abhinavp's picture
Training in progress, epoch 1, checkpoint
e2803fe verified
raw
history blame
No virus
186 kB
{
"best_metric": 4.093703269958496,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/lstm/1/checkpoints/checkpoint-763200",
"epoch": 1.0250006060157382,
"eval_steps": 10,
"global_step": 763200,
"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": 10.8199,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.551,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0623,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 7.0021,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9546,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.9238,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7565,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6535,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5511,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992454285120906e-05,
"loss": 6.4654,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.991615690369854e-05,
"loss": 6.4016,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990777095618801e-05,
"loss": 6.3402,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 6.2709,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 6.2059,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 6.1568,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 6.1029,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 6.0587,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 6.0172,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.9815,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9434,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.9102,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8714,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.981552553357229e-05,
"loss": 5.8488,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.980713958606178e-05,
"loss": 5.8073,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.979875363855125e-05,
"loss": 5.7895,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7573,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.7355,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.7145,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.97652262273129e-05,
"loss": 5.6844,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6589,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6463,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.6339,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.6123,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5885,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5826,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 5.5556,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5418,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.5074,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.5112,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 5.4884,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 5.4798,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965627442489107e-05,
"loss": 5.4668,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964788847738054e-05,
"loss": 5.46,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 5.4286,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 5.4224,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962274701365272e-05,
"loss": 5.4179,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.96143610661422e-05,
"loss": 5.4021,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.9605991497435414e-05,
"loss": 5.4026,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 5.3816,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.95892359812181e-05,
"loss": 5.3603,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 5.3688,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957246408619706e-05,
"loss": 5.3476,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956407813868654e-05,
"loss": 5.3416,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.9555692191176016e-05,
"loss": 5.3141,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.9547306243665496e-05,
"loss": 5.3243,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.9538920296154976e-05,
"loss": 5.3016,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530534348644456e-05,
"loss": 5.3274,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 5.2901,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951379521123089e-05,
"loss": 5.2896,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950540926372037e-05,
"loss": 5.2828,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949702331620985e-05,
"loss": 5.2616,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 5.249,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 5.249,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 5.2329,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 5.2265,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945509357865724e-05,
"loss": 5.2437,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.224,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.2103,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 5.1868,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 5.1829,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 5.1908,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 5.1882,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 5.1793,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 5.1779,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 5.1701,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 5.1609,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362880913648985e-05,
"loss": 5.1472,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354494966138465e-05,
"loss": 5.1387,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 5.1326,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 5.1205,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 5.1279,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 5.1177,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.1207,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 5.1008,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 5.0812,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 5.0957,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 5.0918,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 5.0891,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 5.0756,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925391273242342e-05,
"loss": 5.0762,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.92455267849129e-05,
"loss": 5.0632,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.0563,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.0559,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922038532118507e-05,
"loss": 5.05,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 5.0528,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.0469,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 5.0441,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 5.0222,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 5.0199,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 5.0169,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 5.0173,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 5.0099,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 5.0019,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.9926,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 5.0002,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.9752,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9809,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.9795,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.9702,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908624291862421e-05,
"loss": 4.9662,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907785697111369e-05,
"loss": 4.9702,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9576,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9601,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.9523,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.9411,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.948,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.9449,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.9387,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.9253,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.9312,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.9321,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.9218,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.9084,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.9164,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.9167,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.9043,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943730947356565e-05,
"loss": 4.8989,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.893534499984604e-05,
"loss": 4.8871,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.8939,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.8844,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.8986,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.8888,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.8695,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.8762,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.8749,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.8713,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885990422985882e-05,
"loss": 4.8739,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.88515182823483e-05,
"loss": 4.8609,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884313233483778e-05,
"loss": 4.8637,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883474638732726e-05,
"loss": 4.8692,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.8522,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.8492,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.8495,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.836,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879286578618586e-05,
"loss": 4.8357,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.8425,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.8267,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.8289,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.8353,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.8294,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.7875447273254395,
"eval_runtime": 295.2925,
"eval_samples_per_second": 1292.247,
"eval_steps_per_second": 40.384,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.8119,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.813,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.8272,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717425016198635e-05,
"loss": 4.8125,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709039068688115e-05,
"loss": 4.8226,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.7951,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.8129,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.7959,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867551165744977e-05,
"loss": 4.7911,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866712570993925e-05,
"loss": 4.7977,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.865873976242873e-05,
"loss": 4.7984,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.8013,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.7828,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.7828,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.7744,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.7743,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860845683497307e-05,
"loss": 4.7723,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860007088746255e-05,
"loss": 4.7732,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.7698,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.7885,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.7651,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566543476224204e-05,
"loss": 4.7723,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558157528713684e-05,
"loss": 4.7597,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549771581203164e-05,
"loss": 4.7685,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.7555,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.7546,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.7504,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.7471,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.850785822245429e-05,
"loss": 4.7311,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.849947227494377e-05,
"loss": 4.7456,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.849108632743325e-05,
"loss": 4.7431,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.848270037992273e-05,
"loss": 4.7456,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.7363,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.7394,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.7293,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.7279,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.84408033999776e-05,
"loss": 4.7105,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843241745246708e-05,
"loss": 4.7186,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842403150495656e-05,
"loss": 4.7173,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.841564555744604e-05,
"loss": 4.7154,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840725960993552e-05,
"loss": 4.7191,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.8398873662425e-05,
"loss": 4.7182,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839048771491447e-05,
"loss": 4.7063,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838210176740395e-05,
"loss": 4.7115,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.837371581989343e-05,
"loss": 4.713,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.699,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.7107,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.8348574356165606e-05,
"loss": 4.6963,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.6849,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.7048,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.6878,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315046944927255e-05,
"loss": 4.6877,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306660997416735e-05,
"loss": 4.6754,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298275049906215e-05,
"loss": 4.6846,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289889102395695e-05,
"loss": 4.6731,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.7049,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.827314996498212e-05,
"loss": 4.6736,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.82647640174716e-05,
"loss": 4.6854,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825637806996108e-05,
"loss": 4.6823,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824799212245056e-05,
"loss": 4.6689,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823960617494004e-05,
"loss": 4.6584,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823122022742952e-05,
"loss": 4.6726,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222834279919e-05,
"loss": 4.6576,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821444833240848e-05,
"loss": 4.6573,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820606238489796e-05,
"loss": 4.6734,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.6689,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.6529,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.6476,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817255135246334e-05,
"loss": 4.6473,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816416540495282e-05,
"loss": 4.658,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.8155779457442305e-05,
"loss": 4.6564,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.8147393509931785e-05,
"loss": 4.6558,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.6553,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.6556,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122235667400224e-05,
"loss": 4.6553,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.6391,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105463772379184e-05,
"loss": 4.6418,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809707782486866e-05,
