abhinavp's picture
Training in progress, epoch 1, checkpoint
a3b09e6 verified
{
"best_metric": 4.1663994789123535,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-reconstruction/lstm/4/checkpoints/checkpoint-457920",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 457920,
"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
},
{
"epoch": 0.0,
"learning_rate": 4.7493453392148526e-05,
"loss": 4.498,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748506744463801e-05,
"loss": 4.5051,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747668149712749e-05,
"loss": 4.5258,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746829554961697e-05,
"loss": 4.5149,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7459909602106446e-05,
"loss": 4.5183,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451523654595926e-05,
"loss": 4.5055,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443137707085406e-05,
"loss": 4.5114,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434751759574886e-05,
"loss": 4.4992,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426365812064366e-05,
"loss": 4.5026,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7417979864553846e-05,
"loss": 4.51,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409593917043326e-05,
"loss": 4.5148,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401207969532806e-05,
"loss": 4.5154,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392838400826015e-05,
"loss": 4.4974,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384452453315495e-05,
"loss": 4.4949,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376066505804975e-05,
"loss": 4.4923,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736768055829446e-05,
"loss": 4.4823,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735929461078394e-05,
"loss": 4.4999,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735090866327342e-05,
"loss": 4.4874,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.73425227157629e-05,
"loss": 4.4908,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733413676825238e-05,
"loss": 4.509,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732575082074186e-05,
"loss": 4.4926,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317364873231334e-05,
"loss": 4.4918,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.7308978925720814e-05,
"loss": 4.4936,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300592978210294e-05,
"loss": 4.5058,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729222340950351e-05,
"loss": 4.4754,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728385384079672e-05,
"loss": 4.4837,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.72754678932862e-05,
"loss": 4.4914,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726708194577568e-05,
"loss": 4.4867,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725869599826516e-05,
"loss": 4.4738,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725031005075464e-05,
"loss": 4.4698,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724192410324412e-05,
"loss": 4.4918,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.72335381557336e-05,
"loss": 4.4875,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722515220822308e-05,
"loss": 4.4773,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721678263951629e-05,
"loss": 4.4852,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208413070809504e-05,
"loss": 4.4824,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.7200027123298984e-05,
"loss": 4.4777,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719164117578846e-05,
"loss": 4.4651,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718325522827794e-05,
"loss": 4.4753,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717486928076742e-05,
"loss": 4.4544,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.71664833332569e-05,
"loss": 4.473,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.7158097385746384e-05,
"loss": 4.4674,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714972781703959e-05,
"loss": 4.4749,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714134186952907e-05,
"loss": 4.4633,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713295592201855e-05,
"loss": 4.4704,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712456997450803e-05,
"loss": 4.469,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711618402699751e-05,
"loss": 4.4644,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710779807948699e-05,
"loss": 4.4758,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709941213197647e-05,
"loss": 4.4462,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709102618446595e-05,
"loss": 4.4564,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708265661575916e-05,
"loss": 4.469,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707428704705237e-05,
"loss": 4.4657,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7065917478345586e-05,
"loss": 4.4539,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057531530835066e-05,
"loss": 4.4457,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.7049145583324546e-05,
"loss": 4.4553,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040759635814026e-05,
"loss": 4.4358,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032373688303506e-05,
"loss": 4.4691,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7023987740792986e-05,
"loss": 4.4423,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015601793282466e-05,
"loss": 4.4508,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007215845771946e-05,
"loss": 4.4498,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998829898261426e-05,
"loss": 4.4415,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990443950750906e-05,
"loss": 4.4478,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982058003240386e-05,
"loss": 4.4373,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973672055729866e-05,
"loss": 4.4331,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965302487023075e-05,
"loss": 4.4354,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695693291831629e-05,
"loss": 4.4556,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694854697080577e-05,
"loss": 4.4329,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694016102329525e-05,
"loss": 4.4337,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693177507578473e-05,
"loss": 4.4215,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692338912827421e-05,
"loss": 4.4369,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691500318076369e-05,
"loss": 4.4466,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.69066336120569e-05,
"loss": 4.4462,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689824766454638e-05,
"loss": 4.4302,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688986171703586e-05,
