abhinavp's picture
Training in progress, epoch 1, checkpoint
a342e3e verified
raw
history blame
37.5 kB
{
"best_metric": 4.477574825286865,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-case/lstm/2/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": 10.8202,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5553,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0623,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9941,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9472,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.9029,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7368,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6252,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5249,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.4532,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.3903,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3296,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2678,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.2035,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1464,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0874,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0408,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 5.9952,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9558,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984066699730012e-05,
"loss": 5.9191,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8856,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8505,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8194,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.7915,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7743,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7353,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7141,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6887,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6688,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6429,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6182,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.6126,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5839,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.5749,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714926921053515e-05,
"loss": 5.5602,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706540973542995e-05,
"loss": 5.5357,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5246,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4853,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4867,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4507,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4514,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 5.4323,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 5.4321,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963950252987002e-05,
"loss": 5.4055,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.3987,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 5.3903,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 5.3724,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.3771,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959758917112116e-05,
"loss": 5.3481,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3317,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 5.3419,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 5.336,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956406175988281e-05,
"loss": 5.3088,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2988,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.2973,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2805,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.295,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2557,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 5.2554,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 5.248,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 5.236,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 5.2383,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2159,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.2093,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 5.2024,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2154,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.1879,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1856,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 5.1594,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 5.167,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 5.1745,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1674,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.1439,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 5.1575,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 5.1534,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 5.1289,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 5.1265,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 5.1098,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 5.0966,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 5.0944,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 5.0978,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 5.0972,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.103,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 5.0877,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 5.0679,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 5.0684,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 5.0691,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 5.0567,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 5.049,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 5.0376,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 5.0369,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 5.039,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 5.0247,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 5.0286,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 5.015,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 5.0109,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.9984,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.996,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.9887,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.9917,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.9933,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.9709,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.9769,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.9642,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.9613,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.9545,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.9482,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.9476,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.9395,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.9365,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.9292,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9193,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.9308,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.9186,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.9197,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.9151,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.916,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.9066,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.8912,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.9003,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.9049,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.8902,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.883,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.8822,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.8787,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.8699,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.8723,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935377757453504e-05,
"loss": 4.8611,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.8637,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.8533,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.871,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.8541,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.8452,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.8415,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.8438,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.8436,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.8439,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.8322,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.833,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.8285,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.8268,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.8145,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.8258,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.8122,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.8792882164989586e-05,
"loss": 4.7994,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878449621747907e-05,
"loss": 4.813,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877611026996855e-05,
"loss": 4.8029,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.8033,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.8089,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.7896,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.756977081298828,
"eval_runtime": 297.0801,
"eval_samples_per_second": 1284.472,
"eval_steps_per_second": 40.141,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.7824,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.785,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872581096370916e-05,
"loss": 4.7887,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.871744139500237e-05,
"loss": 4.7825,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870905544749185e-05,
"loss": 4.7872,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870066949998133e-05,
"loss": 4.7708,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869228355247081e-05,
"loss": 4.7773,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.868389760496029e-05,
"loss": 4.7645,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.773,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.7612,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.7583,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.7589,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642000625015155e-05,
