passive-lstm-0 / checkpoint-381600 /trainer_state.json
abhinavp's picture
Training in progress, epoch 0, checkpoint
7c42df2 verified
{
"best_metric": 4.208554267883301,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/passive/lstm/0/checkpoints/checkpoint-381600",
"epoch": 0.025000606015738065,
"eval_steps": 10,
"global_step": 381600,
"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": 10.8198,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.5522,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0566,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.995,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.9475,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.9066,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7464,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.6405,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993292879871958e-05,
"loss": 6.5391,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992454285120906e-05,
"loss": 6.457,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.991615690369854e-05,
"loss": 6.4004,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990777095618801e-05,
"loss": 6.3311,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 6.2652,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 6.1988,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 6.1445,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 6.0779,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 6.0424,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.9952,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.9566,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.9196,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8897,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.982391148108281e-05,
"loss": 5.8524,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 5.8257,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.785,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798786396158716e-05,
"loss": 5.7734,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 5.7366,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 5.7188,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 5.6818,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6646,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6459,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6213,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.6129,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 5.5862,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.9723329247367764e-05,
"loss": 5.5697,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5626,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.9706557352346724e-05,
"loss": 5.5386,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.9698171404836204e-05,
"loss": 5.5296,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4843,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4893,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4519,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4571,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4336,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.4322,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.4024,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963110020355577e-05,
"loss": 5.4078,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3962,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.3903,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960595873982795e-05,
"loss": 5.3811,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959757279231743e-05,
"loss": 5.3518,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958920322361064e-05,
"loss": 5.3426,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958081727610012e-05,
"loss": 5.3434,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.95724313285896e-05,
"loss": 5.3293,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956404538107908e-05,
"loss": 5.324,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2998,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.2981,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2777,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.298,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522148401133936e-05,
"loss": 5.2524,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951376245362342e-05,
"loss": 5.2679,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.95053765061129e-05,
"loss": 5.2567,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2381,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948862098989559e-05,
"loss": 5.2352,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2224,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.2119,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.2041,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.2186,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944670763114672e-05,
"loss": 5.1918,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1825,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1742,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1712,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941318021990837e-05,
"loss": 5.1775,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1722,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.148,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388022377376816e-05,
"loss": 5.1631,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379636429866296e-05,
"loss": 5.1554,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 5.1293,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.936291367125644e-05,
"loss": 5.1272,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.935452772374592e-05,
"loss": 5.1171,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 5.1092,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 5.1037,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 5.1087,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 5.1041,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 5.1052,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 5.0813,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 5.0642,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.928744014366177e-05,
"loss": 5.0683,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927905419615125e-05,
"loss": 5.0714,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927066824864073e-05,
"loss": 5.0689,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 5.0524,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925389635361968e-05,
"loss": 5.0499,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.92455267849129e-05,
"loss": 5.0496,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923714083740238e-05,
"loss": 5.0403,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922875488989185e-05,
"loss": 5.0311,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.922036894238133e-05,
"loss": 5.0276,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921199937367455e-05,
"loss": 5.0154,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920361342616403e-05,
"loss": 5.0273,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919522747865351e-05,
"loss": 5.0144,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 4.9927,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.997,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.9953,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 5.0038,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.9153314119904636e-05,
"loss": 4.9853,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.9823,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.9665,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128172656176805e-05,
"loss": 4.9707,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119786708666285e-05,