"loss": 4.6413,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808869187735814e-05,
"loss": 4.6259,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808032230865135e-05,
"loss": 4.641,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.8071936361140827e-05,
"loss": 4.6399,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.643,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.6224,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804677851860927e-05,
"loss": 4.613,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803839257109875e-05,
"loss": 4.6316,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.6253,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802163705488144e-05,
"loss": 4.6326,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801325110737092e-05,
"loss": 4.6244,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.80048651598604e-05,
"loss": 4.6258,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799647921234988e-05,
"loss": 4.6215,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798809326483936e-05,
"loss": 4.612,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.79797400749363e-05,
"loss": 4.6182,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797135412742578e-05,
"loss": 4.6148,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796296817991526e-05,
"loss": 4.6229,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795458223240474e-05,
"loss": 4.6235,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794619628489423e-05,
"loss": 4.6188,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.6057,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792942438987319e-05,
"loss": 4.6043,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.6038,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.6136,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790426654734163e-05,
"loss": 4.6003,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895880599831107e-05,
"loss": 4.5998,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887494652320587e-05,
"loss": 4.593,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879125083613796e-05,
"loss": 4.6069,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870739136103276e-05,
"loss": 4.581,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862353188592756e-05,
"loss": 4.5932,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853983619885965e-05,
"loss": 4.5958,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845597672375445e-05,
"loss": 4.5875,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.5859,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.5975,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782043982984389e-05,
"loss": 4.5819,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781205388233337e-05,
"loss": 4.5856,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780368431362658e-05,
"loss": 4.5889,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779529836611606e-05,
"loss": 4.5753,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778691241860554e-05,
"loss": 4.5868,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777852647109502e-05,
"loss": 4.5909,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777014052358449e-05,
"loss": 4.5826,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776175457607397e-05,
"loss": 4.5708,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775338500736719e-05,
"loss": 4.5818,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774499905985666e-05,
"loss": 4.58,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773661311234615e-05,
"loss": 4.5725,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772822716483563e-05,
"loss": 4.5674,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771984121732511e-05,
"loss": 4.5698,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771145526981459e-05,
"loss": 4.5811,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770306932230407e-05,
"loss": 4.5696,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769468337479355e-05,
"loss": 4.5671,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768631380608676e-05,
"loss": 4.5565,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767794423737997e-05,
"loss": 4.5634,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766955828986945e-05,
"loss": 4.5588,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766117234235893e-05,
"loss": 4.5743,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.5691,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764440044733789e-05,
"loss": 4.5501,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763601449982737e-05,
"loss": 4.557,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762766130992431e-05,
"loss": 4.561,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761927536241379e-05,
"loss": 4.5579,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761088941490327e-05,
"loss": 4.5651,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760250346739275e-05,
"loss": 4.5509,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.759411751988223e-05,
"loss": 4.5549,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758573157237171e-05,
"loss": 4.5615,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757734562486119e-05,
"loss": 4.548,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756895967735067e-05,
"loss": 4.5505,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756057372984015e-05,
"loss": 4.5553,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755218778232963e-05,
"loss": 4.5391,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754380183481911e-05,
"loss": 4.5434,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753541588730859e-05,
"loss": 4.5489,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.75270463186018e-05,
"loss": 4.5348,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.7518676749895016e-05,
"loss": 4.5415,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.7510290802384496e-05,
"loss": 4.5463,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.7501904854873976e-05,
"loss": 4.542,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.505749702453613,
"eval_runtime": 293.7953,
"eval_samples_per_second": 1298.833,
"eval_steps_per_second": 40.589,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.7493535286167185e-05,
"loss": 4.5283,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485149338656665e-05,
"loss": 4.5294,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476763391146145e-05,
"loss": 4.5492,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468377443635625e-05,
"loss": 4.5295,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7459991496125105e-05,
"loss": 4.5437,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451605548614585e-05,
"loss": 4.5249,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443219601104065e-05,
"loss": 4.5388,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434833653593545e-05,
"loss": 4.5214,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426447706083025e-05,
"loss": 4.5323,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.7418061758572505e-05,
"loss": 4.5265,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.7409675811061985e-05,
"loss": 4.5305,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401289863551465e-05,
"loss": 4.537,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739292029484468e-05,
"loss": 4.5173,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384534347334154e-05,
"loss": 4.5198,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376148399823634e-05,
"loss": 4.5164,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367762452313114e-05,
"loss": 4.5136,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359376504802594e-05,
"loss": 4.5172,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350990557292074e-05,
"loss": 4.5198,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342604609781554e-05,
"loss": 4.5145,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.7334218662271034e-05,
"loss": 4.5359,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325832714760514e-05,
"loss": 4.5154,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731746314605372e-05,
"loss": 4.5225,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.73090771985432e-05,
"loss": 4.5127,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730069125103269e-05,
"loss": 4.5233,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729230530352217e-05,
"loss": 4.5123,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728391935601165e-05,
"loss": 4.5059,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727553340850113e-05,
"loss": 4.5098,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726716383979434e-05,
"loss": 4.5056,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725877789228382e-05,
"loss": 4.4911,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.72503919447733e-05,
"loss": 4.5061,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724200599726278e-05,
"loss": 4.5116,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723363642855599e-05,
"loss": 4.5065,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.722525048104547e-05,
"loss": 4.5035,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721686453353495e-05,
"loss": 4.5052,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.7208494964828156e-05,
"loss": 4.497,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720010901731764e-05,
"loss": 4.4941,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719172306980712e-05,
"loss": 4.4894,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.71833371222966e-05,
"loss": 4.4877,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717495117478608e-05,
"loss": 4.4885,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716656522727556e-05,
"loss": 4.4902,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715817927976504e-05,
"loss": 4.4972,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.7149793332254516e-05,
"loss": 4.4956,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.7141407384743996e-05,
"loss": 4.4843,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713303781603721e-05,
"loss": 4.4902,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124651868526685e-05,
"loss": 4.495,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116265921016165e-05,
"loss": 4.4762,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710789635230938e-05,
"loss": 4.4903,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.709951040479886e-05,
"loss": 4.4839,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.709112445728834e-05,
"loss": 4.4662,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.708273850977782e-05,
"loss": 4.4873,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.70743525622673e-05,
"loss": 4.4791,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706596661475678e-05,
"loss": 4.4737,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705758066724626e-05,
"loss": 4.4694,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704919471973574e-05,
"loss": 4.4734,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704080877222522e-05,
"loss": 4.4614,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.70324228247147e-05,
"loss": 4.4891,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702405325600791e-05,
"loss": 4.4718,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.701566730849739e-05,
"loss": 4.4775,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.700728136098687e-05,
"loss": 4.4793,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699889541347635e-05,
"loss": 4.4634,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699050946596583e-05,
"loss": 4.4556,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698212351845531e-05,
"loss": 4.4732,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697373757094479e-05,
"loss": 4.4573,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.6965351623434276e-05,
"loss": 4.4552,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956982054727485e-05,
"loss": 4.4738,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.6948596107216965e-05,
"loss": 4.4696,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.6940210159706445e-05,
"loss": 4.456,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931824212195925e-05,
"loss": 4.4485,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.6923454643489134e-05,
"loss": 4.4517,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.6915068695978614e-05,
"loss": 4.4604,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690669912727182e-05,
"loss": 4.4653,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.68983131797613e-05,
"loss": 4.4619,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688992723225078e-05,
"loss": 4.4637,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688154128474026e-05,
"loss": 4.462,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687315533722974e-05,
"loss": 4.4666,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686476938971923e-05,
"loss": 4.4501,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685639982101244e-05,
"loss": 4.4544,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684801387350192e-05,
"loss": 4.4565,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.68396279259914e-05,
"loss": 4.4367,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683124197848087e-05,
"loss": 4.4519,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682285603097035e-05,
"loss": 4.4579,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681447008345983e-05,
"loss": 4.4549,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680610051475305e-05,
"loss": 4.4422,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679771456724252e-05,
"loss": 4.4285,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.6789328619732e-05,
"loss": 4.4487,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678094267222148e-05,
"loss": 4.4391,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677255672471097e-05,
"loss": 4.455,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676417077720045e-05,
"loss": 4.4441,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675578482968993e-05,
"loss": 4.4465,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747415260983136e-05,
"loss": 4.442,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739029313472616e-05,
"loss": 4.4326,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730659744765826e-05,
"loss": 4.4398,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722273797255305e-05,
"loss": 4.437,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713887849744785e-05,
"loss": 4.4499,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705501902234265e-05,
"loss": 4.4514,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697115954723745e-05,
"loss": 4.4425,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688730007213225e-05,
"loss": 4.4305,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680344059702705e-05,
"loss": 4.4326,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6671958112192185e-05,
"loss": 4.4326,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663572164681665e-05,
"loss": 4.4416,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655186217171145e-05,
"loss": 4.4283,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664681664846436e-05,
"loss": 4.4321,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663843070095384e-05,
"loss": 4.4213,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663004475344332e-05,
"loss": 4.4398,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.66216588059328e-05,
"loss": 4.4124,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661327285842228e-05,
"loss": 4.4267,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660488691091176e-05,
"loss": 4.4212,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596500963401234e-05,
"loss": 4.4252,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588115015890714e-05,
"loss": 4.4216,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657974544718393e-05,
"loss": 4.4292,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.657135949967341e-05,
"loss": 4.4229,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656297355216288e-05,
"loss": 4.4196,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655458760465237e-05,
"loss": 4.4258,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654620165714185e-05,
"loss": 4.4109,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653781570963133e-05,
