abhinavp's picture
Training in progress, epoch 0, checkpoint
479b636 verified
raw
history blame
No virus
93.1 kB
{
"best_metric": 4.198339939117432,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sim-ques/lstm/0/checkpoints/checkpoint-381600",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 381600,
"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": 10.8201,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.553,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0562,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9924,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9448,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8813,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7286,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6243,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5305,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4522,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3814,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3269,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2581,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.1866,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.141,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0831,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0499,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 5.9938,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9503,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984066699730012e-05,
"loss": 5.9182,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8775,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8501,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8228,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.7916,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.979875363855125e-05,
"loss": 5.7619,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.979036769104073e-05,
"loss": 5.7346,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7035,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6762,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6486,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.975684027980238e-05,
"loss": 5.6356,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.974845433229186e-05,
"loss": 5.6128,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.5915,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5701,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.5486,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714926921053515e-05,
"loss": 5.5418,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5308,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5076,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4692,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4755,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4407,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4363,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4265,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.4179,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.3945,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.3902,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3838,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.3719,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960595873982795e-05,
"loss": 5.3618,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959757279231743e-05,
"loss": 5.341,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958918684480691e-05,
"loss": 5.3299,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3332,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3131,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.302,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2835,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.2883,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2686,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.2825,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2536,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2503,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.9505360127309166e-05,
"loss": 5.244,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.9496974179798646e-05,
"loss": 5.2211,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948858823228813e-05,
"loss": 5.2259,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948021866358134e-05,
"loss": 5.2096,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947183271607082e-05,
"loss": 5.1997,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.94634467685603e-05,
"loss": 5.1942,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945506082104978e-05,
"loss": 5.2113,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.9446674873539255e-05,
"loss": 5.1859,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943830530483247e-05,
"loss": 5.1727,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942991935732195e-05,
"loss": 5.1539,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942153340981143e-05,
"loss": 5.1535,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413147462300904e-05,
"loss": 5.166,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404761514790384e-05,
"loss": 5.162,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.939637556727987e-05,
"loss": 5.1361,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938798961976935e-05,
"loss": 5.1528,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.937960367225883e-05,
"loss": 5.143,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.937123410355204e-05,
"loss": 5.1294,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1094,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935447858733473e-05,
"loss": 5.1131,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934609263982421e-05,
"loss": 5.097,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933770669231369e-05,
"loss": 5.0953,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932932074480317e-05,
"loss": 5.0952,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932093479729265e-05,
"loss": 5.0847,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931256522858586e-05,
"loss": 5.0875,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930417928107534e-05,
"loss": 5.0816,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295793333564825e-05,
"loss": 5.0614,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287407386054305e-05,
"loss": 5.0628,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279021438543785e-05,
"loss": 5.0631,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270635491033264e-05,
"loss": 5.0547,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262249543522744e-05,
"loss": 5.0434,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.9253879974815954e-05,
"loss": 5.041,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.9245494027305433e-05,
"loss": 5.0382,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.9237108079794913e-05,
"loss": 5.0254,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922872213228439e-05,
"loss": 5.0296,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922033618477387e-05,
"loss": 5.0142,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921195023726335e-05,
"loss": 5.0176,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920356428975283e-05,
"loss": 5.0121,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919519472104604e-05,
"loss": 5.0037,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918680877353552e-05,
"loss": 4.982,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917842282602501e-05,
"loss": 4.9832,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917003687851449e-05,
"loss": 4.9821,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916165093100397e-05,
"loss": 4.9936,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915326498349345e-05,
"loss": 4.9794,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914487903598292e-05,
"loss": 4.9682,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.91364930884724e-05,
"loss": 4.9599,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912812351976562e-05,