"loss": 4.4458,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688147576952534e-05,
"loss": 4.4547,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687308982201481e-05,
"loss": 4.4322,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686472025330803e-05,
"loss": 4.4225,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685633430579751e-05,
"loss": 4.4354,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684794835828699e-05,
"loss": 4.427,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683956241077647e-05,
"loss": 4.4312,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683117646326595e-05,
"loss": 4.4213,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682279051575543e-05,
"loss": 4.4346,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681440456824491e-05,
"loss": 4.4379,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680601862073439e-05,
"loss": 4.4291,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679763267322387e-05,
"loss": 4.4139,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678926310451708e-05,
"loss": 4.4229,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678087715700656e-05,
"loss": 4.4248,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677249120949604e-05,
"loss": 4.4339,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676410526198552e-05,
"loss": 4.4245,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755735693278726e-05,
"loss": 4.4261,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747349745768206e-05,
"loss": 4.4243,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673896379825769e-05,
"loss": 4.4155,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673057785074717e-05,
"loss": 4.4149,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672220828204038e-05,
"loss": 4.4166,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671382233452986e-05,
"loss": 4.4172,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.670543638701934e-05,
"loss": 4.4203,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669705043950882e-05,
"loss": 4.4181,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.66886644919983e-05,
"loss": 4.402,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.668027854448778e-05,
"loss": 4.4198,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667189259697726e-05,
"loss": 4.425,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.666350664946674e-05,
"loss": 4.4145,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.665512070195622e-05,
"loss": 4.415,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664675113324943e-05,
"loss": 4.403,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663836518573891e-05,
"loss": 4.41,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.662997923822839e-05,
"loss": 4.4109,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662159329071788e-05,
"loss": 4.3898,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661320734320736e-05,
"loss": 4.4002,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6604837774500567e-05,
"loss": 4.4081,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596451826990047e-05,
"loss": 4.4075,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588082258283256e-05,
"loss": 4.3976,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579696310772736e-05,
"loss": 4.4059,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571310363262216e-05,
"loss": 4.3912,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6562924415751695e-05,
"loss": 4.4102,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554538468241175e-05,
"loss": 4.394,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.6546168899534385e-05,
"loss": 4.3942,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.6537782952023865e-05,
"loss": 4.4095,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.6529397004513344e-05,
"loss": 4.4069,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652101105700283e-05,
"loss": 4.4025,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512625109492304e-05,
"loss": 4.3938,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.6504239161981784e-05,
"loss": 4.3971,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.6495869593275e-05,
"loss": 4.4017,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648748364576447e-05,
"loss": 4.3939,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647909769825395e-05,
"loss": 4.395,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647071175074343e-05,
"loss": 4.3872,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646234218203665e-05,
"loss": 4.399,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645395623452612e-05,
"loss": 4.3873,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.64455702870156e-05,
"loss": 4.3884,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643718433950508e-05,
"loss": 4.3754,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642879839199457e-05,
"loss": 4.3959,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642041244448405e-05,
"loss": 4.3793,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641202649697353e-05,
"loss": 4.4012,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.640364054946301e-05,
"loss": 4.3971,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639525460195249e-05,
"loss": 4.3902,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.63868850332457e-05,
"loss": 4.3761,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637849908573518e-05,
"loss": 4.3957,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637011313822466e-05,
"loss": 4.3911,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636174356951787e-05,
"loss": 4.3954,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635335762200735e-05,
"loss": 4.3816,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634497167449683e-05,
"loss": 4.3893,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633658572698631e-05,
"loss": 4.391,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632819977947579e-05,
"loss": 4.3928,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631981383196527e-05,
"loss": 4.3788,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631142788445475e-05,
"loss": 4.3857,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630304193694423e-05,
"loss": 4.3818,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629465598943371e-05,
"loss": 4.3702,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628627004192319e-05,
"loss": 4.3889,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277884094412666e-05,
"loss": 4.3877,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.6269498146902146e-05,
"loss": 4.3753,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626114495699909e-05,
"loss": 4.381,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625275900948857e-05,
