abhinavp's picture
Training in progress, epoch 0, checkpoint
5b270be verified
{
"best_metric": 3.905977487564087,
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full/transformer/3/checkpoints/checkpoint-305276",
"epoch": 0.025000278439663435,
"eval_steps": 10,
"global_step": 305276,
"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": 10.9262,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.999161405248948e-05,
"loss": 6.8448,
"step": 512
},
{
"epoch": 0.0,
"learning_rate": 4.998322810497896e-05,
"loss": 6.1978,
"step": 1024
},
{
"epoch": 0.0,
"learning_rate": 4.997484215746844e-05,
"loss": 5.9733,
"step": 1536
},
{
"epoch": 0.0,
"learning_rate": 4.996645620995792e-05,
"loss": 5.8185,
"step": 2048
},
{
"epoch": 0.0,
"learning_rate": 4.99580702624474e-05,
"loss": 5.6949,
"step": 2560
},
{
"epoch": 0.0,
"learning_rate": 4.994968431493688e-05,
"loss": 5.5933,
"step": 3072
},
{
"epoch": 0.0,
"learning_rate": 4.994129836742636e-05,
"loss": 5.5267,
"step": 3584
},
{
"epoch": 0.0,
"learning_rate": 4.993291241991584e-05,
"loss": 5.4739,
"step": 4096
},
{
"epoch": 0.0,
"learning_rate": 4.992452647240532e-05,
"loss": 5.3928,
"step": 4608
},
{
"epoch": 0.0,
"learning_rate": 4.99161405248948e-05,
"loss": 5.3519,
"step": 5120
},
{
"epoch": 0.0,
"learning_rate": 4.990775457738428e-05,
"loss": 5.3119,
"step": 5632
},
{
"epoch": 0.0,
"learning_rate": 4.989938500867749e-05,
"loss": 5.2679,
"step": 6144
},
{
"epoch": 0.0,
"learning_rate": 4.989099906116697e-05,
"loss": 5.2061,
"step": 6656
},
{
"epoch": 0.0,
"learning_rate": 4.988261311365645e-05,
"loss": 5.1775,
"step": 7168
},
{
"epoch": 0.0,
"learning_rate": 4.987422716614593e-05,
"loss": 5.146,
"step": 7680
},
{
"epoch": 0.0,
"learning_rate": 4.986584121863541e-05,
"loss": 5.1069,
"step": 8192
},
{
"epoch": 0.0,
"learning_rate": 4.985745527112489e-05,
"loss": 5.0731,
"step": 8704
},
{
"epoch": 0.0,
"learning_rate": 4.984906932361437e-05,
"loss": 5.0519,
"step": 9216
},
{
"epoch": 0.0,
"learning_rate": 4.984068337610385e-05,
"loss": 5.0249,
"step": 9728
},
{
"epoch": 0.0,
"learning_rate": 4.983229742859333e-05,
"loss": 4.9946,
"step": 10240
},
{
"epoch": 0.0,
"learning_rate": 4.9823927859886547e-05,
"loss": 4.966,
"step": 10752
},
{
"epoch": 0.0,
"learning_rate": 4.9815541912376026e-05,
"loss": 4.9543,
"step": 11264
},
{
"epoch": 0.0,
"learning_rate": 4.9807155964865506e-05,
"loss": 4.9242,
"step": 11776
},
{
"epoch": 0.0,
"learning_rate": 4.9798770017354986e-05,
"loss": 4.9154,
"step": 12288
},
{
"epoch": 0.0,
"learning_rate": 4.9790400448648195e-05,
"loss": 4.8875,
"step": 12800
},
{
"epoch": 0.0,
"learning_rate": 4.9782014501137675e-05,
"loss": 4.8765,
"step": 13312
},
{
"epoch": 0.0,
"learning_rate": 4.9773628553627155e-05,
"loss": 4.8582,
"step": 13824
},
{
"epoch": 0.0,
"learning_rate": 4.9765242606116635e-05,
"loss": 4.8245,
"step": 14336
},
{
"epoch": 0.0,
"learning_rate": 4.9756873037409844e-05,
"loss": 4.8264,
"step": 14848
},
{
"epoch": 0.01,
"learning_rate": 4.9748487089899324e-05,
"loss": 4.7969,
"step": 15360
},
{
"epoch": 0.01,
"learning_rate": 4.9740101142388804e-05,
"loss": 4.7862,
"step": 15872
},
{
"epoch": 0.01,
"learning_rate": 4.9731715194878284e-05,
"loss": 4.7754,
"step": 16384
},
{
"epoch": 0.01,
"learning_rate": 4.97233456261715e-05,
"loss": 4.7678,
"step": 16896
},
{
"epoch": 0.01,
"learning_rate": 4.971495967866098e-05,
"loss": 4.7425,
"step": 17408
},
{
"epoch": 0.01,
"learning_rate": 4.970657373115046e-05,
"loss": 4.7337,
"step": 17920
},
{
"epoch": 0.01,
"learning_rate": 4.969818778363994e-05,
"loss": 4.7324,
"step": 18432
},
{
"epoch": 0.01,
"learning_rate": 4.968981821493315e-05,
"loss": 4.7159,
"step": 18944
},
{
"epoch": 0.01,
"learning_rate": 4.968143226742263e-05,
"loss": 4.7065,
"step": 19456
},
{
"epoch": 0.01,
"learning_rate": 4.967304631991211e-05,
"loss": 4.6884,
"step": 19968
},
{
"epoch": 0.01,
"learning_rate": 4.966466037240159e-05,
"loss": 4.6721,
"step": 20480
},
{
"epoch": 0.01,
"learning_rate": 4.96562908036948e-05,
"loss": 4.6661,
"step": 20992
},
{
"epoch": 0.01,
"learning_rate": 4.964790485618428e-05,
"loss": 4.6422,
"step": 21504
},
{
"epoch": 0.01,
"learning_rate": 4.963951890867376e-05,
"loss": 4.6601,
"step": 22016
},
{
"epoch": 0.01,
"learning_rate": 4.963113296116324e-05,
"loss": 4.6347,
"step": 22528
},
{
"epoch": 0.01,
"learning_rate": 4.9622763392456454e-05,
"loss": 4.635,
"step": 23040
},
{
"epoch": 0.01,
"learning_rate": 4.9614377444945934e-05,
"loss": 4.6263,
"step": 23552
},
{
"epoch": 0.01,
"learning_rate": 4.9605991497435414e-05,
"loss": 4.6213,
"step": 24064
},
{
"epoch": 0.01,
"learning_rate": 4.9597605549924894e-05,
"loss": 4.6119,
"step": 24576
},
{
"epoch": 0.01,
"learning_rate": 4.9589219602414374e-05,
"loss": 4.5893,
"step": 25088
},
{
"epoch": 0.01,
"learning_rate": 4.958085003370758e-05,
"loss": 4.5815,
"step": 25600
},
{
"epoch": 0.01,
"learning_rate": 4.957248046500079e-05,
"loss": 4.573,
"step": 26112
},
{
"epoch": 0.01,
"learning_rate": 4.956409451749027e-05,
"loss": 4.5807,
"step": 26624
},
{
"epoch": 0.01,
"learning_rate": 4.955570856997975e-05,
"loss": 4.5585,
"step": 27136
},
{
"epoch": 0.01,
"learning_rate": 4.954732262246923e-05,
"loss": 4.5691,
"step": 27648
},
{
"epoch": 0.01,
"learning_rate": 4.953893667495871e-05,
"loss": 4.544,
"step": 28160
},
{
"epoch": 0.01,
"learning_rate": 4.953055072744819e-05,
"loss": 4.5374,
"step": 28672
},
{
"epoch": 0.01,
"learning_rate": 4.952216477993767e-05,
"loss": 4.5333,
"step": 29184
},
{
"epoch": 0.01,
"learning_rate": 4.951377883242715e-05,
"loss": 4.5289,
"step": 29696
},
{
"epoch": 0.01,
"learning_rate": 4.950539288491663e-05,
"loss": 4.525,
"step": 30208
},
{
"epoch": 0.01,
"learning_rate": 4.949702331620985e-05,
"loss": 4.5084,
"step": 30720
},
{
"epoch": 0.01,
"learning_rate": 4.948863736869932e-05,
"loss": 4.5036,
"step": 31232
},
{
"epoch": 0.01,
"learning_rate": 4.94802514211888e-05,
"loss": 4.5131,
"step": 31744
},
{
"epoch": 0.01,
"learning_rate": 4.947186547367828e-05,
"loss": 4.4943,
"step": 32256
},
{
"epoch": 0.01,
"learning_rate": 4.946347952616776e-05,
"loss": 4.4876,
"step": 32768
},
{
"epoch": 0.01,
"learning_rate": 4.945510995746097e-05,
"loss": 4.4876,
"step": 33280
},
{
"epoch": 0.01,
"learning_rate": 4.944672400995045e-05,
"loss": 4.4839,
"step": 33792
},
{
"epoch": 0.01,
"learning_rate": 4.943833806243993e-05,
"loss": 4.466,
"step": 34304
},
{
"epoch": 0.01,
"learning_rate": 4.942995211492941e-05,
"loss": 4.4773,
"step": 34816
},
{
"epoch": 0.01,
"learning_rate": 4.9421582546222625e-05,
"loss": 4.465,
"step": 35328
},
{
"epoch": 0.01,
"learning_rate": 4.9413196598712105e-05,
"loss": 4.4566,
"step": 35840
},
{
"epoch": 0.01,
"learning_rate": 4.9404810651201585e-05,
"loss": 4.4622,
"step": 36352
},
{
"epoch": 0.01,
"learning_rate": 4.9396424703691065e-05,
"loss": 4.4488,
"step": 36864
},
{
"epoch": 0.01,
"learning_rate": 4.9388055134984274e-05,
"loss": 4.4605,
"step": 37376
