abhinavp's picture
Training in progress, epoch 1, checkpoint
0772e47 verified
{
"best_metric": 4.484683036804199,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-reconstruction/lstm/4/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": 10.8185,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5433,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0559,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9906,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9467,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.8761,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7154,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6163,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993292879871958e-05,
"loss": 6.5258,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992454285120906e-05,
"loss": 6.4501,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.991615690369854e-05,
"loss": 6.3868,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990777095618801e-05,
"loss": 6.328,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 6.259,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 6.1899,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 6.1409,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 6.0809,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 6.0473,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 6.0075,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.9568,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9232,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8839,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8518,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8216,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.7846,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7675,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7279,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7087,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6832,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6563,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6283,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.614,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.6034,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5789,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.5579,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714926921053515e-05,
"loss": 5.5494,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5389,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5135,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4816,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4766,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.445,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4494,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 5.4331,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 5.4314,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.4016,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.4,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3864,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.379,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960595873982795e-05,
"loss": 5.3739,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959757279231743e-05,
"loss": 5.341,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3389,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3428,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.332,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956404538107908e-05,
"loss": 5.3082,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955565943356856e-05,
"loss": 5.296,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954727348605804e-05,
"loss": 5.2874,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2792,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.2906,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2508,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2611,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.9505360127309166e-05,
"loss": 5.2504,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2354,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 5.2373,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2106,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.2055,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.2032,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.2153,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.1855,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943830530483247e-05,
"loss": 5.181,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942991935732195e-05,
"loss": 5.1606,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942153340981143e-05,
"loss": 5.1701,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1689,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.940477789359412e-05,
"loss": 5.1685,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.93963919460836e-05,
"loss": 5.1453,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.938800599857309e-05,
"loss": 5.157,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.937962005106256e-05,
"loss": 5.1578,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.937123410355204e-05,
"loss": 5.1332,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936284815604152e-05,
"loss": 5.1207,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935447858733473e-05,
"loss": 5.1116,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.934609263982421e-05,
"loss": 5.1023,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933770669231369e-05,
"loss": 5.1123,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932932074480317e-05,
"loss": 5.0907,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932093479729265e-05,
"loss": 5.1072,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931254884978213e-05,
"loss": 5.0995,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930417928107534e-05,
"loss": 5.0814,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295793333564825e-05,
"loss": 5.0679,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287407386054305e-05,
"loss": 5.0694,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279021438543785e-05,
"loss": 5.0694,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270635491033264e-05,
"loss": 5.0732,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.9262265922326474e-05,
"loss": 5.0527,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.9253879974815954e-05,
"loss": 5.0515,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.9245494027305433e-05,
"loss": 5.0474,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.9237108079794913e-05,
"loss": 5.0329,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922873851108812e-05,
"loss": 5.0317,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92203525635776e-05,
"loss": 5.0284,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921196661606708e-05,
"loss": 5.021,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920358066855656e-05,
"loss": 5.0197,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919519472104604e-05,
"loss": 5.0085,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918680877353552e-05,
"loss": 5.0013,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917842282602501e-05,
"loss": 5.0073,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917003687851449e-05,
"loss": 5.0022,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.91616673098077e-05,
"loss": 4.9959,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915328136229718e-05,
"loss": 4.9894,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914491179359039e-05,
"loss": 4.9801,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.913652584607987e-05,
"loss": 4.9745,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912813989856935e-05,
"loss": 4.9717,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911975395105883e-05,
"loss": 4.9503,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.911136800354831e-05,
"loss": 4.9574,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910298205603779e-05,
"loss": 4.9549,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909459610852727e-05,
"loss": 4.958,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908621016101675e-05,
"loss": 4.945,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907782421350623e-05,
"loss": 4.9491,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906943826599571e-05,
"loss": 4.9261,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906105231848519e-05,