"loss": 4.3702,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.349175453186035,
"eval_runtime": 291.0538,
"eval_samples_per_second": 1311.067,
"eval_steps_per_second": 40.972,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624437306197805e-05,
"loss": 4.3648,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623598711446753e-05,
"loss": 4.3603,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622760116695701e-05,
"loss": 4.385,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219215219446484e-05,
"loss": 4.371,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621082927193597e-05,
"loss": 4.3821,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620244332442545e-05,
"loss": 4.3657,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619407375571867e-05,
"loss": 4.3724,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.618568780820814e-05,
"loss": 4.3582,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177318239501356e-05,
"loss": 4.3686,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6168932291990836e-05,
"loss": 4.3685,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616054634448031e-05,
"loss": 4.3799,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615216039696979e-05,
"loss": 4.3782,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6143790828263005e-05,
"loss": 4.3605,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135404880752485e-05,
"loss": 4.3603,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612701893324196e-05,
"loss": 4.357,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611863298573144e-05,
"loss": 4.3506,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.6110247038220925e-05,
"loss": 4.361,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.6101861090710405e-05,
"loss": 4.3552,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.6093475143199885e-05,
"loss": 4.3563,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.6085089195689365e-05,
"loss": 4.3791,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.6076703248178845e-05,
"loss": 4.3595,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.6068317300668325e-05,
"loss": 4.3563,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6059947731961534e-05,
"loss": 4.3633,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.6051561784451014e-05,
"loss": 4.3702,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.6043175836940494e-05,
"loss": 4.3465,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.6034789889429974e-05,
"loss": 4.3525,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.6026403941919454e-05,
"loss": 4.3619,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601803437321266e-05,
"loss": 4.3581,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.600964842570214e-05,
"loss": 4.3422,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600126247819162e-05,
"loss": 4.3415,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599287653068111e-05,
"loss": 4.3602,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598449058317059e-05,
"loss": 4.3599,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.59761210144638e-05,
"loss": 4.3535,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596773506695328e-05,
"loss": 4.3564,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595934911944276e-05,
"loss": 4.3527,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595096317193224e-05,
"loss": 4.3517,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594257722442172e-05,
"loss": 4.3371,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.59341912769112e-05,
"loss": 4.3538,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592580532940067e-05,
"loss": 4.331,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591741938189015e-05,
"loss": 4.3458,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590904981318337e-05,
"loss": 4.3406,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590066386567285e-05,
"loss": 4.3544,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589227791816233e-05,
"loss": 4.3421,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588389197065181e-05,
"loss": 4.3442,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587552240194502e-05,
"loss": 4.3444,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867136454434496e-05,
"loss": 4.3466,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585876688572771e-05,
"loss": 4.3521,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585038093821719e-05,
"loss": 4.3273,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584199499070667e-05,
"loss": 4.3327,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.5833609043196145e-05,
"loss": 4.349,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.5825223095685625e-05,
"loss": 4.3446,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.5816837148175105e-05,
"loss": 4.3344,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808451200664585e-05,
"loss": 4.3284,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800065253154065e-05,
"loss": 4.3362,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791679305643545e-05,
"loss": 4.3194,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783293358133025e-05,
"loss": 4.3466,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577490741062251e-05,
"loss": 4.3237,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576652146311199e-05,
"loss": 4.332,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.57581518944052e-05,
"loss": 4.3354,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.574976594689468e-05,
"loss": 4.3244,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574137999938416e-05,
"loss": 4.3272,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573299405187364e-05,
"loss": 4.3238,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572462448316685e-05,
"loss": 4.3166,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571623853565633e-05,
"loss": 4.3255,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570785258814581e-05,
"loss": 4.3343,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569946664063529e-05,
"loss": 4.3203,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.56910970719285e-05,
"loss": 4.3208,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568271112441798e-05,
"loss": 4.3101,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.5674325176907465e-05,
"loss": 4.3195,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.5665955608200674e-05,
"loss": 4.3303,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.5657569660690154e-05,
"loss": 4.339,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.5649183713179634e-05,
"loss": 4.3155,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.5640797765669114e-05,
"loss": 4.3324,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.5632411818158594e-05,
"loss": 4.3377,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624025870648074e-05,