"loss": 4.9646,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911975395105883e-05,
"loss": 4.938,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111384382352036e-05,
"loss": 4.9421,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9102998434841516e-05,
"loss": 4.9385,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.9094612487330996e-05,
"loss": 4.9404,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.9086226539820476e-05,
"loss": 4.929,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907784059230996e-05,
"loss": 4.9365,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906945464479944e-05,
"loss": 4.9146,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906108507609265e-05,
"loss": 4.9364,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905269912858213e-05,
"loss": 4.9156,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904431318107161e-05,
"loss": 4.9182,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903592723356109e-05,
"loss": 4.9199,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027541286050565e-05,
"loss": 4.9177,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019155338540045e-05,
"loss": 4.9044,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901078576983326e-05,
"loss": 4.892,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900239982232274e-05,
"loss": 4.8993,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994013874812214e-05,
"loss": 4.8917,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.89856279273017e-05,
"loss": 4.8928,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897724197979118e-05,
"loss": 4.8881,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.896885603228066e-05,
"loss": 4.8748,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.896047008477014e-05,
"loss": 4.8881,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895208413725962e-05,
"loss": 4.8675,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.89436981897491e-05,
"loss": 4.8627,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893531224223858e-05,
"loss": 4.8576,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892694267353179e-05,
"loss": 4.8634,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891855672602127e-05,
"loss": 4.8477,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891017077851075e-05,
"loss": 4.8665,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890178483100023e-05,
"loss": 4.8562,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889341526229344e-05,
"loss": 4.844,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888502931478292e-05,
"loss": 4.8346,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766433672724e-05,
"loss": 4.8376,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886825741976188e-05,
"loss": 4.8362,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.8859871472251365e-05,
"loss": 4.838,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.8851485524740845e-05,
"loss": 4.8374,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.8843099577230325e-05,
"loss": 4.8321,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.8834713629719805e-05,
"loss": 4.8261,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.8826344061013014e-05,
"loss": 4.821,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.8817958113502494e-05,
"loss": 4.8094,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809572165991974e-05,
"loss": 4.8077,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801186218481454e-05,
"loss": 4.8135,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879283302857839e-05,
"loss": 4.7937,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878444708106787e-05,
"loss": 4.8077,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877606113355735e-05,
"loss": 4.8069,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876767518604683e-05,
"loss": 4.7956,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875928923853632e-05,
"loss": 4.7991,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.87509032910258e-05,
"loss": 4.795,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.7508111000061035,
"eval_runtime": 305.0584,
"eval_samples_per_second": 1250.879,
"eval_steps_per_second": 39.091,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874251734351528e-05,
"loss": 4.7752,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873413139600475e-05,
"loss": 4.7809,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872576182729797e-05,
"loss": 4.7916,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871737587978745e-05,
"loss": 4.7738,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870898993227693e-05,
"loss": 4.7795,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.87006039847664e-05,
"loss": 4.768,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692234416059616e-05,
"loss": 4.7692,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683848468549096e-05,
"loss": 4.7584,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675462521038576e-05,
"loss": 4.7657,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667076573528056e-05,
"loss": 4.7534,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865870700482127e-05,
"loss": 4.7747,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.7671,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864196786740769e-05,
"loss": 4.7462,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863358191989717e-05,
"loss": 4.7438,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862519597238665e-05,
"loss": 4.7412,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861681002487613e-05,
"loss": 4.7418,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860842407736561e-05,
"loss": 4.7353,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860003812985509e-05,
"loss": 4.7348,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859165218234457e-05,
"loss": 4.7295,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858328261363778e-05,
"loss": 4.7406,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857489666612726e-05,
"loss": 4.7319,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856651071861674e-05,
"loss": 4.7364,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558124771106226e-05,
"loss": 4.7306,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.85497388235957e-05,
"loss": 4.7375,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854135287608518e-05,
"loss": 4.7147,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853296692857466e-05,
"loss": 4.7157,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852458098106414e-05,
"loss": 4.7082,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851621141235735e-05,
"loss": 4.7085,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850782546484683e-05,
"loss": 4.708,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849943951733631e-05,
"loss": 4.7061,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.7056,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.7038,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.693,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.8465912106097964e-05,
"loss": 4.7066,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.7077,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.6944,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.6757,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.69,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.669,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.6795,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.6785,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.682,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.672,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.6762,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.6774,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.6724,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.6735,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.6556,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.6579,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833178608234084e-05,