"loss": 4.9461,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.9052682749778396e-05,
"loss": 4.9179,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.9044296802267876e-05,
"loss": 4.9265,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.9035910854757356e-05,
"loss": 4.9276,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.9027524907246836e-05,
"loss": 4.9236,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.9019155338540045e-05,
"loss": 4.9186,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.9010769391029525e-05,
"loss": 4.9054,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.9002383443519005e-05,
"loss": 4.9104,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8993997496008485e-05,
"loss": 4.9144,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985611548497965e-05,
"loss": 4.8975,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977225600987445e-05,
"loss": 4.893,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968839653476924e-05,
"loss": 4.8885,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.896045370596641e-05,
"loss": 4.9005,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.895208413725962e-05,
"loss": 4.8691,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.89436981897491e-05,
"loss": 4.8741,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893532862104231e-05,
"loss": 4.8669,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892694267353179e-05,
"loss": 4.8759,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891855672602127e-05,
"loss": 4.8615,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891017077851075e-05,
"loss": 4.8792,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890180120980396e-05,
"loss": 4.8686,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889341526229344e-05,
"loss": 4.8586,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888502931478292e-05,
"loss": 4.8507,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.8876659746076134e-05,
"loss": 4.8568,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.8868273798565614e-05,
"loss": 4.8555,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.8859887851055094e-05,
"loss": 4.8544,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.8851501903544574e-05,
"loss": 4.8407,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.8843115956034054e-05,
"loss": 4.8504,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.8834730008523534e-05,
"loss": 4.8391,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.8826344061013014e-05,
"loss": 4.8385,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.8817958113502494e-05,
"loss": 4.8202,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88095885447957e-05,
"loss": 4.8369,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880120259728518e-05,
"loss": 4.8212,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879281664977466e-05,
"loss": 4.8019,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878443070226414e-05,
"loss": 4.8289,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877604475475362e-05,
"loss": 4.8157,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87676588072431e-05,
"loss": 4.8132,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875927285973258e-05,
"loss": 4.8133,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875088691222206e-05,
"loss": 4.7992,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.764401912689209,
"eval_runtime": 299.3062,
"eval_samples_per_second": 1274.918,
"eval_steps_per_second": 39.842,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.874251734351528e-05,
"loss": 4.7826,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873413139600475e-05,
"loss": 4.789,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872574544849423e-05,
"loss": 4.8036,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871735950098371e-05,
"loss": 4.7906,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870897355347319e-05,
"loss": 4.7964,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870058760596267e-05,
"loss": 4.7835,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869220165845215e-05,
"loss": 4.7838,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868381571094163e-05,
"loss": 4.7695,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675462521038576e-05,
"loss": 4.7723,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667076573528056e-05,
"loss": 4.7732,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658690626017536e-05,
"loss": 4.7864,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865032105731075e-05,
"loss": 4.7789,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8641935109800225e-05,
"loss": 4.7617,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633549162289705e-05,
"loss": 4.7572,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.8625163214779185e-05,
"loss": 4.7444,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.86167936460724e-05,
"loss": 4.7476,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608407698561874e-05,
"loss": 4.7591,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.8600021751051354e-05,
"loss": 4.7453,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591635803540834e-05,
"loss": 4.7423,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858326623483405e-05,
"loss": 4.7573,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.857488028732352e-05,
"loss": 4.7461,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.856649433981301e-05,
"loss": 4.7397,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.855810839230249e-05,
"loss": 4.7398,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.854972244479197e-05,
"loss": 4.7527,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854133649728145e-05,
"loss": 4.7244,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853295054977093e-05,
"loss": 4.7293,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852456460226041e-05,
"loss": 4.7359,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851617865474989e-05,
"loss": 4.7263,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.85078090860431e-05,
"loss": 4.7099,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849942313853258e-05,
"loss": 4.7139,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849103719102206e-05,
"loss": 4.7273,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848266762231527e-05,
"loss": 4.7177,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847428167480475e-05,
"loss": 4.7145,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846589572729423e-05,
"loss": 4.7184,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845750977978371e-05,
"loss": 4.7155,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.8449123832273194e-05,
"loss": 4.7117,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.8440737884762674e-05,
"loss": 4.6946,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.8432351937252154e-05,
"loss": 4.6992,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.8423965989741634e-05,
"loss": 4.6831,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.8415580042231114e-05,
"loss": 4.6972,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840721047352432e-05,
"loss": 4.6919,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.83988245260138e-05,
"loss": 4.7009,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839045495730701e-05,
"loss": 4.6824,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838206900979649e-05,
"loss": 4.6937,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837368306228597e-05,
"loss": 4.685,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836529711477545e-05,
"loss": 4.6857,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.835691116726493e-05,
"loss": 4.6947,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834852521975441e-05,
"loss": 4.6625,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834013927224389e-05,
"loss": 4.6669,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833175332473337e-05,
"loss": 4.6859,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832336737722285e-05,
"loss": 4.6784,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.831498142971233e-05,
"loss": 4.6676,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830659548220181e-05,
"loss": 4.659,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.829820953469129e-05,
"loss": 4.6605,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.828985634478824e-05,
"loss": 4.6487,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.828147039727771e-05,
"loss": 4.6768,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827308444976719e-05,