"loss": 4.9517,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9615,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.95,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.9536,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.9399,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.9436,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.9305,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9334,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.926,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.9192,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.9306,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902757404365803e-05,
"loss": 4.9147,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.9128,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.9028,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.9081,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994046632419686e-05,
"loss": 4.9029,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.8958,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.8996,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.8859,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960502842377605e-05,
"loss": 4.8855,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952116894867085e-05,
"loss": 4.8663,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.8723,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.8737,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8637,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8563,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.878,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.8901833967411423e-05,
"loss": 4.8603,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.8522,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.8518,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.887667612487986e-05,
"loss": 4.8461,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886829017736934e-05,
"loss": 4.8473,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.8439,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.8398,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884314871364151e-05,
"loss": 4.8412,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883476276613099e-05,
"loss": 4.8394,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882637681862047e-05,
"loss": 4.8276,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.8178,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.8285,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.8157,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.8194,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.878447983867534e-05,
"loss": 4.81,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.8071,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.876772432245803e-05,
"loss": 4.8133,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875933837494751e-05,
"loss": 4.7999,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.8750952427436986e-05,
"loss": 4.7967,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.765356540679932,
"eval_runtime": 295.2513,
"eval_samples_per_second": 1292.428,
"eval_steps_per_second": 40.389,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.785,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.7835,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.8069,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.7913,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.7825,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.7796,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.7803,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.7619,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.7708,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.7703,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7729,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865035381491821e-05,
"loss": 4.7724,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864198424621142e-05,
"loss": 4.754,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.86335982987009e-05,
"loss": 4.7539,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862521235119038e-05,
"loss": 4.7427,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.861682640367986e-05,
"loss": 4.7441,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.860844045616934e-05,
"loss": 4.7515,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.7408,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.859168493995203e-05,
"loss": 4.7454,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.7588,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.7402,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.7456,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.7272,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.746,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541385633692644e-05,
"loss": 4.7239,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532999686182124e-05,
"loss": 4.7276,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524613738671604e-05,
"loss": 4.7133,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.8516227791161084e-05,
"loss": 4.7231,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.714,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.7107,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.7158,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.7195,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847431443241221e-05,
"loss": 4.7115,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.7133,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845754253739117e-05,
"loss": 4.7049,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844915658988065e-05,
"loss": 4.7127,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.6846,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.7,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.6753,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.6969,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.6798,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.6931,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839048771491447e-05,
"loss": 4.6707,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838210176740395e-05,
"loss": 4.6883,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.8373732198697167e-05,
"loss": 4.6851,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.8365346251186646e-05,
"loss": 4.6823,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.8356960303676126e-05,
"loss": 4.6896,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.8348574356165606e-05,
"loss": 4.6592,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.8340188408655086e-05,
"loss": 4.6627,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.8331802461144566e-05,
"loss": 4.6764,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.8323416513634046e-05,
"loss": 4.6683,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.8315030566123526e-05,
"loss": 4.6661,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.8306644618613006e-05,
"loss": 4.6588,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.6525,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.6464,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281486776081446e-05,
"loss": 4.6638,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.6391,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.826474763866787e-05,
"loss": 4.6505,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.825636169115735e-05,
"loss": 4.6565,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.824797574364683e-05,
"loss": 4.6378,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823958979613631e-05,
"loss": 4.639,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823120384862579e-05,
"loss": 4.6387,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.822281790111527e-05,
"loss": 4.6248,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821443195360475e-05,
"loss": 4.6308,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.6469,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819767643738744e-05,