"loss": 4.43,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652944614092454e-05,
"loss": 4.4326,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652106019341402e-05,
"loss": 4.4189,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512690624707234e-05,
"loss": 4.4137,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650430467719671e-05,
"loss": 4.4191,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649591872968619e-05,
"loss": 4.4192,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648753278217567e-05,
"loss": 4.4141,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647914683466515e-05,
"loss": 4.4119,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647076088715463e-05,
"loss": 4.4086,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646237493964411e-05,
"loss": 4.4257,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645398899213359e-05,
"loss": 4.416,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644560304462307e-05,
"loss": 4.411,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437217097112554e-05,
"loss": 4.3994,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642884752840576e-05,
"loss": 4.4123,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642046158089524e-05,
"loss": 4.4021,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641207563338472e-05,
"loss": 4.4215,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.64036896858742e-05,
"loss": 4.4173,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639530373836368e-05,
"loss": 4.4021,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638693416965689e-05,
"loss": 4.3998,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637854822214637e-05,
"loss": 4.4105,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637016227463585e-05,
"loss": 4.4062,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636177632712533e-05,
"loss": 4.4178,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635339037961481e-05,
"loss": 4.3981,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634500443210429e-05,
"loss": 4.4102,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633663486339751e-05,
"loss": 4.4074,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632824891588699e-05,
"loss": 4.4058,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631986296837647e-05,
"loss": 4.4041,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631147702086595e-05,
"loss": 4.4063,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630309107335542e-05,
"loss": 4.394,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.62947051258449e-05,
"loss": 4.4,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628631917833438e-05,
"loss": 4.4025,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627793323082386e-05,
"loss": 4.3956,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626956366211707e-05,
"loss": 4.3932,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.6261194093410286e-05,
"loss": 4.4026,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.6252808145899766e-05,
"loss": 4.3987,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.369894504547119,
"eval_runtime": 308.2574,
"eval_samples_per_second": 1237.897,
"eval_steps_per_second": 38.685,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.6244422198389246e-05,
"loss": 4.3918,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.6236036250878726e-05,
"loss": 4.384,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622766668217194e-05,
"loss": 4.4077,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621928073466142e-05,
"loss": 4.389,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.6210894787150895e-05,
"loss": 4.4066,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202508839640374e-05,
"loss": 4.3806,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194122892129854e-05,
"loss": 4.4019,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185736944619334e-05,
"loss": 4.3866,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177350997108814e-05,
"loss": 4.3911,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6168965049598294e-05,
"loss": 4.3911,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.61605954808915e-05,
"loss": 4.3898,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615220953338098e-05,
"loss": 4.3979,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.61438399646742e-05,
"loss": 4.3811,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613545401716368e-05,
"loss": 4.3802,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612706806965316e-05,
"loss": 4.3856,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611868212214264e-05,
"loss": 4.3715,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611029617463212e-05,
"loss": 4.3826,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.61019102271216e-05,
"loss": 4.3871,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609352427961108e-05,
"loss": 4.3785,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608513833210056e-05,
"loss": 4.399,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607676876339377e-05,
"loss": 4.3862,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606838281588325e-05,
"loss": 4.3919,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.606001324717646e-05,
"loss": 4.3799,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605162729966594e-05,
"loss": 4.388,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604324135215542e-05,
"loss": 4.3808,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.60348554046449e-05,
"loss": 4.3767,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602646945713438e-05,
"loss": 4.3792,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018083509623864e-05,
"loss": 4.3727,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009697562113344e-05,
"loss": 4.3688,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600132799340655e-05,
"loss": 4.3705,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599294204589603e-05,
"loss": 4.381,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598455609838551e-05,
"loss": 4.3794,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597617015087499e-05,
"loss": 4.3776,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596778420336447e-05,
"loss": 4.3807,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595941463465768e-05,
"loss": 4.3626,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595102868714716e-05,
"loss": 4.3682,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594264273963664e-05,
"loss": 4.3684,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593425679212612e-05,
"loss": 4.3578,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.59258708446156e-05,
"loss": 4.3648,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591748489710508e-05,
"loss": 4.3611,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590909894959456e-05,
"loss": 4.3744,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590071300208404e-05,
"loss": 4.3715,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589234343337726e-05,
"loss": 4.3627,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588395748586673e-05,
"loss": 4.3621,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.5875587917159946e-05,
"loss": 4.3738,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.5867201969649426e-05,
"loss": 4.3545,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.5858816022138906e-05,
"loss": 4.3685,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585043007462838e-05,
"loss": 4.3613,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584204412711786e-05,
"loss": 4.3437,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583365817960734e-05,
"loss": 4.3689,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582527223209682e-05,
"loss": 4.3541,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.5816902663390035e-05,
"loss": 4.3573,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808516715879515e-05,
"loss": 4.3455,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800130768368995e-05,
"loss": 4.3545,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791744820858475e-05,
"loss": 4.3421,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783358873347955e-05,
"loss": 4.3659,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5774972925837435e-05,
"loss": 4.3542,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766586978326915e-05,
"loss": 4.3571,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758201030816395e-05,
"loss": 4.3619,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5749831462109604e-05,
"loss": 4.3467,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741445514599084e-05,
"loss": 4.3374,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733059567088564e-05,
"loss": 4.3575,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724673619578044e-05,
"loss": 4.3407,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716287672067524e-05,
"loss": 4.3401,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570791810336074e-05,
"loss": 4.3563,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569954853465395e-05,
"loss": 4.3533,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.569116258714343e-05,
"loss": 4.3422,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568277663963291e-05,
"loss": 4.3398,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567439069212239e-05,
"loss": 4.3323,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566600474461187e-05,
"loss": 4.342,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565761879710135e-05,
"loss": 4.3523,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564923284959083e-05,
"loss": 4.3519,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564084690208031e-05,
"loss": 4.3503,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563247733337352e-05,
"loss": 4.347,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624091385863e-05,
"loss": 4.3612,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615721817156206e-05,
"loss": 4.3354,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560733586964569e-05,
"loss": 4.3462,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559894992213517e-05,
"loss": 4.3432,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559056397462465e-05,
"loss": 4.3252,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558219440591786e-05,
"loss": 4.3459,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557380845840734e-05,
"loss": 4.347,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556542251089682e-05,
"loss": 4.342,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.55570365633863e-05,
"loss": 4.3353,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554865061587578e-05,
"loss": 4.3237,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554028104716899e-05,
"loss": 4.3376,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553189509965847e-05,
"loss": 4.3364,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.552350915214795e-05,
"loss": 4.3428,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.551512320463743e-05,
"loss": 4.3331,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.550673725712691e-05,
"loss": 4.3437,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.549836768842013e-05,
"loss": 4.3286,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.548998174090961e-05,
"loss": 4.3301,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548159579339909e-05,
"loss": 4.3304,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.5473226224692296e-05,
"loss": 4.3286,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.5464840277181776e-05,
"loss": 4.3455,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.5456454329671256e-05,
"loss": 4.3413,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448068382160736e-05,
"loss": 4.3404,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.5439682434650216e-05,
"loss": 4.3225,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543129648713969e-05,
"loss": 4.3285,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542291053962917e-05,
"loss": 4.3291,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541452459211865e-05,
"loss": 4.3329,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540613864460813e-05,
"loss": 4.3261,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539775269709761e-05,
"loss": 4.3248,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389366749587095e-05,
"loss": 4.3172,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5380997180880304e-05,
"loss": 4.3386,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372627612173514e-05,
"loss": 4.31,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364241664662994e-05,
"loss": 4.3218,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5355855717152473e-05,
"loss": 4.3195,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347469769641953e-05,
"loss": 4.3206,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533908382213143e-05,
"loss": 4.3196,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533069787462091e-05,
"loss": 4.3308,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532231192711039e-05,
"loss": 4.3214,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.531392597959987e-05,
"loss": 4.3158,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530554003208935e-05,
"loss": 4.3304,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.529715408457883e-05,
"loss": 4.3125,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528876813706831e-05,
"loss": 4.3273,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528038218955779e-05,
"loss": 4.3341,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527201262085101e-05,
"loss": 4.3215,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526364305214422e-05,
"loss": 4.3152,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.52552571046337e-05,
"loss": 4.3157,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524687115712318e-05,
"loss": 4.3189,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523850158841639e-05,
"loss": 4.3143,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523011564090587e-05,
"loss": 4.3206,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522172969339535e-05,
"loss": 4.3068,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521334374588483e-05,
"loss": 4.3258,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520495779837431e-05,
"loss": 4.3209,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519657185086379e-05,
"loss": 4.3156,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518818590335327e-05,
"loss": 4.2998,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517981633464648e-05,
"loss": 4.3156,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517143038713596e-05,
"loss": 4.3071,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516304443962544e-05,
"loss": 4.3209,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515465849211492e-05,
"loss": 4.3243,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.51462725446044e-05,
"loss": 4.313,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5137886597093876e-05,
"loss": 4.2986,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.5129500649583356e-05,
"loss": 4.3159,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.5121114702072836e-05,
"loss": 4.3091,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.5112728754562316e-05,
"loss": 4.3247,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104359185855525e-05,
"loss": 4.3023,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5095973238345005e-05,
"loss": 4.315,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508760366963822e-05,
"loss": 4.3135,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.50792177221277e-05,
"loss": 4.3168,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507083177461718e-05,
"loss": 4.3097,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506244582710666e-05,
"loss": 4.3102,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505405987959614e-05,
"loss": 4.3004,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504567393208562e-05,
"loss": 4.3098,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.50372879845751e-05,
"loss": 4.3065,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502890203706458e-05,
"loss": 4.3065,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502051608955406e-05,
"loss": 4.2996,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501213014204354e-05,
"loss": 4.3116,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500374419453302e-05,
