448e-05,
"loss": 4.4082,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673894741945396e-05,
"loss": 4.4019,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673056147194344e-05,
"loss": 4.4092,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722175524432924e-05,
"loss": 4.4077,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671380595572613e-05,
"loss": 4.39,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670542000821561e-05,
"loss": 4.394,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669703406070509e-05,
"loss": 4.401,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668864811319457e-05,
"loss": 4.4075,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668027854448778e-05,
"loss": 4.398,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667189259697726e-05,
"loss": 4.4061,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666350664946674e-05,
"loss": 4.3947,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665512070195622e-05,
"loss": 4.3952,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.66467347544457e-05,
"loss": 4.4034,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663836518573891e-05,
"loss": 4.4008,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.662997923822839e-05,
"loss": 4.3845,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662159329071788e-05,
"loss": 4.4039,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661320734320736e-05,
"loss": 4.3781,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660482139569683e-05,
"loss": 4.3844,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659643544818631e-05,
"loss": 4.3972,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588065879479526e-05,
"loss": 4.3828,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579679931969006e-05,
"loss": 4.3914,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657129398445848e-05,
"loss": 4.3791,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656290803694796e-05,
"loss": 4.379,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554538468241175e-05,
"loss": 4.3793,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654615252073065e-05,
"loss": 4.4007,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653776657322013e-05,
"loss": 4.3793,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.6529380625709615e-05,
"loss": 4.3758,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6520994678199095e-05,
"loss": 4.3729,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512608730688575e-05,
"loss": 4.382,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.6504222783178055e-05,
"loss": 4.3872,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6495853214471264e-05,
"loss": 4.3835,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.6487467266960744e-05,
"loss": 4.3809,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479081319450224e-05,
"loss": 4.3827,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.6470695371939704e-05,
"loss": 4.376,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.6462309424429184e-05,
"loss": 4.3779,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.6453923476918664e-05,
"loss": 4.3778,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644555390821187e-05,
"loss": 4.3805,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643716796070135e-05,
"loss": 4.3691,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642878201319083e-05,
"loss": 4.3727,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642039606568031e-05,
"loss": 4.3855,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.64120101181698e-05,
"loss": 4.3629,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640362417065928e-05,
"loss": 4.3732,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639523822314876e-05,
"loss": 4.3729,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638685227563824e-05,
"loss": 4.3848,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637848270693145e-05,
"loss": 4.3756,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637009675942093e-05,
"loss": 4.3693,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636171081191041e-05,
"loss": 4.361,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635334124320362e-05,
"loss": 4.3631,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.63449552956931e-05,
"loss": 4.3723,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633656934818258e-05,
"loss": 4.3792,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632818340067206e-05,
"loss": 4.3761,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631979745316154e-05,
"loss": 4.3615,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631142788445475e-05,
"loss": 4.3614,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630304193694423e-05,
"loss": 4.3729,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629465598943371e-05,
"loss": 4.361,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628627004192319e-05,
"loss": 4.3622,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277884094412666e-05,
"loss": 4.3771,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626951452570588e-05,
"loss": 4.3613,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626112857819536e-05,
"loss": 4.3624,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.6252742630684835e-05,
"loss": 4.3599,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.389575481414795,
"eval_runtime": 546.9044,
"eval_samples_per_second": 697.729,
"eval_steps_per_second": 21.805,
"step": 228957
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 8.810688404024357e+16,
"trial_name": null,
"trial_params": null
}