"loss": 4.6288,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.818929048987692e-05,
"loss": 4.6233,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.6215,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817253497365961e-05,
"loss": 4.6225,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816414902614909e-05,
"loss": 4.6368,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815576307863857e-05,
"loss": 4.6287,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814737713112805e-05,
"loss": 4.6186,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8138991183617535e-05,
"loss": 4.6339,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.813060523610701e-05,
"loss": 4.6298,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.6157,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.6125,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105463772379184e-05,
"loss": 4.6117,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809707782486866e-05,
"loss": 4.6085,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808869187735814e-05,
"loss": 4.6052,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808030592984762e-05,
"loss": 4.6101,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.6155,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.6164,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.6042,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.804677851860927e-05,
"loss": 4.5821,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803839257109875e-05,
"loss": 4.5978,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.6017,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802162067607771e-05,
"loss": 4.6037,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801323472856719e-05,
"loss": 4.5955,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.80048651598604e-05,
"loss": 4.5924,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799647921234988e-05,
"loss": 4.5976,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798809326483936e-05,
"loss": 4.5901,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797970731732884e-05,
"loss": 4.5851,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797132136981832e-05,
"loss": 4.5917,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.79629354223078e-05,
"loss": 4.5754,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795454947479728e-05,
"loss": 4.5956,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794616352728676e-05,
"loss": 4.5863,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793777757977624e-05,
"loss": 4.5659,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792940801106946e-05,
"loss": 4.5785,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.5765,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.5881,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790426654734163e-05,
"loss": 4.5757,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895880599831107e-05,
"loss": 4.571,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887494652320587e-05,
"loss": 4.5641,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879108704810067e-05,
"loss": 4.573,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870722757299546e-05,
"loss": 4.5551,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.7862353188592756e-05,
"loss": 4.5646,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853967241082236e-05,
"loss": 4.5609,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845581293571715e-05,
"loss": 4.5635,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837195346061195e-05,
"loss": 4.5525,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.7828809398550675e-05,
"loss": 4.5622,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.7820423451040155e-05,
"loss": 4.5551,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.7812037503529635e-05,
"loss": 4.5553,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.7803651556019115e-05,
"loss": 4.5572,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.7795265608508595e-05,
"loss": 4.5466,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.7786896039801804e-05,
"loss": 4.5705,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.7778510092291284e-05,
"loss": 4.5544,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.7770124144780764e-05,
"loss": 4.5537,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.7761738197270244e-05,
"loss": 4.5438,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.7753352249759724e-05,
"loss": 4.5499,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774498268105293e-05,
"loss": 4.5502,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773659673354241e-05,
"loss": 4.5402,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772821078603189e-05,
"loss": 4.5556,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771982483852137e-05,
"loss": 4.5424,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771145526981459e-05,
"loss": 4.5371,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770306932230407e-05,
"loss": 4.5334,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769468337479355e-05,
"loss": 4.5353,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768629742728303e-05,
"loss": 4.5338,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767792785857624e-05,
"loss": 4.5353,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766955828986945e-05,
"loss": 4.5217,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766117234235893e-05,
"loss": 4.5502,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.5402,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764440044733789e-05,
"loss": 4.5306,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763601449982737e-05,
"loss": 4.5287,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762762855231685e-05,
"loss": 4.5234,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761924260480633e-05,
"loss": 4.5343,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.7610856657295813e-05,
"loss": 4.5312,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.7602470709785293e-05,
"loss": 4.5271,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941011410785e-05,
"loss": 4.532,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758571519356798e-05,
"loss": 4.528,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757732924605746e-05,
"loss": 4.5252,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756894329854694e-05,
"loss": 4.5177,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756055735103642e-05,
"loss": 4.5303,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755218778232963e-05,
"loss": 4.5181,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754380183481911e-05,
"loss": 4.5205,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753541588730859e-05,
"loss": 4.5149,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752702993979807e-05,
"loss": 4.5163,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751864399228755e-05,
"loss": 4.5176,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751025804477703e-05,
"loss": 4.5059,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750188847607025e-05,
"loss": 4.5105,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.484802722930908,
"eval_runtime": 296.4897,
"eval_samples_per_second": 1287.029,
"eval_steps_per_second": 40.221,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749350252855973e-05,
"loss": 4.4981,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748511658104921e-05,
"loss": 4.4961,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747673063353868e-05,
"loss": 4.5236,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746834468602816e-05,
"loss": 4.5142,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745995873851764e-05,
"loss": 4.5038,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745157279100712e-05,
"loss": 4.5012,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.74431868434966e-05,
"loss": 4.506,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743480089598608e-05,
