abhinavp's picture
Training in progress, epoch 1, checkpoint
b120629 verified
raw
history blame
No virus
37.5 kB
{
"best_metric": 4.51077938079834,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/lstm/4/checkpoints/checkpoint-152640",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 152640,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.999998362119627e-05,
"loss": 10.8207,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5526,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0612,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9978,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9523,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.9164,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7353,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6349,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993292879871958e-05,
"loss": 6.5372,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992454285120906e-05,
"loss": 6.4491,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.991615690369854e-05,
"loss": 6.389,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990777095618801e-05,
"loss": 6.3339,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 6.2708,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 6.2072,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 6.159,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 6.1045,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 6.0613,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 6.0227,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.986,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9484,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.9142,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8747,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8528,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.8107,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.793,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 5.7615,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 5.7385,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 5.7165,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6853,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6601,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 5.6473,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 5.6355,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 5.6129,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5888,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 5.5844,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 5.5564,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5426,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.5091,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.5112,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 5.4898,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966467675120532e-05,
"loss": 5.4805,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.96562908036948e-05,
"loss": 5.4686,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964790485618428e-05,
"loss": 5.4613,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 5.4309,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 5.4245,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 5.4194,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 5.4028,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960597511863168e-05,
"loss": 5.4054,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 5.3842,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 5.3631,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958083365490385e-05,
"loss": 5.3727,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957244770739333e-05,
"loss": 5.3514,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 5.3465,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 5.3189,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 5.3297,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 5.3066,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 5.3341,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 5.2953,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 5.2958,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 5.2888,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949700693740611e-05,
"loss": 5.2691,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 5.2564,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 5.2567,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 5.2384,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 5.2349,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2508,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 5.232,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 5.2178,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 5.195,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942156616741889e-05,
"loss": 5.1929,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 5.2004,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1974,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 5.189,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 5.1869,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 5.1788,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 5.1709,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 5.1581,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 5.1483,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 5.1428,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 5.1312,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 5.1383,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 5.1284,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 5.1309,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930422841748654e-05,
"loss": 5.1123,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929584246997602e-05,
"loss": 5.0928,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 5.1066,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 5.1026,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 5.1002,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 5.0864,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 5.0878,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 5.0741,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 5.0695,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 5.0666,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 5.0613,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 5.0657,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.059,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 5.0564,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 5.0342,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 5.0306,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 5.029,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 5.0287,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 5.0209,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 5.0135,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 5.0041,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 5.0116,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.9868,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9936,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9901,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.90946616237422e-05,
"loss": 4.9818,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908627567623168e-05,
"loss": 4.9765,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.9817,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.9692,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.971,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.9626,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.9535,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.9588,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.9556,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.9494,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.9361,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.9426,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.9439,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.9322,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.9193,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.9288,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.9278,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.9157,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.9097,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.8988,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.892700818874671e-05,
"loss": 4.9044,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.891862224123619e-05,
"loss": 4.8949,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.891023629372567e-05,
"loss": 4.9094,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.8986,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.8797,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888509482999785e-05,
"loss": 4.8879,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887670888248733e-05,
"loss": 4.8857,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886832293497681e-05,
"loss": 4.8811,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885993698746629e-05,
"loss": 4.8845,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885155103995577e-05,
"loss": 4.8712,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884318147124898e-05,
"loss": 4.873,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883479552373846e-05,
"loss": 4.8796,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882640957622794e-05,
"loss": 4.8623,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881802362871742e-05,
"loss": 4.8601,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.88096376812069e-05,
"loss": 4.8617,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880125173369638e-05,
"loss": 4.8468,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.8461,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.8518,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.8371,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.8392,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.8462,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.8393,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.799422264099121,
"eval_runtime": 295.7715,
"eval_samples_per_second": 1290.155,
"eval_steps_per_second": 40.318,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.87425828587302e-05,
"loss": 4.8219,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.873419691121968e-05,
"loss": 4.8218,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.872584372131662e-05,
"loss": 4.8371,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.87174577738061e-05,
"loss": 4.8213,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.870907182629558e-05,
"loss": 4.832,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.870068587878506e-05,
"loss": 4.8041,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.869229993127454e-05,
"loss": 4.8236,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683913983764027e-05,
"loss": 4.8059,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.8675528036253507e-05,
"loss": 4.8006,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.8667142088742986e-05,
"loss": 4.8069,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865875614123246e-05,
"loss": 4.8087,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865037019372194e-05,
"loss": 4.8094,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.8642000625015155e-05,
"loss": 4.7923,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.8633614677504635e-05,