"loss": 4.6671,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.6549,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.6555,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.638,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.6504,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.6382,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.6569,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.6393,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.6438,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.6446,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.6242,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.6351,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.6336,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222834279919e-05,
"loss": 4.62,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.6243,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.6412,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.6261,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.6124,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.6087,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817253497365961e-05,
"loss": 4.6125,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816414902614909e-05,
"loss": 4.6294,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815576307863857e-05,
"loss": 4.6282,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.6116,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138991183617535e-05,
"loss": 4.628,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.6265,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122235667400224e-05,
"loss": 4.6168,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113866098693434e-05,
"loss": 4.601,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.6153,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097094203672393e-05,
"loss": 4.6016,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.8088708256161873e-05,
"loss": 4.5986,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.6032,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.5974,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.6111,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.5991,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804677851860927e-05,
"loss": 4.59,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803840894990248e-05,
"loss": 4.5966,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803002300239196e-05,
"loss": 4.5952,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802163705488144e-05,
"loss": 4.5927,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801325110737092e-05,
"loss": 4.5888,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.80048651598604e-05,
"loss": 4.5841,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799647921234988e-05,
"loss": 4.5942,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798809326483936e-05,
"loss": 4.5804,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797970731732884e-05,
"loss": 4.5866,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797133774862205e-05,
"loss": 4.5741,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796295180111153e-05,
"loss": 4.587,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795456585360101e-05,
"loss": 4.583,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794617990609049e-05,
"loss": 4.5762,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.5626,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792942438987319e-05,
"loss": 4.5679,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.5715,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.5804,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904282926145356e-05,
"loss": 4.5727,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895896978634836e-05,
"loss": 4.562,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887511031124316e-05,
"loss": 4.5586,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879141462417525e-05,
"loss": 4.5655,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870755514907005e-05,
"loss": 4.5414,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862385946200214e-05,
"loss": 4.5526,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853999998689694e-05,
"loss": 4.5526,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784561405117918e-05,
"loss": 4.5536,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783722810366866e-05,
"loss": 4.5469,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782884215615814e-05,
"loss": 4.5559,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782045620864762e-05,
"loss": 4.5436,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.78120702611371e-05,
"loss": 4.5624,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780368431362658e-05,
"loss": 4.5479,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779529836611606e-05,
"loss": 4.5459,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778692879740927e-05,
"loss": 4.563,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777854284989875e-05,
"loss": 4.5589,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777015690238823e-05,
"loss": 4.5442,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776177095487771e-05,
"loss": 4.5367,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775338500736719e-05,
"loss": 4.55,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774499905985666e-05,
"loss": 4.5388,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773661311234615e-05,
"loss": 4.5405,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772822716483563e-05,
"loss": 4.5469,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719857596128845e-05,
"loss": 4.5324,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771147164861832e-05,
"loss": 4.5473,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.77030857011078e-05,
"loss": 4.5292,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694716132401014e-05,
"loss": 4.5303,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686330184890494e-05,
"loss": 4.522,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767794423737997e-05,
"loss": 4.5311,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766955828986945e-05,
"loss": 4.5222,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766117234235893e-05,
"loss": 4.5387,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.5351,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764440044733789e-05,
"loss": 4.5256,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763601449982737e-05,
"loss": 4.5115,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762764493112058e-05,
"loss": 4.528,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761925898361006e-05,
"loss": 4.5222,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761087303609954e-05,
"loss": 4.5274,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760248708858902e-05,
"loss": 4.5266,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759411751988223e-05,
"loss": 4.5219,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758573157237171e-05,
"loss": 4.5201,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757736200366492e-05,
"loss": 4.5228,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.75689760561544e-05,
"loss": 4.5075,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756059010864388e-05,
"loss": 4.508,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755220416113336e-05,
"loss": 4.5148,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754381821362284e-05,
"loss": 4.5023,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753544864491605e-05,
"loss": 4.5101,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527062697405536e-05,
"loss": 4.5207,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518676749895016e-05,
"loss": 4.5056,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510290802384496e-05,
"loss": 4.5059,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501904854873976e-05,
"loss": 4.5086,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.47179651260376,
"eval_runtime": 299.3442,
"eval_samples_per_second": 1274.756,