"loss": 4.4896,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742641494847556e-05,
"loss": 4.5071,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741802900096504e-05,
"loss": 4.5003,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740964305345452e-05,
"loss": 4.5039,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401273484747736e-05,
"loss": 4.5054,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.7392887537237216e-05,
"loss": 4.4864,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384501589726696e-05,
"loss": 4.4917,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376115642216176e-05,
"loss": 4.4858,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367729694705656e-05,
"loss": 4.4861,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359343747195135e-05,
"loss": 4.4895,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350974178488345e-05,
"loss": 4.482,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342588230977825e-05,
"loss": 4.4888,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.7334202283467305e-05,
"loss": 4.5077,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.7325816335956784e-05,
"loss": 4.4862,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.7317430388446264e-05,
"loss": 4.4911,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730904444093574e-05,
"loss": 4.4839,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730065849342522e-05,
"loss": 4.4964,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292272545914704e-05,
"loss": 4.4743,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.7283886598404184e-05,
"loss": 4.487,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.7275500650893664e-05,
"loss": 4.4695,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.7267114703383144e-05,
"loss": 4.4742,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258728755872624e-05,
"loss": 4.4732,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250342808362104e-05,
"loss": 4.4694,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7241956860851584e-05,
"loss": 4.4769,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233570913341064e-05,
"loss": 4.4819,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225184965830544e-05,
"loss": 4.4747,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721681539712375e-05,
"loss": 4.4808,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720844582841696e-05,
"loss": 4.4664,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720005988090644e-05,
"loss": 4.4834,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719169031219965e-05,
"loss": 4.4518,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718330436468914e-05,
"loss": 4.4728,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717491841717862e-05,
"loss": 4.4466,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.71665324696681e-05,
"loss": 4.4688,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715814652215758e-05,
"loss": 4.4563,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714976057464706e-05,
"loss": 4.4698,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714137462713654e-05,
"loss": 4.4504,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.713298867962602e-05,
"loss": 4.4623,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.71246027321155e-05,
"loss": 4.4651,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.711623316340871e-05,
"loss": 4.4636,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.710784721589819e-05,
"loss": 4.4675,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099461268387667e-05,
"loss": 4.4449,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091075320877147e-05,
"loss": 4.4427,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082705752170356e-05,
"loss": 4.4636,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074319804659836e-05,
"loss": 4.4548,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706593385714932e-05,
"loss": 4.4496,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.70575479096388e-05,
"loss": 4.4486,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704916196212828e-05,
"loss": 4.4431,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704079239342149e-05,
"loss": 4.4343,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703240644591097e-05,
"loss": 4.4506,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702402049840045e-05,
"loss": 4.4322,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015634550889924e-05,
"loss": 4.4423,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007248603379404e-05,
"loss": 4.4528,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998862655868884e-05,
"loss": 4.4318,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.69904930871621e-05,
"loss": 4.4342,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982107139651573e-05,
"loss": 4.438,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697372119214106e-05,
"loss": 4.4226,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696533524463054e-05,
"loss": 4.4251,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695694929712002e-05,
"loss": 4.4461,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.69485633496095e-05,
"loss": 4.4319,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694019378090271e-05,
"loss": 4.4243,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693180783339219e-05,
"loss": 4.4247,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692342188588167e-05,
"loss": 4.4279,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691503593837115e-05,
"loss": 4.4411,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690664999086063e-05,
"loss": 4.4358,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689828042215384e-05,
"loss": 4.424,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688989447464332e-05,
"loss": 4.4405,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.68815085271328e-05,
"loss": 4.4339,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687312257962228e-05,
"loss": 4.4245,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686473663211176e-05,
"loss": 4.4208,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856367063404974e-05,
"loss": 4.4274,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6847981115894454e-05,
"loss": 4.4217,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683961154718766e-05,
"loss": 4.4193,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683122559967714e-05,
"loss": 4.4202,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682283965216662e-05,
"loss": 4.4273,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.68144537046561e-05,
"loss": 4.4322,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680606775714558e-05,
"loss": 4.418,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679768180963506e-05,
"loss": 4.4032,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678929586212454e-05,
"loss": 4.4109,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678090991461402e-05,
"loss": 4.4159,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.67725239671035e-05,
"loss": 4.423,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676415439839671e-05,
"loss": 4.4125,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675576845088619e-05,
"loss": 4.4107,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674738250337568e-05,
"loss": 4.4209,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673899655586516e-05,
"loss": 4.407,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673062698715837e-05,
"loss": 4.4078,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722257418451576e-05,
"loss": 4.412,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713871470941056e-05,
"loss": 4.4042,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705485523430536e-05,
"loss": 4.4219,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697099575920016e-05,
"loss": 4.4067,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688713628409496e-05,
"loss": 4.3949,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680327680898976e-05,