},
{
"epoch": 0.01,
"learning_rate": 4.9379669187473754e-05,
"loss": 4.4615,
"step": 37888
},
{
"epoch": 0.01,
"learning_rate": 4.9371283239963234e-05,
"loss": 4.4511,
"step": 38400
},
{
"epoch": 0.01,
"learning_rate": 4.9362897292452714e-05,
"loss": 4.4344,
"step": 38912
},
{
"epoch": 0.01,
"learning_rate": 4.9354511344942194e-05,
"loss": 4.4245,
"step": 39424
},
{
"epoch": 0.01,
"learning_rate": 4.93461417762354e-05,
"loss": 4.4141,
"step": 39936
},
{
"epoch": 0.01,
"learning_rate": 4.933775582872488e-05,
"loss": 4.4273,
"step": 40448
},
{
"epoch": 0.01,
"learning_rate": 4.932936988121436e-05,
"loss": 4.4268,
"step": 40960
},
{
"epoch": 0.01,
"learning_rate": 4.932098393370384e-05,
"loss": 4.4242,
"step": 41472
},
{
"epoch": 0.01,
"learning_rate": 4.931259798619332e-05,
"loss": 4.3983,
"step": 41984
},
{
"epoch": 0.01,
"learning_rate": 4.930421203868281e-05,
"loss": 4.396,
"step": 42496
},
{
"epoch": 0.01,
"learning_rate": 4.929582609117229e-05,
"loss": 4.4027,
"step": 43008
},
{
"epoch": 0.01,
"learning_rate": 4.92874565224655e-05,
"loss": 4.3904,
"step": 43520
},
{
"epoch": 0.01,
"learning_rate": 4.927907057495498e-05,
"loss": 4.3958,
"step": 44032
},
{
"epoch": 0.01,
"learning_rate": 4.927068462744446e-05,
"loss": 4.3909,
"step": 44544
},
{
"epoch": 0.01,
"learning_rate": 4.926229867993394e-05,
"loss": 4.3938,
"step": 45056
},
{
"epoch": 0.01,
"learning_rate": 4.925392911122715e-05,
"loss": 4.3836,
"step": 45568
},
{
"epoch": 0.02,
"learning_rate": 4.924554316371663e-05,
"loss": 4.3786,
"step": 46080
},
{
"epoch": 0.02,
"learning_rate": 4.923715721620611e-05,
"loss": 4.3672,
"step": 46592
},
{
"epoch": 0.02,
"learning_rate": 4.922877126869559e-05,
"loss": 4.3803,
"step": 47104
},
{
"epoch": 0.02,
"learning_rate": 4.92204016999888e-05,
"loss": 4.3646,
"step": 47616
},
{
"epoch": 0.02,
"learning_rate": 4.921201575247828e-05,
"loss": 4.3498,
"step": 48128
},
{
"epoch": 0.02,
"learning_rate": 4.920362980496776e-05,
"loss": 4.3557,
"step": 48640
},
{
"epoch": 0.02,
"learning_rate": 4.919524385745724e-05,
"loss": 4.3683,
"step": 49152
},
{
"epoch": 0.02,
"learning_rate": 4.918685790994672e-05,
"loss": 4.3612,
"step": 49664
},
{
"epoch": 0.02,
"learning_rate": 4.91784719624362e-05,
"loss": 4.3611,
"step": 50176
},
{
"epoch": 0.02,
"learning_rate": 4.9170086014925676e-05,
"loss": 4.3394,
"step": 50688
},
{
"epoch": 0.02,
"learning_rate": 4.9161700067415156e-05,
"loss": 4.3552,
"step": 51200
},
{
"epoch": 0.02,
"learning_rate": 4.915333049870837e-05,
"loss": 4.3306,
"step": 51712
},
{
"epoch": 0.02,
"learning_rate": 4.914494455119785e-05,
"loss": 4.3469,
"step": 52224
},
{
"epoch": 0.02,
"learning_rate": 4.9136558603687325e-05,
"loss": 4.3517,
"step": 52736
},
{
"epoch": 0.02,
"learning_rate": 4.912818903498054e-05,
"loss": 4.3334,
"step": 53248
},
{
"epoch": 0.02,
"learning_rate": 4.911980308747002e-05,
"loss": 4.3284,
"step": 53760
},
{
"epoch": 0.02,
"learning_rate": 4.91114171399595e-05,
"loss": 4.3044,
"step": 54272
},
{
"epoch": 0.02,
"learning_rate": 4.910303119244898e-05,
"loss": 4.3163,
"step": 54784
},
{
"epoch": 0.02,
"learning_rate": 4.909464524493846e-05,
"loss": 4.3181,
"step": 55296
},
{
"epoch": 0.02,
"learning_rate": 4.908625929742794e-05,
"loss": 4.3143,
"step": 55808
},
{
"epoch": 0.02,
"learning_rate": 4.907788972872115e-05,
"loss": 4.3215,
"step": 56320
},
{
"epoch": 0.02,
"learning_rate": 4.906950378121063e-05,
"loss": 4.3028,
"step": 56832
},
{
"epoch": 0.02,
"learning_rate": 4.906111783370011e-05,
"loss": 4.3048,
"step": 57344
},
{
"epoch": 0.02,
"learning_rate": 4.905273188618959e-05,
"loss": 4.3109,
"step": 57856
},
{
"epoch": 0.02,
"learning_rate": 4.904434593867907e-05,
"loss": 4.3139,
"step": 58368
},
{
"epoch": 0.02,
"learning_rate": 4.903595999116855e-05,
"loss": 4.3002,
"step": 58880
},
{
"epoch": 0.02,
"learning_rate": 4.902759042246176e-05,
"loss": 4.2986,
"step": 59392
},
{
"epoch": 0.02,
"learning_rate": 4.901920447495124e-05,
"loss": 4.2944,
"step": 59904
},
{
"epoch": 0.02,
"learning_rate": 4.901081852744072e-05,
"loss": 4.2939,
"step": 60416
},
{
"epoch": 0.02,
"learning_rate": 4.90024325799302e-05,
"loss": 4.2981,
"step": 60928
},
{
"epoch": 0.02,
"learning_rate": 4.8994063011223415e-05,
"loss": 4.285,
"step": 61440
},
{
"epoch": 0.02,
"learning_rate": 4.8985677063712895e-05,
"loss": 4.2811,
"step": 61952
},
{
"epoch": 0.02,
"learning_rate": 4.8977291116202375e-05,
"loss": 4.2789,
"step": 62464
},
{
"epoch": 0.02,
"learning_rate": 4.8968905168691855e-05,
"loss": 4.2744,
"step": 62976
},
{
"epoch": 0.02,
"learning_rate": 4.8960519221181335e-05,
"loss": 4.2793,
"step": 63488
},
{
"epoch": 0.02,
"learning_rate": 4.8952133273670815e-05,
"loss": 4.279,
"step": 64000
},
{
"epoch": 0.02,
"learning_rate": 4.8943747326160294e-05,
"loss": 4.2854,
"step": 64512
},
{
"epoch": 0.02,
"learning_rate": 4.8935361378649774e-05,
"loss": 4.2605,
"step": 65024
},
{
"epoch": 0.02,
"learning_rate": 4.8926991809942984e-05,
"loss": 4.2738,
"step": 65536
},
{
"epoch": 0.02,
"learning_rate": 4.8918605862432463e-05,
"loss": 4.2752,
"step": 66048
},
{
"epoch": 0.02,
"learning_rate": 4.8910219914921943e-05,
"loss": 4.2633,
"step": 66560
},
{
"epoch": 0.02,
"learning_rate": 4.890185034621515e-05,
"loss": 4.2801,
"step": 67072
},
{
"epoch": 0.02,
"learning_rate": 4.889346439870464e-05,
"loss": 4.2603,
"step": 67584
},
{
"epoch": 0.02,
"learning_rate": 4.888507845119412e-05,
"loss": 4.2722,
"step": 68096
},
{
"epoch": 0.02,
"learning_rate": 4.88766925036836e-05,
"loss": 4.2644,
"step": 68608
},
{
"epoch": 0.02,
"learning_rate": 4.886830655617308e-05,
"loss": 4.2423,
"step": 69120
},
{
"epoch": 0.02,
"learning_rate": 4.885992060866256e-05,
"loss": 4.243,
"step": 69632
},
{
"epoch": 0.02,
"learning_rate": 4.885153466115204e-05,
"loss": 4.2468,
"step": 70144
},
{
"epoch": 0.02,
"learning_rate": 4.884316509244525e-05,
"loss": 4.2545,
"step": 70656
},
{
"epoch": 0.02,
"learning_rate": 4.883477914493473e-05,
"loss": 4.2552,
"step": 71168
},
{
"epoch": 0.02,
"learning_rate": 4.882639319742421e-05,
"loss": 4.2537,
"step": 71680
},
{
"epoch": 0.02,
"learning_rate": 4.881800724991369e-05,
"loss": 4.2437,
"step": 72192
},
{
"epoch": 0.02,
"learning_rate": 4.880962130240316e-05,
"loss": 4.24,
"step": 72704
},
{
"epoch": 0.02,
"learning_rate": 4.880123535489264e-05,
"loss": 4.2326,
"step": 73216
},
{
"epoch": 0.02,
"learning_rate": 4.879284940738212e-05,
"loss": 4.2285,
"step": 73728
},
{
"epoch": 0.02,
"learning_rate": 4.87844634598716e-05,
"loss": 4.2368,
"step": 74240
},
{
"epoch": 0.02,
"learning_rate": 4.877609389116482e-05,
"loss": 4.2482,
"step": 74752
},
{
"epoch": 0.02,
"learning_rate": 4.87677079436543e-05,
"loss": 4.2388,
"step": 75264
},
{
"epoch": 0.02,
"learning_rate": 4.875932199614378e-05,
"loss": 4.221,
"step": 75776
},
{
"epoch": 0.02,
"learning_rate": 4.875093604863326e-05,
"loss": 4.2233,
"step": 76288
},
{
"epoch": 0.03,
"eval_loss": 4.19038724899292,