"eval_steps_per_second": 39.837,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493518907363456e-05,
"loss": 4.4917,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485132959852936e-05,
"loss": 4.4958,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476747012342416e-05,
"loss": 4.5093,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468361064831896e-05,
"loss": 4.4975,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7459975117321376e-05,
"loss": 4.5018,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745158916981085e-05,
"loss": 4.4871,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.744320322230033e-05,
"loss": 4.5014,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743481727478981e-05,
"loss": 4.4827,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742643132727929e-05,
"loss": 4.4955,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741804537976877e-05,
"loss": 4.4897,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740965943225825e-05,
"loss": 4.5022,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401273484747736e-05,
"loss": 4.5035,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392903916040945e-05,
"loss": 4.478,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384517968530425e-05,
"loss": 4.4844,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376132021019905e-05,
"loss": 4.4841,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367746073509385e-05,
"loss": 4.4794,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359360125998865e-05,
"loss": 4.4788,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350974178488345e-05,
"loss": 4.4772,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342588230977825e-05,
"loss": 4.4749,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.7334202283467305e-05,
"loss": 4.4942,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325816335956784e-05,
"loss": 4.4757,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317430388446264e-05,
"loss": 4.4884,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730904444093574e-05,
"loss": 4.4826,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300674872228953e-05,
"loss": 4.4909,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292288924718433e-05,
"loss": 4.4638,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728391935601165e-05,
"loss": 4.4742,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727553340850113e-05,
"loss": 4.4634,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726714746099061e-05,
"loss": 4.4718,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725876151348009e-05,
"loss": 4.4616,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725037556596957e-05,
"loss": 4.4671,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724198961845904e-05,
"loss": 4.4743,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723360367094852e-05,
"loss": 4.4676,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225217723438e-05,
"loss": 4.4575,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721684815473121e-05,
"loss": 4.4737,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720847858602443e-05,
"loss": 4.4691,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720009263851391e-05,
"loss": 4.463,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719172306980712e-05,
"loss": 4.4511,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71833371222966e-05,
"loss": 4.4613,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717495117478608e-05,
"loss": 4.4426,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716656522727556e-05,
"loss": 4.4561,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715817927976504e-05,
"loss": 4.4502,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714980971105825e-05,
"loss": 4.4587,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714142376354773e-05,
"loss": 4.4526,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713303781603721e-05,
"loss": 4.4531,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124651868526685e-05,
"loss": 4.4573,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116265921016165e-05,
"loss": 4.4545,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107879973505645e-05,
"loss": 4.4562,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099494025995125e-05,
"loss": 4.4386,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091108078484605e-05,
"loss": 4.4393,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708272213097409e-05,
"loss": 4.4534,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707433618346357e-05,
"loss": 4.4421,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706595023595305e-05,
"loss": 4.4401,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705758066724626e-05,
"loss": 4.4296,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704919471973574e-05,
"loss": 4.4423,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704080877222522e-05,
"loss": 4.4272,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703243920351843e-05,
"loss": 4.4451,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702405325600791e-05,
"loss": 4.432,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701566730849739e-05,
"loss": 4.4411,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700728136098687e-05,
"loss": 4.4382,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699889541347635e-05,
"loss": 4.4224,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699050946596583e-05,
"loss": 4.4291,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698212351845531e-05,
"loss": 4.4303,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697373757094479e-05,
"loss": 4.4196,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965368002238005e-05,
"loss": 4.4283,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956982054727485e-05,
"loss": 4.4355,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.6948612486020694e-05,
"loss": 4.4303,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.69402429173139e-05,
"loss": 4.4186,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693185696980338e-05,
"loss": 4.4105,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692347102229286e-05,
"loss": 4.4173,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691508507478234e-05,
"loss": 4.4326,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690669912727182e-05,
"loss": 4.4368,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.68983131797613e-05,
"loss": 4.4187,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688992723225078e-05,
"loss": 4.4341,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688154128474026e-05,
"loss": 4.4339,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687315533722974e-05,
"loss": 4.4306,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686478576852296e-05,
"loss": 4.406,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685639982101244e-05,
"loss": 4.4276,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684801387350192e-05,
"loss": 4.4198,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.68396279259914e-05,
"loss": 4.4094,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683124197848087e-05,
"loss": 4.4203,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682287240977409e-05,
"loss": 4.4101,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681448646226357e-05,
"loss": 4.4234,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680610051475305e-05,
"loss": 4.4162,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679771456724252e-05,
"loss": 4.4051,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789328619732e-05,
"loss": 4.4141,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678094267222148e-05,
"loss": 4.4123,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677255672471097e-05,
"loss": 4.414,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676420353480791e-05,
"loss": 4.4097,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675581758729739e-05,
"loss": 4.4047,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674743163978687e-05,
"loss": 4.4137,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739045692276346e-05,