"loss": 4.4056,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6671958112192185e-05,
"loss": 4.4026,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663572164681665e-05,
"loss": 4.4202,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655186217171145e-05,
"loss": 4.4087,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664680026966063e-05,
"loss": 4.3994,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663841432215011e-05,
"loss": 4.3899,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663002837463959e-05,
"loss": 4.404,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.6621642427129065e-05,
"loss": 4.3874,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.6613256479618545e-05,
"loss": 4.3986,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.6604870532108025e-05,
"loss": 4.3942,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596484584597505e-05,
"loss": 4.3958,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588115015890714e-05,
"loss": 4.3849,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579729068380194e-05,
"loss": 4.4033,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571343120869674e-05,
"loss": 4.3877,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6562957173359154e-05,
"loss": 4.3884,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.6554571225848634e-05,
"loss": 4.3971,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654620165714185e-05,
"loss": 4.3843,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653781570963133e-05,
"loss": 4.4062,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652944614092454e-05,
"loss": 4.3935,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652106019341402e-05,
"loss": 4.3938,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.65126742459035e-05,
"loss": 4.3856,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650428829839298e-05,
"loss": 4.3896,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649590235088246e-05,
"loss": 4.3915,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648753278217567e-05,
"loss": 4.3804,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647914683466515e-05,
"loss": 4.3956,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647076088715463e-05,
"loss": 4.3881,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646237493964411e-05,
"loss": 4.3805,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645398899213359e-05,
"loss": 4.3823,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644560304462307e-05,
"loss": 4.3803,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437217097112554e-05,
"loss": 4.3731,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642884752840576e-05,
"loss": 4.3875,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642046158089524e-05,
"loss": 4.371,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641207563338472e-05,
"loss": 4.3925,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.64036896858742e-05,
"loss": 4.3894,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639530373836368e-05,
"loss": 4.3771,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638691779085316e-05,
"loss": 4.3755,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637853184334264e-05,
"loss": 4.3741,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637014589583212e-05,
"loss": 4.3834,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6361759948321596e-05,
"loss": 4.3815,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635339037961481e-05,
"loss": 4.3775,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634502081090802e-05,
"loss": 4.3807,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633663486339751e-05,
"loss": 4.3795,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632824891588699e-05,
"loss": 4.3808,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631986296837647e-05,
"loss": 4.3689,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631147702086595e-05,
"loss": 4.387,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630309107335542e-05,
"loss": 4.3739,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.62947051258449e-05,
"loss": 4.3712,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628633555713812e-05,
"loss": 4.3726,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.6277949609627597e-05,
"loss": 4.3748,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626956366211707e-05,
"loss": 4.3699,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626117771460655e-05,
"loss": 4.3608,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625279176709603e-05,
"loss": 4.364,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.348752975463867,
"eval_runtime": 286.9409,
"eval_samples_per_second": 1329.859,
"eval_steps_per_second": 41.559,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.6244422198389246e-05,
"loss": 4.366,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.6236036250878726e-05,
"loss": 4.3528,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.622766668217194e-05,
"loss": 4.3814,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.621928073466142e-05,
"loss": 4.3731,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.6210894787150895e-05,
"loss": 4.3682,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202508839640374e-05,
"loss": 4.357,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194122892129854e-05,
"loss": 4.3695,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185736944619334e-05,
"loss": 4.3493,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177350997108814e-05,
"loss": 4.3695,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6168965049598294e-05,
"loss": 4.3651,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.61605954808915e-05,
"loss": 4.3624,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.615220953338098e-05,
"loss": 4.3725,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.614382358587046e-05,
"loss": 4.349,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.613543763835994e-05,
"loss": 4.3587,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612705169084942e-05,
"loss": 4.3471,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611866574333891e-05,
"loss": 4.3542,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611027979582839e-05,
"loss": 4.3514,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610189384831787e-05,
"loss": 4.3499,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609350790080735e-05,
"loss": 4.3532,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608512195329683e-05,
"loss": 4.3726,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607673600578631e-05,
"loss": 4.3523,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606835005827578e-05,
"loss": 4.3582,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.605999686837273e-05,
"loss": 4.3521,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605161092086221e-05,
"loss": 4.3643,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604322497335169e-05,
"loss": 4.344,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603483902584117e-05,
"loss": 4.3524,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602645307833065e-05,
"loss": 4.3407,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.601806713082013e-05,
"loss": 4.3423,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.600968118330961e-05,
"loss": 4.3412,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.600129523579909e-05,
"loss": 4.3459,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.599290928828857e-05,
"loss": 4.3437,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598452334077805e-05,
"loss": 4.3541,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597613739326753e-05,
"loss": 4.3464,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596775144575701e-05,
"loss": 4.3502,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595939825585395e-05,
"loss": 4.3434,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595101230834343e-05,
