abhinavp's picture
Training in progress, epoch 1, checkpoint
0a47711 verified
raw
history blame
No virus
74.6 kB
{
"best_metric": 4.287594318389893,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/lstm/4/checkpoints/checkpoint-305280",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 305280,
"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
},
{
"epoch": 0.0,
"learning_rate": 4.7493535286167185e-05,
"loss": 4.5317,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485149338656665e-05,
"loss": 4.5335,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476763391146145e-05,
"loss": 4.5516,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468377443635625e-05,
"loss": 4.5319,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7459991496125105e-05,
"loss": 4.5478,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451605548614585e-05,
"loss": 4.5273,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443219601104065e-05,
"loss": 4.5422,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434833653593545e-05,
"loss": 4.5257,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426447706083025e-05,
"loss": 4.5349,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418061758572505e-05,
"loss": 4.5307,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409675811061985e-05,
"loss": 4.5336,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401289863551465e-05,
"loss": 4.5395,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739292029484468e-05,
"loss": 4.5194,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384534347334154e-05,
"loss": 4.5241,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376148399823634e-05,
"loss": 4.5182,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367762452313114e-05,
"loss": 4.5163,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359376504802594e-05,
"loss": 4.5198,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350990557292074e-05,
"loss": 4.5236,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342604609781554e-05,
"loss": 4.5175,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.7334218662271034e-05,
"loss": 4.5393,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325832714760514e-05,
"loss": 4.5188,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731746314605372e-05,
"loss": 4.5246,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73090771985432e-05,
"loss": 4.5168,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730069125103269e-05,
"loss": 4.5255,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729230530352217e-05,
"loss": 4.516,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728391935601165e-05,
"loss": 4.5102,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727553340850113e-05,
"loss": 4.5144,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726714746099061e-05,
"loss": 4.5079,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725876151348009e-05,
"loss": 4.492,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.72503919447733e-05,
"loss": 4.5085,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724200599726278e-05,
"loss": 4.5147,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723362004975226e-05,
"loss": 4.5094,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722523410224174e-05,
"loss": 4.5059,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721686453353495e-05,
"loss": 4.5083,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208494964828156e-05,
"loss": 4.502,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720010901731764e-05,
"loss": 4.4971,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719172306980712e-05,
"loss": 4.4914,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71833371222966e-05,
"loss": 4.491,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717495117478608e-05,
"loss": 4.4923,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716658160607929e-05,
"loss": 4.4927,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715819565856877e-05,
"loss": 4.5006,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714980971105825e-05,
"loss": 4.4996,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714142376354773e-05,
"loss": 4.4878,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713303781603721e-05,
"loss": 4.4938,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124651868526685e-05,
"loss": 4.4986,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116265921016165e-05,
"loss": 4.481,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107879973505645e-05,
"loss": 4.4947,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709951040479886e-05,
"loss": 4.4869,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709112445728834e-05,
"loss": 4.4691,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708273850977782e-05,
"loss": 4.4891,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074368941071037e-05,
"loss": 4.4825,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7065982993560517e-05,
"loss": 4.4762,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705759704604999e-05,
"loss": 4.4726,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704921109853947e-05,
"loss": 4.4774,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040841529832686e-05,
"loss": 4.4642,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703245558232216e-05,
"loss": 4.493,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702406963481164e-05,
"loss": 4.4736,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701568368730112e-05,
"loss": 4.4812,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.70072977397906e-05,
"loss": 4.4824,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699891179228008e-05,
"loss": 4.4666,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699052584476956e-05,
"loss": 4.459,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982139897259045e-05,
"loss": 4.4757,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.6973753949748525e-05,
"loss": 4.4626,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965384381041734e-05,
"loss": 4.4569,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956998433531214e-05,
"loss": 4.4763,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.6948612486020694e-05,
"loss": 4.4744,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.6940226538510174e-05,
"loss": 4.4593,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931840590999654e-05,
"loss": 4.4525,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.6923454643489134e-05,
"loss": 4.4538,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915068695978614e-05,
"loss": 4.464,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.6906682748468094e-05,
"loss": 4.4673,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.68983131797613e-05,
"loss": 4.4641,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688992723225078e-05,