"loss": 4.3041,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.286177635192871,
"eval_runtime": 309.828,
"eval_samples_per_second": 1231.622,
"eval_steps_per_second": 38.489,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.49953582470225e-05,
"loss": 4.2947,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498697229951198e-05,
"loss": 4.2952,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497858635200146e-05,
"loss": 4.3163,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497020040449093e-05,
"loss": 4.2985,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496181445698042e-05,
"loss": 4.3113,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.49534285094699e-05,
"loss": 4.2981,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494504256195938e-05,
"loss": 4.3041,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493665661444886e-05,
"loss": 4.2993,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492827066693834e-05,
"loss": 4.3003,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.491988471942782e-05,
"loss": 4.3012,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.49114987719173e-05,
"loss": 4.3012,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490311282440678e-05,
"loss": 4.3089,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489474325569999e-05,
"loss": 4.2932,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488635730818947e-05,
"loss": 4.2921,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487797136067895e-05,
"loss": 4.2946,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486958541316843e-05,
"loss": 4.2846,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486119946565791e-05,
"loss": 4.2942,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485281351814739e-05,
"loss": 4.2986,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484442757063687e-05,
"loss": 4.2906,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483604162312635e-05,
"loss": 4.3133,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482765567561583e-05,
"loss": 4.2991,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.481926972810531e-05,
"loss": 4.3057,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481088378059479e-05,
"loss": 4.2932,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480249783308427e-05,
"loss": 4.3012,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479412826437748e-05,
"loss": 4.2919,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478574231686696e-05,
"loss": 4.2945,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477735636935644e-05,
"loss": 4.2908,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476897042184592e-05,
"loss": 4.2887,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.4760600853139126e-05,
"loss": 4.2837,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.4752214905628606e-05,
"loss": 4.2855,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.4743828958118086e-05,
"loss": 4.2917,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.47354593894113e-05,
"loss": 4.2949,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472707344190078e-05,
"loss": 4.2913,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471868749439026e-05,
"loss": 4.2949,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471030154687974e-05,
"loss": 4.2792,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470191559936922e-05,
"loss": 4.2854,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.46935296518587e-05,
"loss": 4.285,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468514370434818e-05,
"loss": 4.2714,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467675775683766e-05,
"loss": 4.2855,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466838818813087e-05,
"loss": 4.2754,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466001861942408e-05,
"loss": 4.2908,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465163267191356e-05,
"loss": 4.2875,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464324672440304e-05,
"loss": 4.2822,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4634860776892526e-05,
"loss": 4.2753,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626474829382006e-05,
"loss": 4.2932,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618088881871486e-05,
"loss": 4.272,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4609702934360966e-05,
"loss": 4.2877,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601316986850446e-05,
"loss": 4.2772,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4592947418143655e-05,
"loss": 4.2631,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584561470633135e-05,
"loss": 4.2896,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576175523122615e-05,
"loss": 4.2723,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4567789575612095e-05,
"loss": 4.2738,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559436385709033e-05,
"loss": 4.2699,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551050438198513e-05,
"loss": 4.2685,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454268086949173e-05,
"loss": 4.268,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453429492198121e-05,
"loss": 4.2779,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452590897447069e-05,
"loss": 4.2768,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451752302696017e-05,
"loss": 4.2772,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450913707944965e-05,
"loss": 4.2829,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450075113193913e-05,
"loss": 4.2694,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449236518442861e-05,
"loss": 4.2565,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448397923691809e-05,
"loss": 4.2789,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447559328940757e-05,
"loss": 4.2615,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446720734189705e-05,
"loss": 4.2578,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445882139438653e-05,
"loss": 4.2804,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445043544687601e-05,
"loss": 4.2742,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444206587816922e-05,
"loss": 4.2652,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.44336799306587e-05,
"loss": 4.2635,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442529398314818e-05,
"loss": 4.2527,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441690803563766e-05,
"loss": 4.2653,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.4408538466930874e-05,
"loss": 4.2763,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.4400152519420354e-05,
"loss": 4.2702,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.4391766571909834e-05,
"loss": 4.271,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.4383380624399314e-05,
"loss": 4.2679,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437499467688879e-05,
"loss": 4.286,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436660872937827e-05,
"loss": 4.259,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.4358222781867747e-05,
"loss": 4.2699,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.4349836834357227e-05,
"loss": 4.2676,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.4341467265650436e-05,
"loss": 4.2414,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433309769694365e-05,
"loss": 4.2755,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432471174943313e-05,
"loss": 4.2685,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431632580192261e-05,
"loss": 4.2679,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430793985441209e-05,
"loss": 4.2624,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429955390690157e-05,
"loss": 4.2465,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429118433819479e-05,
"loss": 4.263,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.428279839068426e-05,
"loss": 4.2603,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274428821977476e-05,
"loss": 4.2692,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266042874466956e-05,
"loss": 4.2582,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425765692695643e-05,
"loss": 4.2669,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424927097944591e-05,
"loss": 4.2545,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424088503193539e-05,
"loss": 4.2593,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423249908442487e-05,
"loss": 4.2559,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422411313691435e-05,
"loss": 4.2551,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.4215727189403836e-05,
"loss": 4.2706,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.4207357620697045e-05,
"loss": 4.2668,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.4198971673186525e-05,
"loss": 4.2724,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190585725676005e-05,
"loss": 4.2463,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182199778165485e-05,
"loss": 4.2567,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4173813830654965e-05,
"loss": 4.2574,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.4165427883144445e-05,
"loss": 4.2598,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157041935633925e-05,
"loss": 4.2549,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.4148655988123405e-05,
"loss": 4.249,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.4140286419416614e-05,
"loss": 4.25,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.4131900471906094e-05,
"loss": 4.2656,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123514524395574e-05,
"loss": 4.2366,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411514495568879e-05,
"loss": 4.2497,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.410675900817827e-05,
"loss": 4.245,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409837306066775e-05,
"loss": 4.2562,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.408998711315723e-05,
"loss": 4.2471,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408160116564671e-05,
"loss": 4.2577,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407321521813619e-05,
"loss": 4.2503,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406482927062567e-05,
"loss": 4.2441,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405644332311514e-05,
"loss": 4.2588,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404809013321209e-05,
"loss": 4.2448,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.403970418570157e-05,
"loss": 4.2575,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403131823819105e-05,
"loss": 4.2607,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402293229068053e-05,
"loss": 4.2496,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401454634317001e-05,
"loss": 4.2445,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400616039565949e-05,
"loss": 4.249,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399777444814897e-05,
"loss": 4.2467,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398938850063845e-05,
"loss": 4.2479,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398101893193166e-05,
"loss": 4.2483,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397263298442114e-05,
"loss": 4.238,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396426341571435e-05,
"loss": 4.2568,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395587746820383e-05,
"loss": 4.248,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394749152069331e-05,
"loss": 4.2495,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393910557318279e-05,
"loss": 4.2326,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3930736004476e-05,
"loss": 4.2463,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392235005696548e-05,
"loss": 4.2383,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.39139804882587e-05,
"loss": 4.2508,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390559454074818e-05,
"loss": 4.2526,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389720859323766e-05,
"loss": 4.2474,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388882264572714e-05,
"loss": 4.2288,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388043669821662e-05,
"loss": 4.2493,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387205075070609e-05,
"loss": 4.2423,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386366480319557e-05,
"loss": 4.2553,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385527885568505e-05,
"loss": 4.2334,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.384689290817453e-05,
"loss": 4.2517,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383852333946774e-05,
"loss": 4.2448,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383013739195722e-05,
"loss": 4.2499,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.38217514444467e-05,
"loss": 4.2393,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381336549693618e-05,
"loss": 4.245,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380497954942566e-05,
"loss": 4.2337,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.3796609980718875e-05,
"loss": 4.2445,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.3788224033208355e-05,
"loss": 4.2402,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3779838085697835e-05,
"loss": 4.2389,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771452138187314e-05,
"loss": 4.2348,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763082569480524e-05,
"loss": 4.2414,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3754696621970004e-05,
"loss": 4.2431,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.22830867767334,
"eval_runtime": 299.4563,
"eval_samples_per_second": 1274.279,
"eval_steps_per_second": 39.822,
"step": 381600
},
{
"epoch": 1.0,
"learning_rate": 4.3746310674459483e-05,
"loss": 4.235,
"step": 381952
},
{
"epoch": 1.0,
"learning_rate": 4.3737924726948963e-05,
"loss": 4.2277,
"step": 382464
},
{
"epoch": 1.0,
"learning_rate": 4.372955515824217e-05,
"loss": 4.2485,
"step": 382976
},
{
"epoch": 1.0,
"learning_rate": 4.372116921073165e-05,
"loss": 4.234,
"step": 383488
},
{
"epoch": 1.0,
"learning_rate": 4.371278326322113e-05,
"loss": 4.2447,
"step": 384000
},
{
"epoch": 1.0,
"learning_rate": 4.370439731571061e-05,
"loss": 4.2347,
"step": 384512
},
{
"epoch": 1.0,
"learning_rate": 4.36960113682001e-05,
"loss": 4.238,
"step": 385024
},
{
"epoch": 1.0,
"learning_rate": 4.368764179949331e-05,
"loss": 4.2374,
"step": 385536
},
{
"epoch": 1.0,
"learning_rate": 4.367925585198279e-05,
"loss": 4.2339,
"step": 386048
},
{
"epoch": 1.0,
"learning_rate": 4.367086990447227e-05,
"loss": 4.2362,
"step": 386560
},
{
"epoch": 1.0,
"learning_rate": 4.366248395696175e-05,
"loss": 4.2404,
"step": 387072
},
{
"epoch": 1.0,
"learning_rate": 4.365409800945123e-05,
"loss": 4.24,
"step": 387584
},
{
"epoch": 1.0,
"learning_rate": 4.3645744819548166e-05,
"loss": 4.2316,
"step": 388096
},
{
"epoch": 1.0,
"learning_rate": 4.3637358872037646e-05,
"loss": 4.2268,
"step": 388608
},
{
"epoch": 1.0,
"learning_rate": 4.3628972924527126e-05,
"loss": 4.2324,
"step": 389120
},
{
"epoch": 1.0,
"learning_rate": 4.3620586977016606e-05,
"loss": 4.2179,
"step": 389632
},
{
"epoch": 1.0,
"learning_rate": 4.3612201029506086e-05,
"loss": 4.2319,
"step": 390144
},
{
"epoch": 1.0,
"learning_rate": 4.3603815081995566e-05,
"loss": 4.2317,
"step": 390656
},
{
"epoch": 1.0,
"learning_rate": 4.359542913448505e-05,
"loss": 4.2302,
"step": 391168
},
{
"epoch": 1.0,
"learning_rate": 4.358704318697453e-05,
"loss": 4.2486,
"step": 391680
},
{
"epoch": 1.0,
"learning_rate": 4.357865723946401e-05,
"loss": 4.2369,
"step": 392192
},
{
"epoch": 1.0,
"learning_rate": 4.357027129195349e-05,
"loss": 4.2418,
"step": 392704
},
{
"epoch": 1.0,
"learning_rate": 4.356188534444297e-05,
"loss": 4.233,
"step": 393216
},
{
"epoch": 1.0,
"learning_rate": 4.355349939693245e-05,
"loss": 4.2361,
"step": 393728
},
{
"epoch": 1.0,
"learning_rate": 4.354512982822566e-05,
"loss": 4.2307,
"step": 394240
},
{
"epoch": 1.0,
"learning_rate": 4.353676025951887e-05,
"loss": 4.232,
"step": 394752
},
{
"epoch": 1.0,
"learning_rate": 4.352837431200835e-05,
"loss": 4.2275,
"step": 395264
},
{
"epoch": 1.0,
"learning_rate": 4.351998836449783e-05,
"loss": 4.227,
"step": 395776
},
{
"epoch": 1.0,
"learning_rate": 4.351160241698731e-05,
"loss": 4.222,
"step": 396288
},
{
"epoch": 1.0,
"learning_rate": 4.350321646947679e-05,
"loss": 4.2242,
"step": 396800
},
{
"epoch": 1.01,
"learning_rate": 4.349483052196627e-05,
"loss": 4.2288,
"step": 397312
},
{
"epoch": 1.01,