"eval_runtime": 610.1579,
"eval_samples_per_second": 625.397,
"eval_steps_per_second": 19.544,
"step": 76319
},
{
"epoch": 0.0,
"learning_rate": 4.8742566479926466e-05,
"loss": 4.2252,
"step": 76800
},
{
"epoch": 0.0,
"learning_rate": 4.8734180532415946e-05,
"loss": 4.2202,
"step": 77312
},
{
"epoch": 0.0,
"learning_rate": 4.8725794584905426e-05,
"loss": 4.2162,
"step": 77824
},
{
"epoch": 0.0,
"learning_rate": 4.8717408637394906e-05,
"loss": 4.2165,
"step": 78336
},
{
"epoch": 0.0,
"learning_rate": 4.8709022689884386e-05,
"loss": 4.2069,
"step": 78848
},
{
"epoch": 0.0,
"learning_rate": 4.8700636742373866e-05,
"loss": 4.1919,
"step": 79360
},
{
"epoch": 0.0,
"learning_rate": 4.8692250794863346e-05,
"loss": 4.1979,
"step": 79872
},
{
"epoch": 0.0,
"learning_rate": 4.8683864847352826e-05,
"loss": 4.2106,
"step": 80384
},
{
"epoch": 0.0,
"learning_rate": 4.8675478899842306e-05,
"loss": 4.1975,
"step": 80896
},
{
"epoch": 0.0,
"learning_rate": 4.866710933113552e-05,
"loss": 4.2019,
"step": 81408
},
{
"epoch": 0.0,
"learning_rate": 4.8658723383625e-05,
"loss": 4.2037,
"step": 81920
},
{
"epoch": 0.0,
"learning_rate": 4.865033743611448e-05,
"loss": 4.2043,
"step": 82432
},
{
"epoch": 0.0,
"learning_rate": 4.864195148860396e-05,
"loss": 4.1957,
"step": 82944
},
{
"epoch": 0.0,
"learning_rate": 4.863356554109344e-05,
"loss": 4.1966,
"step": 83456
},
{
"epoch": 0.0,
"learning_rate": 4.862517959358292e-05,
"loss": 4.189,
"step": 83968
},
{
"epoch": 0.0,
"learning_rate": 4.86167936460724e-05,
"loss": 4.175,
"step": 84480
},
{
"epoch": 0.0,
"learning_rate": 4.8608407698561874e-05,
"loss": 4.1831,
"step": 84992
},
{
"epoch": 0.0,
"learning_rate": 4.8600021751051354e-05,
"loss": 4.188,
"step": 85504
},
{
"epoch": 0.0,
"learning_rate": 4.8591635803540834e-05,
"loss": 4.1851,
"step": 86016
},
{
"epoch": 0.0,
"learning_rate": 4.8583249856030314e-05,
"loss": 4.1896,
"step": 86528
},
{
"epoch": 0.0,
"learning_rate": 4.8574863908519794e-05,
"loss": 4.1737,
"step": 87040
},
{
"epoch": 0.0,
"learning_rate": 4.856649433981301e-05,
"loss": 4.1826,
"step": 87552
},
{
"epoch": 0.0,
"learning_rate": 4.8558124771106226e-05,
"loss": 4.1728,
"step": 88064
},
{
"epoch": 0.0,
"learning_rate": 4.85497388235957e-05,
"loss": 4.182,
"step": 88576
},
{
"epoch": 0.0,
"learning_rate": 4.854135287608518e-05,
"loss": 4.1717,
"step": 89088
},
{
"epoch": 0.0,
"learning_rate": 4.853296692857466e-05,
"loss": 4.1693,
"step": 89600
},
{
"epoch": 0.0,
"learning_rate": 4.852458098106414e-05,
"loss": 4.1735,
"step": 90112
},
{
"epoch": 0.0,
"learning_rate": 4.851619503355362e-05,
"loss": 4.1559,
"step": 90624
},
{
"epoch": 0.0,
"learning_rate": 4.850782546484683e-05,
"loss": 4.1716,
"step": 91136
},
{
"epoch": 0.01,
"learning_rate": 4.849943951733631e-05,
"loss": 4.1541,
"step": 91648
},
{
"epoch": 0.01,
"learning_rate": 4.849105356982579e-05,
"loss": 4.1591,
"step": 92160
},
{
"epoch": 0.01,
"learning_rate": 4.848266762231527e-05,
"loss": 4.1601,
"step": 92672
},
{
"epoch": 0.01,
"learning_rate": 4.847428167480475e-05,
"loss": 4.1658,
"step": 93184
},
{
"epoch": 0.01,
"learning_rate": 4.846589572729423e-05,
"loss": 4.1537,
"step": 93696
},
{
"epoch": 0.01,
"learning_rate": 4.845750977978371e-05,
"loss": 4.1486,
"step": 94208
},
{
"epoch": 0.01,
"learning_rate": 4.8449140211076924e-05,
"loss": 4.1617,
"step": 94720
},
{
"epoch": 0.01,
"learning_rate": 4.8440754263566404e-05,
"loss": 4.1508,
"step": 95232
},
{
"epoch": 0.01,
"learning_rate": 4.8432368316055884e-05,
"loss": 4.1596,
"step": 95744
},
{
"epoch": 0.01,
"learning_rate": 4.8423982368545363e-05,
"loss": 4.1428,
"step": 96256
},
{
"epoch": 0.01,
"learning_rate": 4.8415596421034843e-05,
"loss": 4.134,
"step": 96768
},
{
"epoch": 0.01,
"learning_rate": 4.840722685232805e-05,
"loss": 4.1377,
"step": 97280
},
{
"epoch": 0.01,
"learning_rate": 4.839884090481753e-05,
"loss": 4.1325,
"step": 97792
},
{
"epoch": 0.01,
"learning_rate": 4.839045495730701e-05,
"loss": 4.1471,
"step": 98304
},
{
"epoch": 0.01,
"learning_rate": 4.838206900979649e-05,
"loss": 4.1337,
"step": 98816
},
{
"epoch": 0.01,
"learning_rate": 4.837368306228597e-05,
"loss": 4.1398,
"step": 99328
},
{
"epoch": 0.01,
"learning_rate": 4.836531349357918e-05,
"loss": 4.1356,
"step": 99840
},
{
"epoch": 0.01,
"learning_rate": 4.835692754606866e-05,
"loss": 4.1407,
"step": 100352
},
{
"epoch": 0.01,
"learning_rate": 4.834854159855814e-05,
"loss": 4.1386,
"step": 100864
},
{
"epoch": 0.01,
"learning_rate": 4.834015565104763e-05,
"loss": 4.1158,
"step": 101376
},
{
"epoch": 0.01,
"learning_rate": 4.833176970353711e-05,
"loss": 4.1228,
"step": 101888
},
{
"epoch": 0.01,
"learning_rate": 4.832340013483032e-05,
"loss": 4.1172,
"step": 102400
},
{
"epoch": 0.01,
"learning_rate": 4.83150141873198e-05,
"loss": 4.1337,
"step": 102912
},
{
"epoch": 0.01,
"learning_rate": 4.830662823980928e-05,
"loss": 4.1126,
"step": 103424
},
{
"epoch": 0.01,
"learning_rate": 4.829824229229876e-05,
"loss": 4.1327,
"step": 103936
},
{
"epoch": 0.01,
"learning_rate": 4.8289872723591966e-05,
"loss": 4.1079,
"step": 104448
},
{
"epoch": 0.01,
"learning_rate": 4.8281486776081446e-05,
"loss": 4.1093,
"step": 104960
},
{
"epoch": 0.01,
"learning_rate": 4.8273100828570926e-05,
"loss": 4.1178,
"step": 105472
},
{
"epoch": 0.01,
"learning_rate": 4.8264714881060406e-05,
"loss": 4.1109,
"step": 105984
},
{
"epoch": 0.01,
"learning_rate": 4.8256328933549886e-05,
"loss": 4.1103,
"step": 106496
},
{
"epoch": 0.01,
"learning_rate": 4.8247959364843095e-05,
"loss": 4.1066,
"step": 107008
},
{
"epoch": 0.01,
"learning_rate": 4.823957341733258e-05,
"loss": 4.1004,
"step": 107520
},
{
"epoch": 0.01,
"learning_rate": 4.823118746982206e-05,
"loss": 4.1145,
"step": 108032
},
{
"epoch": 0.01,
"learning_rate": 4.8222801522311535e-05,
"loss": 4.1023,
"step": 108544
},
{
"epoch": 0.01,
"learning_rate": 4.8214415574801015e-05,
"loss": 4.1001,
"step": 109056
},
{
"epoch": 0.01,
"learning_rate": 4.820604600609423e-05,
"loss": 4.1009,
"step": 109568
},
{
"epoch": 0.01,
"learning_rate": 4.819766005858371e-05,
"loss": 4.1048,
"step": 110080
},
{
"epoch": 0.01,
"learning_rate": 4.8189274111073184e-05,
"loss": 4.086,
"step": 110592
},
{
"epoch": 0.01,
"learning_rate": 4.8180888163562664e-05,
"loss": 4.1062,
"step": 111104
},
{
"epoch": 0.01,
"learning_rate": 4.8172502216052144e-05,
"loss": 4.0921,
"step": 111616
},
{
"epoch": 0.01,
"learning_rate": 4.816413264734535e-05,
"loss": 4.0949,
"step": 112128
},
{
"epoch": 0.01,
"learning_rate": 4.815574669983483e-05,
"loss": 4.1,
"step": 112640
},
{
"epoch": 0.01,
"learning_rate": 4.814736075232432e-05,
"loss": 4.0925,
"step": 113152
},
{
"epoch": 0.01,
"learning_rate": 4.81389748048138e-05,
"loss": 4.107,
"step": 113664
},
{
"epoch": 0.01,
"learning_rate": 4.813058885730328e-05,
"loss": 4.1115,
"step": 114176
},
{
"epoch": 0.01,
"learning_rate": 4.812221928859649e-05,
"loss": 4.1057,
"step": 114688
},
{
"epoch": 0.01,