"loss": 4.3531,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.5942626360832906e-05,
"loss": 4.3323,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593425679212612e-05,
"loss": 4.3451,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.59258708446156e-05,
"loss": 4.3213,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591748489710508e-05,
"loss": 4.3408,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.590909894959456e-05,
"loss": 4.3355,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590071300208404e-05,
"loss": 4.3473,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589232705457352e-05,
"loss": 4.3288,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.5883941107063e-05,
"loss": 4.3392,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587555515955248e-05,
"loss": 4.3421,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586718559084569e-05,
"loss": 4.3452,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585879964333517e-05,
"loss": 4.3392,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585041369582465e-05,
"loss": 4.3278,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584202774831413e-05,
"loss": 4.319,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583364180080361e-05,
"loss": 4.3424,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582527223209682e-05,
"loss": 4.337,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.58168862845863e-05,
"loss": 4.3304,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808516715879515e-05,
"loss": 4.327,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800130768368995e-05,
"loss": 4.3281,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791744820858475e-05,
"loss": 4.3115,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783375252151684e-05,
"loss": 4.3353,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5774989304641164e-05,
"loss": 4.3112,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766603357130644e-05,
"loss": 4.3256,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758217409620124e-05,
"loss": 4.3326,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5749831462109604e-05,
"loss": 4.3201,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741445514599084e-05,
"loss": 4.3135,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733059567088564e-05,
"loss": 4.3226,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.5724673619578044e-05,
"loss": 4.3064,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.5716287672067524e-05,
"loss": 4.314,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570791810336074e-05,
"loss": 4.3265,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569953215585022e-05,
"loss": 4.318,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.56911462083397e-05,
"loss": 4.3102,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568276026082918e-05,
"loss": 4.306,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567437431331866e-05,
"loss": 4.3142,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566598836580814e-05,
"loss": 4.3224,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565760241829762e-05,
"loss": 4.3221,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564921647078709e-05,
"loss": 4.315,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564084690208031e-05,
"loss": 4.3246,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563246095456979e-05,
"loss": 4.3248,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.562407500705927e-05,
"loss": 4.3102,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.561568905954874e-05,
"loss": 4.309,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560730311203822e-05,
"loss": 4.3175,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.559891716452771e-05,
"loss": 4.3128,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559053121701719e-05,
"loss": 4.311,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558214526950667e-05,
"loss": 4.3075,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557377570079988e-05,
"loss": 4.315,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556538975328936e-05,
"loss": 4.321,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555700380577884e-05,
"loss": 4.3115,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554861785826832e-05,
"loss": 4.2955,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.5540248289561526e-05,
"loss": 4.2983,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.5531862342051006e-05,
"loss": 4.3058,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523476394540486e-05,
"loss": 4.3146,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515090447029966e-05,
"loss": 4.3093,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.5506720878323175e-05,
"loss": 4.2987,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.5498334930812655e-05,
"loss": 4.3116,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.548996536210587e-05,
"loss": 4.3041,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.548157941459535e-05,
"loss": 4.3001,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.547319346708483e-05,
"loss": 4.3022,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.546480751957431e-05,
"loss": 4.3061,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.545642157206379e-05,
"loss": 4.3153,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.544803562455327e-05,
"loss": 4.2963,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.543964967704275e-05,
"loss": 4.2864,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543126372953223e-05,
"loss": 4.3042,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542287778202171e-05,
"loss": 4.2981,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541450821331492e-05,
"loss": 4.3129,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.54061222658044e-05,
"loss": 4.3055,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539773631829388e-05,
"loss": 4.2937,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.538935037078336e-05,
"loss": 4.2878,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.538096442327284e-05,
"loss": 4.3039,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372594854566055e-05,
"loss": 4.2841,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364208907055535e-05,
"loss": 4.2963,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5355822959545015e-05,
"loss": 4.2889,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347437012034495e-05,
"loss": 4.2973,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.5339051064523975e-05,
"loss": 4.2819,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.5330665117013455e-05,
"loss": 4.3016,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.5322295548306664e-05,
"loss": 4.2872,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.5313909600796144e-05,
"loss": 4.2846,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.5305523653285624e-05,
"loss": 4.2996,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.5297137705775104e-05,
"loss": 4.2831,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528875175826458e-05,
"loss": 4.309,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528038218955779e-05,
"loss": 4.2958,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527201262085101e-05,
"loss": 4.2937,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526362667334049e-05,
"loss": 4.2863,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525524072582997e-05,
"loss": 4.2901,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524685477831945e-05,
"loss": 4.2905,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523846883080893e-05,
"loss": 4.2849,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.52300828832984e-05,
"loss": 4.295,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522169693578788e-05,
"loss": 4.2888,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521331098827736e-05,
"loss": 4.2837,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.520494141957057e-05,
"loss": 4.2852,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.519655547206005e-05,
