abhinavp's picture
Training in progress, epoch 1, checkpoint
f3d660a verified
{
"best_metric": 4.482818603515625,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-case/lstm/1/checkpoints/checkpoint-152640",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 152640,
"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": 10.8196,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5539,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0619,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.996,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9493,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.9278,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7713,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.661,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5545,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4791,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.408,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3405,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2693,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.201,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1431,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0832,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0367,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.9903,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.9501,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9117,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8754,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 5.8385,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 5.807,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.7767,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7591,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7182,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.6967,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 5.6697,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6503,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6232,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.5996,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.5935,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5669,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.5579,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714926921053515e-05,
"loss": 5.5434,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5196,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.509,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.9689785457325684e-05,
"loss": 5.4709,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.9681399509815164e-05,
"loss": 5.4719,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.9673013562304644e-05,
"loss": 5.4369,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.438,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4196,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.4202,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.3943,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963110020355577e-05,
"loss": 5.3865,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962271425604525e-05,
"loss": 5.3795,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961432830853473e-05,
"loss": 5.362,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960595873982795e-05,
"loss": 5.3681,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959757279231743e-05,
"loss": 5.3378,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958918684480691e-05,
"loss": 5.3242,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958080089729639e-05,
"loss": 5.3328,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3269,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956404538107908e-05,
"loss": 5.3019,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955565943356856e-05,
"loss": 5.2904,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954727348605804e-05,
"loss": 5.2898,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953888753854752e-05,
"loss": 5.2725,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530501591037e-05,
"loss": 5.2888,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952211564352648e-05,
"loss": 5.2486,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2489,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.9505360127309166e-05,
"loss": 5.2411,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.9496974179798646e-05,
"loss": 5.2295,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948858823228813e-05,
"loss": 5.232,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948020228477761e-05,
"loss": 5.2095,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.9471816337267086e-05,
"loss": 5.2039,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.94634467685603e-05,
"loss": 5.1964,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945506082104978e-05,
"loss": 5.2099,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.9446674873539255e-05,
"loss": 5.1817,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.9438288926028735e-05,
"loss": 5.1809,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.9429902978518215e-05,
"loss": 5.1552,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421517031007695e-05,
"loss": 5.163,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413147462300904e-05,
"loss": 5.171,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404761514790384e-05,
"loss": 5.1636,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.939637556727987e-05,
"loss": 5.1414,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938798961976935e-05,
"loss": 5.1559,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.937960367225883e-05,
"loss": 5.1503,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.937123410355204e-05,
"loss": 5.1265,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362864534845256e-05,
"loss": 5.1243,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935447858733473e-05,
"loss": 5.1062,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934609263982421e-05,
"loss": 5.0947,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933770669231369e-05,
"loss": 5.0932,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932932074480317e-05,
"loss": 5.0959,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932093479729265e-05,
"loss": 5.0953,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931254884978213e-05,
"loss": 5.1009,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930416290227161e-05,
"loss": 5.0863,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295793333564825e-05,
"loss": 5.0666,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287407386054305e-05,
"loss": 5.0672,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279021438543785e-05,
"loss": 5.0676,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270635491033264e-05,
"loss": 5.0571,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262249543522744e-05,
"loss": 5.0484,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.9253879974815954e-05,
"loss": 5.038,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.9245494027305433e-05,
"loss": 5.038,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.9237108079794913e-05,
"loss": 5.039,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922872213228439e-05,
"loss": 5.0252,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922033618477387e-05,
"loss": 5.0294,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921195023726335e-05,
"loss": 5.0171,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920356428975283e-05,
"loss": 5.0131,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919519472104604e-05,
"loss": 5.0,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918680877353552e-05,
"loss": 4.9955,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917842282602501e-05,
"loss": 4.99,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917005325731822e-05,
"loss": 4.9939,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.91616673098077e-05,
"loss": 4.9949,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915328136229718e-05,
"loss": 4.9706,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914489541478666e-05,
"loss": 4.9778,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913650946727614e-05,
"loss": 4.9669,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912812351976562e-05,
"loss": 4.9645,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911975395105883e-05,
"loss": 4.9567,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911136800354831e-05,
"loss": 4.9505,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910298205603779e-05,
"loss": 4.9503,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909459610852727e-05,
