abhinavp's picture
Training in progress, epoch 0, checkpoint
174634c verified
raw
history blame
No virus
93.1 kB
{
"best_metric": 4.202013969421387,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sent-neg/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": 10.8186,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 7.553,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 7.0592,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 6.9948,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 6.948,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 6.9162,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 6.7528,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 6.641,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 6.5477,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 6.473,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 6.4158,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 6.3505,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989936862987376e-05,
"loss": 6.2821,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989098268236324e-05,
"loss": 6.2031,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988259673485272e-05,
"loss": 6.1533,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.98742107873422e-05,
"loss": 6.0877,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986582483983168e-05,
"loss": 6.0439,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985743889232116e-05,
"loss": 5.9966,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984905294481064e-05,
"loss": 5.9585,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984066699730012e-05,
"loss": 5.9177,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 5.8838,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 5.8444,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 5.8116,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 5.7794,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 5.7602,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790384069844466e-05,
"loss": 5.7233,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9781998122333946e-05,
"loss": 5.6991,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773612174823426e-05,
"loss": 5.6725,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 5.6432,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756856658606115e-05,
"loss": 5.6329,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748470711095595e-05,
"loss": 5.6088,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.974008476358507e-05,
"loss": 5.5993,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.973169881607455e-05,
"loss": 5.5635,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.972331286856403e-05,
"loss": 5.5524,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.9714943299857244e-05,
"loss": 5.5409,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 5.5228,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 5.5022,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968980183612942e-05,
"loss": 5.4685,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.96814158886189e-05,
"loss": 5.4697,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967302994110837e-05,
"loss": 5.4366,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966464399359785e-05,
"loss": 5.4386,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.965625804608733e-05,
"loss": 5.4212,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964787209857681e-05,
"loss": 5.4101,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963948615106629e-05,
"loss": 5.3925,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.96311165823595e-05,
"loss": 5.3855,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.962273063484898e-05,
"loss": 5.3848,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.961434468733847e-05,
"loss": 5.3673,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.960595873982795e-05,
"loss": 5.363,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.959757279231743e-05,
"loss": 5.3348,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.958918684480691e-05,
"loss": 5.3217,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958080089729639e-05,
"loss": 5.3314,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957241494978587e-05,
"loss": 5.3156,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956404538107908e-05,
"loss": 5.3077,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955567581237229e-05,
"loss": 5.2786,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954728986486177e-05,
"loss": 5.2929,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953890391735125e-05,
"loss": 5.2686,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.9530517969840727e-05,
"loss": 5.2897,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.9522132022330207e-05,
"loss": 5.2401,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.9513746074819686e-05,
"loss": 5.2521,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.9505360127309166e-05,
"loss": 5.2318,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949699055860238e-05,
"loss": 5.2208,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948860461109186e-05,
"loss": 5.2221,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.948023504238507e-05,
"loss": 5.2075,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947184909487455e-05,
"loss": 5.1871,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946346314736403e-05,
"loss": 5.1891,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945507719985351e-05,
"loss": 5.208,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944669125234299e-05,
"loss": 5.1806,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.94383216836362e-05,
"loss": 5.1691,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942993573612568e-05,
"loss": 5.1589,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.942154978861516e-05,
"loss": 5.1426,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.941316384110464e-05,
"loss": 5.1579,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404794272397856e-05,
"loss": 5.1498,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396408324887336e-05,
"loss": 5.1414,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388038756180545e-05,
"loss": 5.1477,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379652808670025e-05,
"loss": 5.1318,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371266861159505e-05,
"loss": 5.1268,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 5.1051,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 5.1052,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.9346125397431674e-05,
"loss": 5.0958,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.9337739449921154e-05,
"loss": 5.0873,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.9329353502410634e-05,
"loss": 5.0878,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.9320967554900114e-05,
"loss": 5.0846,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.9312581607389594e-05,
"loss": 5.0857,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.9304195659879074e-05,
"loss": 5.0759,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.9295809712368554e-05,
"loss": 5.0512,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.9287423764858034e-05,
"loss": 5.0608,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.9279037817347514e-05,
"loss": 5.0619,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.9270651869836994e-05,
"loss": 5.063,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.92622823011302e-05,
"loss": 5.0407,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925389635361968e-05,
"loss": 5.0444,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924551040610916e-05,
"loss": 5.0357,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923712445859864e-05,
"loss": 5.027,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922873851108812e-05,
"loss": 5.0221,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92203525635776e-05,
"loss": 5.0192,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921196661606708e-05,
"loss": 5.0048,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920358066855656e-05,
"loss": 5.0142,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919521109984978e-05,
"loss": 4.9967,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918684153114299e-05,
"loss": 4.9891,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.917845558363247e-05,