"loss": 4.4022,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730659744765826e-05,
"loss": 4.4087,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722273797255305e-05,
"loss": 4.3996,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713887849744785e-05,
"loss": 4.4138,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705501902234265e-05,
"loss": 4.4092,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697115954723745e-05,
"loss": 4.4001,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688730007213225e-05,
"loss": 4.394,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680344059702705e-05,
"loss": 4.4011,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667197449099592e-05,
"loss": 4.3942,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.66635885434854e-05,
"loss": 4.413,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665520259597488e-05,
"loss": 4.3997,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664681664846436e-05,
"loss": 4.3944,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663844707975757e-05,
"loss": 4.3888,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663006113224705e-05,
"loss": 4.3957,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662167518473653e-05,
"loss": 4.3765,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661328923722601e-05,
"loss": 4.3864,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660490328971549e-05,
"loss": 4.3876,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659651734220497e-05,
"loss": 4.3897,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658814777349818e-05,
"loss": 4.3783,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657976182598766e-05,
"loss": 4.3948,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657137587847714e-05,
"loss": 4.3783,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656298993096662e-05,
"loss": 4.3995,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554620362259835e-05,
"loss": 4.3868,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546234414749315e-05,
"loss": 4.3841,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6537848467238795e-05,
"loss": 4.402,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.6529462519728275e-05,
"loss": 4.4022,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521076572217755e-05,
"loss": 4.386,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512690624707234e-05,
"loss": 4.3776,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650430467719671e-05,
"loss": 4.3857,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649591872968619e-05,
"loss": 4.3823,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648753278217567e-05,
"loss": 4.3814,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647914683466515e-05,
"loss": 4.3934,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647076088715463e-05,
"loss": 4.3745,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646237493964411e-05,
"loss": 4.3912,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645400537093732e-05,
"loss": 4.3768,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.64456194234268e-05,
"loss": 4.3796,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643723347591628e-05,
"loss": 4.3645,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642886390720949e-05,
"loss": 4.3822,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642047795969897e-05,
"loss": 4.3673,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641209201218845e-05,
"loss": 4.3875,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640370606467793e-05,
"loss": 4.3813,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639532011716741e-05,
"loss": 4.3764,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638693416965689e-05,
"loss": 4.3605,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637854822214637e-05,
"loss": 4.3793,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637016227463585e-05,
"loss": 4.3761,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636180908473279e-05,
"loss": 4.3751,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635342313722228e-05,
"loss": 4.3738,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634503718971176e-05,
"loss": 4.3803,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633665124220124e-05,
"loss": 4.3737,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632826529469072e-05,
"loss": 4.3779,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.63198793471802e-05,
"loss": 4.3603,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631149339966968e-05,
"loss": 4.364,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630310745215916e-05,
"loss": 4.3686,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.6294737883452366e-05,
"loss": 4.3559,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286351935941846e-05,
"loss": 4.3664,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277982367235055e-05,
"loss": 4.377,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.6269596419724535e-05,
"loss": 4.3621,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.6261226851017744e-05,
"loss": 4.3611,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625284090350723e-05,
"loss": 4.3698,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.337063789367676,
"eval_runtime": 299.548,
"eval_samples_per_second": 1273.889,
"eval_steps_per_second": 39.81,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624445495599671e-05,
"loss": 4.3585,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623606900848619e-05,
"loss": 4.3552,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622768306097567e-05,
"loss": 4.3682,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621929711346515e-05,
"loss": 4.3537,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621091116595463e-05,
"loss": 4.3652,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620252521844411e-05,
"loss": 4.3494,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619413927093359e-05,
"loss": 4.3613,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.61857697022268e-05,
"loss": 4.3436,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.617738375471628e-05,
"loss": 4.3599,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616899780720576e-05,
"loss": 4.3494,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616061185969524e-05,
"loss": 4.3665,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615222591218472e-05,
"loss": 4.364,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614385634347793e-05,
"loss": 4.344,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135470395967415e-05,
"loss": 4.3525,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.6127084448456895e-05,
"loss": 4.348,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611869850094637e-05,
"loss": 4.3486,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611031255343585e-05,
"loss": 4.3415,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610192660592533e-05,
"loss": 4.3452,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609354065841481e-05,
"loss": 4.3411,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608515471090429e-05,
"loss": 4.3664,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.60767851421975e-05,
"loss": 4.3438,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606839919468698e-05,
"loss": 4.352,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606001324717646e-05,
"loss": 4.357,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605162729966594e-05,
"loss": 4.3574,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604325773095915e-05,
"loss": 4.3348,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603488816225236e-05,
"loss": 4.3441,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602650221474184e-05,
"loss": 4.3347,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601811626723132e-05,
"loss": 4.3418,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.60097303197208e-05,
"loss": 4.334,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600134437221028e-05,
"loss": 4.3391,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599295842469976e-05,