"loss": 4.9408,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908621016101675e-05,
"loss": 4.9391,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907782421350623e-05,
"loss": 4.9327,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906943826599571e-05,
"loss": 4.9236,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906105231848519e-05,
"loss": 4.9333,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052682749778396e-05,
"loss": 4.9213,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904431318107161e-05,
"loss": 4.9224,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903592723356109e-05,
"loss": 4.918,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027541286050565e-05,
"loss": 4.9185,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019155338540045e-05,
"loss": 4.9077,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010769391029525e-05,
"loss": 4.8938,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002383443519005e-05,
"loss": 4.9032,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994013874812214e-05,
"loss": 4.9068,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.89856279273017e-05,
"loss": 4.8935,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.897724197979118e-05,
"loss": 4.8867,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.896885603228066e-05,
"loss": 4.8835,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.896047008477014e-05,
"loss": 4.8824,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895208413725962e-05,
"loss": 4.8726,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.89436981897491e-05,
"loss": 4.8742,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893531224223858e-05,
"loss": 4.8652,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892694267353179e-05,
"loss": 4.865,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891855672602127e-05,
"loss": 4.856,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891017077851075e-05,
"loss": 4.8746,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890178483100023e-05,
"loss": 4.8571,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889339888348971e-05,
"loss": 4.8482,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888502931478292e-05,
"loss": 4.844,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766433672724e-05,
"loss": 4.8459,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886825741976188e-05,
"loss": 4.8461,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.8859871472251365e-05,
"loss": 4.8469,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.8851485524740845e-05,
"loss": 4.8348,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.8843115956034054e-05,
"loss": 4.8359,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.8834730008523534e-05,
"loss": 4.8307,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.8826344061013014e-05,
"loss": 4.8289,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.8817958113502494e-05,
"loss": 4.816,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.8809572165991974e-05,
"loss": 4.8283,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.8801186218481454e-05,
"loss": 4.8155,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879281664977466e-05,
"loss": 4.8013,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878443070226414e-05,
"loss": 4.8165,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877604475475362e-05,
"loss": 4.805,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87676588072431e-05,
"loss": 4.8059,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875927285973258e-05,
"loss": 4.8119,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875088691222206e-05,
"loss": 4.7924,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.760193824768066,
"eval_runtime": 293.8096,
"eval_samples_per_second": 1298.77,
"eval_steps_per_second": 40.588,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874250096471154e-05,
"loss": 4.7851,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873413139600475e-05,
"loss": 4.7883,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872574544849423e-05,
"loss": 4.7909,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871735950098371e-05,
"loss": 4.7833,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870897355347319e-05,
"loss": 4.7897,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870058760596267e-05,
"loss": 4.775,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869221803725588e-05,
"loss": 4.7807,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868383208974536e-05,
"loss": 4.7671,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867544614223484e-05,
"loss": 4.7751,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667076573528056e-05,
"loss": 4.7642,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658690626017536e-05,
"loss": 4.7616,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.8650304678507016e-05,
"loss": 4.7631,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8641918730996496e-05,
"loss": 4.7553,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633549162289705e-05,
"loss": 4.7509,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625163214779185e-05,
"loss": 4.7461,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.8616777267268665e-05,
"loss": 4.7346,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608391319758145e-05,
"loss": 4.7445,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.8600005372247625e-05,
"loss": 4.737,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591619424737105e-05,
"loss": 4.7308,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583233477226585e-05,
"loss": 4.7503,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574847529716065e-05,
"loss": 4.7319,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566461582205545e-05,
"loss": 4.7361,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558075634695025e-05,
"loss": 4.7285,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549689687184505e-05,
"loss": 4.7465,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854132011847772e-05,
"loss": 4.7155,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.85329341709672e-05,
"loss": 4.7169,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852454822345668e-05,
"loss": 4.7201,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851616227594616e-05,
"loss": 4.7218,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850777632843564e-05,
"loss": 4.7077,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849940675972885e-05,
"loss": 4.707,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849103719102206e-05,
"loss": 4.7159,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848265124351154e-05,
"loss": 4.7125,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847426529600102e-05,
"loss": 4.7136,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.84658793484905e-05,
"loss": 4.7087,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845749340097998e-05,
"loss": 4.7004,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844910745346946e-05,
"loss": 4.7085,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844072150595894e-05,
"loss": 4.6788,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843233555844842e-05,
"loss": 4.7005,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.84239496109379e-05,
"loss": 4.6742,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841556366342738e-05,
"loss": 4.6883,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840717771591686e-05,
"loss": 4.6797,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839880814721007e-05,
"loss": 4.6907,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839043857850328e-05,
"loss": 4.6784,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838205263099276e-05,
"loss": 4.6766,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373666683482236e-05,
"loss": 4.6793,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365280735971716e-05,
"loss": 4.6704,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835691116726493e-05,
"loss": 4.6847,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834852521975441e-05,
"loss": 4.6615,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834013927224389e-05,
"loss": 4.6554,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833175332473337e-05,
"loss": 4.6752,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832336737722285e-05,
"loss": 4.6745,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831498142971233e-05,
"loss": 4.658,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830659548220181e-05,
"loss": 4.6522,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829820953469129e-05,
"loss": 4.6587,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828982358718077e-05,