"loss": 4.4672,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688154128474026e-05,
"loss": 4.4666,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687315533722974e-05,
"loss": 4.4672,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686480214732669e-05,
"loss": 4.4526,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685641619981617e-05,
"loss": 4.4574,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684803025230565e-05,
"loss": 4.46,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683964430479513e-05,
"loss": 4.4398,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683127473608834e-05,
"loss": 4.4563,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682288878857782e-05,
"loss": 4.4604,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.68145028410673e-05,
"loss": 4.4588,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680611689355678e-05,
"loss": 4.4444,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679773094604626e-05,
"loss": 4.4319,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789361377339466e-05,
"loss": 4.4518,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678097542982895e-05,
"loss": 4.4431,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677258948231843e-05,
"loss": 4.459,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676420353480791e-05,
"loss": 4.4469,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675583396610112e-05,
"loss": 4.4511,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.67474480185906e-05,
"loss": 4.4466,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673906207108008e-05,
"loss": 4.4341,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673067612356956e-05,
"loss": 4.4437,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672229017605904e-05,
"loss": 4.4402,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671390422854852e-05,
"loss": 4.4522,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705518281037995e-05,
"loss": 4.4542,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697132333527474e-05,
"loss": 4.4461,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668877914362442e-05,
"loss": 4.4318,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680393196113906e-05,
"loss": 4.4381,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6672007248603386e-05,
"loss": 4.4364,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663621301092866e-05,
"loss": 4.4444,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655235353582346e-05,
"loss": 4.4318,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664684940607182e-05,
"loss": 4.4352,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.66384634585613e-05,
"loss": 4.4249,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663007751105078e-05,
"loss": 4.4439,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621707942343995e-05,
"loss": 4.4166,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661332199483347e-05,
"loss": 4.4321,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6604952426126684e-05,
"loss": 4.4229,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596566478616164e-05,
"loss": 4.4278,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588180531105644e-05,
"loss": 4.4241,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579794583595124e-05,
"loss": 4.4338,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571408636084604e-05,
"loss": 4.4272,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6563022688574084e-05,
"loss": 4.4203,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554636741063564e-05,
"loss": 4.43,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654626717235677e-05,
"loss": 4.4137,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653788122484625e-05,
"loss": 4.4331,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652949527733573e-05,
"loss": 4.4359,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652110932982521e-05,
"loss": 4.4217,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.651272338231469e-05,
"loss": 4.418,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650433743480417e-05,
"loss": 4.4215,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649595148729365e-05,
"loss": 4.4238,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648756553978313e-05,
"loss": 4.4157,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647919597107634e-05,
"loss": 4.4147,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647081002356582e-05,
"loss": 4.4135,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646242407605531e-05,
"loss": 4.4294,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645403812854479e-05,
"loss": 4.4187,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.6445668559838e-05,
"loss": 4.4136,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.643728261232748e-05,
"loss": 4.4039,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.6428913043620687e-05,
"loss": 4.4146,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.6420527096110166e-05,
"loss": 4.4041,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.6412141148599646e-05,
"loss": 4.4242,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403755201089126e-05,
"loss": 4.4192,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395369253578606e-05,
"loss": 4.4064,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6386983306068086e-05,
"loss": 4.4034,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378597358557566e-05,
"loss": 4.4133,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370227789850775e-05,
"loss": 4.4097,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636184184234026e-05,
"loss": 4.4212,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635345589482974e-05,
"loss": 4.4026,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634506994731922e-05,
"loss": 4.4128,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.63366839998087e-05,
"loss": 4.4107,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632829805229818e-05,
"loss": 4.4083,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6319912104787655e-05,
"loss": 4.4065,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311526157277135e-05,
"loss": 4.4099,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630315658857035e-05,
"loss": 4.396,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629477064105983e-05,
"loss": 4.4043,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.6286384693549304e-05,
"loss": 4.4064,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277998746038784e-05,
"loss": 4.3988,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.6269629177332e-05,
"loss": 4.3956,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626124322982148e-05,
"loss": 4.4035,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625285728231096e-05,
"loss": 4.4018,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.373067855834961,