"learning_rate": 4.811383334108597e-05,
"loss": 4.0896,
"step": 115200
},
{
"epoch": 0.01,
"learning_rate": 4.810544739357545e-05,
"loss": 4.0812,
"step": 115712
},
{
"epoch": 0.01,
"learning_rate": 4.809706144606493e-05,
"loss": 4.0788,
"step": 116224
},
{
"epoch": 0.01,
"learning_rate": 4.808869187735814e-05,
"loss": 4.0898,
"step": 116736
},
{
"epoch": 0.01,
"learning_rate": 4.808030592984762e-05,
"loss": 4.0992,
"step": 117248
},
{
"epoch": 0.01,
"learning_rate": 4.80719199823371e-05,
"loss": 4.0934,
"step": 117760
},
{
"epoch": 0.01,
"learning_rate": 4.806353403482658e-05,
"loss": 4.0767,
"step": 118272
},
{
"epoch": 0.01,
"learning_rate": 4.805514808731606e-05,
"loss": 4.0712,
"step": 118784
},
{
"epoch": 0.01,
"learning_rate": 4.804677851860927e-05,
"loss": 4.0837,
"step": 119296
},
{
"epoch": 0.01,
"learning_rate": 4.803839257109875e-05,
"loss": 4.0712,
"step": 119808
},
{
"epoch": 0.01,
"learning_rate": 4.803000662358823e-05,
"loss": 4.0787,
"step": 120320
},
{
"epoch": 0.01,
"learning_rate": 4.802162067607771e-05,
"loss": 4.0813,
"step": 120832
},
{
"epoch": 0.01,
"learning_rate": 4.801325110737092e-05,
"loss": 4.0864,
"step": 121344
},
{
"epoch": 0.01,
"learning_rate": 4.80048651598604e-05,
"loss": 4.0758,
"step": 121856
},
{
"epoch": 0.02,
"learning_rate": 4.799647921234988e-05,
"loss": 4.0739,
"step": 122368
},
{
"epoch": 0.02,
"learning_rate": 4.798809326483936e-05,
"loss": 4.0661,
"step": 122880
},
{
"epoch": 0.02,
"learning_rate": 4.797972369613257e-05,
"loss": 4.0764,
"step": 123392
},
{
"epoch": 0.02,
"learning_rate": 4.797133774862205e-05,
"loss": 4.0747,
"step": 123904
},
{
"epoch": 0.02,
"learning_rate": 4.796295180111153e-05,
"loss": 4.0553,
"step": 124416
},
{
"epoch": 0.02,
"learning_rate": 4.795456585360101e-05,
"loss": 4.0645,
"step": 124928
},
{
"epoch": 0.02,
"learning_rate": 4.794619628489423e-05,
"loss": 4.0748,
"step": 125440
},
{
"epoch": 0.02,
"learning_rate": 4.793781033738371e-05,
"loss": 4.0816,
"step": 125952
},
{
"epoch": 0.02,
"learning_rate": 4.792942438987319e-05,
"loss": 4.0709,
"step": 126464
},
{
"epoch": 0.02,
"learning_rate": 4.792103844236267e-05,
"loss": 4.0609,
"step": 126976
},
{
"epoch": 0.02,
"learning_rate": 4.7912668873655876e-05,
"loss": 4.0737,
"step": 127488
},
{
"epoch": 0.02,
"learning_rate": 4.7904282926145356e-05,
"loss": 4.0521,
"step": 128000
},
{
"epoch": 0.02,
"learning_rate": 4.7895896978634836e-05,
"loss": 4.0692,
"step": 128512
},
{
"epoch": 0.02,
"learning_rate": 4.7887511031124316e-05,
"loss": 4.0745,
"step": 129024
},
{
"epoch": 0.02,
"learning_rate": 4.7879141462417525e-05,
"loss": 4.0638,
"step": 129536
},
{
"epoch": 0.02,
"learning_rate": 4.7870755514907005e-05,
"loss": 4.0642,
"step": 130048
},
{
"epoch": 0.02,
"learning_rate": 4.7862369567396485e-05,
"loss": 4.0422,
"step": 130560
},
{
"epoch": 0.02,
"learning_rate": 4.7853983619885965e-05,
"loss": 4.0443,
"step": 131072
},
{
"epoch": 0.02,
"learning_rate": 4.7845597672375445e-05,
"loss": 4.0523,
"step": 131584
},
{
"epoch": 0.02,
"learning_rate": 4.7837211724864925e-05,
"loss": 4.0529,
"step": 132096
},
{
"epoch": 0.02,
"learning_rate": 4.782882577735441e-05,
"loss": 4.0603,
"step": 132608
},
{
"epoch": 0.02,
"learning_rate": 4.782043982984389e-05,
"loss": 4.0472,
"step": 133120
},
{
"epoch": 0.02,
"learning_rate": 4.78120702611371e-05,
"loss": 4.0449,
"step": 133632
},
{
"epoch": 0.02,
"learning_rate": 4.780368431362658e-05,
"loss": 4.0553,
"step": 134144
},
{
"epoch": 0.02,
"learning_rate": 4.779529836611606e-05,
"loss": 4.0625,
"step": 134656
},
{
"epoch": 0.02,
"learning_rate": 4.778691241860554e-05,
"loss": 4.0489,
"step": 135168
},
{
"epoch": 0.02,
"learning_rate": 4.777852647109502e-05,
"loss": 4.0545,
"step": 135680
},
{
"epoch": 0.02,
"learning_rate": 4.777015690238823e-05,
"loss": 4.0463,
"step": 136192
},
{
"epoch": 0.02,
"learning_rate": 4.776177095487771e-05,
"loss": 4.0466,
"step": 136704
},
{
"epoch": 0.02,
"learning_rate": 4.775338500736719e-05,
"loss": 4.053,
"step": 137216
},
{
"epoch": 0.02,
"learning_rate": 4.77450154386604e-05,
"loss": 4.0388,
"step": 137728
},
{
"epoch": 0.02,
"learning_rate": 4.773662949114988e-05,
"loss": 4.0401,
"step": 138240
},
{
"epoch": 0.02,
"learning_rate": 4.772824354363936e-05,
"loss": 4.0383,
"step": 138752
},
{
"epoch": 0.02,
"learning_rate": 4.7719857596128845e-05,
"loss": 4.0374,
"step": 139264
},
{
"epoch": 0.02,
"learning_rate": 4.771147164861832e-05,
"loss": 4.0412,
"step": 139776
},
{
"epoch": 0.02,
"learning_rate": 4.77030857011078e-05,
"loss": 4.045,
"step": 140288
},
{
"epoch": 0.02,
"learning_rate": 4.769469975359728e-05,
"loss": 4.0507,
"step": 140800
},
{
"epoch": 0.02,
"learning_rate": 4.768631380608676e-05,
"loss": 4.0309,
"step": 141312
},
{
"epoch": 0.02,
"learning_rate": 4.767794423737997e-05,
"loss": 4.038,
"step": 141824
},
{
"epoch": 0.02,
"learning_rate": 4.766955828986945e-05,
"loss": 4.0499,
"step": 142336
},
{
"epoch": 0.02,
"learning_rate": 4.766117234235893e-05,
"loss": 4.0353,
"step": 142848
},
{
"epoch": 0.02,
"learning_rate": 4.765278639484841e-05,
"loss": 4.0483,
"step": 143360
},
{
"epoch": 0.02,
"learning_rate": 4.7644416826141616e-05,
"loss": 4.0335,
"step": 143872
},
{
"epoch": 0.02,
"learning_rate": 4.7636030878631096e-05,
"loss": 4.05,
"step": 144384
},
{
"epoch": 0.02,
"learning_rate": 4.762764493112058e-05,
"loss": 4.0397,
"step": 144896
},
{
"epoch": 0.02,
"learning_rate": 4.761925898361006e-05,
"loss": 4.023,
"step": 145408
},
{
"epoch": 0.02,
"learning_rate": 4.761088941490327e-05,
"loss": 4.023,
"step": 145920
},
{
"epoch": 0.02,
"learning_rate": 4.760250346739275e-05,
"loss": 4.0282,
"step": 146432
},
{
"epoch": 0.02,
"learning_rate": 4.759411751988223e-05,
"loss": 4.0403,
"step": 146944
},
{
"epoch": 0.02,
"learning_rate": 4.758573157237171e-05,
"loss": 4.0351,
"step": 147456
},
{
"epoch": 0.02,
"learning_rate": 4.757736200366492e-05,
"loss": 4.038,
"step": 147968
},
{
"epoch": 0.02,
"learning_rate": 4.75689760561544e-05,
"loss": 4.0311,
"step": 148480
},
{
"epoch": 0.02,
"learning_rate": 4.756059010864388e-05,
"loss": 4.0242,
"step": 148992
},
{
"epoch": 0.02,
"learning_rate": 4.755220416113336e-05,
"loss": 4.0243,
"step": 149504
},
{
"epoch": 0.02,
"learning_rate": 4.754383459242657e-05,
"loss": 4.0186,
"step": 150016
},
{
"epoch": 0.02,
"learning_rate": 4.753544864491605e-05,
"loss": 4.0264,
"step": 150528
},
{
"epoch": 0.02,
"learning_rate": 4.7527062697405536e-05,
"loss": 4.042,
"step": 151040
},
{
"epoch": 0.02,
"learning_rate": 4.7518676749895016e-05,
"loss": 4.0257,
"step": 151552
},
{
"epoch": 0.02,
"learning_rate": 4.7510307181188225e-05,
"loss": 4.02,
"step": 152064
},
{
"epoch": 0.02,
"learning_rate": 4.7501921233677705e-05,
"loss": 4.0164,
"step": 152576
},
{
"epoch": 0.03,
"eval_loss": 4.021358489990234,
"eval_runtime": 573.4841,
"eval_samples_per_second": 665.391,
"eval_steps_per_second": 20.794,
"step": 152638
},
{
"epoch": 0.0,