"learning_rate": 4.348644457445575e-05,
"loss": 4.2329,
"step": 397824
},
{
"epoch": 1.01,
"learning_rate": 4.347805862694523e-05,
"loss": 4.2283,
"step": 398336
},
{
"epoch": 1.01,
"learning_rate": 4.3469689058238446e-05,
"loss": 4.2359,
"step": 398848
},
{
"epoch": 1.01,
"learning_rate": 4.3461303110727926e-05,
"loss": 4.218,
"step": 399360
},
{
"epoch": 1.01,
"learning_rate": 4.3452933542021135e-05,
"loss": 4.2259,
"step": 399872
},
{
"epoch": 1.01,
"learning_rate": 4.3444547594510615e-05,
"loss": 4.2233,
"step": 400384
},
{
"epoch": 1.01,
"learning_rate": 4.3436161647000095e-05,
"loss": 4.2128,
"step": 400896
},
{
"epoch": 1.01,
"learning_rate": 4.3427792078293304e-05,
"loss": 4.226,
"step": 401408
},
{
"epoch": 1.01,
"learning_rate": 4.3419406130782784e-05,
"loss": 4.2112,
"step": 401920
},
{
"epoch": 1.01,
"learning_rate": 4.3411020183272264e-05,
"loss": 4.2283,
"step": 402432
},
{
"epoch": 1.01,
"learning_rate": 4.3402634235761744e-05,
"loss": 4.2264,
"step": 402944
},
{
"epoch": 1.01,
"learning_rate": 4.3394248288251224e-05,
"loss": 4.2254,
"step": 403456
},
{
"epoch": 1.01,
"learning_rate": 4.338587871954444e-05,
"loss": 4.2174,
"step": 403968
},
{
"epoch": 1.01,
"learning_rate": 4.337749277203392e-05,
"loss": 4.2336,
"step": 404480
},
{
"epoch": 1.01,
"learning_rate": 4.33691068245234e-05,
"loss": 4.211,
"step": 404992
},
{
"epoch": 1.01,
"learning_rate": 4.336072087701287e-05,
"loss": 4.2294,
"step": 405504
},
{
"epoch": 1.01,
"learning_rate": 4.335233492950235e-05,
"loss": 4.2175,
"step": 406016
},
{
"epoch": 1.01,
"learning_rate": 4.334394898199183e-05,
"loss": 4.1966,
"step": 406528
},
{
"epoch": 1.01,
"learning_rate": 4.333556303448131e-05,
"loss": 4.234,
"step": 407040
},
{
"epoch": 1.01,
"learning_rate": 4.332717708697079e-05,
"loss": 4.2122,
"step": 407552
},
{
"epoch": 1.01,
"learning_rate": 4.3318807518264e-05,
"loss": 4.2188,
"step": 408064
},
{
"epoch": 1.01,
"learning_rate": 4.331042157075348e-05,
"loss": 4.2068,
"step": 408576
},
{
"epoch": 1.01,
"learning_rate": 4.330203562324296e-05,
"loss": 4.2079,
"step": 409088
},
{
"epoch": 1.01,
"learning_rate": 4.329364967573244e-05,
"loss": 4.2136,
"step": 409600
},
{
"epoch": 1.01,
"learning_rate": 4.328528010702566e-05,
"loss": 4.215,
"step": 410112
},
{
"epoch": 1.01,
"learning_rate": 4.327689415951514e-05,
"loss": 4.2201,
"step": 410624
},
{
"epoch": 1.01,
"learning_rate": 4.326850821200462e-05,
"loss": 4.2161,
"step": 411136
},
{
"epoch": 1.01,
"learning_rate": 4.32601222644941e-05,
"loss": 4.2285,
"step": 411648
},
{
"epoch": 1.01,
"learning_rate": 4.325175269578731e-05,
"loss": 4.2086,
"step": 412160
},
{
"epoch": 1.01,
"learning_rate": 4.324336674827679e-05,
"loss": 4.199,
"step": 412672
},
{
"epoch": 1.01,
"learning_rate": 4.323498080076627e-05,
"loss": 4.2177,
"step": 413184
},
{
"epoch": 1.01,
"learning_rate": 4.322659485325575e-05,
"loss": 4.1993,
"step": 413696
},
{
"epoch": 1.01,
"learning_rate": 4.3218225284548956e-05,
"loss": 4.2032,
"step": 414208
},
{
"epoch": 1.01,
"learning_rate": 4.3209839337038436e-05,
"loss": 4.2205,
"step": 414720
},
{
"epoch": 1.01,
"learning_rate": 4.3201453389527916e-05,
"loss": 4.2189,
"step": 415232
},
{
"epoch": 1.01,
"learning_rate": 4.3193067442017396e-05,
"loss": 4.2039,
"step": 415744
},
{
"epoch": 1.01,
"learning_rate": 4.318469787331061e-05,
"loss": 4.2081,
"step": 416256
},
{
"epoch": 1.01,
"learning_rate": 4.317631192580009e-05,
"loss": 4.196,
"step": 416768
},
{
"epoch": 1.01,
"learning_rate": 4.316792597828957e-05,
"loss": 4.2074,
"step": 417280
},
{
"epoch": 1.01,
"learning_rate": 4.315955640958278e-05,
"loss": 4.219,
"step": 417792
},
{
"epoch": 1.01,
"learning_rate": 4.315117046207226e-05,
"loss": 4.2151,
"step": 418304
},
{
"epoch": 1.01,
"learning_rate": 4.314278451456174e-05,
"loss": 4.2137,
"step": 418816
},
{
"epoch": 1.01,
"learning_rate": 4.313439856705122e-05,
"loss": 4.2115,
"step": 419328
},
{
"epoch": 1.01,
"learning_rate": 4.31260126195407e-05,
"loss": 4.2293,
"step": 419840
},
{
"epoch": 1.01,
"learning_rate": 4.311762667203018e-05,
"loss": 4.2028,
"step": 420352
},
{
"epoch": 1.01,
"learning_rate": 4.310925710332339e-05,
"loss": 4.214,
"step": 420864
},
{
"epoch": 1.01,
"learning_rate": 4.310087115581287e-05,
"loss": 4.2105,
"step": 421376
},
{
"epoch": 1.01,
"learning_rate": 4.309248520830235e-05,
"loss": 4.19,
"step": 421888
},
{
"epoch": 1.01,
"learning_rate": 4.308409926079183e-05,
"loss": 4.2166,
"step": 422400
},
{
"epoch": 1.01,
"learning_rate": 4.3075713313281316e-05,
"loss": 4.2133,
"step": 422912
},
{
"epoch": 1.01,
"learning_rate": 4.3067327365770796e-05,
"loss": 4.2115,
"step": 423424
},
{
"epoch": 1.01,
"learning_rate": 4.3058941418260276e-05,
"loss": 4.2091,
"step": 423936
},
{
"epoch": 1.01,
"learning_rate": 4.3050555470749756e-05,
"loss": 4.1948,
"step": 424448
},
{
"epoch": 1.01,
"learning_rate": 4.3042185902042965e-05,
"loss": 4.2003,
"step": 424960
},
{
"epoch": 1.01,
"learning_rate": 4.3033799954532445e-05,
"loss": 4.2062,
"step": 425472
},
{
"epoch": 1.01,
"learning_rate": 4.3025430385825654e-05,
"loss": 4.2123,
"step": 425984
},
{
"epoch": 1.01,
"learning_rate": 4.3017044438315134e-05,
"loss": 4.2015,
"step": 426496
},
{
"epoch": 1.01,
"learning_rate": 4.300867486960834e-05,
"loss": 4.211,
"step": 427008
},
{
"epoch": 1.02,
"learning_rate": 4.300028892209782e-05,
"loss": 4.1982,
"step": 427520
},
{
"epoch": 1.02,
"learning_rate": 4.29919029745873e-05,
"loss": 4.2045,
"step": 428032
},
{
"epoch": 1.02,
"learning_rate": 4.298351702707678e-05,
"loss": 4.1981,
"step": 428544
},
{
"epoch": 1.02,
"learning_rate": 4.297513107956627e-05,
"loss": 4.2007,
"step": 429056
},
{
"epoch": 1.02,
"learning_rate": 4.296674513205575e-05,
"loss": 4.2138,
"step": 429568
},
{
"epoch": 1.02,
"learning_rate": 4.295835918454523e-05,
"loss": 4.2132,
"step": 430080
},
{
"epoch": 1.02,
"learning_rate": 4.294997323703471e-05,
"loss": 4.2159,
"step": 430592
},
{
"epoch": 1.02,
"learning_rate": 4.294158728952418e-05,
"loss": 4.1901,
"step": 431104
},
{
"epoch": 1.02,
"learning_rate": 4.293320134201366e-05,
"loss": 4.2032,
"step": 431616
},
{
"epoch": 1.02,
"learning_rate": 4.292481539450314e-05,
"loss": 4.1983,
"step": 432128
},
{
"epoch": 1.02,
"learning_rate": 4.291642944699262e-05,
"loss": 4.2076,
"step": 432640
},
{
"epoch": 1.02,
"learning_rate": 4.29080434994821e-05,
"loss": 4.1986,
"step": 433152
},
{
"epoch": 1.02,
"learning_rate": 4.289965755197158e-05,
"loss": 4.1997,
"step": 433664
},
{
"epoch": 1.02,
"learning_rate": 4.289128798326479e-05,
"loss": 4.1931,
"step": 434176
},
{
"epoch": 1.02,
"learning_rate": 4.288290203575427e-05,
"loss": 4.2101,
"step": 434688
},
{
"epoch": 1.02,
"learning_rate": 4.287451608824375e-05,
"loss": 4.1849,
"step": 435200
},
{
"epoch": 1.02,
"learning_rate": 4.286613014073324e-05,
"loss": 4.2018,
"step": 435712
},
{
"epoch": 1.02,
"learning_rate": 4.285774419322272e-05,
"loss": 4.1855,
"step": 436224
},
{
"epoch": 1.02,
"learning_rate": 4.28493582457122e-05,
"loss": 4.2047,
"step": 436736
},
{
"epoch": 1.02,
"learning_rate": 4.284097229820168e-05,
"loss": 4.1967,
"step": 437248
},
{
"epoch": 1.02,
"learning_rate": 4.283258635069116e-05,
"loss": 4.1987,
"step": 437760
},
{
"epoch": 1.02,
"learning_rate": 4.282421678198437e-05,
"loss": 4.197,
"step": 438272
},
{
"epoch": 1.02,
"learning_rate": 4.281583083447385e-05,
"loss": 4.197,
"step": 438784
},
{
"epoch": 1.02,
"learning_rate": 4.280744488696333e-05,
"loss": 4.201,
"step": 439296
},
{
"epoch": 1.02,
"learning_rate": 4.279905893945281e-05,
"loss": 4.1934,
"step": 439808
},
{
"epoch": 1.02,
"learning_rate": 4.2790689370746016e-05,
"loss": 4.1993,
"step": 440320
},
{
"epoch": 1.02,
"learning_rate": 4.2782303423235496e-05,
"loss": 4.2137,
"step": 440832
},
{
"epoch": 1.02,
"learning_rate": 4.2773917475724976e-05,
"loss": 4.1968,
"step": 441344
},
{
"epoch": 1.02,
"learning_rate": 4.2765531528214456e-05,
"loss": 4.1916,
"step": 441856
},
{
"epoch": 1.02,
"learning_rate": 4.2757145580703936e-05,
"loss": 4.1966,
"step": 442368
},
{
"epoch": 1.02,
"learning_rate": 4.274879239080088e-05,
"loss": 4.1965,
"step": 442880
},
{
"epoch": 1.02,
"learning_rate": 4.274040644329036e-05,
"loss": 4.1901,
"step": 443392
},
{
"epoch": 1.02,
"learning_rate": 4.273202049577984e-05,
"loss": 4.2001,
"step": 443904
},
{
"epoch": 1.02,
"learning_rate": 4.272363454826932e-05,
"loss": 4.1848,
"step": 444416
},
{
"epoch": 1.02,
"learning_rate": 4.27152486007588e-05,
"loss": 4.2036,
"step": 444928
},
{
"epoch": 1.02,
"learning_rate": 4.270686265324828e-05,
"loss": 4.2016,
"step": 445440
},
{
"epoch": 1.02,
"learning_rate": 4.269847670573776e-05,
"loss": 4.1941,
"step": 445952
},
{
"epoch": 1.02,
"learning_rate": 4.269009075822724e-05,
"loss": 4.1848,
"step": 446464
},
{
"epoch": 1.02,
"learning_rate": 4.2681704810716714e-05,
"loss": 4.1911,
"step": 446976
},
{
"epoch": 1.02,
"learning_rate": 4.267333524200993e-05,
"loss": 4.1908,
"step": 447488
},
{
"epoch": 1.02,
"learning_rate": 4.2664965673303146e-05,
"loss": 4.2014,
"step": 448000
},
{
"epoch": 1.02,
"learning_rate": 4.2656579725792626e-05,
"loss": 4.197,
"step": 448512
},
{
"epoch": 1.02,
"learning_rate": 4.2648193778282105e-05,
"loss": 4.2002,
"step": 449024
},
{
"epoch": 1.02,
"learning_rate": 4.2639807830771585e-05,
"loss": 4.1769,
"step": 449536
},
{
"epoch": 1.02,
"learning_rate": 4.2631421883261065e-05,
"loss": 4.1984,
"step": 450048
},
{
"epoch": 1.02,
"learning_rate": 4.2623035935750545e-05,
"loss": 4.1925,
"step": 450560
},
{
"epoch": 1.02,
"learning_rate": 4.261464998824002e-05,
"loss": 4.2024,
"step": 451072
},
{
"epoch": 1.02,
"learning_rate": 4.26062640407295e-05,
"loss": 4.1827,
"step": 451584
},
{
"epoch": 1.02,
"learning_rate": 4.259787809321898e-05,
"loss": 4.2044,
"step": 452096
},
{
"epoch": 1.02,
"learning_rate": 4.258950852451219e-05,
"loss": 4.1923,
"step": 452608
},
{
"epoch": 1.02,
"learning_rate": 4.258112257700167e-05,
"loss": 4.1999,
"step": 453120
},
{
"epoch": 1.02,
"learning_rate": 4.257273662949115e-05,
"loss": 4.1862,
"step": 453632
},
{
"epoch": 1.02,
"learning_rate": 4.256435068198063e-05,
"loss": 4.2008,
"step": 454144
},
{
"epoch": 1.02,
"learning_rate": 4.255598111327384e-05,
"loss": 4.1775,
"step": 454656
},
{
"epoch": 1.02,
"learning_rate": 4.254759516576332e-05,
"loss": 4.1944,
"step": 455168
},
{
"epoch": 1.02,
"learning_rate": 4.253922559705654e-05,
"loss": 4.1913,
"step": 455680
},
{
"epoch": 1.02,
"learning_rate": 4.253083964954602e-05,
"loss": 4.1855,
"step": 456192
},
{
"epoch": 1.02,
"learning_rate": 4.252245370203549e-05,
"loss": 4.1901,
"step": 456704
},
{
"epoch": 1.02,
"learning_rate": 4.251406775452497e-05,
"loss": 4.1863,
"step": 457216
},
{
"epoch": 1.02,
"learning_rate": 4.250568180701445e-05,
"loss": 4.1925,
"step": 457728
},
{
"epoch": 1.03,
"eval_loss": 4.186344623565674,
"eval_runtime": 295.7915,
"eval_samples_per_second": 1290.067,
"eval_steps_per_second": 40.316,
"step": 457920
},
{
"epoch": 0.0,
"learning_rate": 4.249729585950393e-05,
"loss": 4.1873,
"step": 458240
},
{
"epoch": 0.0,
"learning_rate": 4.248890991199341e-05,
"loss": 4.1771,
"step": 458752
},
{
"epoch": 0.0,
"learning_rate": 4.248052396448289e-05,
"loss": 4.1971,
"step": 459264
},
{
"epoch": 0.0,
"learning_rate": 4.247213801697237e-05,
"loss": 4.1839,
"step": 459776
},
{
"epoch": 0.0,
"learning_rate": 4.246375206946185e-05,
"loss": 4.1935,
"step": 460288
},
{
"epoch": 0.0,
"learning_rate": 4.245536612195133e-05,
"loss": 4.1861,
"step": 460800
},
{
"epoch": 0.0,
"learning_rate": 4.244698017444081e-05,
"loss": 4.1891,
"step": 461312
},
{
"epoch": 0.0,
"learning_rate": 4.243859422693029e-05,
"loss": 4.1887,
"step": 461824
},
{
"epoch": 0.0,
"learning_rate": 4.243020827941978e-05,
"loss": 4.1877,
"step": 462336
},
{
"epoch": 0.0,
"learning_rate": 4.242182233190926e-05,
"loss": 4.1857,
"step": 462848
},
{
"epoch": 0.0,
"learning_rate": 4.241343638439873e-05,
"loss": 4.1898,
"step": 463360
},
{
"epoch": 0.0,
"learning_rate": 4.240505043688821e-05,
"loss": 4.1909,
"step": 463872
},
{
"epoch": 0.0,
"learning_rate": 4.239668086818143e-05,
"loss": 4.1848,
"step": 464384
},
{
"epoch": 0.0,
"learning_rate": 4.238829492067091e-05,
"loss": 4.1811,
"step": 464896
},
{
"epoch": 0.0,
"learning_rate": 4.237990897316038e-05,
"loss": 4.1851,
"step": 465408
},
{
"epoch": 0.0,
"learning_rate": 4.237152302564986e-05,
"loss": 4.1675,
"step": 465920
},
{
"epoch": 0.0,
"learning_rate": 4.236313707813934e-05,
"loss": 4.1846,
"step": 466432
},
{
"epoch": 0.0,
"learning_rate": 4.235475113062882e-05,
"loss": 4.1834,
"step": 466944
},
{
"epoch": 0.0,
"learning_rate": 4.23463651831183e-05,
"loss": 4.1798,
"step": 467456
},
{
"epoch": 0.0,
"learning_rate": 4.233797923560778e-05,
"loss": 4.2011,
"step": 467968
},
{
"epoch": 0.0,
"learning_rate": 4.2329609666900996e-05,
"loss": 4.1919,
"step": 468480
},
{
"epoch": 0.0,
"learning_rate": 4.2321223719390476e-05,
"loss": 4.1953,
"step": 468992
},
{
"epoch": 0.0,
"learning_rate": 4.2312837771879956e-05,
"loss": 4.1826,
"step": 469504
},
{
"epoch": 0.0,
"learning_rate": 4.2304451824369436e-05,
"loss": 4.1869,
"step": 470016
},
{
"epoch": 0.0,
"learning_rate": 4.2296082255662645e-05,
"loss": 4.1851,
"step": 470528
},
{
"epoch": 0.0,
"learning_rate": 4.2287696308152125e-05,
"loss": 4.1827,
"step": 471040
},
{
"epoch": 0.0,
"learning_rate": 4.2279310360641605e-05,
"loss": 4.1805,
"step": 471552
},
{
"epoch": 0.0,
"learning_rate": 4.2270924413131085e-05,
"loss": 4.1816,
"step": 472064
},
{
"epoch": 0.0,
"learning_rate": 4.2262538465620565e-05,
"loss": 4.1739,
"step": 472576
},
{
"epoch": 0.0,
"learning_rate": 4.2254152518110045e-05,
"loss": 4.1775,
"step": 473088
},
{
"epoch": 0.01,
"learning_rate": 4.2245782949403254e-05,
"loss": 4.177,
"step": 473600
},
{
"epoch": 0.01,
"learning_rate": 4.2237397001892734e-05,
"loss": 4.1876,
"step": 474112
},
{
"epoch": 0.01,
"learning_rate": 4.2229011054382214e-05,
"loss": 4.1812,
"step": 474624
},
{
"epoch": 0.01,
"learning_rate": 4.22206251068717e-05,
"loss": 4.1897,
"step": 475136
},
{
"epoch": 0.01,
"learning_rate": 4.221223915936118e-05,
"loss": 4.1701,
"step": 475648
},
{
"epoch": 0.01,
"learning_rate": 4.220386959065439e-05,
"loss": 4.1757,
"step": 476160
},
{
"epoch": 0.01,
"learning_rate": 4.219548364314387e-05,
"loss": 4.1787,
"step": 476672
},
{
"epoch": 0.01,
"learning_rate": 4.218709769563335e-05,
"loss": 4.1665,
"step": 477184
},
{
"epoch": 0.01,
"learning_rate": 4.217871174812283e-05,
"loss": 4.1757,
"step": 477696
},
{
"epoch": 0.01,
"learning_rate": 4.217032580061231e-05,
"loss": 4.1699,
"step": 478208
},
{
"epoch": 0.01,
"learning_rate": 4.216193985310179e-05,
"loss": 4.1786,
"step": 478720
},
{
"epoch": 0.01,
"learning_rate": 4.215355390559126e-05,
"loss": 4.1803,
"step": 479232
},
{
"epoch": 0.01,
"learning_rate": 4.214516795808074e-05,
"loss": 4.1771,
"step": 479744
},
{
"epoch": 0.01,
"learning_rate": 4.213679838937396e-05,
"loss": 4.1721,
"step": 480256
},
{
"epoch": 0.01,
"learning_rate": 4.212842882066717e-05,
"loss": 4.1844,
"step": 480768
},
{
"epoch": 0.01,
"learning_rate": 4.212004287315665e-05,
"loss": 4.1696,
"step": 481280
},
{
"epoch": 0.01,
"learning_rate": 4.2111656925646134e-05,
"loss": 4.1813,
"step": 481792
},
{
"epoch": 0.01,
"learning_rate": 4.2103270978135614e-05,
"loss": 4.1731,
"step": 482304
},
{
"epoch": 0.01,
"learning_rate": 4.2094901409428823e-05,
"loss": 4.1485,
"step": 482816
},
{
"epoch": 0.01,
"learning_rate": 4.20865154619183e-05,
"loss": 4.1941,
"step": 483328
},
{
"epoch": 0.01,
"learning_rate": 4.207812951440778e-05,
"loss": 4.1642,
"step": 483840
},
{
"epoch": 0.01,
"learning_rate": 4.206974356689726e-05,
"loss": 4.1759,
"step": 484352
},
{
"epoch": 0.01,
"learning_rate": 4.2061357619386736e-05,
"loss": 4.158,
"step": 484864
},
{
"epoch": 0.01,
"learning_rate": 4.2052971671876216e-05,
"loss": 4.1658,
"step": 485376
},
{
"epoch": 0.01,
"learning_rate": 4.204460210316943e-05,
"loss": 4.1623,
"step": 485888
},
{
"epoch": 0.01,
"learning_rate": 4.203621615565891e-05,
"loss": 4.1718,
"step": 486400
},
{
"epoch": 0.01,
"learning_rate": 4.2027830208148385e-05,
"loss": 4.1734,
"step": 486912
},
{
"epoch": 0.01,
"learning_rate": 4.201944426063787e-05,
"loss": 4.1727,
"step": 487424
},
{
"epoch": 0.01,
"learning_rate": 4.201105831312735e-05,
"loss": 4.1816,
"step": 487936
},
{
"epoch": 0.01,
"learning_rate": 4.200268874442057e-05,
"loss": 4.1647,
"step": 488448
},
{
"epoch": 0.01,
"learning_rate": 4.199430279691004e-05,
"loss": 4.1533,
"step": 488960
},
{
"epoch": 0.01,