"loss": 4.9853,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.917006963612195e-05,
"loss": 4.9887,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.916168368861143e-05,
"loss": 4.9828,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915329774110091e-05,
"loss": 4.9678,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.9144928172394116e-05,
"loss": 4.97,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136542224883596e-05,
"loss": 4.9575,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.9128156277373076e-05,
"loss": 4.9601,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.9119770329862556e-05,
"loss": 4.9375,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.9111400761155765e-05,
"loss": 4.9463,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.9103014813645245e-05,
"loss": 4.94,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909462886613473e-05,
"loss": 4.9354,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.9402,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907787334991742e-05,
"loss": 4.9329,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.90694874024069e-05,
"loss": 4.912,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906110145489638e-05,
"loss": 4.9222,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905271550738586e-05,
"loss": 4.924,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904432955987534e-05,
"loss": 4.9163,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903594361236482e-05,
"loss": 4.9159,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.90275576648543e-05,
"loss": 4.9069,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901917171734378e-05,
"loss": 4.902,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901078576983326e-05,
"loss": 4.891,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.900239982232274e-05,
"loss": 4.8984,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994013874812214e-05,
"loss": 4.8945,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985660684909166e-05,
"loss": 4.8782,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977274737398646e-05,
"loss": 4.8804,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968888789888125e-05,
"loss": 4.8756,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.883,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.8598,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.8656,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.853,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926975431139254e-05,
"loss": 4.8599,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918589483628734e-05,
"loss": 4.8494,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910203536118214e-05,
"loss": 4.8632,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890181758860769e-05,
"loss": 4.851,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.88934480199009e-05,
"loss": 4.844,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888506207239038e-05,
"loss": 4.8432,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.8375,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.8448,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.8437,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.8339,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.8289,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.8303,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.8183,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.8061,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.815,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.8067,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.7986,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.798,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877607751236109e-05,
"loss": 4.7965,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.7984,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.8001,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.7883,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.753722667694092,
"eval_runtime": 297.919,
"eval_samples_per_second": 1280.855,
"eval_steps_per_second": 40.028,
"step": 76320
},
{
"epoch": 1.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.7777,
"step": 76800
},
{
"epoch": 1.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.7753,
"step": 77312
},
{
"epoch": 1.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.7861,
"step": 77824
},
{
"epoch": 1.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.7783,
"step": 78336
},
{
"epoch": 1.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.7805,
"step": 78848
},
{
"epoch": 1.0,
"learning_rate": 4.8700653121177595e-05,
"loss": 4.7634,
"step": 79360
},
{
"epoch": 1.0,
"learning_rate": 4.8692267173667075e-05,
"loss": 4.7647,
"step": 79872
},
{
"epoch": 1.0,
"learning_rate": 4.8683881226156555e-05,
"loss": 4.759,
"step": 80384
},
{
"epoch": 1.0,
"learning_rate": 4.867549527864604e-05,
"loss": 4.7636,
"step": 80896
},
{
"epoch": 1.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.7644,
"step": 81408
},
{
"epoch": 1.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.7605,
"step": 81920
},
{
"epoch": 1.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.7656,
"step": 82432
},
{
"epoch": 1.0,
"learning_rate": 4.864195148860396e-05,
"loss": 4.7361,
"step": 82944
},
{
"epoch": 1.0,
"learning_rate": 4.863356554109344e-05,
"loss": 4.7466,
"step": 83456
},
{
"epoch": 1.0,
"learning_rate": 4.862517959358292e-05,
"loss": 4.7404,
"step": 83968
},
{
"epoch": 1.0,
"learning_rate": 4.86167936460724e-05,
"loss": 4.7309,
"step": 84480
},
{
"epoch": 1.0,
"learning_rate": 4.8608407698561874e-05,
"loss": 4.7451,
"step": 84992
},
{
"epoch": 1.0,
"learning_rate": 4.860005450865882e-05,
"loss": 4.7345,
"step": 85504
},
{
"epoch": 1.0,
"learning_rate": 4.85916685611483e-05,
"loss": 4.7316,
"step": 86016
},
{
"epoch": 1.0,
"learning_rate": 4.858329899244151e-05,
"loss": 4.7522,
"step": 86528
},
{
"epoch": 1.0,
"learning_rate": 4.8574913044930995e-05,
"loss": 4.7317,
"step": 87040
},
{
"epoch": 1.0,
"learning_rate": 4.8566527097420475e-05,
"loss": 4.7278,
"step": 87552
},
{
"epoch": 1.0,
"learning_rate": 4.8558141149909955e-05,
"loss": 4.7262,
"step": 88064
},
{
"epoch": 1.0,
"learning_rate": 4.8549755202399435e-05,
"loss": 4.7386,
"step": 88576
},
{
"epoch": 1.0,
"learning_rate": 4.8541369254888915e-05,
"loss": 4.7188,
"step": 89088
},
{
"epoch": 1.0,
"learning_rate": 4.8532983307378395e-05,
"loss": 4.7154,
"step": 89600
},
{
"epoch": 1.0,
"learning_rate": 4.8524597359867875e-05,
"loss": 4.7148,
"step": 90112
},
{
"epoch": 1.0,
"learning_rate": 4.851621141235735e-05,
"loss": 4.711,
"step": 90624
},
{
"epoch": 1.0,
"learning_rate": 4.8507841843650564e-05,
"loss": 4.71,
"step": 91136
},
{
"epoch": 1.01,
"learning_rate": 4.8499455896140044e-05,
"loss": 4.7026,
"step": 91648
},
{
"epoch": 1.01,
"learning_rate": 4.8491069948629524e-05,
"loss": 4.7243,
"step": 92160
},
{
"epoch": 1.01,
"learning_rate": 4.8482684001119e-05,
"loss": 4.7044,
"step": 92672
},
{
"epoch": 1.01,
"learning_rate": 4.847429805360848e-05,
"loss": 4.7026,
"step": 93184
},
{
"epoch": 1.01,
"learning_rate": 4.846592848490169e-05,
"loss": 4.7048,
"step": 93696
},
{
"epoch": 1.01,
"learning_rate": 4.845755891619491e-05,
"loss": 4.7023,
"step": 94208
},
{
"epoch": 1.01,
"learning_rate": 4.844917296868439e-05,
"loss": 4.6963,
"step": 94720
},
{
"epoch": 1.01,
"learning_rate": 4.844078702117387e-05,
"loss": 4.6777,
"step": 95232
},
{
"epoch": 1.01,
"learning_rate": 4.843240107366335e-05,
"loss": 4.6842,
"step": 95744
},
{
"epoch": 1.01,
"learning_rate": 4.842401512615282e-05,
"loss": 4.6713,
"step": 96256
},
{
"epoch": 1.01,
"learning_rate": 4.84156291786423e-05,
"loss": 4.6881,
"step": 96768
},
{
"epoch": 1.01,
"learning_rate": 4.840724323113178e-05,
"loss": 4.6769,
"step": 97280
},
{
"epoch": 1.01,
"learning_rate": 4.839885728362126e-05,
"loss": 4.68,
"step": 97792
},
{
"epoch": 1.01,
"learning_rate": 4.839047133611074e-05,
"loss": 4.6711,
"step": 98304
},
{
"epoch": 1.01,
"learning_rate": 4.838208538860022e-05,
"loss": 4.6752,
"step": 98816
},
{
"epoch": 1.01,
"learning_rate": 4.83736994410897e-05,
"loss": 4.6791,
"step": 99328
},
{
"epoch": 1.01,
"learning_rate": 4.836532987238292e-05,
"loss": 4.67,
"step": 99840
},
{
"epoch": 1.01,
"learning_rate": 4.83569439248724e-05,
"loss": 4.6746,
"step": 100352
},
{
"epoch": 1.01,
"learning_rate": 4.834855797736188e-05,