"learning_rate": 4.7493551664970914e-05,
"loss": 4.0235,
"step": 153088
},
{
"epoch": 0.0,
"learning_rate": 4.7485165717460394e-05,
"loss": 4.0212,
"step": 153600
},
{
"epoch": 0.0,
"learning_rate": 4.7476779769949874e-05,
"loss": 4.013,
"step": 154112
},
{
"epoch": 0.0,
"learning_rate": 4.7468393822439354e-05,
"loss": 4.0163,
"step": 154624
},
{
"epoch": 0.0,
"learning_rate": 4.7460007874928834e-05,
"loss": 4.014,
"step": 155136
},
{
"epoch": 0.0,
"learning_rate": 4.7451621927418314e-05,
"loss": 3.9954,
"step": 155648
},
{
"epoch": 0.0,
"learning_rate": 4.7443235979907794e-05,
"loss": 4.0035,
"step": 156160
},
{
"epoch": 0.0,
"learning_rate": 4.7434850032397274e-05,
"loss": 4.0169,
"step": 156672
},
{
"epoch": 0.0,
"learning_rate": 4.7426464084886754e-05,
"loss": 3.9997,
"step": 157184
},
{
"epoch": 0.0,
"learning_rate": 4.741809451617997e-05,
"loss": 4.0077,
"step": 157696
},
{
"epoch": 0.0,
"learning_rate": 4.740970856866945e-05,
"loss": 4.0156,
"step": 158208
},
{
"epoch": 0.0,
"learning_rate": 4.740132262115893e-05,
"loss": 4.013,
"step": 158720
},
{
"epoch": 0.0,
"learning_rate": 4.739295305245214e-05,
"loss": 4.0024,
"step": 159232
},
{
"epoch": 0.0,
"learning_rate": 4.738456710494162e-05,
"loss": 4.0089,
"step": 159744
},
{
"epoch": 0.0,
"learning_rate": 4.73761811574311e-05,
"loss": 4.0003,
"step": 160256
},
{
"epoch": 0.0,
"learning_rate": 4.736779520992058e-05,
"loss": 3.9933,
"step": 160768
},
{
"epoch": 0.0,
"learning_rate": 4.735940926241006e-05,
"loss": 3.9974,
"step": 161280
},
{
"epoch": 0.0,
"learning_rate": 4.735102331489954e-05,
"loss": 4.0036,
"step": 161792
},
{
"epoch": 0.0,
"learning_rate": 4.734263736738902e-05,
"loss": 4.0044,
"step": 162304
},
{
"epoch": 0.0,
"learning_rate": 4.73342514198785e-05,
"loss": 4.0066,
"step": 162816
},
{
"epoch": 0.0,
"learning_rate": 4.732586547236797e-05,
"loss": 3.9932,
"step": 163328
},
{
"epoch": 0.0,
"learning_rate": 4.731747952485746e-05,
"loss": 4.0049,
"step": 163840
},
{
"epoch": 0.0,
"learning_rate": 4.730909357734694e-05,
"loss": 3.9955,
"step": 164352
},
{
"epoch": 0.0,
"learning_rate": 4.7300724008640154e-05,
"loss": 4.0007,
"step": 164864
},
{
"epoch": 0.0,
"learning_rate": 4.729233806112963e-05,
"loss": 3.995,
"step": 165376
},
{
"epoch": 0.0,
"learning_rate": 4.728395211361911e-05,
"loss": 3.9944,
"step": 165888
},
{
"epoch": 0.0,
"learning_rate": 4.727556616610859e-05,
"loss": 4.0008,
"step": 166400
},
{
"epoch": 0.0,
"learning_rate": 4.72671965974018e-05,
"loss": 3.9825,
"step": 166912
},
{
"epoch": 0.0,
"learning_rate": 4.7258810649891277e-05,
"loss": 3.9961,
"step": 167424
},
{
"epoch": 0.01,
"learning_rate": 4.7250424702380757e-05,
"loss": 3.9847,
"step": 167936
},
{
"epoch": 0.01,
"learning_rate": 4.7242038754870237e-05,
"loss": 3.9875,
"step": 168448
},
{
"epoch": 0.01,
"learning_rate": 4.7233669186163446e-05,
"loss": 3.9901,
"step": 168960
},
{
"epoch": 0.01,
"learning_rate": 4.7225283238652926e-05,
"loss": 3.9941,
"step": 169472
},
{
"epoch": 0.01,
"learning_rate": 4.721689729114241e-05,
"loss": 3.9878,
"step": 169984
},
{
"epoch": 0.01,
"learning_rate": 4.720851134363189e-05,
"loss": 3.9793,
"step": 170496
},
{
"epoch": 0.01,
"learning_rate": 4.72001417749251e-05,
"loss": 3.9938,
"step": 171008
},
{
"epoch": 0.01,
"learning_rate": 4.719175582741458e-05,
"loss": 3.9839,
"step": 171520
},
{
"epoch": 0.01,
"learning_rate": 4.718336987990406e-05,
"loss": 3.9973,
"step": 172032
},
{
"epoch": 0.01,
"learning_rate": 4.717498393239354e-05,
"loss": 3.9811,
"step": 172544
},
{
"epoch": 0.01,
"learning_rate": 4.716661436368675e-05,
"loss": 3.9697,
"step": 173056
},
{
"epoch": 0.01,
"learning_rate": 4.715822841617623e-05,
"loss": 3.9731,
"step": 173568
},
{
"epoch": 0.01,
"learning_rate": 4.714984246866571e-05,
"loss": 3.9746,
"step": 174080
},
{
"epoch": 0.01,
"learning_rate": 4.714145652115519e-05,
"loss": 3.9902,
"step": 174592
},
{
"epoch": 0.01,
"learning_rate": 4.71330869524484e-05,
"loss": 3.9687,
"step": 175104
},
{
"epoch": 0.01,
"learning_rate": 4.712470100493788e-05,
"loss": 3.984,
"step": 175616
},
{
"epoch": 0.01,
"learning_rate": 4.7116315057427366e-05,
"loss": 3.9794,
"step": 176128
},
{
"epoch": 0.01,
"learning_rate": 4.7107929109916846e-05,
"loss": 3.9778,
"step": 176640
},
{
"epoch": 0.01,
"learning_rate": 4.7099559541210055e-05,
"loss": 3.9846,
"step": 177152
},
{
"epoch": 0.01,
"learning_rate": 4.7091173593699535e-05,
"loss": 3.9593,
"step": 177664
},
{
"epoch": 0.01,
"learning_rate": 4.7082787646189015e-05,
"loss": 3.9662,
"step": 178176
},
{
"epoch": 0.01,
"learning_rate": 4.7074401698678495e-05,
"loss": 3.9602,
"step": 178688
},
{
"epoch": 0.01,
"learning_rate": 4.7066032129971704e-05,
"loss": 3.9814,
"step": 179200
},
{
"epoch": 0.01,
"learning_rate": 4.7057646182461184e-05,
"loss": 3.9606,
"step": 179712
},
{
"epoch": 0.01,
"learning_rate": 4.7049260234950664e-05,
"loss": 3.9795,
"step": 180224
},
{
"epoch": 0.01,
"learning_rate": 4.7040874287440144e-05,
"loss": 3.9573,
"step": 180736
},
{
"epoch": 0.01,
"learning_rate": 4.7032488339929624e-05,
"loss": 3.9583,
"step": 181248
},
{
"epoch": 0.01,
"learning_rate": 4.7024102392419104e-05,
"loss": 3.9637,
"step": 181760
},
{
"epoch": 0.01,
"learning_rate": 4.7015716444908584e-05,
"loss": 3.9584,
"step": 182272
},
{
"epoch": 0.01,
"learning_rate": 4.70073468762018e-05,
"loss": 3.9656,
"step": 182784
},
{
"epoch": 0.01,
"learning_rate": 4.699896092869128e-05,
"loss": 3.9626,
"step": 183296
},
{
"epoch": 0.01,
"learning_rate": 4.699057498118076e-05,
"loss": 3.9481,
"step": 183808
},
{
"epoch": 0.01,
"learning_rate": 4.698218903367024e-05,
"loss": 3.9645,
"step": 184320
},
{
"epoch": 0.01,
"learning_rate": 4.697381946496345e-05,
"loss": 3.9562,
"step": 184832
},
{
"epoch": 0.01,
"learning_rate": 4.696543351745293e-05,
"loss": 3.9607,
"step": 185344
},
{
"epoch": 0.01,
"learning_rate": 4.695704756994241e-05,
"loss": 3.9531,
"step": 185856
},
{
"epoch": 0.01,
"learning_rate": 4.694866162243189e-05,
"loss": 3.9598,
"step": 186368
},
{
"epoch": 0.01,
"learning_rate": 4.69402920537251e-05,
"loss": 3.9405,
"step": 186880
},
{
"epoch": 0.01,
"learning_rate": 4.693190610621458e-05,
"loss": 3.9621,
"step": 187392
},
{
"epoch": 0.01,
"learning_rate": 4.692352015870406e-05,
"loss": 3.9489,
"step": 187904
},
{
"epoch": 0.01,
"learning_rate": 4.691513421119354e-05,
"loss": 3.9571,
"step": 188416
},
{
"epoch": 0.01,
"learning_rate": 4.690676464248675e-05,
"loss": 3.9555,
"step": 188928
},
{
"epoch": 0.01,
"learning_rate": 4.689837869497623e-05,
"loss": 3.9515,
"step": 189440
},
{
"epoch": 0.01,
"learning_rate": 4.688999274746571e-05,
"loss": 3.965,
"step": 189952
},
{
"epoch": 0.01,
"learning_rate": 4.688160679995519e-05,
"loss": 3.9718,
"step": 190464
},
{
"epoch": 0.01,
"learning_rate": 4.68732372312484e-05,
"loss": 3.9671,
"step": 190976
},
{
"epoch": 0.01,
"learning_rate": 4.686485128373788e-05,
"loss": 3.9559,
"step": 191488
},
{
"epoch": 0.01,