"loss": 4.3297,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561565630194128e-05,
"loss": 4.3059,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560727035443076e-05,
"loss": 4.3258,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559888440692024e-05,
"loss": 4.3208,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559049845940972e-05,
"loss": 4.3145,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.55821125118992e-05,
"loss": 4.3193,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557372656438868e-05,
"loss": 4.3194,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556534061687816e-05,
"loss": 4.3294,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555697104817138e-05,
"loss": 4.319,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554858510066086e-05,
"loss": 4.306,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554019915315033e-05,
"loss": 4.3169,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553181320563981e-05,
"loss": 4.3113,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552342725812929e-05,
"loss": 4.3252,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551504131061877e-05,
"loss": 4.3225,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550668812071572e-05,
"loss": 4.3141,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.5498318552008926e-05,
"loss": 4.3182,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.5489932604498406e-05,
"loss": 4.3053,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.5481546656987886e-05,
"loss": 4.3075,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547316070947737e-05,
"loss": 4.3096,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546477476196685e-05,
"loss": 4.3129,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545638881445633e-05,
"loss": 4.3114,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448002866945806e-05,
"loss": 4.32,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.5439616919435286e-05,
"loss": 4.2945,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.5431230971924765e-05,
"loss": 4.3149,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.5422845024414245e-05,
"loss": 4.3218,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.5414459076903725e-05,
"loss": 4.3109,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.5406073129393205e-05,
"loss": 4.3074,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.5397687181882685e-05,
"loss": 4.3006,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389301234372165e-05,
"loss": 4.3075,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5380931665665374e-05,
"loss": 4.3072,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372545718154854e-05,
"loss": 4.2867,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536415977064434e-05,
"loss": 4.299,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535577382313382e-05,
"loss": 4.3033,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.53473878756233e-05,
"loss": 4.307,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533900192811278e-05,
"loss": 4.2914,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533061598060226e-05,
"loss": 4.3111,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532223003309174e-05,
"loss": 4.2854,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531386046438495e-05,
"loss": 4.3089,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530549089567816e-05,
"loss": 4.2957,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529710494816764e-05,
"loss": 4.2903,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528871900065712e-05,
"loss": 4.3087,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.52803330531466e-05,
"loss": 4.3082,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527196348443981e-05,
"loss": 4.3024,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.5263593915733024e-05,
"loss": 4.297,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.5255207968222504e-05,
"loss": 4.2983,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.5246822020711984e-05,
"loss": 4.3021,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.5238436073201464e-05,
"loss": 4.2914,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.5230050125690944e-05,
"loss": 4.2972,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.5221664178180424e-05,
"loss": 4.2944,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.5213278230669904e-05,
"loss": 4.2973,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.5204892283159384e-05,
"loss": 4.2954,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.5196506335648863e-05,
"loss": 4.2929,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.5188120388138343e-05,
"loss": 4.2735,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517976719823528e-05,
"loss": 4.298,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517138125072476e-05,
"loss": 4.2853,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516299530321425e-05,
"loss": 4.3017,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515460935570373e-05,
"loss": 4.2994,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514622340819321e-05,
"loss": 4.2983,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513783746068269e-05,
"loss": 4.2799,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512945151317217e-05,
"loss": 4.2999,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512106556566164e-05,
"loss": 4.2949,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511269599695486e-05,
"loss": 4.3008,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510431004944434e-05,
"loss": 4.2832,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509592410193382e-05,
"loss": 4.3015,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508753815442329e-05,
"loss": 4.2979,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.507915220691277e-05,
"loss": 4.2999,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507076625940225e-05,
"loss": 4.2788,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506238031189173e-05,
"loss": 4.2936,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505399436438121e-05,
"loss": 4.2891,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.50456084168707e-05,
"loss": 4.28,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.5037238848163906e-05,
"loss": 4.2909,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5028852900653386e-05,
"loss": 4.2936,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020466953142866e-05,
"loss": 4.2846,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012081005632346e-05,
"loss": 4.2852,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.5003711436925555e-05,
"loss": 4.2826,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.2646164894104,
"eval_runtime": 293.7415,
"eval_samples_per_second": 1299.071,