"loss": 4.6606,
"step": 100864
},
{
"epoch": 1.01,
"learning_rate": 4.834017202985136e-05,
"loss": 4.6562,
"step": 101376
},
{
"epoch": 1.01,
"learning_rate": 4.833178608234084e-05,
"loss": 4.6653,
"step": 101888
},
{
"epoch": 1.01,
"learning_rate": 4.832340013483032e-05,
"loss": 4.6606,
"step": 102400
},
{
"epoch": 1.01,
"learning_rate": 4.83150141873198e-05,
"loss": 4.667,
"step": 102912
},
{
"epoch": 1.01,
"learning_rate": 4.830662823980928e-05,
"loss": 4.6373,
"step": 103424
},
{
"epoch": 1.01,
"learning_rate": 4.8298258671102486e-05,
"loss": 4.6617,
"step": 103936
},
{
"epoch": 1.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.6371,
"step": 104448
},
{
"epoch": 1.01,
"learning_rate": 4.8281503154885175e-05,
"loss": 4.6708,
"step": 104960
},
{
"epoch": 1.01,
"learning_rate": 4.8273117207374655e-05,
"loss": 4.6332,
"step": 105472
},
{
"epoch": 1.01,
"learning_rate": 4.8264731259864135e-05,
"loss": 4.6492,
"step": 105984
},
{
"epoch": 1.01,
"learning_rate": 4.8256345312353615e-05,
"loss": 4.6379,
"step": 106496
},
{
"epoch": 1.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.6292,
"step": 107008
},
{
"epoch": 1.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.6351,
"step": 107520
},
{
"epoch": 1.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.6342,
"step": 108032
},
{
"epoch": 1.01,
"learning_rate": 4.8222801522311535e-05,
"loss": 4.6158,
"step": 108544
},
{
"epoch": 1.01,
"learning_rate": 4.821443195360475e-05,
"loss": 4.6226,
"step": 109056
},
{
"epoch": 1.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.6382,
"step": 109568
},
{
"epoch": 1.01,
"learning_rate": 4.819766005858371e-05,
"loss": 4.624,
"step": 110080
},
{
"epoch": 1.01,
"learning_rate": 4.8189274111073184e-05,
"loss": 4.6218,
"step": 110592
},
{
"epoch": 1.01,
"learning_rate": 4.81809045423664e-05,
"loss": 4.6186,
"step": 111104
},
{
"epoch": 1.01,
"learning_rate": 4.817251859485588e-05,
"loss": 4.6063,
"step": 111616
},
{
"epoch": 1.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.6248,
"step": 112128
},
{
"epoch": 1.01,
"learning_rate": 4.815574669983483e-05,
"loss": 4.62,
"step": 112640
},
{
"epoch": 1.01,
"learning_rate": 4.814736075232432e-05,
"loss": 4.6213,
"step": 113152
},
{
"epoch": 1.01,
"learning_rate": 4.8139007562421265e-05,
"loss": 4.6285,
"step": 113664
},
{
"epoch": 1.01,
"learning_rate": 4.8130621614910745e-05,
"loss": 4.6234,
"step": 114176
},
{
"epoch": 1.01,
"learning_rate": 4.8122235667400224e-05,
"loss": 4.6199,
"step": 114688
},
{
"epoch": 1.01,
"learning_rate": 4.8113849719889704e-05,
"loss": 4.5992,
"step": 115200
},
{
"epoch": 1.01,
"learning_rate": 4.8105463772379184e-05,
"loss": 4.6108,
"step": 115712
},
{
"epoch": 1.01,
"learning_rate": 4.809707782486866e-05,
"loss": 4.605,
"step": 116224
},
{
"epoch": 1.01,
"learning_rate": 4.808869187735814e-05,
"loss": 4.5942,
"step": 116736
},
{
"epoch": 1.01,
"learning_rate": 4.808030592984762e-05,
"loss": 4.6048,
"step": 117248
},
{
"epoch": 1.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.6041,
"step": 117760
},
{
"epoch": 1.01,
"learning_rate": 4.8063550413630307e-05,
"loss": 4.6135,
"step": 118272
},
{
"epoch": 1.01,
"learning_rate": 4.8055164466119786e-05,
"loss": 4.6043,
"step": 118784
},
{
"epoch": 1.01,
"learning_rate": 4.8046794897413e-05,
"loss": 4.584,
"step": 119296
},
{
"epoch": 1.01,
"learning_rate": 4.803840894990248e-05,
"loss": 4.5928,
"step": 119808
},
{
"epoch": 1.01,
"learning_rate": 4.803002300239196e-05,
"loss": 4.603,
"step": 120320
},
{
"epoch": 1.01,
"learning_rate": 4.802163705488144e-05,
"loss": 4.6049,
"step": 120832
},
{
"epoch": 1.01,
"learning_rate": 4.801325110737092e-05,
"loss": 4.5946,
"step": 121344
},
{
"epoch": 1.01,
"learning_rate": 4.80048651598604e-05,
"loss": 4.5987,
"step": 121856
},
{
"epoch": 1.02,
"learning_rate": 4.799649559115361e-05,
"loss": 4.5934,
"step": 122368
},
{
"epoch": 1.02,
"learning_rate": 4.798810964364309e-05,
"loss": 4.5815,
"step": 122880
},
{
"epoch": 1.02,
"learning_rate": 4.797972369613257e-05,
"loss": 4.5883,
"step": 123392
},
{
"epoch": 1.02,
"learning_rate": 4.797133774862205e-05,
"loss": 4.5879,
"step": 123904
},
{
"epoch": 1.02,
"learning_rate": 4.796295180111153e-05,
"loss": 4.5774,
"step": 124416
},
{
"epoch": 1.02,
"learning_rate": 4.795458223240474e-05,
"loss": 4.5928,
"step": 124928
},
{
"epoch": 1.02,
"learning_rate": 4.794619628489423e-05,
"loss": 4.575,
"step": 125440
},
{
"epoch": 1.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.5723,
"step": 125952
},
{
"epoch": 1.02,
"learning_rate": 4.792942438987319e-05,
"loss": 4.5741,
"step": 126464
},
{
"epoch": 1.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.5811,
"step": 126976
},
{
"epoch": 1.02,
"learning_rate": 4.791265249485215e-05,
"loss": 4.5785,
"step": 127488
},
{
"epoch": 1.02,
"learning_rate": 4.790426654734163e-05,
"loss": 4.5667,
"step": 128000
},
{
"epoch": 1.02,
"learning_rate": 4.7895880599831107e-05,
"loss": 4.5663,
"step": 128512
},
{
"epoch": 1.02,
"learning_rate": 4.7887494652320587e-05,
"loss": 4.5614,
"step": 129024
},
{
"epoch": 1.02,
"learning_rate": 4.7879108704810067e-05,
"loss": 4.5712,
"step": 129536
},
{
"epoch": 1.02,
"learning_rate": 4.7870722757299546e-05,
"loss": 4.5476,
"step": 130048
},
{
"epoch": 1.02,
"learning_rate": 4.786233680978902e-05,
"loss": 4.5558,
"step": 130560
},
{
"epoch": 1.02,
"learning_rate": 4.7853967241082236e-05,
"loss": 4.565,
"step": 131072
},
{
"epoch": 1.02,
"learning_rate": 4.7845581293571715e-05,
"loss": 4.5587,
"step": 131584
},
{
"epoch": 1.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.5587,
"step": 132096
},
{
"epoch": 1.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.5572,
"step": 132608
},
{
"epoch": 1.02,
"learning_rate": 4.782043982984389e-05,
"loss": 4.5471,
"step": 133120
},
{
"epoch": 1.02,
"learning_rate": 4.781205388233337e-05,
"loss": 4.556,
"step": 133632
},
{
"epoch": 1.02,
"learning_rate": 4.780368431362658e-05,
"loss": 4.5537,
"step": 134144
},
{
"epoch": 1.02,
"learning_rate": 4.779529836611606e-05,
"loss": 4.553,
"step": 134656
},
{
"epoch": 1.02,
"learning_rate": 4.778691241860554e-05,
"loss": 4.5567,
"step": 135168
},
{
"epoch": 1.02,
"learning_rate": 4.777852647109502e-05,
"loss": 4.5559,
"step": 135680
},
{
"epoch": 1.02,
"learning_rate": 4.777014052358449e-05,
"loss": 4.5462,
"step": 136192
},
{
"epoch": 1.02,
"learning_rate": 4.776175457607397e-05,
"loss": 4.5402,
"step": 136704
},
{
"epoch": 1.02,
"learning_rate": 4.775336862856345e-05,
"loss": 4.5509,
"step": 137216
},
{
"epoch": 1.02,
"learning_rate": 4.774499905985666e-05,
"loss": 4.5447,
"step": 137728
},
{
"epoch": 1.02,
"learning_rate": 4.773661311234615e-05,
"loss": 4.5318,
"step": 138240
},
{
"epoch": 1.02,
"learning_rate": 4.772822716483563e-05,
"loss": 4.5421,
"step": 138752
},
{
"epoch": 1.02,
"learning_rate": 4.771984121732511e-05,
"loss": 4.5356,
"step": 139264
},
{
"epoch": 1.02,
"learning_rate": 4.771145526981459e-05,
"loss": 4.5459,
"step": 139776
},
{
"epoch": 1.02,
"learning_rate": 4.770306932230407e-05,
"loss": 4.5295,
"step": 140288
},
{
"epoch": 1.02,
"learning_rate": 4.769468337479355e-05,
"loss": 4.5369,
"step": 140800
},
{
"epoch": 1.02,
"learning_rate": 4.768629742728303e-05,
"loss": 4.5144,
"step": 141312
},
{
"epoch": 1.02,
"learning_rate": 4.767792785857624e-05,
"loss": 4.538,
"step": 141824
},
{
"epoch": 1.02,
"learning_rate": 4.766954191106572e-05,
"loss": 4.5253,
"step": 142336
},
{
"epoch": 1.02,
"learning_rate": 4.766117234235893e-05,
"loss": 4.5435,
"step": 142848
},
{
"epoch": 1.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.5336,
"step": 143360
},
{
"epoch": 1.02,
"learning_rate": 4.764440044733789e-05,
"loss": 4.531,
"step": 143872
},
{
"epoch": 1.02,
"learning_rate": 4.763601449982737e-05,
"loss": 4.5212,
"step": 144384
},
{
"epoch": 1.02,
"learning_rate": 4.762762855231685e-05,
"loss": 4.5243,
"step": 144896
},
{
"epoch": 1.02,
"learning_rate": 4.761924260480633e-05,
"loss": 4.5351,
"step": 145408
},
{
"epoch": 1.02,
"learning_rate": 4.761087303609954e-05,
"loss": 4.5393,
"step": 145920
},
{
"epoch": 1.02,
"learning_rate": 4.760248708858902e-05,
"loss": 4.5278,
"step": 146432
},
{
"epoch": 1.02,
"learning_rate": 4.75941011410785e-05,
"loss": 4.5237,
"step": 146944
},
{
"epoch": 1.02,
"learning_rate": 4.758571519356798e-05,
"loss": 4.5221,
"step": 147456
},
{
"epoch": 1.02,
"learning_rate": 4.757732924605746e-05,
"loss": 4.5189,
"step": 147968