"learning_rate": 4.198591684939952e-05,
"loss": 4.1795,
"step": 489472
},
{
"epoch": 0.01,
"learning_rate": 4.1977530901889e-05,
"loss": 4.1547,
"step": 489984
},
{
"epoch": 0.01,
"learning_rate": 4.196914495437848e-05,
"loss": 4.1531,
"step": 490496
},
{
"epoch": 0.01,
"learning_rate": 4.196075900686796e-05,
"loss": 4.1768,
"step": 491008
},
{
"epoch": 0.01,
"learning_rate": 4.195237305935744e-05,
"loss": 4.1741,
"step": 491520
},
{
"epoch": 0.01,
"learning_rate": 4.194398711184692e-05,
"loss": 4.1588,
"step": 492032
},
{
"epoch": 0.01,
"learning_rate": 4.193561754314013e-05,
"loss": 4.1659,
"step": 492544
},
{
"epoch": 0.01,
"learning_rate": 4.192723159562961e-05,
"loss": 4.1511,
"step": 493056
},
{
"epoch": 0.01,
"learning_rate": 4.191884564811909e-05,
"loss": 4.1626,
"step": 493568
},
{
"epoch": 0.01,
"learning_rate": 4.191045970060857e-05,
"loss": 4.1716,
"step": 494080
},
{
"epoch": 0.01,
"learning_rate": 4.1902090131901786e-05,
"loss": 4.1716,
"step": 494592
},
{
"epoch": 0.01,
"learning_rate": 4.1893704184391266e-05,
"loss": 4.1728,
"step": 495104
},
{
"epoch": 0.01,
"learning_rate": 4.1885318236880746e-05,
"loss": 4.169,
"step": 495616
},
{
"epoch": 0.01,
"learning_rate": 4.1876932289370226e-05,
"loss": 4.1791,
"step": 496128
},
{
"epoch": 0.01,
"learning_rate": 4.1868562720663435e-05,
"loss": 4.1556,
"step": 496640
},
{
"epoch": 0.01,
"learning_rate": 4.1860176773152915e-05,
"loss": 4.1719,
"step": 497152
},
{
"epoch": 0.01,
"learning_rate": 4.1851807204446124e-05,
"loss": 4.1627,
"step": 497664
},
{
"epoch": 0.01,
"learning_rate": 4.1843421256935604e-05,
"loss": 4.1515,
"step": 498176
},
{
"epoch": 0.01,
"learning_rate": 4.1835035309425084e-05,
"loss": 4.1689,
"step": 498688
},
{
"epoch": 0.01,
"learning_rate": 4.1826649361914564e-05,
"loss": 4.172,
"step": 499200
},
{
"epoch": 0.01,
"learning_rate": 4.1818263414404044e-05,
"loss": 4.1671,
"step": 499712
},
{
"epoch": 0.01,
"learning_rate": 4.1809877466893524e-05,
"loss": 4.1663,
"step": 500224
},
{
"epoch": 0.01,
"learning_rate": 4.180149151938301e-05,
"loss": 4.1506,
"step": 500736
},
{
"epoch": 0.01,
"learning_rate": 4.179310557187249e-05,
"loss": 4.1549,
"step": 501248
},
{
"epoch": 0.01,
"learning_rate": 4.17847360031657e-05,
"loss": 4.1654,
"step": 501760
},
{
"epoch": 0.01,
"learning_rate": 4.177635005565518e-05,
"loss": 4.1691,
"step": 502272
},
{
"epoch": 0.01,
"learning_rate": 4.176796410814466e-05,
"loss": 4.1583,
"step": 502784
},
{
"epoch": 0.01,
"learning_rate": 4.175957816063414e-05,
"loss": 4.1689,
"step": 503296
},
{
"epoch": 0.02,
"learning_rate": 4.175119221312362e-05,
"loss": 4.1484,
"step": 503808
},
{
"epoch": 0.02,
"learning_rate": 4.174282264441683e-05,
"loss": 4.1646,
"step": 504320
},
{
"epoch": 0.02,
"learning_rate": 4.173443669690631e-05,
"loss": 4.1571,
"step": 504832
},
{
"epoch": 0.02,
"learning_rate": 4.172605074939579e-05,
"loss": 4.1604,
"step": 505344
},
{
"epoch": 0.02,
"learning_rate": 4.1717681180689e-05,
"loss": 4.1708,
"step": 505856
},
{
"epoch": 0.02,
"learning_rate": 4.170929523317848e-05,
"loss": 4.1713,
"step": 506368
},
{
"epoch": 0.02,
"learning_rate": 4.1700909285667964e-05,
"loss": 4.1726,
"step": 506880
},
{
"epoch": 0.02,
"learning_rate": 4.169253971696117e-05,
"loss": 4.1489,
"step": 507392
},
{
"epoch": 0.02,
"learning_rate": 4.168415376945065e-05,
"loss": 4.1617,
"step": 507904
},
{
"epoch": 0.02,
"learning_rate": 4.167576782194013e-05,
"loss": 4.1547,
"step": 508416
},
{
"epoch": 0.02,
"learning_rate": 4.166738187442961e-05,
"loss": 4.1645,
"step": 508928
},
{
"epoch": 0.02,
"learning_rate": 4.165899592691909e-05,
"loss": 4.1573,
"step": 509440
},
{
"epoch": 0.02,
"learning_rate": 4.16506263582123e-05,
"loss": 4.1609,
"step": 509952
},
{
"epoch": 0.02,
"learning_rate": 4.164224041070178e-05,
"loss": 4.1511,
"step": 510464
},
{
"epoch": 0.02,
"learning_rate": 4.163385446319126e-05,
"loss": 4.163,
"step": 510976
},
{
"epoch": 0.02,
"learning_rate": 4.162546851568074e-05,
"loss": 4.1478,
"step": 511488
},
{
"epoch": 0.02,
"learning_rate": 4.161708256817022e-05,
"loss": 4.1592,
"step": 512000
},
{
"epoch": 0.02,
"learning_rate": 4.16086966206597e-05,
"loss": 4.144,
"step": 512512
},
{
"epoch": 0.02,
"learning_rate": 4.160031067314918e-05,
"loss": 4.1635,
"step": 513024
},
{
"epoch": 0.02,
"learning_rate": 4.159192472563866e-05,
"loss": 4.1536,
"step": 513536
},
{
"epoch": 0.02,
"learning_rate": 4.158353877812814e-05,
"loss": 4.1571,
"step": 514048
},
{
"epoch": 0.02,
"learning_rate": 4.157515283061762e-05,
"loss": 4.152,
"step": 514560
},
{
"epoch": 0.02,
"learning_rate": 4.156678326191083e-05,
"loss": 4.1586,
"step": 515072
},
{
"epoch": 0.02,
"learning_rate": 4.155839731440031e-05,
"loss": 4.1587,
"step": 515584
},
{
"epoch": 0.02,
"learning_rate": 4.155001136688979e-05,
"loss": 4.1503,
"step": 516096
},
{
"epoch": 0.02,
"learning_rate": 4.154162541937927e-05,
"loss": 4.1605,
"step": 516608
},
{
"epoch": 0.02,
"learning_rate": 4.153323947186875e-05,
"loss": 4.1672,
"step": 517120
},
{
"epoch": 0.02,
"learning_rate": 4.152486990316196e-05,
"loss": 4.1602,
"step": 517632
},
{
"epoch": 0.02,
"learning_rate": 4.151648395565144e-05,
"loss": 4.1515,
"step": 518144
},
{
"epoch": 0.02,
"learning_rate": 4.150809800814092e-05,
"loss": 4.1501,
"step": 518656
},
{
"epoch": 0.02,
"learning_rate": 4.14997120606304e-05,
"loss": 4.1591,
"step": 519168
},
{
"epoch": 0.02,
"learning_rate": 4.149132611311988e-05,
"loss": 4.1477,
"step": 519680
},
{
"epoch": 0.02,
"learning_rate": 4.1482940165609366e-05,
"loss": 4.1597,
"step": 520192
},
{
"epoch": 0.02,
"learning_rate": 4.1474554218098846e-05,
"loss": 4.1429,
"step": 520704
},
{
"epoch": 0.02,
"learning_rate": 4.1466184649392055e-05,
"loss": 4.1622,
"step": 521216
},
{
"epoch": 0.02,
"learning_rate": 4.1457798701881535e-05,
"loss": 4.1586,
"step": 521728
},
{
"epoch": 0.02,
"learning_rate": 4.1449412754371015e-05,
"loss": 4.1548,
"step": 522240
},
{
"epoch": 0.02,
"learning_rate": 4.1441026806860495e-05,
"loss": 4.1445,
"step": 522752
},
{
"epoch": 0.02,
"learning_rate": 4.1432657238153704e-05,
"loss": 4.1495,
"step": 523264
},
{
"epoch": 0.02,
"learning_rate": 4.1424271290643184e-05,
"loss": 4.148,
"step": 523776
},
{
"epoch": 0.02,
"learning_rate": 4.1415885343132664e-05,
"loss": 4.1611,
"step": 524288
},
{
"epoch": 0.02,
"learning_rate": 4.1407499395622144e-05,
"loss": 4.1556,
"step": 524800
},
{
"epoch": 0.02,
"learning_rate": 4.1399113448111624e-05,
"loss": 4.1546,
"step": 525312
},
{
"epoch": 0.02,
"learning_rate": 4.1390727500601104e-05,
"loss": 4.1381,
"step": 525824
},
{
"epoch": 0.02,
"learning_rate": 4.1382341553090584e-05,
"loss": 4.1601,
"step": 526336
},
{
"epoch": 0.02,
"learning_rate": 4.1373955605580064e-05,
"loss": 4.1507,
"step": 526848
},
{
"epoch": 0.02,
"learning_rate": 4.1365569658069544e-05,
"loss": 4.1632,
"step": 527360
},
{
"epoch": 0.02,
"learning_rate": 4.135720008936276e-05,
"loss": 4.1427,
"step": 527872
},
{
"epoch": 0.02,
"learning_rate": 4.134881414185223e-05,
"loss": 4.1608,
"step": 528384
},
{
"epoch": 0.02,
"learning_rate": 4.134042819434171e-05,
"loss": 4.1503,
"step": 528896
},
{
"epoch": 0.02,
"learning_rate": 4.133204224683119e-05,
"loss": 4.1652,
"step": 529408
},
{
"epoch": 0.02,
"learning_rate": 4.132367267812441e-05,
"loss": 4.1447,
"step": 529920
},
{
"epoch": 0.02,
"learning_rate": 4.131528673061388e-05,
"loss": 4.1556,
"step": 530432
},
{
"epoch": 0.02,
"learning_rate": 4.130690078310336e-05,
"loss": 4.1405,
"step": 530944
},
{
"epoch": 0.02,
"learning_rate": 4.129851483559284e-05,
"loss": 4.1525,
"step": 531456
},
{
"epoch": 0.02,
"learning_rate": 4.129014526688606e-05,
"loss": 4.1522,
"step": 531968
},
{
"epoch": 0.02,
"learning_rate": 4.128175931937554e-05,
"loss": 4.1418,
"step": 532480
},
{
"epoch": 0.02,
"learning_rate": 4.127337337186502e-05,
"loss": 4.1538,
"step": 532992
},
{
"epoch": 0.02,
"learning_rate": 4.126500380315823e-05,
"loss": 4.142,
"step": 533504
},
{
"epoch": 0.02,
"learning_rate": 4.1256617855647707e-05,
"loss": 4.1569,
"step": 534016
},
{
"epoch": 0.03,
"eval_loss": 4.1547136306762695,
"eval_runtime": 302.437,
"eval_samples_per_second": 1261.721,
"eval_steps_per_second": 39.43,
"step": 534240
},
{
"epoch": 1.0,
"learning_rate": 4.1248231908137186e-05,
"loss": 4.149,
"step": 534528
},
{
"epoch": 1.0,
"learning_rate": 4.1239845960626666e-05,
"loss": 4.1383,
"step": 535040
},
{
"epoch": 1.0,
"learning_rate": 4.1231460013116146e-05,
"loss": 4.1542,
"step": 535552
},
{
"epoch": 1.0,
"learning_rate": 4.1223074065605626e-05,
"loss": 4.1434,
"step": 536064
},
{
"epoch": 1.0,
"learning_rate": 4.1214704496898835e-05,
"loss": 4.1552,
"step": 536576
},
{
"epoch": 1.0,
"learning_rate": 4.1206318549388315e-05,
"loss": 4.1486,
"step": 537088
},
{
"epoch": 1.0,
"learning_rate": 4.1197932601877795e-05,
"loss": 4.1503,
"step": 537600
},
{
"epoch": 1.0,
"learning_rate": 4.1189546654367275e-05,
"loss": 4.1504,
"step": 538112
},
{
"epoch": 1.0,
"learning_rate": 4.1181160706856755e-05,
"loss": 4.1442,
"step": 538624
},
{
"epoch": 1.0,
"learning_rate": 4.117277475934624e-05,
"loss": 4.1488,
"step": 539136
},
{
"epoch": 1.0,
"learning_rate": 4.116438881183572e-05,
"loss": 4.1516,
"step": 539648
},
{
"epoch": 1.0,
"learning_rate": 4.11560028643252e-05,
"loss": 4.1527,
"step": 540160
},
{
"epoch": 1.0,
"learning_rate": 4.114763329561841e-05,
"loss": 4.1484,
"step": 540672
},
{
"epoch": 1.0,
"learning_rate": 4.113924734810789e-05,
"loss": 4.1389,
"step": 541184
},
{
"epoch": 1.0,
"learning_rate": 4.113086140059737e-05,
"loss": 4.1417,
"step": 541696
},
{
"epoch": 1.0,
"learning_rate": 4.112247545308685e-05,
"loss": 4.1324,
"step": 542208
},
{
"epoch": 1.0,
"learning_rate": 4.111408950557633e-05,
"loss": 4.1424,
"step": 542720
},
{
"epoch": 1.0,
"learning_rate": 4.110571993686954e-05,
"loss": 4.1463,
"step": 543232
},
{
"epoch": 1.0,
"learning_rate": 4.109733398935902e-05,
"loss": 4.1375,
"step": 543744
},
{
"epoch": 1.0,
"learning_rate": 4.10889480418485e-05,
"loss": 4.161,
"step": 544256
},
{
"epoch": 1.0,
"learning_rate": 4.108056209433798e-05,
"loss": 4.1526,
"step": 544768
},
{
"epoch": 1.0,
"learning_rate": 4.1072192525631196e-05,
"loss": 4.1553,
"step": 545280
},
{
"epoch": 1.0,
"learning_rate": 4.1063806578120676e-05,
"loss": 4.1457,
"step": 545792
},
{
"epoch": 1.0,
"learning_rate": 4.1055420630610156e-05,
"loss": 4.1437,
"step": 546304
},
{
"epoch": 1.0,
"learning_rate": 4.1047034683099636e-05,
"loss": 4.1516,
"step": 546816
},
{
"epoch": 1.0,
"learning_rate": 4.1038648735589115e-05,
"loss": 4.1409,
"step": 547328
},
{
"epoch": 1.0,
"learning_rate": 4.1030262788078595e-05,
"loss": 4.141,
"step": 547840
},
{
"epoch": 1.0,
"learning_rate": 4.102187684056807e-05,
"loss": 4.1477,
"step": 548352
},
{
"epoch": 1.0,
"learning_rate": 4.101349089305755e-05,
"loss": 4.1316,
"step": 548864
},
{
"epoch": 1.0,
"learning_rate": 4.1005121324350764e-05,
"loss": 4.1375,
"step": 549376
},
{
"epoch": 1.01,
"learning_rate": 4.0996735376840244e-05,
"loss": 4.1408,
"step": 549888
},
{
"epoch": 1.01,
"learning_rate": 4.098834942932972e-05,
"loss": 4.1446,
"step": 550400
},
{
"epoch": 1.01,
"learning_rate": 4.09799634818192e-05,
"loss": 4.1462,
"step": 550912
},
{
"epoch": 1.01,
"learning_rate": 4.0971593913112413e-05,
"loss": 4.1492,
"step": 551424
},
{
"epoch": 1.01,
"learning_rate": 4.096320796560189e-05,
"loss": 4.1337,
"step": 551936
},
{
"epoch": 1.01,
"learning_rate": 4.095483839689511e-05,
"loss": 4.1366,
"step": 552448
},
{
"epoch": 1.01,
"learning_rate": 4.094645244938459e-05,
"loss": 4.1431,
"step": 552960
},
{
"epoch": 1.01,
"learning_rate": 4.093806650187407e-05,
"loss": 4.1288,
"step": 553472
},
{
"epoch": 1.01,
"learning_rate": 4.092968055436354e-05,
"loss": 4.1388,
"step": 553984
},
{
"epoch": 1.01,
"learning_rate": 4.092129460685302e-05,
"loss": 4.129,
"step": 554496
},
{
"epoch": 1.01,
"learning_rate": 4.09129086593425e-05,
"loss": 4.1416,
"step": 555008
},
{
"epoch": 1.01,
"learning_rate": 4.090452271183198e-05,
"loss": 4.1374,
"step": 555520
},
{
"epoch": 1.01,
"learning_rate": 4.089613676432146e-05,
"loss": 4.1397,
"step": 556032
},
{
"epoch": 1.01,
"learning_rate": 4.088776719561467e-05,
"loss": 4.1395,
"step": 556544
},
{
"epoch": 1.01,
"learning_rate": 4.087938124810415e-05,
"loss": 4.1419,
"step": 557056
},
{
"epoch": 1.01,
"learning_rate": 4.087099530059363e-05,
"loss": 4.1322,
"step": 557568
},
{
"epoch": 1.01,
"learning_rate": 4.086260935308311e-05,
"loss": 4.144,
"step": 558080
},
{
"epoch": 1.01,
"learning_rate": 4.085423978437633e-05,
"loss": 4.135,
"step": 558592
},
{
"epoch": 1.01,
"learning_rate": 4.084585383686581e-05,
"loss": 4.114,
"step": 559104
},
{
"epoch": 1.01,
"learning_rate": 4.083746788935529e-05,
"loss": 4.1526,
"step": 559616
},
{
"epoch": 1.01,
"learning_rate": 4.082908194184477e-05,
"loss": 4.1268,
"step": 560128
},
{
"epoch": 1.01,
"learning_rate": 4.0820712373137976e-05,
"loss": 4.1402,
"step": 560640
},
{
"epoch": 1.01,
"learning_rate": 4.0812326425627456e-05,
"loss": 4.1263,
"step": 561152
},
{
"epoch": 1.01,
"learning_rate": 4.0803956856920665e-05,
"loss": 4.1252,
"step": 561664
},
{
"epoch": 1.01,
"learning_rate": 4.0795570909410145e-05,
"loss": 4.1228,
"step": 562176
},
{
"epoch": 1.01,
"learning_rate": 4.0787184961899625e-05,
"loss": 4.1325,
"step": 562688
},
{
"epoch": 1.01,
"learning_rate": 4.0778799014389105e-05,
"loss": 4.1383,
"step": 563200
},
{
"epoch": 1.01,
"learning_rate": 4.077042944568232e-05,
"loss": 4.1322,
"step": 563712
},
{
"epoch": 1.01,
"learning_rate": 4.07620434981718e-05,
"loss": 4.1469,
"step": 564224
},
{
"epoch": 1.01,
"learning_rate": 4.075365755066128e-05,
"loss": 4.1342,
"step": 564736
},
{
"epoch": 1.01,
"learning_rate": 4.074527160315076e-05,
"loss": 4.1133,
"step": 565248
},
{
"epoch": 1.01,
"learning_rate": 4.073688565564024e-05,
"loss": 4.1385,
"step": 565760
},
{
"epoch": 1.01,
"learning_rate": 4.072851608693345e-05,
"loss": 4.1204,
"step": 566272
},
{
"epoch": 1.01,
"learning_rate": 4.072013013942293e-05,
"loss": 4.1148,
"step": 566784
},
{
"epoch": 1.01,
"learning_rate": 4.071174419191241e-05,
"loss": 4.1432,
"step": 567296
},
{
"epoch": 1.01,
"learning_rate": 4.070335824440189e-05,
"loss": 4.1353,
"step": 567808
},
{
"epoch": 1.01,
"learning_rate": 4.069497229689137e-05,
"loss": 4.1219,
"step": 568320
},
{
"epoch": 1.01,
"learning_rate": 4.068658634938085e-05,
"loss": 4.1296,
"step": 568832
},
{
"epoch": 1.01,
"learning_rate": 4.067820040187033e-05,
"loss": 4.1166,
"step": 569344
},
{
"epoch": 1.01,
"learning_rate": 4.066981445435981e-05,
"loss": 4.1258,
"step": 569856
},
{
"epoch": 1.01,
"learning_rate": 4.066144488565302e-05,
"loss": 4.1336,
"step": 570368
},
{
"epoch": 1.01,
"learning_rate": 4.0653058938142505e-05,
"loss": 4.1335,
"step": 570880
},
{
"epoch": 1.01,
"learning_rate": 4.0644672990631985e-05,
"loss": 4.1376,
"step": 571392
},
{
"epoch": 1.01,
"learning_rate": 4.0636287043121465e-05,
"loss": 4.1309,
"step": 571904
},
{
"epoch": 1.01,
"learning_rate": 4.0627901095610945e-05,
"loss": 4.145,
"step": 572416
},
{
"epoch": 1.01,
"learning_rate": 4.0619531526904154e-05,
"loss": 4.1183,
"step": 572928
},
{
"epoch": 1.01,
"learning_rate": 4.0611145579393634e-05,
"loss": 4.138,
"step": 573440
},
{
"epoch": 1.01,
"learning_rate": 4.0602759631883114e-05,
"loss": 4.1245,
"step": 573952
},
{
"epoch": 1.01,
"learning_rate": 4.0594373684372594e-05,
"loss": 4.1215,
"step": 574464
},
{
"epoch": 1.01,
"learning_rate": 4.0585987736862074e-05,
"loss": 4.1315,
"step": 574976
},
{
"epoch": 1.01,
"learning_rate": 4.0577601789351554e-05,
"loss": 4.1345,
"step": 575488
},
{
"epoch": 1.01,
"learning_rate": 4.056923222064476e-05,
"loss": 4.1309,
"step": 576000
},
{
"epoch": 1.01,
"learning_rate": 4.056084627313424e-05,
"loss": 4.135,
"step": 576512
},
{
"epoch": 1.01,
"learning_rate": 4.055246032562372e-05,
"loss": 4.1113,
"step": 577024
},
{
"epoch": 1.01,
"learning_rate": 4.05440743781132e-05,
"loss": 4.1176,
"step": 577536
},
{
"epoch": 1.01,
"learning_rate": 4.053570480940642e-05,
"loss": 4.1291,
"step": 578048
},
{
"epoch": 1.01,
"learning_rate": 4.05273188618959e-05,
"loss": 4.1339,
"step": 578560
},
{
"epoch": 1.01,
"learning_rate": 4.051893291438538e-05,
"loss": 4.1246,
"step": 579072
},
{
"epoch": 1.01,
"learning_rate": 4.051054696687485e-05,
"loss": 4.1317,
"step": 579584
},
{
"epoch": 1.02,
"learning_rate": 4.050216101936433e-05,
"loss": 4.1138,
"step": 580096
},
{
"epoch": 1.02,
"learning_rate": 4.049377507185381e-05,
"loss": 4.1306,
"step": 580608
},
{
"epoch": 1.02,
"learning_rate": 4.048538912434329e-05,