"eval_steps_per_second": 40.597,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.4995325489415035e-05,
"loss": 4.2657,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.4986939541904515e-05,
"loss": 4.2712,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978553594393995e-05,
"loss": 4.2903,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970167646883475e-05,
"loss": 4.2816,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4961781699372955e-05,
"loss": 4.2915,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953395751862435e-05,
"loss": 4.2765,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945009804351915e-05,
"loss": 4.2807,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936623856841395e-05,
"loss": 4.2691,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492825428813461e-05,
"loss": 4.2801,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.491986834062409e-05,
"loss": 4.2803,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.491148239311357e-05,
"loss": 4.2862,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490309644560305e-05,
"loss": 4.29,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489471049809253e-05,
"loss": 4.2708,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.4886324550582003e-05,
"loss": 4.2737,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.4877938603071483e-05,
"loss": 4.2685,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486955265556096e-05,
"loss": 4.2627,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486116670805044e-05,
"loss": 4.2736,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485278076053992e-05,
"loss": 4.2697,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.48443948130294e-05,
"loss": 4.2688,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483600886551888e-05,
"loss": 4.289,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482762291800836e-05,
"loss": 4.2715,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481923697049785e-05,
"loss": 4.2704,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481085102298733e-05,
"loss": 4.2782,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480246507547681e-05,
"loss": 4.2834,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479409550677002e-05,
"loss": 4.2626,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.47857095592595e-05,
"loss": 4.2696,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477732361174898e-05,
"loss": 4.2743,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476893766423846e-05,
"loss": 4.2712,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476056809553167e-05,
"loss": 4.2557,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475218214802115e-05,
"loss": 4.2588,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474379620051063e-05,
"loss": 4.2738,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473541025300011e-05,
"loss": 4.2756,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472704068429332e-05,
"loss": 4.2711,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.4718654736782804e-05,
"loss": 4.2749,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710268789272283e-05,
"loss": 4.2668,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.4701882841761763e-05,
"loss": 4.2716,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693496894251243e-05,
"loss": 4.2573,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.4685110946740717e-05,
"loss": 4.2651,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4676724999230197e-05,
"loss": 4.2497,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668339051719676e-05,
"loss": 4.2613,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.465996948301289e-05,
"loss": 4.2581,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651583535502366e-05,
"loss": 4.2737,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.4643197587991846e-05,
"loss": 4.2615,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4634811640481325e-05,
"loss": 4.2625,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462644207177454e-05,
"loss": 4.2626,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461805612426402e-05,
"loss": 4.2649,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.460968655555724e-05,
"loss": 4.271,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.460130060804672e-05,
"loss": 4.2482,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.459291466053619e-05,
"loss": 4.2499,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.458452871302567e-05,
"loss": 4.2688,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576159144318886e-05,
"loss": 4.2636,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4567773196808366e-05,
"loss": 4.2518,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455938724929784e-05,
"loss": 4.2476,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455100130178732e-05,
"loss": 4.2582,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.45426153542768e-05,
"loss": 4.2426,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453422940676628e-05,
"loss": 4.2635,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452584345925576e-05,
"loss": 4.2428,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451745751174524e-05,
"loss": 4.2527,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.4509087943038455e-05,
"loss": 4.2551,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.4500701995527935e-05,
"loss": 4.2492,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.4492316048017415e-05,
"loss": 4.2443,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.4483930100506895e-05,
"loss": 4.2485,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.4475560531800104e-05,
"loss": 4.2381,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.4467174584289584e-05,
"loss": 4.2474,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.4458788636779064e-05,
"loss": 4.2562,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.4450402689268544e-05,
"loss": 4.2437,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444204949936548e-05,
"loss": 4.243,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443366355185496e-05,
"loss": 4.2326,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442527760434444e-05,
"loss": 4.2389,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441689165683393e-05,
"loss": 4.2559,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440852208812714e-05,
"loss": 4.2575,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440013614061662e-05,
"loss": 4.2438,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.43917501931061e-05,
"loss": 4.2539,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438336424559558e-05,
"loss": 4.2629,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437497829808506e-05,
"loss": 4.2516,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436659235057454e-05,