"loss": 4.2854,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.518816952454953e-05,
"loss": 4.2779,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517978357703902e-05,
"loss": 4.293,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517141400833223e-05,
"loss": 4.2739,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516302806082171e-05,
"loss": 4.293,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515465849211492e-05,
"loss": 4.2889,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.51462725446044e-05,
"loss": 4.2874,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.5137886597093876e-05,
"loss": 4.278,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.5129500649583356e-05,
"loss": 4.2803,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.5121114702072836e-05,
"loss": 4.2898,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.5112728754562316e-05,
"loss": 4.2893,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.5104342807051795e-05,
"loss": 4.2788,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.5095956859541275e-05,
"loss": 4.286,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.5087570912030755e-05,
"loss": 4.2844,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.5079184964520235e-05,
"loss": 4.2908,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.5070799017009715e-05,
"loss": 4.2756,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.5062413069499195e-05,
"loss": 4.2918,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505402712198868e-05,
"loss": 4.2837,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504565755328189e-05,
"loss": 4.2786,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503727160577137e-05,
"loss": 4.2777,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502888565826085e-05,
"loss": 4.2852,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502049971075033e-05,
"loss": 4.2756,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.501211376323981e-05,
"loss": 4.2644,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500374419453302e-05,
"loss": 4.2808,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.265576362609863,
"eval_runtime": 284.2057,
"eval_samples_per_second": 1342.658,
"eval_steps_per_second": 41.959,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.49953582470225e-05,
"loss": 4.2686,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498697229951198e-05,
"loss": 4.2613,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.497858635200146e-05,
"loss": 4.2868,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.497020040449093e-05,
"loss": 4.2825,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.496181445698042e-05,
"loss": 4.2788,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.49534285094699e-05,
"loss": 4.2714,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.494504256195938e-05,
"loss": 4.2755,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.493665661444886e-05,
"loss": 4.2564,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.492827066693834e-05,
"loss": 4.2801,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.491988471942782e-05,
"loss": 4.2775,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.49114987719173e-05,
"loss": 4.2703,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490311282440678e-05,
"loss": 4.2825,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489474325569999e-05,
"loss": 4.2615,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.488635730818947e-05,
"loss": 4.2711,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487797136067895e-05,
"loss": 4.2626,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486958541316843e-05,
"loss": 4.2605,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.486119946565791e-05,
"loss": 4.2641,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.485281351814739e-05,
"loss": 4.2616,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484442757063687e-05,
"loss": 4.2669,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483604162312635e-05,
"loss": 4.2819,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.4827672054419564e-05,
"loss": 4.2703,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.4819286106909044e-05,
"loss": 4.2753,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.4810900159398524e-05,
"loss": 4.2647,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.4802514211888004e-05,
"loss": 4.2747,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479412826437748e-05,
"loss": 4.26,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478575869567069e-05,
"loss": 4.2663,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.477737274816017e-05,
"loss": 4.2586,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476898680064965e-05,
"loss": 4.2541,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.4760600853139126e-05,
"loss": 4.2539,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.4752214905628606e-05,
"loss": 4.261,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474384533692182e-05,
"loss": 4.2595,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.47354593894113e-05,
"loss": 4.2697,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472707344190078e-05,
"loss": 4.2638,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471868749439026e-05,
"loss": 4.2664,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.471031792568348e-05,
"loss": 4.2563,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.470193197817295e-05,
"loss": 4.2709,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.469354603066243e-05,
"loss": 4.252,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.468516008315191e-05,
"loss": 4.2576,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.467677413564139e-05,
"loss": 4.2414,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.466838818813087e-05,
"loss": 4.2553,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.466000224062035e-05,
"loss": 4.2538,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.465161629310983e-05,
"loss": 4.2635,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.464324672440304e-05,
"loss": 4.2469,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.4634860776892526e-05,
"loss": 4.2577,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.4626474829382006e-05,
"loss": 4.2597,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.4618088881871486e-05,
"loss": 4.262,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4609702934360966e-05,
"loss": 4.2588,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601333365654175e-05,
"loss": 4.2439,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4592947418143655e-05,
"loss": 4.2358,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584577849436864e-05,
"loss": 4.2622,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576191901926344e-05,
"loss": 4.2546,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4567805954415824e-05,
"loss": 4.2488,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.4559420006905304e-05,
"loss": 4.2493,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.4551034059394784e-05,
"loss": 4.2469,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.4542648111884264e-05,
"loss": 4.2312,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.4534262164373744e-05,
"loss": 4.2499,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.4525876216863224e-05,
"loss": 4.2348,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.4517490269352704e-05,
"loss": 4.2431,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450912070064592e-05,
"loss": 4.2552,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.45007347531354e-05,
"loss": 4.2395,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449234880562488e-05,
"loss": 4.2344,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448397923691809e-05,
"loss": 4.2484,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.447559328940757e-05,
"loss": 4.2262,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446720734189705e-05,