"loss": 4.3451,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598457247718924e-05,
"loss": 4.3416,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597620290848245e-05,
"loss": 4.3368,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596781696097193e-05,
"loss": 4.3439,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595943101346141e-05,
"loss": 4.3445,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595104506595089e-05,
"loss": 4.3363,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.59426754972441e-05,
"loss": 4.3247,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.5934289549733587e-05,
"loss": 4.3386,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.5925903602223066e-05,
"loss": 4.3162,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.5917517654712546e-05,
"loss": 4.3313,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.5909148086005756e-05,
"loss": 4.3271,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.5900762138495235e-05,
"loss": 4.3372,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.5892376190984715e-05,
"loss": 4.3353,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5883990243474195e-05,
"loss": 4.3278,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.5875604295963675e-05,
"loss": 4.3339,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867218348453155e-05,
"loss": 4.3351,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858832400942635e-05,
"loss": 4.3342,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.5850446453432115e-05,
"loss": 4.3175,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.5842060505921595e-05,
"loss": 4.3188,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.5833690937214804e-05,
"loss": 4.3362,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.5825304989704284e-05,
"loss": 4.3194,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581691904219377e-05,
"loss": 4.3187,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580853309468325e-05,
"loss": 4.3142,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580016352597646e-05,
"loss": 4.324,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579177757846594e-05,
"loss": 4.3113,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578339163095542e-05,
"loss": 4.3247,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577502206224863e-05,
"loss": 4.3185,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576663611473811e-05,
"loss": 4.322,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575825016722759e-05,
"loss": 4.3214,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.574986421971707e-05,
"loss": 4.3096,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574147827220655e-05,
"loss": 4.3115,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573309232469602e-05,
"loss": 4.3203,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572470637718551e-05,
"loss": 4.3029,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571632042967499e-05,
"loss": 4.3142,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.5707950860968205e-05,
"loss": 4.3199,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569956491345768e-05,
"loss": 4.3204,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569117896594716e-05,
"loss": 4.3045,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568279301843664e-05,
"loss": 4.2991,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567440707092612e-05,
"loss": 4.3037,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566603750221933e-05,
"loss": 4.3163,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565765155470881e-05,
"loss": 4.3244,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564926560719829e-05,
"loss": 4.3092,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.5640879659687767e-05,
"loss": 4.3215,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.5632510090980976e-05,
"loss": 4.3233,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562412414347046e-05,
"loss": 4.3201,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561573819595994e-05,
"loss": 4.2991,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560735224844942e-05,
"loss": 4.316,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559898267974263e-05,
"loss": 4.3113,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559059673223211e-05,
"loss": 4.301,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558221078472159e-05,
"loss": 4.3095,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557382483721107e-05,
"loss": 4.3035,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556543888970055e-05,
"loss": 4.3107,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555706932099376e-05,
"loss": 4.31,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554868337348324e-05,
"loss": 4.2998,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554029742597272e-05,
"loss": 4.3092,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.55319114784622e-05,
"loss": 4.3017,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523541909755416e-05,
"loss": 4.307,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515172341048625e-05,
"loss": 4.3036,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.5506786393538105e-05,
"loss": 4.2962,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.5498400446027585e-05,
"loss": 4.3085,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.5490014498517065e-05,
"loss": 4.3011,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.5481628551006545e-05,
"loss": 4.2995,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.5473242603496025e-05,
"loss": 4.2938,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.5464856655985505e-05,
"loss": 4.3102,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.5456470708474985e-05,
"loss": 4.3036,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448101139768194e-05,
"loss": 4.2966,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.5439715192257674e-05,
"loss": 4.2886,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.5431329244747154e-05,
"loss": 4.2958,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.5422943297236634e-05,
"loss": 4.2905,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541457372852985e-05,
"loss": 4.3129,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540618778101933e-05,
"loss": 4.2983,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539780183350881e-05,
"loss": 4.2913,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538941588599829e-05,
"loss": 4.288,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.53810463172915e-05,
"loss": 4.2975,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537266036978098e-05,
"loss": 4.2703,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536429080107419e-05,
"loss": 4.2854,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535590485356367e-05,
"loss": 4.2855,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534751890605315e-05,
"loss": 4.2911,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533913295854263e-05,
"loss": 4.2765,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533074701103211e-05,
"loss": 4.2954,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532237744232532e-05,
"loss": 4.2785,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.53139914948148e-05,
"loss": 4.2955,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530562192610801e-05,
"loss": 4.2891,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529723597859749e-05,
"loss": 4.2839,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528885003108697e-05,
"loss": 4.3025,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528046408357645e-05,
"loss": 4.3048,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527209451486966e-05,
"loss": 4.29,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526370856735914e-05,
"loss": 4.2818,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525532261984862e-05,
"loss": 4.2879,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.52469366723381e-05,
"loss": 4.2823,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523855072482758e-05,
"loss": 4.2818,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523016477731706e-05,