"eval_runtime": 292.1016,
"eval_samples_per_second": 1306.364,
"eval_steps_per_second": 40.825,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624447133480044e-05,
"loss": 4.3954,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623608538728992e-05,
"loss": 4.3865,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.62276994397794e-05,
"loss": 4.4115,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621932987107261e-05,
"loss": 4.3908,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.621094392356209e-05,
"loss": 4.4104,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.620255797605157e-05,
"loss": 4.3828,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.619417202854105e-05,
"loss": 4.4047,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185818838637994e-05,
"loss": 4.3897,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177432891127474e-05,
"loss": 4.3931,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.616906332242068e-05,
"loss": 4.3933,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.616067737491017e-05,
"loss": 4.3947,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615229142739965e-05,
"loss": 4.4016,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614392185869286e-05,
"loss": 4.3859,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613553591118234e-05,
"loss": 4.3842,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612714996367182e-05,
"loss": 4.3895,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.61187640161613e-05,
"loss": 4.3743,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611037806865078e-05,
"loss": 4.3866,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610199212114025e-05,
"loss": 4.3878,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609360617362973e-05,
"loss": 4.3805,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608522022611921e-05,
"loss": 4.4037,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607683427860869e-05,
"loss": 4.39,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606844833109817e-05,
"loss": 4.3946,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606006238358765e-05,
"loss": 4.3838,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605167643607714e-05,
"loss": 4.39,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604329048856662e-05,
"loss": 4.3832,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603492091985983e-05,
"loss": 4.3807,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602653497234931e-05,
"loss": 4.3842,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601814902483879e-05,
"loss": 4.3734,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.600976307732827e-05,
"loss": 4.3701,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600137712981775e-05,
"loss": 4.3734,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599299118230723e-05,
"loss": 4.3849,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598460523479671e-05,
"loss": 4.3831,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597621928728619e-05,
"loss": 4.3803,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.5967849718579396e-05,
"loss": 4.3835,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.5959480149872605e-05,
"loss": 4.3671,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595109420236209e-05,
"loss": 4.3727,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594270825485157e-05,
"loss": 4.3707,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593432230734105e-05,
"loss": 4.3607,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.592593635983053e-05,
"loss": 4.3674,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591755041232001e-05,
"loss": 4.3639,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590916446480949e-05,
"loss": 4.3763,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.59007948961027e-05,
"loss": 4.3753,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589240894859218e-05,
"loss": 4.3667,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588402300108166e-05,
"loss": 4.3648,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587563705357114e-05,
"loss": 4.3778,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867251106060614e-05,
"loss": 4.3575,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858865158550094e-05,
"loss": 4.3723,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.5850479211039573e-05,
"loss": 4.3639,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.5842093263529053e-05,
"loss": 4.3481,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583370731601854e-05,
"loss": 4.371,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582532136850802e-05,
"loss": 4.3605,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.581695179980123e-05,
"loss": 4.3595,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.580856585229071e-05,
"loss": 4.3477,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.580017990478019e-05,
"loss": 4.3573,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.579179395726967e-05,
"loss": 4.3479,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.578340800975915e-05,
"loss": 4.3675,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.577503844105236e-05,
"loss": 4.3558,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.576665249354184e-05,
"loss": 4.3603,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.575826654603132e-05,
"loss": 4.3636,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.57498805985208e-05,
"loss": 4.3508,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.574149465101028e-05,
"loss": 4.3396,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.573310870349976e-05,
"loss": 4.3617,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572472275598924e-05,
"loss": 4.3456,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716336808478725e-05,
"loss": 4.3419,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570798361857566e-05,
"loss": 4.3597,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569959767106514e-05,
"loss": 4.3565,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569121172355462e-05,
"loss": 4.3449,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.56828257760441e-05,
"loss": 4.3424,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567443982853358e-05,
"loss": 4.3347,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566605388102306e-05,
"loss": 4.346,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565768431231627e-05,
"loss": 4.3558,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564929836480575e-05,
"loss": 4.3556,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564091241729523e-05,
"loss": 4.3523,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563252646978471e-05,
"loss": 4.349,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562414052227419e-05,
"loss": 4.3614,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561575457476368e-05,