"learning_rate": 4.685646533622736e-05,
"loss": 3.9443,
"step": 192000
},
{
"epoch": 0.01,
"learning_rate": 4.684807938871684e-05,
"loss": 3.9369,
"step": 192512
},
{
"epoch": 0.01,
"learning_rate": 4.683970982001005e-05,
"loss": 3.9566,
"step": 193024
},
{
"epoch": 0.01,
"learning_rate": 4.683132387249953e-05,
"loss": 3.9623,
"step": 193536
},
{
"epoch": 0.01,
"learning_rate": 4.682293792498901e-05,
"loss": 3.9598,
"step": 194048
},
{
"epoch": 0.01,
"learning_rate": 4.681455197747849e-05,
"loss": 3.9423,
"step": 194560
},
{
"epoch": 0.01,
"learning_rate": 4.680618240877171e-05,
"loss": 3.9382,
"step": 195072
},
{
"epoch": 0.01,
"learning_rate": 4.679779646126119e-05,
"loss": 3.9468,
"step": 195584
},
{
"epoch": 0.01,
"learning_rate": 4.678941051375067e-05,
"loss": 3.9368,
"step": 196096
},
{
"epoch": 0.01,
"learning_rate": 4.678102456624015e-05,
"loss": 3.9441,
"step": 196608
},
{
"epoch": 0.01,
"learning_rate": 4.6772654997533356e-05,
"loss": 3.9503,
"step": 197120
},
{
"epoch": 0.01,
"learning_rate": 4.6764269050022836e-05,
"loss": 3.9515,
"step": 197632
},
{
"epoch": 0.01,
"learning_rate": 4.6755883102512316e-05,
"loss": 3.9443,
"step": 198144
},
{
"epoch": 0.02,
"learning_rate": 4.6747513533805525e-05,
"loss": 3.9466,
"step": 198656
},
{
"epoch": 0.02,
"learning_rate": 4.6739127586295005e-05,
"loss": 3.9364,
"step": 199168
},
{
"epoch": 0.02,
"learning_rate": 4.6730741638784485e-05,
"loss": 3.9473,
"step": 199680
},
{
"epoch": 0.02,
"learning_rate": 4.6722355691273965e-05,
"loss": 3.9421,
"step": 200192
},
{
"epoch": 0.02,
"learning_rate": 4.6713969743763445e-05,
"loss": 3.9311,
"step": 200704
},
{
"epoch": 0.02,
"learning_rate": 4.6705583796252925e-05,
"loss": 3.9362,
"step": 201216
},
{
"epoch": 0.02,
"learning_rate": 4.669721422754614e-05,
"loss": 3.9461,
"step": 201728
},
{
"epoch": 0.02,
"learning_rate": 4.668882828003562e-05,
"loss": 3.9543,
"step": 202240
},
{
"epoch": 0.02,
"learning_rate": 4.66804423325251e-05,
"loss": 3.9418,
"step": 202752
},
{
"epoch": 0.02,
"learning_rate": 4.667205638501458e-05,
"loss": 3.9397,
"step": 203264
},
{
"epoch": 0.02,
"learning_rate": 4.6663670437504054e-05,
"loss": 3.9464,
"step": 203776
},
{
"epoch": 0.02,
"learning_rate": 4.6655284489993534e-05,
"loss": 3.9267,
"step": 204288
},
{
"epoch": 0.02,
"learning_rate": 4.6646898542483013e-05,
"loss": 3.9445,
"step": 204800
},
{
"epoch": 0.02,
"learning_rate": 4.6638512594972493e-05,
"loss": 3.9484,
"step": 205312
},
{
"epoch": 0.02,
"learning_rate": 4.663015940506944e-05,
"loss": 3.9366,
"step": 205824
},
{
"epoch": 0.02,
"learning_rate": 4.662177345755892e-05,
"loss": 3.9453,
"step": 206336
},
{
"epoch": 0.02,
"learning_rate": 4.66133875100484e-05,
"loss": 3.9215,
"step": 206848
},
{
"epoch": 0.02,
"learning_rate": 4.660500156253788e-05,
"loss": 3.919,
"step": 207360
},
{
"epoch": 0.02,
"learning_rate": 4.659661561502736e-05,
"loss": 3.9327,
"step": 207872
},
{
"epoch": 0.02,
"learning_rate": 4.658822966751684e-05,
"loss": 3.9315,
"step": 208384
},
{
"epoch": 0.02,
"learning_rate": 4.657984372000632e-05,
"loss": 3.9407,
"step": 208896
},
{
"epoch": 0.02,
"learning_rate": 4.65714577724958e-05,
"loss": 3.9262,
"step": 209408
},
{
"epoch": 0.02,
"learning_rate": 4.656308820378901e-05,
"loss": 3.9234,
"step": 209920
},
{
"epoch": 0.02,
"learning_rate": 4.655470225627849e-05,
"loss": 3.9304,
"step": 210432
},
{
"epoch": 0.02,
"learning_rate": 4.654631630876797e-05,
"loss": 3.943,
"step": 210944
},
{
"epoch": 0.02,
"learning_rate": 4.653793036125745e-05,
"loss": 3.9323,
"step": 211456
},
{
"epoch": 0.02,
"learning_rate": 4.6529560792550656e-05,
"loss": 3.9396,
"step": 211968
},
{
"epoch": 0.02,
"learning_rate": 4.6521174845040136e-05,
"loss": 3.9249,
"step": 212480
},
{
"epoch": 0.02,
"learning_rate": 4.6512788897529616e-05,
"loss": 3.925,
"step": 212992
},
{
"epoch": 0.02,
"learning_rate": 4.6504402950019096e-05,
"loss": 3.9398,
"step": 213504
},
{
"epoch": 0.02,
"learning_rate": 4.649604976011605e-05,
"loss": 3.9217,
"step": 214016
},
{
"epoch": 0.02,
"learning_rate": 4.648766381260553e-05,
"loss": 3.9232,
"step": 214528
},
{
"epoch": 0.02,
"learning_rate": 4.6479277865095e-05,
"loss": 3.9222,
"step": 215040
},
{
"epoch": 0.02,
"learning_rate": 4.647089191758448e-05,
"loss": 3.9193,
"step": 215552
},
{
"epoch": 0.02,
"learning_rate": 4.646250597007396e-05,
"loss": 3.9248,
"step": 216064
},
{
"epoch": 0.02,
"learning_rate": 4.645412002256344e-05,
"loss": 3.9264,
"step": 216576
},
{
"epoch": 0.02,
"learning_rate": 4.644573407505292e-05,
"loss": 3.9381,
"step": 217088
},
{
"epoch": 0.02,
"learning_rate": 4.64373481275424e-05,
"loss": 3.9164,
"step": 217600
},
{
"epoch": 0.02,
"learning_rate": 4.642897855883561e-05,
"loss": 3.9204,
"step": 218112
},
{
"epoch": 0.02,
"learning_rate": 4.642059261132509e-05,
"loss": 3.9392,
"step": 218624
},
{
"epoch": 0.02,
"learning_rate": 4.641220666381457e-05,
"loss": 3.9199,
"step": 219136
},
{
"epoch": 0.02,
"learning_rate": 4.6403837095107786e-05,
"loss": 3.9367,
"step": 219648
},
{
"epoch": 0.02,
"learning_rate": 4.6395451147597266e-05,
"loss": 3.9232,
"step": 220160
},
{
"epoch": 0.02,
"learning_rate": 4.6387065200086746e-05,
"loss": 3.9351,
"step": 220672
},
{
"epoch": 0.02,
"learning_rate": 4.6378679252576226e-05,
"loss": 3.9274,
"step": 221184
},
{
"epoch": 0.02,
"learning_rate": 4.6370293305065705e-05,
"loss": 3.9129,
"step": 221696
},
{
"epoch": 0.02,
"learning_rate": 4.6361907357555185e-05,
"loss": 3.9144,
"step": 222208
},
{
"epoch": 0.02,
"learning_rate": 4.6353521410044665e-05,
"loss": 3.9147,
"step": 222720
},
{
"epoch": 0.02,
"learning_rate": 4.6345135462534145e-05,
"loss": 3.9261,
"step": 223232
},
{
"epoch": 0.02,
"learning_rate": 4.6336765893827354e-05,
"loss": 3.9289,
"step": 223744
},
{
"epoch": 0.02,
"learning_rate": 4.6328379946316834e-05,
"loss": 3.9246,
"step": 224256
},
{
"epoch": 0.02,
"learning_rate": 4.6319993998806314e-05,
"loss": 3.9204,
"step": 224768
},
{
"epoch": 0.02,
"learning_rate": 4.6311608051295794e-05,
"loss": 3.9152,
"step": 225280
},
{
"epoch": 0.02,
"learning_rate": 4.6303238482589003e-05,
"loss": 3.916,
"step": 225792
},
{
"epoch": 0.02,
"learning_rate": 4.629485253507848e-05,
"loss": 3.909,
"step": 226304
},
{
"epoch": 0.02,
"learning_rate": 4.628646658756797e-05,
"loss": 3.9198,
"step": 226816
},
{
"epoch": 0.02,
"learning_rate": 4.627808064005745e-05,
"loss": 3.9292,
"step": 227328
},
{
"epoch": 0.02,
"learning_rate": 4.626971107135066e-05,
"loss": 3.9176,
"step": 227840
},
{
"epoch": 0.02,
"learning_rate": 4.626132512384014e-05,
"loss": 3.9138,
"step": 228352
},
{
"epoch": 0.02,
"learning_rate": 4.625295555513335e-05,
"loss": 3.9108,
"step": 228864
},
{
"epoch": 0.03,
"eval_loss": 3.946960926055908,
"eval_runtime": 561.2521,
"eval_samples_per_second": 679.892,
"eval_steps_per_second": 21.247,
"step": 228957
},
{
"epoch": 0.0,
"learning_rate": 4.624456960762283e-05,
"loss": 3.9148,
"step": 229376
},
{
"epoch": 0.0,