"loss": 4.2971,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522177882980654e-05,
"loss": 4.2787,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521339288229602e-05,
"loss": 4.2926,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520502331358924e-05,
"loss": 4.2823,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519663736607872e-05,
"loss": 4.2869,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.51882514185682e-05,
"loss": 4.2638,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.5179881849861406e-05,
"loss": 4.2896,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.5171495902350886e-05,
"loss": 4.2714,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.5163109954840366e-05,
"loss": 4.2913,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.5154724007329846e-05,
"loss": 4.284,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.5146338059819326e-05,
"loss": 4.2858,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5137952112308806e-05,
"loss": 4.2662,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512956616479828e-05,
"loss": 4.2891,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512118021728776e-05,
"loss": 4.2792,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511279426977724e-05,
"loss": 4.2823,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104408322266726e-05,
"loss": 4.2798,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5096022374756206e-05,
"loss": 4.2888,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087636427245685e-05,
"loss": 4.2825,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079250479735165e-05,
"loss": 4.285,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070864532224645e-05,
"loss": 4.2693,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062478584714125e-05,
"loss": 4.2739,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.5054109016007334e-05,
"loss": 4.2737,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.5045723068496814e-05,
"loss": 4.2683,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.5037337120986294e-05,
"loss": 4.277,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5028951173475774e-05,
"loss": 4.2818,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020565225965254e-05,
"loss": 4.2726,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012179278454734e-05,
"loss": 4.2685,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.5003793330944214e-05,
"loss": 4.2801,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.254773139953613,
"eval_runtime": 303.4646,
"eval_samples_per_second": 1257.448,
"eval_steps_per_second": 39.296,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.4995407383433694e-05,
"loss": 4.2623,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4987021435923174e-05,
"loss": 4.2659,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978635488412654e-05,
"loss": 4.2764,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970249540902134e-05,
"loss": 4.2667,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4961863593391614e-05,
"loss": 4.2795,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953477645881094e-05,
"loss": 4.2608,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945091698370574e-05,
"loss": 4.2691,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936705750860054e-05,
"loss": 4.2576,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928319803349534e-05,
"loss": 4.2744,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4919933855839014e-05,
"loss": 4.2636,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911547908328494e-05,
"loss": 4.2729,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.4903161960817974e-05,
"loss": 4.2784,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489479239211118e-05,
"loss": 4.2536,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488640644460066e-05,
"loss": 4.269,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487802049709014e-05,
"loss": 4.2608,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486963454957962e-05,
"loss": 4.262,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.48612486020691e-05,
"loss": 4.2519,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485286265455859e-05,
"loss": 4.2608,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484447670704806e-05,
"loss": 4.2575,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483609075953754e-05,
"loss": 4.2784,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482770481202702e-05,
"loss": 4.2581,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.48193188645165e-05,
"loss": 4.2661,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481094929580971e-05,
"loss": 4.2733,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480256334829919e-05,
"loss": 4.2738,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479417740078867e-05,
"loss": 4.2511,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478579145327815e-05,
"loss": 4.2627,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477740550576763e-05,
"loss": 4.2482,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476901955825711e-05,
"loss": 4.2576,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476063361074659e-05,
"loss": 4.2482,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475224766323607e-05,
"loss": 4.2577,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474387809452929e-05,
"loss": 4.2593,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473549214701877e-05,
"loss": 4.26,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.4727122578311976e-05,
"loss": 4.2509,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.4718736630801456e-05,
"loss": 4.2639,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710350683290936e-05,
"loss": 4.2564,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.4701964735780416e-05,
"loss": 4.2592,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693578788269896e-05,
"loss": 4.2425,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.4685209219563105e-05,
"loss": 4.2557,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4676839650856314e-05,
"loss": 4.2409,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668453703345794e-05,
"loss": 4.2464,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466006775583528e-05,
"loss": 4.2459,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465168180832476e-05,
"loss": 4.2574,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464329586081424e-05,
"loss": 4.2537,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463490991330372e-05,
"loss": 4.252,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.46265239657932e-05,
"loss": 4.2538,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461813801828268e-05,
"loss": 4.2548,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460975207077216e-05,
"loss": 4.2511,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460136612326164e-05,
"loss": 4.2457,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459298017575112e-05,
"loss": 4.2318,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584594228240594e-05,
"loss": 4.2556,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.457622465953381e-05,
"loss": 4.2439,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.456783871202329e-05,
"loss": 4.2387,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455945276451277e-05,
"loss": 4.2392,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455106681700225e-05,
"loss": 4.2457,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542697248295465e-05,
"loss": 4.2353,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534311300784945e-05,
"loss": 4.2387,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4525925353274425e-05,
"loss": 4.2419,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.45175394057639e-05,
"loss": 4.2397,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450915345825338e-05,
"loss": 4.2511,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450076751074286e-05,
"loss": 4.2308,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449238156323234e-05,
"loss": 4.2336,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448401199452555e-05,