"loss": 4.6448,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828143763967025e-05,
"loss": 4.6685,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827305169215973e-05,
"loss": 4.6432,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826466574464921e-05,
"loss": 4.6502,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825629617594242e-05,
"loss": 4.6437,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824792660723563e-05,
"loss": 4.6369,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823954065972511e-05,
"loss": 4.6481,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.82311547122146e-05,
"loss": 4.633,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222785143507806e-05,
"loss": 4.6298,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214399195997286e-05,
"loss": 4.6314,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206013248486766e-05,
"loss": 4.6453,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197627300976246e-05,
"loss": 4.6295,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189241353465726e-05,
"loss": 4.6251,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180855405955206e-05,
"loss": 4.6192,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172469458444685e-05,
"loss": 4.6216,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164083510934165e-05,
"loss": 4.6409,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155697563423645e-05,
"loss": 4.6361,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147311615913125e-05,
"loss": 4.619,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.81389256684026e-05,
"loss": 4.6306,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813053972089208e-05,
"loss": 4.6345,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122170152185294e-05,
"loss": 4.621,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113784204674774e-05,
"loss": 4.6216,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105398257164254e-05,
"loss": 4.611,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097012309653734e-05,
"loss": 4.5993,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.8088626362143214e-05,
"loss": 4.6032,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.8080240414632694e-05,
"loss": 4.6074,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80718708459259e-05,
"loss": 4.6098,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806348489841538e-05,
"loss": 4.6276,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805509895090486e-05,
"loss": 4.6136,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804671300339434e-05,
"loss": 4.5942,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803832705588382e-05,
"loss": 4.6009,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.80299411083733e-05,
"loss": 4.606,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802155516086278e-05,
"loss": 4.6017,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.8013185592156e-05,
"loss": 4.5941,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800479964464548e-05,
"loss": 4.5926,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799641369713496e-05,
"loss": 4.5907,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798802774962444e-05,
"loss": 4.5966,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797965818091765e-05,
"loss": 4.5876,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797128861221086e-05,
"loss": 4.5927,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796290266470034e-05,
"loss": 4.5876,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795451671718982e-05,
"loss": 4.5867,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.79461307696793e-05,
"loss": 4.5766,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793774482216878e-05,
"loss": 4.5836,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792935887465826e-05,
"loss": 4.5771,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792097292714774e-05,
"loss": 4.5814,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912586979637217e-05,
"loss": 4.5849,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904201032126697e-05,
"loss": 4.569,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789581508461618e-05,
"loss": 4.5725,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788742913710566e-05,
"loss": 4.5689,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879043189595136e-05,
"loss": 4.5694,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.787067362088835e-05,
"loss": 4.5609,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786230405218156e-05,
"loss": 4.5626,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785391810467104e-05,
"loss": 4.5667,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784553215716052e-05,
"loss": 4.5558,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783714620965e-05,
"loss": 4.5615,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782876026213948e-05,
"loss": 4.5548,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782037431462896e-05,
"loss": 4.5482,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7811988367118434e-05,
"loss": 4.5677,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780360241960792e-05,
"loss": 4.5531,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779523285090114e-05,
"loss": 4.5585,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778684690339061e-05,
"loss": 4.5553,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777846095588009e-05,
"loss": 4.5656,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777007500836957e-05,
"loss": 4.555,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761705439662786e-05,
"loss": 4.5398,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775331949215226e-05,
"loss": 4.5526,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774493354464174e-05,
"loss": 4.5564,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773654759713122e-05,
"loss": 4.5428,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728194407228164e-05,
"loss": 4.5464,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771982483852137e-05,
"loss": 4.54,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771143889101086e-05,
"loss": 4.5481,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770305294350034e-05,
"loss": 4.5357,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769466699598982e-05,
"loss": 4.5434,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.76862810484793e-05,
"loss": 4.5344,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767789510096878e-05,
"loss": 4.539,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766950915345826e-05,
"loss": 4.528,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766112320594773e-05,
"loss": 4.5533,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765275363724095e-05,
"loss": 4.5398,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764436768973043e-05,
"loss": 4.5264,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.76359817422199e-05,
"loss": 4.5284,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762759579470938e-05,
"loss": 4.5303,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761920984719886e-05,
"loss": 4.5338,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761082389968834e-05,
"loss": 4.5413,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760245433098156e-05,
"loss": 4.5247,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759406838347104e-05,
"loss": 4.5302,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758568243596052e-05,
"loss": 4.524,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757729648845e-05,
"loss": 4.5297,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756891054093948e-05,
"loss": 4.5199,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560540972232686e-05,
"loss": 4.5288,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552155024722166e-05,
"loss": 4.5189,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543785456015375e-05,
"loss": 4.5133,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535399508504855e-05,
"loss": 4.5265,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527013560994335e-05,
"loss": 4.5199,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518627613483815e-05,
"loss": 4.5183,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510241665973295e-05,
"loss": 4.5198,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750185571846278e-05,
"loss": 4.5106,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.482818603515625,
"eval_runtime": 290.2427,
"eval_samples_per_second": 1314.731,
"eval_steps_per_second": 41.086,
"step": 152640
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 6.262592319085234e+16,
"trial_name": null,
"trial_params": null
}