"loss": 4.1221,
"step": 581120
},
{
"epoch": 1.02,
"learning_rate": 4.047700317683277e-05,
"loss": 4.1232,
"step": 581632
},
{
"epoch": 1.02,
"learning_rate": 4.046861722932225e-05,
"loss": 4.1352,
"step": 582144
},
{
"epoch": 1.02,
"learning_rate": 4.046024766061546e-05,
"loss": 4.1341,
"step": 582656
},
{
"epoch": 1.02,
"learning_rate": 4.045186171310494e-05,
"loss": 4.1384,
"step": 583168
},
{
"epoch": 1.02,
"learning_rate": 4.044347576559443e-05,
"loss": 4.1188,
"step": 583680
},
{
"epoch": 1.02,
"learning_rate": 4.043508981808391e-05,
"loss": 4.1239,
"step": 584192
},
{
"epoch": 1.02,
"learning_rate": 4.042670387057339e-05,
"loss": 4.121,
"step": 584704
},
{
"epoch": 1.02,
"learning_rate": 4.041831792306287e-05,
"loss": 4.1282,
"step": 585216
},
{
"epoch": 1.02,
"learning_rate": 4.040993197555235e-05,
"loss": 4.1213,
"step": 585728
},
{
"epoch": 1.02,
"learning_rate": 4.040154602804183e-05,
"loss": 4.1259,
"step": 586240
},
{
"epoch": 1.02,
"learning_rate": 4.039316008053131e-05,
"loss": 4.1194,
"step": 586752
},
{
"epoch": 1.02,
"learning_rate": 4.0384790511824516e-05,
"loss": 4.1228,
"step": 587264
},
{
"epoch": 1.02,
"learning_rate": 4.0376404564313996e-05,
"loss": 4.1189,
"step": 587776
},
{
"epoch": 1.02,
"learning_rate": 4.0368018616803476e-05,
"loss": 4.1194,
"step": 588288
},
{
"epoch": 1.02,
"learning_rate": 4.0359649048096685e-05,
"loss": 4.1073,
"step": 588800
},
{
"epoch": 1.02,
"learning_rate": 4.0351263100586165e-05,
"loss": 4.1281,
"step": 589312
},
{
"epoch": 1.02,
"learning_rate": 4.0342877153075645e-05,
"loss": 4.1211,
"step": 589824
},
{
"epoch": 1.02,
"learning_rate": 4.0334491205565125e-05,
"loss": 4.1229,
"step": 590336
},
{
"epoch": 1.02,
"learning_rate": 4.032612163685834e-05,
"loss": 4.1177,
"step": 590848
},
{
"epoch": 1.02,
"learning_rate": 4.031773568934782e-05,
"loss": 4.1237,
"step": 591360
},
{
"epoch": 1.02,
"learning_rate": 4.03093497418373e-05,
"loss": 4.1256,
"step": 591872
},
{
"epoch": 1.02,
"learning_rate": 4.030096379432678e-05,
"loss": 4.1161,
"step": 592384
},
{
"epoch": 1.02,
"learning_rate": 4.029257784681626e-05,
"loss": 4.1268,
"step": 592896
},
{
"epoch": 1.02,
"learning_rate": 4.028420827810947e-05,
"loss": 4.1323,
"step": 593408
},
{
"epoch": 1.02,
"learning_rate": 4.027582233059895e-05,
"loss": 4.1198,
"step": 593920
},
{
"epoch": 1.02,
"learning_rate": 4.026743638308843e-05,
"loss": 4.1244,
"step": 594432
},
{
"epoch": 1.02,
"learning_rate": 4.025905043557791e-05,
"loss": 4.1143,
"step": 594944
},
{
"epoch": 1.02,
"learning_rate": 4.025066448806738e-05,
"loss": 4.1208,
"step": 595456
},
{
"epoch": 1.02,
"learning_rate": 4.02422949193606e-05,
"loss": 4.1218,
"step": 595968
},
{
"epoch": 1.02,
"learning_rate": 4.023390897185008e-05,
"loss": 4.1245,
"step": 596480
},
{
"epoch": 1.02,
"learning_rate": 4.022552302433956e-05,
"loss": 4.1048,
"step": 596992
},
{
"epoch": 1.02,
"learning_rate": 4.021713707682904e-05,
"loss": 4.1275,
"step": 597504
},
{
"epoch": 1.02,
"learning_rate": 4.020875112931852e-05,
"loss": 4.1263,
"step": 598016
},
{
"epoch": 1.02,
"learning_rate": 4.0200365181808e-05,
"loss": 4.1225,
"step": 598528
},
{
"epoch": 1.02,
"learning_rate": 4.019197923429748e-05,
"loss": 4.1111,
"step": 599040
},
{
"epoch": 1.02,
"learning_rate": 4.018360966559069e-05,
"loss": 4.1165,
"step": 599552
},
{
"epoch": 1.02,
"learning_rate": 4.017522371808017e-05,
"loss": 4.1134,
"step": 600064
},
{
"epoch": 1.02,
"learning_rate": 4.016683777056965e-05,
"loss": 4.1262,
"step": 600576
},
{
"epoch": 1.02,
"learning_rate": 4.015845182305913e-05,
"loss": 4.1218,
"step": 601088
},
{
"epoch": 1.02,
"learning_rate": 4.015008225435234e-05,
"loss": 4.1247,
"step": 601600
},
{
"epoch": 1.02,
"learning_rate": 4.0141696306841817e-05,
"loss": 4.1028,
"step": 602112
},
{
"epoch": 1.02,
"learning_rate": 4.0133310359331297e-05,
"loss": 4.126,
"step": 602624
},
{
"epoch": 1.02,
"learning_rate": 4.012492441182078e-05,
"loss": 4.1179,
"step": 603136
},
{
"epoch": 1.02,
"learning_rate": 4.011653846431026e-05,
"loss": 4.1294,
"step": 603648
},
{
"epoch": 1.02,
"learning_rate": 4.010815251679974e-05,
"loss": 4.1129,
"step": 604160
},
{
"epoch": 1.02,
"learning_rate": 4.009976656928922e-05,
"loss": 4.1225,
"step": 604672
},
{
"epoch": 1.02,
"learning_rate": 4.00913806217787e-05,
"loss": 4.1174,
"step": 605184
},
{
"epoch": 1.02,
"learning_rate": 4.008301105307191e-05,
"loss": 4.134,
"step": 605696
},
{
"epoch": 1.02,
"learning_rate": 4.007462510556139e-05,
"loss": 4.1127,
"step": 606208
},
{
"epoch": 1.02,
"learning_rate": 4.006623915805087e-05,
"loss": 4.1201,
"step": 606720
},
{
"epoch": 1.02,
"learning_rate": 4.005786958934408e-05,
"loss": 4.1115,
"step": 607232
},
{
"epoch": 1.02,
"learning_rate": 4.004948364183356e-05,
"loss": 4.1199,
"step": 607744
},
{
"epoch": 1.02,
"learning_rate": 4.004109769432304e-05,
"loss": 4.1138,
"step": 608256
},
{
"epoch": 1.02,
"learning_rate": 4.003271174681252e-05,
"loss": 4.1107,
"step": 608768
},
{
"epoch": 1.02,
"learning_rate": 4.0024325799302e-05,
"loss": 4.1207,
"step": 609280
},
{
"epoch": 1.02,
"learning_rate": 4.001595623059522e-05,
"loss": 4.1057,
"step": 609792
},
{
"epoch": 1.02,
"learning_rate": 4.00075702830847e-05,
"loss": 4.1273,
"step": 610304
},
{
"epoch": 1.03,
"eval_loss": 4.128954887390137,
"eval_runtime": 309.3142,
"eval_samples_per_second": 1233.668,
"eval_steps_per_second": 38.553,
"step": 610560
},
{
"epoch": 0.0,
"learning_rate": 3.999918433557418e-05,
"loss": 4.1118,
"step": 610816
},
{
"epoch": 0.0,
"learning_rate": 3.999079838806366e-05,
"loss": 4.1076,
"step": 611328
},
{
"epoch": 0.0,
"learning_rate": 3.998241244055314e-05,
"loss": 4.1191,
"step": 611840
},
{
"epoch": 0.0,
"learning_rate": 3.997402649304262e-05,
"loss": 4.1133,
"step": 612352
},
{
"epoch": 0.0,
"learning_rate": 3.99656405455321e-05,
"loss": 4.1238,
"step": 612864
},
{
"epoch": 0.0,
"learning_rate": 3.9957254598021577e-05,
"loss": 4.1145,
"step": 613376
},
{
"epoch": 0.0,
"learning_rate": 3.994886865051105e-05,
"loss": 4.1167,
"step": 613888
},
{
"epoch": 0.0,
"learning_rate": 3.994048270300053e-05,
"loss": 4.1186,
"step": 614400
},
{
"epoch": 0.0,
"learning_rate": 3.993209675549001e-05,
"loss": 4.1105,
"step": 614912
},
{
"epoch": 0.0,
"learning_rate": 3.992371080797949e-05,
"loss": 4.1174,
"step": 615424
},
{
"epoch": 0.0,
"learning_rate": 3.991532486046897e-05,
"loss": 4.1184,
"step": 615936
},
{
"epoch": 0.0,
"learning_rate": 3.990693891295845e-05,
"loss": 4.1198,
"step": 616448
},
{
"epoch": 0.0,
"learning_rate": 3.9898569344251665e-05,
"loss": 4.1197,
"step": 616960
},
{
"epoch": 0.0,
"learning_rate": 3.9890183396741145e-05,
"loss": 4.1026,
"step": 617472
},
{
"epoch": 0.0,
"learning_rate": 3.9881797449230625e-05,
"loss": 4.1127,
"step": 617984
},
{
"epoch": 0.0,
"learning_rate": 3.9873411501720105e-05,
"loss": 4.0968,
"step": 618496
},
{
"epoch": 0.0,
"learning_rate": 3.9865025554209585e-05,
"loss": 4.1144,
"step": 619008
},
{
"epoch": 0.0,
"learning_rate": 3.9856639606699065e-05,
"loss": 4.1141,
"step": 619520
},
{
"epoch": 0.0,
"learning_rate": 3.9848253659188545e-05,
"loss": 4.1072,
"step": 620032
},
{
"epoch": 0.0,
"learning_rate": 3.9839867711678025e-05,
"loss": 4.1281,
"step": 620544
},
{
"epoch": 0.0,
"learning_rate": 3.9831481764167505e-05,
"loss": 4.1229,
"step": 621056
},
{
"epoch": 0.0,
"learning_rate": 3.9823095816656985e-05,
"loss": 4.1218,
"step": 621568
},
{
"epoch": 0.0,
"learning_rate": 3.981470986914646e-05,
"loss": 4.1169,
"step": 622080
},
{
"epoch": 0.0,
"learning_rate": 3.980632392163594e-05,
"loss": 4.1147,
"step": 622592
},
{
"epoch": 0.0,
"learning_rate": 3.9797954352929154e-05,
"loss": 4.1204,
"step": 623104
},
{
"epoch": 0.0,
"learning_rate": 3.9789568405418634e-05,
"loss": 4.1075,
"step": 623616
},
{
"epoch": 0.0,
"learning_rate": 3.9781182457908114e-05,
"loss": 4.1083,
"step": 624128
},
{
"epoch": 0.0,
"learning_rate": 3.977281288920133e-05,
"loss": 4.1153,
"step": 624640
},
{
"epoch": 0.0,
"learning_rate": 3.976442694169081e-05,
"loss": 4.1025,
"step": 625152
},
{
"epoch": 0.0,
"learning_rate": 3.975604099418029e-05,
"loss": 4.1048,
"step": 625664
},
{
"epoch": 0.01,
"learning_rate": 3.974765504666976e-05,
"loss": 4.1109,
"step": 626176
},
{
"epoch": 0.01,
"learning_rate": 3.973926909915924e-05,
"loss": 4.1139,
"step": 626688
},
{
"epoch": 0.01,
"learning_rate": 3.973088315164872e-05,
"loss": 4.1091,
"step": 627200
},
{
"epoch": 0.01,
"learning_rate": 3.97224972041382e-05,
"loss": 4.1221,
"step": 627712
},
{
"epoch": 0.01,
"learning_rate": 3.971411125662768e-05,
"loss": 4.1028,
"step": 628224
},
{
"epoch": 0.01,
"learning_rate": 3.970574168792089e-05,
"loss": 4.1048,
"step": 628736
},
{
"epoch": 0.01,
"learning_rate": 3.969735574041037e-05,
"loss": 4.1116,
"step": 629248
},
{
"epoch": 0.01,
"learning_rate": 3.968896979289985e-05,
"loss": 4.0952,
"step": 629760
},
{
"epoch": 0.01,
"learning_rate": 3.968058384538934e-05,
"loss": 4.1096,
"step": 630272
},
{
"epoch": 0.01,
"learning_rate": 3.967219789787882e-05,
"loss": 4.1035,
"step": 630784
},
{
"epoch": 0.01,
"learning_rate": 3.966382832917203e-05,
"loss": 4.107,
"step": 631296
},
{
"epoch": 0.01,
"learning_rate": 3.965544238166151e-05,
"loss": 4.1097,
"step": 631808
},
{
"epoch": 0.01,
"learning_rate": 3.964705643415099e-05,
"loss": 4.1084,
"step": 632320
},
{
"epoch": 0.01,
"learning_rate": 3.963867048664047e-05,
"loss": 4.1108,
"step": 632832
},
{
"epoch": 0.01,
"learning_rate": 3.963028453912995e-05,
"loss": 4.1107,
"step": 633344
},
{
"epoch": 0.01,
"learning_rate": 3.962189859161943e-05,
"loss": 4.1054,
"step": 633856
},
{
"epoch": 0.01,
"learning_rate": 3.961351264410891e-05,
"loss": 4.1095,
"step": 634368
},
{
"epoch": 0.01,
"learning_rate": 3.960512669659839e-05,
"loss": 4.1101,
"step": 634880
},
{
"epoch": 0.01,
"learning_rate": 3.9596757127891596e-05,
"loss": 4.0823,
"step": 635392
},
{
"epoch": 0.01,
"learning_rate": 3.9588371180381076e-05,
"loss": 4.1186,
"step": 635904
},
{
"epoch": 0.01,
"learning_rate": 3.9579985232870556e-05,
"loss": 4.0985,
"step": 636416
},
{
"epoch": 0.01,
"learning_rate": 3.9571599285360036e-05,
"loss": 4.1105,
"step": 636928
},
{
"epoch": 0.01,
"learning_rate": 3.956322971665325e-05,
"loss": 4.096,
"step": 637440
},
{
"epoch": 0.01,
"learning_rate": 3.955486014794646e-05,
"loss": 4.0936,
"step": 637952
},
{
"epoch": 0.01,
"learning_rate": 3.954647420043594e-05,
"loss": 4.0963,
"step": 638464
},
{
"epoch": 0.01,
"learning_rate": 3.953808825292542e-05,
"loss": 4.0966,
"step": 638976
},
{
"epoch": 0.01,
"learning_rate": 3.95297023054149e-05,
"loss": 4.113,
"step": 639488
},
{
"epoch": 0.01,
"learning_rate": 3.952131635790438e-05,
"loss": 4.0977,
"step": 640000
},
{
"epoch": 0.01,
"learning_rate": 3.951294678919759e-05,
"loss": 4.1201,
"step": 640512
},
{
"epoch": 0.01,
"learning_rate": 3.950456084168707e-05,
"loss": 4.1045,
"step": 641024
},
{
"epoch": 0.01,
"learning_rate": 3.949617489417655e-05,
"loss": 4.0841,
"step": 641536
},
{
"epoch": 0.01,
"learning_rate": 3.948778894666603e-05,
"loss": 4.107,
"step": 642048
},
{
"epoch": 0.01,
"learning_rate": 3.947940299915551e-05,
"loss": 4.096,
"step": 642560
},
{
"epoch": 0.01,
"learning_rate": 3.947101705164499e-05,
"loss": 4.0851,
"step": 643072
},
{
"epoch": 0.01,
"learning_rate": 3.946263110413447e-05,
"loss": 4.11,
"step": 643584
},
{
"epoch": 0.01,
"learning_rate": 3.945424515662395e-05,
"loss": 4.1053,
"step": 644096
},
{
"epoch": 0.01,
"learning_rate": 3.9445875587917166e-05,
"loss": 4.0927,
"step": 644608
},
{
"epoch": 0.01,
"learning_rate": 3.9437506019210375e-05,
"loss": 4.1025,
"step": 645120
},
{
"epoch": 0.01,
"learning_rate": 3.9429120071699855e-05,
"loss": 4.0836,
"step": 645632
},
{
"epoch": 0.01,
"learning_rate": 3.9420734124189335e-05,
"loss": 4.0983,
"step": 646144
},
{
"epoch": 0.01,
"learning_rate": 3.9412348176678815e-05,
"loss": 4.1031,
"step": 646656
},
{
"epoch": 0.01,
"learning_rate": 3.9403962229168295e-05,
"loss": 4.102,
"step": 647168
},
{
"epoch": 0.01,
"learning_rate": 3.939557628165777e-05,
"loss": 4.1118,
"step": 647680
},
{
"epoch": 0.01,
"learning_rate": 3.938719033414725e-05,
"loss": 4.0971,
"step": 648192
},
{
"epoch": 0.01,
"learning_rate": 3.937880438663673e-05,
"loss": 4.1149,
"step": 648704
},
{
"epoch": 0.01,
"learning_rate": 3.937045119673368e-05,
"loss": 4.0947,
"step": 649216
},
{
"epoch": 0.01,
"learning_rate": 3.936206524922316e-05,
"loss": 4.1055,
"step": 649728
},
{
"epoch": 0.01,
"learning_rate": 3.935367930171264e-05,
"loss": 4.0918,
"step": 650240
},
{
"epoch": 0.01,
"learning_rate": 3.934529335420212e-05,
"loss": 4.0908,
"step": 650752
},
{
"epoch": 0.01,
"learning_rate": 3.933690740669159e-05,
"loss": 4.1029,
"step": 651264
},
{
"epoch": 0.01,
"learning_rate": 3.932852145918107e-05,
"loss": 4.1081,
"step": 651776
},
{
"epoch": 0.01,
"learning_rate": 3.932013551167055e-05,
"loss": 4.1005,
"step": 652288
},
{
"epoch": 0.01,
"learning_rate": 3.931174956416003e-05,
"loss": 4.1072,
"step": 652800
},
{
"epoch": 0.01,
"learning_rate": 3.930337999545324e-05,
"loss": 4.0811,
"step": 653312
},
{
"epoch": 0.01,
"learning_rate": 3.929499404794272e-05,
"loss": 4.0893,
"step": 653824
},
{
"epoch": 0.01,
"learning_rate": 3.92866081004322e-05,
"loss": 4.1027,
"step": 654336
},
{
"epoch": 0.01,
"learning_rate": 3.927823853172542e-05,
"loss": 4.1028,
"step": 654848
},
{
"epoch": 0.01,
"learning_rate": 3.92698525842149e-05,
"loss": 4.0934,
"step": 655360
},
{
"epoch": 0.01,
"learning_rate": 3.926146663670438e-05,
"loss": 4.1041,
"step": 655872
},
{
"epoch": 0.02,
"learning_rate": 3.925308068919386e-05,
"loss": 4.0872,
"step": 656384
},
{
"epoch": 0.02,
"learning_rate": 3.924469474168334e-05,
"loss": 4.0987,
"step": 656896
},
{
"epoch": 0.02,
"learning_rate": 3.923630879417282e-05,
"loss": 4.094,
"step": 657408
},
{
"epoch": 0.02,
"learning_rate": 3.92279228466623e-05,
"loss": 4.095,
"step": 657920
},
{
"epoch": 0.02,
"learning_rate": 3.9219553277955506e-05,
"loss": 4.1057,
"step": 658432
},
{
"epoch": 0.02,
"learning_rate": 3.9211167330444986e-05,
"loss": 4.1063,
"step": 658944
},
{
"epoch": 0.02,
"learning_rate": 3.9202781382934466e-05,
"loss": 4.1109,
"step": 659456
},
{
"epoch": 0.02,
"learning_rate": 3.9194395435423946e-05,
"loss": 4.0898,
"step": 659968
},
{
"epoch": 0.02,
"learning_rate": 3.9186009487913426e-05,
"loss": 4.0944,
"step": 660480
},
{
"epoch": 0.02,
"learning_rate": 3.9177623540402906e-05,
"loss": 4.0933,
"step": 660992
},
{
"epoch": 0.02,
"learning_rate": 3.9169237592892386e-05,
"loss": 4.0993,
"step": 661504
},
{
"epoch": 0.02,
"learning_rate": 3.9160851645381866e-05,
"loss": 4.095,
"step": 662016
},
{
"epoch": 0.02,
"learning_rate": 3.9152465697871346e-05,
"loss": 4.0951,
"step": 662528
},
{
"epoch": 0.02,
"learning_rate": 3.914407975036083e-05,
"loss": 4.0947,
"step": 663040
},
{
"epoch": 0.02,
"learning_rate": 3.913571018165404e-05,
"loss": 4.0921,
"step": 663552
},
{
"epoch": 0.02,
"learning_rate": 3.912732423414352e-05,
"loss": 4.092,
"step": 664064
},
{
"epoch": 0.02,
"learning_rate": 3.9118938286633e-05,
"loss": 4.09,
"step": 664576
},
{
"epoch": 0.02,
"learning_rate": 3.911055233912248e-05,
"loss": 4.0832,
"step": 665088
},
{
"epoch": 0.02,
"learning_rate": 3.9102166391611955e-05,
"loss": 4.0994,
"step": 665600
},
{
"epoch": 0.02,
"learning_rate": 3.909379682290517e-05,
"loss": 4.0952,
"step": 666112
},
{
"epoch": 0.02,
"learning_rate": 3.908541087539465e-05,
"loss": 4.0901,
"step": 666624
},
{
"epoch": 0.02,
"learning_rate": 3.907702492788413e-05,
"loss": 4.0938,
"step": 667136
},
{
"epoch": 0.02,
"learning_rate": 3.9068638980373604e-05,
"loss": 4.0929,
"step": 667648
},
{
"epoch": 0.02,
"learning_rate": 3.9060253032863083e-05,
"loss": 4.099,
"step": 668160
},
{
"epoch": 0.02,
"learning_rate": 3.90518834641563e-05,
"loss": 4.0868,
"step": 668672
},
{
"epoch": 0.02,
"learning_rate": 3.9043497516645786e-05,
"loss": 4.1021,
"step": 669184
},
{
"epoch": 0.02,
"learning_rate": 3.903511156913526e-05,
"loss": 4.1023,
"step": 669696
},
{
"epoch": 0.02,
"learning_rate": 3.902672562162474e-05,
"loss": 4.0965,
"step": 670208
},
{
"epoch": 0.02,
"learning_rate": 3.9018356052917955e-05,
"loss": 4.0952,
"step": 670720
},
{
"epoch": 0.02,
"learning_rate": 3.900997010540743e-05,
"loss": 4.0888,
"step": 671232
},
{
"epoch": 0.02,
"learning_rate": 3.900158415789691e-05,
"loss": 4.0902,
"step": 671744
},
{
"epoch": 0.02,
"learning_rate": 3.899319821038639e-05,
"loss": 4.0946,
"step": 672256
},
{
"epoch": 0.02,
"learning_rate": 3.898481226287587e-05,
"loss": 4.096,