},
{
"epoch": 1.02,
"learning_rate": 4.756894329854694e-05,
"loss": 4.5113,
"step": 148480
},
{
"epoch": 1.02,
"learning_rate": 4.756055735103642e-05,
"loss": 4.5196,
"step": 148992
},
{
"epoch": 1.02,
"learning_rate": 4.755218778232963e-05,
"loss": 4.5119,
"step": 149504
},
{
"epoch": 1.02,
"learning_rate": 4.754380183481911e-05,
"loss": 4.5069,
"step": 150016
},
{
"epoch": 1.02,
"learning_rate": 4.753541588730859e-05,
"loss": 4.5095,
"step": 150528
},
{
"epoch": 1.02,
"learning_rate": 4.752702993979807e-05,
"loss": 4.5075,
"step": 151040
},
{
"epoch": 1.02,
"learning_rate": 4.751864399228755e-05,
"loss": 4.5108,
"step": 151552
},
{
"epoch": 1.02,
"learning_rate": 4.751027442358077e-05,
"loss": 4.5118,
"step": 152064
},
{
"epoch": 1.02,
"learning_rate": 4.750188847607025e-05,
"loss": 4.5088,
"step": 152576
},
{
"epoch": 1.03,
"eval_loss": 4.475302696228027,
"eval_runtime": 295.3079,
"eval_samples_per_second": 1292.18,
"eval_steps_per_second": 40.382,
"step": 152640
},
{
"epoch": 0.0,
"learning_rate": 4.749350252855973e-05,
"loss": 4.4942,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.748511658104921e-05,
"loss": 4.4973,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.747673063353868e-05,
"loss": 4.5066,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.746834468602816e-05,
"loss": 4.5038,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.745995873851764e-05,
"loss": 4.5091,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.745157279100712e-05,
"loss": 4.4866,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.74431868434966e-05,
"loss": 4.4975,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.743480089598608e-05,
"loss": 4.4891,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.742641494847556e-05,
"loss": 4.4978,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741802900096504e-05,
"loss": 4.4982,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740964305345452e-05,
"loss": 4.4991,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.7401257105944e-05,
"loss": 4.4996,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739287115843348e-05,
"loss": 4.4754,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.7384501589726696e-05,
"loss": 4.4845,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.7376115642216176e-05,
"loss": 4.4863,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.7367729694705656e-05,
"loss": 4.4776,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.7359343747195135e-05,
"loss": 4.4885,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.7350957799684615e-05,
"loss": 4.4801,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.7342571852174095e-05,
"loss": 4.48,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.733418590466357e-05,
"loss": 4.5073,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732579995715305e-05,
"loss": 4.4793,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731741400964253e-05,
"loss": 4.4829,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730902806213201e-05,
"loss": 4.4795,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.730064211462149e-05,
"loss": 4.4944,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.7292272545914704e-05,
"loss": 4.4736,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728390297720791e-05,
"loss": 4.472,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727551702969739e-05,
"loss": 4.4748,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.726713108218687e-05,
"loss": 4.4763,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.725874513467635e-05,
"loss": 4.4668,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.725035918716583e-05,
"loss": 4.4694,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.724197323965531e-05,
"loss": 4.4861,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.723360367094852e-05,
"loss": 4.4728,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225217723438e-05,
"loss": 4.4693,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721683177592748e-05,
"loss": 4.475,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720846220722069e-05,
"loss": 4.4704,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.720007625971017e-05,
"loss": 4.4669,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719169031219965e-05,
"loss": 4.4494,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718330436468914e-05,
"loss": 4.4634,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717491841717862e-05,
"loss": 4.447,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.71665324696681e-05,
"loss": 4.4617,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715814652215758e-05,
"loss": 4.4536,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714976057464706e-05,
"loss": 4.4612,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714137462713654e-05,
"loss": 4.453,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.7133021437233476e-05,
"loss": 4.4553,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.7124635489722956e-05,
"loss": 4.458,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116249542212436e-05,
"loss": 4.4559,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107863594701916e-05,
"loss": 4.4604,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099477647191396e-05,
"loss": 4.4454,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091091699680876e-05,
"loss": 4.4397,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082705752170356e-05,
"loss": 4.457,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.707433618346357e-05,
"loss": 4.4485,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.706595023595305e-05,
"loss": 4.4521,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.705756428844253e-05,
"loss": 4.431,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.704917834093201e-05,
"loss": 4.4565,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.704079239342149e-05,
"loss": 4.43,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.703240644591097e-05,
"loss": 4.4617,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.702402049840045e-05,
"loss": 4.4222,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015634550889924e-05,
"loss": 4.4472,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.7007248603379404e-05,
"loss": 4.4354,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.6998862655868884e-05,
"loss": 4.4333,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.6990476708358364e-05,
"loss": 4.4319,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.6982090760847844e-05,
"loss": 4.4354,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697372119214106e-05,
"loss": 4.4184,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696533524463054e-05,
"loss": 4.4239,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.6956965675923756e-05,
"loss": 4.4344,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694857972841323e-05,
"loss": 4.4315,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.694019378090271e-05,
"loss": 4.4241,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.6931824212195925e-05,
"loss": 4.423,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.69234382646854e-05,
"loss": 4.4186,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691505231717488e-05,
"loss": 4.4273,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690666636966436e-05,
"loss": 4.4269,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689828042215384e-05,
"loss": 4.4286,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688989447464332e-05,
"loss": 4.4373,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.68815085271328e-05,
"loss": 4.4361,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.687312257962228e-05,
"loss": 4.4337,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.6864753010915494e-05,
"loss": 4.4117,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.6856367063404974e-05,
"loss": 4.4232,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.6847981115894454e-05,
"loss": 4.4254,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.6839595168383934e-05,
"loss": 4.4072,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.6831209220873414e-05,
"loss": 4.4212,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.6822823273362894e-05,
"loss": 4.4194,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.6814437325852373e-05,
"loss": 4.429,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.6806051378341853e-05,