"loss": 4.233,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435820640306402e-05,
"loss": 4.2503,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.4349836834357227e-05,
"loss": 4.2464,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.4341450886846707e-05,
"loss": 4.2399,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333081318139916e-05,
"loss": 4.2433,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4324695370629396e-05,
"loss": 4.2483,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431630942311888e-05,
"loss": 4.2544,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430792347560836e-05,
"loss": 4.2446,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429953752809784e-05,
"loss": 4.2285,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429115158058732e-05,
"loss": 4.2433,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.42827656330768e-05,
"loss": 4.241,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427437968556628e-05,
"loss": 4.2443,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426599373805576e-05,
"loss": 4.2475,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425762416934897e-05,
"loss": 4.2426,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424923822183845e-05,
"loss": 4.2455,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424085227432793e-05,
"loss": 4.2338,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423246632681741e-05,
"loss": 4.231,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422408037930689e-05,
"loss": 4.2344,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421569443179637e-05,
"loss": 4.2441,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420732486308958e-05,
"loss": 4.2386,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419893891557907e-05,
"loss": 4.2449,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.419055296806855e-05,
"loss": 4.224,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.418216702055803e-05,
"loss": 4.2396,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.41737810730475e-05,
"loss": 4.2479,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.416539512553698e-05,
"loss": 4.242,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415700917802646e-05,
"loss": 4.2356,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.4148639609319676e-05,
"loss": 4.2308,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414025366180915e-05,
"loss": 4.2341,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413186771429863e-05,
"loss": 4.2382,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412348176678811e-05,
"loss": 4.2147,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411509581927759e-05,
"loss": 4.2316,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106726250570805e-05,
"loss": 4.2279,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098340303060284e-05,
"loss": 4.2372,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.4089954355549764e-05,
"loss": 4.2216,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081568408039244e-05,
"loss": 4.2393,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.4073182460528724e-05,
"loss": 4.2254,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.4064812891821933e-05,
"loss": 4.2346,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.4056426944311413e-05,
"loss": 4.226,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404804099680089e-05,
"loss": 4.217,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.403965504929037e-05,
"loss": 4.2392,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403126910177985e-05,
"loss": 4.2411,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402289953307306e-05,
"loss": 4.236,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401451358556254e-05,
"loss": 4.2252,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400614401685576e-05,
"loss": 4.2291,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399775806934524e-05,
"loss": 4.235,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398937212183472e-05,
"loss": 4.2213,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.39809861743242e-05,
"loss": 4.2288,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397260022681368e-05,
"loss": 4.2234,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396421427930316e-05,
"loss": 4.2275,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395582833179264e-05,
"loss": 4.2279,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394744238428212e-05,
"loss": 4.2266,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.39390564367716e-05,
"loss": 4.2089,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393067048926108e-05,
"loss": 4.2281,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392228454175056e-05,
"loss": 4.2202,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391389859424003e-05,
"loss": 4.2355,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390552902553325e-05,
"loss": 4.2277,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389714307802273e-05,
"loss": 4.2336,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388875713051221e-05,
"loss": 4.214,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388037118300169e-05,
"loss": 4.235,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387198523549117e-05,
"loss": 4.2306,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3863599287980647e-05,
"loss": 4.2318,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855213340470127e-05,
"loss": 4.2168,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3846827392959606e-05,
"loss": 4.232,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.3838457824252816e-05,
"loss": 4.2318,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830071876742296e-05,
"loss": 4.2381,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3821685929231775e-05,
"loss": 4.2116,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813299981721255e-05,
"loss": 4.2273,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3804930413014465e-05,
"loss": 4.222,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796544465503944e-05,
"loss": 4.213,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378817489679716e-05,
"loss": 4.2258,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.377978894928664e-05,
"loss": 4.2277,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771419380579856e-05,
"loss": 4.2236,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763033433069336e-05,
"loss": 4.2181,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375464748555881e-05,
"loss": 4.2213,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.208026885986328,
"eval_runtime": 297.3865,
"eval_samples_per_second": 1283.148,
"eval_steps_per_second": 40.099,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.374626153804829e-05,