"learning_rate": 4.623618366011231e-05,
"loss": 3.9194,
"step": 229888
},
{
"epoch": 0.0,
"learning_rate": 4.622779771260179e-05,
"loss": 3.9081,
"step": 230400
},
{
"epoch": 0.0,
"learning_rate": 4.621941176509127e-05,
"loss": 3.9091,
"step": 230912
},
{
"epoch": 0.0,
"learning_rate": 4.621102581758075e-05,
"loss": 3.9116,
"step": 231424
},
{
"epoch": 0.0,
"learning_rate": 4.620263987007023e-05,
"loss": 3.8901,
"step": 231936
},
{
"epoch": 0.0,
"learning_rate": 4.619425392255971e-05,
"loss": 3.8972,
"step": 232448
},
{
"epoch": 0.0,
"learning_rate": 4.618586797504919e-05,
"loss": 3.9123,
"step": 232960
},
{
"epoch": 0.0,
"learning_rate": 4.6177498406342404e-05,
"loss": 3.9026,
"step": 233472
},
{
"epoch": 0.0,
"learning_rate": 4.6169112458831884e-05,
"loss": 3.9083,
"step": 233984
},
{
"epoch": 0.0,
"learning_rate": 4.6160726511321364e-05,
"loss": 3.9097,
"step": 234496
},
{
"epoch": 0.0,
"learning_rate": 4.615234056381084e-05,
"loss": 3.9069,
"step": 235008
},
{
"epoch": 0.0,
"learning_rate": 4.614397099510405e-05,
"loss": 3.9001,
"step": 235520
},
{
"epoch": 0.0,
"learning_rate": 4.613558504759353e-05,
"loss": 3.9101,
"step": 236032
},
{
"epoch": 0.0,
"learning_rate": 4.6127199100083006e-05,
"loss": 3.8955,
"step": 236544
},
{
"epoch": 0.0,
"learning_rate": 4.6118813152572486e-05,
"loss": 3.8933,
"step": 237056
},
{
"epoch": 0.0,
"learning_rate": 4.6110427205061966e-05,
"loss": 3.8944,
"step": 237568
},
{
"epoch": 0.0,
"learning_rate": 4.6102041257551446e-05,
"loss": 3.9004,
"step": 238080
},
{
"epoch": 0.0,
"learning_rate": 4.6093655310040926e-05,
"loss": 3.9046,
"step": 238592
},
{
"epoch": 0.0,
"learning_rate": 4.6085269362530406e-05,
"loss": 3.9084,
"step": 239104
},
{
"epoch": 0.0,
"learning_rate": 4.607689979382362e-05,
"loss": 3.8949,
"step": 239616
},
{
"epoch": 0.0,
"learning_rate": 4.60685138463131e-05,
"loss": 3.9076,
"step": 240128
},
{
"epoch": 0.0,
"learning_rate": 4.606012789880258e-05,
"loss": 3.8985,
"step": 240640
},
{
"epoch": 0.0,
"learning_rate": 4.605174195129206e-05,
"loss": 3.8976,
"step": 241152
},
{
"epoch": 0.0,
"learning_rate": 4.604335600378154e-05,
"loss": 3.8984,
"step": 241664
},
{
"epoch": 0.0,
"learning_rate": 4.603497005627102e-05,
"loss": 3.8927,
"step": 242176
},
{
"epoch": 0.0,
"learning_rate": 4.60265841087605e-05,
"loss": 3.9022,
"step": 242688
},
{
"epoch": 0.0,
"learning_rate": 4.601819816124998e-05,
"loss": 3.8863,
"step": 243200
},
{
"epoch": 0.0,
"learning_rate": 4.600982859254319e-05,
"loss": 3.9018,
"step": 243712
},
{
"epoch": 0.01,
"learning_rate": 4.600144264503267e-05,
"loss": 3.8868,
"step": 244224
},
{
"epoch": 0.01,
"learning_rate": 4.599305669752215e-05,
"loss": 3.8888,
"step": 244736
},
{
"epoch": 0.01,
"learning_rate": 4.598467075001163e-05,
"loss": 3.895,
"step": 245248
},
{
"epoch": 0.01,
"learning_rate": 4.5976317560108575e-05,
"loss": 3.9025,
"step": 245760
},
{
"epoch": 0.01,
"learning_rate": 4.5967931612598055e-05,
"loss": 3.8881,
"step": 246272
},
{
"epoch": 0.01,
"learning_rate": 4.5959545665087535e-05,
"loss": 3.8911,
"step": 246784
},
{
"epoch": 0.01,
"learning_rate": 4.5951159717577015e-05,
"loss": 3.8944,
"step": 247296
},
{
"epoch": 0.01,
"learning_rate": 4.5942773770066495e-05,
"loss": 3.8894,
"step": 247808
},
{
"epoch": 0.01,
"learning_rate": 4.5934404201359704e-05,
"loss": 3.9076,
"step": 248320
},
{
"epoch": 0.01,
"learning_rate": 4.5926018253849184e-05,
"loss": 3.8868,
"step": 248832
},
{
"epoch": 0.01,
"learning_rate": 4.5917632306338664e-05,
"loss": 3.8762,
"step": 249344
},
{
"epoch": 0.01,
"learning_rate": 4.5909246358828144e-05,
"loss": 3.8819,
"step": 249856
},
{
"epoch": 0.01,
"learning_rate": 4.590087679012135e-05,
"loss": 3.8762,
"step": 250368
},
{
"epoch": 0.01,
"learning_rate": 4.589249084261083e-05,
"loss": 3.8977,
"step": 250880
},
{
"epoch": 0.01,
"learning_rate": 4.588410489510031e-05,
"loss": 3.8819,
"step": 251392
},
{
"epoch": 0.01,
"learning_rate": 4.58757189475898e-05,
"loss": 3.8898,
"step": 251904
},
{
"epoch": 0.01,
"learning_rate": 4.586733300007928e-05,
"loss": 3.8842,
"step": 252416
},
{
"epoch": 0.01,
"learning_rate": 4.585894705256876e-05,
"loss": 3.888,
"step": 252928
},
{
"epoch": 0.01,
"learning_rate": 4.585056110505824e-05,
"loss": 3.8913,
"step": 253440
},
{
"epoch": 0.01,
"learning_rate": 4.584217515754772e-05,
"loss": 3.8705,
"step": 253952
},
{
"epoch": 0.01,
"learning_rate": 4.583380558884093e-05,
"loss": 3.8703,
"step": 254464
},
{
"epoch": 0.01,
"learning_rate": 4.582541964133041e-05,
"loss": 3.8748,
"step": 254976
},
{
"epoch": 0.01,
"learning_rate": 4.581705007262362e-05,
"loss": 3.8894,
"step": 255488
},
{
"epoch": 0.01,
"learning_rate": 4.58086641251131e-05,
"loss": 3.8717,
"step": 256000
},
{
"epoch": 0.01,
"learning_rate": 4.580027817760258e-05,
"loss": 3.8859,
"step": 256512
},
{
"epoch": 0.01,
"learning_rate": 4.579189223009206e-05,
"loss": 3.8689,
"step": 257024
},
{
"epoch": 0.01,
"learning_rate": 4.5783522661385267e-05,
"loss": 3.8667,
"step": 257536
},
{
"epoch": 0.01,
"learning_rate": 4.577513671387475e-05,
"loss": 3.8775,
"step": 258048
},
{
"epoch": 0.01,
"learning_rate": 4.576675076636423e-05,
"loss": 3.8652,
"step": 258560
},
{
"epoch": 0.01,
"learning_rate": 4.575836481885371e-05,
"loss": 3.8819,
"step": 259072
},
{
"epoch": 0.01,
"learning_rate": 4.574997887134319e-05,
"loss": 3.8763,
"step": 259584
},
{
"epoch": 0.01,
"learning_rate": 4.57416093026364e-05,
"loss": 3.8596,
"step": 260096
},
{
"epoch": 0.01,
"learning_rate": 4.573322335512588e-05,
"loss": 3.8747,
"step": 260608
},
{
"epoch": 0.01,
"learning_rate": 4.572483740761536e-05,
"loss": 3.8676,
"step": 261120
},
{
"epoch": 0.01,
"learning_rate": 4.571645146010484e-05,
"loss": 3.8756,
"step": 261632
},
{
"epoch": 0.01,
"learning_rate": 4.5708065512594315e-05,
"loss": 3.8635,
"step": 262144
},
{
"epoch": 0.01,
"learning_rate": 4.569969594388753e-05,
"loss": 3.8741,
"step": 262656
},
{
"epoch": 0.01,
"learning_rate": 4.569130999637701e-05,
"loss": 3.8572,
"step": 263168
},
{
"epoch": 0.01,
"learning_rate": 4.568292404886649e-05,
"loss": 3.872,
"step": 263680
},
{
"epoch": 0.01,
"learning_rate": 4.567453810135597e-05,
"loss": 3.8588,
"step": 264192
},
{
"epoch": 0.01,
"learning_rate": 4.566615215384545e-05,
"loss": 3.8674,
"step": 264704
},
{
"epoch": 0.01,
"learning_rate": 4.565776620633493e-05,
"loss": 3.8704,
"step": 265216
},
{
"epoch": 0.01,
"learning_rate": 4.564939663762814e-05,
"loss": 3.8704,
"step": 265728
},
{
"epoch": 0.01,
"learning_rate": 4.564101069011762e-05,
"loss": 3.8742,
"step": 266240
},
{
"epoch": 0.01,
"learning_rate": 4.56326247426071e-05,
"loss": 3.8881,
"step": 266752
},
{
"epoch": 0.01,
"learning_rate": 4.562423879509658e-05,
"loss": 3.8813,
"step": 267264
},
{
"epoch": 0.01,
"learning_rate": 4.561586922638979e-05,
"loss": 3.8695,
"step": 267776
},
{
"epoch": 0.01,
"learning_rate": 4.560748327887927e-05,
"loss": 3.8628,
"step": 268288
},
{
"epoch": 0.01,