"loss": 4.3392,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560736862725315e-05,
"loss": 4.3488,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559898267974263e-05,
"loss": 4.3458,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.5590629489839576e-05,
"loss": 4.3257,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.5582243542329056e-05,
"loss": 4.3517,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.5573857594818536e-05,
"loss": 4.3484,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.5565471647308016e-05,
"loss": 4.3457,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.5557085699797496e-05,
"loss": 4.3369,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.5548716131090705e-05,
"loss": 4.3264,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.5540330183580185e-05,
"loss": 4.3413,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.5531944236069665e-05,
"loss": 4.3394,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523558288559145e-05,
"loss": 4.3455,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551518871985236e-05,
"loss": 4.3356,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550680277234184e-05,
"loss": 4.3471,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549841682483132e-05,
"loss": 4.3318,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.54900308773208e-05,
"loss": 4.3323,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.5481644929810274e-05,
"loss": 4.3328,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.5473258982299754e-05,
"loss": 4.3296,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546488941359297e-05,
"loss": 4.3484,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545650346608244e-05,
"loss": 4.3443,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544811751857192e-05,
"loss": 4.3456,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.54397315710614e-05,
"loss": 4.3248,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543134562355088e-05,
"loss": 4.3328,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542295967604037e-05,
"loss": 4.3329,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541459010733358e-05,
"loss": 4.3374,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540620415982306e-05,
"loss": 4.329,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539781821231254e-05,
"loss": 4.3271,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538943226480202e-05,
"loss": 4.3202,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.53810463172915e-05,
"loss": 4.341,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.537266036978098e-05,
"loss": 4.312,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.536427442227046e-05,
"loss": 4.3272,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.535590485356367e-05,
"loss": 4.3229,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.534751890605315e-05,
"loss": 4.3255,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533913295854263e-05,
"loss": 4.3215,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533074701103211e-05,
"loss": 4.3354,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532236106352159e-05,
"loss": 4.3241,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531397511601107e-05,
"loss": 4.3164,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530558916850055e-05,
"loss": 4.3315,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297203220990034e-05,
"loss": 4.3158,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528883365228324e-05,
"loss": 4.3296,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528044770477272e-05,
"loss": 4.3363,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.52720617572622e-05,
"loss": 4.3247,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526369218855541e-05,
"loss": 4.3186,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525530624104489e-05,
"loss": 4.3181,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524692029353437e-05,
"loss": 4.3229,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523853434602385e-05,
"loss": 4.3191,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523016477731706e-05,
"loss": 4.3223,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522177882980654e-05,
"loss": 4.3097,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521339288229602e-05,
"loss": 4.3295,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.52050069347855e-05,
"loss": 4.3243,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519662098727499e-05,
"loss": 4.3187,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518823503976446e-05,
"loss": 4.3035,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517986547105768e-05,
"loss": 4.3192,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517147952354716e-05,
"loss": 4.3091,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516309357603663e-05,
"loss": 4.323,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515470762852611e-05,
"loss": 4.3271,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514632168101559e-05,
"loss": 4.316,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513793573350507e-05,
"loss": 4.2994,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512954978599455e-05,
"loss": 4.3174,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.512118021728776e-05,
"loss": 4.3128,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511279426977724e-05,
"loss": 4.3282,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104408322266726e-05,
"loss": 4.305,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5096022374756206e-05,
"loss": 4.3181,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087636427245685e-05,
"loss": 4.3173,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079266858538895e-05,
"loss": 4.3189,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070880911028375e-05,
"loss": 4.3126,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062494963517855e-05,
"loss": 4.3143,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.5054109016007334e-05,
"loss": 4.3022,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.5045723068496814e-05,
"loss": 4.3137,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.5037337120986294e-05,
"loss": 4.3108,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.5028951173475774e-05,
"loss": 4.3092,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.5020565225965254e-05,
"loss": 4.3017,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501221203606219e-05,
"loss": 4.3137,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500382608855168e-05,
"loss": 4.307,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.287594318389893,
"eval_runtime": 291.8841,
"eval_samples_per_second": 1307.337,
"eval_steps_per_second": 40.855,
"step": 305280
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.2543876023734512e+17,
"trial_name": null,
"trial_params": null
}