"loss": 4.246,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447562604701503e-05,
"loss": 4.2294,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446724009950451e-05,
"loss": 4.2353,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445885415199399e-05,
"loss": 4.2409,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.44504845832872e-05,
"loss": 4.2443,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444209863577668e-05,
"loss": 4.2308,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443371268826616e-05,
"loss": 4.2244,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442532674075564e-05,
"loss": 4.2226,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441694079324512e-05,
"loss": 4.2394,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.44085548457346e-05,
"loss": 4.2526,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440016889822408e-05,
"loss": 4.2324,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439178295071356e-05,
"loss": 4.2458,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438339700320304e-05,
"loss": 4.2453,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437502743449625e-05,
"loss": 4.249,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436665786578946e-05,
"loss": 4.2243,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435827191827894e-05,
"loss": 4.2408,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.434990234957216e-05,
"loss": 4.2356,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.434151640206164e-05,
"loss": 4.2235,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333130454551117e-05,
"loss": 4.2397,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4324744507040597e-05,
"loss": 4.2303,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316358559530076e-05,
"loss": 4.2312,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4307972612019556e-05,
"loss": 4.2367,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299586664509036e-05,
"loss": 4.2307,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291200716998516e-05,
"loss": 4.2345,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4282814769487996e-05,
"loss": 4.2271,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274428821977476e-05,
"loss": 4.2333,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266042874466956e-05,
"loss": 4.2268,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.4257673305760165e-05,
"loss": 4.2283,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.4249287358249645e-05,
"loss": 4.2329,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.4240901410739125e-05,
"loss": 4.2308,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232515463228605e-05,
"loss": 4.2251,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224129515718085e-05,
"loss": 4.2222,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4215743568207565e-05,
"loss": 4.2395,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207357620697045e-05,
"loss": 4.2324,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.4198971673186525e-05,
"loss": 4.2261,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190602104479734e-05,
"loss": 4.2173,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182216156969214e-05,
"loss": 4.2239,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4173830209458694e-05,
"loss": 4.2221,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.41654606407519e-05,
"loss": 4.2347,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415707469324138e-05,
"loss": 4.2338,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414868874573086e-05,
"loss": 4.2202,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414030279822034e-05,
"loss": 4.2159,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413191685070982e-05,
"loss": 4.2296,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.41235309031993e-05,
"loss": 4.1951,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411516133449252e-05,
"loss": 4.2217,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106775386982e-05,
"loss": 4.2106,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409838943947148e-05,
"loss": 4.2217,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409000349196096e-05,
"loss": 4.2075,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408161754445044e-05,
"loss": 4.224,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407323159693992e-05,
"loss": 4.2147,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.40648456494294e-05,
"loss": 4.2197,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405645970191888e-05,
"loss": 4.224,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404807375440836e-05,
"loss": 4.2113,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.403970418570157e-05,
"loss": 4.2344,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.4031334616994777e-05,
"loss": 4.2363,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.4022948669484257e-05,
"loss": 4.2229,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401456272197374e-05,
"loss": 4.2101,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400617677446322e-05,
"loss": 4.2213,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.39977908269527e-05,
"loss": 4.217,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398940487944218e-05,
"loss": 4.2107,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398101893193166e-05,
"loss": 4.2291,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397263298442114e-05,
"loss": 4.2112,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396426341571435e-05,
"loss": 4.2221,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395587746820383e-05,
"loss": 4.218,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394749152069331e-05,
"loss": 4.219,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393910557318279e-05,
"loss": 4.2057,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393075238327973e-05,
"loss": 4.2161,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392236643576921e-05,
"loss": 4.2094,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.39139804882587e-05,
"loss": 4.2242,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390559454074818e-05,
"loss": 4.216,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389720859323766e-05,
"loss": 4.2174,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388882264572714e-05,
"loss": 4.2004,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388043669821662e-05,
"loss": 4.2226,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387205075070609e-05,
"loss": 4.214,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3863681181999306e-05,
"loss": 4.218,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855295234488786e-05,
"loss": 4.2107,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3846909286978266e-05,
"loss": 4.2235,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383852333946774e-05,
"loss": 4.2143,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830153770760955e-05,
"loss": 4.2219,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3821767823250435e-05,
"loss": 4.2005,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813381875739915e-05,
"loss": 4.2115,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3804995928229395e-05,
"loss": 4.2069,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796609980718875e-05,
"loss": 4.2031,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378824041201209e-05,
"loss": 4.2134,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.37798708433053e-05,
"loss": 4.2148,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.377148489579478e-05,
"loss": 4.2136,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.376309894828426e-05,
"loss": 4.1987,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375471300077374e-05,
"loss": 4.2165,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.198339939117432,
"eval_runtime": 301.9446,
"eval_samples_per_second": 1263.778,
"eval_steps_per_second": 39.494,
"step": 381600
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.5875508092244262e+17,
"trial_name": null,
"trial_params": null
}