"loss": 4.4202,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679768180963506e-05,
"loss": 4.4017,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678931224092827e-05,
"loss": 4.4145,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678092629341775e-05,
"loss": 4.4203,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.677254034590723e-05,
"loss": 4.4248,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.676415439839671e-05,
"loss": 4.4169,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.675578482968993e-05,
"loss": 4.4227,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.674739888217941e-05,
"loss": 4.4185,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.673901293466889e-05,
"loss": 4.4025,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.673062698715837e-05,
"loss": 4.4166,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.672224103964785e-05,
"loss": 4.4096,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.671385509213733e-05,
"loss": 4.402,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705485523430536e-05,
"loss": 4.423,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.6697099575920016e-05,
"loss": 4.4047,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.6688713628409496e-05,
"loss": 4.3965,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.6680327680898976e-05,
"loss": 4.405,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.6671941733388456e-05,
"loss": 4.4113,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663555785877936e-05,
"loss": 4.4096,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655186217171145e-05,
"loss": 4.4004,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.664681664846436e-05,
"loss": 4.3942,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.663843070095384e-05,
"loss": 4.3941,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663004475344332e-05,
"loss": 4.4058,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.66216588059328e-05,
"loss": 4.3811,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.661327285842228e-05,
"loss": 4.3936,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660488691091176e-05,
"loss": 4.3997,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.6596500963401234e-05,
"loss": 4.3944,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.6588115015890714e-05,
"loss": 4.3943,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.6579729068380194e-05,
"loss": 4.3962,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.6571343120869674e-05,
"loss": 4.3874,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.6562957173359154e-05,
"loss": 4.393,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655458760465237e-05,
"loss": 4.3933,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654620165714185e-05,
"loss": 4.3904,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653781570963133e-05,
"loss": 4.3973,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.652942976212081e-05,
"loss": 4.3978,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.652106019341402e-05,
"loss": 4.3935,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.65126742459035e-05,
"loss": 4.3799,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.650428829839298e-05,
"loss": 4.3887,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649590235088246e-05,
"loss": 4.3871,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648751640337194e-05,
"loss": 4.3748,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.647913045586142e-05,
"loss": 4.3902,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647076088715463e-05,
"loss": 4.3759,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646237493964411e-05,
"loss": 4.3903,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645398899213359e-05,
"loss": 4.3751,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644560304462307e-05,
"loss": 4.3838,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.6437217097112554e-05,
"loss": 4.365,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642884752840576e-05,
"loss": 4.3846,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642046158089524e-05,
"loss": 4.3705,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641207563338472e-05,
"loss": 4.3915,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.64036896858742e-05,
"loss": 4.3868,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.639530373836368e-05,
"loss": 4.3797,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.638691779085316e-05,
"loss": 4.3694,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.637854822214637e-05,
"loss": 4.3743,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.637016227463585e-05,
"loss": 4.3868,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.636177632712533e-05,
"loss": 4.3923,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.635339037961481e-05,
"loss": 4.3774,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.634500443210429e-05,
"loss": 4.3786,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.633661848459377e-05,
"loss": 4.3771,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.632823253708325e-05,
"loss": 4.3755,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.631986296837647e-05,
"loss": 4.3671,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.631147702086595e-05,
"loss": 4.3709,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.630309107335542e-05,
"loss": 4.3696,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.62947051258449e-05,
"loss": 4.3644,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628631917833438e-05,
"loss": 4.3651,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627793323082386e-05,
"loss": 4.369,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626954728331334e-05,
"loss": 4.3627,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626117771460655e-05,
"loss": 4.3693,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625279176709603e-05,
"loss": 4.3647,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 4.341277122497559,
"eval_runtime": 300.372,
"eval_samples_per_second": 1270.395,
"eval_steps_per_second": 39.701,
"step": 228960
},
{
"epoch": 1.0,
"learning_rate": 4.624440581958551e-05,
"loss": 4.3616,
"step": 229376
},
{
"epoch": 1.0,
"learning_rate": 4.623601987207499e-05,
"loss": 4.3538,
"step": 229888
},
{
"epoch": 1.0,
"learning_rate": 4.6227633924564476e-05,
"loss": 4.3705,
"step": 230400
},
{
"epoch": 1.0,
"learning_rate": 4.6219247977053956e-05,
"loss": 4.361,
"step": 230912
},
{
"epoch": 1.0,
"learning_rate": 4.6210862029543436e-05,
"loss": 4.3702,
"step": 231424
},
{
"epoch": 1.0,
"learning_rate": 4.6202476082032916e-05,
"loss": 4.348,
"step": 231936
},
{
"epoch": 1.0,
"learning_rate": 4.6194106513326125e-05,
"loss": 4.3599,
"step": 232448
},
{
"epoch": 1.0,
"learning_rate": 4.6185720565815605e-05,
"loss": 4.3488,
"step": 232960
},
{
"epoch": 1.0,
"learning_rate": 4.6177350997108814e-05,
"loss": 4.3648,
"step": 233472
},
{
"epoch": 1.0,
"learning_rate": 4.6168965049598294e-05,
"loss": 4.3605,
"step": 233984
},
{
"epoch": 1.0,
"learning_rate": 4.6160579102087774e-05,
"loss": 4.3626,
"step": 234496
},
{
"epoch": 1.0,
"learning_rate": 4.6152193154577254e-05,
"loss": 4.3637,
"step": 235008
},
{
"epoch": 1.0,
"learning_rate": 4.6143807207066734e-05,
"loss": 4.3417,
"step": 235520
},
{
"epoch": 1.0,
"learning_rate": 4.6135421259556214e-05,
"loss": 4.3507,
"step": 236032
},
{
"epoch": 1.0,
"learning_rate": 4.612705169084942e-05,
"loss": 4.351,
"step": 236544
},
{
"epoch": 1.0,
"learning_rate": 4.611866574333891e-05,
"loss": 4.3482,
"step": 237056
},
{
"epoch": 1.0,
"learning_rate": 4.611027979582839e-05,
"loss": 4.3516,
"step": 237568
},
{
"epoch": 1.0,
"learning_rate": 4.610189384831787e-05,
"loss": 4.352,
"step": 238080
},
{
"epoch": 1.0,
"learning_rate": 4.609350790080735e-05,
"loss": 4.3449,
"step": 238592
},
{
"epoch": 1.0,
"learning_rate": 4.608512195329683e-05,
"loss": 4.3786,
"step": 239104
},
{
"epoch": 1.0,
"learning_rate": 4.607673600578631e-05,
"loss": 4.3471,
"step": 239616
},
{
"epoch": 1.0,
"learning_rate": 4.606835005827578e-05,
"loss": 4.3499,
"step": 240128
},
{
"epoch": 1.0,
"learning_rate": 4.6059980489569e-05,
"loss": 4.3513,
"step": 240640
},
{
"epoch": 1.0,
"learning_rate": 4.605161092086221e-05,
"loss": 4.3616,
"step": 241152
},
{
"epoch": 1.0,
"learning_rate": 4.604322497335169e-05,
"loss": 4.3433,
"step": 241664
},
{
"epoch": 1.0,
"learning_rate": 4.603483902584117e-05,