"learning_rate": 4.559909733136875e-05,
"loss": 3.856,
"step": 268800
},
{
"epoch": 0.01,
"learning_rate": 4.559071138385823e-05,
"loss": 3.87,
"step": 269312
},
{
"epoch": 0.01,
"learning_rate": 4.5582341815151445e-05,
"loss": 3.8789,
"step": 269824
},
{
"epoch": 0.01,
"learning_rate": 4.5573955867640925e-05,
"loss": 3.8758,
"step": 270336
},
{
"epoch": 0.01,
"learning_rate": 4.5565569920130405e-05,
"loss": 3.8578,
"step": 270848
},
{
"epoch": 0.01,
"learning_rate": 4.5557183972619885e-05,
"loss": 3.8556,
"step": 271360
},
{
"epoch": 0.01,
"learning_rate": 4.5548798025109365e-05,
"loss": 3.8688,
"step": 271872
},
{
"epoch": 0.01,
"learning_rate": 4.5540428456402574e-05,
"loss": 3.8484,
"step": 272384
},
{
"epoch": 0.01,
"learning_rate": 4.5532042508892054e-05,
"loss": 3.8637,
"step": 272896
},
{
"epoch": 0.01,
"learning_rate": 4.5523656561381534e-05,
"loss": 3.8648,
"step": 273408
},
{
"epoch": 0.01,
"learning_rate": 4.5515270613871014e-05,
"loss": 3.868,
"step": 273920
},
{
"epoch": 0.01,
"learning_rate": 4.5506884666360494e-05,
"loss": 3.8651,
"step": 274432
},
{
"epoch": 0.02,
"learning_rate": 4.54985150976537e-05,
"loss": 3.8682,
"step": 274944
},
{
"epoch": 0.02,
"learning_rate": 4.549012915014318e-05,
"loss": 3.8534,
"step": 275456
},
{
"epoch": 0.02,
"learning_rate": 4.548174320263266e-05,
"loss": 3.8638,
"step": 275968
},
{
"epoch": 0.02,
"learning_rate": 4.547335725512214e-05,
"loss": 3.8587,
"step": 276480
},
{
"epoch": 0.02,
"learning_rate": 4.546498768641536e-05,
"loss": 3.8545,
"step": 276992
},
{
"epoch": 0.02,
"learning_rate": 4.545660173890484e-05,
"loss": 3.8546,
"step": 277504
},
{
"epoch": 0.02,
"learning_rate": 4.544821579139432e-05,
"loss": 3.8694,
"step": 278016
},
{
"epoch": 0.02,
"learning_rate": 4.54398298438838e-05,
"loss": 3.8694,
"step": 278528
},
{
"epoch": 0.02,
"learning_rate": 4.543144389637328e-05,
"loss": 3.8677,
"step": 279040
},
{
"epoch": 0.02,
"learning_rate": 4.542305794886276e-05,
"loss": 3.8574,
"step": 279552
},
{
"epoch": 0.02,
"learning_rate": 4.541467200135224e-05,
"loss": 3.8662,
"step": 280064
},
{
"epoch": 0.02,
"learning_rate": 4.540628605384172e-05,
"loss": 3.8499,
"step": 280576
},
{
"epoch": 0.02,
"learning_rate": 4.539791648513493e-05,
"loss": 3.8619,
"step": 281088
},
{
"epoch": 0.02,
"learning_rate": 4.5389546916428136e-05,
"loss": 3.8686,
"step": 281600
},
{
"epoch": 0.02,
"learning_rate": 4.5381160968917616e-05,
"loss": 3.8562,
"step": 282112
},
{
"epoch": 0.02,
"learning_rate": 4.5372775021407096e-05,
"loss": 3.869,
"step": 282624
},
{
"epoch": 0.02,
"learning_rate": 4.5364389073896576e-05,
"loss": 3.839,
"step": 283136
},
{
"epoch": 0.02,
"learning_rate": 4.535600312638606e-05,
"loss": 3.8419,
"step": 283648
},
{
"epoch": 0.02,
"learning_rate": 4.534763355767927e-05,
"loss": 3.854,
"step": 284160
},
{
"epoch": 0.02,
"learning_rate": 4.533924761016875e-05,
"loss": 3.8545,
"step": 284672
},
{
"epoch": 0.02,
"learning_rate": 4.533086166265823e-05,
"loss": 3.8618,
"step": 285184
},
{
"epoch": 0.02,
"learning_rate": 4.532247571514771e-05,
"loss": 3.8477,
"step": 285696
},
{
"epoch": 0.02,
"learning_rate": 4.531408976763719e-05,
"loss": 3.8448,
"step": 286208
},
{
"epoch": 0.02,
"learning_rate": 4.53057201989304e-05,
"loss": 3.853,
"step": 286720
},
{
"epoch": 0.02,
"learning_rate": 4.529733425141988e-05,
"loss": 3.8649,
"step": 287232
},
{
"epoch": 0.02,
"learning_rate": 4.528894830390936e-05,
"loss": 3.8569,
"step": 287744
},
{
"epoch": 0.02,
"learning_rate": 4.528056235639884e-05,
"loss": 3.8625,
"step": 288256
},
{
"epoch": 0.02,
"learning_rate": 4.527217640888832e-05,
"loss": 3.8478,
"step": 288768
},
{
"epoch": 0.02,
"learning_rate": 4.526380684018153e-05,
"loss": 3.8469,
"step": 289280
},
{
"epoch": 0.02,
"learning_rate": 4.5255420892671017e-05,
"loss": 3.8651,
"step": 289792
},
{
"epoch": 0.02,
"learning_rate": 4.5247034945160496e-05,
"loss": 3.8467,
"step": 290304
},
{
"epoch": 0.02,
"learning_rate": 4.5238648997649976e-05,
"loss": 3.8435,
"step": 290816
},
{
"epoch": 0.02,
"learning_rate": 4.5230279428943186e-05,
"loss": 3.8484,
"step": 291328
},
{
"epoch": 0.02,
"learning_rate": 4.5221893481432665e-05,
"loss": 3.8407,
"step": 291840
},
{
"epoch": 0.02,
"learning_rate": 4.5213507533922145e-05,
"loss": 3.8528,
"step": 292352
},
{
"epoch": 0.02,
"learning_rate": 4.5205121586411625e-05,
"loss": 3.8502,
"step": 292864
},
{
"epoch": 0.02,
"learning_rate": 4.51967356389011e-05,
"loss": 3.8643,
"step": 293376
},
{
"epoch": 0.02,
"learning_rate": 4.518834969139058e-05,
"loss": 3.8417,
"step": 293888
},
{
"epoch": 0.02,
"learning_rate": 4.5179980122683794e-05,
"loss": 3.8425,
"step": 294400
},
{
"epoch": 0.02,
"learning_rate": 4.5171594175173274e-05,
"loss": 3.8678,
"step": 294912
},
{
"epoch": 0.02,
"learning_rate": 4.5163208227662754e-05,
"loss": 3.8427,
"step": 295424
},
{
"epoch": 0.02,
"learning_rate": 4.5154822280152234e-05,
"loss": 3.8577,
"step": 295936
},
{
"epoch": 0.02,
"learning_rate": 4.5146436332641714e-05,
"loss": 3.8522,
"step": 296448
},
{
"epoch": 0.02,
"learning_rate": 4.5138050385131194e-05,
"loss": 3.8599,
"step": 296960
},
{
"epoch": 0.02,
"learning_rate": 4.51296808164244e-05,
"loss": 3.8515,
"step": 297472
},
{
"epoch": 0.02,
"learning_rate": 4.512129486891388e-05,
"loss": 3.8449,
"step": 297984
},
{
"epoch": 0.02,
"learning_rate": 4.511290892140336e-05,
"loss": 3.838,
"step": 298496
},
{
"epoch": 0.02,
"learning_rate": 4.510452297389284e-05,
"loss": 3.8403,
"step": 299008
},
{
"epoch": 0.02,
"learning_rate": 4.509615340518605e-05,
"loss": 3.8493,
"step": 299520
},
{
"epoch": 0.02,
"learning_rate": 4.508776745767553e-05,
"loss": 3.8571,
"step": 300032
},
{
"epoch": 0.02,
"learning_rate": 4.507938151016501e-05,
"loss": 3.8492,
"step": 300544
},
{
"epoch": 0.02,
"learning_rate": 4.507099556265449e-05,
"loss": 3.8521,
"step": 301056
},
{
"epoch": 0.02,
"learning_rate": 4.506262599394771e-05,
"loss": 3.8406,
"step": 301568
},
{
"epoch": 0.02,
"learning_rate": 4.505424004643719e-05,
"loss": 3.8453,
"step": 302080
},
{
"epoch": 0.02,
"learning_rate": 4.504585409892667e-05,
"loss": 3.8336,
"step": 302592
},
{
"epoch": 0.02,
"learning_rate": 4.503746815141615e-05,
"loss": 3.8493,
"step": 303104
},
{
"epoch": 0.02,
"learning_rate": 4.502908220390563e-05,
"loss": 3.8526,
"step": 303616
},
{
"epoch": 0.02,
"learning_rate": 4.502071263519884e-05,
"loss": 3.8532,
"step": 304128
},
{
"epoch": 0.02,
"learning_rate": 4.501232668768832e-05,
"loss": 3.8393,
"step": 304640
},
{
"epoch": 0.02,
"learning_rate": 4.50039407401778e-05,
"loss": 3.8387,
"step": 305152
},
{
"epoch": 0.03,
"eval_loss": 3.905977487564087,
"eval_runtime": 573.4819,
"eval_samples_per_second": 665.393,
"eval_steps_per_second": 20.794,
"step": 305276
}
],
"logging_steps": 512,
"max_steps": 3052726,
"num_train_epochs": 9223372036854775807,
"save_steps": 10,
"total_flos": 2.122416208464814e+17,
"trial_name": null,
"trial_params": null
}