"loss": 4.6443,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826469850225667e-05,
"loss": 4.6643,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256328933549886e-05,
"loss": 4.653,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247942986039366e-05,
"loss": 4.6465,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.8239557038528846e-05,
"loss": 4.6516,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.8231171091018326e-05,
"loss": 4.6381,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222785143507806e-05,
"loss": 4.6316,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.8214399195997286e-05,
"loss": 4.6396,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.8206029627290495e-05,
"loss": 4.6582,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.8197643679779975e-05,
"loss": 4.6277,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189257732269455e-05,
"loss": 4.6318,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.8180871784758935e-05,
"loss": 4.6177,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.8172502216052144e-05,
"loss": 4.6324,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.8164116268541624e-05,
"loss": 4.6451,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155730321031104e-05,
"loss": 4.6375,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147344373520584e-05,
"loss": 4.6243,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138958426010064e-05,
"loss": 4.6384,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813057247849955e-05,
"loss": 4.6444,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812218653098903e-05,
"loss": 4.6227,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.811381696228224e-05,
"loss": 4.6178,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.810543101477172e-05,
"loss": 4.6199,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.80970450672612e-05,
"loss": 4.6112,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808865911975068e-05,
"loss": 4.6203,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808028955104389e-05,
"loss": 4.6084,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807190360353337e-05,
"loss": 4.6225,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806351765602285e-05,
"loss": 4.619,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805513170851233e-05,
"loss": 4.614,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804674576100181e-05,
"loss": 4.5967,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803835981349129e-05,
"loss": 4.6055,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.802997386598077e-05,
"loss": 4.6078,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802158791847025e-05,
"loss": 4.6152,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801320197095973e-05,
"loss": 4.6061,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800481602344921e-05,
"loss": 4.6005,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799643007593869e-05,
"loss": 4.6044,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798804412842817e-05,
"loss": 4.5925,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797967455972138e-05,
"loss": 4.5912,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797128861221086e-05,
"loss": 4.5988,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796290266470034e-05,
"loss": 4.5899,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795451671718982e-05,
"loss": 4.5921,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.79461307696793e-05,
"loss": 4.5919,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793774482216878e-05,
"loss": 4.5788,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.7929375253461986e-05,
"loss": 4.591,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792098930595147e-05,
"loss": 4.5968,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791261973724468e-05,
"loss": 4.5871,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790423378973416e-05,
"loss": 4.5822,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789584784222364e-05,
"loss": 4.5732,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788746189471312e-05,
"loss": 4.578,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.78790759472026e-05,
"loss": 4.5778,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.787068999969208e-05,
"loss": 4.5613,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786232043098529e-05,
"loss": 4.5651,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785393448347477e-05,
"loss": 4.5697,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784554853596425e-05,
"loss": 4.5774,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783716258845373e-05,
"loss": 4.5651,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782877664094321e-05,
"loss": 4.5702,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782039069343269e-05,
"loss": 4.5531,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781200474592217e-05,
"loss": 4.5751,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780361879841165e-05,
"loss": 4.5542,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779523285090114e-05,
"loss": 4.5592,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786863282194346e-05,
"loss": 4.5696,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778477334683826e-05,
"loss": 4.5639,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770091387173306e-05,
"loss": 4.5626,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761705439662786e-05,
"loss": 4.5488,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.7753335870955995e-05,
"loss": 4.5587,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7744966302249204e-05,
"loss": 4.566,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736580354738684e-05,
"loss": 4.5484,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728194407228164e-05,
"loss": 4.5505,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719808459717644e-05,
"loss": 4.5451,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.7711422512207124e-05,
"loss": 4.5622,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.7703036564696604e-05,
"loss": 4.5333,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.7694650617186084e-05,
"loss": 4.5424,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.7686264669675564e-05,
"loss": 4.5339,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767789510096878e-05,
"loss": 4.5474,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766950915345826e-05,
"loss": 4.5346,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766112320594773e-05,
"loss": 4.5548,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765273725843721e-05,
"loss": 4.5489,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764435131092669e-05,
"loss": 4.5381,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763596536341617e-05,
"loss": 4.5313,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762759579470938e-05,
"loss": 4.5422,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761920984719886e-05,
"loss": 4.5407,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761082389968834e-05,
"loss": 4.5475,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760243795217783e-05,
"loss": 4.525,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759405200466731e-05,
"loss": 4.5431,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758566605715679e-05,
"loss": 4.5349,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757729648845e-05,
"loss": 4.5387,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756891054093948e-05,
"loss": 4.5212,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756052459342896e-05,
"loss": 4.5354,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755213864591844e-05,
"loss": 4.5275,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754375269840792e-05,
"loss": 4.5157,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.75353667508974e-05,
"loss": 4.5329,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7526997182190606e-05,
"loss": 4.5275,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518611234680086e-05,
"loss": 4.5235,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510225287169566e-05,
"loss": 4.5208,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501839339659046e-05,
"loss": 4.5125,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.484683036804199,
"eval_runtime": 299.2612,
"eval_samples_per_second": 1275.11,
"eval_steps_per_second": 39.848,
"step": 152640
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 6.290097853776826e+16,
"trial_name": null,
"trial_params": null
}