"loss": 4.3483,
"step": 242176
},
{
"epoch": 1.0,
"learning_rate": 4.602645307833065e-05,
"loss": 4.3438,
"step": 242688
},
{
"epoch": 1.0,
"learning_rate": 4.6018083509623864e-05,
"loss": 4.3462,
"step": 243200
},
{
"epoch": 1.0,
"learning_rate": 4.6009697562113344e-05,
"loss": 4.3361,
"step": 243712
},
{
"epoch": 1.01,
"learning_rate": 4.6001311614602824e-05,
"loss": 4.3455,
"step": 244224
},
{
"epoch": 1.01,
"learning_rate": 4.5992925667092303e-05,
"loss": 4.355,
"step": 244736
},
{
"epoch": 1.01,
"learning_rate": 4.598455609838551e-05,
"loss": 4.3473,
"step": 245248
},
{
"epoch": 1.01,
"learning_rate": 4.597617015087499e-05,
"loss": 4.3465,
"step": 245760
},
{
"epoch": 1.01,
"learning_rate": 4.596778420336447e-05,
"loss": 4.346,
"step": 246272
},
{
"epoch": 1.01,
"learning_rate": 4.595941463465768e-05,
"loss": 4.3446,
"step": 246784
},
{
"epoch": 1.01,
"learning_rate": 4.595102868714716e-05,
"loss": 4.3481,
"step": 247296
},
{
"epoch": 1.01,
"learning_rate": 4.594264273963664e-05,
"loss": 4.3249,
"step": 247808
},
{
"epoch": 1.01,
"learning_rate": 4.593425679212612e-05,
"loss": 4.3405,
"step": 248320
},
{
"epoch": 1.01,
"learning_rate": 4.59258708446156e-05,
"loss": 4.3229,
"step": 248832
},
{
"epoch": 1.01,
"learning_rate": 4.591748489710508e-05,
"loss": 4.3389,
"step": 249344
},
{
"epoch": 1.01,
"learning_rate": 4.59091153283983e-05,
"loss": 4.3332,
"step": 249856
},
{
"epoch": 1.01,
"learning_rate": 4.590072938088778e-05,
"loss": 4.3407,
"step": 250368
},
{
"epoch": 1.01,
"learning_rate": 4.589234343337726e-05,
"loss": 4.3328,
"step": 250880
},
{
"epoch": 1.01,
"learning_rate": 4.588395748586673e-05,
"loss": 4.3318,
"step": 251392
},
{
"epoch": 1.01,
"learning_rate": 4.587557153835621e-05,
"loss": 4.3399,
"step": 251904
},
{
"epoch": 1.01,
"learning_rate": 4.586718559084569e-05,
"loss": 4.3358,
"step": 252416
},
{
"epoch": 1.01,
"learning_rate": 4.585879964333517e-05,
"loss": 4.3362,
"step": 252928
},
{
"epoch": 1.01,
"learning_rate": 4.585041369582465e-05,
"loss": 4.3297,
"step": 253440
},
{
"epoch": 1.01,
"learning_rate": 4.584204412711786e-05,
"loss": 4.3156,
"step": 253952
},
{
"epoch": 1.01,
"learning_rate": 4.583365817960734e-05,
"loss": 4.3369,
"step": 254464
},
{
"epoch": 1.01,
"learning_rate": 4.582527223209682e-05,
"loss": 4.3288,
"step": 254976
},
{
"epoch": 1.01,
"learning_rate": 4.58168862845863e-05,
"loss": 4.3319,
"step": 255488
},
{
"epoch": 1.01,
"learning_rate": 4.5808516715879515e-05,
"loss": 4.3182,
"step": 256000
},
{
"epoch": 1.01,
"learning_rate": 4.5800130768368995e-05,
"loss": 4.3408,
"step": 256512
},
{
"epoch": 1.01,
"learning_rate": 4.5791744820858475e-05,
"loss": 4.3075,
"step": 257024
},
{
"epoch": 1.01,
"learning_rate": 4.5783358873347955e-05,
"loss": 4.3444,
"step": 257536
},
{
"epoch": 1.01,
"learning_rate": 4.5774972925837435e-05,
"loss": 4.3079,
"step": 258048
},
{
"epoch": 1.01,
"learning_rate": 4.5766586978326915e-05,
"loss": 4.3267,
"step": 258560
},
{
"epoch": 1.01,
"learning_rate": 4.5758201030816395e-05,
"loss": 4.3205,
"step": 259072
},
{
"epoch": 1.01,
"learning_rate": 4.5749815083305875e-05,
"loss": 4.3193,
"step": 259584
},
{
"epoch": 1.01,
"learning_rate": 4.5741429135795355e-05,
"loss": 4.3146,
"step": 260096
},
{
"epoch": 1.01,
"learning_rate": 4.5733059567088564e-05,
"loss": 4.3265,
"step": 260608
},
{
"epoch": 1.01,
"learning_rate": 4.572468999838177e-05,
"loss": 4.3017,
"step": 261120
},
{
"epoch": 1.01,
"learning_rate": 4.571630405087125e-05,
"loss": 4.3088,
"step": 261632
},
{
"epoch": 1.01,
"learning_rate": 4.570791810336074e-05,
"loss": 4.3236,
"step": 262144
},
{
"epoch": 1.01,
"learning_rate": 4.569953215585022e-05,
"loss": 4.3179,
"step": 262656
},
{
"epoch": 1.01,
"learning_rate": 4.56911462083397e-05,
"loss": 4.313,
"step": 263168
},
{
"epoch": 1.01,
"learning_rate": 4.568276026082918e-05,
"loss": 4.3128,
"step": 263680
},
{
"epoch": 1.01,
"learning_rate": 4.567437431331866e-05,
"loss": 4.3015,
"step": 264192
},
{
"epoch": 1.01,
"learning_rate": 4.566598836580814e-05,
"loss": 4.314,
"step": 264704
},
{
"epoch": 1.01,
"learning_rate": 4.565763517590508e-05,
"loss": 4.3163,
"step": 265216
},
{
"epoch": 1.01,
"learning_rate": 4.564924922839456e-05,
"loss": 4.3185,
"step": 265728
},
{
"epoch": 1.01,
"learning_rate": 4.564086328088404e-05,
"loss": 4.3272,
"step": 266240
},
{
"epoch": 1.01,
"learning_rate": 4.563247733337352e-05,
"loss": 4.3237,
"step": 266752
},
{
"epoch": 1.01,
"learning_rate": 4.5624107764666726e-05,
"loss": 4.3237,
"step": 267264
},
{
"epoch": 1.01,
"learning_rate": 4.5615721817156206e-05,
"loss": 4.3029,
"step": 267776
},
{
"epoch": 1.01,
"learning_rate": 4.560735224844942e-05,
"loss": 4.3106,
"step": 268288
},
{
"epoch": 1.01,
"learning_rate": 4.55989663009389e-05,
"loss": 4.3175,
"step": 268800
},
{
"epoch": 1.01,
"learning_rate": 4.559058035342838e-05,
"loss": 4.2997,
"step": 269312
},
{
"epoch": 1.01,
"learning_rate": 4.558219440591786e-05,
"loss": 4.3137,
"step": 269824
},
{
"epoch": 1.01,
"learning_rate": 4.557380845840734e-05,
"loss": 4.3086,
"step": 270336
},
{
"epoch": 1.01,
"learning_rate": 4.556543888970055e-05,
"loss": 4.3189,
"step": 270848
},
{
"epoch": 1.01,
"learning_rate": 4.555706932099376e-05,
"loss": 4.3138,
"step": 271360
},
{
"epoch": 1.01,
"learning_rate": 4.554869975228697e-05,
"loss": 4.2971,
"step": 271872
},
{
"epoch": 1.01,
"learning_rate": 4.554031380477645e-05,
"loss": 4.3101,
"step": 272384
},
{
"epoch": 1.01,
"learning_rate": 4.553192785726593e-05,
"loss": 4.3096,
"step": 272896
},
{
"epoch": 1.01,
"learning_rate": 4.5523541909755416e-05,
"loss": 4.3196,
"step": 273408
},
{
"epoch": 1.01,
"learning_rate": 4.5515155962244896e-05,
"loss": 4.3116,
"step": 273920
},
{
"epoch": 1.01,
"learning_rate": 4.5506770014734376e-05,
"loss": 4.3141,
"step": 274432
},
{
"epoch": 1.02,
"learning_rate": 4.5498384067223856e-05,
"loss": 4.3166,
"step": 274944
},
{
"epoch": 1.02,
"learning_rate": 4.5489998119713336e-05,
"loss": 4.2962,
"step": 275456
},
{
"epoch": 1.02,
"learning_rate": 4.5481612172202816e-05,
"loss": 4.312,
"step": 275968
},
{
"epoch": 1.02,
"learning_rate": 4.5473226224692296e-05,
"loss": 4.3011,
"step": 276480
},
{
"epoch": 1.02,
"learning_rate": 4.5464840277181776e-05,
"loss": 4.3024,
"step": 276992
},
{
"epoch": 1.02,
"learning_rate": 4.5456454329671256e-05,
"loss": 4.3156,
"step": 277504
},
{
"epoch": 1.02,
"learning_rate": 4.5448068382160736e-05,
"loss": 4.3029,
"step": 278016
},
{
"epoch": 1.02,
"learning_rate": 4.5439682434650216e-05,
"loss": 4.2916,
"step": 278528
},
{
"epoch": 1.02,
"learning_rate": 4.543129648713969e-05,
"loss": 4.3007,
"step": 279040
},
{
"epoch": 1.02,
"learning_rate": 4.542291053962917e-05,
"loss": 4.3109,
"step": 279552
},
{
"epoch": 1.02,
"learning_rate": 4.541452459211865e-05,
"loss": 4.3083,
"step": 280064
},
{
"epoch": 1.02,
"learning_rate": 4.540613864460813e-05,
"loss": 4.2976,
"step": 280576
},
{
"epoch": 1.02,
"learning_rate": 4.539775269709761e-05,
"loss": 4.292,
"step": 281088
},
{
"epoch": 1.02,
"learning_rate": 4.5389366749587095e-05,
"loss": 4.2926,
"step": 281600
},
{
"epoch": 1.02,
"learning_rate": 4.5380997180880304e-05,
"loss": 4.306,
"step": 282112
},
{
"epoch": 1.02,
"learning_rate": 4.5372611233369784e-05,
"loss": 4.279,
"step": 282624
},
{
"epoch": 1.02,
"learning_rate": 4.5364225285859264e-05,
"loss": 4.2918,
"step": 283136
},
{
"epoch": 1.02,
"learning_rate": 4.5355839338348744e-05,
"loss": 4.2994,
"step": 283648
},
{
"epoch": 1.02,
"learning_rate": 4.5347469769641953e-05,
"loss": 4.2973,
"step": 284160
},
{
"epoch": 1.02,
"learning_rate": 4.533910020093516e-05,
"loss": 4.2897,
"step": 284672
},
{
"epoch": 1.02,
"learning_rate": 4.533071425342464e-05,
"loss": 4.2997,
"step": 285184
},
{
"epoch": 1.02,
"learning_rate": 4.532232830591412e-05,
"loss": 4.29,
"step": 285696
},
{
"epoch": 1.02,
"learning_rate": 4.53139423584036e-05,
"loss": 4.2915,
"step": 286208
},
{
"epoch": 1.02,
"learning_rate": 4.530555641089308e-05,
"loss": 4.295,
"step": 286720
},
{
"epoch": 1.02,
"learning_rate": 4.52971868421863e-05,
"loss": 4.2913,
"step": 287232
},
{
"epoch": 1.02,
"learning_rate": 4.528880089467578e-05,
"loss": 4.3032,
"step": 287744
},
{
"epoch": 1.02,
"learning_rate": 4.528041494716526e-05,
"loss": 4.2957,
"step": 288256
},
{
"epoch": 1.02,
"learning_rate": 4.527202899965474e-05,
"loss": 4.2963,
"step": 288768
},
{
"epoch": 1.02,
"learning_rate": 4.526364305214422e-05,
"loss": 4.282,
"step": 289280