"loss": 4.753,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.7484,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.7442,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.7312,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.7409,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.735,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.7282,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.7471,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.7299,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.733,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.7264,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.7431,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.854140201249637e-05,
"loss": 4.7129,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.853301606498585e-05,
"loss": 4.7131,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.852463011747533e-05,
"loss": 4.7177,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851624416996481e-05,
"loss": 4.7192,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.7046,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.7045,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.7123,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.7097,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.711,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.7071,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.6983,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.7047,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.6755,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.6972,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.6709,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.6846,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840725960993552e-05,
"loss": 4.6764,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398873662425e-05,
"loss": 4.6888,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839048771491447e-05,
"loss": 4.6775,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838210176740395e-05,
"loss": 4.6735,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.6763,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365346251186646e-05,
"loss": 4.6684,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8356960303676126e-05,
"loss": 4.682,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.8348574356165606e-05,
"loss": 4.6582,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.6516,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.6727,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.6695,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315046944927255e-05,
"loss": 4.6538,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306660997416735e-05,
"loss": 4.6483,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.656,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289905481199424e-05,
"loss": 4.6427,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281519533688904e-05,
"loss": 4.6653,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273133586178384e-05,
"loss": 4.6398,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826474763866787e-05,
"loss": 4.6462,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.6412,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824797574364683e-05,
"loss": 4.634,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823960617494004e-05,
"loss": 4.6454,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823122022742952e-05,
"loss": 4.6314,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222834279919e-05,
"loss": 4.6268,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.6282,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.6439,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.6249,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.6211,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.6151,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817255135246334e-05,
"loss": 4.618,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816416540495282e-05,
"loss": 4.6373,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155779457442305e-05,
"loss": 4.6324,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147393509931785e-05,
"loss": 4.6143,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.6287,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.632,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122252046203954e-05,
"loss": 4.6175,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113866098693434e-05,
"loss": 4.6175,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.6072,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097094203672393e-05,
"loss": 4.5947,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.8088708256161873e-05,
"loss": 4.5987,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.6039,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.6066,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.6237,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805518084492352e-05,
"loss": 4.609,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804681127621674e-05,
"loss": 4.59,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803842532870622e-05,
"loss": 4.5987,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.80300393811957e-05,
"loss": 4.6011,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802165343368518e-05,
"loss": 4.5985,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.5894,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800488153866413e-05,
"loss": 4.5868,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799651196995735e-05,
"loss": 4.5881,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798812602244683e-05,
"loss": 4.5923,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.79797400749363e-05,
"loss": 4.5833,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.5894,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7963000937522725e-05,
"loss": 4.5841,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795461499001221e-05,
"loss": 4.582,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794622904250169e-05,
"loss": 4.5716,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793784309499117e-05,
"loss": 4.5778,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792945714748065e-05,
"loss": 4.5731,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792107119997013e-05,
"loss": 4.5754,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.7912685252459605e-05,
"loss": 4.5787,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.7904299304949085e-05,
"loss": 4.5653,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895913357438565e-05,
"loss": 4.5691,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887527409928045e-05,
"loss": 4.5652,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879141462417525e-05,
"loss": 4.5641,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870755514907005e-05,
"loss": 4.5573,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786240232500395e-05,
"loss": 4.5585,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785401637749343e-05,
"loss": 4.5627,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784563042998291e-05,
"loss": 4.5528,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783724448247239e-05,
"loss": 4.5567,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782885853496187e-05,
"loss": 4.5498,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782047258745135e-05,
"loss": 4.5415,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781208663994083e-05,
"loss": 4.5631,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780370069243031e-05,
"loss": 4.5487,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779533112372352e-05,
"loss": 4.5546,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786945176213e-05,
"loss": 4.549,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777855922870248e-05,
"loss": 4.5603,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777017328119196e-05,
"loss": 4.5498,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776178733368144e-05,
"loss": 4.5354,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775340138617092e-05,
"loss": 4.548,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.77450154386604e-05,
"loss": 4.5517,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773666224875734e-05,
"loss": 4.5378,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772829268005055e-05,
"loss": 4.5408,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771990673254003e-05,
"loss": 4.5351,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771152078502951e-05,
"loss": 4.5433,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770313483751899e-05,
"loss": 4.5304,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769474889000847e-05,
"loss": 4.5364,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768636294249795e-05,
"loss": 4.5291,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767797699498743e-05,
"loss": 4.5349,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766959104747691e-05,
"loss": 4.5229,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766120509996639e-05,
"loss": 4.5462,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765281915245587e-05,
"loss": 4.5354,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764443320494535e-05,
"loss": 4.5208,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763606363623857e-05,
"loss": 4.5247,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762767768872805e-05,
"loss": 4.5259,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761929174121753e-05,
"loss": 4.5286,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761090579370701e-05,
"loss": 4.5371,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760253622500022e-05,
"loss": 4.5188,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941502774897e-05,
"loss": 4.5247,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.7585780708782906e-05,
"loss": 4.5206,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.7577394761272386e-05,
"loss": 4.5246,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7569008813761866e-05,
"loss": 4.5155,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.7560622866251346e-05,
"loss": 4.524,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.7552236918740826e-05,
"loss": 4.5126,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543850971230306e-05,
"loss": 4.5083,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535465023719786e-05,
"loss": 4.5211,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527079076209266e-05,
"loss": 4.5121,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518693128698745e-05,
"loss": 4.513,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751032355999196e-05,
"loss": 4.5134,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501937612481435e-05,
"loss": 4.5056,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.477574825286865,
"eval_runtime": 297.0621,
"eval_samples_per_second": 1284.549,
"eval_steps_per_second": 40.143,
"step": 152640
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 6.262592319085234e+16,
"trial_name": null,
"trial_params": null
}