"loss": 4.2383,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445882139438653e-05,
"loss": 4.2451,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445043544687601e-05,
"loss": 4.2433,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444204949936548e-05,
"loss": 4.2332,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443366355185496e-05,
"loss": 4.2317,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.442527760434444e-05,
"loss": 4.2337,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.441689165683393e-05,
"loss": 4.2447,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.440850570932341e-05,
"loss": 4.2441,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440013614061662e-05,
"loss": 4.2392,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.43917501931061e-05,
"loss": 4.2473,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438336424559558e-05,
"loss": 4.2494,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437497829808506e-05,
"loss": 4.2365,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436659235057454e-05,
"loss": 4.2291,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435820640306402e-05,
"loss": 4.2465,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.4349836834357227e-05,
"loss": 4.2391,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.4341450886846707e-05,
"loss": 4.2317,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.4333064939336186e-05,
"loss": 4.2336,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.4324678991825666e-05,
"loss": 4.2407,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.4316293044315146e-05,
"loss": 4.248,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.4307907096804626e-05,
"loss": 4.2341,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.429952114929411e-05,
"loss": 4.2216,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.429115158058732e-05,
"loss": 4.2305,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.42827656330768e-05,
"loss": 4.2251,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.427437968556628e-05,
"loss": 4.2401,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.426599373805576e-05,
"loss": 4.2359,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425760779054524e-05,
"loss": 4.2232,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424923822183845e-05,
"loss": 4.239,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424085227432793e-05,
"loss": 4.2286,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.423246632681741e-05,
"loss": 4.2319,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.422408037930689e-05,
"loss": 4.2252,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.421569443179637e-05,
"loss": 4.2309,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420730848428585e-05,
"loss": 4.2442,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419892253677533e-05,
"loss": 4.229,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190569346872276e-05,
"loss": 4.2115,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182183399361756e-05,
"loss": 4.2284,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.4173797451851236e-05,
"loss": 4.228,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.4165411504340716e-05,
"loss": 4.2352,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.4157025556830196e-05,
"loss": 4.2376,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.4148639609319676e-05,
"loss": 4.2229,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414025366180915e-05,
"loss": 4.2179,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413186771429863e-05,
"loss": 4.2312,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.4123498145591845e-05,
"loss": 4.2083,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.411511219808132e-05,
"loss": 4.2252,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106726250570805e-05,
"loss": 4.2173,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.4098340303060284e-05,
"loss": 4.2269,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.4089954355549764e-05,
"loss": 4.2133,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.4081584786842974e-05,
"loss": 4.2298,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407321521813619e-05,
"loss": 4.2157,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406482927062567e-05,
"loss": 4.2143,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405644332311514e-05,
"loss": 4.2289,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404805737560462e-05,
"loss": 4.2173,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.40396714280941e-05,
"loss": 4.2373,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.403128548058358e-05,
"loss": 4.2256,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.402291591187679e-05,
"loss": 4.2195,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401452996436627e-05,
"loss": 4.2261,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400614401685576e-05,
"loss": 4.2136,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.399775806934524e-05,
"loss": 4.223,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398938850063845e-05,
"loss": 4.216,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398100255312793e-05,
"loss": 4.2279,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397261660561741e-05,
"loss": 4.2168,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396423065810689e-05,
"loss": 4.2133,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395584471059637e-05,
"loss": 4.2162,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394745876308585e-05,
"loss": 4.2193,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393907281557533e-05,
"loss": 4.2096,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.393068686806481e-05,
"loss": 4.2229,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392230092055429e-05,
"loss": 4.2092,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.3913931351847496e-05,
"loss": 4.2254,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.3905545404336976e-05,
"loss": 4.2192,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.3897159456826456e-05,
"loss": 4.2202,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.3888773509315936e-05,
"loss": 4.2113,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388040394060915e-05,
"loss": 4.2122,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.387201799309863e-05,
"loss": 4.2254,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.386364842439184e-05,
"loss": 4.2173,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.385526247688132e-05,
"loss": 4.2123,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.38468765293708e-05,
"loss": 4.2219,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.383849058186028e-05,
"loss": 4.2171,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.383010463434976e-05,
"loss": 4.2248,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.382173506564297e-05,
"loss": 4.2127,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.381334911813245e-05,
"loss": 4.2229,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.380496317062193e-05,
"loss": 4.2153,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379657722311141e-05,
"loss": 4.2126,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378819127560089e-05,
"loss": 4.2145,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3779805328090376e-05,
"loss": 4.2153,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771419380579856e-05,
"loss": 4.2131,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763033433069336e-05,
"loss": 4.2008,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.375464748555881e-05,
"loss": 4.2147,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.208554267883301,
"eval_runtime": 299.6848,
"eval_samples_per_second": 1273.308,
"eval_steps_per_second": 39.792,
"step": 381600
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.576778732850636e+17,
"trial_name": null,
"trial_params": null
}