"step": 672768
},
{
"epoch": 0.02,
"learning_rate": 3.897642631536535e-05,
"loss": 4.0771,
"step": 673280
},
{
"epoch": 0.02,
"learning_rate": 3.896804036785483e-05,
"loss": 4.1033,
"step": 673792
},
{
"epoch": 0.02,
"learning_rate": 3.895965442034431e-05,
"loss": 4.0963,
"step": 674304
},
{
"epoch": 0.02,
"learning_rate": 3.895126847283379e-05,
"loss": 4.0959,
"step": 674816
},
{
"epoch": 0.02,
"learning_rate": 3.894288252532327e-05,
"loss": 4.0858,
"step": 675328
},
{
"epoch": 0.02,
"learning_rate": 3.8934512956616484e-05,
"loss": 4.0879,
"step": 675840
},
{
"epoch": 0.02,
"learning_rate": 3.8926127009105964e-05,
"loss": 4.0872,
"step": 676352
},
{
"epoch": 0.02,
"learning_rate": 3.8917741061595444e-05,
"loss": 4.0975,
"step": 676864
},
{
"epoch": 0.02,
"learning_rate": 3.8909355114084924e-05,
"loss": 4.095,
"step": 677376
},
{
"epoch": 0.02,
"learning_rate": 3.8900969166574404e-05,
"loss": 4.098,
"step": 677888
},
{
"epoch": 0.02,
"learning_rate": 3.889259959786761e-05,
"loss": 4.0743,
"step": 678400
},
{
"epoch": 0.02,
"learning_rate": 3.888423002916082e-05,
"loss": 4.099,
"step": 678912
},
{
"epoch": 0.02,
"learning_rate": 3.88758440816503e-05,
"loss": 4.0931,
"step": 679424
},
{
"epoch": 0.02,
"learning_rate": 3.886745813413978e-05,
"loss": 4.1041,
"step": 679936
},
{
"epoch": 0.02,
"learning_rate": 3.885907218662926e-05,
"loss": 4.0859,
"step": 680448
},
{
"epoch": 0.02,
"learning_rate": 3.885068623911874e-05,
"loss": 4.092,
"step": 680960
},
{
"epoch": 0.02,
"learning_rate": 3.884230029160822e-05,
"loss": 4.0943,
"step": 681472
},
{
"epoch": 0.02,
"learning_rate": 3.88339143440977e-05,
"loss": 4.1043,
"step": 681984
},
{
"epoch": 0.02,
"learning_rate": 3.882552839658719e-05,
"loss": 4.0839,
"step": 682496
},
{
"epoch": 0.02,
"learning_rate": 3.881714244907667e-05,
"loss": 4.0941,
"step": 683008
},
{
"epoch": 0.02,
"learning_rate": 3.880875650156615e-05,
"loss": 4.088,
"step": 683520
},
{
"epoch": 0.02,
"learning_rate": 3.880037055405562e-05,
"loss": 4.0972,
"step": 684032
},
{
"epoch": 0.02,
"learning_rate": 3.87919846065451e-05,
"loss": 4.0825,
"step": 684544
},
{
"epoch": 0.02,
"learning_rate": 3.8783631416642046e-05,
"loss": 4.0819,
"step": 685056
},
{
"epoch": 0.02,
"learning_rate": 3.8775245469131526e-05,
"loss": 4.0914,
"step": 685568
},
{
"epoch": 0.02,
"learning_rate": 3.8766859521621006e-05,
"loss": 4.0829,
"step": 686080
},
{
"epoch": 0.02,
"learning_rate": 3.8758473574110486e-05,
"loss": 4.0981,
"step": 686592
},
{
"epoch": 0.03,
"eval_loss": 4.110414028167725,
"eval_runtime": 302.541,
"eval_samples_per_second": 1261.287,
"eval_steps_per_second": 39.416,
"step": 686880
},
{
"epoch": 1.0,
"learning_rate": 3.8750087626599966e-05,
"loss": 4.0861,
"step": 687104
},
{
"epoch": 1.0,
"learning_rate": 3.874170167908944e-05,
"loss": 4.0788,
"step": 687616
},
{
"epoch": 1.0,
"learning_rate": 3.8733315731578926e-05,
"loss": 4.0911,
"step": 688128
},
{
"epoch": 1.0,
"learning_rate": 3.872494616287214e-05,
"loss": 4.0877,
"step": 688640
},
{
"epoch": 1.0,
"learning_rate": 3.8716560215361615e-05,
"loss": 4.0997,
"step": 689152
},
{
"epoch": 1.0,
"learning_rate": 3.8708174267851095e-05,
"loss": 4.0883,
"step": 689664
},
{
"epoch": 1.0,
"learning_rate": 3.8699788320340575e-05,
"loss": 4.086,
"step": 690176
},
{
"epoch": 1.0,
"learning_rate": 3.8691402372830055e-05,
"loss": 4.0955,
"step": 690688
},
{
"epoch": 1.0,
"learning_rate": 3.8683016425319535e-05,
"loss": 4.0845,
"step": 691200
},
{
"epoch": 1.0,
"learning_rate": 3.8674630477809015e-05,
"loss": 4.0898,
"step": 691712
},
{
"epoch": 1.0,
"learning_rate": 3.8666244530298495e-05,
"loss": 4.0926,
"step": 692224
},
{
"epoch": 1.0,
"learning_rate": 3.8657874961591704e-05,
"loss": 4.0925,
"step": 692736
},
{
"epoch": 1.0,
"learning_rate": 3.864950539288491e-05,
"loss": 4.0944,
"step": 693248
},
{
"epoch": 1.0,
"learning_rate": 3.864111944537439e-05,
"loss": 4.0792,
"step": 693760
},
{
"epoch": 1.0,
"learning_rate": 3.863273349786388e-05,
"loss": 4.0832,
"step": 694272
},
{
"epoch": 1.0,
"learning_rate": 3.862434755035336e-05,
"loss": 4.0701,
"step": 694784
},
{
"epoch": 1.0,
"learning_rate": 3.861596160284284e-05,
"loss": 4.0861,
"step": 695296
},
{
"epoch": 1.0,
"learning_rate": 3.860759203413605e-05,
"loss": 4.091,
"step": 695808
},
{
"epoch": 1.0,
"learning_rate": 3.859920608662553e-05,
"loss": 4.077,
"step": 696320
},
{
"epoch": 1.0,
"learning_rate": 3.859083651791874e-05,
"loss": 4.0998,
"step": 696832
},
{
"epoch": 1.0,
"learning_rate": 3.858245057040822e-05,
"loss": 4.0955,
"step": 697344
},
{
"epoch": 1.0,
"learning_rate": 3.85740646228977e-05,
"loss": 4.093,
"step": 697856
},
{
"epoch": 1.0,
"learning_rate": 3.856567867538718e-05,
"loss": 4.0914,
"step": 698368
},
{
"epoch": 1.0,
"learning_rate": 3.855729272787666e-05,
"loss": 4.0879,
"step": 698880
},
{
"epoch": 1.0,
"learning_rate": 3.854890678036614e-05,
"loss": 4.0922,
"step": 699392
},
{
"epoch": 1.0,
"learning_rate": 3.854052083285562e-05,
"loss": 4.0896,
"step": 699904
},
{
"epoch": 1.0,
"learning_rate": 3.8532151264148833e-05,
"loss": 4.0756,
"step": 700416
},
{
"epoch": 1.0,
"learning_rate": 3.852376531663831e-05,
"loss": 4.0918,
"step": 700928
},
{
"epoch": 1.0,
"learning_rate": 3.851537936912779e-05,
"loss": 4.0734,
"step": 701440
},
{
"epoch": 1.0,
"learning_rate": 3.850699342161727e-05,
"loss": 4.0807,
"step": 701952
},
{
"epoch": 1.01,
"learning_rate": 3.849860747410675e-05,
"loss": 4.087,
"step": 702464
},
{
"epoch": 1.01,
"learning_rate": 3.849022152659623e-05,
"loss": 4.0875,
"step": 702976
},
{
"epoch": 1.01,
"learning_rate": 3.848183557908571e-05,
"loss": 4.0826,
"step": 703488
},
{
"epoch": 1.01,
"learning_rate": 3.847344963157519e-05,
"loss": 4.0955,
"step": 704000
},
{
"epoch": 1.01,
"learning_rate": 3.846506368406467e-05,
"loss": 4.0786,
"step": 704512
},
{
"epoch": 1.01,
"learning_rate": 3.845669411535788e-05,
"loss": 4.0763,
"step": 705024
},
{
"epoch": 1.01,
"learning_rate": 3.844830816784736e-05,
"loss": 4.0882,
"step": 705536
},
{
"epoch": 1.01,
"learning_rate": 3.843993859914057e-05,
"loss": 4.0693,
"step": 706048
},
{
"epoch": 1.01,
"learning_rate": 3.843155265163005e-05,
"loss": 4.0818,
"step": 706560
},
{
"epoch": 1.01,
"learning_rate": 3.842316670411953e-05,
"loss": 4.0833,
"step": 707072
},
{
"epoch": 1.01,
"learning_rate": 3.841478075660902e-05,
"loss": 4.0804,
"step": 707584
},
{
"epoch": 1.01,
"learning_rate": 3.84063948090985e-05,
"loss": 4.0837,
"step": 708096
},
{
"epoch": 1.01,
"learning_rate": 3.839800886158798e-05,
"loss": 4.0844,
"step": 708608
},
{
"epoch": 1.01,
"learning_rate": 3.838962291407745e-05,
"loss": 4.0828,
"step": 709120
},
{
"epoch": 1.01,
"learning_rate": 3.838123696656693e-05,
"loss": 4.0845,
"step": 709632
},
{
"epoch": 1.01,
"learning_rate": 3.837285101905641e-05,
"loss": 4.0783,
"step": 710144
},
{
"epoch": 1.01,
"learning_rate": 3.836446507154589e-05,
"loss": 4.0826,
"step": 710656
},
{
"epoch": 1.01,
"learning_rate": 3.835607912403537e-05,
"loss": 4.0844,
"step": 711168
},
{
"epoch": 1.01,
"learning_rate": 3.834769317652485e-05,
"loss": 4.0601,
"step": 711680
},
{
"epoch": 1.01,
"learning_rate": 3.833932360781806e-05,
"loss": 4.0908,
"step": 712192
},
{
"epoch": 1.01,
"learning_rate": 3.833093766030754e-05,
"loss": 4.0739,
"step": 712704
},
{
"epoch": 1.01,
"learning_rate": 3.832255171279702e-05,
"loss": 4.0814,
"step": 713216
},
{
"epoch": 1.01,
"learning_rate": 3.83141657652865e-05,
"loss": 4.0705,
"step": 713728
},
{
"epoch": 1.01,
"learning_rate": 3.8305796196579716e-05,
"loss": 4.0672,
"step": 714240
},
{
"epoch": 1.01,
"learning_rate": 3.8297410249069195e-05,
"loss": 4.0709,
"step": 714752
},
{
"epoch": 1.01,
"learning_rate": 3.8289024301558675e-05,
"loss": 4.0731,
"step": 715264
},
{
"epoch": 1.01,
"learning_rate": 3.8280654732851885e-05,
"loss": 4.087,
"step": 715776
},
{
"epoch": 1.01,
"learning_rate": 3.8272268785341364e-05,
"loss": 4.0725,
"step": 716288
},
{
"epoch": 1.01,
"learning_rate": 3.8263882837830844e-05,
"loss": 4.0945,
"step": 716800
},
{
"epoch": 1.01,
"learning_rate": 3.8255496890320324e-05,
"loss": 4.0821,
"step": 717312
},
{
"epoch": 1.01,
"learning_rate": 3.8247110942809804e-05,
"loss": 4.0565,
"step": 717824
},
{
"epoch": 1.01,
"learning_rate": 3.8238741374103013e-05,
"loss": 4.0784,
"step": 718336
},
{
"epoch": 1.01,
"learning_rate": 3.8230355426592493e-05,
"loss": 4.0666,
"step": 718848
},
{
"epoch": 1.01,
"learning_rate": 3.822196947908197e-05,
"loss": 4.0663,
"step": 719360
},
{
"epoch": 1.01,
"learning_rate": 3.821358353157145e-05,
"loss": 4.0817,
"step": 719872
},
{
"epoch": 1.01,
"learning_rate": 3.820519758406093e-05,
"loss": 4.0793,
"step": 720384
},
{
"epoch": 1.01,
"learning_rate": 3.819681163655042e-05,
"loss": 4.0685,
"step": 720896
},
{
"epoch": 1.01,
"learning_rate": 3.818844206784363e-05,
"loss": 4.0783,
"step": 721408
},
{
"epoch": 1.01,
"learning_rate": 3.818005612033311e-05,
"loss": 4.0599,
"step": 721920
},
{
"epoch": 1.01,
"learning_rate": 3.817167017282259e-05,
"loss": 4.0668,
"step": 722432
},
{
"epoch": 1.01,
"learning_rate": 3.816328422531207e-05,
"loss": 4.0786,
"step": 722944
},
{
"epoch": 1.01,
"learning_rate": 3.815489827780155e-05,
"loss": 4.08,
"step": 723456
},
{
"epoch": 1.01,
"learning_rate": 3.814652870909476e-05,
"loss": 4.0858,
"step": 723968
},
{
"epoch": 1.01,
"learning_rate": 3.813814276158424e-05,
"loss": 4.0722,
"step": 724480
},
{
"epoch": 1.01,
"learning_rate": 3.812975681407372e-05,
"loss": 4.0932,
"step": 724992
},
{
"epoch": 1.01,
"learning_rate": 3.81213708665632e-05,
"loss": 4.0688,
"step": 725504
},
{
"epoch": 1.01,
"learning_rate": 3.811298491905268e-05,
"loss": 4.0849,
"step": 726016
},
{
"epoch": 1.01,
"learning_rate": 3.810459897154216e-05,
"loss": 4.0652,
"step": 726528
},
{
"epoch": 1.01,
"learning_rate": 3.809621302403164e-05,
"loss": 4.0692,
"step": 727040
},
{
"epoch": 1.01,
"learning_rate": 3.808782707652112e-05,
"loss": 4.0738,
"step": 727552
},
{
"epoch": 1.01,
"learning_rate": 3.8079457507814334e-05,
"loss": 4.0832,
"step": 728064
},
{
"epoch": 1.01,
"learning_rate": 3.8071071560303814e-05,
"loss": 4.0755,
"step": 728576
},
{
"epoch": 1.01,
"learning_rate": 3.806270199159702e-05,
"loss": 4.0821,
"step": 729088
},
{
"epoch": 1.01,
"learning_rate": 3.80543160440865e-05,
"loss": 4.0586,
"step": 729600
},
{
"epoch": 1.01,
"learning_rate": 3.804593009657598e-05,
"loss": 4.0616,
"step": 730112
},
{
"epoch": 1.01,
"learning_rate": 3.803754414906546e-05,
"loss": 4.08,
"step": 730624
},
{
"epoch": 1.01,
"learning_rate": 3.8029158201554936e-05,
"loss": 4.0757,
"step": 731136
},
{
"epoch": 1.01,
"learning_rate": 3.8020772254044416e-05,
"loss": 4.0681,
"step": 731648
},
{
"epoch": 1.01,
"learning_rate": 3.8012386306533896e-05,
"loss": 4.0764,
"step": 732160
},
{
"epoch": 1.02,
"learning_rate": 3.8004000359023376e-05,
"loss": 4.068,
"step": 732672
},
{
"epoch": 1.02,
"learning_rate": 3.799563079031659e-05,
"loss": 4.07,
"step": 733184
},
{
"epoch": 1.02,
"learning_rate": 3.798724484280607e-05,
"loss": 4.0688,
"step": 733696
},
{
"epoch": 1.02,
"learning_rate": 3.797885889529555e-05,
"loss": 4.0681,
"step": 734208
},
{
"epoch": 1.02,
"learning_rate": 3.797047294778503e-05,
"loss": 4.0828,
"step": 734720
},
{
"epoch": 1.02,
"learning_rate": 3.796210337907824e-05,
"loss": 4.0834,
"step": 735232
},
{
"epoch": 1.02,
"learning_rate": 3.795371743156772e-05,
"loss": 4.0833,
"step": 735744
},
{
"epoch": 1.02,
"learning_rate": 3.79453314840572e-05,
"loss": 4.066,
"step": 736256
},
{
"epoch": 1.02,
"learning_rate": 3.793694553654668e-05,
"loss": 4.0693,
"step": 736768
},
{
"epoch": 1.02,
"learning_rate": 3.792857596783989e-05,
"loss": 4.0685,
"step": 737280
},
{
"epoch": 1.02,
"learning_rate": 3.7920206399133105e-05,
"loss": 4.0754,
"step": 737792
},
{
"epoch": 1.02,
"learning_rate": 3.791182045162258e-05,
"loss": 4.073,
"step": 738304
},
{
"epoch": 1.02,
"learning_rate": 3.7903434504112065e-05,
"loss": 4.0659,
"step": 738816
},
{
"epoch": 1.02,
"learning_rate": 3.7895048556601545e-05,
"loss": 4.0716,
"step": 739328
},
{
"epoch": 1.02,
"learning_rate": 3.7886662609091025e-05,
"loss": 4.0658,
"step": 739840
},
{
"epoch": 1.02,
"learning_rate": 3.7878293040384234e-05,
"loss": 4.0682,
"step": 740352
},
{
"epoch": 1.02,
"learning_rate": 3.7869907092873714e-05,
"loss": 4.0665,
"step": 740864
},
{
"epoch": 1.02,
"learning_rate": 3.7861521145363194e-05,
"loss": 4.0601,
"step": 741376
},
{
"epoch": 1.02,
"learning_rate": 3.7853135197852674e-05,
"loss": 4.074,
"step": 741888
},
{
"epoch": 1.02,
"learning_rate": 3.7844749250342154e-05,
"loss": 4.0714,
"step": 742400
},
{
"epoch": 1.02,
"learning_rate": 3.783637968163536e-05,
"loss": 4.0669,
"step": 742912
},
{
"epoch": 1.02,
"learning_rate": 3.782799373412484e-05,
"loss": 4.0669,
"step": 743424
},
{
"epoch": 1.02,
"learning_rate": 3.781960778661432e-05,
"loss": 4.0686,
"step": 743936
},
{
"epoch": 1.02,
"learning_rate": 3.78112218391038e-05,
"loss": 4.0747,
"step": 744448
},
{
"epoch": 1.02,
"learning_rate": 3.780283589159328e-05,
"loss": 4.0638,
"step": 744960
},
{
"epoch": 1.02,
"learning_rate": 3.77944663228865e-05,
"loss": 4.0761,
"step": 745472
},
{
"epoch": 1.02,
"learning_rate": 3.778608037537598e-05,
"loss": 4.0757,
"step": 745984
},
{
"epoch": 1.02,
"learning_rate": 3.777769442786546e-05,
"loss": 4.0721,
"step": 746496
},
{
"epoch": 1.02,
"learning_rate": 3.776930848035494e-05,
"loss": 4.0698,
"step": 747008
},
{
"epoch": 1.02,
"learning_rate": 3.776092253284442e-05,
"loss": 4.0665,
"step": 747520
},
{
"epoch": 1.02,
"learning_rate": 3.77525365853339e-05,
"loss": 4.0629,
"step": 748032
},
{
"epoch": 1.02,
"learning_rate": 3.774415063782338e-05,
"loss": 4.0745,
"step": 748544
},
{
"epoch": 1.02,
"learning_rate": 3.773578106911659e-05,
"loss": 4.069,
"step": 749056
},
{
"epoch": 1.02,
"learning_rate": 3.772739512160607e-05,
"loss": 4.0552,
"step": 749568
},
{
"epoch": 1.02,
"learning_rate": 3.771900917409555e-05,
"loss": 4.0787,
"step": 750080
},
{
"epoch": 1.02,
"learning_rate": 3.771062322658503e-05,
"loss": 4.0743,
"step": 750592
},
{
"epoch": 1.02,
"learning_rate": 3.770223727907451e-05,
"loss": 4.071,
"step": 751104
},
{
"epoch": 1.02,
"learning_rate": 3.769385133156399e-05,
"loss": 4.0617,
"step": 751616
},
{
"epoch": 1.02,
"learning_rate": 3.76854817628572e-05,
"loss": 4.0619,
"step": 752128
},
{
"epoch": 1.02,
"learning_rate": 3.767709581534668e-05,
"loss": 4.0638,
"step": 752640
},
{
"epoch": 1.02,
"learning_rate": 3.766870986783616e-05,
"loss": 4.0737,
"step": 753152
},
{
"epoch": 1.02,
"learning_rate": 3.766032392032564e-05,
"loss": 4.0701,
"step": 753664
},
{
"epoch": 1.02,
"learning_rate": 3.765193797281512e-05,
"loss": 4.0759,
"step": 754176
},
{
"epoch": 1.02,
"learning_rate": 3.7643552025304596e-05,
"loss": 4.0488,
"step": 754688
},
{
"epoch": 1.02,
"learning_rate": 3.7635166077794076e-05,
"loss": 4.0779,
"step": 755200
},
{
"epoch": 1.02,
"learning_rate": 3.7626780130283556e-05,
"loss": 4.0649,
"step": 755712
},
{
"epoch": 1.02,
"learning_rate": 3.7618394182773036e-05,
"loss": 4.0789,
"step": 756224
},
{
"epoch": 1.02,
"learning_rate": 3.761004099286998e-05,
"loss": 4.0646,
"step": 756736
},
{
"epoch": 1.02,
"learning_rate": 3.760165504535946e-05,
"loss": 4.0638,
"step": 757248
},
{
"epoch": 1.02,
"learning_rate": 3.759326909784894e-05,
"loss": 4.07,
"step": 757760
},
{
"epoch": 1.02,
"learning_rate": 3.758488315033842e-05,
"loss": 4.0824,
"step": 758272
},
{
"epoch": 1.02,
"learning_rate": 3.75764972028279e-05,
"loss": 4.0619,
"step": 758784
},
{
"epoch": 1.02,
"learning_rate": 3.756811125531738e-05,
"loss": 4.0701,
"step": 759296
},
{
"epoch": 1.02,
"learning_rate": 3.755972530780686e-05,
"loss": 4.0627,
"step": 759808
},
{
"epoch": 1.02,
"learning_rate": 3.755135573910007e-05,
"loss": 4.0706,
"step": 760320
},
{
"epoch": 1.02,
"learning_rate": 3.754296979158955e-05,
"loss": 4.0596,
"step": 760832
},
{
"epoch": 1.02,
"learning_rate": 3.753458384407903e-05,
"loss": 4.0613,
"step": 761344
},
{
"epoch": 1.02,
"learning_rate": 3.752619789656851e-05,
"loss": 4.0677,
"step": 761856
},
{
"epoch": 1.02,
"learning_rate": 3.751781194905799e-05,
"loss": 4.0601,
"step": 762368
},
{
"epoch": 1.02,
"learning_rate": 3.750942600154747e-05,
"loss": 4.0785,
"step": 762880
},
{
"epoch": 1.03,
"eval_loss": 4.093703269958496,
"eval_runtime": 301.5926,
"eval_samples_per_second": 1265.253,
"eval_steps_per_second": 39.54,
"step": 763200
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 3.135969005933628e+17,
"trial_name": null,
"trial_params": null
}