},
{
"epoch": 1.02,
"learning_rate": 4.525527348343743e-05,
"loss": 4.2923,
"step": 289792
},
{
"epoch": 1.02,
"learning_rate": 4.524688753592691e-05,
"loss": 4.2912,
"step": 290304
},
{
"epoch": 1.02,
"learning_rate": 4.523850158841639e-05,
"loss": 4.2789,
"step": 290816
},
{
"epoch": 1.02,
"learning_rate": 4.523011564090587e-05,
"loss": 4.2926,
"step": 291328
},
{
"epoch": 1.02,
"learning_rate": 4.522172969339535e-05,
"loss": 4.2827,
"step": 291840
},
{
"epoch": 1.02,
"learning_rate": 4.521334374588483e-05,
"loss": 4.2922,
"step": 292352
},
{
"epoch": 1.02,
"learning_rate": 4.5204974177178036e-05,
"loss": 4.2804,
"step": 292864
},
{
"epoch": 1.02,
"learning_rate": 4.5196588229667516e-05,
"loss": 4.2897,
"step": 293376
},
{
"epoch": 1.02,
"learning_rate": 4.5188202282157e-05,
"loss": 4.2642,
"step": 293888
},
{
"epoch": 1.02,
"learning_rate": 4.517981633464648e-05,
"loss": 4.2922,
"step": 294400
},
{
"epoch": 1.02,
"learning_rate": 4.517143038713596e-05,
"loss": 4.2778,
"step": 294912
},
{
"epoch": 1.02,
"learning_rate": 4.516304443962544e-05,
"loss": 4.2931,
"step": 295424
},
{
"epoch": 1.02,
"learning_rate": 4.515467487091865e-05,
"loss": 4.291,
"step": 295936
},
{
"epoch": 1.02,
"learning_rate": 4.514628892340813e-05,
"loss": 4.2905,
"step": 296448
},
{
"epoch": 1.02,
"learning_rate": 4.513790297589761e-05,
"loss": 4.2723,
"step": 296960
},
{
"epoch": 1.02,
"learning_rate": 4.512953340719082e-05,
"loss": 4.2849,
"step": 297472
},
{
"epoch": 1.02,
"learning_rate": 4.51211474596803e-05,
"loss": 4.2909,
"step": 297984
},
{
"epoch": 1.02,
"learning_rate": 4.511276151216978e-05,
"loss": 4.2961,
"step": 298496
},
{
"epoch": 1.02,
"learning_rate": 4.510437556465926e-05,
"loss": 4.2861,
"step": 299008
},
{
"epoch": 1.02,
"learning_rate": 4.509598961714874e-05,
"loss": 4.2846,
"step": 299520
},
{
"epoch": 1.02,
"learning_rate": 4.508760366963822e-05,
"loss": 4.2851,
"step": 300032
},
{
"epoch": 1.02,
"learning_rate": 4.50792177221277e-05,
"loss": 4.2864,
"step": 300544
},
{
"epoch": 1.02,
"learning_rate": 4.507083177461718e-05,
"loss": 4.2718,
"step": 301056
},
{
"epoch": 1.02,
"learning_rate": 4.506244582710666e-05,
"loss": 4.2788,
"step": 301568
},
{
"epoch": 1.02,
"learning_rate": 4.505405987959614e-05,
"loss": 4.2766,
"step": 302080
},
{
"epoch": 1.02,
"learning_rate": 4.504569031088935e-05,
"loss": 4.2731,
"step": 302592
},
{
"epoch": 1.02,
"learning_rate": 4.503730436337883e-05,
"loss": 4.2738,
"step": 303104
},
{
"epoch": 1.02,
"learning_rate": 4.502891841586831e-05,
"loss": 4.2823,
"step": 303616
},
{
"epoch": 1.02,
"learning_rate": 4.502053246835779e-05,
"loss": 4.2713,
"step": 304128
},
{
"epoch": 1.02,
"learning_rate": 4.5012162899651e-05,
"loss": 4.2757,
"step": 304640
},
{
"epoch": 1.02,
"learning_rate": 4.500377695214048e-05,
"loss": 4.2824,
"step": 305152
},
{
"epoch": 1.03,
"eval_loss": 4.258530616760254,
"eval_runtime": 297.5439,
"eval_samples_per_second": 1282.47,
"eval_steps_per_second": 40.078,
"step": 305280
},
{
"epoch": 0.0,
"learning_rate": 4.499539100462996e-05,
"loss": 4.2631,
"step": 305664
},
{
"epoch": 0.0,
"learning_rate": 4.498700505711944e-05,
"loss": 4.267,
"step": 306176
},
{
"epoch": 0.0,
"learning_rate": 4.4978619109608925e-05,
"loss": 4.2794,
"step": 306688
},
{
"epoch": 0.0,
"learning_rate": 4.4970233162098405e-05,
"loss": 4.2717,
"step": 307200
},
{
"epoch": 0.0,
"learning_rate": 4.4961847214587885e-05,
"loss": 4.2845,
"step": 307712
},
{
"epoch": 0.0,
"learning_rate": 4.4953461267077365e-05,
"loss": 4.2606,
"step": 308224
},
{
"epoch": 0.0,
"learning_rate": 4.4945075319566845e-05,
"loss": 4.2694,
"step": 308736
},
{
"epoch": 0.0,
"learning_rate": 4.4936689372056325e-05,
"loss": 4.2617,
"step": 309248
},
{
"epoch": 0.0,
"learning_rate": 4.4928303424545805e-05,
"loss": 4.2765,
"step": 309760
},
{
"epoch": 0.0,
"learning_rate": 4.4919917477035285e-05,
"loss": 4.2743,
"step": 310272
},
{
"epoch": 0.0,
"learning_rate": 4.4911531529524765e-05,
"loss": 4.2669,
"step": 310784
},
{
"epoch": 0.0,
"learning_rate": 4.490314558201424e-05,
"loss": 4.282,
"step": 311296
},
{
"epoch": 0.0,
"learning_rate": 4.489475963450372e-05,
"loss": 4.2524,
"step": 311808
},
{
"epoch": 0.0,
"learning_rate": 4.48863736869932e-05,
"loss": 4.2639,
"step": 312320
},
{
"epoch": 0.0,
"learning_rate": 4.487800411828641e-05,
"loss": 4.2673,
"step": 312832
},
{
"epoch": 0.0,
"learning_rate": 4.486961817077589e-05,
"loss": 4.2584,
"step": 313344
},
{
"epoch": 0.0,
"learning_rate": 4.4861232223265373e-05,
"loss": 4.2644,
"step": 313856
},
{
"epoch": 0.0,
"learning_rate": 4.4852846275754853e-05,
"loss": 4.2646,
"step": 314368
},
{
"epoch": 0.0,
"learning_rate": 4.484446032824433e-05,
"loss": 4.2614,
"step": 314880
},
{
"epoch": 0.0,
"learning_rate": 4.483609075953754e-05,
"loss": 4.2894,
"step": 315392
},
{
"epoch": 0.0,
"learning_rate": 4.482770481202702e-05,
"loss": 4.2625,
"step": 315904
},
{
"epoch": 0.0,
"learning_rate": 4.48193188645165e-05,
"loss": 4.2616,
"step": 316416
},
{
"epoch": 0.0,
"learning_rate": 4.481093291700598e-05,
"loss": 4.2697,
"step": 316928
},
{
"epoch": 0.0,
"learning_rate": 4.480254696949546e-05,
"loss": 4.2754,
"step": 317440
},
{
"epoch": 0.0,
"learning_rate": 4.479416102198494e-05,
"loss": 4.2565,
"step": 317952
},
{
"epoch": 0.0,
"learning_rate": 4.478577507447442e-05,
"loss": 4.2672,
"step": 318464
},
{
"epoch": 0.0,
"learning_rate": 4.47773891269639e-05,
"loss": 4.2564,
"step": 318976
},
{
"epoch": 0.0,
"learning_rate": 4.476900317945338e-05,
"loss": 4.2631,
"step": 319488
},
{
"epoch": 0.0,
"learning_rate": 4.476061723194286e-05,
"loss": 4.2535,
"step": 320000
},
{
"epoch": 0.0,
"learning_rate": 4.475223128443234e-05,
"loss": 4.2627,
"step": 320512
},
{
"epoch": 0.01,
"learning_rate": 4.474384533692182e-05,
"loss": 4.2745,
"step": 321024
},
{
"epoch": 0.01,
"learning_rate": 4.473547576821504e-05,
"loss": 4.2635,
"step": 321536
},
{
"epoch": 0.01,
"learning_rate": 4.472710619950825e-05,
"loss": 4.2614,
"step": 322048
},
{
"epoch": 0.01,
"learning_rate": 4.471872025199773e-05,
"loss": 4.2652,
"step": 322560
},
{
"epoch": 0.01,
"learning_rate": 4.4710350683290936e-05,
"loss": 4.262,
"step": 323072
},
{
"epoch": 0.01,
"learning_rate": 4.4701964735780416e-05,
"loss": 4.2643,
"step": 323584
},
{
"epoch": 0.01,
"learning_rate": 4.4693578788269896e-05,
"loss": 4.244,
"step": 324096
},
{
"epoch": 0.01,
"learning_rate": 4.4685192840759376e-05,
"loss": 4.2554,
"step": 324608
},
{
"epoch": 0.01,
"learning_rate": 4.4676806893248856e-05,
"loss": 4.247,
"step": 325120
},
{
"epoch": 0.01,
"learning_rate": 4.4668420945738336e-05,
"loss": 4.2524,
"step": 325632
},
{
"epoch": 0.01,
"learning_rate": 4.4660034998227816e-05,
"loss": 4.2542,
"step": 326144
},
{
"epoch": 0.01,
"learning_rate": 4.4651649050717296e-05,
"loss": 4.2588,
"step": 326656
},
{
"epoch": 0.01,
"learning_rate": 4.4643263103206776e-05,
"loss": 4.2511,
"step": 327168
},
{
"epoch": 0.01,
"learning_rate": 4.463489353449999e-05,
"loss": 4.2544,
"step": 327680
},
{
"epoch": 0.01,
"learning_rate": 4.462650758698947e-05,
"loss": 4.2569,
"step": 328192
},
{
"epoch": 0.01,
"learning_rate": 4.461812163947895e-05,
"loss": 4.2539,
"step": 328704
},
{
"epoch": 0.01,
"learning_rate": 4.4609735691968425e-05,
"loss": 4.2574,
"step": 329216
},
{
"epoch": 0.01,
"learning_rate": 4.4601349744457905e-05,
"loss": 4.2505,
"step": 329728
},
{
"epoch": 0.01,
"learning_rate": 4.4592963796947384e-05,
"loss": 4.2358,
"step": 330240
},
{
"epoch": 0.01,
"learning_rate": 4.4584577849436864e-05,
"loss": 4.2578,
"step": 330752
},
{
"epoch": 0.01,
"learning_rate": 4.4576191901926344e-05,
"loss": 4.2469,
"step": 331264
},
{
"epoch": 0.01,
"learning_rate": 4.4567822333219554e-05,
"loss": 4.2547,
"step": 331776
},
{
"epoch": 0.01,
"learning_rate": 4.455945276451277e-05,
"loss": 4.2415,
"step": 332288
},
{
"epoch": 0.01,
"learning_rate": 4.455106681700225e-05,
"loss": 4.2547,
"step": 332800
},
{
"epoch": 0.01,
"learning_rate": 4.454268086949173e-05,
"loss": 4.2327,
"step": 333312
},
{
"epoch": 0.01,
"learning_rate": 4.453429492198121e-05,
"loss": 4.2635,
"step": 333824
},
{
"epoch": 0.01,
"learning_rate": 4.452590897447069e-05,
"loss": 4.2314,
"step": 334336
},
{
"epoch": 0.01,
"learning_rate": 4.451752302696017e-05,
"loss": 4.2429,
"step": 334848
},
{
"epoch": 0.01,
"learning_rate": 4.450913707944965e-05,
"loss": 4.2487,
"step": 335360
},
{
"epoch": 0.01,
"learning_rate": 4.450075113193913e-05,
"loss": 4.2388,