"loss": 4.2087,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.373787559053777e-05,
"loss": 4.2043,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.372948964302725e-05,
"loss": 4.226,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.372110369551673e-05,
"loss": 4.2183,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.371271774800621e-05,
"loss": 4.2232,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.370433180049569e-05,
"loss": 4.2172,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.369594585298517e-05,
"loss": 4.2141,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368755990547465e-05,
"loss": 4.2069,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367917395796413e-05,
"loss": 4.2139,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.3670804389257345e-05,
"loss": 4.216,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.3662434820550554e-05,
"loss": 4.2227,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.3654048873040034e-05,
"loss": 4.2239,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.3645662925529514e-05,
"loss": 4.2083,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.3637276978018994e-05,
"loss": 4.2114,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.3628891030508474e-05,
"loss": 4.2096,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.3620505082997954e-05,
"loss": 4.1955,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.3612119135487434e-05,
"loss": 4.2126,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.360374956678064e-05,
"loss": 4.2076,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.359536361927012e-05,
"loss": 4.2038,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.35869776717596e-05,
"loss": 4.2225,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.357859172424908e-05,
"loss": 4.2143,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.357020577673856e-05,
"loss": 4.2105,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.356183620803178e-05,
"loss": 4.215,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.355345026052126e-05,
"loss": 4.2224,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.354506431301074e-05,
"loss": 4.1979,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.353667836550022e-05,
"loss": 4.2081,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.352830879679343e-05,
"loss": 4.2145,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.3519939228086636e-05,
"loss": 4.2049,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.3511553280576116e-05,
"loss": 4.1958,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.3503167333065596e-05,
"loss": 4.1975,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.3494781385555076e-05,
"loss": 4.2115,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.3486395438044556e-05,
"loss": 4.2127,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.3478009490534036e-05,
"loss": 4.2101,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.3469623543023516e-05,
"loss": 4.2137,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.346125397431673e-05,
"loss": 4.2073,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.345286802680621e-05,
"loss": 4.2062,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.344448207929569e-05,
"loss": 4.2001,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.3436096131785165e-05,
"loss": 4.2033,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.3427710184274645e-05,
"loss": 4.1916,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.3419324236764125e-05,
"loss": 4.1989,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.341097104686107e-05,
"loss": 4.2001,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.340258509935055e-05,
"loss": 4.213,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.339419915184003e-05,
"loss": 4.2014,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338581320432951e-05,
"loss": 4.2036,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337742725681899e-05,
"loss": 4.2062,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.336904130930847e-05,
"loss": 4.1986,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.336065536179795e-05,
"loss": 4.2105,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.335226941428743e-05,
"loss": 4.1933,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334388346677691e-05,
"loss": 4.1882,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.333549751926639e-05,
"loss": 4.2077,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.332711157175587e-05,
"loss": 4.2052,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.331872562424535e-05,
"loss": 4.1929,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331033967673483e-05,
"loss": 4.1935,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.330197010802804e-05,
"loss": 4.1992,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.329360053932125e-05,
"loss": 4.1814,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328521459181073e-05,
"loss": 4.2044,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.327682864430021e-05,
"loss": 4.1873,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326844269678969e-05,
"loss": 4.191,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.326005674927917e-05,
"loss": 4.2012,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.3251670801768654e-05,
"loss": 4.1913,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.3243284854258134e-05,
"loss": 4.1898,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.3234898906747614e-05,
"loss": 4.1896,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.3226512959237094e-05,
"loss": 4.1808,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.32181433905303e-05,
"loss": 4.1892,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.320977382182351e-05,
"loss": 4.1975,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.320138787431299e-05,
"loss": 4.1913,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.319300192680247e-05,
"loss": 4.1867,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.318461597929195e-05,
"loss": 4.1791,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.317623003178143e-05,
"loss": 4.1797,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.316784408427091e-05,
"loss": 4.1952,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.315945813676039e-05,
"loss": 4.2,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.315107218924987e-05,
"loss": 4.1923,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.314270262054309e-05,
"loss": 4.1964,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313431667303257e-05,
"loss": 4.2041,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.312593072552205e-05,
"loss": 4.2016,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311756115681526e-05,
"loss": 4.1757,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310917520930474e-05,