"loss": 4.791,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862522872999411e-05,
"loss": 4.783,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861684278248359e-05,
"loss": 4.7842,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.7828,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860008726626628e-05,
"loss": 4.7821,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.8591701318755764e-05,
"loss": 4.7787,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.8583315371245244e-05,
"loss": 4.7981,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574929423734724e-05,
"loss": 4.7739,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.7823,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.7685,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.7764,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.7643,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.764,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.7594,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.7562,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.7383,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.7541,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849110270623698e-05,
"loss": 4.7518,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848271675872646e-05,
"loss": 4.7549,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847433081121595e-05,
"loss": 4.7442,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846594486370543e-05,
"loss": 4.7474,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.7392,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.7355,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.7197,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.7267,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842404788376029e-05,
"loss": 4.7266,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841566193624977e-05,
"loss": 4.7228,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840727598873925e-05,
"loss": 4.7273,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839889004122873e-05,
"loss": 4.7262,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839050409371821e-05,
"loss": 4.7139,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.8382118146207687e-05,
"loss": 4.72,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.7204,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365346251186646e-05,
"loss": 4.7064,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8356960303676126e-05,
"loss": 4.7187,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.8348574356165606e-05,
"loss": 4.7039,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.6918,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.7119,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323432892437775e-05,
"loss": 4.6953,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315046944927255e-05,
"loss": 4.6944,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306660997416735e-05,
"loss": 4.6834,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.6934,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.6804,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281519533688904e-05,
"loss": 4.7121,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273133586178384e-05,
"loss": 4.6815,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826474763866787e-05,
"loss": 4.6921,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.6893,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824799212245056e-05,
"loss": 4.6755,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823960617494004e-05,
"loss": 4.6665,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823122022742952e-05,
"loss": 4.6787,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222834279919e-05,
"loss": 4.6655,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.6638,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.6798,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819769281619117e-05,
"loss": 4.6746,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818930686868065e-05,
"loss": 4.6598,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.818092092117013e-05,
"loss": 4.6541,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817253497365961e-05,
"loss": 4.6529,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816414902614909e-05,
"loss": 4.6649,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155779457442305e-05,
"loss": 4.6638,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147393509931785e-05,
"loss": 4.662,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.6623,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.662,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122252046203954e-05,
"loss": 4.6613,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113866098693434e-05,
"loss": 4.6441,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105480151182914e-05,
"loss": 4.6484,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.8097094203672393e-05,
"loss": 4.6472,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.80887246349656e-05,
"loss": 4.6311,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808033868745508e-05,
"loss": 4.6473,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.807196911874829e-05,
"loss": 4.6442,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.806358317123777e-05,
"loss": 4.6475,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.805519722372726e-05,
"loss": 4.6287,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804681127621674e-05,
"loss": 4.6191,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803842532870622e-05,
"loss": 4.6375,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.80300393811957e-05,
"loss": 4.6317,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802165343368518e-05,
"loss": 4.6388,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801326748617466e-05,
"loss": 4.6295,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.800489791746787e-05,
"loss": 4.632,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799651196995735e-05,
"loss": 4.626,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798812602244683e-05,
"loss": 4.6175,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.79797400749363e-05,
"loss": 4.6234,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.6214,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.7962984558718996e-05,
"loss": 4.628,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.7954598611208476e-05,
"loss": 4.6271,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.7946212663697956e-05,
"loss": 4.6239,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.7937826716187436e-05,
"loss": 4.6118,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792947352628438e-05,
"loss": 4.6111,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792108757877386e-05,
"loss": 4.6092,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791270163126334e-05,
"loss": 4.6179,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790433206255655e-05,
"loss": 4.6047,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.789594611504603e-05,
"loss": 4.604,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.788756016753551e-05,
"loss": 4.5983,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.787917422002499e-05,
"loss": 4.6117,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.787078827251447e-05,
"loss": 4.5861,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786240232500395e-05,
"loss": 4.5974,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.785401637749343e-05,
"loss": 4.6002,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.784563042998291e-05,
"loss": 4.592,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.783724448247239e-05,
"loss": 4.5896,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782885853496187e-05,
"loss": 4.6012,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782047258745135e-05,
"loss": 4.5868,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781208663994083e-05,
"loss": 4.5885,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780370069243031e-05,
"loss": 4.595,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779531474491979e-05,
"loss": 4.5808,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778692879740927e-05,
"loss": 4.5913,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777854284989875e-05,
"loss": 4.5959,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777017328119196e-05,
"loss": 4.5871,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776178733368144e-05,
"loss": 4.5757,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775340138617092e-05,
"loss": 4.5863,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.7745031817464134e-05,
"loss": 4.5848,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.7736645869953614e-05,
"loss": 4.575,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.7728259922443094e-05,
"loss": 4.5728,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.7719873974932574e-05,
"loss": 4.5759,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771150440622578e-05,
"loss": 4.5863,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770311845871526e-05,
"loss": 4.5743,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769473251120474e-05,
"loss": 4.5702,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768634656369422e-05,
"loss": 4.5606,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767797699498743e-05,
"loss": 4.5676,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766960742628064e-05,
"loss": 4.5603,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766122147877012e-05,
"loss": 4.5779,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.76528355312596e-05,
"loss": 4.5716,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764444958374909e-05,
"loss": 4.5538,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763606363623857e-05,
"loss": 4.5601,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762767768872805e-05,
"loss": 4.5664,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761929174121753e-05,
"loss": 4.5628,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761090579370701e-05,
"loss": 4.5687,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760251984619649e-05,
"loss": 4.5555,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941502774897e-05,
"loss": 4.5572,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758576432997918e-05,
"loss": 4.5652,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757737838246866e-05,
"loss": 4.5521,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.7568992434958137e-05,
"loss": 4.5536,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756060648744761e-05,
"loss": 4.5588,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755222053993709e-05,
"loss": 4.5431,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.7543850971230306e-05,
"loss": 4.5473,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.7535465023719786e-05,
"loss": 4.554,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.7527079076209266e-05,
"loss": 4.5381,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518693128698745e-05,
"loss": 4.5445,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510307181188225e-05,
"loss": 4.5499,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501921233677705e-05,
"loss": 4.545,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.51077938079834,
"eval_runtime": 296.1256,
"eval_samples_per_second": 1288.612,
"eval_steps_per_second": 40.27,
"step": 152640
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 6.271938011867256e+16,
"trial_name": null,
"trial_params": null
}