"step": 335872
},
{
"epoch": 0.01,
"learning_rate": 4.449236518442861e-05,
"loss": 4.2411,
"step": 336384
},
{
"epoch": 0.01,
"learning_rate": 4.448399561572182e-05,
"loss": 4.2447,
"step": 336896
},
{
"epoch": 0.01,
"learning_rate": 4.44756096682113e-05,
"loss": 4.2321,
"step": 337408
},
{
"epoch": 0.01,
"learning_rate": 4.446724009950451e-05,
"loss": 4.2299,
"step": 337920
},
{
"epoch": 0.01,
"learning_rate": 4.445885415199399e-05,
"loss": 4.2432,
"step": 338432
},
{
"epoch": 0.01,
"learning_rate": 4.445046820448347e-05,
"loss": 4.2431,
"step": 338944
},
{
"epoch": 0.01,
"learning_rate": 4.444208225697295e-05,
"loss": 4.2334,
"step": 339456
},
{
"epoch": 0.01,
"learning_rate": 4.443369630946243e-05,
"loss": 4.24,
"step": 339968
},
{
"epoch": 0.01,
"learning_rate": 4.4425310361951914e-05,
"loss": 4.2219,
"step": 340480
},
{
"epoch": 0.01,
"learning_rate": 4.4416924414441394e-05,
"loss": 4.2398,
"step": 340992
},
{
"epoch": 0.01,
"learning_rate": 4.4408538466930874e-05,
"loss": 4.2406,
"step": 341504
},
{
"epoch": 0.01,
"learning_rate": 4.440016889822408e-05,
"loss": 4.2409,
"step": 342016
},
{
"epoch": 0.01,
"learning_rate": 4.439178295071356e-05,
"loss": 4.2493,
"step": 342528
},
{
"epoch": 0.01,
"learning_rate": 4.438341338200677e-05,
"loss": 4.2477,
"step": 343040
},
{
"epoch": 0.01,
"learning_rate": 4.437502743449625e-05,
"loss": 4.253,
"step": 343552
},
{
"epoch": 0.01,
"learning_rate": 4.436664148698573e-05,
"loss": 4.2274,
"step": 344064
},
{
"epoch": 0.01,
"learning_rate": 4.435825553947521e-05,
"loss": 4.2364,
"step": 344576
},
{
"epoch": 0.01,
"learning_rate": 4.434986959196469e-05,
"loss": 4.2416,
"step": 345088
},
{
"epoch": 0.01,
"learning_rate": 4.43415000232579e-05,
"loss": 4.2201,
"step": 345600
},
{
"epoch": 0.01,
"learning_rate": 4.433311407574738e-05,
"loss": 4.2421,
"step": 346112
},
{
"epoch": 0.01,
"learning_rate": 4.432472812823687e-05,
"loss": 4.2354,
"step": 346624
},
{
"epoch": 0.01,
"learning_rate": 4.431634218072635e-05,
"loss": 4.2429,
"step": 347136
},
{
"epoch": 0.01,
"learning_rate": 4.430795623321583e-05,
"loss": 4.2422,
"step": 347648
},
{
"epoch": 0.01,
"learning_rate": 4.4299586664509036e-05,
"loss": 4.2228,
"step": 348160
},
{
"epoch": 0.01,
"learning_rate": 4.4291200716998516e-05,
"loss": 4.2376,
"step": 348672
},
{
"epoch": 0.01,
"learning_rate": 4.4282814769487996e-05,
"loss": 4.2344,
"step": 349184
},
{
"epoch": 0.01,
"learning_rate": 4.4274428821977476e-05,
"loss": 4.244,
"step": 349696
},
{
"epoch": 0.01,
"learning_rate": 4.4266042874466956e-05,
"loss": 4.2363,
"step": 350208
},
{
"epoch": 0.01,
"learning_rate": 4.425765692695643e-05,
"loss": 4.2438,
"step": 350720
},
{
"epoch": 0.02,
"learning_rate": 4.424927097944591e-05,
"loss": 4.2402,
"step": 351232
},
{
"epoch": 0.02,
"learning_rate": 4.424088503193539e-05,
"loss": 4.2267,
"step": 351744
},
{
"epoch": 0.02,
"learning_rate": 4.4232515463228605e-05,
"loss": 4.2391,
"step": 352256
},
{
"epoch": 0.02,
"learning_rate": 4.4224129515718085e-05,
"loss": 4.2259,
"step": 352768
},
{
"epoch": 0.02,
"learning_rate": 4.42157599470113e-05,
"loss": 4.2344,
"step": 353280
},
{
"epoch": 0.02,
"learning_rate": 4.420737399950078e-05,
"loss": 4.2442,
"step": 353792
},
{
"epoch": 0.02,
"learning_rate": 4.419898805199026e-05,
"loss": 4.2271,
"step": 354304
},
{
"epoch": 0.02,
"learning_rate": 4.4190602104479734e-05,
"loss": 4.2227,
"step": 354816
},
{
"epoch": 0.02,
"learning_rate": 4.4182216156969214e-05,
"loss": 4.2276,
"step": 355328
},
{
"epoch": 0.02,
"learning_rate": 4.417384658826243e-05,
"loss": 4.2348,
"step": 355840
},
{
"epoch": 0.02,
"learning_rate": 4.41654606407519e-05,
"loss": 4.2407,
"step": 356352
},
{
"epoch": 0.02,
"learning_rate": 4.415707469324138e-05,
"loss": 4.2234,
"step": 356864
},
{
"epoch": 0.02,
"learning_rate": 4.414868874573086e-05,
"loss": 4.2232,
"step": 357376
},
{
"epoch": 0.02,
"learning_rate": 4.414031917702408e-05,
"loss": 4.2193,
"step": 357888
},
{
"epoch": 0.02,
"learning_rate": 4.413193322951356e-05,
"loss": 4.2358,
"step": 358400
},
{
"epoch": 0.02,
"learning_rate": 4.412354728200304e-05,
"loss": 4.2086,
"step": 358912
},
{
"epoch": 0.02,
"learning_rate": 4.4115177713296255e-05,
"loss": 4.2219,
"step": 359424
},
{
"epoch": 0.02,
"learning_rate": 4.4106791765785735e-05,
"loss": 4.2296,
"step": 359936
},
{
"epoch": 0.02,
"learning_rate": 4.409840581827521e-05,
"loss": 4.2228,
"step": 360448
},
{
"epoch": 0.02,
"learning_rate": 4.409001987076469e-05,
"loss": 4.2199,
"step": 360960
},
{
"epoch": 0.02,
"learning_rate": 4.408163392325417e-05,
"loss": 4.2316,
"step": 361472
},
{
"epoch": 0.02,
"learning_rate": 4.407324797574365e-05,
"loss": 4.2199,
"step": 361984
},
{
"epoch": 0.02,
"learning_rate": 4.406487840703686e-05,
"loss": 4.2172,
"step": 362496
},
{
"epoch": 0.02,
"learning_rate": 4.405649245952634e-05,
"loss": 4.2266,
"step": 363008
},
{
"epoch": 0.02,
"learning_rate": 4.404810651201582e-05,
"loss": 4.2251,
"step": 363520
},
{
"epoch": 0.02,
"learning_rate": 4.40397205645053e-05,
"loss": 4.232,
"step": 364032
},
{
"epoch": 0.02,
"learning_rate": 4.4031334616994777e-05,
"loss": 4.229,
"step": 364544
},
{
"epoch": 0.02,
"learning_rate": 4.4022948669484257e-05,
"loss": 4.2274,
"step": 365056
},
{
"epoch": 0.02,
"learning_rate": 4.401456272197374e-05,
"loss": 4.2127,
"step": 365568
},
{
"epoch": 0.02,
"learning_rate": 4.400617677446322e-05,
"loss": 4.2227,
"step": 366080
},
{
"epoch": 0.02,
"learning_rate": 4.39977908269527e-05,
"loss": 4.2211,
"step": 366592
},
{
"epoch": 0.02,
"learning_rate": 4.398940487944218e-05,
"loss": 4.2076,
"step": 367104
},
{
"epoch": 0.02,
"learning_rate": 4.398103531073539e-05,
"loss": 4.2278,
"step": 367616
},
{
"epoch": 0.02,
"learning_rate": 4.397264936322487e-05,
"loss": 4.2105,
"step": 368128
},
{
"epoch": 0.02,
"learning_rate": 4.396426341571435e-05,
"loss": 4.2239,
"step": 368640
},
{
"epoch": 0.02,
"learning_rate": 4.395587746820383e-05,
"loss": 4.2171,
"step": 369152
},
{
"epoch": 0.02,
"learning_rate": 4.394750789949704e-05,
"loss": 4.2199,
"step": 369664
},
{
"epoch": 0.02,
"learning_rate": 4.393912195198652e-05,
"loss": 4.1988,
"step": 370176
},
{
"epoch": 0.02,
"learning_rate": 4.3930736004476e-05,
"loss": 4.2196,
"step": 370688
},
{
"epoch": 0.02,
"learning_rate": 4.392235005696548e-05,
"loss": 4.2158,
"step": 371200
},
{
"epoch": 0.02,
"learning_rate": 4.391396410945496e-05,
"loss": 4.2216,
"step": 371712
},
{
"epoch": 0.02,
"learning_rate": 4.390559454074818e-05,
"loss": 4.222,
"step": 372224
},
{
"epoch": 0.02,
"learning_rate": 4.389720859323766e-05,
"loss": 4.2268,
"step": 372736
},
{
"epoch": 0.02,
"learning_rate": 4.388882264572714e-05,
"loss": 4.2037,
"step": 373248
},
{
"epoch": 0.02,
"learning_rate": 4.388043669821662e-05,
"loss": 4.2205,
"step": 373760
},
{
"epoch": 0.02,
"learning_rate": 4.3872067129509826e-05,
"loss": 4.2278,
"step": 374272
},
{
"epoch": 0.02,
"learning_rate": 4.3863681181999306e-05,
"loss": 4.2257,
"step": 374784
},
{
"epoch": 0.02,
"learning_rate": 4.3855295234488786e-05,
"loss": 4.2197,
"step": 375296
},
{
"epoch": 0.02,
"learning_rate": 4.3846909286978266e-05,
"loss": 4.2243,
"step": 375808
},
{
"epoch": 0.02,
"learning_rate": 4.3838539718271475e-05,
"loss": 4.2167,
"step": 376320
},
{
"epoch": 0.02,
"learning_rate": 4.3830153770760955e-05,
"loss": 4.2209,
"step": 376832
},
{
"epoch": 0.02,
"learning_rate": 4.3821767823250435e-05,
"loss": 4.2017,
"step": 377344
},
{
"epoch": 0.02,
"learning_rate": 4.3813381875739915e-05,
"loss": 4.2156,
"step": 377856
},
{
"epoch": 0.02,
"learning_rate": 4.3804995928229395e-05,
"loss": 4.2084,
"step": 378368
},
{
"epoch": 0.02,
"learning_rate": 4.379662635952261e-05,
"loss": 4.2109,
"step": 378880
},
{
"epoch": 0.02,
"learning_rate": 4.378824041201209e-05,
"loss": 4.2111,
"step": 379392
},
{
"epoch": 0.02,
"learning_rate": 4.3779854464501564e-05,
"loss": 4.2109,
"step": 379904
},
{
"epoch": 0.02,
"learning_rate": 4.3771468516991044e-05,
"loss": 4.2102,
"step": 380416
},
{
"epoch": 0.02,
"learning_rate": 4.3763082569480524e-05,
"loss": 4.2088,
"step": 380928
},
{
"epoch": 0.02,
"learning_rate": 4.3754696621970004e-05,
"loss": 4.2205,
"step": 381440
},
{
"epoch": 0.03,
"eval_loss": 4.202013969421387,
"eval_runtime": 284.1681,
"eval_samples_per_second": 1342.835,
"eval_steps_per_second": 41.965,
"step": 381600
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 1.5663775323805632e+17,
"trial_name": null,
"trial_params": null
}