"loss": 4.1895,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310078926179422e-05,
"loss": 4.1941,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.30924033142837e-05,
"loss": 4.1783,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308401736677318e-05,
"loss": 4.1915,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.307563141926265e-05,
"loss": 4.1874,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.306724547175213e-05,
"loss": 4.1995,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.305885952424161e-05,
"loss": 4.1901,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.3050489955534826e-05,
"loss": 4.1716,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.3042104008024306e-05,
"loss": 4.1871,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.3033718060513786e-05,
"loss": 4.1868,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.3025332113003266e-05,
"loss": 4.1932,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.3016962544296475e-05,
"loss": 4.1869,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.300859297558969e-05,
"loss": 4.1896,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.300020702807917e-05,
"loss": 4.1881,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.299182108056865e-05,
"loss": 4.1805,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.2983435133058124e-05,
"loss": 4.1741,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.2975049185547604e-05,
"loss": 4.1799,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.2966663238037084e-05,
"loss": 4.1913,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.2958277290526564e-05,
"loss": 4.1849,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.2949891343016043e-05,
"loss": 4.1874,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294152177430926e-05,
"loss": 4.1736,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293313582679874e-05,
"loss": 4.1846,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.292474987928822e-05,
"loss": 4.192,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.29163639317777e-05,
"loss": 4.1913,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.290799436307091e-05,
"loss": 4.1801,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.289960841556039e-05,
"loss": 4.1786,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289122246804987e-05,
"loss": 4.1765,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288283652053935e-05,
"loss": 4.1878,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.287445057302883e-05,
"loss": 4.1584,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286608100432204e-05,
"loss": 4.1796,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.285769505681152e-05,
"loss": 4.1722,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.2849309109301e-05,
"loss": 4.1847,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284092316179048e-05,
"loss": 4.1678,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.2832537214279964e-05,
"loss": 4.1894,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.282416764557317e-05,
"loss": 4.1743,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281578169806265e-05,
"loss": 4.1821,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.280739575055213e-05,
"loss": 4.174,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.279900980304161e-05,
"loss": 4.1672,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.279064023433482e-05,
"loss": 4.1837,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.27822542868243e-05,
"loss": 4.1896,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.277388471811751e-05,
"loss": 4.1838,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.276549877060699e-05,
"loss": 4.1706,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.275711282309647e-05,
"loss": 4.1762,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.274872687558595e-05,
"loss": 4.1827,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.274034092807543e-05,
"loss": 4.1691,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273195498056492e-05,
"loss": 4.1802,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.27235690330544e-05,
"loss": 4.1668,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.2715199464347607e-05,
"loss": 4.1755,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.2706813516837087e-05,
"loss": 4.1767,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.2698427569326566e-05,
"loss": 4.1767,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.2690041621816046e-05,
"loss": 4.1539,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.2681672053109256e-05,
"loss": 4.1771,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.2673286105598735e-05,
"loss": 4.168,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.2664900158088215e-05,
"loss": 4.1836,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.2656514210577695e-05,
"loss": 4.1787,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.2648128263067175e-05,
"loss": 4.1802,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.2639742315556655e-05,
"loss": 4.1624,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.2631356368046135e-05,
"loss": 4.1831,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.2622970420535615e-05,
"loss": 4.1804,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.2614584473025095e-05,
"loss": 4.1795,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.2606198525514575e-05,
"loss": 4.171,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.2597812578004055e-05,
"loss": 4.1797,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.2589443009297264e-05,
"loss": 4.1808,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.2581057061786744e-05,
"loss": 4.184,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.2572671114276224e-05,
"loss": 4.1632,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.2564285166765704e-05,
"loss": 4.1768,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.2555899219255184e-05,
"loss": 4.1731,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.2547513271744664e-05,
"loss": 4.1637,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253914370303787e-05,
"loss": 4.1776,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253075775552735e-05,
"loss": 4.1726,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252237180801684e-05,
"loss": 4.1796,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251398586050632e-05,
"loss": 4.1651,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.25055999129958e-05,
"loss": 4.1709,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 4.1663994789123535,
"eval_runtime": 301.3955,
"eval_samples_per_second": 1266.081,
"eval_steps_per_second": 39.566,
"step": 457920
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.8870293561330477e+17,
"trial_name": null,
"trial_params": null
}